fix(download): accept newer CivitAI file types for primary file selection

Downloads failed with "No suitable file found in metadata" for models whose only file uses newer CivitAI file types (e.g. 'Enhancement LoRA' for Anima/AIR image-editing LoRAs) because the primary-file allowlist only covered legacy types. - unify the weights-type allowlist as MODEL_WEIGHT_FILE_TYPES (py/utils/constants.py) and apply it across download, recipe and metadata-refresh lookups - mirror CivitAI's getPrimaryFile() semantics: prefer weights-type primary, fall back to weights files, then trust CivitAI's primary flag (excluding non-downloadable artifacts like Config/Archive/Workflow) - mirror the allowlist in the frontend via shared isModelWeightFile() helper - add regression tests for the Enhancement LoRA primary-file download, primary-flag fallback and weights-over-non-weights-primary preference
fix(metadata): keep identity selectors from leaking unselected prompts
2026-08-13 17:23:22 -03:00 · 2026-08-12 21:14:23 +08:00 · 2026-08-12 19:44:43 +08:00 · 2026-08-12 19:18:46 +08:00 · 2026-08-12 19:16:30 +08:00 · 2026-08-12 19:15:03 +08:00
426 changed files with 57052 additions and 6363 deletions
@@ -1,47 +1,145 @@
 ---
 name: lora-manager-e2e
-description: End-to-end testing and validation for LoRa Manager features. Use when performing automated E2E validation of LoRa Manager standalone mode, including starting/restarting the server, using Chrome DevTools MCP to interact with the web UI at http://127.0.0.1:8188/loras, and verifying frontend-to-backend functionality. Covers workflow validation, UI interaction testing, and integration testing between the standalone Python backend and the browser frontend.
+description: End-to-end testing and validation for LoRa Manager features. Use when performing automated E2E validation of LoRa Manager standalone mode in a SANDBOXED, disposable configuration: check the port, start/restart the standalone server on a free port, use Chrome DevTools MCP to interact with the web UI (http://127.0.0.1:{PORT}/loras), and verify frontend-to-backend functionality. Covers workflow validation, UI interaction testing, and integration testing between the standalone Python backend and the browser frontend. Trigger keywords: E2E, standalone, Chrome DevTools MCP, lora-manager-e2e, sandbox.
 ---

 # LoRa Manager E2E Testing

 This skill provides workflows and utilities for end-to-end testing of LoRa Manager using Chrome DevTools MCP.

+## Conventions Used in This Document
+
+- **`{PORT}`**: The server port. The default candidate is `8188`, but **`8188` is commonly occupied by a live ComfyUI process** and MUST NOT be assumed to be free. Always check availability first (see [Port Selection](#port-selection)) and use a free port (e.g. `8199`) for the E2E run. Substitute the actual port for every `{PORT}` in the commands below.
+- **`<repo-root>`**: The repository/worktree root. Always run commands from the repo or worktree root; never assume a specific absolute path (paths such as `/home/<user>/...` differ per machine). The E2E scripts resolve the project root themselves, but fixture/settings paths are relative to `<repo-root>`.
+
+## SANDBOX (MANDATORY)
+
+> **Read this section before running anything.** Every E2E run MUST target a throwaway sandbox, never the real user data. A fresh subagent that skips this section WILL permanently mutate real user recipes.
+
+1. **Portable settings**: create `<repo-root>/settings.json` (gitignored) with `"use_portable_settings": true` plus sandboxed `folder_paths` (lora/checkpoint roots) and `recipes_path`. This keeps the configuration inside the repo instead of the real user config dir (`~/.config/ComfyUI-LoRA-Manager/settings.json`).
+2. **Sandboxed paths**: point `folder_paths` / `recipes_path` / `example_images_path` at disposable dirs — e.g. under `/tmp/opencode/<plan-name>-e2e/` (or worktree-local dirs). NEVER point the E2E at the real library (`~/models/...`), real recipe dir, or real settings.
+3. **Never touch the real config**: the real user config at `~/.config/ComfyUI-LoRA-Manager/settings.json` and the real recipe dir must remain byte-identical before and after the run.
+4. **Record real-data protection proof** before starting and after finishing:
+   ```bash
+   # BEFORE: snapshot real config + recipe library state
+   sha256sum ~/.config/ComfyUI-LoRA-Manager/settings.json > /tmp/opencode/<plan>-e2e/settings.before.sha256
+   ls ~/models/recipes/*.recipe.json 2>/dev/null | wc -l > /tmp/opencode/<plan>-e2e/recipes-count.before.txt
+   find ~/models/recipes -name '*.recipe.json' -newermt "$(date -Iseconds)" | head   # expect empty after run
+   # AFTER: record again, then diff the two snapshots. Any change = the run leaked into real data.
+   ```
+   Also confirm `<repo-root>/git status` stays clean for `settings.json`/`cache/` (both are gitignored).
+
+### Portable Settings Example
+
+```json
+{
+  "use_portable_settings": true,
+  "folder_paths": {
+    "loras": ["/tmp/opencode/<plan>-e2e/models/loras"],
+    "checkpoints": ["/tmp/opencode/<plan>-e2e/models/checkpoints"],
+    "unet": ["/tmp/opencode/<plan>-e2e/models/checkpoints"],
+    "diffusers": []
+  },
+  "recipes_path": "/tmp/opencode/<plan>-e2e/recipes",
+  "example_images_path": "/tmp/opencode/<plan>-e2e/example_images"
+}
+```
+
+The scanner computes and persists model hashes during the library scan, so the sandbox model dirs just need the model files + `.metadata.json` sidecars (see [Fixture + Fresh-State Guidance](#fixture--fresh-state-guidance)).
+
+## Time Budgets & Abort Guidance
+
+A fresh subagent should complete a sandboxed standalone E2E **in well under 30 minutes**. Budget each phase:
+
+| Phase | Expected duration | Abort if |
+| --- | --- | --- |
+| Port check + sandbox setup | < 2 min | — |
+| Server start (detached) + readiness | < 30 s | > 60 s (2x) → stop |
+| Chrome DevTools MCP connect | < 1 min | > 2 min → stop |
+| Per entry-point run (after fixtures ready) | < 5 min | > 10 min (2x) → stop |
+| Fixture reset + cache clear between runs | < 1 min | > 2 min → stop |
+
+**Abort rule**: if a phase exceeds ~2x its budget, OR any single tool call fails/retries 3+ times in a row, **STOP**. Do not loop or retry blindly. Report `BLOCKED` with: the phase, the last observed state (server PID + `ss -tlnp` output, page snapshot, last API response), and the suspected cause. Record the partial state as evidence; a clean BLOCKED report is more valuable than an hour of retries.
+
 ## Prerequisites

- LoRa Manager project cloned and dependencies installed (`pip install -r requirements.txt`)
+- LoRa Manager project cloned and dependencies installed (`pip install -r requirements.txt`) — run everything from `<repo-root>`
 - Chrome browser available for debugging
 - Chrome DevTools MCP connected
+- `ss` (or `lsof`/`netstat`) available for port checks: `ss -tlnp`

-## Quick Start Workflow
+## Port Selection

-### 1. Start LoRa Manager Standalone
-
-```python
-# Use the provided script to start the server
-python .agents/skills/lora-manager-e2e/scripts/start_server.py --port 8188
-```
-
-Or manually:
-```bash
-cd /home/miao/workspace/ComfyUI/custom_nodes/ComfyUI-Lora-Manager
-python standalone.py --port 8188
-```
-
-Wait for server ready message before proceeding.
-
-### 2. Open Chrome Debug Mode
+`8188` is only the *default candidate*. Verify it is actually free before every run:

 ```bash
-# Chrome with remote debugging on port 9222
-google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-lora-manager http://127.0.0.1:8188/loras
+# Is anything listening on 8188?
+ss -tlnp | grep ':8188' || echo "8188 is free"
 ```

-### 3. Connect Chrome DevTools MCP
+- If a process holds `8188` (e.g. a live ComfyUI — pid 6575 on this machine), pick a different free port, e.g. `8199`:
+  ```bash
+  ss -tlnp | grep ':8199' || echo "8199 is free"
+  ```
+- **Never** kill a process you did not start for this E2E. The live ComfyUI is off-limits. Pick a free port instead.
+- Use your chosen port for **all** subsequent commands (server, Chrome launch, browser URLs).

-Ensure the MCP server is connected to Chrome at `http://localhost:9222`.
+## Quick Start Workflow (sandboxed)

-### 4. Navigate and Interact
+### 1. Prepare the sandbox
+
+```bash
+cd <repo-root>                       # ALWAYS run from the repo/worktree root
+mkdir -p /tmp/opencode/<plan>-e2e/models/{loras,checkpoints}
+mkdir -p /tmp/opencode/<plan>-e2e/{recipes,example_images,recipes-before}
+# write <repo-root>/settings.json per the portable-settings example above
+# record real-data protection proof (see SANDBOX section)
+```
+
+### 2. Check port availability
+
+```bash
+ss -tlnp | grep ':{PORT}' || echo "port {PORT} is free"
+```
+
+If `{PORT}` is occupied by an unrelated process, pick a free one and use it everywhere below. When in doubt use `8199`.
+
+### 3. Start LoRa Manager Standalone (detached)
+
+The standalone server **dies with the shell unless launched fully detached** — a plain background `&` from the bash tool is killed when the tool call returns. Launch via the helper script:
+
+```bash
+python .agents/skills/lora-manager-e2e/scripts/start_server.py --port {PORT} --wait --timeout 30 --detach
+```
+
+Or manually (equivalent detached form):
+
+```bash
+setsid nohup python standalone.py --port {PORT} --host 127.0.0.1 < /dev/null \
+  >> /tmp/opencode/<plan>-e2e/server.log 2>&1 &
+echo "started"   # record the printed/pidfile PID for cleanup
+```
+
+Verify it is listening **before** proceeding (readiness poll is not a substitute for this):
+
+```bash
+ss -tlnp | grep ':{PORT}'
+```
+
+Record the server PID for cleanup: the helper script writes it to `/tmp/lora-manager-e2e-server-{PORT}.pid`; a manual `setsid` launch has no pidfile, so capture it explicitly (e.g. from `ss -tlnp`).
+
+### 4. Open Chrome Debug Mode
+
+```bash
+# Chrome with remote debugging on port 9222 (note the {PORT} URL)
+google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-lora-manager http://127.0.0.1:{PORT}/loras
+```
+
+### 5. Connect Chrome DevTools MCP
+
+Ensure the MCP server is connected to Chrome at `http://localhost:9222`. Verify with `list_pages` — if it fails with "browser is already running", see [Chrome DevTools MCP Troubleshooting](#chrome-devtools-mcp-troubleshooting).
+
+### 6. Navigate and Interact

 Use Chrome DevTools MCP tools to:
 - Take snapshots: `take_snapshot`
@@ -56,7 +154,7 @@ Use Chrome DevTools MCP tools to:

 ```python
 # Navigate to LoRA list page
-navigate_page(type="url", url="http://127.0.0.1:8188/loras")
+navigate_page(type="url", url="http://127.0.0.1:{PORT}/loras")

 # Wait for page to load
 wait_for(text="LoRAs", timeout=10000)
@@ -68,9 +166,10 @@ snapshot = take_snapshot()
 ### Pattern: Restart Server for Configuration Changes

 ```python
-# Stop current server (if running)
-# Start with new configuration
-python .agents/skills/lora-manager-e2e/scripts/start_server.py --port 8188 --restart
+# Stop current server (if running), start with new configuration.
+# --restart only kills the E2E server this script started before (via its pidfile);
+# it refuses to blindly kill unrelated processes on the port.
+python .agents/skills/lora-manager-e2e/scripts/start_server.py --port {PORT} --restart --wait --detach

 # Wait and refresh browser
 navigate_page(type="reload", ignoreCache=True)
@@ -130,24 +229,96 @@ click(uid="modal-submit-button")
 wait_for(text="Success", timeout=5000)
 ```

+## Fixture + Fresh-State Guidance
+
+For rematch/repair E2E runs, seed the **sandboxed** `recipes_path` with hand-written fixture recipes. Rules (validated by the task-8 E2E):
+
+1. **Filename constraint**: each file MUST be named `f"{id}.recipe.json"` **and** the in-JSON `id` field MUST equal the filename. Discovery accepts any `*.recipe.json`, but persistence resolves the path via `get_recipe_json_path` and `_save_recipe_persistently` returns `False` on a mismatch → the fixture would be counted as an error.
+   - `recipe-a.recipe.json` → in-JSON `"id": "recipe-a"`
+2. **File format**: mirror an existing recipe JSON — top-level `id`, `file_path`, `title`, `loras`, `fingerprint`, `gen_params`; lora entries per the persistence conventions (`hash`, `file_name`, `modelVersionId`, `isDeleted`, ...).
+3. **Companion image**: each recipe needs an image (e.g. a `.webp` generated with PIL) referenced by `file_path`, used for EXIF verification (`ExifUtils.append_recipe_metadata` writes a `"Recipe metadata: ..."` marker; a freshly generated `.webp` with no marker is the clean "untouched" control).
+4. **autov3 three-state contract**: for L3 (autov3-only, renamed-file) fixtures the local model's `.metadata.json` sidecar MUST have the `autov3` key **ABSENT** (the "unchecked" state), NOT `""` — `""` is the TERMINAL "checked but unavailable" state that L3 deliberately skips. The scanner computes + persists `autov3` from the file header during the normal library scan (`model_scanner.py` `_process_model_file`), so the live L3 match resolves through the local autov3/hash cache; the computed-autov3 branch for unchecked items is covered by the unit suite.
+5. **Fixture design for a rematch run** (mirrors the task-8 E2E):
+   - `recipe-a`: lora entry `isDeleted=True`, `hash` = 12-char autov3 computed from the local model (`calculate_autov3`, `py/utils/file_utils.py`), whose local model file was RENAMED after the recipe was written so `file_name` differs (proves L3 match without filename).
+   - `recipe-b`: parser-convention checkpoint entry (uses `id`, no `modelVersionId`) matching a local checkpoint via L2 — the local checkpoint's `.metadata.json` MUST carry civitai version data with that `id` so `version_index` contains it (L2 cannot match otherwise).
+   - `recipe-c`: healthy recipe (no deleted entries) → must remain untouched.
+
+### Fresh state between entry-point runs
+
+Each entry point (global / per-recipe / selection-bulk) must start from the same deleted state. Between runs:
+
+```bash
+# 1. Reset fixtures to the before-state snapshot (copy back from recipes-before/)
+cp /tmp/opencode/<plan>-e2e/recipes-before/*.recipe.json /tmp/opencode/<plan>-e2e/recipes/
+# 2. Clear the recipe/FTS caches so the stale in-memory/library state is gone
+rm -f <repo-root>/cache/recipe/*.sqlite
+rm -rf <repo-root>/cache/fts/*
+# 3. Restart the server (fresh process, fresh scan)
+python .agents/skills/lora-manager-e2e/scripts/start_server.py --port {PORT} --restart --wait --timeout 30 --detach
+# 4. Re-verify server listening + reload the browser page
+```
+
+## Server Lifecycle
+
+- **Detached launch is mandatory**: the standalone server dies with the shell unless launched via `setsid` (or the helper script's `--detach`). Use `setsid nohup python standalone.py --port {PORT} --host 127.0.0.1 ... < /dev/null &`.
+- **Verify with `ss -tlnp`** after every (re)start; do not proceed on a blind "server starting" message.
+- **Never kill pre-existing processes** — only kill the E2E server PID you started (`start_server.py --restart` kills only PIDs it manages via its pidfile). The live ComfyUI or a stale QA Chrome must never be killed as part of cleanup unless explicitly identified as such (see Chrome troubleshooting).
+- **Record your PID for cleanup**: note the PID printed/pidfile, and stop exactly that PID at the end (`kill <PID>`, then confirm with `ss -tlnp` that `{PORT}` is released).
+
+## Chrome DevTools MCP Troubleshooting
+
+### Stale profile lock ("browser is already running" / `list_pages` fails)
+
+A Chrome profile can be held by a stale Chrome from a prior MCP session, which makes `list_pages` fail with "browser is already running":
+
+1. Identify the stale Chrome — it owns the profile dir in `--user-data-dir` (e.g. `~/.config/chrome-dev-profile`). Find its process:
+   ```bash
+   ps -ef | grep -i '[c]hrome.*user-data-dir'
+   ```
+2. Confirm it is a QA Chrome from a completed task (its parent is an old MCP/browser process, it is NOT the live ComfyUI server, and it is NOT your current MCP instance).
+3. Kill ONLY that stale Chrome:
+   ```bash
+   kill <stale-chrome-pid>
+   ```
+   Never kill the live server or unrelated processes.
+4. Retry `list_pages`. The current MCP will spawn a fresh browser.
+
+### Screenshot-write restrictions
+
+The chrome-devtools MCP may refuse to write into paths outside its configured workspace roots (e.g. the worktree `.omo/evidence/...` canonicalizing to an unmapped path). Workaround:
+
+```bash
+# 1. Save the screenshot to /tmp via the MCP
+#    take_screenshot(filePath="/tmp/<plan>-e2e/recipe-b-after.png", format="png")
+# 2. Copy it into the evidence dir from the shell
+mkdir -p <repo-root>/.omo/evidence/screenshots
+cp /tmp/<plan>-e2e/recipe-b-after.png <repo-root>/.omo/evidence/screenshots/
+```
+
+## Cancellation Testing (KNOWN GAP)
+
+Testing the rematch-cancel path E2E requires a run long enough to cancel mid-flight. A tiny 3-recipe fixture set completes in **seconds** — too fast to reliably cancel. The cancel path is currently **unit-covered only** (`rematch_all_recipes` cancellation tests); do not block an E2E run on cancel-path verification. If you must attempt it, you would need an artificially large/deferred fixture set to create a cancellable window — treat this as a research task, not part of the standard E2E.
+
 ## Available Scripts

 ### scripts/start_server.py

-Starts or restarts the LoRa Manager standalone server.
+Starts or restarts the LoRa Manager standalone server for E2E testing.

 ```bash
-python scripts/start_server.py [--port PORT] [--restart] [--wait]
+python scripts/start_server.py [--port PORT] [--restart] [--wait] [--timeout SECONDS] [--detach]
 ```

 Options:
- `--port`: Server port (default: 8188)
- `--restart`: Kill existing server before starting
- `--wait`: Wait for server to be ready before exiting
+- `--port`: Server port (default: 8188). The script exits early with a clear message if the port is already in use by an unrelated process.
+- `--restart`: Kill the E2E server this script previously managed (tracked via `/tmp/lora-manager-e2e-server-{PORT}.pid`) before starting. If unrelated processes still hold the port after that, the script reports them and aborts instead of killing them.
+- `--wait`: Wait for the server to be ready before exiting.
+- `--timeout`: Readiness wait timeout in seconds (default: 30).
+- `--detach`: Launch the server fully detached (`setsid`-style, survives shell death — REQUIRED for E2E). Default off: a normal background process that dies with the shell.

 ### scripts/wait_for_server.py

-Polls server until ready or timeout.
+Polls the server until ready or timeout.

 ```bash
 python scripts/wait_for_server.py [--port PORT] [--timeout SECONDS]
@@ -196,6 +367,7 @@ results = performance_stop_trace()
 ## Cleanup

 Always ensure proper cleanup after tests:
-1. Stop the standalone server
-2. Close browser pages (keep at least one open)
-3. Clear temporary data if needed
+1. Stop the standalone server: `kill <recorded-pid>` (only the PID you started), then confirm `ss -tlnp | grep ':{PORT}'` is empty.
+2. Close browser pages (keep at least one open).
+3. Remove the sandbox: `rm -rf /tmp/opencode/<plan>-e2e` and `<repo-root>/settings.json` + `<repo-root>/cache` (both gitignored).
+4. Re-run the real-data protection check from the SANDBOX section and record the result in your evidence.
@@ -2,11 +2,13 @@

 Quick reference for common MCP commands used in LoRa Manager E2E testing.

+> **Port convention**: `{PORT}` is the port chosen for the E2E run (default candidate `8188`, but only if actually free — see the SKILL.md Port Selection section; use e.g. `8199` when `8188` is occupied by a live ComfyUI). Always run against the **sandboxed** standalone server, never a live instance.
+
 ## Navigation

 ```python
 # Navigate to LoRA list page
-navigate_page(type="url", url="http://127.0.0.1:8188/loras")
+navigate_page(type="url", url="http://127.0.0.1:{PORT}/loras")

 # Reload page with cache clear
 navigate_page(type="reload", ignoreCache=True)
@@ -179,7 +181,7 @@ pages = list_pages()
 select_page(pageId=0, bringToFront=True)

 # Create new page
-new_page(url="http://127.0.0.1:8188/loras")
+new_page(url="http://127.0.0.1:{PORT}/loras")

 # Close page (keep at least one open!)
 close_page(pageId=1)
@@ -261,7 +263,7 @@ drag(from_uid="draggable-item", to_uid="drop-zone")
 ### Verify LoRA Cards Loaded

 ```python
-navigate_page(type="url", url="http://127.0.0.1:8188/loras")
+navigate_page(type="url", url="http://127.0.0.1:{PORT}/loras")
 wait_for(text="LoRAs", timeout=10000)

 # Check if cards loaded
@@ -322,3 +324,37 @@ navigate_page(type="reload")
 errors = list_console_messages(types=["error"])
 assert len(errors) == 0, f"Console errors: {errors}"
 ```
+
+## Troubleshooting
+
+### Stale profile lock ("browser is already running" / `list_pages` fails)
+
+A Chrome profile held by a stale Chrome from a prior MCP session makes `list_pages`
+fail with "browser is already running". Fix:
+
+1. Find the stale Chrome that owns the profile dir (e.g. `~/.config/chrome-dev-profile`):
+   ```bash
+   ps -ef | grep -i '[c]hrome.*user-data-dir'
+   ```
+2. Confirm it is a QA Chrome from a completed task (NOT the live ComfyUI server, NOT
+   your current MCP instance).
+3. Kill ONLY that stale Chrome (`kill <stale-pid>`), then retry `list_pages`.
+
+### Screenshot-write restrictions
+
+The MCP may refuse to write into paths outside its configured workspace roots
+(e.g. `.omo/evidence/screenshots/` under a worktree that canonicalizes to an unmapped
+path). Save the screenshot to `/tmp` via the MCP, then copy it into the evidence dir:
+
+```bash
+# MCP:  take_screenshot(filePath="/tmp/<plan>-e2e/recipe-b-after.png", format="png")
+# Shell:
+mkdir -p <repo-root>/.omo/evidence/screenshots
+cp /tmp/<plan>-e2e/recipe-b-after.png <repo-root>/.omo/evidence/screenshots/
+```
+
+### Time budgets & abort rule
+
+See SKILL.md "Time Budgets & Abort Guidance": if a phase exceeds ~2x its budget or a
+tool call retries 3+ times in a row, STOP and report BLOCKED with the last observed
+state (server PID + `ss -tlnp`, page snapshot, last API response). Do not loop.
@@ -2,6 +2,14 @@

 This document provides detailed test scenarios for end-to-end validation of LoRa Manager features.

+> **Run preconditions (from SKILL.md)**: every run uses the **sandboxed** standalone
+> server on a free port `{PORT}` (default candidate `8188`, only if actually free — pick
+> e.g. `8199` when `8188` is occupied by a live ComfyUI). Fixtures live in the sandboxed
+> `recipes_path` as `f"{id}.recipe.json"` files with matching in-JSON `id`; the real user
+> config and real library are never touched (record protection proof before/after).
+> Abort if a phase exceeds ~2x its budget or a tool call retries 3+ times (SKILL.md
+> "Time Budgets & Abort Guidance").
+
 ## Table of Contents

 1. [LoRA List Page](#lora-list-page)
@@ -19,7 +27,7 @@ This document provides detailed test scenarios for end-to-end validation of LoRa
 **Objective**: Verify the LoRA list page loads correctly and displays models.

 **Steps**:
-1. Navigate to `http://127.0.0.1:8188/loras`
+1. Navigate to `http://127.0.0.1:{PORT}/loras`
 2. Wait for page title "LoRAs" to appear
 3. Take snapshot to verify:
   - Header with "LoRAs" title is visible
@@ -134,7 +142,7 @@ evaluate_script(function="""
 **Objective**: Verify recipes page loads and displays recipes.

 **Steps**:
-1. Navigate to `http://127.0.0.1:8188/recipes`
+1. Navigate to `http://127.0.0.1:{PORT}/recipes`
 2. Wait for "Recipes" title
 3. Take snapshot

@@ -176,7 +184,7 @@ evaluate_script(function="""
 **Objective**: Verify settings page displays correctly.

 **Steps**:
-1. Navigate to `http://127.0.0.1:8188/settings`
+1. Navigate to `http://127.0.0.1:{PORT}/settings`
 2. Wait for "Settings" title
 3. Take snapshot

@@ -190,7 +198,7 @@ evaluate_script(function="""
 1. Navigate to settings page
 2. Change a setting (e.g., default view mode)
 3. Save settings
-4. Restart server: `python scripts/start_server.py --restart --wait`
+4. Restart server: `python scripts/start_server.py --port {PORT} --restart --wait --timeout 30 --detach`
 5. Refresh browser page
 6. Navigate to settings

@@ -8,186 +8,208 @@ This script shows how to:
 3. Verify functionality end-to-end

 Note: This is a template. Actual execution requires Chrome DevTools MCP.
+
+Port: pick a FREE port for the run — 8188 is commonly occupied by a live
+ComfyUI (see the skill's Port Selection section). Set PORT below to e.g. 8199
+when 8188 is taken. Always run against a SANDBOXED standalone server.
 """

 import subprocess
 import sys
-import time
+
+# Choose the E2E port. 8188 is only the default candidate; use 8199 (or any
+# free port checked with `ss -tlnp`) when 8188 is occupied by a live ComfyUI.
+PORT = "8188"


 def run_test():
    """Run example E2E test flow."""
-    
+
    print("=" * 60)
    print("LoRa Manager E2E Test Example")
    print("=" * 60)
-    
-    # Step 1: Start server
+
+    # Step 1: Start server (detached so it survives the shell)
    print("\n[1/5] Starting LoRa Manager standalone server...")
    result = subprocess.run(
-        [sys.executable, "start_server.py", "--port", "8188", "--wait", "--timeout", "30"],
+        [sys.executable, "start_server.py", "--port", PORT, "--wait", "--timeout", "30", "--detach"],
        capture_output=True,
-        text=True
+        text=True,
    )
    if result.returncode != 0:
        print(f"Failed to start server: {result.stderr}")
        return 1
    print("Server ready!")
-    
+
    # Step 2: Open Chrome (manual step - show command)
    print("\n[2/5] Open Chrome with debug mode:")
-    print("google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-lora-manager http://127.0.0.1:8188/loras")
+    print(
+        f"google-chrome --remote-debugging-port=9222 "
+        f"--user-data-dir=/tmp/chrome-lora-manager http://127.0.0.1:{PORT}/loras"
+    )
    print("(In actual test, this would be automated via MCP)")
-    
+
    # Step 3: Navigate and verify page load
    print("\n[3/5] Page Load Verification:")
-    print("""
+    print(
+        f"""
    MCP Commands to execute:
-    1. navigate_page(type="url", url="http://127.0.0.1:8188/loras")
+    1. navigate_page(type="url", url="http://127.0.0.1:{PORT}/loras")
    2. wait_for(text="LoRAs", timeout=10000)
    3. snapshot = take_snapshot()
-    """)
-    
+    """
+    )
+
    # Step 4: Test search functionality
    print("\n[4/5] Search Functionality Test:")
-    print("""
+    print(
+        """
    MCP Commands to execute:
    1. fill(uid="search-input", value="test")
    2. press_key(key="Enter")
    3. wait_for(text="Results", timeout=5000)
-    4. result = evaluate_script(function="""
+    4. result = evaluate_script(function=`
        () => {
            const cards = document.querySelectorAll('.lora-card');
            return { count: cards.length };
        }
-        """)
-    """)
-    
+        `)
+    """
+    )
+
    # Step 5: Verify API
    print("\n[5/5] API Verification:")
-    print("""
+    print(
+        """
    MCP Commands to execute:
-    1. api_result = evaluate_script(function="""
+    1. api_result = evaluate_script(function=`
        async () => {
            const response = await fetch('/loras/api/list');
            const data = await response.json();
            return { count: data.length, status: response.status };
        }
-        """)
+        `)
    2. Verify api_result['status'] == 200
-    """)
-    
+    """
+    )
+
    print("\n" + "=" * 60)
    print("Test flow completed!")
    print("=" * 60)
-    
+
    return 0


 def example_restart_flow():
    """Example: Testing configuration change that requires restart."""
-    
+
    print("\n" + "=" * 60)
    print("Example: Server Restart Flow")
    print("=" * 60)
-    
-    print("""
+
+    print(
+        f"""
    Scenario: Change setting and verify after restart
-    
+
    Steps:
    1. Navigate to settings page
-       - navigate_page(type="url", url="http://127.0.0.1:8188/settings")
-    
+       - navigate_page(type="url", url="http://127.0.0.1:{PORT}/settings")
+
    2. Change a setting (e.g., theme)
       - fill(uid="theme-select", value="dark")
       - click(uid="save-settings-button")
-    
+
    3. Restart server
-       - subprocess.run([python, "start_server.py", "--restart", "--wait"])
-    
+       - subprocess.run([python, "start_server.py", "--port", "{PORT}", "--restart", "--wait", "--detach"])
+
    4. Refresh browser
       - navigate_page(type="reload", ignoreCache=True)
       - wait_for(text="LoRAs", timeout=15000)
-    
+
    5. Verify setting persisted
-       - navigate_page(type="url", url="http://127.0.0.1:8188/settings")
+       - navigate_page(type="url", url="http://127.0.0.1:{PORT}/settings")
       - theme = evaluate_script(function="() => document.querySelector('#theme-select').value")
       - assert theme == "dark"
-    """)
+    """
+    )


 def example_modal_interaction():
    """Example: Testing modal dialog interaction."""
-    
+
    print("\n" + "=" * 60)
    print("Example: Modal Dialog Interaction")
    print("=" * 60)
-    
-    print("""
+
+    print(
+        """
    Scenario: Add new LoRA via modal
-    
+
    Steps:
    1. Open modal
       - click(uid="add-lora-button")
       - wait_for(text="Add LoRA", timeout=3000)
-    
+
    2. Fill form
       - fill_form(elements=[
           {"uid": "lora-name", "value": "Test Character"},
           {"uid": "lora-path", "value": "/models/test.safetensors"},
       ])
-    
+
    3. Submit
       - click(uid="modal-submit-button")
-    
+
    4. Verify success
       - wait_for(text="Successfully added", timeout=5000)
       - snapshot = take_snapshot()
-    """)
+    """
+    )


 def example_network_monitoring():
    """Example: Network request monitoring."""
-    
+
    print("\n" + "=" * 60)
    print("Example: Network Request Monitoring")
    print("=" * 60)
-    
-    print("""
+
+    print(
+        f"""
    Scenario: Verify API calls during user interaction
-    
+
    Steps:
    1. Clear network log (implicit on navigation)
-       - navigate_page(type="url", url="http://127.0.0.1:8188/loras")
-    
+       - navigate_page(type="url", url="http://127.0.0.1:{PORT}/loras")
+
    2. Perform action that triggers API call
       - fill(uid="search-input", value="character")
       - press_key(key="Enter")
-    
+
    3. List network requests
       - requests = list_network_requests(resourceTypes=["xhr", "fetch"])
-    
+
    4. Find search API call
       - search_requests = [r for r in requests if "/api/search" in r.get("url", "")]
       - assert len(search_requests) > 0, "Search API was not called"
-    
+
    5. Get request details
       - if search_requests:
           details = get_network_request(reqid=search_requests[0]["reqid"])
           - Verify request method, response status, etc.
-    """)
+    """
+    )


 if __name__ == "__main__":
    print("LoRa Manager E2E Test Examples\n")
    print("This script demonstrates E2E testing patterns.\n")
    print("Note: Actual execution requires Chrome DevTools MCP connection.\n")
-    
+
    run_test()
    example_restart_flow()
    example_modal_interaction()
    example_network_monitoring()
-    
+
    print("\n" + "=" * 60)
    print("All examples shown!")
    print("=" * 60)
@@ -1,15 +1,78 @@
 #!/usr/bin/env python3
 """
 Start or restart LoRa Manager standalone server for E2E testing.
+
+Backward-compatible CLI: --port, --restart, --wait, --timeout all work as before.
+New options: --detach (setsid-style fully detached launch, survives shell death).
+
+Safety rules implemented here:
+- Never kill processes the script did not start. The script tracks the PIDs it
+  manages in a pidfile (/tmp/lora-manager-e2e-server-{PORT}.pid).
+- If the port is held by an unrelated process (e.g. a live ComfyUI) the script
+  reports the conflict and exits early instead of killing it.
+- --restart only kills managed PIDs; if unrelated processes still hold the port
+  afterwards, the script reports them and aborts.
 """

+from __future__ import annotations
+
 import argparse
+import os
+import signal
+import socket
 import subprocess
 import sys
 import time
-import socket
-import signal
-import os
+
+PIDFILE_PREFIX = "/tmp/lora-manager-e2e-server"
+
+
+def pidfile_path(port: int) -> str:
+    """Path of the pidfile that records PIDs this script started for a port."""
+    return f"{PIDFILE_PREFIX}-{port}.pid"
+
+
+def read_managed_pids(port: int) -> list[int]:
+    """Read PIDs this script previously managed for the port (may be stale)."""
+    path = pidfile_path(port)
+    if not os.path.exists(path):
+        return []
+    try:
+        with open(path, "r", encoding="utf-8") as fh:
+            return [int(line.strip()) for line in fh if line.strip().isdigit()]
+    except (OSError, ValueError):
+        return []
+
+
+def write_managed_pids(port: int, pids: list[int]) -> None:
+    """Record PIDs this script manages for the port."""
+    try:
+        with open(pidfile_path(port), "w", encoding="utf-8") as fh:
+            for pid in pids:
+                fh.write(f"{pid}\n")
+    except OSError as exc:
+        print(f"Warning: could not write pidfile for port {port}: {exc}")
+
+
+def clear_managed_pids(port: int) -> None:
+    """Remove the pidfile for the port (no longer managed)."""
+    path = pidfile_path(port)
+    try:
+        if os.path.exists(path):
+            os.remove(path)
+    except OSError as exc:
+        print(f"Warning: could not remove pidfile {path}: {exc}")
+
+
+def process_alive(pid: int) -> bool:
+    """Return True if a process with the given pid exists."""
+    try:
+        os.kill(pid, 0)
+        return True
+    except ProcessLookupError:
+        return False
+    except PermissionError:
+        return True  # exists but owned by someone else


 def find_server_process(port: int) -> list[int]:
@@ -19,7 +82,7 @@ def find_server_process(port: int) -> list[int]:
            ["lsof", "-ti", f":{port}"],
            capture_output=True,
            text=True,
-            check=False
+            check=False,
        )
        if result.returncode == 0 and result.stdout.strip():
            return [int(pid) for pid in result.stdout.strip().split("\n") if pid]
@@ -30,7 +93,7 @@ def find_server_process(port: int) -> list[int]:
                ["netstat", "-tlnp"],
                capture_output=True,
                text=True,
-                check=False
+                check=False,
            )
            pids = []
            for line in result.stdout.split("\n"):
@@ -49,30 +112,48 @@ def find_server_process(port: int) -> list[int]:
    return []


-def kill_server(port: int) -> None:
-    """Kill processes using the specified port."""
-    pids = find_server_process(port)
+def describe_processes(pids: list[int]) -> str:
+    """Human-readable description of a pid list (pid + command line)."""
+    descriptions = []
    for pid in pids:
+        cmdline = ""
+        try:
+            with open(f"/proc/{pid}/cmdline", "rb") as fh:
+                raw = fh.read().replace(b"\x00", b" ").decode("utf-8", "replace")
+                cmdline = raw.strip()
+        except OSError:
+            pass
+        descriptions.append(f"pid {pid}{' (' + cmdline + ')' if cmdline else ''}")
+    return ", ".join(descriptions) if descriptions else "none"
+
+
+def kill_pids(pids: list[int], what: str) -> None:
+    """Send SIGTERM (then SIGKILL) to the given PIDs, only after reporting."""
+    for pid in pids:
+        print(f"Sent SIGTERM to {what} pid {pid}")
        try:
            os.kill(pid, signal.SIGTERM)
-            print(f"Sent SIGTERM to process {pid}")
        except ProcessLookupError:
            pass
-    
+
    # Wait for processes to terminate
-    time.sleep(1)
-    
+    deadline = time.time() + 5
+    while time.time() < deadline:
+        if not any(process_alive(pid) for pid in pids):
+            break
+        time.sleep(0.2)
+
    # Force kill if still running
-    pids = find_server_process(port)
    for pid in pids:
-        try:
-            os.kill(pid, signal.SIGKILL)
-            print(f"Sent SIGKILL to process {pid}")
-        except ProcessLookupError:
-            pass
+        if process_alive(pid):
+            try:
+                os.kill(pid, signal.SIGKILL)
+                print(f"Sent SIGKILL to {what} pid {pid}")
+            except ProcessLookupError:
+                pass


-def is_server_ready(port: int, timeout: float = 0.5) -> bool:
+def is_server_ready(port: int, timeout: float = 2.0) -> bool:
    """Check if server is accepting connections."""
    try:
        with socket.create_connection(("127.0.0.1", port), timeout=timeout):
@@ -84,9 +165,15 @@ def is_server_ready(port: int, timeout: float = 0.5) -> bool:
 def wait_for_server(port: int, timeout: int = 30) -> bool:
    """Wait for server to become ready."""
    start = time.time()
+    last_report = 0.0
    while time.time() - start < timeout:
        if is_server_ready(port):
            return True
+        # Report progress every ~5s so a slow boot is visible, not silent.
+        elapsed = time.time() - start
+        if elapsed - last_report >= 5:
+            print(f"  ...still waiting ({int(elapsed)}s/{timeout}s)")
+            last_report = elapsed
        time.sleep(0.5)
    return False

@@ -99,68 +186,148 @@ def main() -> int:
        "--port",
        type=int,
        default=8188,
-        help="Server port (default: 8188)"
+        help="Server port (default: 8188)",
    )
    parser.add_argument(
        "--restart",
        action="store_true",
-        help="Kill existing server before starting"
+        help="Kill the E2E server previously managed by this script for the port "
+        "(tracked via pidfile) before starting; refuse to kill unrelated processes",
    )
    parser.add_argument(
        "--wait",
        action="store_true",
-        help="Wait for server to be ready before exiting"
+        help="Wait for server to be ready before exiting",
    )
    parser.add_argument(
        "--timeout",
        type=int,
        default=30,
-        help="Timeout for waiting (default: 30)"
+        help="Timeout for waiting (default: 30)",
    )
-    
+    parser.add_argument(
+        "--detach",
+        action="store_true",
+        help="Launch the server fully detached (setsid-style) so it survives shell "
+        "death. REQUIRED for E2E: a plain background process dies with the shell",
+    )
+
    args = parser.parse_args()
-    
+
    # Get project root (parent of .agents directory)
    script_dir = os.path.dirname(os.path.abspath(__file__))
    skill_dir = os.path.dirname(script_dir)
    project_root = os.path.dirname(os.path.dirname(os.path.dirname(skill_dir)))
-    
-    # Restart if requested
+
+    managed_pids = read_managed_pids(args.port)
+
+    # Restart if requested: kill ONLY managed PIDs.
    if args.restart:
-        print(f"Killing existing server on port {args.port}...")
-        kill_server(args.port)
+        alive_managed = [pid for pid in managed_pids if process_alive(pid)]
+        if alive_managed:
+            print(
+                f"Killing E2E server previously started by this script on port "
+                f"{args.port} ({describe_processes(alive_managed)})..."
+            )
+            kill_pids(alive_managed, "managed E2E server")
+        else:
+            print(
+                f"No live managed E2E server for port {args.port} "
+                f"(pidfile: {pidfile_path(args.port)})"
+            )
        time.sleep(1)
-    
-    # Check if already running
-    if is_server_ready(args.port):
-        print(f"Server already running on port {args.port}")
-        return 0
-    
+        # Refuse to kill anything the script did not manage.
+        remaining = find_server_process(args.port)
+        if remaining:
+            print(
+                f"ERROR: port {args.port} is still held by process(es) this script "
+                f"did not start: {describe_processes(remaining)}."
+            )
+            print(
+                "These may be unrelated (e.g. a live ComfyUI). The script will NOT "
+                "kill them. Pick a different --port, or stop them manually if you "
+                "are certain they are stale E2E servers."
+            )
+            return 2
+        clear_managed_pids(args.port)
+
+    # Port conflict check before starting: never blind-kill.
+    port_pids = find_server_process(args.port)
+    if port_pids:
+        alive_managed = [pid for pid in port_pids if pid in managed_pids]
+        unmanaged = [pid for pid in port_pids if pid not in managed_pids]
+        if alive_managed and not unmanaged:
+            print(
+                f"Server already running on port {args.port} "
+                f"({describe_processes(alive_managed)}, started by this script). "
+                f"Use --restart to recycle it."
+            )
+            return 0
+        print(
+            f"ERROR: port {args.port} is already in use by process(es): "
+            f"{describe_processes(port_pids)}."
+        )
+        print(
+            "This is likely an unrelated process (e.g. a live ComfyUI holding 8188). "
+            "The script will NOT kill it. Pick a free port with --port, e.g. 8199."
+        )
+        return 2
+
    # Start server
    print(f"Starting LoRa Manager standalone server on port {args.port}...")
-    cmd = [sys.executable, "standalone.py", "--port", str(args.port)]
-    
-    # Start in background
-    process = subprocess.Popen(
-        cmd,
-        cwd=project_root,
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        start_new_session=True
-    )
-    
-    print(f"Server process started with PID {process.pid}")
-    
+    cmd = [
+        sys.executable,
+        "standalone.py",
+        "--host",
+        "127.0.0.1",
+        "--port",
+        str(args.port),
+    ]
+
+    if args.detach:
+        # Fully detached launch: new session (setsid), no controlling terminal,
+        # stdin from /dev/null, stdout/stderr to a log file. Survives the shell.
+        log_dir = os.path.join(script_dir, "logs")
+        os.makedirs(log_dir, exist_ok=True)
+        log_path = os.path.join(log_dir, f"server-{args.port}.log")
+        with open(log_path, "ab") as log_fh:
+            process = subprocess.Popen(
+                cmd,
+                cwd=project_root,
+                stdin=subprocess.DEVNULL,
+                stdout=log_fh,
+                stderr=subprocess.STDOUT,
+                start_new_session=True,
+                close_fds=True,
+            )
+        print(f"Detached server process started with PID {process.pid} (setsid)")
+        print(f"Log: {log_path}")
+    else:
+        # Plain background process (legacy behavior): dies with the shell.
+        process = subprocess.Popen(
+            cmd,
+            cwd=project_root,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            start_new_session=True,
+        )
+        print(f"Server process started with PID {process.pid}")
+        print(
+            "NOTE: not detached — this process dies when the launching shell exits. "
+            "For E2E use --detach."
+        )
+
+    write_managed_pids(args.port, [process.pid])
+
    # Wait for ready if requested
    if args.wait:
        print(f"Waiting for server to be ready (timeout: {args.timeout}s)...")
        if wait_for_server(args.port, args.timeout):
            print(f"Server ready at http://127.0.0.1:{args.port}/loras")
            return 0
-        else:
-            print(f"Timeout waiting for server")
-            return 1
-    
+        print(f"Timeout waiting for server on port {args.port}")
+        return 1
+
    print(f"Server starting at http://127.0.0.1:{args.port}/loras")
    return 0

@@ -1,15 +1,20 @@
 #!/usr/bin/env python3
 """
 Wait for LoRa Manager server to become ready.
+
+Timeout is configurable via --timeout (default 30s); the script polls the port
+until the server accepts connections or the timeout expires.
 """

+from __future__ import annotations
+
 import argparse
 import socket
 import sys
 import time


-def is_server_ready(port: int, timeout: float = 0.5) -> bool:
+def is_server_ready(port: int, timeout: float = 2.0) -> bool:
    """Check if server is accepting connections."""
    try:
        with socket.create_connection(("127.0.0.1", port), timeout=timeout):
@@ -21,9 +26,15 @@ def is_server_ready(port: int, timeout: float = 0.5) -> bool:
 def wait_for_server(port: int, timeout: int = 30) -> bool:
    """Wait for server to become ready."""
    start = time.time()
+    last_report = 0.0
    while time.time() - start < timeout:
        if is_server_ready(port):
            return True
+        # Report progress every ~5s so a slow boot is visible, not silent.
+        elapsed = time.time() - start
+        if elapsed - last_report >= 5:
+            print(f"  ...still waiting ({int(elapsed)}s/{timeout}s)")
+            last_report = elapsed
        time.sleep(0.5)
    return False

@@ -36,25 +47,24 @@ def main() -> int:
        "--port",
        type=int,
        default=8188,
-        help="Server port (default: 8188)"
+        help="Server port (default: 8188)",
    )
    parser.add_argument(
        "--timeout",
        type=int,
        default=30,
-        help="Timeout in seconds (default: 30)"
+        help="Timeout in seconds (default: 30)",
    )
-    
+
    args = parser.parse_args()
-    
+
    print(f"Waiting for server on port {args.port} (timeout: {args.timeout}s)...")
-    
+
    if wait_for_server(args.port, args.timeout):
        print(f"Server ready at http://127.0.0.1:{args.port}/loras")
        return 0
-    else:
-        print(f"Timeout: Server not ready after {args.timeout}s")
-        return 1
+    print(f"Timeout: Server not ready after {args.timeout}s")
+    return 1


 if __name__ == "__main__":
@@ -25,6 +25,7 @@ model_cache/
 reasonix.toml
 .reasonix/
 .codegraph/
+.playwright-mcp/

 # Vue widgets development cache (but keep build output)
 vue-widgets/node_modules/
@@ -36,3 +37,7 @@ vue-widgets/dist/

 # Working/research notes (not committed)
 .docs/
+
+# HF enrichment validation baseline snapshots (contain potentially
+# NSFW README content fetched from community model repos)
+tests/enrich_hf_validation/baselines/
@@ -0,0 +1,202 @@
+---
+slug: undo-delete-staging
+status: drafting
+intent: clear
+review_required: false
+pending-action: write .omo/plans/undo-delete-staging.md
+approach: "Option B: delayed physical deletion with Undo. Backend: same-volume rename to per-root staging dir (.lm-pending-delete/) [updated 2026-08: model staging moved to a SIBLING dir inside each deleted model's own folder — see 'Symlink fix (2026-08)' under Decisions] + manifest JSON (batch_id, expires_at, staged->original map) + purge (30s TTL timer + startup sweep + opportunistic) + undo-delete endpoint + settings toggle 'skip undo'. Small files (recipes: JSON+preview) copy to global staging under settings dir instead of rename. Frontend: extend toast system with action button + 30s countdown; delete flows (single model / recipe / bulk / duplicates) consume batch_id from delete response and show Undo toast; expired undo -> 'undo expired' toast. Plus confirm-modal friction (C-friction, NO type-to-confirm): delete button delay-activation 1.5s + modal shows file size 'will free X GB' + Cancel gets initial focus. i18n keys + sync_translation_keys.py."
+---
+
+# Draft: undo-delete-staging
+
+## Components (topology ledger)
+<!-- Lock the SHAPE before depth. One row per top-level component that can succeed or fail independently. -->
+<!-- id | outcome (one line) | status: active|deferred | evidence path -->
+- backend staging module (stage/purge/undo + manifest + per-volume dir resolution) | new module, active | pending exploration: model_lifecycle_service.py delete_model / delete_model_artifacts
+- delete endpoints return batch_id (model/recipe/bulk/duplicates) | active | pending exploration: handlers + response shapes
+- undo-delete HTTP endpoint + route registration | active | pending exploration: route registrar pattern
+- purge scheduling (30s timer + startup sweep + opportunistic) | active | pending exploration: app on_startup hooks
+- settings toggle "skip undo window" | active | pending exploration: settings service read pattern
+- frontend toast extension (action button + countdown) | active | pending exploration: showToast impl
+- frontend delete flows consume batch_id + Undo toast | active | pending exploration: call sites
+- confirm-modal friction (delay-activate + size display + cancel focus) | active | pending exploration: modal focus behavior
+- i18n keys + sync_translation_keys.py | active | known
+
+## Open assumptions (announced defaults)
+<!-- Record any default you adopt instead of asking, so the user can veto it at the gate. -->
+<!-- assumption | adopted default | rationale | reversible? -->
+- Undo window TTL = 30s | 30s balances space-freeing intent vs accident recovery | yes (constant)
+- Staging dir name: `.lm-pending-delete/` under each model root; recipes: `{settings_dir}/.lm-pending-delete/` | hidden, same-volume [updated 2026-08: same-volume is now guaranteed by sibling staging inside the model's own folder, not by the root location], consistent | yes
+- Staging failure falls back to existing hard delete | user intent is delete; staging is best-effort; hard delete likely fails identically under same conditions | yes
+- Purge on startup uses expires_at (not purge-all) so a <30s restart with live tab can still undo | robust, matches client-side timer | yes
+- Settings toggle label: "Delete permanently immediately (skip undo window)" | power users freeing space | yes
+- C-friction: delete button enabled after 1.5s + modal shows freed size; NO type-to-confirm (user vetoed) | user explicitly rejected type-to-confirm | n/a
+- Bulk/duplicates delete: one batch id for whole action, one undo restores all | simplest consistent semantics | yes
+
+## Findings (cited - path:lines)
+
+### Backend
+- `delete_model_artifacts` (py/services/model_lifecycle_service.py:19-48) = physical delete via os.remove; patterns: main file + `{name}.metadata.json` + PREVIEW_EXTENSIONS (py/utils/constants.py:22-37). ALSO called by ModelScanner.bulk_delete_models (py/services/model_scanner.py:2221) - single swap point covers bulk models.
+- `ModelLifecycleService.delete_model` (model_lifecycle_service.py:101-154): fetches `cached_entry` (111-116) - SNAPSHOT available for cache restore; after delete: cache.raw_data removal + resort + bump_cache_version (136-143), `_hash_index.remove_by_path` (145-146), `_sync_update_for_model` (148; update-service only, no recipe JSON rewrites - recipe refs are hash-based, re-resolve on restore), `_persist_current_cache` (150-152), returns `{"success": True, "deleted_files": [...]}` (154).
+- Handler `delete_model` (py/routes/handlers/model_handlers.py:478-492): POST /api/lm/{prefix}/delete; response passthrough; `_broadcast_models_changed()` (57-74) after success; 400 `{"success":false,"error"}`; 500 plain text.
+- Recipe delete: handler (recipe_handlers.py:1422-1438) DELETE /api/lm/recipe/{recipe_id} -> persistence_service.delete_recipe (py/services/recipes/persistence_service.py:193-209): os.remove(recipe_json_path) + os.remove(image_path) (204-206), recipe_scanner.remove_recipe (208), returns `{"success": true, "message": ...}`. PersistenceResult dataclass (20-25).
+- Bulk models: POST /api/lm/{prefix}/bulk-delete (model_route_registrar.py:39) -> handler (model_handlers.py:974-994) -> lifecycle_service.bulk_delete_models (model_lifecycle_service.py:308-318) -> scanner.bulk_delete_models (model_scanner.py:2181-2269) which calls delete_model_artifacts per file (2221) + `_batch_update_cache_for_deleted_models` (2271-2335); response `{"success","status","total_deleted","total_attempted","cache_updated","results"}` (2254-2269).
+- Bulk recipes: POST /api/lm/recipes/bulk-delete (recipe_route_registrar.py:50) -> handler (recipe_handlers.py:1554-1573) -> persistence_service.bulk_delete (persistence_service.py:439-482): per-id os.remove x2 (464-466), recipe_scanner.bulk_remove (472); response `{"success","deleted","failed","total_deleted","total_failed"}` (474-482).
+- Duplicates: NO dedicated delete endpoints (find-only: GET /api/lm/{prefix}/find-duplicates model_route_registrar.py:59, GET /api/lm/recipes/find-duplicates recipe_route_registrar.py:49). Duplicate deletion reuses bulk-delete endpoints.
+- Startup hooks: lora_manager.py:183-187 `app.on_startup.append(lambda app: cls._initialize_services())` (ComfyUI mode, app = PromptServer.instance.app at :78); standalone.py:370-374 same (StandaloneLoraManager.add_routes). Background tasks: `asyncio.create_task(name=...)` (lora_manager.py:224-239; recipe_handlers.py:793). Singleton+asyncio.Lock pattern: model_scanner.py:40-63.
+- Settings: DEFAULT_SETTINGS (py/services/settings_manager.py:57-119), `get(key, default)` (1390-1392), get_settings_manager() (2215-2228), reset_settings_manager() (2231). Typed-bool getter example: get_skip_previously_downloaded_model_versions (1253-1262). Handlers: base_model_routes.py:70, base_recipe_routes.py:54.
+- Model roots: ModelScanner.get_model_roots base NotImplementedError (model_scanner.py:1073-1075); impls lora_scanner.py:31-45, checkpoint_scanner.py:428-441, embedding_scanner.py:24-36. `_find_root_for_file(file_path)` (model_scanner.py:1108-1124) returns containing root - for per-root staging dir computation [updated 2026-08: staging no longer uses the containing root; batches are siblings inside the model's own folder]. Business-path rule (AGENTS.md): use os.path.abspath, never realpath, for staging/undo routing.
+- Cache restore methods: ModelCache has raw_data + resort (conftest mocks: tests/conftest.py:144-154); ModelHashIndex.add_entry(sha256, file_path, autov3) (py/services/model_hash_index.py:16); RecipeScanner.add_recipe(recipe_data) (recipe_scanner.py:2136) -> recipe_cache.add_recipe (recipe_cache.py:64). No single-file incremental model rescan - use snapshot restore instead of rescan.
+- Route registrar: model_route_registrar.py:177 add_route(method, path, handler), :180 add_prefixed_route - undo endpoint can be a non-prefixed route via add_route.
+- Tests: tests/services/test_model_lifecycle_service.py (inline tmp_path files, per-test stub scanners ScannerForDelete/VersionAwareScanner etc); conftest MockScanner/MockCache/MockHashIndex (tests/conftest.py:134-212); integration fixtures tests/integration/conftest.py; lifecycle hook tests tests/routes/test_lora_manager_lifecycle.py:177-178, tests/standalone/test_standalone_server.py:83-84.
+
+### Frontend
+- 5 delete call sites:
+  a) Single model: static/js/utils/modalUtils.js confirmDelete (27-42) -> getModelApiClient().deleteModel(path); ignores return.
+  b) Recipe single: static/js/components/RecipeCard.js confirmDeleteRecipe (405-449) - RAW fetch DELETE /api/lm/recipe/{id}, checks only response.ok, showToast toast.recipes.deletedSuccessfully, state.virtualScroller.removeItemByFilePath.
+  c) Bulk: static/js/managers/BulkManager.js confirmBulkDelete (633-672) -> getActiveApiClient() (134-142) -> bulkDeleteModels(filePaths); reads result.cancelled/success/deleted_count/error.
+  d) Recipe duplicates: static/js/components/DuplicatesManager.js confirmDeleteDuplicates (457-494) - RAW fetch POST /api/lm/recipes/bulk-delete, reads data.success/data.total_deleted, exitDuplicateMode().
+  e) Model duplicates: static/js/components/ModelDuplicatesManager.js confirmDeleteDuplicates (710-776) - RAW fetch POST /api/lm/{type}/bulk-delete, reads data.total_deleted, then resetAndReload(true) + find-duplicates re-check.
+  Bonus: static/js/components/shared/ModelVersionsTab.js:1136-1144 client.deleteModel (ignores return).
+- API clients: BaseModelApiClient.deleteModel (static/js/api/baseModelApi.js:184-216) returns true/false, shows its own toasts, does removeItemByFilePath inside; bulkDeleteModels (1591-1642) returns {success, deleted_count, failed_count, errors} or {success:false, cancelled:true}; RecipeSidebarApiClient.bulkDeleteModels (recipeApi.js:623-664) returns {success, deleted_count: total_deleted, ...}. Endpoint map apiConfig.js:56,64.
+- Toast: showToast(key, params={}, type='info', fallback=null) (static/js/utils/uiHelpers.js:136-193) - textContent only, NO action/button support; durations 2000/5000ms; CSS static/css/components/toast.css (.toast flex gap:12px - button can be added). Closest action pattern: bannerService.registerBanner actions array + onRegister (static/js/managers/BannerService.js; used uiHelpers.js:18-57).
+- i18n: locales/en.json delete keys (1303-1314 bulkDelete, 1945-1948 recipes, 1987-1991 models, 2124-2130 duplicates, 2166-2170 toast.api); t()/interpolate (static/js/i18n/index.js:193-248); translate wrapper (utils/i18nHelpers.js:13-23); sync script scripts/sync_translation_keys.py (en reference, [TODO: Translate] placeholders).
+- Refresh after undo: recipes -> window.recipeManager.loadRecipes(true) (recipes.js:359; used by FilterManager.js:752 etc) or refreshRecipes (recipeApi.js:308); models -> resetAndReload(true) from modelApiFactory (used by ModelDuplicatesManager.js:740).
+- Size for modal: card.dataset.file_size (ModelCard.js:467), formatFileSize (ModelModal.js:615).
+- Tests: tests/frontend/utils/uiHelpers.dom.test.js (toast), api/recipeApi.bulk.test.js, components/duplicatesManager.test.js, components/modelDuplicatesManager.test.js, pages/*Page.test.js, i18n tests tests/i18n/test_i18n.py.
+
+## Decisions (with rationale)
+
+1. Same-volume rename staging for model files (atomic, no copy cost for multi-GB files); cross-volume rename forbidden. [CORRECTED 2026-08: "same-volume because under the containing root" was only true for plain directories — nested symlinked subdirs could cross volumes. Superseded by sibling staging: `.lm-pending-delete/<batch_id>/` inside the deleted model's own folder makes stage/undo same-device by construction; see "Symlink fix (2026-08)" below.]
+2. Copy-to-global-staging for recipes (small files; avoids recipe JSON vs preview image cross-volume problem).
+3. Manifest JSON files are the only state - no DB changes. Manifest includes model cached_entry snapshot for exact cache restore (no rescan needed).
+4. Undo endpoint returns restored paths; expired batch -> 404-style error -> frontend 'undo expired' toast.
+5. Skip-undo setting honored server-side (no batch_id in response -> no undo toast client-side).
+6. Staging failure falls back to existing hard delete (best-effort undo, never blocks delete).
+7. Undo window TTL = 30s constant (PENDING_DELETE_TTL_SECONDS); startup sweep uses expires_at (survives restart; browser-tab timer survives).
+8. Purge triple-trigger: per-batch asyncio timer task + on_startup sweep + opportunistic purge at each stage/undo.
+9. Frontend: new showActionToast (keep showToast signature untouched; extract shared createToastElement/appendToast internals); undo click -> shared handleUndoDelete(batchId, refreshFn); full list refresh after undo (recipes: window.recipeManager.loadRecipes(true); models: resetAndReload(true)).
+10. C-friction wave (NO type-to-confirm - user vetoed): delete buttons delay-activate 1.5s after modal open, initial focus on Cancel, model delete modal gains "permanently deleted from disk" warning + file size display (card.dataset.file_size + formatFileSize).
+11. Model cache restore on undo: append snapshot to cache.raw_data (dedupe by file_path) + resort + bump_cache_version + _persist_current_cache + _hash_index.add_entry + _broadcast_models_changed. Recipe restore: copy back files + recipe_scanner.add_recipe(recipe_data loaded from restored JSON).
+
+### Symlink fix (2026-08)
+
+Post-execution addendum (plan `.omo/plans/undo-delete-symlink-fix.md`, commits 5fd4946b / 0c00ee22):
+
+12. Model staging moved from `<model_root>/.lm-pending-delete/<batch_id>/` to `<model_dir>/.lm-pending-delete/<batch_id>/` (sibling of the model artifacts, inside the deleted model's own folder). Stage/undo renames are same-device BY CONSTRUCTION — EXDEV is impossible even when the business path traverses nested symlinks to other volumes (the decision-1 "containing root" guarantee covered only plain directories). EXDEV remains possible only for cross-volume merges, which keep the batch_ids-array fallback. Accepted edge: deleting the model's whole FOLDER during the 30s window destroys that batch (undo returns 404). Batch discovery uses an in-memory registry (`_known_batch_dirs`) with a startup reconciliation scan (`purge_expired(scan_roots=True)`) covering restarts and crash leftovers. Recipe batches unchanged (copy-based settings-dir staging with the `_restore_file` EXDEV fallback).
+
+## Scope IN
+
+- Model single delete (model_handlers delete_model / model_lifecycle_service)
+- Recipe delete (recipe_handlers delete_recipe / persistence_service)
+- Bulk delete (models scanner + recipes persistence) + duplicates (reuse bulk endpoints)
+- Undo endpoint POST /api/lm/undo-delete (models + recipes, one batch space)
+- Purge: timer + startup sweep + opportunistic
+- Settings toggle delete_undo_enabled + settings page checkbox
+- Frontend: showActionToast + all 5 delete flows + shared undo handler
+- C-friction modal changes (delay-activate + cancel focus + warning copy + size display)
+- i18n keys + sync_translation_keys.py
+- Backend + frontend tests
+
+## Scope OUT (Must NOT have)
+
+- NO type-to-confirm / hold-to-confirm friction (user vetoed)
+- NO OS trash integration (send2trash) in this iteration
+- NO persistent recycle-bin UI (no trash browsing page)
+- NO changes to exclude/unexclude flow
+- NO DB migrations
+- NO new dependencies (no send2trash)
+- NO changes to download flows
+- NO recipe-JSON rewriting on model undo (hash-based refs re-resolve themselves)
+
+## Open questions
+
+None - all implementation details resolved by exploration. Design decisions settled in conversation (B+C, no type-to-confirm).
+
+## Approval gate
+status: approved
+<!-- Approach approved -> rerun scaffold without --draft-only, run Metis gap analysis, APPEND todo batches, fill TL;DR last, run structural self-check, then Phase 4 handoff. -->
+
+## Review round state (ulw-plan-review-round-state-contract)
+```json
+{
+  "transition": "replace",
+  "phase": "review_round_initialized",
+  "applies_when": ["retry_after_plan_change"],
+  "atomic": true,
+  "review_required": true,
+  "plan_path": ".omo/plans/undo-delete-staging.md",
+  "plan_sha256": "8cf7c9be38a76d8ef1fb832aba043d6d7e82b60465b1bf28c6eafa7045117adc",
+  "review_round_id": "rr-undo-del-20260811-006",
+  "round_status": "active",
+  "pending-action": "review .omo/plans/undo-delete-staging.md",
+  "review": {
+    "momus": { "status": "pending", "workspace_root": "/mnt/data/reinstall-backup-2026-04-12/data/workspace/ComfyUI/custom_nodes/ComfyUI-Lora-Manager", "runtime_home": null, "target": ".omo/plans/undo-delete-staging.md", "round_id": "rr-undo-del-20260811-006", "plan_sha256": "8cf7c9be38a76d8ef1fb832aba043d6d7e82b60465b1bf28c6eafa7045117adc", "launch_id": null, "session": null, "result": null },
+    "independent": { "status": "pending", "workspace_root": "/mnt/data/reinstall-backup-2026-04-12/data/workspace/ComfyUI/custom_nodes/ComfyUI-Lora-Manager", "runtime_home": null, "target": ".omo/plans/undo-delete-staging.md", "round_id": "rr-undo-del-20260811-006", "plan_sha256": "8cf7c9be38a76d8ef1fb832aba043d6d7e82b60465b1bf28c6eafa7045117adc", "launch_id": null, "session": null, "result": null }
+  }
+}
+```
+
+## Review results + fix/retry ledger
+
+### Round 1 (rr-undo-del-20260811-001, plan sha256 6c52bf99...)
+- momus: APPROVE (non-blocking notes: todo1+7 duplicate DEFAULT_SETTINGS key -> fixed todo 7 to verify-only; "batch_ids" plural in todos 8/9 acceptance -> fixed; purge OSError note -> folded into todo 1 purge semantics)
+- independent (oracle): CHANGES_REQUESTED
+  - BLOCKING S1: scanner walks would index .lm-pending-delete staged files as ghost entries -> fixed: todo 1 now mandates scanner walk exclusion at model_scanner.py:706/:867/:1404/_process_model_file + acceptance (o) scanner-visibility test
+  - BLOCKING S2: manifest lacks model_type, undo could restore into wrong cache/hash index -> fixed: manifest now carries model_type + todo 5 resolves per-type scanner via registrar pattern + acceptance (b) checkpoint-batch test
+  - S3 merged-batch expires_at re-anchor -> fixed: merge_batches re-anchors now+TTL in todo 1 + todo 3/4 assertions
+  - S4 manifest-less dir policy -> fixed: quarantine to <batch_id>.orphaned, never delete (todo 1 + acceptance g)
+  - S5 partial-undo retry semantics -> fixed: per-entry restored flag write-through + retry test (acceptance e)
+  - S6 purge locked-file failure semantics -> fixed: skip file, keep batch, never rmtree past errors (todo 1 + acceptance i)
+  - T8 undo-after-restart test -> fixed: todo 5 acceptance (f)
+  - T9 recipe undo -> re-delete test -> fixed: todo 5 acceptance (h)
+  - T7 rescan-stale-entry test -> fixed: todo 5 acceptance (g)
+  - Route registration pinned to shared routes class per mode (NOT per-model-type registrar which registers 3x) -> fixed: todo 5 now creates py/routes/pending_delete_routes.py registered once in lora_manager.py:170-172 + standalone.py:356-358 + duplicate-route test (e)
+  - Version-index staleness on single-delete undo -> fixed: todo 5 follows bulk cache-update pattern incl. rebuild_version_index (model_scanner.py:2324)
+  - Cancelled-bulk batch_id frontend handling -> fixed: todo 9 shows action toast on cancelled+staged-subset
+  - Single-instance assumption -> added to Scope OUT
+  - Occupied-refusal loss UX -> accepted-intent documented in success criteria + modal copy
+
+### Round 2 (rr-undo-del-20260811-002, plan sha256 f3d52235...)
+- momus: APPROVE (all 12 round-1 fixes verified present; zero dead references; non-blocking nits only)
+- independent (oracle): CHANGES_REQUESTED
+  - BLOCK-1: merge_batches file-movement semantics unspecified (silent data-loss vector) -> fixed: todo 1 now specifies move-into-winner-dir + entry re-point + loser-dirs-removed-only-when-empty + abort-on-move-failure (all batches intact) + merge inside service lock + acceptance (k) file-survival assertions + acceptance (l) merge-failure abort test
+  - BLOCK-2: same-file parallel edits within waves (todo 5 vs 6 on lora_manager.py; todo 8 vs 9 on baseModelApi.js) -> fixed: waves/matrix now serialize 5->6 and 8->9 with explicit reasons; matrix updated
+  - Recommended: checkpoint_scanner.py:331 exclusion -> fixed (todo 1 + acceptance p); S5 pre-check skips restored:true entries -> fixed (todo 1); _tags_count restore on undo -> fixed (todo 5 + acceptance j); undo-blind flows documented (ModelVersionsTab + misc_handlers:2456) -> fixed (todo 8 note + Scope OUT); merge-failure no-merge fallback contract (batch_ids array) -> fixed (todos 3/4/9)
+
+### Round 3 (rr-undo-del-20260811-003, plan sha256 8f2dfd46...)
+- momus: APPROVE (all round-2 fixes verified present + spot-checked refs; no new contradictions)
+- independent (oracle): CHANGES_REQUESTED
+  - BLOCKING A: merged batches never timer-purged after re-anchor (winner's original timer no-ops at old expiry; no fresh timer for re-anchored expiry; idle server -> merged batch lingers, violating "30s purge" success criterion; affects EVERY bulk delete) -> fixed: todo 1 merge_batches now ARMS A FRESH PURGE TIMER for the winner with re-anchored expiry + acceptance (q) fresh-timer test + purge_expired must enumerate ALL scanner types' roots (explicit in todo 1)
+  - BLOCKING B: dependency matrix contradicted same-file policy for todos 8/9<->11 (5 shared files) and 12<->11 -> fixed: todo 11 now "Blocked by: 8, 9 (same files...)"; todo 12 blocked by 11 (sync after 11); wave text updated (11, then 12 AFTER 11); "Can parallelize with" columns corrected
+  - BLOCKING C: frontend batch_ids sequential-undo fallback has NO test + merge->undo loser-restore + merge->purge assertions missing -> fixed: todo 9 acceptance now tests the batch_ids fallback path; todo 1 acceptance now has (k2)/(k3)
+  - Notes folded: sub-second toast-tail expiry race accepted; EXDEV fallback = NORMAL path for cross-volume bulks [annotated 2026-08: after the sibling-staging fix, EXDEV can only arise during cross-volume MERGES, never during single stage/undo renames]
+
+### Round 4 (rr-undo-del-20260811-004, plan sha256 179e7ff7...)
+- momus: APPROVE (round-3 fixes verified; one non-blocking nit: todo 11 inline "Blocked by: —" stale -> fixed to "8, 9")
+- independent (oracle): CHANGES_REQUESTED
+  - BLOCKING GAP-1 (NEW, introduced by round-3 fix): todo 8 handleUndoDelete always-refresh/always-toast contract contradicted todo 9's sequential loop "exactly ONE final refresh" -> fixed: handleUndoDelete(batchId, refreshFn, {showToast, refresh}) suppression options; todo 9 loop uses suppressed calls + one final refresh/toast; acceptance extended (loop failure mid-way -> stop + error toast + no final refresh; 404 body discrimination expired vs occupied)
+  - BLOCKING GAP-2: no cross-type purge enumeration test -> fixed: todo 1 acceptance (r) purges expired batches across lora root + checkpoint root + recipe staging dir in one call
+  - Non-blocking folded: GAP-3 404-copy discrimination -> fixed in todo 8 (d); GAP-4 merge partial-failure rollback direction (move back + restore manifests, extended (l) asserts sequential constituent undo still restores everything) -> fixed in todo 1; GAP-5 post-restart timer-loss residual gap documented -> fixed in todo 6; GAP-6 usage_stats.py:424 walk added to exclusion mandate + todo 5 acceptance (k) embeddings undo test
+
+### Round 5 (rr-undo-del-20260811-005, plan sha256 dfaa39ea...)
+- momus: APPROVE (all round-4 fixes verified; no new contradictions)
+- independent (oracle): CHANGES_REQUESTED
+  - BLOCK-1: lock-ordering deadlock ambiguity (asyncio.Lock not re-entrant: opportunistic purge_expired called while stage/undo hold the lock would deadlock on first use) -> fixed: todo 1 now has explicit LOCK HIERARCHY (lock acquired ONLY by stage/merge/undo/purge_batch; purge_expired is lock-free and must be called BEFORE lock acquisition); todo 6 (c) updated with the same rule + acceptance (u) lock-no-deadlock test
+  - BLOCK-2: purge edge semantics unspecified -> fixed: purge_batch treats missing staged files (partially-restored batches) as already-purged (FileNotFoundError silent no-op); sweep skips `.orphaned`-suffixed dirs (quarantine is terminal); acceptance (s) partially-restored purge + (t) quarantine-terminal tests
+  - Non-blocking folded: todo 2/3 test-file collision -> todo 3's bulk tests moved to tests/services/test_model_scanner.py; todo 9 (d) DuplicatesManager refreshFn stated explicitly (recipes loadRecipes / models resetAndReload); modal-copy + bulk-count trade-offs acknowledged in success criteria; acceptance (r) extended with embeddings root
+
+### Round 6 (rr-undo-del-20260811-006, plan sha256 8cf7c9be...)
+- momus: APPROVE (all round-5 fixes verified; no new contradictions; references verified)
+- independent (oracle): APPROVE — no blocking issues; all round-5 items fixed with working, tested solutions; no new race/data-loss/consistency defects
+- Deferred optional improvements (non-blocking, recorded for executor awareness; plan file left untouched to preserve the approved digest):
+  1. Tag-count asymmetry: single delete_model never decrements _tags_count (lifecycle 101-154), bulk does (scanner 2297-2303); undo re-increment is exact for bulk, over-counts for single until rescan (cosmetic, self-healing). Optional fix riding in todo 2: decrement tags in the single-delete path to mirror bulk.
+  2. Todo 5 factual nit: ModelCache.resort() already rebuilds the version index — explicit rebuild in undo is belt-and-braces, no action needed.
+  3. Todo 8 premise nit: ModelVersionsTab call ignores deleteModel's return entirely — nothing breaks, no adaptation needed.
+  4. Todo 3's pytest command includes test_model_lifecycle_service.py which todo 2 edits in the same wave — run that file's tests after todo 2 lands.
+  5. merge_batches with a missing/quarantined constituent id: any sane fallback (abort -> batch_ids, or skip missing) acceptable — files stay staged either way.
+
+## Review lifecycle
+- rounds: 6 (rr-undo-del-20260811-001..006); final round both lanes APPROVE
+- final live-plan validation: sha256 = 8cf7c9be38a76d8ef1fb832aba043d6d7e82b60465b1bf28c6eafa7045117adc — MATCHES approved round-6 digest
+- status: APPROVED — ready for execution handoff ($start-work undo-delete-staging)
@@ -31,7 +31,7 @@ COVERAGE_FILE=coverage/backend/.coverage pytest \
  --cov-report=xml:coverage/backend/coverage.xml
 ```

-### Frontend Development (Standalone Web UI)
+### Frontend Development (LoRA Manager Web UI)

 ```bash
 npm install
@@ -102,6 +102,7 @@ npm run test:coverage       # Generate coverage report
 - ComfyUI: `app.registerExtension()`, `node.addDOMWidget(name, type, element, options)`
 - Event handlers via `addEventListener` or widget callbacks
 - Shared utilities: `web/comfyui/utils.js`
+- Dual-mode rendering patterns (canvas vs Vue): see `docs/comfyui-dual-mode-widgets.md`

 ### Vue Composables Pattern

@@ -136,7 +137,13 @@ npm run test:coverage       # Generate coverage report
 - Dual mode: ComfyUI plugin (folder_paths) vs standalone (settings.json)
 - Detection: `os.environ.get("LORA_MANAGER_STANDALONE", "0") == "1"`
 - Run `python scripts/sync_translation_keys.py` after adding UI strings to `locales/en.json`
- Symlinks require normalized paths
+- Symlinks require normalized paths.
+  **Business paths vs real paths**: All stored paths and operation routing use the
+  original paths as they appear under configured model roots — symlinks are NOT
+  resolved. `os.path.realpath` is only for scanner dedup and the symlink cache.
+  Any path passed to `os.remove`/`os.rename`/`shutil.move` or validated by a
+  containment check MUST use the business path (i.e. `os.path.abspath`, not
+  `realpath`).

 ## Git / Commit Messages

@@ -147,9 +154,9 @@ npm run test:coverage       # Generate coverage report

 ## Frontend UI Architecture

-### 1. Standalone Web UI
+### 1. LoRA Manager Web UI
 - Location: `./static/` and `./templates/`
- Tech: Vanilla JS + CSS, served by standalone server
+- Tech: Vanilla JS + CSS, served by the hosting server (ComfyUI app in plugin mode, `standalone.py` in standalone mode)
 - Tests via npm in root directory

 ### 2. ComfyUI Custom Node Widgets
@@ -15,6 +15,10 @@ try:  # pragma: no cover - import fallback for pytest collection
    from .py.nodes.lora_pool import LoraPoolLM
    from .py.nodes.lora_randomizer import LoraRandomizerLM
    from .py.nodes.lora_cycler import LoraCyclerLM
+    from .py.nodes.lora_info import LoraInfoLM
+    from .py.nodes.lora_syntax_to_path import LoraSyntaxToPath
+    from .py.nodes.create_hook_lora import CreateHookLoraLM
+    from .py.nodes.metadata_overwrite import MetadataOverwriteLM
    from .py.metadata_collector import init as init_metadata_collector
 except (
    ImportError
@@ -56,6 +60,16 @@ except (
        "py.nodes.lora_randomizer"
    ).LoraRandomizerLM
    LoraCyclerLM = importlib.import_module("py.nodes.lora_cycler").LoraCyclerLM
+    LoraInfoLM = importlib.import_module("py.nodes.lora_info").LoraInfoLM
+    LoraSyntaxToPath = importlib.import_module(
+        "py.nodes.lora_syntax_to_path"
+    ).LoraSyntaxToPath
+    CreateHookLoraLM = importlib.import_module(
+        "py.nodes.create_hook_lora"
+    ).CreateHookLoraLM
+    MetadataOverwriteLM = importlib.import_module(
+        "py.nodes.metadata_overwrite"
+    ).MetadataOverwriteLM
    init_metadata_collector = importlib.import_module("py.metadata_collector").init

 NODE_CLASS_MAPPINGS = {
@@ -75,6 +89,10 @@ NODE_CLASS_MAPPINGS = {
    LoraPoolLM.NAME: LoraPoolLM,
    LoraRandomizerLM.NAME: LoraRandomizerLM,
    LoraCyclerLM.NAME: LoraCyclerLM,
+    LoraInfoLM.NAME: LoraInfoLM,
+    LoraSyntaxToPath.NAME: LoraSyntaxToPath,
+    CreateHookLoraLM.NAME: CreateHookLoraLM,
+    MetadataOverwriteLM.NAME: MetadataOverwriteLM,
 }

 WEB_DIRECTORY = "./web/comfyui"
@@ -0,0 +1,208 @@
+# Agent Skills System
+
+The LoRA Manager agent skills system enables LLM-powered metadata enrichment and other AI-driven tasks. Users configure their own LLM provider (BYOK), and skills are executed through right-click context menu actions.
+
+## Architecture
+
+```
+┌──────────────────────────────────────────────┐
+│              LoRA Manager Backend             │
+│                                               │
+│  ┌──────────────┐    ┌────────────────┐       │
+│  │ LLMService    │───▶│ LLM Provider   │       │
+│  │ (BYOK config, │◀───│ (OpenAI/Ollama │       │
+│  │  API calls)   │    │ /custom)       │       │
+│  └───────┬───────┘    └────────────────┘       │
+│          │                                     │
+│  ┌───────▼───────────────────────┐             │
+│  │     AgentService              │             │
+│  │  (orchestration: validate     │             │
+│  │   → LLM call → post-process   │             │
+│  │   → WebSocket broadcast)      │             │
+│  └───────┬───────────────────────┘             │
+│          │                                     │
+│  ┌───────▼───────────────────────┐             │
+│  │     SkillRegistry             │             │
+│  │  ┌─────────────────────────┐  │             │
+│  │  │ enrich_hf_metadata:     │  │             │
+│  │  │  - skill.yaml           │  │             │
+│  │  │  - prompt.md            │  │             │
+│  │  │  - handler.py           │  │             │
+│  │  └─────────────────────────┘  │             │
+│  └───────────────────────────────┘             │
+└──────────────────────────────────────────────┘
+```
+
+### Key Design Principle
+
+**Skills define *what* to do (prompt + post-processing). The AgentService handles *how* (LLM calls, validation, progress).**
+
+Skills never call the LLM directly. This keeps BYOK configuration centralized and provider-agnostic.
+
+## BYOK Configuration
+
+Users configure their LLM provider in **Settings → AI Provider**:
+
+| Setting | Description | Example |
+|---|---|---|
+| `llm_provider` | Provider type | `openai`, `ollama`, or `custom` |
+| `llm_api_key` | API key (not needed for local Ollama) | `sk-...` |
+| `llm_api_base` | Custom API base URL (empty = provider default) | `https://api.openai.com/v1` |
+| `llm_model` | Model name | `gpt-4o-mini` |
+
+Environment variable overrides: `LLM_API_KEY`, `LLM_MODEL`, `LLM_API_BASE`, `LLM_PROVIDER`.
+
+### Supported Providers
+
+- **OpenAI**: Uses `https://api.openai.com/v1` by default
+- **Ollama** (local): Uses `http://localhost:11434/v1`, no API key required
+- **Custom**: Any OpenAI-compatible endpoint (vLLM, LM Studio, etc.) — set `llm_api_base` explicitly
+
+## Available Skills
+
+### enrich_hf_metadata
+
+Enriches HuggingFace-downloaded models with metadata extracted by an LLM from the HF model card.
+
+**Entry point**: Right-click context menu → "Enrich Metadata (Agent)"
+
+**What it does**:
+1. Reads the model's `.metadata.json` to get the `hf_url`
+2. Fetches the README.md from the HuggingFace repository
+3. Sends the README + local metadata to the LLM for structured extraction
+4. Writes extracted fields to `.metadata.json`:
+   - `base_model` — only if current value is empty
+   - `trainedWords` — trigger words (LoRA only, if none exist)
+   - `modelDescription` — concise summary (if none exists)
+   - `tags` — merged with existing tags, deduplicated
+   - `metadata_source` — audit trail: `agent:enrich_hf_metadata`
+   - `llm_enriched_at` — ISO timestamp
+5. Downloads and optimizes preview image (if LLM found one in the README)
+6. Updates the scanner cache
+7. Broadcasts WebSocket progress events
+
+**Model types**: LoRA, Checkpoint, Embedding
+
+## Adding a New Skill
+
+### 1. Create the skill directory
+
+```
+py/services/agent/skills/<skill_name>/
+├── skill.yaml      # Skill metadata and schemas
+├── prompt.md       # LLM prompt template
+└── handler.py      # Pre-processing and post-processing
+```
+
+### 2. Write skill.yaml
+
+```yaml
+name: my_skill
+title: "My Skill"
+description: "What this skill does"
+llm_required: true
+model_type_filter: ["lora"]  # or null for all types
+input_schema:
+  type: object
+  properties:
+    model_paths:
+      type: array
+      items:
+        type: string
+  required:
+    - model_paths
+output_schema:
+  type: object
+  properties:
+    # ... JSON schema for LLM output
+permissions:
+  write_metadata: true
+  write_previews: false
+  network_domains:
+    - "example.com"
+```
+
+### 3. Write prompt.md
+
+Use `{{variable}}` placeholders that will be replaced with data from the `prepare` function:
+
+```markdown
+You are an expert assistant...
+
+Model URL: {{hf_url}}
+README content:
+{{readme_content}}
+
+Current metadata:
+{{current_metadata}}
+```
+
+### 4. Write handler.py
+
+```python
+async def prepare(model_path: str, input_data: dict) -> dict:
+    """Gather context for the LLM prompt. Returns variables for template rendering."""
+    return {
+        "model_path": model_path,
+        # ... other variables used in prompt.md
+    }
+
+async def post_process(context) -> dict:
+    """Apply the LLM-extracted data to the model."""
+    llm_response = context.llm_response
+    # ... write metadata, download previews, update cache
+    return {
+        "success": True,
+        "updated_fields": ["base_model", "tags"],
+        "errors": [],
+    }
+```
+
+**Important**: Use absolute imports (`from py.utils.metadata_manager import MetadataManager`) because skills are loaded via `importlib.util.spec_from_file_location`, which doesn't support relative imports.
+
+### 5. Test
+
+The skill is automatically discovered by `SkillRegistry` on startup. Test with:
+
+```python
+pytest tests/services/test_agent_service.py
+```
+
+## API Endpoints
+
+| Method | Path | Description |
+|---|---|---|
+| GET | `/api/lm/agent/skills` | List available skills |
+| POST | `/api/lm/agent/execute/{skill_name}` | Execute a skill (body: `{"model_paths": [...]}`) |
+| POST | `/api/lm/agent/cancel` | Cancel running skill (stub) |
+
+## WebSocket Events
+
+| Type | When | Key fields |
+|---|---|---|
+| `agent_progress` | Skill started/processing | `skill`, `status`, `total`, `processed`, `success`, `current_path` |
+| `agent_progress` | Skill completed | `skill`, `status`, `updated_models`, `errors`, `summary` |
+| `agent_progress` | Skill error | `skill`, `status`, `error` |
+
+## Security Model
+
+Skills declare permissions in `skill.yaml`:
+- `write_metadata` — can write `.metadata.json` files
+- `write_previews` — can download/replace preview images
+- `network_domains` — allowed domains for HTTP requests
+
+These are declarative constraints checked by `AgentService`. They are defense-in-depth, not a sandbox — the Python process can technically do anything, but the contract is clear and auditable.
+
+## File Locations
+
+| Component | Path |
+|---|---|
+| LLMService | `py/services/llm_service.py` |
+| AgentService | `py/services/agent/agent_service.py` |
+| SkillRegistry | `py/services/agent/skill_registry.py` |
+| SkillDefinition | `py/services/agent/skill_definition.py` |
+| Skills directory | `py/services/agent/skills/` |
+| Route handlers | `py/routes/handlers/agent_handlers.py` |
+| Frontend manager | `static/js/managers/AgentManager.js` |
+| Settings UI | `templates/components/modals/settings_modal.html` |
+| Context menu | `templates/components/context_menu.html` |
@@ -0,0 +1,65 @@
+# ComfyUI Dual-Mode Widget Rendering
+
+ComfyUI custom node widgets render in one of two modes. Patterns that work in one often fail silently in the other. Test both.
+
+## Mode Detection
+
+```js
+typeof LiteGraph !== 'undefined' && LiteGraph.vueNodesMode
+```
+
+In Vue SFCs, `window.LiteGraph` is unavailable — pass as a prop from `main.ts`.
+
+## Canvas Mode Layout
+
+Uses `computeLayoutSize()` + `distributeSpace()` to allocate widget height within the node. Widgets with `computeLayoutSize` participate in space distribution; those with `computeSize` have fixed height.
+
+- `getMinHeight()` in `addDOMWidget` options → minimum widget height
+- `widget.computeLayoutSize()` → `{ minHeight, minWidth, maxHeight? }`
+- Avoid `getMaxHeight()` unless the widget genuinely needs a fixed cap (prevents user resize)
+
+## Vue Mode Layout
+
+Uses CSS Grid (`grid-template-rows`) + `ResizeObserver`. The ResizeObserver watches the widget's DOM and feeds back into grid row sizing. This creates a feedback loop: content grows → row resizes → more space for content → content reflows/grows → row resizes again.
+
+### Height Containment
+
+The fix: `contain: layout size` on the widget root. This tells the browser the element's intrinsic size is CSS-determined, not driven by descendant content. The ResizeObserver sees a stable size and the loop is broken.
+
+```css
+.widget-root.lm-vue-node {
+  height: 100%;
+  min-height: var(--comfy-widget-min-height, 200px);
+  contain: layout size;
+}
+```
+
+Existing examples: `.lm-loras-container.lm-vue-node` and `.comfy-tags-container.lm-vue-node` in `web/comfyui/lm_styles.css`.
+
+**Do NOT** fix height issues with `maxHeight`, `getMaxHeight()`, or inline `max-height` — these prevent the user from resizing the node.
+
+## Scroll Wheel Isolation
+
+Both modes need to distinguish "user wants to scroll widget content" from "user wants to zoom canvas".
+
+**Canvas mode:** Add `@wheel` on widget root. Check `event.target.closest(selector)` for scrollable sub-areas. If scrollable → `event.stopPropagation()`. Otherwise → `app.canvas.processMouseWheel(event)`.
+
+**Vue mode:** Add CSS class `lm-wheel-scrollable` to scrollable elements. The global capture-phase hook in `web/comfyui/utils.js` (`enableListWheelScroll`) detects wheel events on marked elements and manually scrolls them via `element.scrollTop`, consuming the event before canvas zoom sees it.
+
+## DOM Structure
+
+`main.ts` creates an outer `<div>` container, then `vueApp.mount(container)`. The Vue app renders its own root element inside.
+
+- `container.id` / `container.style.*` → outer element
+- Vue scoped `<style>` → `[data-v-hash]` applies only to Vue root
+
+Classes needed by scoped Vue CSS must go on the Vue root element. Pass data as props and bind with `:class` rather than manipulating the DOM from `main.ts`.
+
+## Serialization
+
+For stateful widgets that need workflow persistence:
+
+- `serialize: true` in `addDOMWidget` options
+- `serializeValue()` → state snapshot (called on workflow save)
+- `onSetValue(v)` → restore state (called on workflow load)
+- Always handle missing keys in restored value for backward compatibility with old workflows
@@ -39,6 +39,7 @@ These fields are present in all model metadata files.
 | `metadata_source` | string\|null | ❌ No | ✅ Yes | Last provider that supplied metadata (see below) |
 | `last_checked_at` | float | ❌ No (default: `0`) | ✅ Yes | Unix timestamp of last metadata check |
 | `hash_status` | string | ❌ No (default: `"completed"`) | ✅ Yes | Hash calculation status: `"pending"`, `"calculating"`, `"completed"`, `"failed"` |
+| `autov3` | string\|null | ❌ No | ✅ Yes | CivitAI AutoV3 hash (first 12 chars, lowercase hex) sourced from the safetensors embedded metadata (`sshs_model_hash` / `modelspec.hash_sha256`). **Absent** = not yet checked (may be backfilled later); **`null`** = checked but unavailable (header has no recognized hash); **12-char hex string** = value |

 ---

@@ -287,6 +288,7 @@ These fields are automatically synchronized with the filesystem:
 - `preview_url` — Updated if preview file is moved/removed
 - `sha256` — Updated during hash calculation (when `hash_status="pending"`)
 - `hash_status` — Updated during hash calculation
+- `autov3` — Set when metadata is first created (from safetensors header); may be backfilled later for entries where it is absent
 - `last_checked_at` — Timestamp of scan
 - `metadata_source` — Set based on metadata provider

@@ -345,6 +347,7 @@ These fields can be edited by users at any time through the Lora Manager UI or b
 | `metadata_source` | `null` |
 | `last_checked_at` | `0` |
 | `hash_status` | `"completed"` |
+| `autov3` | absent (not checked) or `null` (checked, no value) |
 | `usage_tips` | `"{}"` (LoRA only) |
 | `model_type` | `"checkpoint"` or `"embedding"` (not present in LoRA models) |

@@ -354,6 +357,7 @@ These fields can be edited by users at any time through the Lora Manager UI or b

 | Version | Date | Changes |
 |---------|------|---------|
+| 1.1 | 2026-08 | Added `autov3` field (CivitAI AutoV3 hash with three-state semantics) |
 | 1.0 | 2026-03 | Initial schema documentation |

 ---
@@ -186,6 +186,16 @@
            "cancelled": "Reparatur abgebrochen. {count} Rezepte wurden repariert.",
            "error": "Recipe-Reparatur fehlgeschlagen: {message}"
        },
+        "rematchRecipes": {
+            "label": "Rezepte lokalen Modellen neu zuordnen",
+            "loading": "Rezepte werden lokalen Modellen neu zugeordnet...",
+            "success": "{entries} Einträge in {recipes} Rezepten zugeordnet",
+            "successErrors": "{entries} Einträge in {recipes} Rezepten zugeordnet, {failures} fehlgeschlagen",
+            "allFailed": "Zuordnung fehlgeschlagen für {failures} von {total} Rezepten",
+            "noMatch": "Keine lokale Übereinstimmung für {entries} Einträge in {recipes} Rezepten gefunden",
+            "cancelled": "Zuordnung abgebrochen. {recipes} Rezepte aktualisiert ({entries} Einträge)",
+            "error": "Zuordnung der Rezepte fehlgeschlagen: {message}"
+        },
        "manageExcludedModels": {
            "label": "Ausgeschlossene Modelle verwalten"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "Voreinstellungsname...",
            "baseModel": "Basis-Modell",
            "baseModelSearchPlaceholder": "Basismodelle durchsuchen...",
-            "modelTags": "Tags (Top 20)",
+            "modelTags": "Tags",
            "modelTypes": "Modelltypen",
            "license": "Lizenz",
            "noCreditRequired": "Kein Credit erforderlich",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "Verkauf generierter Bilder erlauben",
            "noCreditRequiredTooltip": "Modell ohne Nennung des Erstellers verwenden",
            "noTags": "Keine Tags",
+            "tagSearchPlaceholder": "Tags durchsuchen...",
+            "noTagMatches": "Keine Tags entsprechen der aktuellen Suche.",
            "autoTags": "Auto-Tags",
            "noBaseModelMatches": "Keine Basismodelle entsprechen der aktuellen Suche.",
            "clearAll": "Alle Filter löschen",
@@ -447,6 +459,12 @@
                "compact": "7 (1080p), 8 (2K), 10 (4K)"
            },
            "displayDensityWarning": "Warnung: Höhere Dichten können bei Systemen mit begrenzten Ressourcen zu Performance-Problemen führen.",
+            "recipesLayout": "Rezepte-Layout",
+            "recipesLayoutHelp": "Wählen Sie, wie Rezeptkarten angeordnet werden: ein einheitliches Raster oder ein Masonry-Layout (Pinterest-Stil), das das Seitenverhältnis jedes Bildes beibehält.",
+            "recipesLayoutOptions": {
+                "grid": "Raster",
+                "masonry": "Masonry"
+            },
            "showFolderSidebar": "Ordner-Seitenleiste anzeigen",
            "showFolderSidebarHelp": "Blenden Sie die Ordner-Navigationsleiste auf den Modellseiten ein oder aus. Wenn deaktiviert, bleiben Seitenleiste und Hoverbereich verborgen.",
            "cardInfoDisplay": "Karten-Info-Anzeige",
@@ -505,7 +523,9 @@
            "saveSuccess": "Zusätzliche Ordnerpfade aktualisiert. Neustart erforderlich, um Änderungen anzuwenden.",
            "saveError": "Fehler beim Aktualisieren der zusätzlichen Ordnerpfade: {message}",
            "validation": {
-                "duplicatePath": "Dieser Pfad ist bereits konfiguriert"
+                "duplicatePath": "Dieser Pfad ist bereits konfiguriert",
+                "checkpointUnetOverlap": "Derselbe Pfad kann nicht für Checkpoints und Diffusionsmodelle verwendet werden: {paths}",
+                "checkpointUnetOverlapInline": "Dieser Pfad wird bereits für einen anderen Modelltyp verwendet. Bitte verwenden Sie separate Ordner für Checkpoints und Diffusionsmodelle."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "Download wird vorbereitet...",
            "connecting": "Verbindung zum Download-Server wird hergestellt...",
            "completed": "Abgeschlossen",
-            "downloadComplete": "Download erfolgreich abgeschlossen"
+            "downloadComplete": "Download erfolgreich abgeschlossen",
+            "enableCivarchiveApi": "CivArchive API als Metadaten-Anbieter aktivieren",
+            "enableCivarchiveApiHelp": "Wenn aktiviert, wird die CivArchive API als alternative Quelle für Modell-Metadaten verwendet (z. B. für von CivitAI gelöschte Modelle). Deaktivieren, um die Ratenbegrenzungen von CivArchive vollständig zu vermeiden.",
+            "providerOrder": "Reihenfolge der Metadaten-Anbieter",
+            "providerOrderHelp": "Die CivitAI API wird immer zuerst versucht. Wählen Sie die Reihenfolge der übrigen Anbieter bei der Metadatensuche.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "App-Proxy aktivieren",
@@ -657,6 +683,33 @@
            "proxyPassword": "Passwort (optional)",
            "proxyPasswordPlaceholder": "passwort",
            "proxyPasswordHelp": "Passwort für die Proxy-Authentifizierung (falls erforderlich)"
+        },
+        "aiProvider": {
+            "title": "KI-Anbieter",
+            "provider": "Anbieter",
+            "providerHelp": "Wählen Sie Ihren LLM-Anbieter. OpenAI und Ollama verwenden voreingestellte API-Endpunkte. Mit \"Benutzerdefiniert\" können Sie jeden OpenAI-kompatiblen Endpunkt angeben.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (lokal)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "Benutzerdefiniert (OpenAI-kompatibel)"
+            },
+            "apiBase": "API-Basis-URL",
+            "apiBaseHelp": "Die Basis-URL für die LLM-API (z.B. https://api.openai.com/v1). Leer lassen, um die Anbietervoreinstellung zu verwenden.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "API-Schlüssel",
+            "apiKeyHelp": "Ihr LLM-API-Schlüssel. Wird lokal gespeichert und niemals an einen anderen Server außer Ihrem gewählten LLM-Anbieter gesendet.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "Nicht festgelegt",
+            "apiKeyConfigured": "Konfiguriert",
+            "apiKeySet": "Einrichten",
+            "model": "Modell",
+            "modelHelp": "Der zu verwendende Modellname (z.B. deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). Prüfen Sie Ihren Anbieter auf verfügbare Modelle.",
+            "modelPlaceholder": "Modell auswählen..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "Lokale Versionen",
                "versionsCountDesc": "Meiste Versionen zuerst",
                "versionsCountAsc": "Wenigste Versionen zuerst",
-                "versionIdDesc": "Neueste Version zuerst"
+                "versionIdDesc": "Neueste Version zuerst",
+                "random": "Zufällig",
+                "randomAction": "Zufällig mischen"
            },
            "refresh": {
                "title": "Modelliste aktualisieren",
@@ -723,6 +778,7 @@
            "copyAll": "Alle Syntax kopieren",
            "refreshAll": "Alle Metadaten aktualisieren",
            "repairMetadata": "Metadaten der Auswahl reparieren",
+            "rematchMetadata": "Ausgewählte mit lokalen Modellen abgleichen",
            "reimportMetadata": "Aus Quelle neu importieren",
            "checkUpdates": "Auswahl auf Updates prüfen",
            "moveAll": "Alle in Ordner verschieben",
@@ -735,6 +791,8 @@
            "deleteAll": "Ausgewählte löschen",
            "downloadMissingLoras": "Fehlende LoRAs herunterladen",
            "downloadExamples": "Beispielbilder herunterladen",
+            "downloadMissingExamples": "Fehlende herunterladen",
+            "reprocessExamples": "Alle erneut verarbeiten",
            "clear": "Auswahl löschen",
            "skipMetadataRefreshCount": "Überspringen（{count} Modelle）",
            "resumeMetadataRefreshCount": "Fortsetzen（{count} Modelle）",
@@ -754,12 +812,15 @@
                "completed": "Abgeschlossen: {success} verschoben, {skipped} übersprungen, {failures} fehlgeschlagen",
                "complete": "Automatische Organisation abgeschlossen",
                "error": "Fehler: {error}"
-            }
+            },
+            "enrichHfAgent": "HF-Metadaten mit KI anreichern"
        },
        "contextMenu": {
            "refreshMetadata": "Civitai-Daten aktualisieren",
            "checkUpdates": "Updates prüfen",
-            "relinkCivitai": "Mit Civitai neu verknüpfen",
+            "linkModel": "Modell verknüpfen",
+            "linkCivitai": "Mit Civitai neu verknüpfen",
+            "linkHuggingFace": "Mit HuggingFace verknüpfen",
            "copySyntax": "LoRA-Syntax kopieren",
            "copyFilename": "Modell-Dateiname kopieren",
            "copyRecipeSyntax": "Rezept-Syntax kopieren",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "An Workflow senden (Ersetzen)",
            "openExamples": "Beispiele-Ordner öffnen",
            "downloadExamples": "Beispielbilder herunterladen",
+            "downloadMissingExamples": "Fehlende herunterladen",
+            "reprocessExamples": "Alle erneut verarbeiten",
            "replacePreview": "Vorschau ersetzen",
            "setContentRating": "Inhaltsbewertung festlegen",
            "moveToFolder": "In Ordner verschieben",
            "repairMetadata": "Metadaten reparieren",
+            "rematchMetadata": "Mit lokalen Modellen abgleichen",
            "reimportMetadata": "Aus Quelle neu importieren",
            "excludeModel": "Modell ausschließen",
            "restoreModel": "Modell wiederherstellen",
@@ -778,7 +842,8 @@
            "shareRecipe": "Rezept teilen",
            "viewAllLoras": "Alle LoRAs anzeigen",
            "downloadMissingLoras": "Fehlende LoRAs herunterladen",
-            "deleteRecipe": "Rezept löschen"
+            "deleteRecipe": "Rezept löschen",
+            "enrichHfAgent": "HF-Metadaten mit KI anreichern"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "{count} Duplikat-Gruppen gefunden",
+            "noGroups": "Keine Duplikat-Gruppen mit dem aktuellen Abgleichskriterium gefunden",
            "keepLatest": "Neueste Versionen behalten",
-            "deleteSelected": "Ausgewählte löschen"
+            "deleteSelected": "Ausgewählte löschen",
+            "includePromptLabel": "Prompt beim Abgleich berücksichtigen",
+            "basis": {
+                "loraCombo": "Abgeglichen nach: LoRA-Kombination",
+                "loraComboAndPrompt": "Abgeglichen nach: LoRA-Kombination + Prompt",
+                "hintLoraCombo": "Rezepte mit denselben LoRAs bei identischen Stärken werden gruppiert.",
+                "hintPromptIncluded": "Rezepte werden nur gruppiert, wenn sie dieselben LoRAs bei identischen Stärken UND denselben Prompt verwenden."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "Download wird vorbereitet...",
                "downloadedPreview": "Vorschaubild heruntergeladen",
                "downloadingFile": "{type}-Datei wird heruntergeladen",
-                "finalizing": "Download wird abgeschlossen..."
+                "finalizing": "Download wird abgeschlossen...",
+                "cancelling": "Download wird abgebrochen...",
+                "cancelled": "Download abgebrochen"
            },
            "progress": {
                "currentFile": "Aktuelle Datei:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "Gibt {size} frei",
            "title": "Modell löschen",
-            "message": "Sind Sie sicher, dass Sie dieses Modell und alle zugehörigen Dateien löschen möchten?"
+            "message": "Sind Sie sicher, dass Sie dieses Modell und alle zugehörigen Dateien löschen möchten?",
+            "recoverableWarning": "Die Datei wird nach 20 Sekunden endgültig gelöscht, sofern Sie nicht rückgängig machen."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "Diese Aktion kann 20 Sekunden lang rückgängig gemacht werden."
        },
        "excludeModel": {
            "title": "Modell ausschließen",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "Ordnerpfad eingeben oder aus Baum unten auswählen...",
            "root": "Stammverzeichnis"
        },
+        "linkHuggingFace": {
+            "title": "Mit HuggingFace verknüpfen",
+            "infoText": "Fügen Sie die HuggingFace-Repository-URL ein, um dieses Modell zuzuordnen. Dies ermöglicht die KI-gestützte Metadatenanreicherung.",
+            "urlLabel": "HuggingFace-Repository-URL:",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "Geben Sie die vollständige URL des HuggingFace-Repositorys ein.",
+            "confirmAction": "Speichern & Verknüpfen"
+        },
        "relinkCivitai": {
            "title": "Mit Civitai neu verknüpfen",
            "warning": "Warnung:",
@@ -1498,6 +1586,7 @@
                "empty": "Noch keine Versionshistorie für dieses Modell vorhanden.",
                "error": "Versionen konnten nicht geladen werden.",
                "missingModelId": "Für dieses Modell ist keine Civitai-Model-ID vorhanden.",
+                "hfGroupInfo": "Dies ist eine HuggingFace-Modellgruppe. Öffnen Sie die Bibliothek, um alle Versionen im Raster zu sehen.",
                "confirm": {
                    "delete": "Diese Version aus Ihrer Bibliothek löschen?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "CSV herunterladen",
            "columnModelName": "Modellname",
            "columnError": "Fehler"
+        },
+        "downloadBatchSummary": {
+            "title": "Zusammenfassung des Batch-Downloads",
+            "statSuccess": "Erfolgreich",
+            "statFailed": "Fehlgeschlagen",
+            "statTotal": "Gesamt",
+            "successMessage": "Alle {count} Modelle erfolgreich heruntergeladen",
+            "completedWithErrors": "Abgeschlossen, aber mit Fehlern",
+            "failed": "Download fehlgeschlagen",
+            "failedItems": "Fehlgeschlagene Elemente ({count})",
+            "columnName": "Modellname",
+            "columnError": "Fehler",
+            "close": "Schließen",
+            "copyReport": "Bericht kopieren",
+            "retryFailed": "Fehlgeschlagene erneut versuchen ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "Rezept im Workflow ersetzt",
            "recipeFailedToSend": "Fehler beim Senden des Rezepts an den Workflow",
            "noMatchingNodes": "Keine kompatiblen Knoten im aktuellen Workflow verfügbar",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "Kein Zielknoten ausgewählt",
            "modelUpdated": "Modell im Workflow aktualisiert",
            "modelFailed": "Fehler beim Aktualisieren des Modellknotens",
@@ -1701,6 +1806,12 @@
        "checkingMessage": "Bitte warten Sie, während wir nach der neuesten Version suchen.",
        "showNotifications": "Update-Benachrichtigungen anzeigen",
        "latestBadge": "Neueste",
+        "latestMain": "Main-Branch",
+        "channel": "Update-Kanal",
+        "channels": {
+            "release": "Release",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "Update wird vorbereitet...",
            "installing": "Update wird installiert...",
@@ -1721,6 +1832,15 @@
            "warning": "Warnung: Nightly Builds können experimentelle Funktionen enthalten und könnten instabil sein.",
            "enable": "Nightly Updates aktivieren"
        },
+        "channelSwitch": {
+            "nightlyTitle": "Zu Nightly-Kanal wechseln",
+            "nightlyMessage": "Der Wechsel zu Nightly initialisiert ein Git-Repository und verfolgt die neuesten Commits des main-Branches. Updates sind häufiger, können aber instabil sein. Sie können jederzeit zu Release zurückwechseln.",
+            "releaseTitle": "Zu Release-Kanal wechseln",
+            "releaseMessage": "Der Wechsel zu Release checkt den neuesten stabilen Versions-Tag aus. Sie können jederzeit zu Nightly zurückwechseln.",
+            "switching": "Wechsle zu {channel}-Kanal...",
+            "completed": "Erfolgreich zu {channel}-Kanal gewechselt",
+            "failed": "Kanalwechsel fehlgeschlagen"
+        },
        "banners": {
            "recent": "Neueste Mitteilungen",
            "empty": "Keine aktuellen Banner verfügbar.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "Reparatur abgeschlossen: {repaired} repariert, {skipped} übersprungen (von {total})",
            "repairBulkSkipped": "Keine Reparatur für die {total} ausgewählten Rezepte erforderlich",
            "repairBulkFailed": "Reparatur der ausgewählten Rezepte fehlgeschlagen: {message}",
+            "rematchComplete": "{entries} Einträge in {recipes} Rezepten zugeordnet",
+            "rematchCompleteErrors": "{entries} Einträge in {recipes} Rezepten zugeordnet, {failures} fehlgeschlagen",
+            "rematchAllFailed": "Zuordnung fehlgeschlagen für {failures} von {total} ausgewählten Rezepten",
+            "rematchUnmatched": "Keine lokale Übereinstimmung für {entries} Einträge in {recipes} Rezepten gefunden",
+            "rematchSkipped": "Keine Zuordnung für die {total} ausgewählten Rezepte erforderlich",
+            "rematchFailed": "Zuordnung der ausgewählten Rezepte fehlgeschlagen: {message}",
            "reimporting": "Rezept wird aus Quelle neu importiert...",
            "reimportSuccess": "Rezept erfolgreich neu importiert",
            "reimportBulkComplete": "Neuimport abgeschlossen: {completed} importiert, {failed} fehlgeschlagen (von {total})",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "Voreinstellungsname darf maximal {max} Zeichen haben",
            "presetNameInvalidChars": "Voreinstellungsname enthält ungültige Zeichen",
            "presetNameExists": "Eine Voreinstellung mit diesem Namen existiert bereits",
-            "maxPresetsReached": "Maximal {max} Voreinstellungen erlaubt. Löschen Sie eine, um weitere hinzuzufügen.",
            "presetNotFound": "Voreinstellung nicht gefunden",
            "invalidPreset": "Ungültige Voreinstellungsdaten",
            "deletePresetFailed": "Fehler beim Löschen der Voreinstellung",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "Beispielbilder {action} abgeschlossen",
            "imagesFailed": "Beispielbilder {action} fehlgeschlagen",
            "loadError": "Fehler beim Laden der Downloads: {message}",
-            "downloadError": "Download-Fehler: {message}"
+            "downloadError": "Download-Fehler: {message}",
+            "downloadStopped": "Download abgebrochen"
        },
        "import": {
            "folderTreeFailed": "Fehler beim Laden des Ordnerbaums",
@@ -1993,6 +2119,14 @@
            "updateFailed": "Fehler beim Aktualisieren der Trigger Words",
            "copyFailed": "Kopieren fehlgeschlagen"
        },
+        "undo": {
+            "action": "Rückgängig",
+            "deleted": "Gelöscht: {name}",
+            "deletedBulk": "{count} Element(e) gelöscht",
+            "expired": "Undo-Fenster abgelaufen. Das Element wurde endgültig gelöscht.",
+            "failed": "Rückgängig machen fehlgeschlagen: {error}",
+            "restored": "Element wiederhergestellt"
+        },
        "virtual": {
            "loadFailed": "Fehler beim Laden der Elemente",
            "loadMoreFailed": "Fehler beim Laden weiterer Elemente",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "Fehler beim Setzen der Inhaltsbewertung: {message}",
            "relinkSuccess": "Modell erfolgreich mit Civitai neu verknüpft",
            "relinkFailed": "Fehler: {message}",
+            "linkHfSuccess": "Modell erfolgreich mit HuggingFace verknüpft",
+            "linkHfFailed": "Fehler: {message}",
            "fetchMetadataFirst": "Bitte rufen Sie zuerst Metadaten von CivitAI ab",
            "noCivitaiInfo": "Keine CivitAI-Informationen verfügbar",
            "missingHash": "Modell-Hash nicht verfügbar"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "In die Zwischenablage kopiert",
            "downloadStarted": "Download gestartet"
+        },
+        "agent": {
+            "llmNotConfigured": "KI-Anbieter nicht konfiguriert. Aktivieren Sie ihn unter Einstellungen → KI-Anbieter.",
+            "enrichStarted": "Metadaten werden mit KI angereichert...",
+            "enrichComplete": "Metadatenanreicherung abgeschlossen: {{summary}}",
+            "enrichFailed": "Metadatenanreicherung fehlgeschlagen: {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "Reparación cancelada. {count} recetas fueron reparadas.",
            "error": "Error al reparar recetas: {message}"
        },
+        "rematchRecipes": {
+            "label": "Reasociar recetas con modelos locales",
+            "loading": "Reasociando recetas con modelos locales...",
+            "success": "{entries} entradas asociadas en {recipes} recetas",
+            "successErrors": "{entries} entradas asociadas en {recipes} recetas, {failures} fallidas",
+            "allFailed": "Falló la reasociación de {failures} de {total} recetas",
+            "noMatch": "No se encontró coincidencia local para {entries} entradas en {recipes} recetas",
+            "cancelled": "Reasociación cancelada. {recipes} recetas actualizadas ({entries} entradas)",
+            "error": "Falló la reasociación de recetas: {message}"
+        },
        "manageExcludedModels": {
            "label": "Gestionar modelos excluidos"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "Nombre del preajuste...",
            "baseModel": "Modelo base",
            "baseModelSearchPlaceholder": "Buscar modelos base...",
-            "modelTags": "Etiquetas (Top 20)",
+            "modelTags": "Etiquetas",
            "modelTypes": "Tipos de modelos",
            "license": "Licencia",
            "noCreditRequired": "Sin crédito requerido",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "Permitir la venta de imágenes generadas",
            "noCreditRequiredTooltip": "Usar el modelo sin atribuir al creador",
            "noTags": "Sin etiquetas",
+            "tagSearchPlaceholder": "Buscar etiquetas...",
+            "noTagMatches": "Ninguna etiqueta coincide con la búsqueda actual.",
            "autoTags": "Etiquetas automáticas",
            "noBaseModelMatches": "Ningún modelo base coincide con la búsqueda actual.",
            "clearAll": "Limpiar todos los filtros",
@@ -447,6 +459,12 @@
                "compact": "7 (1080p), 8 (2K), 10 (4K)"
            },
            "displayDensityWarning": "Advertencia: Densidades más altas pueden causar problemas de rendimiento en sistemas con recursos limitados.",
+            "recipesLayout": "Diseño de recetas",
+            "recipesLayoutHelp": "Elige cómo se organizan las tarjetas de recetas: una cuadrícula uniforme o un diseño masonry (estilo Pinterest) que conserva la proporción de aspecto de cada imagen.",
+            "recipesLayoutOptions": {
+                "grid": "Cuadrícula",
+                "masonry": "Masonry"
+            },
            "showFolderSidebar": "Mostrar barra lateral de carpetas",
            "showFolderSidebarHelp": "Activa o desactiva la barra lateral de navegación de carpetas en las páginas de modelos. Cuando está desactivada, la barra lateral y el área de desplazamiento permanecen ocultas.",
            "cardInfoDisplay": "Visualización de información de tarjeta",
@@ -505,7 +523,9 @@
            "saveSuccess": "Rutas de carpetas adicionales actualizadas. Se requiere reinicio para aplicar los cambios.",
            "saveError": "Error al actualizar las rutas de carpetas adicionales: {message}",
            "validation": {
-                "duplicatePath": "Esta ruta ya está configurada"
+                "duplicatePath": "Esta ruta ya está configurada",
+                "checkpointUnetOverlap": "No se puede usar la misma ruta para checkpoints y modelos de difusión: {paths}",
+                "checkpointUnetOverlapInline": "Esta ruta ya se usa para otro tipo de modelo. Use carpetas separadas para checkpoints y modelos de difusión."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "Preparando descarga...",
            "connecting": "Conectando al servidor de descarga...",
            "completed": "Completado",
-            "downloadComplete": "Descarga completada exitosamente"
+            "downloadComplete": "Descarga completada exitosamente",
+            "enableCivarchiveApi": "Habilitar CivArchive API como proveedor de metadatos",
+            "enableCivarchiveApiHelp": "Al activarlo, la API de CivArchive se usa como fuente alternativa de metadatos de modelos (p. ej. para modelos eliminados de CivitAI). Desactívelo para evitar por completo los límites de velocidad de CivArchive.",
+            "providerOrder": "Orden de proveedores de metadatos de respaldo",
+            "providerOrderHelp": "La API de CivitAI siempre se intenta primero. Elija el orden de los demás proveedores al buscar metadatos.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "Habilitar proxy a nivel de aplicación",
@@ -657,6 +683,33 @@
            "proxyPassword": "Contraseña (opcional)",
            "proxyPasswordPlaceholder": "contraseña",
            "proxyPasswordHelp": "Contraseña para autenticación de proxy (si es necesario)"
+        },
+        "aiProvider": {
+            "title": "Proveedor de IA",
+            "provider": "Proveedor",
+            "providerHelp": "Elija su proveedor de LLM. OpenAI y Ollama usan endpoints predefinidos. Personalizado le permite especificar cualquier endpoint compatible con OpenAI.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (local)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "Personalizado (compatible con OpenAI)"
+            },
+            "apiBase": "URL base de la API",
+            "apiBaseHelp": "La URL base para la API LLM (p.ej. https://api.openai.com/v1). Déjelo vacío para usar el valor predeterminado del proveedor.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "Clave de API",
+            "apiKeyHelp": "Su clave de API del proveedor LLM. Se almacena localmente y nunca se envía a ningún servidor excepto a su proveedor LLM elegido.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "No configurada",
+            "apiKeyConfigured": "Configurada",
+            "apiKeySet": "Configurar",
+            "model": "Modelo",
+            "modelHelp": "El nombre del modelo a usar (p.ej. deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). Consulte a su proveedor para ver los modelos disponibles.",
+            "modelPlaceholder": "Seleccionar un modelo..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "Versiones locales",
                "versionsCountDesc": "Más versiones primero",
                "versionsCountAsc": "Menos versiones primero",
-                "versionIdDesc": "Versión más nueva primero"
+                "versionIdDesc": "Versión más nueva primero",
+                "random": "Aleatorio",
+                "randomAction": "Aleatorizar (barajar)"
            },
            "refresh": {
                "title": "Actualizar lista de modelos",
@@ -723,6 +778,7 @@
            "copyAll": "Copiar toda la sintaxis",
            "refreshAll": "Actualizar todos los metadatos",
            "repairMetadata": "Reparar metadatos de la selección",
+            "rematchMetadata": "Reasociar los seleccionados con modelos locales",
            "reimportMetadata": "Reimportar desde origen",
            "checkUpdates": "Comprobar actualizaciones para la selección",
            "moveAll": "Mover todos a carpeta",
@@ -735,6 +791,8 @@
            "deleteAll": "Eliminar seleccionados",
            "downloadMissingLoras": "Descargar LoRAs faltantes",
            "downloadExamples": "Descargar imágenes de ejemplo",
+            "downloadMissingExamples": "Descargar faltantes",
+            "reprocessExamples": "Reprocesar todo",
            "clear": "Limpiar selección",
            "skipMetadataRefreshCount": "Omitir（{count} modelos）",
            "resumeMetadataRefreshCount": "Reanudar（{count} modelos）",
@@ -754,12 +812,15 @@
                "completed": "Completado: {success} movidos, {skipped} omitidos, {failures} fallidos",
                "complete": "Auto-organización completada",
                "error": "Error: {error}"
-            }
+            },
+            "enrichHfAgent": "Enriquecer metadatos HF (IA)"
        },
        "contextMenu": {
            "refreshMetadata": "Actualizar datos de Civitai",
            "checkUpdates": "Comprobar actualizaciones",
-            "relinkCivitai": "Re-vincular a Civitai",
+            "linkModel": "Vincular modelo",
+            "linkCivitai": "Re-vincular a Civitai",
+            "linkHuggingFace": "Vincular a HuggingFace",
            "copySyntax": "Copiar sintaxis de LoRA",
            "copyFilename": "Copiar nombre de archivo del modelo",
            "copyRecipeSyntax": "Copiar sintaxis de receta",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "Enviar al flujo de trabajo (Reemplazar)",
            "openExamples": "Abrir carpeta de ejemplos",
            "downloadExamples": "Descargar imágenes de ejemplo",
+            "downloadMissingExamples": "Descargar faltantes",
+            "reprocessExamples": "Reprocesar todo",
            "replacePreview": "Reemplazar vista previa",
            "setContentRating": "Establecer clasificación de contenido",
            "moveToFolder": "Mover a carpeta",
            "repairMetadata": "Reparar metadatos",
+            "rematchMetadata": "Reasociar con modelos locales",
            "reimportMetadata": "Reimportar desde origen",
            "excludeModel": "Excluir modelo",
            "restoreModel": "Restaurar modelo",
@@ -778,7 +842,8 @@
            "shareRecipe": "Compartir receta",
            "viewAllLoras": "Ver todos los LoRAs",
            "downloadMissingLoras": "Descargar LoRAs faltantes",
-            "deleteRecipe": "Eliminar receta"
+            "deleteRecipe": "Eliminar receta",
+            "enrichHfAgent": "Enriquecer metadatos HF (IA)"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "Se encontraron {count} grupos de duplicados",
+            "noGroups": "No se encontraron grupos de duplicados con el criterio de coincidencia actual",
            "keepLatest": "Mantener versiones más recientes",
-            "deleteSelected": "Eliminar seleccionados"
+            "deleteSelected": "Eliminar seleccionados",
+            "includePromptLabel": "Incluir prompt en la coincidencia",
+            "basis": {
+                "loraCombo": "Coincidencia por: combinación de LoRA",
+                "loraComboAndPrompt": "Coincidencia por: combinación de LoRA + prompt",
+                "hintLoraCombo": "Se agrupan las recetas con los mismos LoRAs y las mismas intensidades.",
+                "hintPromptIncluded": "Las recetas solo se agrupan cuando usan los mismos LoRAs con intensidades idénticas Y tienen el mismo prompt."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "Preparando descarga...",
                "downloadedPreview": "Imagen de vista previa descargada",
                "downloadingFile": "Descargando archivo de {type}",
-                "finalizing": "Finalizando descarga..."
+                "finalizing": "Finalizando descarga...",
+                "cancelling": "Cancelando descarga...",
+                "cancelled": "Descarga cancelada"
            },
            "progress": {
                "currentFile": "Archivo actual:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "Libera {size}",
            "title": "Eliminar modelo",
-            "message": "¿Estás seguro de que quieres eliminar este modelo y todos los archivos asociados?"
+            "message": "¿Estás seguro de que quieres eliminar este modelo y todos los archivos asociados?",
+            "recoverableWarning": "El archivo se eliminará permanentemente después de 20 segundos a menos que deshaga la acción."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "Esta acción se puede deshacer durante 20 segundos."
        },
        "excludeModel": {
            "title": "Excluir modelo",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "Escribe la ruta de la carpeta o selecciona del árbol de abajo...",
            "root": "Raíz"
        },
+        "linkHuggingFace": {
+            "title": "Vincular a HuggingFace",
+            "infoText": "Pegue la URL del repositorio de HuggingFace para asociar este modelo. Esto permite el enriquecimiento de metadatos con IA.",
+            "urlLabel": "URL del repositorio de HuggingFace:",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "Ingrese la URL completa del repositorio de HuggingFace.",
+            "confirmAction": "Guardar y vincular"
+        },
        "relinkCivitai": {
            "title": "Re-vincular a Civitai",
            "warning": "Advertencia:",
@@ -1498,6 +1586,7 @@
                "empty": "Aún no hay historial de versiones para este modelo.",
                "error": "No se pudieron cargar las versiones.",
                "missingModelId": "Este modelo no tiene un ID de modelo de Civitai.",
+                "hfGroupInfo": "Este es un grupo de modelos de HuggingFace. Abra la biblioteca para ver todas las versiones en la cuadrícula.",
                "confirm": {
                    "delete": "¿Eliminar esta versión de tu biblioteca?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "Descargar CSV",
            "columnModelName": "Nombre del modelo",
            "columnError": "Error"
+        },
+        "downloadBatchSummary": {
+            "title": "Resumen de descarga por lotes",
+            "statSuccess": "Correctos",
+            "statFailed": "Fallidos",
+            "statTotal": "Total",
+            "successMessage": "Todos los {count} modelos se descargaron correctamente",
+            "completedWithErrors": "Completado con errores",
+            "failed": "Descarga fallida",
+            "failedItems": "Elementos fallidos ({count})",
+            "columnName": "Nombre del modelo",
+            "columnError": "Error",
+            "close": "Cerrar",
+            "copyReport": "Copiar informe",
+            "retryFailed": "Reintentar fallidos ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "Receta reemplazada en el flujo de trabajo",
            "recipeFailedToSend": "Error al enviar receta al flujo de trabajo",
            "noMatchingNodes": "No hay nodos compatibles disponibles en el flujo de trabajo actual",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "No se ha seleccionado ningún nodo de destino",
            "modelUpdated": "Modelo actualizado en el flujo de trabajo",
            "modelFailed": "Error al actualizar nodo de modelo",
@@ -1700,7 +1805,13 @@
        "checkingUpdates": "Comprobando actualizaciones...",
        "checkingMessage": "Por favor espera mientras comprobamos la última versión.",
        "showNotifications": "Mostrar notificaciones de actualización",
-        "latestBadge": "Último",
+        "latestBadge": "Última",
+        "latestMain": "Rama main",
+        "channel": "Canal de actualizacion",
+        "channels": {
+            "release": "Release",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "Preparando actualización...",
            "installing": "Instalando actualización...",
@@ -1721,6 +1832,15 @@
            "warning": "Advertencia: Las compilaciones nocturnas pueden contener características experimentales y podrían ser inestables.",
            "enable": "Habilitar actualizaciones nocturnas"
        },
+        "channelSwitch": {
+            "nightlyTitle": "Cambiar a canal Nightly",
+            "nightlyMessage": "Cambiar a Nightly inicializara un repositorio Git y seguira los ultimos commits de la rama main. Las actualizaciones son mas frecuentes pero pueden ser inestables. Puede volver a Release en cualquier momento.",
+            "releaseTitle": "Cambiar a canal Release",
+            "releaseMessage": "Cambiar a Release hara checkout de la ultima etiqueta de version estable. Puede volver a Nightly en cualquier momento.",
+            "switching": "Cambiando a canal {channel}...",
+            "completed": "Cambio a canal {channel} exitoso",
+            "failed": "Error al cambiar de canal"
+        },
        "banners": {
            "recent": "Notificaciones recientes",
            "empty": "No hay banners recientes.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "Reparación completa: {repaired} reparadas, {skipped} omitidas (de {total})",
            "repairBulkSkipped": "No se necesita reparación para ninguna de las {total} recetas seleccionadas",
            "repairBulkFailed": "Error al reparar las recetas seleccionadas: {message}",
+            "rematchComplete": "{entries} entradas asociadas en {recipes} recetas",
+            "rematchCompleteErrors": "{entries} entradas asociadas en {recipes} recetas, {failures} fallidas",
+            "rematchAllFailed": "Falló la reasociación de {failures} de {total} recetas seleccionadas",
+            "rematchUnmatched": "No se encontró coincidencia local para {entries} entradas en {recipes} recetas",
+            "rematchSkipped": "Ninguna de las {total} recetas seleccionadas necesita reasociación",
+            "rematchFailed": "Falló la reasociación de las recetas seleccionadas: {message}",
            "reimporting": "Reimportando receta desde origen...",
            "reimportSuccess": "Receta reimportada exitosamente",
            "reimportBulkComplete": "Reimportación completa: {completed} reimportadas, {failed} fallidas (de {total})",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "El nombre del preajuste debe tener {max} caracteres o menos",
            "presetNameInvalidChars": "El nombre del preajuste contiene caracteres inválidos",
            "presetNameExists": "Ya existe un preajuste con este nombre",
-            "maxPresetsReached": "Máximo {max} preajustes permitidos. Elimine uno para agregar más.",
            "presetNotFound": "Preajuste no encontrado",
            "invalidPreset": "Datos de preajuste inválidos",
            "deletePresetFailed": "Error al eliminar el preajuste",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "Imágenes de ejemplo {action} completadas",
            "imagesFailed": "Imágenes de ejemplo {action} fallidas",
            "loadError": "Error al cargar descargas: {message}",
-            "downloadError": "Error de descarga: {message}"
+            "downloadError": "Error de descarga: {message}",
+            "downloadStopped": "Descarga cancelada"
        },
        "import": {
            "folderTreeFailed": "Error al cargar árbol de carpetas",
@@ -1993,6 +2119,14 @@
            "updateFailed": "Error al actualizar palabras clave",
            "copyFailed": "Error al copiar"
        },
+        "undo": {
+            "action": "Deshacer",
+            "deleted": "Eliminado: {name}",
+            "deletedBulk": "{count} elemento(s) eliminado(s)",
+            "expired": "La ventana de deshacer ha caducado. El elemento se eliminó permanentemente.",
+            "failed": "No se pudo deshacer: {error}",
+            "restored": "Elemento restaurado"
+        },
        "virtual": {
            "loadFailed": "Error al cargar elementos",
            "loadMoreFailed": "Error al cargar más elementos",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "Error al establecer clasificación de contenido: {message}",
            "relinkSuccess": "Modelo re-vinculado exitosamente a Civitai",
            "relinkFailed": "Error: {message}",
+            "linkHfSuccess": "Modelo vinculado a HuggingFace exitosamente",
+            "linkHfFailed": "Error: {message}",
            "fetchMetadataFirst": "Por favor obtén metadatos de CivitAI primero",
            "noCivitaiInfo": "No hay información de CivitAI disponible",
            "missingHash": "Hash del modelo no disponible"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "Copiado al portapapeles",
            "downloadStarted": "Descarga iniciada"
+        },
+        "agent": {
+            "llmNotConfigured": "Proveedor de IA no configurado. Actívelo en Configuración → Proveedor de IA.",
+            "enrichStarted": "Enriqueciendo metadatos con IA...",
+            "enrichComplete": "Enriquecimiento de metadatos completado: {{summary}}",
+            "enrichFailed": "Enriquecimiento de metadatos fallido: {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "Réparation annulée. {count} recettes ont été réparées.",
            "error": "Échec de la réparation des recettes : {message}"
        },
+        "rematchRecipes": {
+            "label": "Réassocier les recettes aux modèles locaux",
+            "loading": "Réassociation des recettes aux modèles locaux...",
+            "success": "{entries} entrées associées dans {recipes} recettes",
+            "successErrors": "{entries} entrées associées dans {recipes} recettes, {failures} échecs",
+            "allFailed": "Échec de la réassociation de {failures} recettes sur {total}",
+            "noMatch": "Aucune correspondance locale trouvée pour {entries} entrées dans {recipes} recettes",
+            "cancelled": "Réassociation annulée. {recipes} recettes mises à jour ({entries} entrées)",
+            "error": "Échec de la réassociation des recettes : {message}"
+        },
        "manageExcludedModels": {
            "label": "Gérer les modèles exclus"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "Nom du préréglage...",
            "baseModel": "Modèle de base",
            "baseModelSearchPlaceholder": "Rechercher des modèles de base...",
-            "modelTags": "Tags (Top 20)",
+            "modelTags": "Tags",
            "modelTypes": "Types de modèles",
            "license": "Licence",
            "noCreditRequired": "Crédit non requis",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "Autoriser la vente d\"images générées",
            "noCreditRequiredTooltip": "Utiliser le modèle sans créditer le créateur",
            "noTags": "Aucun tag",
+            "tagSearchPlaceholder": "Rechercher des tags...",
+            "noTagMatches": "Aucun tag ne correspond à la recherche actuelle.",
            "autoTags": "Auto-Tags",
            "noBaseModelMatches": "Aucun modèle de base ne correspond à la recherche actuelle.",
            "clearAll": "Effacer tous les filtres",
@@ -447,6 +459,12 @@
                "compact": "7 (1080p), 8 (2K), 10 (4K)"
            },
            "displayDensityWarning": "Attention : Des densités plus élevées peuvent causer des problèmes de performance sur les systèmes avec des ressources limitées.",
+            "recipesLayout": "Disposition des recettes",
+            "recipesLayoutHelp": "Choisissez comment les cartes de recettes sont organisées : une grille uniforme ou une disposition masonry (style Pinterest) qui préserve le rapport d'aspect de chaque image.",
+            "recipesLayoutOptions": {
+                "grid": "Grille",
+                "masonry": "Masonry"
+            },
            "showFolderSidebar": "Afficher la barre latérale des dossiers",
            "showFolderSidebarHelp": "Activez ou désactivez la barre latérale de navigation des dossiers sur les pages de modèles. Lorsqu'elle est désactivée, la barre latérale et la zone de survol restent masquées.",
            "cardInfoDisplay": "Affichage des informations de carte",
@@ -505,7 +523,9 @@
            "saveSuccess": "Chemins de dossiers supplémentaires mis à jour. Redémarrage requis pour appliquer les changements.",
            "saveError": "Échec de la mise à jour des chemins de dossiers supplémentaires: {message}",
            "validation": {
-                "duplicatePath": "Ce chemin est déjà configuré"
+                "duplicatePath": "Ce chemin est déjà configuré",
+                "checkpointUnetOverlap": "Impossible d'utiliser le même chemin pour les checkpoints et les modèles de diffusion : {paths}",
+                "checkpointUnetOverlapInline": "Ce chemin est déjà utilisé pour un autre type de modèle. Utilisez des dossiers séparés pour les checkpoints et les modèles de diffusion."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "Préparation du téléchargement...",
            "connecting": "Connexion au serveur de téléchargement...",
            "completed": "Terminé",
-            "downloadComplete": "Téléchargement terminé avec succès"
+            "downloadComplete": "Téléchargement terminé avec succès",
+            "enableCivarchiveApi": "Activer l'API CivArchive comme fournisseur de métadonnées",
+            "enableCivarchiveApiHelp": "Lorsqu'elle est activée, l'API CivArchive est utilisée comme source de secours pour les métadonnées des modèles (par ex. pour les modèles supprimés de CivitAI). Désactivez pour éviter entièrement les limites de débit de CivArchive.",
+            "providerOrder": "Ordre de secours des fournisseurs de métadonnées",
+            "providerOrderHelp": "L'API CivitAI est toujours essayée en premier. Choisissez l'ordre des autres fournisseurs lors de la recherche de métadonnées.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "Activer le proxy au niveau de l'application",
@@ -657,6 +683,33 @@
            "proxyPassword": "Mot de passe (optionnel)",
            "proxyPasswordPlaceholder": "mot_de_passe",
            "proxyPasswordHelp": "Mot de passe pour l'authentification proxy (si nécessaire)"
+        },
+        "aiProvider": {
+            "title": "Fournisseur d'IA",
+            "provider": "Fournisseur",
+            "providerHelp": "Choisissez votre fournisseur LLM. OpenAI et Ollama utilisent des endpoints prédéfinis. Personnalisé vous permet de spécifier n'importe quel endpoint compatible OpenAI.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (local)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "Personnalisé (compatible OpenAI)"
+            },
+            "apiBase": "URL de base de l'API",
+            "apiBaseHelp": "L'URL de base pour l'API LLM (ex. https://api.openai.com/v1). Laissez vide pour utiliser le fournisseur par défaut.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "Clé API",
+            "apiKeyHelp": "Votre clé API du fournisseur LLM. Stockée localement, jamais envoyée à un serveur autre que votre fournisseur LLM choisi.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "Non définie",
+            "apiKeyConfigured": "Configurée",
+            "apiKeySet": "Configurer",
+            "model": "Modèle",
+            "modelHelp": "Le nom du modèle à utiliser (ex. deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). Consultez votre fournisseur pour les modèles disponibles.",
+            "modelPlaceholder": "Sélectionner un modèle..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "Versions locales",
                "versionsCountDesc": "Plus de versions d'abord",
                "versionsCountAsc": "Moins de versions d'abord",
-                "versionIdDesc": "Version la plus récente d'abord"
+                "versionIdDesc": "Version la plus récente d'abord",
+                "random": "Aléatoire",
+                "randomAction": "Aléatoire (mélanger)"
            },
            "refresh": {
                "title": "Actualiser la liste des modèles",
@@ -723,6 +778,7 @@
            "copyAll": "Copier toute la syntaxe",
            "refreshAll": "Actualiser toutes les métadonnées",
            "repairMetadata": "Réparer les métadonnées de la sélection",
+            "rematchMetadata": "Réassocier la sélection aux modèles locaux",
            "reimportMetadata": "Ré-importer depuis la source",
            "checkUpdates": "Vérifier les mises à jour pour la sélection",
            "moveAll": "Déplacer tout vers un dossier",
@@ -735,6 +791,8 @@
            "deleteAll": "Supprimer la sélection",
            "downloadMissingLoras": "Télécharger les LoRAs manquants",
            "downloadExamples": "Télécharger les images d'exemple",
+            "downloadMissingExamples": "Télécharger les manquantes",
+            "reprocessExamples": "Tout retraiter",
            "clear": "Effacer la sélection",
            "skipMetadataRefreshCount": "Ignorer（{count} modèles）",
            "resumeMetadataRefreshCount": "Reprendre（{count} modèles）",
@@ -754,12 +812,15 @@
                "completed": "Terminé : {success} déplacés, {skipped} ignorés, {failures} échecs",
                "complete": "Auto-organisation terminée",
                "error": "Erreur : {error}"
-            }
+            },
+            "enrichHfAgent": "Enrichir les métadonnées HF (IA)"
        },
        "contextMenu": {
            "refreshMetadata": "Actualiser les données Civitai",
            "checkUpdates": "Vérifier les mises à jour",
-            "relinkCivitai": "Relier à nouveau à Civitai",
+            "linkModel": "Lier le modèle",
+            "linkCivitai": "Relier à nouveau à Civitai",
+            "linkHuggingFace": "Lier à HuggingFace",
            "copySyntax": "Copier la syntaxe LoRA",
            "copyFilename": "Copier le nom de fichier du modèle",
            "copyRecipeSyntax": "Copier la syntaxe de la recipe",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "Envoyer vers le workflow (Remplacer)",
            "openExamples": "Ouvrir le dossier d'exemples",
            "downloadExamples": "Télécharger les images d'exemple",
+            "downloadMissingExamples": "Télécharger les manquantes",
+            "reprocessExamples": "Tout retraiter",
            "replacePreview": "Remplacer l'aperçu",
            "setContentRating": "Définir la classification du contenu",
            "moveToFolder": "Déplacer vers un dossier",
            "repairMetadata": "Réparer les métadonnées",
+            "rematchMetadata": "Réassocier aux modèles locaux",
            "reimportMetadata": "Ré-importer depuis la source",
            "excludeModel": "Exclure le modèle",
            "restoreModel": "Restaurer le modèle",
@@ -778,7 +842,8 @@
            "shareRecipe": "Partager la recipe",
            "viewAllLoras": "Voir tous les LoRAs",
            "downloadMissingLoras": "Télécharger les LoRAs manquants",
-            "deleteRecipe": "Supprimer la recipe"
+            "deleteRecipe": "Supprimer la recipe",
+            "enrichHfAgent": "Enrichir les métadonnées HF (IA)"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "Trouvé {count} groupes de doublons",
+            "noGroups": "Aucun groupe de doublons trouvé avec le critère de correspondance actuel",
            "keepLatest": "Garder les dernières versions",
-            "deleteSelected": "Supprimer la sélection"
+            "deleteSelected": "Supprimer la sélection",
+            "includePromptLabel": "Inclure le prompt dans la correspondance",
+            "basis": {
+                "loraCombo": "Correspondance : combinaison de LoRA",
+                "loraComboAndPrompt": "Correspondance : combinaison de LoRA + prompt",
+                "hintLoraCombo": "Les recettes avec les mêmes LoRAs et des forces identiques sont regroupées.",
+                "hintPromptIncluded": "Les recettes ne sont regroupées que si elles utilisent les mêmes LoRAs avec des forces identiques ET ont le même prompt."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "Préparation du téléchargement...",
                "downloadedPreview": "Image d'aperçu téléchargée",
                "downloadingFile": "Téléchargement du fichier {type}",
-                "finalizing": "Finalisation du téléchargement..."
+                "finalizing": "Finalisation du téléchargement...",
+                "cancelling": "Annulation du téléchargement...",
+                "cancelled": "Téléchargement annulé"
            },
            "progress": {
                "currentFile": "Fichier actuel :",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "Libère {size}",
            "title": "Supprimer le modèle",
-            "message": "Êtes-vous sûr de vouloir supprimer ce modèle et tous les fichiers associés ?"
+            "message": "Êtes-vous sûr de vouloir supprimer ce modèle et tous les fichiers associés ?",
+            "recoverableWarning": "Le fichier sera définitivement supprimé après 20 secondes, sauf si vous annulez."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "Cette action peut être annulée pendant 20 secondes."
        },
        "excludeModel": {
            "title": "Exclure le modèle",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "Tapez le chemin du dossier ou sélectionnez dans l'arbre ci-dessous...",
            "root": "Racine"
        },
+        "linkHuggingFace": {
+            "title": "Lier à HuggingFace",
+            "infoText": "Collez l'URL du dépôt HuggingFace pour associer ce modèle à sa source. Cela permet l'enrichissement des métadonnées par IA.",
+            "urlLabel": "URL du dépôt HuggingFace :",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "Entrez l'URL complète du dépôt HuggingFace.",
+            "confirmAction": "Enregistrer & lier"
+        },
        "relinkCivitai": {
            "title": "Relier à nouveau à Civitai",
            "warning": "Attention :",
@@ -1498,6 +1586,7 @@
                "empty": "Aucun historique de versions n'est disponible pour ce modèle pour le moment.",
                "error": "Échec du chargement des versions.",
                "missingModelId": "Ce modèle ne possède pas d'identifiant de modèle Civitai.",
+                "hfGroupInfo": "Ceci est un groupe de modèles HuggingFace. Ouvrez la bibliothèque pour voir toutes les versions dans la grille.",
                "confirm": {
                    "delete": "Supprimer cette version de votre bibliothèque ?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "Télécharger CSV",
            "columnModelName": "Nom du modèle",
            "columnError": "Erreur"
+        },
+        "downloadBatchSummary": {
+            "title": "Résumé du téléchargement groupé",
+            "statSuccess": "Réussis",
+            "statFailed": "Échoués",
+            "statTotal": "Total",
+            "successMessage": "Les {count} modèles ont été téléchargés avec succès",
+            "completedWithErrors": "Terminé avec des erreurs",
+            "failed": "Échec du téléchargement",
+            "failedItems": "Éléments échoués ({count})",
+            "columnName": "Nom du modèle",
+            "columnError": "Erreur",
+            "close": "Fermer",
+            "copyReport": "Copier le rapport",
+            "retryFailed": "Réessayer les échecs ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "Recipe remplacée dans le workflow",
            "recipeFailedToSend": "Échec de l'envoi de la recipe au workflow",
            "noMatchingNodes": "Aucun nœud compatible disponible dans le workflow actuel",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "Aucun nœud cible sélectionné",
            "modelUpdated": "Modèle mis à jour dans le workflow",
            "modelFailed": "Échec de la mise à jour du nœud modèle",
@@ -1700,7 +1805,13 @@
        "checkingUpdates": "Vérification des mises à jour...",
        "checkingMessage": "Veuillez patienter pendant la vérification de la dernière version.",
        "showNotifications": "Afficher les notifications de mise à jour",
-        "latestBadge": "Dernier",
+        "latestBadge": "Dernière",
+        "latestMain": "Branche main",
+        "channel": "Canal de mise a jour",
+        "channels": {
+            "release": "Release",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "Préparation de la mise à jour...",
            "installing": "Installation de la mise à jour...",
@@ -1721,6 +1832,15 @@
            "warning": "Attention : Les versions nightly peuvent contenir des fonctionnalités expérimentales et être instables.",
            "enable": "Activer les mises à jour nightly"
        },
+        "channelSwitch": {
+            "nightlyTitle": "Passer au canal Nightly",
+            "nightlyMessage": "Passer a Nightly initialisera un depot Git et suivra les derniers commits de la branche main. Les mises a jour sont plus frequentes mais peuvent etre instables. Vous pouvez revenir a Release a tout moment.",
+            "releaseTitle": "Passer au canal Release",
+            "releaseMessage": "Passer a Release passera au dernier tag de version stable. Vous pouvez revenir a Nightly a tout moment.",
+            "switching": "Passage au canal {channel}...",
+            "completed": "Basculement vers le canal {channel} reussi",
+            "failed": "Echec du changement de canal"
+        },
        "banners": {
            "recent": "Messages récents",
            "empty": "Aucune bannière récente.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "Réparation terminée : {repaired} réparée(s), {skipped} ignorée(s) (sur {total})",
            "repairBulkSkipped": "Aucune réparation nécessaire parmi les {total} recettes sélectionnées",
            "repairBulkFailed": "Échec de la réparation des recettes sélectionnées : {message}",
+            "rematchComplete": "{entries} entrées associées dans {recipes} recettes",
+            "rematchCompleteErrors": "{entries} entrées associées dans {recipes} recettes, {failures} échecs",
+            "rematchAllFailed": "Échec de la réassociation de {failures} recettes sélectionnées sur {total}",
+            "rematchUnmatched": "Aucune correspondance locale trouvée pour {entries} entrées dans {recipes} recettes",
+            "rematchSkipped": "Aucune des {total} recettes sélectionnées ne nécessite de réassociation",
+            "rematchFailed": "Échec de la réassociation des recettes sélectionnées : {message}",
            "reimporting": "Ré-import de la recette depuis la source...",
            "reimportSuccess": "Recette ré-importée avec succès",
            "reimportBulkComplete": "Ré-import terminé : {completed} ré-importé(s), {failed} échec(s) (sur {total})",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "Le nom du préréglage doit contenir au maximum {max} caractères",
            "presetNameInvalidChars": "Le nom du préréglage contient des caractères invalides",
            "presetNameExists": "Un préréglage avec ce nom existe déjà",
-            "maxPresetsReached": "Maximum {max} préréglages autorisés. Supprimez-en un pour en ajouter plus.",
            "presetNotFound": "Préréglage non trouvé",
            "invalidPreset": "Données de préréglage invalides",
            "deletePresetFailed": "Échec de la suppression du préréglage",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "Images d'exemple {action} terminées",
            "imagesFailed": "Images d'exemple {action} échouées",
            "loadError": "Erreur lors du chargement des téléchargements : {message}",
-            "downloadError": "Erreur de téléchargement : {message}"
+            "downloadError": "Erreur de téléchargement : {message}",
+            "downloadStopped": "Téléchargement annulé"
        },
        "import": {
            "folderTreeFailed": "Échec du chargement de l'arborescence des dossiers",
@@ -1993,6 +2119,14 @@
            "updateFailed": "Échec de la mise à jour des mots-clés",
            "copyFailed": "Échec de la copie"
        },
+        "undo": {
+            "action": "Annuler",
+            "deleted": "Supprimé : {name}",
+            "deletedBulk": "{count} élément(s) supprimé(s)",
+            "expired": "La fenêtre d'annulation a expiré. L'élément a été définitivement supprimé.",
+            "failed": "Échec de l'annulation : {error}",
+            "restored": "Élément restauré"
+        },
        "virtual": {
            "loadFailed": "Échec du chargement des éléments",
            "loadMoreFailed": "Échec du chargement de plus d'éléments",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "Échec de la définition de la classification du contenu : {message}",
            "relinkSuccess": "Modèle relié à Civitai avec succès",
            "relinkFailed": "Erreur : {message}",
+            "linkHfSuccess": "Modèle lié à HuggingFace avec succès",
+            "linkHfFailed": "Erreur : {message}",
            "fetchMetadataFirst": "Veuillez d'abord récupérer les métadonnées depuis CivitAI",
            "noCivitaiInfo": "Aucune information CivitAI disponible",
            "missingHash": "Hash du modèle non disponible"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "Copié dans le presse-papiers",
            "downloadStarted": "Téléchargement démarré"
+        },
+        "agent": {
+            "llmNotConfigured": "Fournisseur d'IA non configuré. Activez-le dans Paramètres → Fournisseur d'IA.",
+            "enrichStarted": "Enrichissement des métadonnées par IA...",
+            "enrichComplete": "Enrichissement des métadonnées terminé : {{summary}}",
+            "enrichFailed": "Échec de l'enrichissement des métadonnées : {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "תיקון בוטל. {count} מתכונים תוקנו.",
            "error": "תיקון המתכונים נכשל: {message}"
        },
+        "rematchRecipes": {
+            "label": "התאמה מחדש של מתכונים למודלים מקומיים",
+            "loading": "מתבצעת התאמה מחדש של מתכונים למודלים מקומיים...",
+            "success": "הותאמו {entries} פריטים ב־{recipes} מתכונים",
+            "successErrors": "הותאמו {entries} פריטים ב־{recipes} מתכונים, {failures} נכשלו",
+            "allFailed": "ההתאמה נכשלה עבור {failures} מתוך {total} מתכונים",
+            "noMatch": "לא נמצאה התאמה מקומית עבור {entries} פריטים ב־{recipes} מתכונים",
+            "cancelled": "ההתאמה בוטלה. עודכנו {recipes} מתכונים ({entries} פריטים)",
+            "error": "ההתאמה מחדש של המתכונים נכשלה: {message}"
+        },
        "manageExcludedModels": {
            "label": "ניהול מודלים מוחרגים"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "שם קביעה מראש...",
            "baseModel": "מודל בסיס",
            "baseModelSearchPlaceholder": "חפש מודלי בסיס...",
-            "modelTags": "תגיות (20 המובילות)",
+            "modelTags": "תגיות",
            "modelTypes": "סוגי מודלים",
            "license": "רישיון",
            "noCreditRequired": "ללא קרדיט נדרש",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "אפשר מכירת תמונות שנוצרו",
            "noCreditRequiredTooltip": "שימוש במודל ללא מתן קרדיט ליוצר",
            "noTags": "ללא תגיות",
+            "tagSearchPlaceholder": "חיפוש תגיות...",
+            "noTagMatches": "אין תגיות שתואמות את החיפוש הנוכחי.",
            "autoTags": "תגיות אוטומטיות",
            "noBaseModelMatches": "אין מודלי בסיס התואמים לחיפוש הנוכחי.",
            "clearAll": "נקה את כל המסננים",
@@ -447,6 +459,12 @@
                "compact": "7 (1080p), 8 (2K), 10 (4K)"
            },
            "displayDensityWarning": "אזהרה: צפיפויות גבוהות יותר עלולות לגרום לבעיות ביצועים במערכות עם משאבים מוגבלים.",
+            "recipesLayout": "פריסת מתכונים",
+            "recipesLayoutHelp": "בחר כיצד יסודרו כרטיסי המתכונים: רשת אחידה או פריסת Masonry (בסגנון Pinterest) השומרת על יחס הגובה-רוחב של כל תמונה.",
+            "recipesLayoutOptions": {
+                "grid": "רשת",
+                "masonry": "Masonry"
+            },
            "showFolderSidebar": "הצג סרגל צד תיקיות",
            "showFolderSidebarHelp": "הפעל או כבה את סרגל הצד לניווט תיקיות בדפי המודל. כאשר הוא כבוי, סרגל הצד ואזור הריחוף נשארים מוסתרים.",
            "cardInfoDisplay": "תצוגת מידע בכרטיס",
@@ -505,7 +523,9 @@
            "saveSuccess": "נתיבי תיקיות נוספים עודכנו. נדרשת הפעלה מחדש כדי להחיל את השינויים.",
            "saveError": "נכשל בעדכון נתיבי תיקיות נוספים: {message}",
            "validation": {
-                "duplicatePath": "נתיב זה כבר מוגדר"
+                "duplicatePath": "נתיב זה כבר מוגדר",
+                "checkpointUnetOverlap": "לא ניתן להשתמש באותו נתיב עבור checkpoints ומודלי דיפוזיה: {paths}",
+                "checkpointUnetOverlapInline": "הנתיב הזה כבר נמצא בשימוש עבור סוג מודל אחר. יש להשתמש בתיקיות נפרדות עבור checkpoints ומודלי דיפוזיה."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "מכין הורדה...",
            "connecting": "מתחבר לשרת ההורדות...",
            "completed": "הושלם",
-            "downloadComplete": "ההורדה הושלמה בהצלחה"
+            "downloadComplete": "ההורדה הושלמה בהצלחה",
+            "enableCivarchiveApi": "הפעל את CivArchive API כספק מטא-נתונים",
+            "enableCivarchiveApiHelp": "כאשר מופעל, CivArchive API משמש כמקור גיבוי למטא-נתונים של מודלים (למשל עבור מודלים שנמחקו מ-CivitAI). כבה כדי להימנע לחלוטין ממגבלות הקצב של CivArchive.",
+            "providerOrder": "סדר ספקי מטא-נתונים לגיבוי",
+            "providerOrderHelp": "CivitAI API תמיד מנוסה ראשון. בחר את סדר הספקים הנותרים בעת חיפוש מטא-נתונים.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "הפעל פרוקסי ברמת האפליקציה",
@@ -657,6 +683,33 @@
            "proxyPassword": "סיסמה (אופציונלי)",
            "proxyPasswordPlaceholder": "password",
            "proxyPasswordHelp": "סיסמה לאימות מול הפרוקסי (אם נדרש)"
+        },
+        "aiProvider": {
+            "title": "ספק AI",
+            "provider": "ספק",
+            "providerHelp": "בחר את ספק ה-LLM שלך. OpenAI ו-Ollama משתמשים בנקודות קצה מוגדרות מראש. מותאם אישית מאפשר לך לציין כל נקודת קצה תואמת OpenAI.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (מקומי)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "מותאם אישית (תואם OpenAI)"
+            },
+            "apiBase": "כתובת בסיס API",
+            "apiBaseHelp": "כתובת ה-URL הבסיסית ל-API של LLM (לדוגמה https://api.openai.com/v1). השאר ריק לשימוש בברירת המחדל של הספק.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "מפתח API",
+            "apiKeyHelp": "מפתח ה-API של ספק ה-LLM שלך. נשמר מקומית, לעולם לא נשלח לשרת כלשהו מלבד ספק ה-LLM שבחרת.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "לא הוגדר",
+            "apiKeyConfigured": "הוגדר",
+            "apiKeySet": "הגדר",
+            "model": "מודל",
+            "modelHelp": "שם המודל לשימוש (לדוגמה deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). בדוק אצל הספק שלך אילו מודלים זמינים.",
+            "modelPlaceholder": "בחר מודל..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "גרסאות מקומיות",
                "versionsCountDesc": "הכי הרבה גרסאות ראשונות",
                "versionsCountAsc": "הכי מעט גרסאות ראשונות",
-                "versionIdDesc": "גרסה חדשה ביותר ראשונה"
+                "versionIdDesc": "גרסה חדשה ביותר ראשונה",
+                "random": "אקראי",
+                "randomAction": "ערבוב אקראי"
            },
            "refresh": {
                "title": "רענן רשימת מודלים",
@@ -723,6 +778,7 @@
            "copyAll": "העתק את כל התחבירים",
            "refreshAll": "רענן את כל המטא-דאטה",
            "repairMetadata": "תקן מטא-דאטה עבור הנבחרים",
+            "rematchMetadata": "התאמה מחדש של הנבחרים למודלים מקומיים",
            "reimportMetadata": "ייבא מחדש ממקור",
            "checkUpdates": "בדוק עדכונים לבחירה",
            "moveAll": "העבר הכל לתיקייה",
@@ -735,6 +791,8 @@
            "deleteAll": "מחק נבחרים",
            "downloadMissingLoras": "הורדת LoRAs חסרים",
            "downloadExamples": "הורד תמונות דוגמה",
+            "downloadMissingExamples": "הורדת חסרים",
+            "reprocessExamples": "עיבוד מחדש של הכול",
            "clear": "נקה בחירה",
            "skipMetadataRefreshCount": "דילוג（{count} מודלים）",
            "resumeMetadataRefreshCount": "המשך（{count} מודלים）",
@@ -754,12 +812,15 @@
                "completed": "הושלם: {success} הועברו, {skipped} דולגו, {failures} נכשלו",
                "complete": "ארגון אוטומטי הושלם",
                "error": "שגיאה: {error}"
-            }
+            },
+            "enrichHfAgent": "העשרת HF מטא-דאטה (AI)"
        },
        "contextMenu": {
            "refreshMetadata": "רענן נתוני Civitai",
            "checkUpdates": "בדוק עדכונים",
-            "relinkCivitai": "קשר מחדש ל-Civitai",
+            "linkModel": "קישור מודל",
+            "linkCivitai": "קשר מחדש ל-Civitai",
+            "linkHuggingFace": "קישור ל-HuggingFace",
            "copySyntax": "העתק תחביר LoRA",
            "copyFilename": "העתק שם קובץ מודל",
            "copyRecipeSyntax": "העתק תחביר מתכון",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "שלח ל-Workflow (החלף)",
            "openExamples": "פתח תיקיית דוגמאות",
            "downloadExamples": "הורד תמונות דוגמה",
+            "downloadMissingExamples": "הורדת חסרים",
+            "reprocessExamples": "עיבוד מחדש של הכול",
            "replacePreview": "החלף תצוגה מקדימה",
            "setContentRating": "הגדר דירוג תוכן",
            "moveToFolder": "העבר לתיקייה",
            "repairMetadata": "תיקון מטא-דאטה",
+            "rematchMetadata": "התאמה מחדש למודלים מקומיים",
            "reimportMetadata": "ייבא מחדש ממקור",
            "excludeModel": "החרג מודל",
            "restoreModel": "שחזור מודל",
@@ -778,7 +842,8 @@
            "shareRecipe": "שתף מתכון",
            "viewAllLoras": "הצג את כל ה-LoRAs",
            "downloadMissingLoras": "הורד LoRAs חסרים",
-            "deleteRecipe": "מחק מתכון"
+            "deleteRecipe": "מחק מתכון",
+            "enrichHfAgent": "העשרת HF מטא-דאטה (AI)"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "נמצאו {count} קבוצות כפולות",
+            "noGroups": "לא נמצאו קבוצות כפולות לפי קריטריון ההתאמה הנוכחי",
            "keepLatest": "שמור גרסאות אחרונות",
-            "deleteSelected": "מחק נבחרים"
+            "deleteSelected": "מחק נבחרים",
+            "includePromptLabel": "כלול הנחיה בהתאמה",
+            "basis": {
+                "loraCombo": "התאמה לפי: שילוב LoRA",
+                "loraComboAndPrompt": "התאמה לפי: שילוב LoRA + הנחיה",
+                "hintLoraCombo": "מתכונים עם אותם LoRAs בעוצמות זהות מקובצים יחד.",
+                "hintPromptIncluded": "מתכונים מקובצים רק כאשר הם משתמשים באותם LoRAs בעוצמות זהות ויש להם אותה הנחיה."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "מכין הורדה...",
                "downloadedPreview": "תמונת תצוגה מקדימה הורדה",
                "downloadingFile": "מוריד קובץ {type}",
-                "finalizing": "מסיים הורדה..."
+                "finalizing": "מסיים הורדה...",
+                "cancelling": "מבטל הורדה...",
+                "cancelled": "ההורדה בוטלה"
            },
            "progress": {
                "currentFile": "הקובץ הנוכחי:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "מפנה {size}",
            "title": "מחק מודל",
-            "message": "האם אתה בטוח שברצונך למחוק מודל זה וכל הקבצים הנלווים?"
+            "message": "האם אתה בטוח שברצונך למחוק מודל זה וכל הקבצים הנלווים?",
+            "recoverableWarning": "הקובץ יימחק לצמיתות לאחר 20 שניות, אלא אם תבטלו את הפעולה."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "ניתן לבטל פעולה זו תוך 20 שניות."
        },
        "excludeModel": {
            "title": "החרג מודל",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "הקלד נתיב תיקייה או בחר מהעץ למטה...",
            "root": "שורש"
        },
+        "linkHuggingFace": {
+            "title": "קישור ל-HuggingFace",
+            "infoText": "הדבק את כתובת ה-URL של מאגר HuggingFace כדי לשייך מודל זה למקורו. פעולה זו מאפשרת העשרת מטא-דאטה באמצעות AI.",
+            "urlLabel": "כתובת URL של מאגר HuggingFace:",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "הזן את כתובת ה-URL המלאה של מאגר HuggingFace.",
+            "confirmAction": "שמור וקשר"
+        },
        "relinkCivitai": {
            "title": "קשר מחדש ל-Civitai",
            "warning": "אזהרה:",
@@ -1498,6 +1586,7 @@
                "empty": "אין עדיין היסטוריית גרסאות למודל זה.",
                "error": "טעינת הגרסאות נכשלה.",
                "missingModelId": "למודל זה אין מזהה מודל של Civitai.",
+                "hfGroupInfo": "זוהי קבוצת דגמים של HuggingFace. פתח את הספרייה כדי לראות את כל הגרסאות ברשת.",
                "confirm": {
                    "delete": "למחוק גרסה זו מהספרייה שלך?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "הורד CSV",
            "columnModelName": "שם המודל",
            "columnError": "שגיאה"
+        },
+        "downloadBatchSummary": {
+            "title": "סיכום הורדה בכמות",
+            "statSuccess": "הצליחו",
+            "statFailed": "נכשלו",
+            "statTotal": "סה\"כ",
+            "successMessage": "כל {count} הדגמים הורדו בהצלחה",
+            "completedWithErrors": "הושלם עם שגיאות",
+            "failed": "ההורדה נכשלה",
+            "failedItems": "פריטים שנכשלו ({count})",
+            "columnName": "שם הדגם",
+            "columnError": "שגיאה",
+            "close": "סגור",
+            "copyReport": "העתק דוח",
+            "retryFailed": "נסה שוב ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "מתכון הוחלף ב-workflow",
            "recipeFailedToSend": "שליחת מתכון ל-workflow נכשלה",
            "noMatchingNodes": "אין צמתים תואמים זמינים ב-workflow הנוכחי",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "לא נבחר צומת יעד",
            "modelUpdated": "מודל עודכן ב-workflow",
            "modelFailed": "עדכון צומת המודל נכשל",
@@ -1700,7 +1805,13 @@
        "checkingUpdates": "בודק עדכונים...",
        "checkingMessage": "אנא המתן בזמן שאנו בודקים את הגרסה האחרונה.",
        "showNotifications": "הצג התראות עדכון",
-        "latestBadge": "עדכן",
+        "latestBadge": "אחרון",
+        "latestMain": "ענף main",
+        "channel": "ערוץ עדכון",
+        "channels": {
+            "release": "Release",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "מכין עדכון...",
            "installing": "מתקין עדכון...",
@@ -1721,6 +1832,15 @@
            "warning": "אזהרה: גרסאות ליליות עשויות להכיל תכונות ניסיוניות ועלולות להיות לא יציבות.",
            "enable": "הפעל עדכונים ליליים"
        },
+        "channelSwitch": {
+            "nightlyTitle": "מעבר לערוץ Nightly",
+            "nightlyMessage": "מעבר ל-Nightly יאתחל מאגר Git ויעקוב אחר הקומיטים האחרונים בענף main. העדכונים תכופים יותר אך עשויים להיות לא יציבים. ניתן לחזור ל-Release בכל עת.",
+            "releaseTitle": "מעבר לערוץ Release",
+            "releaseMessage": "מעבר ל-Release יעבור לתגית הגרסה היציבה האחרונה. ניתן לחזור ל-Nightly בכל עת.",
+            "switching": "מעבר לערוץ {channel}...",
+            "completed": "המעבר לערוץ {channel} הושלם",
+            "failed": "החלפת ערוץ נכשלה"
+        },
        "banners": {
            "recent": "הודעות אחרונות",
            "empty": "אין כרגע באנרים אחרונים.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "התיקון הושלם: {repaired} תוקנו, {skipped} דולגו (מתוך {total})",
            "repairBulkSkipped": "אין צורך בתיקון עבור {total} המתכונים הנבחרים",
            "repairBulkFailed": "תיקון המתכונים הנבחרים נכשל: {message}",
+            "rematchComplete": "הותאמו {entries} פריטים ב־{recipes} מתכונים",
+            "rematchCompleteErrors": "הותאמו {entries} פריטים ב־{recipes} מתכונים, {failures} נכשלו",
+            "rematchAllFailed": "ההתאמה נכשלה עבור {failures} מתוך {total} מתכונים שנבחרו",
+            "rematchUnmatched": "לא נמצאה התאמה מקומית עבור {entries} פריטים ב־{recipes} מתכונים",
+            "rematchSkipped": "אין צורך בהתאמה עבור {total} המתכונים שנבחרו",
+            "rematchFailed": "ההתאמה מחדש של המתכונים שנבחרו נכשלה: {message}",
            "reimporting": "מייבא מתכון מחדש מהמקור...",
            "reimportSuccess": "המתכון יובא מחדש בהצלחה",
            "reimportBulkComplete": "ייבוא מחדש הושלם: {completed} יובאו, {failed} נכשלו (מתוך {total})",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "שם קביעה מראש חייב להיות {max} תווים או פחות",
            "presetNameInvalidChars": "שם קביעה מראש מכיל תווים לא חוקיים",
            "presetNameExists": "קביעה מראש עם שם זה כבר קיימת",
-            "maxPresetsReached": "מותר מקסימום {max} קביעות מראש. מחק אחת כדי להוסיף עוד.",
            "presetNotFound": "קביעה מראש לא נמצאה",
            "invalidPreset": "נתוני קביעה מראש לא חוקיים",
            "deletePresetFailed": "מחיקת קביעה מראש נכשלה",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "{action} תמונות הדוגמה הושלם",
            "imagesFailed": "{action} תמונות הדוגמה נכשל",
            "loadError": "שגיאה בטעינת הורדות: {message}",
-            "downloadError": "שגיאת הורדה: {message}"
+            "downloadError": "שגיאת הורדה: {message}",
+            "downloadStopped": "ההורדה בוטלה"
        },
        "import": {
            "folderTreeFailed": "טעינת עץ התיקיות נכשלה",
@@ -1993,6 +2119,14 @@
            "updateFailed": "עדכון מילות הטריגר נכשל",
            "copyFailed": "ההעתקה נכשלה"
        },
+        "undo": {
+            "action": "בטל",
+            "deleted": "נמחק: {name}",
+            "deletedBulk": "{count} פריטים נמחקו",
+            "expired": "חלון הביטול פג. הפריט נמחק לצמיתות.",
+            "failed": "הביטול נכשל: {error}",
+            "restored": "הפריט שוחזר"
+        },
        "virtual": {
            "loadFailed": "טעינת הפריטים נכשלה",
            "loadMoreFailed": "טעינת פריטים נוספים נכשלה",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "הגדרת דירוג התוכן נכשלה: {message}",
            "relinkSuccess": "המודל קושר מחדש ל-Civitai בהצלחה",
            "relinkFailed": "שגיאה: {message}",
+            "linkHfSuccess": "המודל נקשר בהצלחה ל-HuggingFace",
+            "linkHfFailed": "שגיאה: {message}",
            "fetchMetadataFirst": "אנא אחזר מטא-דאטה מ-CivitAI תחילה",
            "noCivitaiInfo": "אין מידע מ-CivitAI זמין",
            "missingHash": "ה-hash של המודל אינו זמין"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "הועתק ללוח",
            "downloadStarted": "ההורדה החלה"
+        },
+        "agent": {
+            "llmNotConfigured": "ספק AI לא הוגדר. הפעל אותו בהגדרות → ספק AI.",
+            "enrichStarted": "מעשיר מטא-דאטה באמצעות AI...",
+            "enrichComplete": "העשרת מטא-דאטה הושלמה: {{summary}}",
+            "enrichFailed": "העשרת מטא-דאטה נכשלה: {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "修復がキャンセルされました。{count}個のレシピが修復されました。",
            "error": "レシピの修復に失敗しました: {message}"
        },
+        "rematchRecipes": {
+            "label": "レシピをローカルモデルに再マッチング",
+            "loading": "レシピをローカルモデルに再マッチングしています...",
+            "success": "{recipes} 件のレシピで {entries} エントリをマッチングしました",
+            "successErrors": "{recipes} 件のレシピで {entries} エントリをマッチングしました（{failures} 件失敗）",
+            "allFailed": "{total} 件中 {failures} 件のレシピの再マッチングに失敗しました",
+            "noMatch": "{recipes} 件のレシピで {entries} エントリのローカルマッチが見つかりませんでした",
+            "cancelled": "再マッチングをキャンセルしました。{recipes} 件のレシピを更新（{entries} エントリ）",
+            "error": "レシピの再マッチングに失敗しました：{message}"
+        },
        "manageExcludedModels": {
            "label": "除外モデルを管理"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "プリセット名...",
            "baseModel": "ベースモデル",
            "baseModelSearchPlaceholder": "ベースモデルを検索...",
-            "modelTags": "タグ（上位20）",
+            "modelTags": "タグ",
            "modelTypes": "モデルタイプ",
            "license": "ライセンス",
            "noCreditRequired": "クレジット不要",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "生成した画像の販売を許可",
            "noCreditRequiredTooltip": "クレジット表記なしでモデルを使用可能",
            "noTags": "タグなし",
+            "tagSearchPlaceholder": "タグを検索...",
+            "noTagMatches": "現在の検索に一致するタグはありません。",
            "autoTags": "自動タグ",
            "noBaseModelMatches": "現在の検索に一致するベースモデルはありません。",
            "clearAll": "すべてのフィルタをクリア",
@@ -447,6 +459,12 @@
                "compact": "7（1080p）、8（2K）、10（4K）"
            },
            "displayDensityWarning": "警告：高密度設定は、リソースが限られたシステムでパフォーマンスの問題を引き起こす可能性があります。",
+            "recipesLayout": "レシピのレイアウト",
+            "recipesLayoutHelp": "レシピカードの配置方法を選択：均一なグリッド、または各画像のアスペクト比を保持するメイソンリー（Pinterest スタイル）レイアウト。",
+            "recipesLayoutOptions": {
+                "grid": "グリッド",
+                "masonry": "メイソンリー"
+            },
            "showFolderSidebar": "フォルダサイドバーを表示",
            "showFolderSidebarHelp": "モデルページのフォルダナビゲーションサイドバーを表示/非表示にします。無効にするとサイドバーとホバーエリアは表示されません。",
            "cardInfoDisplay": "カード情報表示",
@@ -505,7 +523,9 @@
            "saveSuccess": "追加フォルダーパスを更新しました。変更を適用するには再起動が必要です。",
            "saveError": "追加フォルダーパスの更新に失敗しました: {message}",
            "validation": {
-                "duplicatePath": "このパスはすでに設定されています"
+                "duplicatePath": "このパスはすでに設定されています",
+                "checkpointUnetOverlap": "checkpoints と diffusion models に同じパスは使用できません：{paths}",
+                "checkpointUnetOverlapInline": "このパスは別のモデルタイプですでに使用されています。checkpoints と diffusion models には別々のフォルダを使用してください。"
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "ダウンロードを準備中...",
            "connecting": "ダウンロードサーバーに接続中...",
            "completed": "完了",
-            "downloadComplete": "ダウンロードが正常に完了しました"
+            "downloadComplete": "ダウンロードが正常に完了しました",
+            "enableCivarchiveApi": "CivArchive API をメタデータプロバイダーとして有効化",
+            "enableCivarchiveApiHelp": "有効にすると、CivArchive API がモデルメタデータの代替ソースとして使用されます（例：CivitAI から削除されたモデルの場合）。オフにすると、CivArchive のレート制限を完全に回避できます。",
+            "providerOrder": "メタデータプロバイダーのフォールバック順序",
+            "providerOrderHelp": "CivitAI API が常に最初に試行されます。メタデータ検索時の残りのプロバイダーの順序を選択してください。",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "アプリレベルのプロキシを有効化",
@@ -657,6 +683,33 @@
            "proxyPassword": "パスワード（任意）",
            "proxyPasswordPlaceholder": "パスワード",
            "proxyPasswordHelp": "プロキシ認証用のパスワード（必要な場合）"
+        },
+        "aiProvider": {
+            "title": "AIプロバイダー",
+            "provider": "プロバイダー",
+            "providerHelp": "LLMプロバイダーを選択してください。OpenAIとOllamaはプリセットのAPIエンドポイントを使用します。カスタムでは任意のOpenAI互換エンドポイントを指定できます。",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama（ローカル）",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "カスタム（OpenAI 互換）"
+            },
+            "apiBase": "APIベースURL",
+            "apiBaseHelp": "LLM APIのベースURL（例：https://api.openai.com/v1）。空の場合はプロバイダーのデフォルトが使用されます。",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "APIキー",
+            "apiKeyHelp": "LLMプロバイダーのAPIキー。ローカルに保存され、選択したLLMプロバイダー以外のサーバーに送信されることはありません。",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "未設定",
+            "apiKeyConfigured": "設定済み",
+            "apiKeySet": "設定",
+            "model": "モデル",
+            "modelHelp": "使用するモデル名（例：deepseek-v4-flash, gemini-2.5-flash, gemma4:12b）。プロバイダーで利用可能なモデルをご確認ください。",
+            "modelPlaceholder": "モデルを選択..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "ローカルバージョン数",
                "versionsCountDesc": "バージョン数の多い順",
                "versionsCountAsc": "バージョン数の少ない順",
-                "versionIdDesc": "最新バージョン順"
+                "versionIdDesc": "最新バージョン順",
+                "random": "ランダム",
+                "randomAction": "シャッフル（ランダム）"
            },
            "refresh": {
                "title": "モデルリストを更新",
@@ -723,6 +778,7 @@
            "copyAll": "すべての構文をコピー",
            "refreshAll": "すべてのメタデータを更新",
            "repairMetadata": "選択したレシピのメタデータを修復",
+            "rematchMetadata": "選択したモデルをローカルモデルに再マッチング",
            "reimportMetadata": "ソースから再インポート",
            "checkUpdates": "選択項目の更新を確認",
            "moveAll": "すべてをフォルダに移動",
@@ -735,6 +791,8 @@
            "deleteAll": "選択したものを削除",
            "downloadMissingLoras": "不足している LoRA をダウンロード",
            "downloadExamples": "例画像をダウンロード",
+            "downloadMissingExamples": "不足分をダウンロード",
+            "reprocessExamples": "すべて再処理",
            "clear": "選択をクリア",
            "skipMetadataRefreshCount": "スキップ（{count}モデル）",
            "resumeMetadataRefreshCount": "再開（{count}モデル）",
@@ -754,12 +812,15 @@
                "completed": "完了：{success} 移動、{skipped} スキップ、{failures} 失敗",
                "complete": "自動整理が完了しました",
                "error": "エラー：{error}"
-            }
+            },
+            "enrichHfAgent": "HF メタデータをAIで補完"
        },
        "contextMenu": {
            "refreshMetadata": "Civitaiデータを更新",
            "checkUpdates": "更新確認",
-            "relinkCivitai": "Civitaiに再リンク",
+            "linkModel": "モデルをリンク",
+            "linkCivitai": "Civitai にリンク",
+            "linkHuggingFace": "HuggingFace にリンク",
            "copySyntax": "LoRA構文をコピー",
            "copyFilename": "モデルファイル名をコピー",
            "copyRecipeSyntax": "レシピ構文をコピー",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "ワークフローに送信（置換）",
            "openExamples": "例画像フォルダを開く",
            "downloadExamples": "例画像をダウンロード",
+            "downloadMissingExamples": "不足分をダウンロード",
+            "reprocessExamples": "すべて再処理",
            "replacePreview": "プレビューを置換",
            "setContentRating": "コンテンツレーティングを設定",
            "moveToFolder": "フォルダに移動",
            "repairMetadata": "メタデータを修復",
+            "rematchMetadata": "ローカルモデルに再マッチング",
            "reimportMetadata": "ソースから再インポート",
            "excludeModel": "モデルを除外",
            "restoreModel": "モデルを復元",
@@ -778,7 +842,8 @@
            "shareRecipe": "レシピを共有",
            "viewAllLoras": "すべてのLoRAを表示",
            "downloadMissingLoras": "不足しているLoRAをダウンロード",
-            "deleteRecipe": "レシピを削除"
+            "deleteRecipe": "レシピを削除",
+            "enrichHfAgent": "HF メタデータをAIで補完"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "{count} 個の重複グループが見つかりました",
+            "noGroups": "現在の一致基準では重複グループが見つかりませんでした",
            "keepLatest": "最新バージョンを保持",
-            "deleteSelected": "選択したものを削除"
+            "deleteSelected": "選択したものを削除",
+            "includePromptLabel": "一致判定にプロンプトを含める",
+            "basis": {
+                "loraCombo": "一致基準: LoRA の組み合わせ",
+                "loraComboAndPrompt": "一致基準: LoRA の組み合わせ + プロンプト",
+                "hintLoraCombo": "同じ LoRA を同じ強度で使用するレシピがグループ化されます。",
+                "hintPromptIncluded": "レシピは、同じ LoRA を同じ強度で使用し、かつプロンプトが同じ場合にのみグループ化されます。"
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "ダウンロードを準備中...",
                "downloadedPreview": "プレビュー画像をダウンロードしました",
                "downloadingFile": "{type}ファイルをダウンロード中",
-                "finalizing": "ダウンロードを完了中..."
+                "finalizing": "ダウンロードを完了中...",
+                "cancelling": "ダウンロードをキャンセル中...",
+                "cancelled": "ダウンロードをキャンセルしました"
            },
            "progress": {
                "currentFile": "現在のファイル:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "{size} を解放します",
            "title": "モデルを削除",
-            "message": "このモデルと関連するすべてのファイルを削除してもよろしいですか？"
+            "message": "このモデルと関連するすべてのファイルを削除してもよろしいですか？",
+            "recoverableWarning": "元に戻さない場合、このファイルは20秒後に完全に削除されます。"
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "この操作は20秒以内であれば元に戻せます。"
        },
        "excludeModel": {
            "title": "モデルを除外",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "フォルダパスを入力するか、下のツリーから選択...",
            "root": "ルート"
        },
+        "linkHuggingFace": {
+            "title": "HuggingFace にリンク",
+            "infoText": "HuggingFace リポジトリの URL を貼り付けてモデルを関連付けます。AI によるメタデータ補完が有効になります。",
+            "urlLabel": "HuggingFace リポジトリ URL：",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "完全な HuggingFace リポジトリ URL を入力してください。",
+            "confirmAction": "保存＆リンク"
+        },
        "relinkCivitai": {
            "title": "Civitaiに再リンク",
            "warning": "警告：",
@@ -1498,6 +1586,7 @@
                "empty": "このモデルにはまだバージョン履歴がありません。",
                "error": "バージョンの読み込みに失敗しました。",
                "missingModelId": "このモデルにはCivitaiのモデルIDがありません。",
+                "hfGroupInfo": "これは HuggingFace モデルグループです。ライブラリを開いてグリッドですべてのバージョンを表示してください。",
                "confirm": {
                    "delete": "このバージョンをライブラリから削除しますか？"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "CSVをダウンロード",
            "columnModelName": "モデル名",
            "columnError": "エラー"
+        },
+        "downloadBatchSummary": {
+            "title": "バッチダウンロードの概要",
+            "statSuccess": "成功",
+            "statFailed": "失敗",
+            "statTotal": "合計",
+            "successMessage": "{count} 個のモデルがすべて正常にダウンロードされました",
+            "completedWithErrors": "エラーありで完了",
+            "failed": "ダウンロードに失敗しました",
+            "failedItems": "失敗した項目（{count}）",
+            "columnName": "モデル名",
+            "columnError": "エラー",
+            "close": "閉じる",
+            "copyReport": "レポートをコピー",
+            "retryFailed": "失敗した項目を再試行（{count}）"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "レシピがワークフローで置換されました",
            "recipeFailedToSend": "レシピをワークフローに送信できませんでした",
            "noMatchingNodes": "現在のワークフローには互換性のあるノードがありません",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "ターゲットノードが選択されていません",
            "modelUpdated": "モデルがワークフローで更新されました",
            "modelFailed": "モデルノードの更新に失敗しました",
@@ -1701,6 +1806,12 @@
        "checkingMessage": "最新バージョンを確認しています。お待ちください。",
        "showNotifications": "更新通知を表示",
        "latestBadge": "最新",
+        "latestMain": "Main ブランチ",
+        "channel": "更新チャンネル",
+        "channels": {
+            "release": "リリース",
+            "nightly": "ナイトリー"
+        },
        "updateProgress": {
            "preparing": "更新を準備中...",
            "installing": "更新をインストール中...",
@@ -1721,6 +1832,15 @@
            "warning": "警告：ナイトリービルドには実験的機能が含まれており、不安定な場合があります。",
            "enable": "ナイトリー更新を有効にする"
        },
+        "channelSwitch": {
+            "nightlyTitle": "ナイトリーチャンネルに切り替え",
+            "nightlyMessage": "ナイトリーに切り替えると、Gitリポジトリが初期化され、mainブランチの最新コミットを追跡します。更新頻度は高くなりますが、不安定な場合があります。いつでもリリース版に戻せます。",
+            "releaseTitle": "リリースチャンネルに切り替え",
+            "releaseMessage": "リリースに切り替えると、最新の安定版タグにチェックアウトされます。いつでもNightlyに戻せます。",
+            "switching": "{channel} チャンネルに切り替え中...",
+            "completed": "{channel} チャンネルに切り替えました",
+            "failed": "チャンネルの切り替えに失敗しました"
+        },
        "banners": {
            "recent": "最近の通知",
            "empty": "最近のバナーはありません。",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "修復完了：{repaired} 件修復、{skipped} 件スキップ（合計 {total} 件）",
            "repairBulkSkipped": "選択した {total} 件のレシピは修復不要です",
            "repairBulkFailed": "選択したレシピの修復に失敗しました：{message}",
+            "rematchComplete": "{recipes} 件のレシピで {entries} エントリをマッチングしました",
+            "rematchCompleteErrors": "{recipes} 件のレシピで {entries} エントリをマッチングしました（{failures} 件失敗）",
+            "rematchAllFailed": "選択した {total} 件中 {failures} 件のレシピの再マッチングに失敗しました",
+            "rematchUnmatched": "{recipes} 件のレシピで {entries} エントリのローカルマッチが見つかりませんでした",
+            "rematchSkipped": "選択した {total} 件のレシピは再マッチングの必要がありませんでした",
+            "rematchFailed": "選択したレシピの再マッチングに失敗しました：{message}",
            "reimporting": "ソースからレシピを再インポート中...",
            "reimportSuccess": "レシピの再インポートが完了しました",
            "reimportBulkComplete": "再インポート完了：{completed} 件成功、{failed} 件失敗（合計 {total} 件）",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "プリセット名は{max}文字以内にしてください",
            "presetNameInvalidChars": "プリセット名に使用できない文字が含まれています",
            "presetNameExists": "同じ名前のプリセットが既に存在します",
-            "maxPresetsReached": "プリセットは最大{max}個までです。追加するには既存のものを削除してください。",
            "presetNotFound": "プリセットが見つかりません",
            "invalidPreset": "無効なプリセットデータです",
            "deletePresetFailed": "プリセットの削除に失敗しました",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "例画像 {action} が完了しました",
            "imagesFailed": "例画像 {action} が失敗しました",
            "loadError": "ダウンロード読み込みエラー：{message}",
-            "downloadError": "ダウンロードエラー：{message}"
+            "downloadError": "ダウンロードエラー：{message}",
+            "downloadStopped": "ダウンロードをキャンセルしました"
        },
        "import": {
            "folderTreeFailed": "フォルダツリーの読み込みに失敗しました",
@@ -1993,6 +2119,14 @@
            "updateFailed": "トリガーワードの更新に失敗しました",
            "copyFailed": "コピーに失敗しました"
        },
+        "undo": {
+            "action": "元に戻す",
+            "deleted": "{name} を削除しました",
+            "deletedBulk": "{count} 個のアイテムを削除しました",
+            "expired": "元に戻せる時間が経過しました。アイテムは完全に削除されました。",
+            "failed": "元に戻せませんでした: {error}",
+            "restored": "アイテムを復元しました"
+        },
        "virtual": {
            "loadFailed": "アイテムの読み込みに失敗しました",
            "loadMoreFailed": "追加アイテムの読み込みに失敗しました",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "コンテンツレーティングの設定に失敗しました：{message}",
            "relinkSuccess": "モデルがCivitaiに正常に再リンクされました",
            "relinkFailed": "エラー：{message}",
+            "linkHfSuccess": "モデルを HuggingFace にリンクしました",
+            "linkHfFailed": "エラー：{message}",
            "fetchMetadataFirst": "最初にCivitAIからメタデータを取得してください",
            "noCivitaiInfo": "CivitAI情報が利用できません",
            "missingHash": "モデルハッシュが利用できません"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "クリップボードにコピーしました",
            "downloadStarted": "ダウンロードを開始しました"
+        },
+        "agent": {
+            "llmNotConfigured": "AIプロバイダーが設定されていません。設定 → AIプロバイダーで有効にしてください。",
+            "enrichStarted": "AIでメタデータを補完中...",
+            "enrichComplete": "メタデータの補完が完了しました：{{summary}}",
+            "enrichFailed": "メタデータの補完に失敗しました：{{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "수리가 취소되었습니다. {count}개의 레시피가 수리되었습니다.",
            "error": "레시피 복구 실패: {message}"
        },
+        "rematchRecipes": {
+            "label": "레시피를 로컬 모델에 다시 매칭",
+            "loading": "레시피를 로컬 모델에 다시 매칭하는 중...",
+            "success": "{recipes}개 레시피에서 {entries}개 항목이 매칭되었습니다",
+            "successErrors": "{recipes}개 레시피에서 {entries}개 항목이 매칭되었습니다. {failures}개 실패",
+            "allFailed": "{total}개 레시피 중 {failures}개 재매칭 실패",
+            "noMatch": "{recipes}개 레시피에서 {entries}개 항목의 로컬 매칭을 찾지 못했습니다",
+            "cancelled": "재매칭이 취소되었습니다. {recipes}개 레시피 업데이트됨({entries}개 항목)",
+            "error": "레시피 재매칭 실패: {message}"
+        },
        "manageExcludedModels": {
            "label": "제외된 모델 관리"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "프리셋 이름...",
            "baseModel": "베이스 모델",
            "baseModelSearchPlaceholder": "베이스 모델 검색...",
-            "modelTags": "태그 (상위 20개)",
+            "modelTags": "태그",
            "modelTypes": "모델 유형",
            "license": "라이선스",
            "noCreditRequired": "크레딧 표기 없음",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "생성된 이미지 판매 허용",
            "noCreditRequiredTooltip": "크리에이터 저작자 표시 없이 모델 사용 가능",
            "noTags": "태그 없음",
+            "tagSearchPlaceholder": "태그 검색...",
+            "noTagMatches": "현재 검색과 일치하는 태그가 없습니다.",
            "autoTags": "자동 태그",
            "noBaseModelMatches": "현재 검색과 일치하는 베이스 모델이 없습니다.",
            "clearAll": "모든 필터 지우기",
@@ -447,6 +459,12 @@
                "compact": "7개 (1080p), 8개 (2K), 10개 (4K)"
            },
            "displayDensityWarning": "경고: 높은 밀도는 리소스가 제한된 시스템에서 성능 문제를 일으킬 수 있습니다.",
+            "recipesLayout": "레시피 레이아웃",
+            "recipesLayoutHelp": "레시피 카드의 배열 방식을 선택하세요: 균일한 그리드 또는 각 이미지의 종횡비를 유지하는 메이슨리(Pinterest 스타일) 레이아웃.",
+            "recipesLayoutOptions": {
+                "grid": "그리드",
+                "masonry": "메이슨리"
+            },
            "showFolderSidebar": "폴더 사이드바 표시",
            "showFolderSidebarHelp": "모델 페이지에서 폴더 탐색 사이드바를 켜거나 끕니다. 비활성화하면 사이드바와 호버 영역이 표시되지 않습니다.",
            "cardInfoDisplay": "카드 정보 표시",
@@ -505,7 +523,9 @@
            "saveSuccess": "추가 폴다 경로가 업데이트되었습니다. 변경 사항을 적용하려면 재시작이 필요합니다.",
            "saveError": "추가 폴다 경로 업데이트 실패: {message}",
            "validation": {
-                "duplicatePath": "이 경로는 이미 구성되어 있습니다"
+                "duplicatePath": "이 경로는 이미 구성되어 있습니다",
+                "checkpointUnetOverlap": "checkpoints와 diffusion models에 동일한 경로를 사용할 수 없습니다: {paths}",
+                "checkpointUnetOverlapInline": "이 경로는 다른 모델 유형에 이미 사용 중입니다. checkpoints와 diffusion models에 별도의 폴더를 사용하세요."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "다운로드 준비 중...",
            "connecting": "다운로드 서버에 연결 중...",
            "completed": "완료됨",
-            "downloadComplete": "다운로드가 성공적으로 완료되었습니다"
+            "downloadComplete": "다운로드가 성공적으로 완료되었습니다",
+            "enableCivarchiveApi": "CivArchive API를 메타데이터 제공자로 활성화",
+            "enableCivarchiveApiHelp": "활성화하면 CivArchive API가 모델 메타데이터의 대체 소스로 사용됩니다 (예: CivitAI에서 삭제된 모델의 경우). 비활성화하면 CivArchive의 속도 제한을 완전히 피할 수 있습니다.",
+            "providerOrder": "메타데이터 제공자 폴백 순서",
+            "providerOrderHelp": "CivitAI API가 항상 먼저 시도됩니다. 메타데이터 조회 시 나머지 제공자의 순서를 선택하세요.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "앱 수준 프록시 활성화",
@@ -657,6 +683,33 @@
            "proxyPassword": "비밀번호 (선택사항)",
            "proxyPasswordPlaceholder": "password",
            "proxyPasswordHelp": "프록시 인증에 필요한 비밀번호 (필요한 경우)"
+        },
+        "aiProvider": {
+            "title": "AI 제공자",
+            "provider": "제공자",
+            "providerHelp": "LLM 제공자를 선택하세요. OpenAI와 Ollama는 사전 설정된 API 엔드포인트를 사용합니다. 사용자 정의를 선택하면 모든 OpenAI 호환 엔드포인트를 지정할 수 있습니다.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (로컬)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "사용자 정의 (OpenAI 호환)"
+            },
+            "apiBase": "API 기본 URL",
+            "apiBaseHelp": "LLM API의 기본 URL입니다 (예: https://api.openai.com/v1). 비워두면 제공자 기본값이 사용됩니다.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "API 키",
+            "apiKeyHelp": "LLM 제공자의 API 키입니다. 로컬에 저장되며 선택한 LLM 제공자 외의 서버로 전송되지 않습니다.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "설정되지 않음",
+            "apiKeyConfigured": "설정됨",
+            "apiKeySet": "설정",
+            "model": "모델",
+            "modelHelp": "사용할 모델 이름 (예: deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). 제공자에서 사용 가능한 모델을 확인하세요.",
+            "modelPlaceholder": "모델 선택..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "로컬 버전 수",
                "versionsCountDesc": "버전 수 많은 순",
                "versionsCountAsc": "버전 수 적은 순",
-                "versionIdDesc": "최신 버전순"
+                "versionIdDesc": "최신 버전순",
+                "random": "랜덤",
+                "randomAction": "셔플 (무작위)"
            },
            "refresh": {
                "title": "모델 목록 새로고침",
@@ -723,6 +778,7 @@
            "copyAll": "모든 문법 복사",
            "refreshAll": "모든 메타데이터 새로고침",
            "repairMetadata": "선택한 레시피 메타데이터 복구",
+            "rematchMetadata": "선택 항목을 로컬 모델에 다시 매칭",
            "reimportMetadata": "소스에서 다시 가져오기",
            "checkUpdates": "선택 항목 업데이트 확인",
            "moveAll": "모두 폴더로 이동",
@@ -735,6 +791,8 @@
            "deleteAll": "선택된 항목 삭제",
            "downloadMissingLoras": "누락된 LoRA 다운로드",
            "downloadExamples": "예시 이미지 다운로드",
+            "downloadMissingExamples": "누락된 것만 다운로드",
+            "reprocessExamples": "모두 다시 처리",
            "clear": "선택 지우기",
            "skipMetadataRefreshCount": "건너뛰기（{count}개 모델）",
            "resumeMetadataRefreshCount": "재개（{count}개 모델）",
@@ -754,12 +812,15 @@
                "completed": "완료: {success}개 이동, {skipped}개 건너뜀, {failures}개 실패",
                "complete": "자동 정리 완료",
                "error": "오류: {error}"
-            }
+            },
+            "enrichHfAgent": "HF AI로 메타데이터 보강"
        },
        "contextMenu": {
            "refreshMetadata": "Civitai 데이터 새로고침",
            "checkUpdates": "업데이트 확인",
-            "relinkCivitai": "Civitai에 다시 연결",
+            "linkModel": "모델 연결",
+            "linkCivitai": "Civitai에 연결",
+            "linkHuggingFace": "HuggingFace에 연결",
            "copySyntax": "LoRA 문법 복사",
            "copyFilename": "모델 파일명 복사",
            "copyRecipeSyntax": "레시피 문법 복사",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "워크플로로 전송 (교체)",
            "openExamples": "예시 폴더 열기",
            "downloadExamples": "예시 이미지 다운로드",
+            "downloadMissingExamples": "누락된 것만 다운로드",
+            "reprocessExamples": "모두 다시 처리",
            "replacePreview": "미리보기 교체",
            "setContentRating": "콘텐츠 등급 설정",
            "moveToFolder": "폴더로 이동",
            "repairMetadata": "메타데이터 복구",
+            "rematchMetadata": "로컬 모델에 다시 매칭",
            "reimportMetadata": "소스에서 다시 가져오기",
            "excludeModel": "모델 제외",
            "restoreModel": "모델 복원",
@@ -778,7 +842,8 @@
            "shareRecipe": "레시피 공유",
            "viewAllLoras": "모든 LoRA 보기",
            "downloadMissingLoras": "누락된 LoRA 다운로드",
-            "deleteRecipe": "레시피 삭제"
+            "deleteRecipe": "레시피 삭제",
+            "enrichHfAgent": "HF AI로 메타데이터 보강"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "{count}개의 중복 그룹 발견",
+            "noGroups": "현재 일치 기준으로 중복 그룹을 찾을 수 없습니다",
            "keepLatest": "최신 버전 유지",
-            "deleteSelected": "선택된 항목 삭제"
+            "deleteSelected": "선택된 항목 삭제",
+            "includePromptLabel": "일치 항목에 프롬프트 포함",
+            "basis": {
+                "loraCombo": "일치 기준: LoRA 조합",
+                "loraComboAndPrompt": "일치 기준: LoRA 조합 + 프롬프트",
+                "hintLoraCombo": "동일한 LoRA를 동일한 강도로 사용하는 레시피가 그룹화됩니다.",
+                "hintPromptIncluded": "동일한 LoRA를 동일한 강도로 사용하고 프롬프트도 동일한 경우에만 레시피가 그룹화됩니다."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "다운로드 준비 중...",
                "downloadedPreview": "미리보기 이미지 다운로드됨",
                "downloadingFile": "{type} 파일 다운로드 중",
-                "finalizing": "다운로드 완료 중..."
+                "finalizing": "다운로드 완료 중...",
+                "cancelling": "다운로드 취소 중...",
+                "cancelled": "다운로드가 취소되었습니다"
            },
            "progress": {
                "currentFile": "현재 파일:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "{size} 확보",
            "title": "모델 삭제",
-            "message": "이 모델과 모든 관련 파일을 삭제하시겠습니까?"
+            "message": "이 모델과 모든 관련 파일을 삭제하시겠습니까?",
+            "recoverableWarning": "실행 취소하지 않으면 20초 후에 파일이 영구적으로 삭제됩니다."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "이 작업은 20초 이내에 실행 취소할 수 있습니다."
        },
        "excludeModel": {
            "title": "모델 제외",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "폴더 경로를 입력하거나 아래 트리에서 선택하세요...",
            "root": "루트"
        },
+        "linkHuggingFace": {
+            "title": "HuggingFace에 연결",
+            "infoText": "HuggingFace 저장소 URL을 붙여넣어 모델을 연결합니다. AI 메타데이터 보강 기능을 사용할 수 있습니다.",
+            "urlLabel": "HuggingFace 저장소 URL：",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "전체 HuggingFace 저장소 URL을 입력하세요.",
+            "confirmAction": "저장 및 연결"
+        },
        "relinkCivitai": {
            "title": "Civitai에 다시 연결",
            "warning": "경고:",
@@ -1498,6 +1586,7 @@
                "empty": "이 모델에는 아직 버전 기록이 없습니다.",
                "error": "버전을 불러오지 못했습니다.",
                "missingModelId": "이 모델에는 Civitai 모델 ID가 없습니다.",
+                "hfGroupInfo": "HuggingFace 모델 그룹입니다. 라이브러리를 열어 그리드에서 모든 버전을 확인하세요.",
                "confirm": {
                    "delete": "이 버전을 라이브러리에서 삭제하시겠습니까?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "CSV 다운로드",
            "columnModelName": "모델 이름",
            "columnError": "오류"
+        },
+        "downloadBatchSummary": {
+            "title": "일괄 다운로드 요약",
+            "statSuccess": "성공",
+            "statFailed": "실패",
+            "statTotal": "전체",
+            "successMessage": "{count}개 모델이 모두 성공적으로 다운로드되었습니다",
+            "completedWithErrors": "오류와 함께 완료됨",
+            "failed": "다운로드 실패",
+            "failedItems": "실패한 항목 ({count})",
+            "columnName": "모델 이름",
+            "columnError": "오류",
+            "close": "닫기",
+            "copyReport": "보고서 복사",
+            "retryFailed": "실패 항목 재시도 ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "레시피가 워크플로에서 교체되었습니다",
            "recipeFailedToSend": "레시피를 워크플로로 전송하지 못했습니다",
            "noMatchingNodes": "현재 워크플로에서 호환되는 노드가 없습니다",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "대상 노드가 선택되지 않았습니다",
            "modelUpdated": "모델이 워크플로에서 업데이트되었습니다",
            "modelFailed": "모델 노드 업데이트 실패",
@@ -1701,6 +1806,12 @@
        "checkingMessage": "최신 버전을 확인하는 동안 잠시 기다려주세요.",
        "showNotifications": "업데이트 알림 표시",
        "latestBadge": "최신",
+        "latestMain": "Main 브랜치",
+        "channel": "업데이트 채널",
+        "channels": {
+            "release": "릴리스",
+            "nightly": "나이틀리"
+        },
        "updateProgress": {
            "preparing": "업데이트 준비 중...",
            "installing": "업데이트 설치 중...",
@@ -1721,6 +1832,15 @@
            "warning": "경고: 나이틀리 빌드는 실험적 기능을 포함할 수 있으며 불안정할 수 있습니다.",
            "enable": "나이틀리 업데이트 활성화"
        },
+        "channelSwitch": {
+            "nightlyTitle": "나이틀리 채널로 전환",
+            "nightlyMessage": "나이틀리로 전환하면 Git 저장소가 초기화되고 main 브랜치의 최신 커밋을 추적합니다. 업데이트 빈도는 높지만 불안정할 수 있습니다. 언제든지 릴리스로 돌아갈 수 있습니다.",
+            "releaseTitle": "릴리스 채널로 전환",
+            "releaseMessage": "릴리스로 전환하면 최신 안정 버전 태그로 체크아웃됩니다. 언제든지 나이틀리로 돌아갈 수 있습니다.",
+            "switching": "{channel} 채널로 전환 중...",
+            "completed": "{channel} 채널로 전환 완료",
+            "failed": "채널 전환 실패"
+        },
        "banners": {
            "recent": "최근 알림",
            "empty": "최근 배너가 없습니다.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "복구 완료: {repaired}개 복구, {skipped}개 건너뜀 (총 {total}개)",
            "repairBulkSkipped": "선택한 {total}개 레시피는 복구가 필요하지 않습니다",
            "repairBulkFailed": "선택한 레시피 복구 실패: {message}",
+            "rematchComplete": "{recipes}개 레시피에서 {entries}개 항목이 매칭되었습니다",
+            "rematchCompleteErrors": "{recipes}개 레시피에서 {entries}개 항목이 매칭되었습니다. {failures}개 실패",
+            "rematchAllFailed": "선택한 {total}개 레시피 중 {failures}개 재매칭 실패",
+            "rematchUnmatched": "{recipes}개 레시피에서 {entries}개 항목의 로컬 매칭을 찾지 못했습니다",
+            "rematchSkipped": "선택한 {total}개 레시피는 재매칭이 필요하지 않습니다",
+            "rematchFailed": "선택한 레시피 재매칭 실패: {message}",
            "reimporting": "소스에서 레시피를 다시 가져오는 중...",
            "reimportSuccess": "레시피를 다시 가져왔습니다",
            "reimportBulkComplete": "다시 가져오기 완료: {completed}개 성공, {failed}개 실패 (총 {total}개)",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "프리셋 이름은 {max}자 이하여야 합니다",
            "presetNameInvalidChars": "프리셋 이름에 유효하지 않은 문자가 포함되어 있습니다",
            "presetNameExists": "동일한 이름의 프리셋이 이미 존재합니다",
-            "maxPresetsReached": "최대 {max}개의 프리셋만 허용됩니다. 더 추가하려면 기존 것을 삭제하세요.",
            "presetNotFound": "프리셋을 찾을 수 없습니다",
            "invalidPreset": "잘못된 프리셋 데이터입니다",
            "deletePresetFailed": "프리셋 삭제에 실패했습니다",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "예시 이미지 {action}이(가) 완료되었습니다",
            "imagesFailed": "예시 이미지 {action}이(가) 실패했습니다",
            "loadError": "다운로드 로딩 오류: {message}",
-            "downloadError": "다운로드 오류: {message}"
+            "downloadError": "다운로드 오류: {message}",
+            "downloadStopped": "다운로드가 취소되었습니다"
        },
        "import": {
            "folderTreeFailed": "폴더 트리 로딩 실패",
@@ -1993,6 +2119,14 @@
            "updateFailed": "트리거 단어 업데이트에 실패했습니다",
            "copyFailed": "복사 실패"
        },
+        "undo": {
+            "action": "실행 취소",
+            "deleted": "{name} 삭제됨",
+            "deletedBulk": "{count}개 항목 삭제됨",
+            "expired": "실행 취소 기간이 만료되었습니다. 항목이 영구적으로 삭제되었습니다.",
+            "failed": "실행 취소 실패: {error}",
+            "restored": "항목이 복원되었습니다"
+        },
        "virtual": {
            "loadFailed": "항목 로딩 실패",
            "loadMoreFailed": "더 많은 항목 로딩 실패",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "콘텐츠 등급 설정 실패: {message}",
            "relinkSuccess": "모델이 Civitai에 성공적으로 다시 연결되었습니다",
            "relinkFailed": "오류: {message}",
+            "linkHfSuccess": "모델이 HuggingFace에 연결되었습니다",
+            "linkHfFailed": "오류: {message}",
            "fetchMetadataFirst": "먼저 CivitAI에서 메타데이터를 가져와주세요",
            "noCivitaiInfo": "사용 가능한 CivitAI 정보가 없습니다",
            "missingHash": "모델 해시를 사용할 수 없습니다"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "클립보드에 복사됨",
            "downloadStarted": "다운로드 시작됨"
+        },
+        "agent": {
+            "llmNotConfigured": "AI 제공자가 설정되지 않았습니다. 설정 → AI 제공자에서 활성화하세요.",
+            "enrichStarted": "AI로 메타데이터 보강 중...",
+            "enrichComplete": "메타데이터 보강 완료: {{summary}}",
+            "enrichFailed": "메타데이터 보강 실패: {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "Восстановление отменено. {count} рецептов было восстановлено.",
            "error": "Ошибка восстановления рецептов: {message}"
        },
+        "rematchRecipes": {
+            "label": "Повторное сопоставление рецептов с локальными моделями",
+            "loading": "Повторное сопоставление рецептов с локальными моделями...",
+            "success": "Сопоставлено записей: {entries} в рецептах: {recipes}",
+            "successErrors": "Сопоставлено записей: {entries} в рецептах: {recipes}, ошибок: {failures}",
+            "allFailed": "Не удалось сопоставить: {failures} из {total} рецептов",
+            "noMatch": "Не найдено локального сопоставления для {entries} записей в {recipes} рецептах",
+            "cancelled": "Сопоставление отменено. Обновлено рецептов: {recipes} (записей: {entries})",
+            "error": "Не удалось выполнить сопоставление рецептов: {message}"
+        },
        "manageExcludedModels": {
            "label": "Управление исключёнными моделями"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "Имя пресета...",
            "baseModel": "Базовая модель",
            "baseModelSearchPlaceholder": "Поиск базовых моделей...",
-            "modelTags": "Теги (Топ 20)",
+            "modelTags": "Теги",
            "modelTypes": "Типы моделей",
            "license": "Лицензия",
            "noCreditRequired": "Без указания авторства",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "Разрешить продажу сгенерированных изображений",
            "noCreditRequiredTooltip": "Использование модели без указания автора",
            "noTags": "Без тегов",
+            "tagSearchPlaceholder": "Поиск тегов...",
+            "noTagMatches": "Нет тегов, соответствующих текущему поиску.",
            "autoTags": "Авто-теги",
            "noBaseModelMatches": "Нет базовых моделей, соответствующих текущему поиску.",
            "clearAll": "Очистить все фильтры",
@@ -447,6 +459,12 @@
                "compact": "7 (1080p), 8 (2K), 10 (4K)"
            },
            "displayDensityWarning": "Предупреждение: Высокая плотность может вызвать проблемы с производительностью на системах с ограниченными ресурсами.",
+            "recipesLayout": "Макет рецептов",
+            "recipesLayoutHelp": "Выберите, как располагаются карточки рецептов: единая сетка или masonry-макет (в стиле Pinterest), сохраняющий пропорции каждого изображения.",
+            "recipesLayoutOptions": {
+                "grid": "Сетка",
+                "masonry": "Masonry"
+            },
            "showFolderSidebar": "Показывать боковую панель папок",
            "showFolderSidebarHelp": "Включает или выключает боковую панель навигации по папкам на страницах моделей. При отключении панель и область наведения скрыты.",
            "cardInfoDisplay": "Отображение информации карточки",
@@ -505,7 +523,9 @@
            "saveSuccess": "Дополнительные пути к папкам обновлены. Требуется перезапуск для применения изменений.",
            "saveError": "Не удалось обновить дополнительные пути к папкам: {message}",
            "validation": {
-                "duplicatePath": "Этот путь уже настроен"
+                "duplicatePath": "Этот путь уже настроен",
+                "checkpointUnetOverlap": "Нельзя использовать один и тот же путь для checkpoints и diffusion models: {paths}",
+                "checkpointUnetOverlapInline": "Этот путь уже используется для другого типа модели. Используйте отдельные папки для checkpoints и diffusion models."
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "Подготовка к загрузке...",
            "connecting": "Подключение к серверу загрузки...",
            "completed": "Завершено",
-            "downloadComplete": "Загрузка успешно завершена"
+            "downloadComplete": "Загрузка успешно завершена",
+            "enableCivarchiveApi": "Включить CivArchive API как источник метаданных",
+            "enableCivarchiveApiHelp": "При включении CivArchive API используется как резервный источник метаданных моделей (например, для моделей, удалённых с CivitAI). Отключите, чтобы полностью избежать ограничений скорости CivArchive.",
+            "providerOrder": "Порядок резервных источников метаданных",
+            "providerOrderHelp": "CivitAI API всегда проверяется первым. Выберите порядок остальных источников при поиске метаданных.",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "Включить прокси на уровне приложения",
@@ -657,6 +683,33 @@
            "proxyPassword": "Пароль (необязательно)",
            "proxyPasswordPlaceholder": "пароль",
            "proxyPasswordHelp": "Пароль для аутентификации на прокси (если требуется)"
+        },
+        "aiProvider": {
+            "title": "Поставщик ИИ",
+            "provider": "Поставщик",
+            "providerHelp": "Выберите поставщика LLM. OpenAI и Ollama используют предустановленные API-эндпоинты. Пользовательский позволяет указать любой совместимый с OpenAI эндпоинт.",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama (локальный)",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "Пользовательский (совместимый с OpenAI)"
+            },
+            "apiBase": "Базовый URL API",
+            "apiBaseHelp": "Базовый URL для LLM API (например, https://api.openai.com/v1). Оставьте пустым, чтобы использовать значение по умолчанию.",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "API-ключ",
+            "apiKeyHelp": "Ваш API-ключ поставщика LLM. Хранится локально и никогда не отправляется на другие серверы, кроме выбранного поставщика LLM.",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "Не задан",
+            "apiKeyConfigured": "Настроен",
+            "apiKeySet": "Настроить",
+            "model": "Модель",
+            "modelHelp": "Имя модели для использования (например, deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). Проверьте доступные модели у вашего поставщика.",
+            "modelPlaceholder": "Выберите модель..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "Локальные версии",
                "versionsCountDesc": "Сначала больше версий",
                "versionsCountAsc": "Сначала меньше версий",
-                "versionIdDesc": "Сначала новые версии"
+                "versionIdDesc": "Сначала новые версии",
+                "random": "Случайно",
+                "randomAction": "Перемешать"
            },
            "refresh": {
                "title": "Обновить список моделей",
@@ -723,6 +778,7 @@
            "copyAll": "Копировать весь синтаксис",
            "refreshAll": "Обновить все метаданные",
            "repairMetadata": "Восстановить метаданные для выбранных",
+            "rematchMetadata": "Сопоставить выбранные с локальными моделями",
            "reimportMetadata": "Переимпортировать из источника",
            "checkUpdates": "Проверить обновления для выбранных",
            "moveAll": "Переместить все в папку",
@@ -735,6 +791,8 @@
            "deleteAll": "Удалить выбранные",
            "downloadMissingLoras": "Скачать отсутствующие LoRAs",
            "downloadExamples": "Загрузить примеры изображений",
+            "downloadMissingExamples": "Скачать недостающие",
+            "reprocessExamples": "Обработать всё заново",
            "clear": "Очистить выбор",
            "skipMetadataRefreshCount": "Пропустить（{count} моделей）",
            "resumeMetadataRefreshCount": "Возобновить（{count} моделей）",
@@ -754,12 +812,15 @@
                "completed": "Завершено: {success} перемещено, {skipped} пропущено, {failures} не удалось",
                "complete": "Автоматическая организация завершена",
                "error": "Ошибка: {error}"
-            }
+            },
+            "enrichHfAgent": "Обогатить HF метаданные (ИИ)"
        },
        "contextMenu": {
            "refreshMetadata": "Обновить данные Civitai",
            "checkUpdates": "Проверить обновления",
-            "relinkCivitai": "Пересвязать с Civitai",
+            "linkModel": "Связать модель",
+            "linkCivitai": "Пересвязать с Civitai",
+            "linkHuggingFace": "Связать с HuggingFace",
            "copySyntax": "Копировать синтаксис LoRA",
            "copyFilename": "Копировать имя файла модели",
            "copyRecipeSyntax": "Копировать синтаксис рецепта",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "Отправить в Workflow (Заменить)",
            "openExamples": "Открыть папку примеров",
            "downloadExamples": "Загрузить примеры изображений",
+            "downloadMissingExamples": "Скачать недостающие",
+            "reprocessExamples": "Обработать всё заново",
            "replacePreview": "Заменить превью",
            "setContentRating": "Установить рейтинг контента",
            "moveToFolder": "Переместить в папку",
            "repairMetadata": "Восстановить метаданные",
+            "rematchMetadata": "Сопоставить с локальными моделями",
            "reimportMetadata": "Переимпортировать из источника",
            "excludeModel": "Исключить модель",
            "restoreModel": "Восстановить модель",
@@ -778,7 +842,8 @@
            "shareRecipe": "Поделиться рецептом",
            "viewAllLoras": "Посмотреть все LoRAs",
            "downloadMissingLoras": "Загрузить отсутствующие LoRAs",
-            "deleteRecipe": "Удалить рецепт"
+            "deleteRecipe": "Удалить рецепт",
+            "enrichHfAgent": "Обогатить HF метаданные (ИИ)"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "Найдено {count} групп дубликатов",
+            "noGroups": "Дубликатов с текущим критерием не найдено",
            "keepLatest": "Оставить последние версии",
-            "deleteSelected": "Удалить выбранные"
+            "deleteSelected": "Удалить выбранные",
+            "includePromptLabel": "Учитывать запрос при поиске дубликатов",
+            "basis": {
+                "loraCombo": "Критерий: комбинация LoRA",
+                "loraComboAndPrompt": "Критерий: комбинация LoRA + запрос",
+                "hintLoraCombo": "Рецепты с одинаковыми LoRA и одинаковой силой группируются вместе.",
+                "hintPromptIncluded": "Рецепты группируются только при одинаковых LoRA с одинаковой силой И одинаковом запросе."
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "Подготовка загрузки...",
                "downloadedPreview": "Превью изображение загружено",
                "downloadingFile": "Загрузка файла {type}",
-                "finalizing": "Завершение загрузки..."
+                "finalizing": "Завершение загрузки...",
+                "cancelling": "Отмена загрузки...",
+                "cancelled": "Загрузка отменена"
            },
            "progress": {
                "currentFile": "Текущий файл:",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "Освобождает {size}",
            "title": "Удалить модель",
-            "message": "Вы уверены, что хотите удалить эту модель и все связанные файлы?"
+            "message": "Вы уверены, что хотите удалить эту модель и все связанные файлы?",
+            "recoverableWarning": "Файл будет удалён навсегда через 20 секунд, если вы не отмените действие."
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "Это действие можно отменить в течение 20 секунд."
        },
        "excludeModel": {
            "title": "Исключить модель",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "Введите путь к папке или выберите из дерева ниже...",
            "root": "Корень"
        },
+        "linkHuggingFace": {
+            "title": "Связать с HuggingFace",
+            "infoText": "Вставьте URL репозитория HuggingFace, чтобы связать эту модель с её источником. Это позволит обогащать метаданные с помощью ИИ.",
+            "urlLabel": "URL репозитория HuggingFace:",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "Введите полный URL репозитория HuggingFace.",
+            "confirmAction": "Сохранить и связать"
+        },
        "relinkCivitai": {
            "title": "Пересвязать с Civitai",
            "warning": "Предупреждение:",
@@ -1498,6 +1586,7 @@
                "empty": "Для этой модели пока нет истории версий.",
                "error": "Не удалось загрузить версии.",
                "missingModelId": "У этой модели отсутствует идентификатор модели Civitai.",
+                "hfGroupInfo": "Это группа моделей HuggingFace. Откройте библиотеку, чтобы увидеть все версии в сетке.",
                "confirm": {
                    "delete": "Удалить эту версию из библиотеки?"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "Скачать CSV",
            "columnModelName": "Имя модели",
            "columnError": "Ошибка"
+        },
+        "downloadBatchSummary": {
+            "title": "Сводка пакетной загрузки",
+            "statSuccess": "Успешно",
+            "statFailed": "Ошибки",
+            "statTotal": "Всего",
+            "successMessage": "Все {count} моделей успешно загружены",
+            "completedWithErrors": "Завершено с ошибками",
+            "failed": "Не удалось загрузить",
+            "failedItems": "Неудачные элементы ({count})",
+            "columnName": "Имя модели",
+            "columnError": "Ошибка",
+            "close": "Закрыть",
+            "copyReport": "Скопировать отчёт",
+            "retryFailed": "Повторить неудачные ({count})"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "Рецепт заменён в workflow",
            "recipeFailedToSend": "Не удалось отправить рецепт в workflow",
            "noMatchingNodes": "В текущем workflow нет совместимых узлов",
+            "noPromptTargets": "[TODO: Translate] No compatible prompt targets in the workflow.\nRight-click a node in ComfyUI → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "Целевой узел не выбран",
            "modelUpdated": "Модель обновлена в workflow",
            "modelFailed": "Не удалось обновить узел модели",
@@ -1700,7 +1805,13 @@
        "checkingUpdates": "Проверка обновлений...",
        "checkingMessage": "Пожалуйста, подождите, пока мы проверяем последнюю версию.",
        "showNotifications": "Показывать уведомления об обновлениях",
-        "latestBadge": "Последний",
+        "latestBadge": "Последняя",
+        "latestMain": "Ветка main",
+        "channel": "Канал обновлений",
+        "channels": {
+            "release": "Релиз",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "Подготовка обновления...",
            "installing": "Установка обновления...",
@@ -1721,6 +1832,15 @@
            "warning": "Предупреждение: Ночные сборки могут содержать экспериментальные функции и могут быть нестабильными.",
            "enable": "Включить ночные обновления"
        },
+        "channelSwitch": {
+            "nightlyTitle": "Переключиться на Nightly",
+            "nightlyMessage": "Переключение на Nightly инициализирует Git-репозиторий и отслеживает последние коммиты ветки main. Обновления чаще, но могут быть нестабильными. Вы можете вернуться к Release в любое время.",
+            "releaseTitle": "Переключиться на Release",
+            "releaseMessage": "Переключение на Release выполнит checkout последнего стабильного тега. Вы можете вернуться к Nightly в любое время.",
+            "switching": "Переключение на канал {channel}...",
+            "completed": "Успешно переключено на канал {channel}",
+            "failed": "Не удалось переключить канал"
+        },
        "banners": {
            "recent": "Недавние уведомления",
            "empty": "Недавних баннеров нет.",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "Восстановление завершено: {repaired} восстановлено, {skipped} пропущено (из {total})",
            "repairBulkSkipped": "Ни один из {total} выбранных рецептов не требует восстановления",
            "repairBulkFailed": "Не удалось восстановить выбранные рецепты: {message}",
+            "rematchComplete": "Сопоставлено записей: {entries} в рецептах: {recipes}",
+            "rematchCompleteErrors": "Сопоставлено записей: {entries} в рецептах: {recipes}, ошибок: {failures}",
+            "rematchAllFailed": "Не удалось сопоставить: {failures} из {total} выбранных рецептов",
+            "rematchUnmatched": "Не найдено локального сопоставления для {entries} записей в {recipes} рецептах",
+            "rematchSkipped": "Ни один из {total} выбранных рецептов не требует сопоставления",
+            "rematchFailed": "Не удалось сопоставить выбранные рецепты: {message}",
            "reimporting": "Переимпорт рецепта из источника...",
            "reimportSuccess": "Рецепт успешно переимпортирован",
            "reimportBulkComplete": "Переимпорт завершён: {completed} переимпортировано, {failed} ошибок (из {total})",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "Имя пресета должно содержать не более {max} символов",
            "presetNameInvalidChars": "Имя пресета содержит недопустимые символы",
            "presetNameExists": "Пресет с таким именем уже существует",
-            "maxPresetsReached": "Допустимо максимум {max} пресетов. Удалите один, чтобы добавить больше.",
            "presetNotFound": "Пресет не найден",
            "invalidPreset": "Недопустимые данные пресета",
            "deletePresetFailed": "Не удалось удалить пресет",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "Примеры изображений {action} завершены",
            "imagesFailed": "Примеры изображений {action} не удались",
            "loadError": "Ошибка загрузки downloads: {message}",
-            "downloadError": "Ошибка загрузки: {message}"
+            "downloadError": "Ошибка загрузки: {message}",
+            "downloadStopped": "Загрузка отменена"
        },
        "import": {
            "folderTreeFailed": "Не удалось загрузить дерево папок",
@@ -1993,6 +2119,14 @@
            "updateFailed": "Не удалось обновить триггерные слова",
            "copyFailed": "Копирование не удалось"
        },
+        "undo": {
+            "action": "Отменить",
+            "deleted": "Удалено: {name}",
+            "deletedBulk": "Удалено: {count} шт.",
+            "expired": "Время отмены истекло. Элемент был удалён навсегда.",
+            "failed": "Не удалось отменить: {error}",
+            "restored": "Элемент восстановлен"
+        },
        "virtual": {
            "loadFailed": "Не удалось загрузить элементы",
            "loadMoreFailed": "Не удалось загрузить больше элементов",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "Не удалось установить рейтинг контента: {message}",
            "relinkSuccess": "Модель успешно пересвязана с Civitai",
            "relinkFailed": "Ошибка: {message}",
+            "linkHfSuccess": "Модель успешно связана с HuggingFace",
+            "linkHfFailed": "Ошибка: {message}",
            "fetchMetadataFirst": "Пожалуйста, сначала получите метаданные с CivitAI",
            "noCivitaiInfo": "Информация CivitAI недоступна",
            "missingHash": "Хеш модели недоступен"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "Скопировано в буфер обмена",
            "downloadStarted": "Загрузка начата"
+        },
+        "agent": {
+            "llmNotConfigured": "Поставщик ИИ не настроен. Включите его в Настройки → Поставщик ИИ.",
+            "enrichStarted": "Обогащение метаданных с помощью ИИ...",
+            "enrichComplete": "Обогащение метаданных завершено: {{summary}}",
+            "enrichFailed": "Ошибка обогащения метаданных: {{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "修复已取消。已修复 {count} 个配方。",
            "error": "配方修复失败：{message}"
        },
+        "rematchRecipes": {
+            "label": "将食谱重新匹配到本地模型",
+            "loading": "正在将食谱重新匹配到本地模型...",
+            "success": "已匹配 {entries} 个条目，涉及 {recipes} 个食谱",
+            "successErrors": "已匹配 {entries} 个条目，涉及 {recipes} 个食谱，{failures} 个失败",
+            "allFailed": "{failures}/{total} 个食谱重新匹配失败",
+            "noMatch": "在 {recipes} 个食谱中未找到 {entries} 个条目的本地匹配",
+            "cancelled": "已取消重新匹配。{recipes} 个食谱已更新（{entries} 个条目）。",
+            "error": "食谱重新匹配失败：{message}"
+        },
        "manageExcludedModels": {
            "label": "管理已排除的模型"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "预设名称...",
            "baseModel": "基础模型",
            "baseModelSearchPlaceholder": "搜索基础模型...",
-            "modelTags": "标签（前20）",
+            "modelTags": "标签",
            "modelTypes": "模型类型",
            "license": "许可证",
            "noCreditRequired": "无需署名",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "允许出售生成的图片",
            "noCreditRequiredTooltip": "使用模型时无需注明原作者",
            "noTags": "无标签",
+            "tagSearchPlaceholder": "搜索标签...",
+            "noTagMatches": "没有匹配当前搜索的标签。",
            "autoTags": "自动标签",
            "noBaseModelMatches": "没有基础模型符合当前搜索。",
            "clearAll": "清除所有筛选",
@@ -447,6 +459,12 @@
                "compact": "7（1080p），8（2K），10（4K）"
            },
            "displayDensityWarning": "警告：高密度可能导致资源有限的系统性能下降。",
+            "recipesLayout": "配方布局",
+            "recipesLayoutHelp": "选择配方卡片的排列方式：统一网格，或保留每张图片原始宽高比的瀑布流（Pinterest 风格）布局。",
+            "recipesLayoutOptions": {
+                "grid": "网格",
+                "masonry": "瀑布流"
+            },
            "showFolderSidebar": "显示文件夹侧边栏",
            "showFolderSidebarHelp": "在模型页面启用或禁用文件夹导航侧边栏。关闭后，侧边栏和悬停区域将保持隐藏。",
            "cardInfoDisplay": "卡片信息显示",
@@ -505,7 +523,9 @@
            "saveSuccess": "额外文件夹路径已更新，需要重启才能生效。",
            "saveError": "更新额外文件夹路径失败：{message}",
            "validation": {
-                "duplicatePath": "此路径已配置"
+                "duplicatePath": "此路径已配置",
+                "checkpointUnetOverlap": "checkpoints 和 diffusion models 不能使用相同的路径：{paths}",
+                "checkpointUnetOverlapInline": "此路径已被用于另一种模型类型。请为 checkpoints 和 diffusion models 使用不同的文件夹。"
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "正在准备下载...",
            "connecting": "正在连接下载服务器...",
            "completed": "已完成",
-            "downloadComplete": "下载成功完成"
+            "downloadComplete": "下载成功完成",
+            "enableCivarchiveApi": "启用 CivArchive API 作为元数据提供者",
+            "enableCivarchiveApiHelp": "开启后，CivArchive API 将作为模型元数据的备用来源（例如用于已从 CivitAI 删除的模型）。关闭可完全避免 CivArchive 的速率限制。",
+            "providerOrder": "元数据提供者回退顺序",
+            "providerOrderHelp": "CivitAI API 始终优先尝试。选择查找元数据时其余提供者的顺序。",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "启用应用级代理",
@@ -657,6 +683,33 @@
            "proxyPassword": "密码 (可选)",
            "proxyPasswordPlaceholder": "密码",
            "proxyPasswordHelp": "代理认证的密码 (如果需要)"
+        },
+        "aiProvider": {
+            "title": "AI 提供商",
+            "provider": "提供商",
+            "providerHelp": "选择您的 LLM 提供商。OpenAI 和 Ollama 使用预设的 API 端点。自定义允许您指定任何兼容 OpenAI 的端点。",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama（本地）",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "自定义（OpenAI 兼容）"
+            },
+            "apiBase": "API 基础地址",
+            "apiBaseHelp": "LLM API 的基础地址。选择预设或输入自定义地址，下拉框显示所有支持的提供商预设。",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "API 密钥",
+            "apiKeyHelp": "LLM 提供商的 API 密钥。本地存储，除您选择的 LLM 提供商外不会发送到任何服务器。",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "未设置",
+            "apiKeyConfigured": "已配置",
+            "apiKeySet": "设置",
+            "model": "模型",
+            "modelHelp": "要使用的模型。从下拉框选择（从提供商获取）或输入自定义模型名称。",
+            "modelPlaceholder": "选择一个模型..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "本地版本数",
                "versionsCountDesc": "版本数从多到少",
                "versionsCountAsc": "版本数从少到多",
-                "versionIdDesc": "最新版本优先"
+                "versionIdDesc": "最新版本优先",
+                "random": "随机",
+                "randomAction": "随机排序（洗牌）"
            },
            "refresh": {
                "title": "刷新模型列表",
@@ -723,6 +778,7 @@
            "copyAll": "复制所选中语法",
            "refreshAll": "刷新所选中元数据",
            "repairMetadata": "修复所选中元数据",
+            "rematchMetadata": "将所选中重新匹配到本地模型",
            "reimportMetadata": "从源重新导入",
            "checkUpdates": "检查所选更新",
            "moveAll": "移动所选中到文件夹",
@@ -735,6 +791,8 @@
            "deleteAll": "删除已选",
            "downloadMissingLoras": "下载缺失的 LoRAs",
            "downloadExamples": "下载示例图片",
+            "downloadMissingExamples": "下载缺失的",
+            "reprocessExamples": "重新处理全部",
            "clear": "清除选择",
            "skipMetadataRefreshCount": "跳过（{count} 个模型）",
            "resumeMetadataRefreshCount": "恢复（{count} 个模型）",
@@ -754,12 +812,15 @@
                "completed": "完成：已移动 {success} 个，跳过 {skipped} 个，失败 {failures} 个",
                "complete": "自动整理已完成",
                "error": "错误：{error}"
-            }
+            },
+            "enrichHfAgent": "AI HF 元数据增强"
        },
        "contextMenu": {
            "refreshMetadata": "刷新 Civitai 数据",
            "checkUpdates": "检查更新",
-            "relinkCivitai": "重新关联到 Civitai",
+            "linkModel": "链接模型",
+            "linkCivitai": "链接到 Civitai",
+            "linkHuggingFace": "链接到 HuggingFace",
            "copySyntax": "复制 LoRA 语法",
            "copyFilename": "复制模型文件名",
            "copyRecipeSyntax": "复制配方语法",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "发送到工作流（替换）",
            "openExamples": "打开示例文件夹",
            "downloadExamples": "下载示例图片",
+            "downloadMissingExamples": "下载缺失的",
+            "reprocessExamples": "重新处理全部",
            "replacePreview": "替换预览",
            "setContentRating": "设置内容评级",
            "moveToFolder": "移动到文件夹",
            "repairMetadata": "修复元数据",
+            "rematchMetadata": "重新匹配到本地模型",
            "reimportMetadata": "从源重新导入",
            "excludeModel": "排除模型",
            "restoreModel": "恢复模型",
@@ -778,7 +842,8 @@
            "shareRecipe": "分享配方",
            "viewAllLoras": "查看所有 LoRA",
            "downloadMissingLoras": "下载缺失的 LoRA",
-            "deleteRecipe": "删除配方"
+            "deleteRecipe": "删除配方",
+            "enrichHfAgent": "AI HF 元数据增强"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "发现 {count} 个重复组",
+            "noGroups": "按当前判重依据未找到重复组",
            "keepLatest": "保留最新版本",
-            "deleteSelected": "删除已选"
+            "deleteSelected": "删除已选",
+            "includePromptLabel": "将提示词纳入判重",
+            "basis": {
+                "loraCombo": "判重依据：LoRA 组合",
+                "loraComboAndPrompt": "判重依据：LoRA 组合 + 提示词",
+                "hintLoraCombo": "使用相同 LoRA（强度一致）的配方会被分组。",
+                "hintPromptIncluded": "仅当配方使用相同的 LoRA（强度一致）且提示词相同时才会被分组。"
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "正在准备下载...",
                "downloadedPreview": "预览图片已下载",
                "downloadingFile": "正在下载 {type} 文件",
-                "finalizing": "正在完成下载..."
+                "finalizing": "正在完成下载...",
+                "cancelling": "取消下载中...",
+                "cancelled": "下载已取消"
            },
            "progress": {
                "currentFile": "当前文件：",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "释放 {size}",
            "title": "删除模型",
-            "message": "你确定要删除此模型及所有相关文件吗？"
+            "message": "你确定要删除此模型及所有相关文件吗？",
+            "recoverableWarning": "如果不撤销，文件将在 20 秒后被永久删除。"
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "此操作可在 20 秒内撤销。"
        },
        "excludeModel": {
            "title": "排除模型",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "输入文件夹路径或从下方树中选择...",
            "root": "根目录"
        },
+        "linkHuggingFace": {
+            "title": "链接到 HuggingFace",
+            "infoText": "粘贴 HuggingFace 仓库 URL 以关联此模型。关联后可启用 AI 元数据增强功能。",
+            "urlLabel": "HuggingFace 仓库 URL：",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "请输入完整的 HuggingFace 仓库 URL。",
+            "confirmAction": "保存并链接"
+        },
        "relinkCivitai": {
            "title": "重新关联到 Civitai",
            "warning": "警告：",
@@ -1498,6 +1586,7 @@
                "empty": "该模型还没有版本历史。",
                "error": "加载版本失败。",
                "missingModelId": "该模型缺少 Civitai 模型 ID。",
+                "hfGroupInfo": "这是一个 HuggingFace 模型组。打开库页面即可在网格中查看所有版本。",
                "confirm": {
                    "delete": "从库中删除此版本？"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "下载 CSV",
            "columnModelName": "模型名称",
            "columnError": "错误"
+        },
+        "downloadBatchSummary": {
+            "title": "批量下载摘要",
+            "statSuccess": "成功",
+            "statFailed": "失败",
+            "statTotal": "总数",
+            "successMessage": "全部 {count} 个模型下载成功",
+            "completedWithErrors": "已完成，但有错误",
+            "failed": "下载失败",
+            "failedItems": "失败项（{count}）",
+            "columnName": "模型名称",
+            "columnError": "错误",
+            "close": "关闭",
+            "copyReport": "复制报告",
+            "retryFailed": "重试失败项（{count}）"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "配方已替换到工作流",
            "recipeFailedToSend": "发送配方到工作流失败",
            "noMatchingNodes": "当前工作流中没有兼容的节点",
+            "noPromptTargets": "工作流中没有兼容的 prompt 目标节点。\n在 ComfyUI 中右键节点 → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "未选择目标节点",
            "modelUpdated": "模型已更新到工作流",
            "modelFailed": "更新模型节点失败",
@@ -1701,6 +1806,12 @@
        "checkingMessage": "请稍候，正在检查最新版本。",
        "showNotifications": "显示更新通知",
        "latestBadge": "最新",
+        "latestMain": "Main 分支",
+        "channel": "更新频道",
+        "channels": {
+            "release": "稳定版",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "正在准备更新...",
            "installing": "正在安装更新...",
@@ -1721,6 +1832,15 @@
            "warning": "警告：Nightly 版本可能包含实验性功能，可能不稳定。",
            "enable": "启用 Nightly 更新"
        },
+        "channelSwitch": {
+            "nightlyTitle": "切换到 Nightly",
+            "nightlyMessage": "切换到 Nightly 将初始化 Git 仓库并跟踪 main 分支的最新提交。更新更频繁但可能不稳定，可随时切回稳定版。",
+            "releaseTitle": "切换到稳定版",
+            "releaseMessage": "切换到稳定版将检出最新的发布标签。可随时切换回每日构建版。",
+            "switching": "正在切换到 {channel} 频道...",
+            "completed": "已切换到 {channel} 频道",
+            "failed": "切换频道失败"
+        },
        "banners": {
            "recent": "最近的通知",
            "empty": "暂无最近的横幅通知。",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "修复完成：{repaired} 个已修复，{skipped} 个已跳过（共 {total} 个）",
            "repairBulkSkipped": "所选 {total} 个配方无需修复",
            "repairBulkFailed": "修复所选配方失败：{message}",
+            "rematchComplete": "已匹配 {entries} 个条目，涉及 {recipes} 个食谱",
+            "rematchCompleteErrors": "已匹配 {entries} 个条目，涉及 {recipes} 个食谱，{failures} 个失败",
+            "rematchAllFailed": "{failures}/{total} 个所选食谱重新匹配失败",
+            "rematchUnmatched": "在 {recipes} 个食谱中未找到 {entries} 个条目的本地匹配",
+            "rematchSkipped": "{total} 个所选食谱均无需重新匹配",
+            "rematchFailed": "重新匹配所选食谱失败：{message}",
            "reimporting": "正在从源重新导入配方...",
            "reimportSuccess": "配方已从源重新导入成功",
            "reimportBulkComplete": "重新导入完成：{completed} 个已导入，{failed} 个失败（共 {total} 个）",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "预设名称不能超过 {max} 个字符",
            "presetNameInvalidChars": "预设名称包含无效字符",
            "presetNameExists": "已存在同名预设",
-            "maxPresetsReached": "最多允许 {max} 个预设。删除一个以添加更多。",
            "presetNotFound": "预设未找到",
            "invalidPreset": "无效的预设数据",
            "deletePresetFailed": "删除预设失败",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "示例图片{action}完成",
            "imagesFailed": "示例图片{action}失败",
            "loadError": "加载下载项出错：{message}",
-            "downloadError": "下载错误：{message}"
+            "downloadError": "下载错误：{message}",
+            "downloadStopped": "下载已取消"
        },
        "import": {
            "folderTreeFailed": "加载文件夹树失败",
@@ -1993,6 +2119,14 @@
            "updateFailed": "触发词更新失败",
            "copyFailed": "复制失败"
        },
+        "undo": {
+            "action": "撤销",
+            "deleted": "已删除 {name}",
+            "deletedBulk": "已删除 {count} 个项目",
+            "expired": "撤销窗口已过期，项目已被永久删除。",
+            "failed": "撤销失败：{error}",
+            "restored": "项目已恢复"
+        },
        "virtual": {
            "loadFailed": "加载项目失败",
            "loadMoreFailed": "加载更多项目失败",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "设置内容评级失败：{message}",
            "relinkSuccess": "模型已成功重新关联到 Civitai",
            "relinkFailed": "错误：{message}",
+            "linkHfSuccess": "模型已成功链接到 HuggingFace",
+            "linkHfFailed": "错误：{message}",
            "fetchMetadataFirst": "请先从 CivitAI 获取元数据",
            "noCivitaiInfo": "无 CivitAI 信息",
            "missingHash": "模型哈希不可用"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "已复制到剪贴板",
            "downloadStarted": "下载已开始"
+        },
+        "agent": {
+            "llmNotConfigured": "AI 提供商未配置。请在 设置 → AI 提供商 中进行配置。",
+            "enrichStarted": "正在使用 AI 增强元数据...",
+            "enrichComplete": "元数据增强完成：{{summary}}",
+            "enrichFailed": "元数据增强失败：{{error}}"
        }
    },
    "doctor": {
@@ -186,6 +186,16 @@
            "cancelled": "修復已取消。已修復 {count} 個配方。",
            "error": "配方修復失敗：{message}"
        },
+        "rematchRecipes": {
+            "label": "將食譜重新匹配到本地模型",
+            "loading": "正在將食譜重新匹配到本地模型...",
+            "success": "已匹配 {entries} 個條目，涉及 {recipes} 個食譜",
+            "successErrors": "已匹配 {entries} 個條目，涉及 {recipes} 個食譜，{failures} 個失敗",
+            "allFailed": "{failures}/{total} 個食譜重新匹配失敗",
+            "noMatch": "在 {recipes} 個食譜中找不到 {entries} 個條目的本地匹配",
+            "cancelled": "已取消重新匹配。{recipes} 個食譜已更新（{entries} 個條目）。",
+            "error": "食譜重新匹配失敗：{message}"
+        },
        "manageExcludedModels": {
            "label": "管理已排除的模型"
        },
@@ -233,7 +243,7 @@
            "presetNamePlaceholder": "預設名稱...",
            "baseModel": "基礎模型",
            "baseModelSearchPlaceholder": "搜尋基礎模型...",
-            "modelTags": "標籤（前 20）",
+            "modelTags": "標籤",
            "modelTypes": "模型類型",
            "license": "授權",
            "noCreditRequired": "無需署名",
@@ -241,6 +251,8 @@
            "allowSellingGeneratedContentTooltip": "允許出售生成的圖片",
            "noCreditRequiredTooltip": "使用模型時無需註明原作者",
            "noTags": "無標籤",
+            "tagSearchPlaceholder": "搜尋標籤...",
+            "noTagMatches": "沒有符合目前搜尋的標籤。",
            "autoTags": "自動標籤",
            "noBaseModelMatches": "沒有基礎模型符合目前的搜尋。",
            "clearAll": "清除所有篩選",
@@ -447,6 +459,12 @@
                "compact": "7（1080p）、8（2K）、10（4K）"
            },
            "displayDensityWarning": "警告：較高密度可能導致資源有限的系統效能下降。",
+            "recipesLayout": "配方版面",
+            "recipesLayoutHelp": "選擇配方卡片的排列方式：統一網格，或保留每張圖片原始寬高比的瀑布流（Pinterest 風格）版面。",
+            "recipesLayoutOptions": {
+                "grid": "網格",
+                "masonry": "瀑布流"
+            },
            "showFolderSidebar": "顯示資料夾側邊欄",
            "showFolderSidebarHelp": "在模型頁面啟用或停用資料夾導覽側邊欄。停用後，側邊欄與滑鼠懸停區域將保持隱藏。",
            "cardInfoDisplay": "卡片資訊顯示",
@@ -505,7 +523,9 @@
            "saveSuccess": "額外資料夾路徑已更新，需要重啟才能生效。",
            "saveError": "更新額外資料夾路徑失敗：{message}",
            "validation": {
-                "duplicatePath": "此路徑已設定"
+                "duplicatePath": "此路徑已設定",
+                "checkpointUnetOverlap": "checkpoints 和 diffusion models 不能使用相同的路徑：{paths}",
+                "checkpointUnetOverlapInline": "此路徑已被用於另一種模型類型。請為 checkpoints 和 diffusion models 使用不同的資料夾。"
            }
        },
        "priorityTags": {
@@ -638,7 +658,13 @@
            "preparing": "準備下載中...",
            "connecting": "正在連接下載伺服器...",
            "completed": "已完成",
-            "downloadComplete": "下載成功完成"
+            "downloadComplete": "下載成功完成",
+            "enableCivarchiveApi": "啟用 CivArchive API 作為中繼資料提供者",
+            "enableCivarchiveApiHelp": "開啟後，CivArchive API 將作為模型中繼資料的備用來源（例如用於已從 CivitAI 刪除的模型）。關閉可完全避免 CivArchive 的速率限制。",
+            "providerOrder": "中繼資料提供者回退順序",
+            "providerOrderHelp": "CivitAI API 始終優先嘗試。選擇查詢中繼資料時其餘提供者的順序。",
+            "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+            "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
        },
        "proxySettings": {
            "enableProxy": "啟用應用程式代理",
@@ -657,6 +683,33 @@
            "proxyPassword": "密碼（選填）",
            "proxyPasswordPlaceholder": "password",
            "proxyPasswordHelp": "代理驗證所需的密碼（如有需要）"
+        },
+        "aiProvider": {
+            "title": "AI 提供者",
+            "provider": "提供者",
+            "providerHelp": "選擇您的 LLM 提供者。OpenAI 和 Ollama 使用預設 API 端點。自訂允許您指定任何相容 OpenAI 的端點。",
+            "providerOptions": {
+                "openai": "OpenAI",
+                "ollama": "Ollama（本地）",
+                "deepseek": "DeepSeek",
+                "groq": "Groq",
+                "openrouter": "OpenRouter",
+                "google": "Gemini",
+                "opencode-go": "OpenCode Go",
+                "custom": "自訂（OpenAI 相容）"
+            },
+            "apiBase": "API 基礎網址",
+            "apiBaseHelp": "LLM API 的基礎網址。選擇預設或輸入自訂網址，下拉選單顯示所有支援的提供者預設。",
+            "apiBasePlaceholder": "https://api.openai.com/v1",
+            "apiKey": "API 金鑰",
+            "apiKeyHelp": "LLM 提供者的 API 金鑰。儲存在本地，除您選擇的 LLM 提供者外不會傳送到任何伺服器。",
+            "apiKeyPlaceholder": "sk-...",
+            "apiKeyNotSet": "未設定",
+            "apiKeyConfigured": "已設定",
+            "apiKeySet": "設定",
+            "model": "模型",
+            "modelHelp": "要使用的模型。從下拉選單選擇（從提供者取得）或輸入自訂模型名稱。",
+            "modelPlaceholder": "選擇一個模型..."
        }
    },
    "loras": {
@@ -678,7 +731,9 @@
                "versionsCount": "本地版本數",
                "versionsCountDesc": "版本數從多到少",
                "versionsCountAsc": "版本數從少到多",
-                "versionIdDesc": "最新版本優先"
+                "versionIdDesc": "最新版本優先",
+                "random": "隨機",
+                "randomAction": "隨機排序（洗牌）"
            },
            "refresh": {
                "title": "重新整理模型列表",
@@ -723,6 +778,7 @@
            "copyAll": "複製全部語法",
            "refreshAll": "刷新全部 metadata",
            "repairMetadata": "修復所選中元數據",
+            "rematchMetadata": "將所選中重新匹配到本地模型",
            "reimportMetadata": "從來源重新匯入",
            "checkUpdates": "檢查所選更新",
            "moveAll": "全部移動到資料夾",
@@ -735,6 +791,8 @@
            "deleteAll": "刪除所選",
            "downloadMissingLoras": "下載缺失的 LoRAs",
            "downloadExamples": "下載範例圖片",
+            "downloadMissingExamples": "下載缺少的",
+            "reprocessExamples": "重新處理全部",
            "clear": "清除選取",
            "skipMetadataRefreshCount": "跳過（{count} 個模型）",
            "resumeMetadataRefreshCount": "恢復（{count} 個模型）",
@@ -754,12 +812,15 @@
                "completed": "完成：已移動 {success}，已略過 {skipped}，失敗 {failures}",
                "complete": "自動整理完成",
                "error": "錯誤：{error}"
-            }
+            },
+            "enrichHfAgent": "AI HF 中繼資料增強"
        },
        "contextMenu": {
            "refreshMetadata": "刷新 Civitai 資料",
            "checkUpdates": "檢查更新",
-            "relinkCivitai": "重新連結 Civitai",
+            "linkModel": "連結模型",
+            "linkCivitai": "連結到 Civitai",
+            "linkHuggingFace": "連結到 HuggingFace",
            "copySyntax": "複製 LoRA 語法",
            "copyFilename": "複製模型檔名",
            "copyRecipeSyntax": "複製配方語法",
@@ -767,10 +828,13 @@
            "sendToWorkflowReplace": "傳送到工作流（取代）",
            "openExamples": "開啟範例資料夾",
            "downloadExamples": "下載範例圖片",
+            "downloadMissingExamples": "下載缺少的",
+            "reprocessExamples": "重新處理全部",
            "replacePreview": "更換預覽圖",
            "setContentRating": "設定內容分級",
            "moveToFolder": "移動到資料夾",
            "repairMetadata": "修復元數據",
+            "rematchMetadata": "重新匹配到本地模型",
            "reimportMetadata": "從來源重新匯入",
            "excludeModel": "排除模型",
            "restoreModel": "還原模型",
@@ -778,7 +842,8 @@
            "shareRecipe": "分享配方",
            "viewAllLoras": "檢視全部 LoRA",
            "downloadMissingLoras": "下載缺少的 LoRA",
-            "deleteRecipe": "刪除配方"
+            "deleteRecipe": "刪除配方",
+            "enrichHfAgent": "AI HF 中繼資料增強"
        }
    },
    "recipes": {
@@ -870,8 +935,16 @@
        },
        "duplicates": {
            "found": "發現 {count} 組重複項",
+            "noGroups": "按目前判重依據未找到重複組",
            "keepLatest": "保留最新版本",
-            "deleteSelected": "刪除所選"
+            "deleteSelected": "刪除所選",
+            "includePromptLabel": "將提示詞納入判重",
+            "basis": {
+                "loraCombo": "判重依據：LoRA 組合",
+                "loraComboAndPrompt": "判重依據：LoRA 組合 + 提示詞",
+                "hintLoraCombo": "使用相同 LoRA（強度一致）的配方會被分組。",
+                "hintPromptIncluded": "僅當配方使用相同的 LoRA（強度一致）且提示詞相同時才會被分組。"
+            }
        },
        "contextMenu": {
            "copyRecipe": {
@@ -1175,7 +1248,9 @@
                "preparing": "準備下載中...",
                "downloadedPreview": "已下載預覽圖片",
                "downloadingFile": "正在下載 {type} 檔案",
-                "finalizing": "完成下載中..."
+                "finalizing": "完成下載中...",
+                "cancelling": "取消下載中...",
+                "cancelled": "下載已取消"
            },
            "progress": {
                "currentFile": "目前檔案：",
@@ -1202,8 +1277,13 @@
            }
        },
        "deleteModel": {
+            "freesSpace": "釋放 {size}",
            "title": "刪除模型",
-            "message": "您確定要刪除此模型及所有相關檔案嗎？"
+            "message": "您確定要刪除此模型及所有相關檔案嗎？",
+            "recoverableWarning": "如果未復原，檔案將在 20 秒後被永久刪除。"
+        },
+        "deleteRecipe": {
+            "recoverableWarning": "此操作可在 20 秒內復原。"
        },
        "excludeModel": {
            "title": "排除模型",
@@ -1291,6 +1371,14 @@
            "pathPlaceholder": "輸入資料夾路徑或從下方樹狀結構選擇...",
            "root": "根目錄"
        },
+        "linkHuggingFace": {
+            "title": "連結到 HuggingFace",
+            "infoText": "貼上 HuggingFace 倉庫 URL 以關聯此模型。關聯後可啟用 AI 中繼資料增強功能。",
+            "urlLabel": "HuggingFace 倉庫 URL：",
+            "urlPlaceholder": "https://huggingface.co/user/repo",
+            "helpText": "請輸入完整的 HuggingFace 倉庫 URL。",
+            "confirmAction": "儲存並連結"
+        },
        "relinkCivitai": {
            "title": "重新連結至 Civitai",
            "warning": "警告：",
@@ -1498,6 +1586,7 @@
                "empty": "此模型尚無版本歷史。",
                "error": "載入版本失敗。",
                "missingModelId": "此模型缺少 Civitai 模型 ID。",
+                "hfGroupInfo": "這是一個 HuggingFace 模型組。打開庫頁面即可在網格中查看所有版本。",
                "confirm": {
                    "delete": "要從庫中刪除此版本嗎？"
                },
@@ -1524,6 +1613,21 @@
            "downloadCsv": "下載 CSV",
            "columnModelName": "模型名稱",
            "columnError": "錯誤"
+        },
+        "downloadBatchSummary": {
+            "title": "批次下載摘要",
+            "statSuccess": "成功",
+            "statFailed": "失敗",
+            "statTotal": "總數",
+            "successMessage": "全部 {count} 個模型下載成功",
+            "completedWithErrors": "已完成，但有錯誤",
+            "failed": "下載失敗",
+            "failedItems": "失敗項目（{count}）",
+            "columnName": "模型名稱",
+            "columnError": "錯誤",
+            "close": "關閉",
+            "copyReport": "複製報告",
+            "retryFailed": "重試失敗項目（{count}）"
        }
    },
    "modelTags": {
@@ -1622,6 +1726,7 @@
            "recipeReplaced": "配方已取代於工作流",
            "recipeFailedToSend": "傳送配方到工作流失敗",
            "noMatchingNodes": "目前工作流程中沒有相容的節點",
+            "noPromptTargets": "工作流中沒有相容的 prompt 目標節點。\n在 ComfyUI 中右鍵節點 → Mark as → Send Prompt Target",
            "noTargetNodeSelected": "未選擇目標節點",
            "modelUpdated": "模型已更新到工作流",
            "modelFailed": "更新模型節點失敗",
@@ -1701,6 +1806,12 @@
        "checkingMessage": "請稍候，正在檢查最新版本。",
        "showNotifications": "顯示更新通知",
        "latestBadge": "最新",
+        "latestMain": "Main 分支",
+        "channel": "更新頻道",
+        "channels": {
+            "release": "稳定版",
+            "nightly": "Nightly"
+        },
        "updateProgress": {
            "preparing": "正在準備更新...",
            "installing": "正在安裝更新...",
@@ -1721,6 +1832,15 @@
            "warning": "警告：Nightly 版本可能包含實驗性功能且可能不穩定。",
            "enable": "啟用 Nightly 更新"
        },
+        "channelSwitch": {
+            "nightlyTitle": "切换到 Nightly",
+            "nightlyMessage": "切换到 Nightly 将初始化 Git 仓库并跟踪 main 分支的最新提交。更新更频繁但可能不稳定，可随时切回稳定版。",
+            "releaseTitle": "切换到稳定版",
+            "releaseMessage": "切換到穩定版將檢出最新的發布標籤。可隨時切換回每日構建版。",
+            "switching": "正在切換到 {channel} 頻道...",
+            "completed": "已切換到 {channel} 頻道",
+            "failed": "切換頻道失敗"
+        },
        "banners": {
            "recent": "最新通知",
            "empty": "目前沒有最近的橫幅通知。",
@@ -1857,6 +1977,12 @@
            "repairBulkComplete": "修復完成：{repaired} 個已修復，{skipped} 個已跳過（共 {total} 個）",
            "repairBulkSkipped": "所選 {total} 個配方無需修復",
            "repairBulkFailed": "修復所選配方失敗：{message}",
+            "rematchComplete": "已匹配 {entries} 個條目，涉及 {recipes} 個食譜",
+            "rematchCompleteErrors": "已匹配 {entries} 個條目，涉及 {recipes} 個食譜，{failures} 個失敗",
+            "rematchAllFailed": "{failures}/{total} 個所選食譜重新匹配失敗",
+            "rematchUnmatched": "在 {recipes} 個食譜中找不到 {entries} 個條目的本地匹配",
+            "rematchSkipped": "{total} 個所選食譜均無需重新匹配",
+            "rematchFailed": "重新匹配所選食譜失敗：{message}",
            "reimporting": "正在從來源重新匯入配方...",
            "reimportSuccess": "配方已從來源重新匯入成功",
            "reimportBulkComplete": "重新匯入完成：{completed} 個已匯入，{failed} 個失敗（共 {total} 個）",
@@ -1965,7 +2091,6 @@
            "presetNameTooLong": "預設名稱不能超過 {max} 個字元",
            "presetNameInvalidChars": "預設名稱包含無效字元",
            "presetNameExists": "已存在同名預設",
-            "maxPresetsReached": "最多允許 {max} 個預設。刪除一個以新增更多。",
            "presetNotFound": "預設未找到",
            "invalidPreset": "無效的預設資料",
            "deletePresetFailed": "刪除預設失敗",
@@ -1975,7 +2100,8 @@
            "imagesCompleted": "範例圖片{action}完成",
            "imagesFailed": "範例圖片{action}失敗",
            "loadError": "載入下載時發生錯誤：{message}",
-            "downloadError": "下載錯誤：{message}"
+            "downloadError": "下載錯誤：{message}",
+            "downloadStopped": "下載已取消"
        },
        "import": {
            "folderTreeFailed": "載入資料夾樹狀結構失敗",
@@ -1993,6 +2119,14 @@
            "updateFailed": "更新觸發詞失敗",
            "copyFailed": "複製失敗"
        },
+        "undo": {
+            "action": "復原",
+            "deleted": "已刪除 {name}",
+            "deletedBulk": "已刪除 {count} 個項目",
+            "expired": "復原視窗已過期，項目已被永久刪除。",
+            "failed": "復原失敗：{error}",
+            "restored": "項目已還原"
+        },
        "virtual": {
            "loadFailed": "載入項目失敗",
            "loadMoreFailed": "載入更多項目失敗",
@@ -2020,6 +2154,8 @@
            "contentRatingFailed": "設定內容分級失敗：{message}",
            "relinkSuccess": "模型已成功重新連結至 Civitai",
            "relinkFailed": "錯誤：{message}",
+            "linkHfSuccess": "模型已成功連結到 HuggingFace",
+            "linkHfFailed": "錯誤：{message}",
            "fetchMetadataFirst": "請先從 CivitAI 取得 metadata",
            "noCivitaiInfo": "無 CivitAI 資訊",
            "missingHash": "模型雜湊不可用"
@@ -2081,6 +2217,12 @@
            "moveFailed": "Failed to move item: {message}",
            "copiedToClipboard": "已複製到剪貼簿",
            "downloadStarted": "下載已開始"
+        },
+        "agent": {
+            "llmNotConfigured": "AI 提供者尚未設定。請在 設定 → AI 提供者 中進行設定。",
+            "enrichStarted": "正在使用 AI 增強中繼資料...",
+            "enrichComplete": "中繼資料增強完成：{{summary}}",
+            "enrichFailed": "中繼資料增強失敗：{{error}}"
        }
    },
    "doctor": {
@@ -1,13 +1,19 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 import os
 import platform
 import posixpath
 import threading
 from pathlib import Path
-import folder_paths  # type: ignore
+import folder_paths  # pyright: ignore[reportMissingImports]
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Set, Tuple
 import logging
 import json
 import urllib.parse
+import sys as _sys
+import types as _types
 import time

 from .utils.cache_paths import CacheType, get_cache_file_path, get_legacy_cache_paths
@@ -88,7 +94,7 @@ def _resolve_valid_default_root(


 def _normalize_folder_paths_for_comparison(
-    folder_paths: Mapping[str, Iterable[str]],
+    folder_paths: Mapping[str, Any],
 ) -> Dict[str, Set[str]]:
    """Normalize folder paths for comparison across libraries."""

@@ -175,8 +181,7 @@ class Config:

        # Load extra folder paths from active library settings before symlink scan
        # so both primary and extra paths are discovered in a single pass.
-        if not standalone_mode:
-            self._load_extra_paths_from_settings()
+        self._load_extra_paths_from_settings()

        # Scan symbolic links during initialization
        self._initialize_symlink_mappings()
@@ -191,7 +196,7 @@ class Config:
        Called during ``Config.__init__`` before the symlink scan so both primary and
        extra paths are discovered in a single pass.  Mirrors the extra-path
        portion of ``_apply_library_paths`` without replacing the primary roots
-        that were already resolved from ComfyUI's ``folder_paths``.
+        that were already resolved via ``folder_paths.get_folder_paths``.
        """
        try:
            from .services.settings_manager import get_settings_manager
@@ -207,6 +212,12 @@ class Config:
            if not isinstance(library_config, dict):
                return

+            # Always read recipes_path — it is independent of extra folder paths
+            # and must be set before any early returns below.
+            recipes_path = library_config.get("recipes_path", "")
+            if isinstance(recipes_path, str) and recipes_path:
+                self.recipes_path = recipes_path
+
            extra_folder_paths = library_config.get("extra_folder_paths")
            if not isinstance(extra_folder_paths, dict):
                return
@@ -232,10 +243,6 @@ class Config:
                extra_embedding
            )

-            recipes_path = library_config.get("recipes_path", "")
-            if isinstance(recipes_path, str) and recipes_path:
-                self.recipes_path = recipes_path
-
            if self.extra_loras_roots:
                logger.info(
                    "Found extra LoRA roots:"
@@ -356,6 +363,47 @@ class Config:
                        "Failed to rename legacy 'default' library: %s", rename_error
                    )

+            # Clean up a stale "default" library entry that has no meaningful
+            # paths configured (e.g. leftover bootstrap artifact).  This only
+            # fires when "comfyui" already exists so we never delete the last
+            # remaining library.
+            if (
+                "default" in libraries
+                and "comfyui" in libraries
+                and isinstance(default_library, Mapping)
+            ):
+                default_folder_paths = _normalize_library_folder_paths(
+                    default_library
+                )
+                default_extra_paths = default_library.get("extra_folder_paths", {})
+                has_meaningful_paths = bool(default_folder_paths) or bool(
+                    default_extra_paths
+                ) or any(
+                    default_library.get(key)
+                    for key in (
+                        "default_lora_root",
+                        "default_checkpoint_root",
+                        "default_unet_root",
+                        "default_embedding_root",
+                        "recipes_path",
+                    )
+                )
+                if not has_meaningful_paths:
+                    try:
+                        settings_service.delete_library("default")
+                        libraries_changed = True
+                        logger.info(
+                            "Removed stale 'default' library entry "
+                            "with no meaningful paths configured"
+                        )
+                        libraries = settings_service.get_libraries()
+                        comfy_library = libraries.get("comfyui", {})
+                    except Exception as delete_error:
+                        logger.debug(
+                            "Failed to remove stale 'default' library: %s",
+                            delete_error,
+                        )
+
            default_lora_root = _resolve_valid_default_root(
                comfy_library.get("default_lora_root", ""),
                list(self.loras_roots or []),
@@ -438,7 +486,7 @@ class Config:
                    import ctypes

                    FILE_ATTRIBUTE_REPARSE_POINT = 0x400
-                    attrs = ctypes.windll.kernel32.GetFileAttributesW(str(path))  # type: ignore[attr-defined]
+                    attrs = ctypes.windll.kernel32.GetFileAttributesW(str(path))  # pyright: ignore[reportAttributeAccessIssue]
                    return attrs != -1 and (attrs & FILE_ATTRIBUTE_REPARSE_POINT)
                except Exception as e:
                    logger.error(f"Error checking Windows reparse point: {e}")
@@ -447,7 +495,7 @@ class Config:
            logger.error(f"Error checking link status for {path}: {e}")
            return False

-    def _entry_is_symlink(self, entry: os.DirEntry) -> bool:
+    def _entry_is_symlink(self, entry: os.DirEntry[str]) -> bool:
        """Check if a directory entry is a symlink, including Windows junctions."""
        if entry.is_symlink():
            return True
@@ -456,7 +504,7 @@ class Config:
                import ctypes

                FILE_ATTRIBUTE_REPARSE_POINT = 0x400
-                attrs = ctypes.windll.kernel32.GetFileAttributesW(entry.path)  # type: ignore[attr-defined]
+                attrs = ctypes.windll.kernel32.GetFileAttributesW(entry.path)  # pyright: ignore[reportAttributeAccessIssue]
                return attrs != -1 and (attrs & FILE_ATTRIBUTE_REPARSE_POINT)
            except Exception:
                pass
@@ -1082,8 +1130,8 @@ class Config:

    def _apply_library_paths(
        self,
-        folder_paths: Mapping[str, Iterable[str]],
-        extra_folder_paths: Optional[Mapping[str, Iterable[str]]] = None,
+        folder_paths: Mapping[str, Any],
+        extra_folder_paths: Optional[Mapping[str, Any]] = None,
        recipes_path: str = "",
    ) -> None:
        self._path_mappings.clear()
@@ -1380,4 +1428,21 @@ class Config:


 # Global config instance
-config = Config()
+# NOTE: Guard against re-import.  When ServiceRegistry.get_lora_scanner() triggers
+# a fresh import of lora_scanner → config, we must NOT re-execute Config.__init__()
+# (which re-scans all roots, re-registers libraries, etc.).
+#
+# Strategy: store the config instance in a dedicated sentinel module
+# ('_lm_config_cache') that is NEVER removed from sys.modules (its key does
+# NOT start with 'py.'), so it survives re-imports of py.* modules.
+_CONFIG_SENTINEL = "_lm_config_cache"
+config: Config
+if _CONFIG_SENTINEL in _sys.modules:
+    # Re-import: reuse the existing singleton from the sentinel.
+    config = _sys.modules[_CONFIG_SENTINEL].config
+else:
+    config = Config()
+    # Register the sentinel so re-imports of py.config find us.
+    _sentinel_mod = _types.ModuleType(_CONFIG_SENTINEL)
+    setattr(_sentinel_mod, "config", config)
+    _sys.modules[_CONFIG_SENTINEL] = _sentinel_mod
@@ -14,7 +14,7 @@ standalone_mode = (
 if not standalone_mode:
    setup_logging()

-from server import PromptServer  # type: ignore
+from server import PromptServer  # pyright: ignore[reportMissingImports]

 from .config import config
 from .services.model_service_factory import (
@@ -25,10 +25,12 @@ from .routes.recipe_routes import RecipeRoutes
 from .routes.stats_routes import StatsRoutes
 from .routes.update_routes import UpdateRoutes
 from .routes.misc_routes import MiscRoutes
+from .routes.pending_delete_routes import PendingDeleteRoutes
 from .routes.preview_routes import PreviewRoutes
 from .routes.example_images_routes import ExampleImagesRoutes
 from .services.service_registry import ServiceRegistry
 from .services.settings_manager import get_settings_manager
+from .services.pending_delete_service import get_pending_delete_service
 from .utils.example_images_migration import ExampleImagesMigration
 from .services.websocket_manager import ws_manager
 from .services.example_images_cleanup_service import ExampleImagesCleanupService
@@ -170,6 +172,7 @@ class LoraManager:
        RecipeRoutes.setup_routes(app)
        UpdateRoutes.setup_routes(app)
        MiscRoutes.setup_routes(app)
+        PendingDeleteRoutes.setup_routes(app)
        ExampleImagesRoutes.setup_routes(app, ws_manager=ws_manager)
        PreviewRoutes.setup_routes(app)

@@ -208,6 +211,10 @@ class LoraManager:
            # Initialize WebSocket manager
            await ServiceRegistry.get_websocket_manager()

+            # Preload LLM model catalog (background task, non-blocking)
+            from .services.llm_service import LLMService
+            await LLMService.get_instance()
+
            # Initialize scanners in background
            lora_scanner = await ServiceRegistry.get_lora_scanner()
            checkpoint_scanner = await ServiceRegistry.get_checkpoint_scanner()
@@ -241,6 +248,20 @@ class LoraManager:
                cls._run_post_initialization_tasks(init_tasks), name="post_init_tasks"
            )

+            # Startup sweep: purge pending-delete batches that expired during a
+            # previous run. Non-blocking (fire-and-forget); purge_expired only
+            # removes already-expired batches, so a staged undo that survived a
+            # restart stays restorable. scan_roots=True runs the reconciliation
+            # pass first so leftover batches (the in-process registry is empty
+            # after a restart) are re-discovered on disk. Covers both plugin
+            # and standalone modes (StandaloneLoraManager reuses this
+            # classmethod).
+            pending_delete_service = await get_pending_delete_service()
+            asyncio.create_task(
+                pending_delete_service.purge_expired(scan_roots=True),
+                name="pending_delete_startup_sweep",
+            )
+
            logger.debug(
                "LoRA Manager: All services initialized and background tasks scheduled"
            )
@@ -445,5 +466,12 @@ class LoraManager:
                    scanner.cancel_task()
                    logger.debug("LoRA Manager: Cancelled %s", name)

+            # Close shared aiohttp sessions to avoid "Unclosed client session" warnings
+            try:
+                from py.routes.handlers.hf_handlers import close_hf_api_session
+                await close_hf_api_session()
+            except Exception as exc:
+                logger.debug("Error closing HF API session: %s", exc)
+
        except Exception as e:
            logger.error(f"Error during cleanup: {e}", exc_info=True)
@@ -22,7 +22,7 @@ if not standalone_mode:

        logger.info("ComfyUI Metadata Collector initialized")

-    def get_metadata(prompt_id=None):  # type: ignore[no-redef]
+    def get_metadata(prompt_id=None):  # pyright: ignore[reportRedeclaration]
        """Helper function to get metadata from the registry"""
        registry = MetadataRegistry()
        return registry.get_metadata(prompt_id)
@@ -31,6 +31,6 @@ else:
    def init():
        logger.info("ComfyUI Metadata Collector disabled in standalone mode")

-    def get_metadata(prompt_id=None):  # type: ignore[no-redef]
+    def get_metadata(prompt_id=None):  # pyright: ignore[reportRedeclaration]
        """Dummy implementation for standalone mode"""
        return {}
@@ -1,5 +1,11 @@
 """Constants used by the metadata collector"""

+# Sentinel value for clip_skip to distinguish "unconnected / widget default"
+# from "user wired value 0".  Both ComfyUI CLIPSetLastLayer (-24..-1) and
+# A1111 conventions treat 0 as meaningless for clip skipping, but users may
+# explicitly wire 0 to the overwrite node to express "no clip skip / default".
+CLIP_SKIP_SENTINEL = -25
+
 # Metadata categories
 MODELS = "models"
 PROMPTS = "prompts"
@@ -9,6 +15,14 @@ EMBEDDINGS = "embeddings"
 SIZE = "size"
 IMAGES = "images"
 IS_SAMPLER = "is_sampler"  # New constant to mark sampler nodes
+OVERWRITE = "overwrite"  # Manual metadata overwrite from MetadataOverwriteLM node
+
+# Field names that the MetadataOverwriteLM node and its extractor share
+METADATA_OVERWRITE_FIELDS = (
+    "prompt", "negative_prompt", "seed", "steps", "cfg_scale",
+    "sampler", "scheduler", "model", "loras", "size",
+    "clip_skip", "additional_data",
+)

 # Complete list of categories to track
-METADATA_CATEGORIES = [MODELS, PROMPTS, SAMPLING, LORAS, EMBEDDINGS, SIZE, IMAGES]
+METADATA_CATEGORIES = [MODELS, PROMPTS, SAMPLING, LORAS, EMBEDDINGS, SIZE, IMAGES, OVERWRITE]
@@ -16,7 +16,7 @@ class MetadataHook:
            execution = None
            try:
                # Try direct import first
-                import execution # type: ignore
+                import execution # pyright: ignore[reportMissingImports]
            except ImportError:
                # Try to locate from system modules
                for module_name in sys.modules:
@@ -83,7 +83,8 @@ class MetadataHook:
                        
                        # Record inputs before execution
                        if node_id is not None:
-                            registry.record_node_execution(node_id, class_type, input_data_all, None)
+                            return_types = getattr(obj, 'RETURN_TYPES', None)
+                            registry.record_node_execution(node_id, class_type, input_data_all, None, return_types=return_types)
                except Exception as e:
                    logger.error(f"Error collecting metadata (pre-execution): {str(e)}")
            
@@ -114,7 +115,8 @@ class MetadataHook:
                        
                        # Record outputs after execution
                        if node_id is not None:
-                            registry.update_node_execution(node_id, class_type, results)
+                            return_types = getattr(obj, 'RETURN_TYPES', None)
+                            registry.update_node_execution(node_id, class_type, results, return_types=return_types)
                except Exception as e:
                    logger.error(f"Error collecting metadata (post-execution): {str(e)}")
            
@@ -135,10 +137,13 @@ class MetadataHook:
                # Store the dynprompt reference for node lookups
                if hasattr(prompt, 'original_prompt'):
                    registry.set_current_prompt(prompt)
-            
+
+                # Store extra_data for accessing full workflow node properties
+                registry.set_extra_data(extra_data)
+
            # Execute the original function
            return original_execute(*args, **kwargs)
-            
+
        # Replace the functions
        execution._map_node_over_list = map_node_over_list_with_metadata
        execution.execute = execute_with_prompt_tracking
@@ -163,7 +168,8 @@ class MetadataHook:
                        class_type = obj.__class__.__name__
                        node_id = unique_id
                        if node_id is not None:
-                            registry.record_node_execution(node_id, class_type, input_data_all, None)
+                            return_types = getattr(obj, 'RETURN_TYPES', None)
+                            registry.record_node_execution(node_id, class_type, input_data_all, None, return_types=return_types)
                except Exception as e:
                    logger.error(f"Error collecting metadata (pre-execution): {str(e)}")

@@ -180,7 +186,8 @@ class MetadataHook:
                        class_type = obj.__class__.__name__
                        node_id = unique_id
                        if node_id is not None:
-                            registry.update_node_execution(node_id, class_type, results)
+                            return_types = getattr(obj, 'RETURN_TYPES', None)
+                            registry.update_node_execution(node_id, class_type, results, return_types=return_types)
                except Exception as e:
                    logger.error(f"Error collecting metadata (post-execution): {str(e)}")

@@ -202,6 +209,9 @@ class MetadataHook:
                if hasattr(prompt, 'original_prompt'):
                    registry.set_current_prompt(prompt)

+                # Store extra_data for accessing full workflow node properties
+                registry.set_extra_data(extra_data)
+
            # Execute the original function
            return await original_execute(*args, **kwargs)

@@ -1,15 +1,68 @@
 import json
+import logging
 import os
 from .constants import IMAGES

 # Check if running in standalone mode
 standalone_mode = os.environ.get("LORA_MANAGER_STANDALONE", "0") == "1" or os.environ.get("HF_HUB_DISABLE_TELEMETRY", "0") == "0"

-from .constants import MODELS, PROMPTS, SAMPLING, LORAS, SIZE, IS_SAMPLER
+from .constants import MODELS, PROMPTS, SAMPLING, LORAS, SIZE, IS_SAMPLER, OVERWRITE
+from .node_extractors import NODE_EXTRACTORS
+
+logger = logging.getLogger(__name__)
+
+# Keys that identify metadata hint marks stored in node.properties.lm_marker_role
+_META_MARK_PREFIX = "meta_"
+_MARK_PRIMARY_MODEL = "primary_model"
+_MARK_PRIMARY_SAMPLER = "primary_sampler"
+_MARK_POSITIVE_PROMPT = "positive_prompt"
+_MARK_NEGATIVE_PROMPT = "negative_prompt"

 class MetadataProcessor:
    """Process and format collected metadata"""
-    
+
+    @staticmethod
+    def _get_user_marks(metadata):
+        """Scan workflow nodes (from extra_data.extra_pnginfo.workflow) for user-assigned
+        metadata hint marks stored in node.properties.lm_marker_role.
+
+        Returns a dict mapping mark type keys to node IDs.
+        Example: {'primary_model': '42', 'primary_sampler': '17'}
+        """
+        marks: dict[str, str] = {}
+
+        # Primary source: extra_data.extra_pnginfo.workflow.nodes (has full properties)
+        extra_data = metadata.get("extra_data")
+        if extra_data and isinstance(extra_data, dict):
+            extra_pnginfo = extra_data.get("extra_pnginfo", {})
+            if isinstance(extra_pnginfo, dict):
+                workflow = extra_pnginfo.get("workflow", {})
+                nodes = workflow.get("nodes", [])
+                for node in nodes:
+                    node_id = str(node.get("id", ""))
+                    role = node.get("properties", {}).get("lm_marker_role", "")
+                    if role.startswith(_META_MARK_PREFIX):
+                        mark_type = role[len(_META_MARK_PREFIX):]
+                        if mark_type in marks:
+                            logger.warning(
+                                "Duplicate meta hint '%s': node %s (previous: %s), "
+                                "last match wins",
+                                mark_type, node_id, marks[mark_type],
+                            )
+                        marks[mark_type] = node_id
+
+        # Fallback: try prompt.original_prompt (API-only submissions may not have workflow)
+        if not marks:
+            prompt = metadata.get("current_prompt")
+            if prompt and getattr(prompt, "original_prompt", None):
+                for node_id, node_data in prompt.original_prompt.items():
+                    role = node_data.get("properties", {}).get("lm_marker_role", "")
+                    if role.startswith(_META_MARK_PREFIX):
+                        mark_type = role[len(_META_MARK_PREFIX):]
+                        marks[mark_type] = node_id
+
+        return marks
+
    @staticmethod
    def find_primary_sampler(metadata, downstream_id=None):
        """
@@ -471,20 +524,57 @@ class MetadataProcessor:
            "checkpoint": None,
            "loras": "",
            "size": None,
-            "clip_skip": None
+            "clip_skip": None,
+            "additional_data": "",
        }
        
        # Get the prompt object for node relationship tracing
        prompt = metadata.get("current_prompt")
-        
-        # Find the primary KSampler node
-        primary_sampler_id, primary_sampler = MetadataProcessor.find_primary_sampler(metadata, id)
-        
-        # Directly get checkpoint from metadata instead of tracing
-        # Pass primary_sampler_id to avoid redundant calculation
-        checkpoint = MetadataProcessor.find_primary_checkpoint(metadata, id, primary_sampler_id)
-        if checkpoint:
-            params["checkpoint"] = checkpoint
+
+        # ---- User marks: override heuristic inference with user-assigned hints ----
+        user_marks = MetadataProcessor._get_user_marks(metadata)
+
+        # Find the primary KSampler node (user mark takes priority)
+        primary_sampler_id = None
+        primary_sampler = None
+        if _MARK_PRIMARY_SAMPLER in user_marks:
+            marked_id = user_marks[_MARK_PRIMARY_SAMPLER]
+            sampler_data = metadata.get(SAMPLING, {}).get(marked_id)
+            if sampler_data and sampler_data.get(IS_SAMPLER):
+                primary_sampler_id = marked_id
+                primary_sampler = sampler_data
+            else:
+                logger.warning(
+                    "User-marked primary sampler %s has no runtime metadata, "
+                    "falling back to heuristic",
+                    marked_id,
+                )
+        if primary_sampler is None:
+            primary_sampler_id, primary_sampler = MetadataProcessor.find_primary_sampler(metadata, id)
+
+        # Resolve checkpoint / model (user mark takes priority)
+        if _MARK_PRIMARY_MODEL in user_marks:
+            marked_id = user_marks[_MARK_PRIMARY_MODEL]
+            if marked_id in metadata.get(MODELS, {}):
+                params["checkpoint"] = metadata[MODELS][marked_id].get("name")
+            else:
+                extra_data = metadata.get("extra_data")
+                extra_pnginfo = extra_data.get("extra_pnginfo", {}) if extra_data and isinstance(extra_data, dict) else {}
+                workflow = extra_pnginfo.get("workflow", {}) if isinstance(extra_pnginfo, dict) else {}
+                node_type = "unknown"
+                for n in workflow.get("nodes", []):
+                    if str(n.get("id", "")) == marked_id:
+                        node_type = n.get("type", "unknown")
+                        break
+                logger.warning(
+                    "User-marked primary model %s (type=%s, registered=%s) has no runtime metadata, "
+                    "falling back to heuristic",
+                    marked_id, node_type, node_type in NODE_EXTRACTORS,
+                )
+        if params["checkpoint"] is None:
+            checkpoint = MetadataProcessor.find_primary_checkpoint(metadata, id, primary_sampler_id)
+            if checkpoint:
+                params["checkpoint"] = checkpoint
        
        # Check if guidance parameter exists in any sampling node
        for node_id, sampler_info in metadata.get(SAMPLING, {}).items():
@@ -539,7 +629,22 @@ class MetadataProcessor:
                    
                    # For SamplerCustom, handle any additional parameters
                    MetadataProcessor.handle_custom_advanced_sampler(metadata, prompt, primary_sampler_id, params)
-                
+
+            # ---- User marks: override prompts with explicitly tagged nodes ----
+            prompts_data = metadata.get(PROMPTS, {})
+            if _MARK_POSITIVE_PROMPT in user_marks:
+                pos_id = user_marks[_MARK_POSITIVE_PROMPT]
+                if pos_id in prompts_data:
+                    prompt_text = prompts_data[pos_id].get("text") or prompts_data[pos_id].get("positive_text")
+                    if prompt_text:
+                        params["prompt"] = prompt_text
+            if _MARK_NEGATIVE_PROMPT in user_marks:
+                neg_id = user_marks[_MARK_NEGATIVE_PROMPT]
+                if neg_id in prompts_data:
+                    prompt_text = prompts_data[neg_id].get("text") or prompts_data[neg_id].get("negative_text")
+                    if prompt_text:
+                        params["negative_prompt"] = prompt_text
+
            # Size extraction is same for all sampler types
            # Check if the sampler itself has size information (from latent_image)
            if primary_sampler_id in metadata.get(SIZE, {}):
@@ -568,7 +673,26 @@ class MetadataProcessor:
                break
        if params["clip_skip"] is None:
            params["clip_skip"] = "1"
-        
+
+        # ---- Apply manual metadata overwrites ----
+        for overwrite_info in metadata.get(OVERWRITE, {}).values():
+            overwrite_params = overwrite_info.get("parameters", {})
+            for key, value in overwrite_params.items():
+                if key == "clip_skip":
+                    # Accept any value from overwrite node (sentinel -25 already
+                    # filtered upstream).  Needed because falsy check treats 0
+                    # as "not set" even though 0 is a valid wired input here.
+                    params[key] = value
+                elif value:  # truthy check — only overwrite when user provided a real value
+                    params[key] = value
+
+        # Bridge: the overwrite node exposes the field as "model" (more accurate),
+        # but the internal pipeline key remains "checkpoint" for backward compatibility
+        # with A1111 metadata format and downstream consumers.
+        if params.get("model"):
+            params["checkpoint"] = params["model"]
+            del params["model"]
+
        return params
    
    @staticmethod
@@ -1,7 +1,8 @@
 import time
-from nodes import NODE_CLASS_MAPPINGS  # type: ignore
+from typing import Any
+from nodes import NODE_CLASS_MAPPINGS  # pyright: ignore[reportMissingImports, reportAttributeAccessIssue]
 from .node_extractors import NODE_EXTRACTORS, GenericNodeExtractor
-from .constants import METADATA_CATEGORIES, IMAGES
+from .constants import METADATA_CATEGORIES, IMAGES, OVERWRITE


 class MetadataRegistry:
@@ -9,6 +10,15 @@ class MetadataRegistry:

    _instance = None

+    current_prompt_id: Any = None
+    current_prompt: Any = None
+    metadata: dict[str, Any] = {}
+    prompt_metadata: dict[str, Any] = {}
+    executed_nodes: set[str] = set()
+    node_cache: dict[str, Any] = {}
+    max_prompt_history: int = 3
+    metadata_categories: list[str] = METADATA_CATEGORIES
+
    def __new__(cls):
        if cls._instance is None:
            cls._instance = super().__new__(cls)
@@ -61,6 +71,7 @@ class MetadataRegistry:
            {
                "execution_order": [],
                "current_prompt": None,  # Will store the prompt object
+                "extra_data": None,  # Will store the API extra_data for workflow metadata
                "timestamp": time.time(),
            }
        )
@@ -75,6 +86,11 @@ class MetadataRegistry:
            # Store the prompt in the metadata for later relationship tracing
            self.prompt_metadata[self.current_prompt_id]["current_prompt"] = prompt

+    def set_extra_data(self, extra_data):
+        """Store the API extra_data (contains extra_pnginfo.workflow with node properties)"""
+        if self.current_prompt_id and self.current_prompt_id in self.prompt_metadata:
+            self.prompt_metadata[self.current_prompt_id]["extra_data"] = extra_data
+
    def get_metadata(self, prompt_id=None):
        """Get collected metadata for a prompt"""
        key = prompt_id if prompt_id is not None else self.current_prompt_id
@@ -122,20 +138,28 @@ class MetadataRegistry:
            cache_key = f"{node_id}:{class_type}"

            # Check if this node type is relevant for metadata collection
-            if class_type in NODE_EXTRACTORS:
+            if class_type in NODE_EXTRACTORS or cache_key in self.node_cache:
                # Check if we have cached metadata for this node
                if cache_key in self.node_cache:
                    cached_data = self.node_cache[cache_key]

+                    # Detect bypass (mode=4) / mute (mode=2) — these nodes
+                    # were intentionally disabled and should not contribute
+                    # overwrite values from a previous execution's cache.
+                    node_mode = node_data.get("mode", 0)
+                    node_is_disabled = node_mode in (2, 4)
+
                    # Apply cached metadata to the current metadata
                    for category in self.metadata_categories:
+                        if category == OVERWRITE and node_is_disabled:
+                            continue
                        if category in cached_data and node_id in cached_data[category]:
                            if node_id not in metadata[category]:
                                metadata[category][node_id] = cached_data[category][
                                    node_id
                                ]

-    def record_node_execution(self, node_id, class_type, inputs, outputs):
+    def record_node_execution(self, node_id, class_type, inputs, outputs, return_types=None):
        """Record information about a node's execution"""
        if not self.current_prompt_id:
            return
@@ -158,17 +182,18 @@ class MetadataRegistry:

        # Extract node-specific metadata
        extractor = NODE_EXTRACTORS.get(class_type, GenericNodeExtractor)
-        extractor.extract(
-            node_id,
-            processed_inputs,
-            outputs,
-            self.prompt_metadata[self.current_prompt_id],
-        )
+        if extractor is GenericNodeExtractor:
+            extractor.extract(node_id, processed_inputs, outputs,
+                              self.prompt_metadata[self.current_prompt_id],
+                              return_types=return_types)
+        else:
+            extractor.extract(node_id, processed_inputs, outputs,
+                              self.prompt_metadata[self.current_prompt_id])

        # Cache this node's metadata
        self._cache_node_metadata(node_id, class_type)

-    def update_node_execution(self, node_id, class_type, outputs):
+    def update_node_execution(self, node_id, class_type, outputs, return_types=None):
        """Update node metadata with output information"""
        if not self.current_prompt_id:
            return
@@ -179,9 +204,17 @@ class MetadataRegistry:
        # Use the same extractor to update with outputs
        extractor = NODE_EXTRACTORS.get(class_type, GenericNodeExtractor)
        if hasattr(extractor, "update"):
-            extractor.update(
-                node_id, processed_outputs, self.prompt_metadata[self.current_prompt_id]
-            )
+            if extractor is GenericNodeExtractor:
+                extractor.update(
+                    node_id, processed_outputs,
+                    self.prompt_metadata[self.current_prompt_id],
+                    return_types=return_types,
+                )
+            else:
+                extractor.update(
+                    node_id, processed_outputs,
+                    self.prompt_metadata[self.current_prompt_id],
+                )

        # Update the cached metadata for this node
        self._cache_node_metadata(node_id, class_type)
@@ -2,7 +2,8 @@ import json
 import os
 import re

-from .constants import MODELS, PROMPTS, SAMPLING, LORAS, SIZE, IMAGES, IS_SAMPLER
+from .constants import MODELS, PROMPTS, SAMPLING, LORAS, SIZE, IMAGES, IS_SAMPLER, OVERWRITE
+from .overwrite_utils import collect_overwrite_params


 def _store_checkpoint_metadata(metadata, node_id, model_name):
@@ -31,11 +32,95 @@ class NodeMetadataExtractor:
        pass
        
 class GenericNodeExtractor(NodeMetadataExtractor):
-    """Default extractor for nodes without specific handling"""
+    """Fallback extractor with type-signature-based detection.
+
+    When a node is not in the NODE_EXTRACTORS registry, the hook layer
+    passes ``return_types`` from ``obj.RETURN_TYPES``:
+
+    * ``MODEL`` output: common input fields (ckpt_name, unet_name, etc.)
+      are checked for a model file name and stored as checkpoint metadata.
+    * ``CONDITIONING`` output: common text input fields are checked for
+      prompt text, and conditioning inputs are tracked through transforms.
+    """
+
+    # Input field names that carry a model path in loader-style nodes.
+    _MODEL_NAME_FIELDS = (
+        "ckpt_name", "unet_name", "model_path", "model_name", "gguf_name",
+    )
+
+    # Extensions used by checkpoint_scanner.py — only record values that look
+    # like real model filenames to avoid capturing unrelated string fields.
+    _MODEL_EXTENSIONS = {
+        ".ckpt", ".pt", ".pt2", ".bin", ".pth", ".safetensors", ".pkl", ".sft", ".gguf",
+    }
+
+    # Input field names that may carry prompt text in encoder-style nodes.
+    _TEXT_FIELDS = ("text", "clip_l", "t5xxl", "prompt", "positive", "negative")
+
    @staticmethod
-    def extract(node_id, inputs, outputs, metadata):
-        pass
-        
+    def extract(node_id, inputs, outputs, metadata, return_types=None):
+        if return_types is None:
+            return
+
+        # — MODEL loader detection (checkpoint / UNET / GGUF) —
+        if "MODEL" in return_types or any("MODEL" in str(t) for t in return_types):
+            for field in GenericNodeExtractor._MODEL_NAME_FIELDS:
+                val = inputs.get(field)
+                if val and isinstance(val, str) and val.strip():
+                    name = val.strip()
+                    if not any(name.lower().endswith(ext) for ext in GenericNodeExtractor._MODEL_EXTENSIONS):
+                        continue
+                    _store_checkpoint_metadata(metadata, node_id, name)
+                    return
+
+        # — CONDITIONING encoder / transform detection —
+        if "CONDITIONING" in return_types or any("CONDITIONING" in str(t) for t in return_types):
+            text = None
+            for field in GenericNodeExtractor._TEXT_FIELDS:
+                val = inputs.get(field)
+                if val and isinstance(val, str) and val.strip():
+                    text = val.strip()
+                    break
+
+            input_conditionings = _collect_conditioning_inputs(inputs)
+            if text or input_conditionings:
+                prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+                if text:
+                    prompt_metadata["text"] = text
+                if input_conditionings:
+                    prompt_metadata["orig_conditionings"] = input_conditionings
+
+    @staticmethod
+    def update(node_id, outputs, metadata, return_types=None):
+        if return_types is None:
+            return
+        if "CONDITIONING" not in return_types and not any(
+            "CONDITIONING" in str(t) for t in return_types
+        ):
+            return
+        if node_id not in metadata.get(PROMPTS, {}):
+            return
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple or len(output_tuple) < 1:
+            return
+
+        conditioning_index = _first_conditioning_index(return_types)
+        if conditioning_index is None or len(output_tuple) <= conditioning_index:
+            return
+
+        output_conditioning = output_tuple[conditioning_index]
+        if output_conditioning is None:
+            return
+
+        prompt_metadata = metadata[PROMPTS][node_id]
+        prompt_metadata["conditioning"] = output_conditioning
+        _record_conditioning_source(
+            metadata,
+            node_id,
+            output_conditioning,
+            prompt_metadata.get("orig_conditionings", []),
+        )
+
 class CheckpointLoaderExtractor(NodeMetadataExtractor):
    @staticmethod
    def extract(node_id, inputs, outputs, metadata):
@@ -349,6 +434,34 @@ def _first_output_tuple(outputs):
    return None


+def _first_conditioning_index(return_types):
+    """Return the index of the first CONDITIONING output slot, or None."""
+    if not return_types:
+        return None
+    for index, return_type in enumerate(return_types):
+        if "CONDITIONING" in str(return_type):
+            return index
+    return None
+
+
+def _collect_conditioning_inputs(inputs):
+    """Collect conditioning object inputs (``conditioning*`` keys).
+
+    Primitive values (None, str, int, float, bool) are excluded so scalar
+    fields like ``conditioning_strength`` are not mistaken for conditioning
+    objects during provenance tracking.
+    """
+    if not inputs:
+        return []
+    return [
+        value
+        for input_name, value in inputs.items()
+        if input_name.startswith("conditioning")
+        and value is not None
+        and not isinstance(value, (str, int, float, bool))
+    ]
+
+
 def _record_conditioning_source(
    metadata, node_id, output_conditioning, input_conditionings
 ):
@@ -361,6 +474,14 @@ def _record_conditioning_source(
    if not sources:
        return

+    # Identity-preserving selectors return one of their inputs unchanged:
+    # only that input contributed to the output, so record it alone instead
+    # of treating every input as a combination source.
+    for conditioning in sources:
+        if id(conditioning) == id(output_conditioning):
+            sources = [conditioning]
+            break
+
    prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
    prompt_metadata.setdefault("conditioning_sources", []).append(
        {
@@ -440,13 +561,7 @@ class ConditioningCombineExtractor(NodeMetadataExtractor):
        if not inputs:
            return

-        input_conditionings = []
-        for input_name in inputs:
-            if (
-                input_name.startswith("conditioning")
-                and inputs[input_name] is not None
-            ):
-                input_conditionings.append(inputs[input_name])
+        input_conditionings = _collect_conditioning_inputs(inputs)

        if input_conditionings:
            prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
@@ -1154,6 +1269,28 @@ class CR_ApplyControlNetStackExtractor(NodeMetadataExtractor):
                metadata[PROMPTS][node_id]["positive_encoded"] = transformed_positive
                metadata[PROMPTS][node_id]["negative_encoded"] = transformed_negative

+class MetadataOverwriteExtractor(NodeMetadataExtractor):
+    """Extract manually specified metadata from MetadataOverwriteLM node.
+
+    Stores truthy input values under the OVERWRITE category so that
+    extract_generation_params can merge them over the inferred params.
+    """
+
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        overwrite_params = collect_overwrite_params(inputs)
+
+        if overwrite_params:
+            metadata.setdefault(OVERWRITE, {})
+            metadata[OVERWRITE][node_id] = {
+                "parameters": overwrite_params,
+                "node_id": node_id,
+            }
+
+
 # Registry of node-specific extractors
 # Keys are node class names
 NODE_EXTRACTORS = {
@@ -1221,5 +1358,7 @@ NODE_EXTRACTORS = {
    "CFGGuider": CFGGuiderExtractor,            # Add CFGGuider
    # Image
    "VAEDecode": VAEDecodeExtractor,  # Added VAEDecode extractor
+    # Metadata overwrite
+    "MetadataOverwriteLM": MetadataOverwriteExtractor,
    # Add other nodes as needed
 }
@@ -0,0 +1,42 @@
+"""Shared helpers for Metadata Overwrite node metadata collection.
+
+Used by both the MetadataOverwriteLM node (execution time) and the
+MetadataOverwriteExtractor (hook time) so the conversion/filtering logic
+cannot drift between the two paths.
+"""
+
+import logging
+from typing import Any, Dict
+
+from ..utils.utils import model_patcher_to_name
+from .constants import CLIP_SKIP_SENTINEL, METADATA_OVERWRITE_FIELDS
+
+logger = logging.getLogger(__name__)
+
+
+def collect_overwrite_params(values: Dict[str, Any]) -> Dict[str, Any]:
+    """Convert node input values into non-default overwrite parameters.
+
+    For most fields, a falsy value (empty string, 0) means "not set" and is
+    skipped.  clip_skip uses a dedicated sentinel (-25) so that a wired value
+    of 0 is preserved.  The ``model`` field accepts either a manual string or
+    a wired MODEL (ModelPatcher) connection; in the latter case the source
+    model name is extracted from the patcher's ``cached_patcher_init`` and
+    stored as a ComfyUI-style relative path.
+    """
+    result: Dict[str, Any] = {}
+    for key in METADATA_OVERWRITE_FIELDS:
+        value = values.get(key)
+        if key == "model" and not isinstance(value, str):
+            value = model_patcher_to_name(value)
+            if value is None:
+                logger.warning(
+                    "Could not extract model name from wired MODEL input "
+                    "(no cached_patcher_init); model metadata overwrite skipped"
+                )
+        if key == "clip_skip":
+            if value != CLIP_SKIP_SENTINEL:
+                result[key] = value
+        elif value:
+            result[key] = value
+    return result
@@ -0,0 +1,233 @@
+"""Metadata operations — thin in-process wrappers around LoRA Manager internal services.
+
+All functions are simple Python async functions that delegate to the
+appropriate internal service.  They use **relative imports** within the
+``py`` package, so ``sys.modules`` caching works normally and there is no
+risk of double import or circular dependencies.
+
+Usage (in-process, primary)::
+
+    from py.metadata_ops import list_base_models, read_metadata
+
+    models = await list_base_models()
+    meta   = await read_metadata("/path/to/model.safetensors")
+
+Usage (subprocess, debugging / external)::
+
+    python -m py.metadata_ops base-models list
+    python -m py.metadata_ops metadata read /path/to/model.safetensors
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import os
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+SCANNER_TYPE_MAP: dict[str, str] = {
+    "get_lora_scanner": "lora",
+    "get_checkpoint_scanner": "checkpoint",
+    "get_embedding_scanner": "embedding",
+}
+
+SCANNER_GETTER_NAMES = tuple(SCANNER_TYPE_MAP.keys())
+
+
+async def _find_model_entry(
+    model_path: str,
+) -> tuple[Any, object, str | None] | tuple[None, None, None]:
+    """Iterate all scanners and return the first (scanner, entry, getter_name)
+    that owns *model_path*.  Returns ``(None, None, None)`` when no scanner
+    claims it.
+    """
+    from ..services.service_registry import ServiceRegistry
+
+    normalized = os.path.normpath(model_path)
+    for getter_name in SCANNER_GETTER_NAMES:
+        getter = getattr(ServiceRegistry, getter_name, None)
+        if getter is None:
+            continue
+        try:
+            scanner = await getter()
+            if scanner is None:
+                continue
+            cache = await scanner.get_cached_data()
+            for entry in cache.raw_data:
+                if os.path.normpath(entry.get("file_path", "")) == normalized:
+                    return scanner, entry, getter_name
+        except Exception as exc:
+            logger.debug(
+                "Scanner %s check failed for %s: %s",
+                getter_name, model_path, exc,
+            )
+    return None, None, None
+
+
+async def _find_scanner_for_model(
+    model_path: str,
+) -> tuple[Any, object] | tuple[None, None]:
+    """Find the (scanner, cache_entry) responsible for *model_path*."""
+    scanner, entry, _ = await _find_model_entry(model_path)
+    return scanner, entry
+
+
+async def identify_model_type(model_path: str) -> str:
+    """Determine the model type (``\"lora\"``, ``\"checkpoint\"``, or
+    ``\"embedding\"``) for *model_path*.
+
+    Falls back to ``\"lora\"`` when unknown.
+    """
+    _, _, getter_name = await _find_model_entry(model_path)
+    return SCANNER_TYPE_MAP[getter_name] if getter_name else "lora"
+
+
+# ---------------------------------------------------------------------------
+# Public API
+# ---------------------------------------------------------------------------
+
+
+async def list_base_models(limit: int = 0) -> List[str]:
+    """Return all valid CivitAI base model names.
+
+    Uses ``CivitaiBaseModelService.get_base_models()`` which merges a
+    hardcoded list (``SUPPORTED_DOWNLOAD_SKIP_BASE_MODELS``) with remote
+    models fetched from the CivitAI API.  Never empty — the hardcoded
+    fallback always provides a complete set.
+
+    The result is sorted alphabetically.  Pass *limit* = 0 for all models.
+    """
+    from ..services.civitai_base_model_service import (
+        CivitaiBaseModelService,
+    )
+
+    try:
+        service = await CivitaiBaseModelService.get_instance()
+        response = await service.get_base_models()
+        names: List[str] = response.get("models", [])
+    except Exception as exc:
+        logger.warning("list_base_models failed: %s", exc)
+        names = []
+    if limit > 0:
+        return names[:limit]
+    return names
+
+
+async def read_metadata(model_path: str) -> Dict[str, Any]:
+    """Load the full metadata payload for *model_path* from disk.
+
+    Returns an empty dict when the metadata file does not exist or cannot
+    be parsed — never raises.
+    """
+    from ..utils.metadata_manager import MetadataManager
+
+    try:
+        return await MetadataManager.load_metadata_payload(model_path) or {}
+    except Exception as exc:
+        logger.warning("read_metadata failed for %s: %s", model_path, exc)
+        return {}
+
+
+async def apply_metadata_updates(
+    model_path: str,
+    updates: Dict[str, Any],
+) -> List[str]:
+    """Merge *updates* into the model's on-disk metadata and persist.
+
+    Returns the list of field names that actually changed.
+    """
+    from ..utils.metadata_manager import MetadataManager
+
+    metadata = await read_metadata(model_path)
+    updated_fields: List[str] = []
+    for key, value in updates.items():
+        old = metadata.get(key)
+        if old != value:
+            metadata[key] = value
+            updated_fields.append(key)
+    if updated_fields:
+        await MetadataManager.save_metadata(model_path, metadata)
+    return updated_fields
+
+
+async def download_preview(
+    model_path: str,
+    url: str,
+    *,
+    target_width: int = 480,
+    quality: int = 85,
+) -> str | None:
+    """Download a preview image from *url*, optimise to .webp, and save it.
+
+    The output file is placed alongside the model file with a ``.webp``
+    extension.  Returns the local file path on success, ``None`` on failure.
+    """
+    from ..services.downloader import get_downloader
+    from ..utils.exif_utils import ExifUtils
+
+    if not url or not url.strip():
+        return None
+
+    base_name = os.path.splitext(os.path.basename(model_path))[0]
+    preview_dir = os.path.dirname(model_path)
+    output_path = os.path.join(preview_dir, base_name + ".webp")
+
+    downloader = await get_downloader()
+
+    # Try in-memory download + optimise first
+    success, content, _headers = await downloader.download_to_memory(
+        url, use_auth=False,
+    )
+    if success and content:
+        try:
+            optimized_data, _ = ExifUtils.optimize_image(
+                image_data=content,
+                target_width=target_width,
+                format="webp",
+                quality=quality,
+                preserve_metadata=False,
+            )
+            with open(output_path, "wb") as f:
+                f.write(optimized_data)
+            return output_path
+        except Exception as exc:
+            logger.warning("Preview optimisation failed, saving raw: %s", exc)
+            # Fall through to raw save
+
+    # Fallback: download directly to file
+    try:
+        ok, _ = await downloader.download_file(url, output_path, use_auth=False)
+        if ok:
+            return output_path
+    except Exception as exc:
+        logger.warning("Preview fallback download failed for %s: %s", model_path, exc)
+
+    return None
+
+
+async def refresh_cache(model_path: str) -> bool:
+    """Invalidate and reload the scanner cache entry for *model_path*.
+
+    Returns ``True`` when the model was found and the cache was refreshed.
+    """
+    scanner, entry = await _find_scanner_for_model(model_path)
+    if scanner is None:
+        logger.warning("refresh_cache: no scanner found for %s", model_path)
+        return False
+    try:
+        metadata = await read_metadata(model_path)
+        if not metadata:
+            logger.warning("refresh_cache: no metadata for %s", model_path)
+            return False
+        await scanner.update_single_model_cache(model_path, model_path, metadata)
+        return True
+    except Exception as exc:
+        logger.warning("refresh_cache failed for %s: %s", model_path, exc)
+        return False
@@ -0,0 +1,113 @@
+"""Subprocess entry point for ``metadata_ops`` (debugging / external use).
+
+Usage::
+
+    python -m py.metadata_ops base-models list [--limit N]
+    python -m py.metadata_ops metadata read <path>
+    python -m py.metadata_ops metadata update <path> --json '{...}'
+    python -m py.metadata_ops preview download <path> --url <url>
+    python -m py.metadata_ops cache refresh <path>
+"""
+
+from __future__ import annotations
+
+import argparse
+import asyncio
+import json
+import sys
+from typing import Any, Dict, List
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="lmcli", description="LoRA Manager Agent CLI")
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    # base-models list
+    base_models = sub.add_parser("base-models", aliases=["bm"])
+    base_models_cmds = base_models.add_subparsers(dest="subcommand", required=True)
+    base_models_list = base_models_cmds.add_parser("list")
+    base_models_list.add_argument(
+        "--limit", type=int, default=0, help="Max number of models (0 = all)"
+    )
+
+    # metadata read
+    meta = sub.add_parser("metadata", aliases=["md"])
+    meta_cmds = meta.add_subparsers(dest="subcommand", required=True)
+    meta_read = meta_cmds.add_parser("read")
+    meta_read.add_argument("path", type=str, help="Model file path")
+
+    # metadata update
+    meta_update = meta_cmds.add_parser("update")
+    meta_update.add_argument("path", type=str, help="Model file path")
+    meta_update.add_argument(
+        "--json",
+        type=str,
+        required=True,
+        help='JSON object of fields to update, e.g. \'{"base_model": "SDXL 1.0"}\'',
+    )
+
+    # preview download
+    prev = sub.add_parser("preview", aliases=["pv"])
+    prev_cmds = prev.add_subparsers(dest="subcommand", required=True)
+    prev_dl = prev_cmds.add_parser("download")
+    prev_dl.add_argument("path", type=str, help="Model file path")
+    prev_dl.add_argument("--url", type=str, required=True, help="Preview image URL")
+
+    # cache refresh
+    cache = sub.add_parser("cache")
+    cache_cmds = cache.add_subparsers(dest="subcommand", required=True)
+    cache_refresh = cache_cmds.add_parser("refresh")
+    cache_refresh.add_argument("path", type=str, help="Model file path")
+
+    return parser
+
+
+async def _run(args: argparse.Namespace) -> Any:
+    from . import (  # lazy import so startup is fast
+        list_base_models,
+        read_metadata,
+        apply_metadata_updates,
+        download_preview,
+        refresh_cache,
+    )
+
+    cmd = args.command
+    sub = args.subcommand
+
+    if cmd in ("base-models", "bm") and sub == "list":
+        return await list_base_models(limit=args.limit)
+
+    if cmd in ("metadata", "md") and sub == "read":
+        return await read_metadata(args.path)
+
+    if cmd in ("metadata", "md") and sub == "update":
+        updates: Dict[str, Any] = json.loads(args.json)
+        return await apply_metadata_updates(args.path, updates)
+
+    if cmd in ("preview", "pv") and sub == "download":
+        return await download_preview(args.path, args.url)
+
+    if cmd == "cache" and sub == "refresh":
+        return await refresh_cache(args.path)
+
+    raise ValueError(f"Unknown command: {cmd} {sub}")
+
+
+def main() -> None:
+    parser = _build_parser()
+    args = parser.parse_args()
+
+    result = asyncio.run(_run(args))
+    # Always print as JSON so callers can parse reliably
+    if isinstance(result, list):
+        for item in result:
+            print(item)
+    elif isinstance(result, dict):
+        json.dump(result, sys.stdout, ensure_ascii=False, indent=2)
+        print()
+    else:
+        print(json.dumps(result))
+
+
+if __name__ == "__main__":
+    main()
@@ -41,7 +41,12 @@ async def api_json_error(
        if exc.status < 400:
            raise

-        logger.warning(
+        # Preview 404 is routine (file deleted from disk) — not worth a warning.
+        logger_method = logger.warning
+        if request.path.startswith("/api/lm/previews") and exc.status == 404:
+            logger_method = logger.debug
+
+        logger_method(
            "API %s %s returned HTTP %d: %s",
            request.method,
            request.path,
@@ -1,7 +1,8 @@
 import logging
-from typing import List, Tuple
-import comfy.sd # type: ignore
-import folder_paths # type: ignore
+import os
+from typing import Any, List, Tuple
+import comfy.sd  # pyright: ignore[reportMissingImports]
+import folder_paths  # pyright: ignore[reportMissingImports]
 from ..utils.utils import get_checkpoint_info_absolute, _format_model_name_for_comfyui

 logger = logging.getLogger(__name__)
@@ -18,9 +19,9 @@ class CheckpointLoaderLM:
    CATEGORY = "Lora Manager/loaders"

    @classmethod
-    def INPUT_TYPES(s):
+    def INPUT_TYPES(cls):
        # Get list of checkpoint names from scanner (includes extra folder paths)
-        checkpoint_names = s._get_checkpoint_names()
+        checkpoint_names = cls._get_checkpoint_names()
        return {
            "required": {
                "ckpt_name": (
@@ -58,7 +59,10 @@ class CheckpointLoaderLM:
                for item in cache.raw_data:
                    if item.get("sub_type") == "checkpoint":
                        file_path = item.get("file_path", "")
-                        if file_path:
+                        # Only offer models that still exist on disk so ComfyUI
+                        # flags missing checkpoints at queue time via
+                        # "value not in list" (the scanner cache can be stale).
+                        if file_path and os.path.exists(file_path):
                            # Format using relative path with OS-native separator
                            formatted_name = _format_model_name_for_comfyui(
                                file_path, model_roots
@@ -89,7 +93,7 @@ class CheckpointLoaderLM:
            logger.error(f"Error getting checkpoint names: {e}")
            return []

-    def load_checkpoint(self, ckpt_name: str) -> Tuple:
+    def load_checkpoint(self, ckpt_name: str) -> Tuple[Any, Any, Any]:
        """Load a checkpoint by name, supporting extra folder paths

        Args:
@@ -0,0 +1,123 @@
+"""Create Hook LoRA (LoraManager) — multi-LoRA hook node compatible with ComfyUI's built-in hook pipeline.
+
+Produces ``("HOOKS",)`` output that chains seamlessly with downstream hook consumers
+(ConditioningSetProperties, SetHookKeyframes, CombineHooks, SetClipHooks, etc.).
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+
+from ..utils.utils import get_lora_info_absolute
+from .utils import (
+    FlexibleOptionalInputType,
+    any_type,
+    apply_lora_syntax_format,
+    get_loras_list,
+    validate_lora_entries,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class CreateHookLoraLM:
+    NAME = "Create Hook LoRA (LoraManager)"
+    CATEGORY = "Lora Manager/hooks"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "text": (
+                    "AUTOCOMPLETE_TEXT_LORAS",
+                    {
+                        "placeholder": "Search LoRAs to add...",
+                        "tooltip": (
+                            "Search and select LoRAs. Each LoRA gets its own "
+                            "model/clip strength. Hooks chain with prev_hooks."
+                        ),
+                    },
+                ),
+            },
+            "optional": FlexibleOptionalInputType(any_type),
+        }
+
+    @classmethod
+    def VALIDATE_INPUTS(cls, loras=None):
+        """Queue-time validation: reject missing local LoRAs before execution."""
+        return validate_lora_entries({"loras": loras}) or True
+
+    RETURN_TYPES = ("HOOKS", "STRING", "STRING")
+    RETURN_NAMES = ("HOOKS", "trigger_words", "active_loras")
+    FUNCTION = "create_hook"
+
+    def create_hook(self, text: str, **kwargs):
+        """Create a HookGroup from the selected LoRAs, chained with prev_hooks.
+
+        Each active LoRA from the widget is loaded and wrapped in a WeightHook
+        via :func:`comfy.hooks.create_hook_lora`.  All hooks are combined into a
+        single group and returned alongside trigger words and a human-readable
+        summary of the active LoRAs.
+        """
+        del text  # used by the frontend widget only
+
+        # Lazy imports: comfy is not available in CI/test environment at module level
+        import comfy.hooks  # pyright: ignore[reportMissingImports]  # noqa: C0415
+        import comfy.utils  # pyright: ignore[reportMissingImports]  # noqa: C0415
+
+        prev_hooks: comfy.hooks.HookGroup | None = kwargs.get("prev_hooks")
+
+        hook_group = prev_hooks.clone() if prev_hooks is not None else comfy.hooks.HookGroup()
+
+        all_trigger_words: list[str] = []
+        active_loras: list[tuple[str, float, float]] = []
+
+        for lora in get_loras_list(kwargs):
+            if not lora.get("active", False):
+                continue
+
+            lora_name = apply_lora_syntax_format(lora["name"])
+            model_strength = float(lora["strength"])
+            clip_strength = float(lora.get("clipStrength", model_strength))
+
+            # Skip useless no-op entries (both strengths are zero)
+            if model_strength == 0.0 and clip_strength == 0.0:
+                continue
+
+            lora_path, trigger_words = get_lora_info_absolute(lora_name)
+            if not lora_path or not os.path.isfile(lora_path):
+                logger.warning("LoRA '%s' not found — skipping", lora_name)
+                continue
+
+            try:
+                lora_weights = comfy.utils.load_torch_file(lora_path, safe_load=True)
+
+                lora_hooks = comfy.hooks.create_hook_lora(
+                    lora=lora_weights,
+                    strength_model=model_strength,
+                    strength_clip=clip_strength,
+                )
+            except Exception:
+                logger.exception("Failed to load LoRA '%s' — skipping", lora_name)
+                continue
+            hook_group = hook_group.clone_and_combine(lora_hooks)
+
+            active_loras.append((lora_name, model_strength, clip_strength))
+            all_trigger_words.extend(trigger_words)
+
+        # Format trigger words (group mode separator)
+        trigger_words_text = ",, ".join(all_trigger_words) if all_trigger_words else ""
+
+        # Format active LoRAs summary
+        formatted_loras = []
+        for name, model_s, clip_s in active_loras:
+            if abs(model_s - clip_s) > 0.001:
+                formatted_loras.append(
+                    f"<lora:{name}:{model_s}:{clip_s}>"
+                )
+            else:
+                formatted_loras.append(f"<lora:{name}:{model_s}>")
+        active_loras_text = " ".join(formatted_loras)
+
+        return (hook_group, trigger_words_text, active_loras_text)
@@ -0,0 +1,45 @@
+"""Lora Info display node — pure frontend node for showing selected LoRA info.
+
+This node does NOT participate in workflow execution. Its single optional
+"lora_source" input exists solely as a wire-connection anchor so that the
+frontend can traverse the graph and push selection data to connected info nodes.
+"""
+
+from __future__ import annotations
+
+
+class LoraInfoLM:
+    """Display node that shows filename and notes for the selected LoRA."""
+
+    NAME = "Lora Info (LoraManager)"
+    CATEGORY = "Lora Manager/utils"
+    DESCRIPTION = (
+        "Displays information (filename, notes) about the currently selected "
+        "LoRA. Connect any output from a LoRA Loader or Stacker to the "
+        "lora_source input, then select a LoRA in the source widget — the "
+        "info updates automatically. Does not affect workflow execution."
+    )
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {},
+        }
+
+    RETURN_TYPES = ()
+    RETURN_NAMES = ()
+    OUTPUT_NODE = False
+    FUNCTION = "noop"
+
+    def noop(self, **kwargs):
+        # This node is display-only — no workflow execution needed.
+        return ()
+
+
+NODE_CLASS_MAPPINGS = {
+    LoraInfoLM.NAME: LoraInfoLM,
+}
+
+NODE_DISPLAY_NAME_MAPPINGS = {
+    LoraInfoLM.NAME: "Lora Info (LoraManager)",
+}
@@ -1,9 +1,8 @@
 import importlib
 import logging
-import re

-import comfy.sd  # type: ignore
-import comfy.utils  # type: ignore
+import comfy.sd  # pyright: ignore[reportMissingImports]
+import comfy.utils  # pyright: ignore[reportMissingImports]

 from ..utils.utils import get_lora_info_absolute
 from .utils import (
@@ -14,6 +13,8 @@ from .utils import (
    extract_lora_name,
    get_loras_list,
    nunchaku_load_lora,
+    parse_lora_syntax,
+    validate_lora_entries,
 )

 logger = logging.getLogger(__name__)
@@ -142,6 +143,11 @@ class LoraLoaderLM:
            "optional": FlexibleOptionalInputType(any_type),
        }

+    @classmethod
+    def VALIDATE_INPUTS(cls, loras=None):
+        """Queue-time validation: reject missing local LoRAs before execution."""
+        return validate_lora_entries({"loras": loras}) or True
+
    RETURN_TYPES = ("MODEL", "CLIP", "STRING", "STRING")
    RETURN_NAMES = ("MODEL", "CLIP", "trigger_words", "loaded_loras")
    FUNCTION = "load_loras"
@@ -189,25 +195,10 @@ class LoraTextLoaderLM:
    RETURN_NAMES = ("MODEL", "CLIP", "trigger_words", "loaded_loras")
    FUNCTION = "load_loras_from_text"

-    def parse_lora_syntax(self, text):
-        """Parse LoRA syntax from text input."""
-        pattern = r"<lora:([^:>]+):([^:>]+)(?::([^:>]+))?>"
-        matches = re.findall(pattern, text, re.IGNORECASE)
-
-        loras = []
-        for match in matches:
-            model_strength = float(match[1])
-            loras.append({
-                "name": match[0],
-                "model_strength": model_strength,
-                "clip_strength": float(match[2]) if match[2] else model_strength,
-            })
-        return loras
-
    def load_loras_from_text(self, model, lora_syntax, clip=None, lora_stack=None):
        """Load LoRAs based on text syntax input."""
        lora_entries = _collect_stack_entries(lora_stack)
-        for lora in self.parse_lora_syntax(lora_syntax):
+        for lora in parse_lora_syntax(lora_syntax):
            lora_path, trigger_words = get_lora_info_absolute(lora["name"])
            lora_entries.append({
                "name": lora["name"],
@@ -9,6 +9,7 @@ and tracks the last used combination for reuse.
 import logging
 import os
 from ..utils.utils import get_lora_info
+from .utils import validate_lora_entries

 logger = logging.getLogger(__name__)

@@ -31,6 +32,11 @@ class LoraRandomizerLM:
            },
        }

+    @classmethod
+    def VALIDATE_INPUTS(cls, loras=None):
+        """Queue-time validation: reject missing local LoRAs before execution."""
+        return validate_lora_entries({"loras": loras}) or True
+
    RETURN_TYPES = ("LORA_STACK",)
    RETURN_NAMES = ("LORA_STACK",)

@@ -1,26 +1,102 @@
+from __future__ import annotations
+
+import inspect
+import re
+from typing import Any
+
+_STACK_INPUT_PATTERN = re.compile(r"^lora_stack(?:_([ab])|(\d+))$")
+
+
+def _is_stack_input(name: str) -> bool:
+    return bool(_STACK_INPUT_PATTERN.match(name))
+
+
+def _stack_slot_number(name: str) -> int:
+    """Numeric slot used to order stack inputs; legacy a/b map to 1/2."""
+    match = _STACK_INPUT_PATTERN.match(name)
+    if not match:
+        return -1
+    letter, digits = match.group(1), match.group(2)
+    if digits is not None:
+        return int(digits)
+    return 1 if letter == "a" else 2
+
+
+class _LoraStackOptionalInputs:
+    """Lookup that preserves explicit optional inputs and dynamic lora_stack slots."""
+
+    def __init__(self, explicit_inputs: dict[str, tuple[str, dict[str, Any]]]) -> None:
+        self._explicit_inputs = explicit_inputs
+
+    def __contains__(self, item: object) -> bool:
+        if not isinstance(item, str):
+            return False
+        return item in self._explicit_inputs or _is_stack_input(item)
+
+    def __getitem__(self, key: str) -> tuple[str, dict[str, Any]]:
+        if key in self._explicit_inputs:
+            return self._explicit_inputs[key]
+        if _is_stack_input(key):
+            return (
+                "LORA_STACK",
+                {
+                    "tooltip": "A LoRA stack to combine. Connect to add more inputs.",
+                },
+            )
+        raise KeyError(key)
+
+
 class LoraStackCombinerLM:
    NAME = "Lora Stack Combiner (LoraManager)"
    CATEGORY = "Lora Manager/stackers"
+    DESCRIPTION = (
+        "Combines multiple LoRA stacks into a single stack. "
+        "Supports dynamic inputs: connect a stack to add more inputs."
+    )

    @classmethod
    def INPUT_TYPES(cls):
+        optional_inputs: dict[str, tuple[str, dict[str, Any]]] = {
+            "lora_stack1": (
+                "LORA_STACK",
+                {
+                    "tooltip": "A LoRA stack to combine. Connect to add more inputs.",
+                },
+            ),
+            "lora_stack2": (
+                "LORA_STACK",
+                {
+                    "tooltip": "A LoRA stack to combine. Connect to add more inputs.",
+                },
+            ),
+        }
+
+        stack = inspect.stack()
+        if len(stack) > 2 and stack[2].function == "get_input_info":
+            optional_inputs = _LoraStackOptionalInputs(optional_inputs)  # pyright: ignore[reportAssignmentType]
+
        return {
-            "required": {
-                "lora_stack_a": ("LORA_STACK",),
-                "lora_stack_b": ("LORA_STACK",),
-            },
+            "required": {},
+            "optional": optional_inputs,
        }

    RETURN_TYPES = ("LORA_STACK",)
    RETURN_NAMES = ("LORA_STACK",)
    FUNCTION = "combine_stacks"

-    def combine_stacks(self, lora_stack_a, lora_stack_b):
-        combined_stack = []
+    def combine_stacks(self, lora_stack1=None, lora_stack2=None, **kwargs):
+        stacks = {
+            "lora_stack1": lora_stack1,
+            "lora_stack2": lora_stack2,
+        }
+        for key, value in kwargs.items():
+            if _is_stack_input(key) and value is not None:
+                stacks[key] = value

-        if lora_stack_a:
-            combined_stack.extend(lora_stack_a)
-        if lora_stack_b:
-            combined_stack.extend(lora_stack_b)
+        combined_stack = []
+        for key in sorted(stacks, key=_stack_slot_number):
+            stack = stacks[key]
+            if stack:
+                combined_stack.extend(stack)

        return (combined_stack,)
@@ -1,6 +1,6 @@
 import os
 from ..utils.utils import get_lora_info
-from .utils import FlexibleOptionalInputType, any_type, apply_lora_syntax_format, extract_lora_name, get_loras_list
+from .utils import FlexibleOptionalInputType, any_type, apply_lora_syntax_format, extract_lora_name, get_loras_list, validate_lora_entries

 import logging

@@ -22,6 +22,11 @@ class LoraStackerLM:
            "optional": FlexibleOptionalInputType(any_type),
        }

+    @classmethod
+    def VALIDATE_INPUTS(cls, loras=None):
+        """Queue-time validation: reject missing local LoRAs before execution."""
+        return validate_lora_entries({"loras": loras}) or True
+
    RETURN_TYPES = ("LORA_STACK", "STRING", "STRING")
    RETURN_NAMES = ("LORA_STACK", "trigger_words", "active_loras")
    FUNCTION = "stack_loras"
@@ -0,0 +1,62 @@
+"""Node to resolve `<lora:name:strength>` syntax to absolute file system paths.
+
+Takes the loaded_loras / active_loras STRING output from LoraLoaderLM or
+LoraStackerLM and resolves each lora name to its absolute path on disk via
+the scanner cache. Unknown names are returned as-is.
+"""
+
+import logging
+
+from ..utils.utils import get_lora_info_absolute
+from .utils import parse_lora_syntax
+
+logger = logging.getLogger(__name__)
+
+
+class LoraSyntaxToPath:
+    NAME = "LoRA Syntax → Path (LoraManager)"
+    CATEGORY = "Lora Manager/utils"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "lora_syntax": (
+                    "STRING",
+                    {
+                        "forceInput": True,
+                        "multiline": True,
+                        "tooltip": (
+                            "<lora:name:strength> formatted text from "
+                            "loaded_loras / active_loras output"
+                        ),
+                    },
+                ),
+            },
+        }
+
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("paths",)
+    FUNCTION = "resolve"
+
+    def resolve(self, lora_syntax: str) -> tuple[str]:
+        """Parse <lora:...> syntax and resolve each name to its absolute path."""
+        if not lora_syntax or not lora_syntax.strip():
+            logger.info("Received empty lora_syntax input")
+            return ("",)
+
+        parsed = parse_lora_syntax(lora_syntax)
+        if not parsed:
+            logger.info("No valid <lora:...> entries found in input")
+            return ("",)
+
+        paths: list[str] = []
+        for entry in parsed:
+            try:
+                absolute_path, _ = get_lora_info_absolute(entry["name"])
+                paths.append(absolute_path)
+            except Exception:
+                logger.warning("Failed to resolve lora '%s', skipping", entry["name"])
+                continue
+
+        return ("\n".join(paths),)
@@ -0,0 +1,169 @@
+"""Metadata Overwrite node — allows users to manually specify generation parameters
+that override the automatically collected/inferred metadata.
+
+Most inputs have falsy defaults (empty string / 0) which are skipped.
+clip_skip uses a sentinel default (-25) so that a wired value of 0 is
+preserved — both ComfyUI and A1111 conventions have no meaningful 0 value,
+but users may wire 0 to express "no clip skip / default".
+"""
+
+from typing import Any
+
+from ..metadata_collector.constants import CLIP_SKIP_SENTINEL as _CLIP_SKIP_SENTINEL
+from ..metadata_collector.overwrite_utils import collect_overwrite_params
+
+
+class MetadataOverwriteLM:
+    NAME = "Metadata Overwrite (LoraManager)"
+    CATEGORY = "Lora Manager/utils"
+    DESCRIPTION = (
+        "Manually specify generation parameters to override automatically collected "
+        "metadata. Only filled/connected inputs will take effect — empty defaults "
+        "are ignored."
+    )
+
+    @classmethod
+    def INPUT_TYPES(cls) -> dict[str, Any]:
+        return {
+            "optional": {
+                "prompt": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Positive prompt. Only overwrites when non-empty.",
+                    },
+                ),
+                "negative_prompt": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Negative prompt. Only overwrites when non-empty.",
+                    },
+                ),
+                "seed": (
+                    "INT",
+                    {
+                        "default": 0,
+                        "min": 0,
+                        "max": 0xFFFFFFFFFFFFFFFF,
+                        "control_after_generate": False,
+                        "tooltip": "Seed value. Only overwrites when > 0.",
+                    },
+                ),
+                "steps": (
+                    "INT",
+                    {
+                        "default": 0,
+                        "min": 0,
+                        "max": 10000,
+                        "tooltip": "Number of steps. Only overwrites when > 0.",
+                    },
+                ),
+                "cfg_scale": (
+                    "FLOAT",
+                    {
+                        "default": 0.0,
+                        "min": 0.0,
+                        "max": 100.0,
+                        "tooltip": "CFG scale. Only overwrites when > 0.",
+                    },
+                ),
+                "sampler": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "tooltip": "Sampler name. Only overwrites when non-empty.",
+                    },
+                ),
+                "scheduler": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "tooltip": "Scheduler name. Only overwrites when non-empty.",
+                    },
+                ),
+                "model": (
+                    "STRING,MODEL",
+                    {
+                        "default": "",
+                        "widgetType": "STRING",
+                        "tooltip": (
+                            "The checkpoint or diffusion model (UNet) used "
+                            "for generation. Fill in the name manually or "
+                            "connect a MODEL output — the model name is then "
+                            "extracted automatically. Only overwrites when "
+                            "non-empty."
+                        ),
+                    },
+                ),
+                "loras": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": (
+                            "LoRA syntax, e.g. <lora:name:strength> "
+                            "or <lora:name:model_strength:clip_strength>, "
+                            "separated by spaces. Only overwrites when non-empty."
+                        ),
+                    },
+                ),
+                "size": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "tooltip": (
+                            "Image size in WIDTHxHEIGHT format (e.g. 512x768). "
+                            "Only overwrites when non-empty."
+                        ),
+                    },
+                ),
+                "clip_skip": (
+                    "INT",
+                    {
+                        "default": _CLIP_SKIP_SENTINEL,
+                        "min": -25,
+                        "max": 24,
+                        "tooltip": (
+                            "Clip skip (ComfyUI: -24..-1, A1111: 1+). "
+                            "Default -25 means not set — any other value "
+                            "overwrites."
+                        ),
+                    },
+                ),
+                "additional_data": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": (
+                            "Additional data to embed in the image metadata. "
+                            "Inserted between Clip skip and Model hash in the "
+                            "A1111-compatible parameters string. "
+                            'Example: "Copyright": "Some license info"'
+                        ),
+                    },
+                ),
+            },
+        }
+
+    RETURN_TYPES = ("METADATA",)
+    RETURN_NAMES = ("metadata",)
+    FUNCTION = "collect_metadata"
+    OUTPUT_NODE = True
+
+    def collect_metadata(self, **kwargs: Any) -> tuple[dict[str, Any]]:
+        """Collect non-default input values into a metadata dict.
+
+        For most fields, a falsy value (empty string, 0) means "not set"
+        and is skipped.  clip_skip uses a dedicated sentinel (-25) so that
+        a wired value of 0 is preserved and reaches the metadata pipeline.
+
+        The ``model`` field accepts either a manual string or a wired MODEL
+        (ModelPatcher) connection; in the latter case the underlying model
+        name is extracted from the patcher's ``cached_patcher_init`` and
+        stored as a ComfyUI-style relative path.
+        """
+        return (collect_overwrite_params(kwargs),)
@@ -15,15 +15,15 @@ import os
 import re
 from collections import defaultdict
 from pathlib import Path
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Optional, Tuple, Union, cast

-import comfy.utils  # type: ignore
-import folder_paths  # type: ignore
+import comfy.utils  # pyright: ignore[reportMissingImports]
+import folder_paths  # pyright: ignore[reportMissingImports]
 import torch
 import torch.nn as nn
 from safetensors import safe_open

-from nunchaku.lora.flux.nunchaku_converter import (
+from nunchaku.lora.flux.nunchaku_converter import (  # pyright: ignore[reportMissingTypeStubs]
    pack_lowrank_weight,
    unpack_lowrank_weight,
 )
@@ -87,10 +87,6 @@ def _rename_layer_underscore_layer_name(old_name: str) -> str:
    return new_name


-def _is_indexable_module(module):
-    return isinstance(module, (nn.ModuleList, nn.Sequential, list, tuple))
-
-
 def _get_module_by_name(model: nn.Module, name: str) -> Optional[nn.Module]:
    if not name:
        return model
@@ -100,7 +96,7 @@ def _get_module_by_name(model: nn.Module, name: str) -> Optional[nn.Module]:
            continue
        if hasattr(module, part):
            module = getattr(module, part)
-        elif part.isdigit() and _is_indexable_module(module):
+        elif part.isdigit() and isinstance(module, (nn.ModuleList, nn.Sequential, list, tuple)):
            try:
                module = module[int(part)]
            except (IndexError, TypeError):
@@ -267,7 +263,9 @@ def _handle_proj_out_split(lora_dict: Dict[str, Dict[str, torch.Tensor]], base_k
    return result, consumed


-def _apply_lora_to_module(module: nn.Module, a_tensor: torch.Tensor, b_tensor: torch.Tensor, module_name: str, model: nn.Module) -> None:
+def _apply_lora_to_module(module: Any, a_tensor: torch.Tensor, b_tensor: torch.Tensor, module_name: str, model: Any) -> None:
+    # These modules are dynamic torch containers; monkey-patched attributes
+    # below are set at runtime, so the module/model types are deliberately Any.
    if not hasattr(module, "in_features") or not hasattr(module, "out_features"):
        raise ValueError(f"{module_name}: unsupported module without in/out features")
    if a_tensor.shape[1] != module.in_features or b_tensor.shape[0] != module.out_features:
@@ -336,7 +334,7 @@ def _apply_lora_to_module(module: nn.Module, a_tensor: torch.Tensor, b_tensor: t
    raise ValueError(f"{module_name}: unsupported module type {type(module)}")


-def reset_lora_v2(model: nn.Module) -> None:
+def reset_lora_v2(model: Any) -> None:
    slots = getattr(model, "_lora_slots", None)
    if not slots:
        return
@@ -344,6 +342,7 @@ def reset_lora_v2(model: nn.Module) -> None:
        module = _get_module_by_name(model, name)
        if module is None:
            continue
+        module = cast(Any, module)
        module_type = info.get("type", "nunchaku")
        if module_type == "nunchaku":
            base_rank = info["base_rank"]
@@ -371,7 +370,7 @@ def reset_lora_v2(model: nn.Module) -> None:
 def compose_loras_v2(model: nn.Module, lora_configs: List[Tuple[Union[str, Path, Dict[str, torch.Tensor]], float]], apply_awq_mod: bool = True) -> bool:
    del apply_awq_mod  # retained for interface compatibility
    reset_lora_v2(model)
-    aggregated_weights: Dict[str, List[Dict[str, object]]] = defaultdict(list)
+    aggregated_weights: Dict[str, List[Dict[str, Any]]] = defaultdict(list)
    saw_supported_format = False
    unresolved_targets = 0

@@ -471,7 +470,7 @@ def compose_loras_v2(model: nn.Module, lora_configs: List[Tuple[Union[str, Path,
 class ComfyQwenImageWrapperLM(nn.Module):
    def __init__(self, model: nn.Module, config=None, apply_awq_mod: bool = True):
        super().__init__()
-        self.model = model
+        self.model: Any = model
        self.config = {} if config is None else config
        self.dtype = next(model.parameters()).dtype
        self.loras: List[Tuple[Union[str, Path, Dict[str, torch.Tensor]], float]] = []
@@ -67,7 +67,7 @@ class PromptLM:

        stack = inspect.stack()
        if len(stack) > 2 and stack[2].function == "get_input_info":
-            optional_inputs = _PromptOptionalInputs(optional_inputs)  # type: ignore[assignment]
+            optional_inputs = _PromptOptionalInputs(optional_inputs)  # pyright: ignore[reportAssignmentType]

        return {
            "required": {
@@ -126,7 +126,7 @@ class PromptLM:
        else:
            prompt = expanded_text

-        from nodes import CLIPTextEncode  # type: ignore
+        from nodes import CLIPTextEncode  # pyright: ignore[reportMissingImports, reportAttributeAccessIssue]

        conditioning = CLIPTextEncode().encode(clip, prompt)[0]
        return (conditioning, prompt)
@@ -5,7 +5,7 @@ import time
 import uuid
 from typing import Any, Dict, Optional
 import numpy as np
-import folder_paths  # type: ignore
+import folder_paths  # pyright: ignore[reportMissingImports]
 from ..services.service_registry import ServiceRegistry
 from ..metadata_collector.metadata_processor import MetadataProcessor
 from ..metadata_collector import get_metadata
@@ -13,9 +13,159 @@ from ..utils.constants import CARD_PREVIEW_WIDTH
 from ..utils.exif_utils import ExifUtils
 from ..utils.utils import calculate_recipe_fingerprint, sanitize_folder_name
 from PIL import Image, PngImagePlugin
-import piexif
+import piexif  # pyright: ignore[reportMissingTypeStubs]
 import logging

+# Civitai-compatible sampler name mapping: ComfyUI internal → A1111 display name
+CIVITAI_SAMPLER_MAP = {
+    "euler": "Euler",
+    "euler_ancestral": "Euler a",
+    "lms": "LMS",
+    "heun": "Heun",
+    "dpm_2": "DPM2",
+    "dpm_2_ancestral": "DPM2 a",
+    "dpmpp_2s_ancestral": "DPM++ 2S a",
+    "dpmpp_2m": "DPM++ 2M",
+    "dpmpp_sde": "DPM++ SDE",
+    "dpmpp_sde_gpu": "DPM++ SDE",
+    "dpmpp_2m_sde": "DPM++ 2M SDE",
+    "dpmpp_2m_sde_gpu": "DPM++ 2M SDE",
+    "dpmpp_3m_sde": "DPM++ 3M SDE",
+    "dpm_fast": "DPM fast",
+    "dpm_adaptive": "DPM adaptive",
+    "ddim": "DDIM",
+    "plms": "PLMS",
+    "uni_pc_bh2": "UniPC",
+    "uni_pc": "UniPC",
+    "lcm": "LCM",
+}
+
+# Base model display name → AIR URN slug
+# Sourced from civitai source: src/shared/constants/basemodel.constants.ts
+BASE_MODEL_AIR_SLUG = {
+    # Stable Diffusion family
+    "SD 1.4": "sd1",
+    "SD 1.5": "sd1",
+    "SD 1.5 LCM": "sd1",
+    "SD 1.5 Hyper": "sd1",
+    "SD 2.0": "sd2",
+    "SD 2.0 768": "sd2",
+    "SD 2.1": "sd2",
+    "SD 2.1 768": "sd2",
+    "SD 2.1 Unclip": "sd2",
+    "SD 3.0": "sd3",
+    "SD 3.5": "sd35",
+    "SD 3.5 Large": "sd35",
+    "SD 3.5 Large Turbo": "sd35",
+    "SD 3.5 Medium": "sd35",
+    "SDXL 0.9": "sdxl",
+    "SDXL 1.0": "sdxl",
+    "SDXL 1.0 LCM": "sdxl",
+    "SDXL Lightning": "sdxl",
+    "SDXL Hyper": "sdxl",
+    "SDXL Turbo": "sdxl",
+    "SDXL Distilled": "sdxldistilled",
+    "Stable Cascade": "scascade",
+    "Stable Video Diffusion": "svd",
+    "SVD": "svd",
+    "SVD XT": "svdxt",
+
+    # SDXL community fine-tunes
+    "Pony": "pony",
+    "Pony Diffusion": "pony",
+    "Illustrious": "illustrious",
+    "NoobAI": "noobai",
+    "Animagine": "illustrious",
+
+    # Flux family
+    "Flux.1": "flux1",
+    "Flux.1 D": "flux1",
+    "Flux.1 S": "flux1",
+    "Flux.1 Krea": "fluxkrea",
+    "Flux.1 Kontext": "flux1kontext",
+    "Flux.2": "flux2",
+    "Flux.2 D": "flux2",
+    "Flux.2 Klein 9B": "flux2klein_9b",
+    "Flux.2 Klein 9B Base": "flux2klein_9b_base",
+    "Flux.2 Klein 4B": "flux2klein_4b",
+    "Flux.2 Klein 4B Base": "flux2klein_4b_base",
+
+    # Other image models (sorted alphabetically)
+    "AuraFlow": "auraflow",
+    "Chroma": "chroma",
+    "HiDream": "hidream",
+    "HiDream-O1": "hidream-o1",
+    "Hunyuan DiT": "hydit1",
+    "Hunyuan Video": "hyv1",
+    "Kolors": "kolors",
+    "Lumina": "lumina",
+    "Mochi": "mochi",
+    "ODOR": "odor",
+    "PixArt Alpha": "pixarta",
+    "PixArt Sigma": "pixarte",
+    "Playground v2": "playgroundv2",
+    "Playground v2.5": "playgroundv2",
+    "Pony Diffusion V7": "ponyv7",
+
+    # Video models
+    "CogVideoX": "cogvideox",
+    "LTX Video": "ltxv",
+    "LTX Video 2": "ltxv2",
+    "LTX Video 2.3": "ltxv23",
+    "Wan Video": "wanvideo",
+    "Wan Video 1.3B T2V": "wanvideo_13b_t2v",
+    "Wan Video 14B T2V": "wanvideo_14b_t2v",
+    "Wan Video 14B I2V 480p": "wanvideo_14b_i2v_480p",
+    "Wan Video 14B I2V 720p": "wanvideo_14b_i2v_720p",
+
+    # Third-party / proprietary image models
+    "Boogu": "boogu",
+    "Ernie": "ernie",
+    "Grok": "grok",
+    "HappyHorse": "happyhorse",
+    "Ideogram": "ideogram",
+    "Ideogram 4.0": "ideogram",
+    "Imagen": "imagen4",
+    "Imagen 4": "imagen4",
+    "Krea": "krea2",
+    "Krea 2": "krea2",
+    "Lens": "lens",
+    "MAI": "mai",
+    "Nano Banana": "nanobanana",
+    "OpenAI": "openai",
+    "Reve": "reve",
+    "Reve 2": "reve",
+    "Reve 2.1": "reve",
+    "Seedream": "seedream",
+    "Sora": "sora2",
+    "Sora 2": "sora2",
+    "Veo": "veo3",
+    "Veo 2": "veo3",
+    "Veo 3": "veo3",
+    "ZImageTurbo": "zimageturbo",
+    "ZImageBase": "zimagebase",
+    "ZImage": "zimagebase",
+
+    # Third-party video models
+    "Hailuo by MiniMax": "minimax",
+    "Haiper": "haiper",
+    "Kling": "kling",
+    "Lightricks": "lightricks",
+    "Seedance": "seedance",
+    "Vidu": "vidu",
+
+    # Qwen family
+    "Qwen": "qwen",
+    "Qwen 2": "qwen2",
+
+    # Anima
+    "Anima": "anima",
+
+    # Special
+    "Upscaler": "upscaler",
+    "Other": "other",
+}
+
 logger = logging.getLogger(__name__)


@@ -70,11 +220,29 @@ class SaveImageLM:
                        "tooltip": "Compression quality for JPEG and lossy WebP formats (1-100). Higher values mean better quality but larger files.",
                    },
                ),
+                "webp_method": (
+                    "INT",
+                    {
+                        "default": 6,
+                        "min": 0,
+                        "max": 6,
+                        "tooltip": "WebP compression method (0-6). 0=fastest/largest, 6=slowest/smallest. Only applies when file_format is 'webp'.",
+                    },
+                ),
+                "jpeg_subsampling": (
+                    "INT",
+                    {
+                        "default": 0,
+                        "min": 0,
+                        "max": 2,
+                        "tooltip": "JPEG chroma subsampling level. 0=4:4:4 (best quality), 1=4:2:2, 2=4:2:0 (smallest files). Only applies when file_format is 'jpeg'.",
+                    },
+                ),
                "embed_workflow": (
                    "BOOLEAN",
                    {
                        "default": False,
-                        "tooltip": "Embeds the complete workflow data into the image metadata. Only works with PNG and WebP formats.",
+                        "tooltip": "When enabled, saved images store the complete workflow. Drag the image back into ComfyUI to restore the original node graph. PNG and WebP only.",
                    },
                ),
                "save_with_metadata": (
@@ -84,6 +252,13 @@ class SaveImageLM:
                        "tooltip": "When enabled, embeds generation parameters into the saved image metadata. Disable to skip writing generation metadata.",
                    },
                ),
+                "add_loras_to_prompt": (
+                    "BOOLEAN",
+                    {
+                        "default": False,
+                        "tooltip": "When enabled, appends the LoRA syntax line (e.g. <lora:name:strength>) after the positive prompt in the saved metadata.",
+                    },
+                ),
                "add_counter_to_filename": (
                    "BOOLEAN",
                    {
@@ -142,148 +317,197 @@ class SaveImageLM:

        return None

-    def format_metadata(self, metadata_dict):
-        """Format metadata in the requested format similar to userComment example"""
-        if not metadata_dict:
-            return ""
+    def _resolve_model_cache_entry(self, scanner_type: str, name: str):
+        """Resolve model hash, civitai metadata, and base_model from scanner cache.
+        Returns (hash_str, civitai_dict, base_model_str). All values are empty defaults when not found."""
+        scanner = ServiceRegistry.get_service_sync(scanner_type)
+        if scanner is None or not name:
+            return "", {}, ""

-        # Helper function to only add parameter if value is not None
-        def add_param_if_not_none(param_list, label, value):
-            if value is not None:
-                param_list.append(f"{label}: {value}")
+        entry = self._get_cached_model_by_name(scanner, name)
+        if entry is None:
+            basename = os.path.splitext(os.path.basename(name))[0]
+            hash_val = scanner.get_hash_by_filename(basename)
+            return (hash_val or "").lower(), {}, ""
+
+        hash_val = (entry.get("sha256") or "").lower()
+        civitai = entry.get("civitai") or {}
+        base_model = entry.get("base_model") or ""
+        return hash_val, civitai, base_model
+
+    @staticmethod
+    def _get_civitai_sampler_name(sampler_name: str, scheduler: str) -> str:
+        if sampler_name in CIVITAI_SAMPLER_MAP:
+            civitai_name = CIVITAI_SAMPLER_MAP[sampler_name]
+            if scheduler == "karras":
+                civitai_name += " Karras"
+            elif scheduler == "exponential":
+                civitai_name += " Exponential"
+            return civitai_name
+        else:
+            if scheduler and scheduler != "normal":
+                return f"{sampler_name}_{scheduler}"
+            return sampler_name
+
+    @staticmethod
+    def _build_air_string(base_model: str, model_type: str, model_id: int, version_id: int) -> str:
+        slug = BASE_MODEL_AIR_SLUG.get(base_model, "other")
+        type_lower = model_type.lower() if model_type else "other"
+        return f"urn:air:{slug}:{type_lower}:civitai:{model_id}@{version_id}"
+
+    def format_metadata(self, metadata_dict: dict[str, Any], add_loras_to_prompt: bool = False) -> str:
+        """Format metadata as A1111-compatible parameters string with Hashes JSON and Civitai resources."""
+        if not metadata_dict: return ""

-        # Extract the prompt and negative prompt
        prompt = metadata_dict.get("prompt", "")
        negative_prompt = metadata_dict.get("negative_prompt", "")
-
-        # Extract loras from the prompt if present
+        steps = metadata_dict.get("steps")
+        cfg = metadata_dict.get("guidance")
+        if cfg is None:
+            cfg = metadata_dict.get("cfg_scale")
+        if cfg is None:
+            cfg = metadata_dict.get("cfg")
+        seed = metadata_dict.get("seed")
+        size = metadata_dict.get("size")
+        sampler = metadata_dict.get("sampler") or ""
+        scheduler = metadata_dict.get("scheduler") or "normal"
+        checkpoint = metadata_dict.get("checkpoint") or ""
        loras_text = metadata_dict.get("loras", "")
-        lora_hashes = {}
+        clip_skip = metadata_dict.get("clip_skip")

-        # If loras are found, add them on a new line after the prompt
+        # Parse LoRA entries from <lora:name:strength> format
+        lora_entries: list[tuple[str, float]] = []
        if loras_text:
-            prompt_with_loras = f"{prompt}\n{loras_text}"
+            for match in re.findall(r"<lora:([^:]+):([^>]+)>", loras_text):
+                lora_name, strength_str = match
+                try:
+                    strength = float(strength_str)
+                except (ValueError, TypeError):
+                    strength = 1.0
+                lora_entries.append((lora_name, strength))

-            # Extract lora names from the format <lora:name:strength>
-            lora_matches = re.findall(r"<lora:([^:]+):([^>]+)>", loras_text)
+        # Resolve checkpoint hash and Civitai data from local cache
+        ckpt_hash, ckpt_civitai, ckpt_base_model = "", {}, ""
+        ckpt_display_name = ""
+        if checkpoint:
+            ckpt_hash, ckpt_civitai, ckpt_base_model = self._resolve_model_cache_entry(
+                "checkpoint_scanner", checkpoint
+            )
+            ckpt_display_name = os.path.splitext(os.path.basename(checkpoint))[0]

-            # Get hash for each lora
-            for lora_name, strength in lora_matches:
-                hash_value = self.get_lora_hash(lora_name)
-                if hash_value:
-                    lora_hashes[lora_name] = hash_value
-        else:
-            prompt_with_loras = prompt
+        # Resolve LoRA hash and Civitai data from local cache
+        loras_data: list[dict[str, Any]] = []
+        for lora_name, strength in lora_entries:
+            lora_hash, lora_civitai, lora_base_model = self._resolve_model_cache_entry(
+                "lora_scanner", lora_name
+            )
+            loras_data.append({
+                "name": lora_name,
+                "strength": strength,
+                "hash": lora_hash,
+                "civitai": lora_civitai,
+                "base_model": lora_base_model,
+            })

-        # Format the first part (prompt and loras)
-        metadata_parts = [prompt_with_loras]
+        # Build Hashes JSON (A1111 / Civitai standard format)
+        hashes: dict[str, str] = {}
+        if ckpt_hash:
+            hashes["model"] = ckpt_hash[:10].upper()
+        for lora in loras_data:
+            if lora["hash"]:
+                hashes[f"LORA:{lora['name']}"] = lora["hash"][:10].upper()

-        # Add negative prompt
+        # Build Civitai resources JSON array
+        civitai_resources: list[dict[str, Any]] = []
+        if ckpt_civitai.get("id", 0) > 0:
+            ckpt_resource: dict[str, Any] = {}
+            ckpt_type = (ckpt_civitai.get("model") or {}).get("type", "Checkpoint")
+            model_id = ckpt_civitai.get("modelId", 0)
+            version_id = ckpt_civitai.get("id", 0)
+            if model_id and version_id:
+                ckpt_resource["air"] = self._build_air_string(
+                    ckpt_base_model, ckpt_type, int(model_id), int(version_id)
+                )
+            elif version_id:
+                ckpt_resource["modelVersionId"] = int(version_id)
+            if ckpt_civitai.get("name"):
+                ckpt_resource["versionName"] = ckpt_civitai["name"]
+            if ckpt_resource:
+                civitai_resources.append(ckpt_resource)
+
+        for lora in loras_data:
+            lora_civitai = lora["civitai"]
+            if not lora_civitai or lora_civitai.get("id", 0) <= 0:
+                continue
+            lora_resource: dict[str, Any] = {"weight": lora["strength"]}
+            lora_type = (lora_civitai.get("model") or {}).get("type", "LORA")
+            model_id = lora_civitai.get("modelId", 0)
+            version_id = lora_civitai.get("id", 0)
+            if model_id and version_id:
+                lora_resource["air"] = self._build_air_string(
+                    lora["base_model"], lora_type, int(model_id), int(version_id)
+                )
+            elif version_id:
+                lora_resource["modelVersionId"] = int(version_id)
+            if lora_civitai.get("name"):
+                lora_resource["versionName"] = lora_civitai["name"]
+            civitai_resources.append(lora_resource)
+
+        sampler_name = CIVITAI_SAMPLER_MAP.get(sampler, sampler) if sampler else None
+
+        scheduler_mapping = {
+            "normal": "Normal",
+            "karras": "Karras",
+            "exponential": "Exponential",
+            "sgm_uniform": "SGM Uniform",
+            "sgm_quadratic": "SGM Quadratic",
+        }
+        scheduler_name = scheduler_mapping.get(scheduler, scheduler) if scheduler else None
+
+        # Build output lines
+        prompt_line = prompt if prompt else ""
+        if add_loras_to_prompt and loras_text:
+            prompt_line = f"{prompt_line}\n{loras_text}" if prompt_line else loras_text
+        lines = [prompt_line] if prompt_line else [""]
        if negative_prompt:
-            metadata_parts.append(f"Negative prompt: {negative_prompt}")
+            lines.append(f"Negative prompt: {negative_prompt}")

-        # Format the second part (generation parameters)
-        params = []
-
-        # Add standard parameters in the correct order
-        if "steps" in metadata_dict:
-            add_param_if_not_none(params, "Steps", metadata_dict.get("steps"))
-
-        # Combine sampler and scheduler information
-        sampler_name = None
-        scheduler_name = None
-
-        if "sampler" in metadata_dict:
-            sampler = metadata_dict.get("sampler")
-            # Convert ComfyUI sampler names to user-friendly names
-            sampler_mapping = {
-                "euler": "Euler",
-                "euler_ancestral": "Euler a",
-                "dpm_2": "DPM2",
-                "dpm_2_ancestral": "DPM2 a",
-                "heun": "Heun",
-                "dpm_fast": "DPM fast",
-                "dpm_adaptive": "DPM adaptive",
-                "lms": "LMS",
-                "dpmpp_2s_ancestral": "DPM++ 2S a",
-                "dpmpp_sde": "DPM++ SDE",
-                "dpmpp_sde_gpu": "DPM++ SDE",
-                "dpmpp_2m": "DPM++ 2M",
-                "dpmpp_2m_sde": "DPM++ 2M SDE",
-                "dpmpp_2m_sde_gpu": "DPM++ 2M SDE",
-                "ddim": "DDIM",
-            }
-            sampler_name = sampler_mapping.get(sampler, sampler)
-
-        if "scheduler" in metadata_dict:
-            scheduler = metadata_dict.get("scheduler")
-            scheduler_mapping = {
-                "normal": "Simple",
-                "karras": "Karras",
-                "exponential": "Exponential",
-                "sgm_uniform": "SGM Uniform",
-                "sgm_quadratic": "SGM Quadratic",
-            }
-            scheduler_name = scheduler_mapping.get(scheduler, scheduler)
-
-        # Add combined sampler and scheduler information
+        params: list[str] = []
+        if steps is not None:
+            params.append(f"Steps: {steps}")
        if sampler_name:
            if scheduler_name:
                params.append(f"Sampler: {sampler_name} {scheduler_name}")
            else:
                params.append(f"Sampler: {sampler_name}")
+        if cfg is not None:
+            params.append(f"CFG scale: {cfg}")
+        if seed is not None:
+            params.append(f"Seed: {seed}")
+        if size:
+            params.append(f"Size: {size}")
+        if clip_skip is not None:
+            try:
+                params.append(f"Clip skip: {abs(int(clip_skip))}")
+            except (ValueError, TypeError):
+                pass
+        additional_data = metadata_dict.get("additional_data", "")
+        if additional_data:
+            params.append(additional_data)
+        if ckpt_hash:
+            params.append(f"Model hash: {ckpt_hash[:10].upper()}")
+        if ckpt_display_name:
+            params.append(f"Model: {ckpt_display_name}")
+        if hashes:
+            params.append(f"Hashes: {json.dumps(hashes, separators=(',', ':'))}")
+        params.append("Version: ComfyUI")
+        if civitai_resources:
+            params.append(
+                f"Civitai resources: {json.dumps(civitai_resources, separators=(',', ':'))}"
+            )

-        # CFG scale (Use guidance if available, otherwise fall back to cfg_scale or cfg)
-        if "guidance" in metadata_dict:
-            add_param_if_not_none(params, "CFG scale", metadata_dict.get("guidance"))
-        elif "cfg_scale" in metadata_dict:
-            add_param_if_not_none(params, "CFG scale", metadata_dict.get("cfg_scale"))
-        elif "cfg" in metadata_dict:
-            add_param_if_not_none(params, "CFG scale", metadata_dict.get("cfg"))
-
-        # Seed
-        if "seed" in metadata_dict:
-            add_param_if_not_none(params, "Seed", metadata_dict.get("seed"))
-
-        # Size
-        if "size" in metadata_dict:
-            add_param_if_not_none(params, "Size", metadata_dict.get("size"))
-
-        # Model info
-        if "checkpoint" in metadata_dict:
-            # Ensure checkpoint is a string before processing
-            checkpoint = metadata_dict.get("checkpoint")
-            if checkpoint is not None:
-                # Get model hash
-                model_hash = self.get_checkpoint_hash(checkpoint)
-
-                # Extract basename without path
-                checkpoint_name = os.path.basename(checkpoint)
-                # Remove extension if present
-                checkpoint_name = os.path.splitext(checkpoint_name)[0]
-
-                # Add model hash if available
-                if model_hash:
-                    params.append(
-                        f"Model hash: {model_hash[:10]}, Model: {checkpoint_name}"
-                    )
-                else:
-                    params.append(f"Model: {checkpoint_name}")
-
-        # Add LoRA hashes if available
-        if lora_hashes:
-            lora_hash_parts = []
-            for lora_name, hash_value in lora_hashes.items():
-                lora_hash_parts.append(f"{lora_name}: {hash_value[:10]}")
-
-            if lora_hash_parts:
-                params.append(f'Lora hashes: "{", ".join(lora_hash_parts)}"')
-
-        # Combine all parameters with commas
-        metadata_parts.append(", ".join(params))
-
-        # Join all parts with a new line
-        return "\n".join(metadata_parts)
+        lines.append(", ".join(params))
+        return "\n".join(lines)

    # credit to nkchocoai
    # Add format_filename method to handle pattern substitution
@@ -573,10 +797,13 @@ class SaveImageLM:
        extra_pnginfo=None,
        lossless_webp=True,
        quality=100,
+        webp_method=6,
+        jpeg_subsampling=0,
        embed_workflow=False,
        save_with_metadata=True,
        add_counter_to_filename=True,
        save_as_recipe=False,
+        add_loras_to_prompt=False,
    ):
        """Save images with metadata"""
        results = []
@@ -585,7 +812,7 @@ class SaveImageLM:
        raw_metadata = get_metadata()
        metadata_dict = MetadataProcessor.to_dict(raw_metadata, id)

-        metadata = self.format_metadata(metadata_dict)
+        metadata = self.format_metadata(metadata_dict, add_loras_to_prompt)

        # Process filename_prefix with pattern substitution
        filename_prefix = self.format_filename(filename_prefix, metadata_dict)
@@ -627,15 +854,14 @@ class SaveImageLM:
            elif file_format == "jpeg":
                file = base_filename + ".jpg"
                file_extension = ".jpg"
-                save_kwargs = {"quality": quality, "optimize": True}
+                save_kwargs = {"quality": quality, "optimize": True, "subsampling": jpeg_subsampling}
            elif file_format == "webp":
                file = base_filename + ".webp"
                file_extension = ".webp"
-                # Add optimization param to control performance
                save_kwargs = {
                    "quality": quality,
                    "lossless": lossless_webp,
-                    "method": 0,
+                    "method": webp_method,
                }
            else:
                raise ValueError(f"Unsupported file format: {file_format}")
@@ -722,10 +948,13 @@ class SaveImageLM:
        extra_pnginfo=None,
        lossless_webp=True,
        quality=100,
+        webp_method=6,
+        jpeg_subsampling=0,
        embed_workflow=False,
        save_with_metadata=True,
        add_counter_to_filename=True,
        save_as_recipe=False,
+        add_loras_to_prompt=False,
    ):
        """Process and save image with metadata"""
        # Make sure the output directory exists
@@ -751,10 +980,13 @@ class SaveImageLM:
            extra_pnginfo,
            lossless_webp,
            quality,
+            webp_method,
+            jpeg_subsampling,
            embed_workflow,
            save_with_metadata,
            add_counter_to_filename,
            save_as_recipe,
+            add_loras_to_prompt,
        )

        return {
@@ -1,12 +1,27 @@
 import logging
 import os
-from typing import List, Tuple
-import comfy.sd # type: ignore
+from typing import Any, List, Tuple
+import comfy.sd  # pyright: ignore[reportMissingImports]
 from ..utils.utils import get_checkpoint_info_absolute, _format_model_name_for_comfyui

 logger = logging.getLogger(__name__)


+def _reload_gguf_unet(
+    unet_path: str, weight_dtype: str, disable_dynamic: bool = False
+) -> object:
+    """Reload a GGUF diffusion model from disk (cached_patcher_init factory).
+
+    Mirrors the GGUF branch of UNETLoaderLM.load_unet so ModelPatcher
+    deepclone/dynamic machinery can rebuild GGUF models with the correct
+    GGMLOps. ``disable_dynamic`` is accepted for signature compatibility
+    with core ComfyUI loaders.
+    """
+    loader = UNETLoaderLM()
+    model, = loader._load_gguf_unet(unet_path, unet_path, weight_dtype)
+    return model
+
+
 class UNETLoaderLM:
    """UNET Loader with support for extra folder paths

@@ -19,9 +34,9 @@ class UNETLoaderLM:
    CATEGORY = "Lora Manager/loaders"

    @classmethod
-    def INPUT_TYPES(s):
+    def INPUT_TYPES(cls):
        # Get list of unet names from scanner (includes extra folder paths)
-        unet_names = s._get_unet_names()
+        unet_names = cls._get_unet_names()
        return {
            "required": {
                "unet_name": (
@@ -59,7 +74,10 @@ class UNETLoaderLM:
                for item in cache.raw_data:
                    if item.get("sub_type") == "diffusion_model":
                        file_path = item.get("file_path", "")
-                        if file_path:
+                        # Only offer models that still exist on disk so ComfyUI
+                        # flags missing diffusion models at queue time via
+                        # "value not in list" (the scanner cache can be stale).
+                        if file_path and os.path.exists(file_path):
                            # Format using relative path with OS-native separator
                            formatted_name = _format_model_name_for_comfyui(
                                file_path, model_roots
@@ -90,7 +108,7 @@ class UNETLoaderLM:
            logger.error(f"Error getting unet names: {e}")
            return []

-    def load_unet(self, unet_name: str, weight_dtype: str) -> Tuple:
+    def load_unet(self, unet_name: str, weight_dtype: str) -> Tuple[Any, ...]:
        """Load a diffusion model by name, supporting extra folder paths

        Args:
@@ -133,7 +151,7 @@ class UNETLoaderLM:

    def _load_gguf_unet(
        self, unet_path: str, unet_name: str, weight_dtype: str
-    ) -> Tuple:
+    ) -> Tuple[Any, ...]:
        """Load a GGUF format diffusion model

        Args:
@@ -196,6 +214,12 @@ class UNETLoaderLM:
            # Wrap with GGUFModelPatcher
            model = GGUFModelPatcher.clone(model)

+            # Register a reload factory so the MODEL carries its source path
+            # (cached_patcher_init) like core ComfyUI loaders do — required
+            # for model-name extraction downstream and for ModelPatcher
+            # deepclone/dynamic machinery.
+            model.cached_patcher_init = (_reload_gguf_unet, (unet_path, weight_dtype))
+
            return (model,)

        except Exception as e:
@@ -1,3 +1,6 @@
+from typing import Any
+
+
 class AnyType(str):
    """A special class that is always equal in not equal comparisons. Credit to pythongosssss"""

@@ -6,7 +9,7 @@ class AnyType(str):


 # Credit to Regis Gaughan, III (rgthree)
-class FlexibleOptionalInputType(dict):
+class FlexibleOptionalInputType(dict[str, Any]):
    """A special class to make flexible nodes that pass data to our python handlers.

    Enables both flexible/dynamic input types (like for Any Switch) or a dynamic number of inputs
@@ -23,6 +26,7 @@ class FlexibleOptionalInputType(dict):
    """

    def __init__(self, type):
+        super().__init__()
        self.type = type

    def __getitem__(self, key):
@@ -36,10 +40,12 @@ any_type = AnyType("*")

 # Common methods extracted from lora_loader.py and lora_stacker.py
 import os
+import re
 import logging
 import copy
 import sys
-import folder_paths  # type: ignore
+import asyncio
+import folder_paths  # pyright: ignore[reportMissingImports]

 logger = logging.getLogger(__name__)

@@ -69,6 +75,25 @@ def extract_lora_name(lora_path):
    return apply_lora_syntax_format(name_no_ext)


+def parse_lora_syntax(text: str) -> list[dict[str, Any]]:
+    """Parse <lora:name:strength> syntax from text input into a list of dicts.
+
+    Each entry contains: name, model_strength, clip_strength.
+    Supports both ``<lora:name:strength>`` and ``<lora:name:model_strength:clip_strength>``.
+    """
+    pattern = r"<lora:([^:>]+):([^:>]+)(?::([^:>]+))?>"
+    matches = re.findall(pattern, text, re.IGNORECASE)
+    loras = []
+    for match in matches:
+        model_strength = float(match[1])
+        loras.append({
+            "name": match[0],
+            "model_strength": model_strength,
+            "clip_strength": float(match[2]) if match[2] else model_strength,
+        })
+    return loras
+
+
 def get_loras_list(kwargs):
    """Helper to extract loras list from either old or new kwargs format"""
    if "loras" not in kwargs:
@@ -87,6 +112,157 @@ def get_loras_list(kwargs):
        return []


+_LORA_EXTENSIONS = (".safetensors", ".ckpt", ".pt", ".bin")
+
+
+def _strip_lora_extension(name: str) -> str:
+    """Strip a known LoRA model extension from a name (case-insensitive)."""
+    lowered = name.lower()
+    for ext in _LORA_EXTENSIONS:
+        if lowered.endswith(ext):
+            return name[: -len(ext)]
+    return name
+
+
+def _find_missing_loras(names: list[str]) -> list[str]:
+    """Return the names that cannot be resolved to an existing local LoRA file.
+
+    Mirrors the matching semantics of ``get_lora_info_absolute``
+    (py/utils/utils.py): after stripping the extension, a name matches a cached
+    LoRA when it equals the cached file name or the ``folder/file`` path. As a
+    fallback, a name containing a folder that only matches by basename resolves
+    to the first basename match (same behavior as the runtime resolver). Raw
+    absolute paths that exist on disk are always considered available.
+
+    The scanner cache is fetched once for all names; the cache may be stale, so
+    resolved paths are additionally verified with ``os.path.isfile``.
+    """
+    if not names:
+        return []
+
+    async def _check() -> list[str]:
+        from ..services.service_registry import ServiceRegistry
+
+        scanner = await ServiceRegistry.get_lora_scanner()
+        # The scanner cache may not be hydrated yet (startup, library path
+        # change). An empty cache is not authoritative — treat it as "cannot
+        # verify" and skip validation instead of flagging every active LoRA
+        # as missing.
+        if getattr(scanner, "_cache", None) is None or getattr(
+            scanner, "_is_initializing", False
+        ):
+            return []
+        cache = await scanner.get_cached_data()
+
+        lookup = {}
+        basename_candidates = {}
+        for item in cache.raw_data:
+            file_path = item.get("file_path")
+            if not file_path:
+                continue
+            file_name = item.get("file_name", "")
+            folder = item.get("folder", "")
+            file_name_no_ext = _strip_lora_extension(file_name)
+            path_name_no_ext = (
+                f"{folder}/{file_name_no_ext}".replace("\\", "/")
+                if folder
+                else file_name_no_ext
+            )
+            lookup.setdefault(file_name_no_ext, file_path)
+            lookup.setdefault(path_name_no_ext, file_path)
+            basename_candidates.setdefault(file_name_no_ext, []).append(
+                (folder, file_path)
+            )
+
+        missing = []
+        for name in names:
+            if not name:
+                continue
+            normalized = name.replace("\\", "/")
+            # Raw absolute paths (outside the library) are usable as-is.
+            if os.path.isfile(normalized):
+                continue
+            no_ext = _strip_lora_extension(normalized)
+            file_path = lookup.get(no_ext)
+            if file_path is None and "/" in no_ext:
+                # A name with a folder that matches only by basename resolves
+                # at runtime like get_lora_info_absolute's fallback does:
+                # prefer a candidate whose folder prefixes the name, else the
+                # first basename match.
+                folder, basename = no_ext.rsplit("/", 1)
+                candidates = basename_candidates.get(basename, [])
+                file_path = next(
+                    (
+                        fp
+                        for fld, fp in candidates
+                        if fld and no_ext.startswith(fld + "/")
+                    ),
+                    None,
+                )
+                if file_path is None and candidates:
+                    file_path = candidates[0][1]
+            if file_path is None or not os.path.isfile(file_path):
+                missing.append(name)
+        return missing
+
+    try:
+        # Check if we're already in an event loop
+        loop = asyncio.get_running_loop()
+        # If we're in a running loop, run the async check in a separate thread
+        import concurrent.futures
+
+        def run_in_thread():
+            new_loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(new_loop)
+            try:
+                return new_loop.run_until_complete(_check())
+            finally:
+                new_loop.close()
+
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future = executor.submit(run_in_thread)
+            return future.result()
+    except RuntimeError:
+        # No event loop is running, we can use asyncio.run()
+        return asyncio.run(_check())
+
+
+def validate_lora_entries(kwargs):
+    """Validate active LoRA widget entries against the local library.
+
+    Used by node ``VALIDATE_INPUTS`` implementations so ComfyUI rejects the
+    prompt at queue time (``custom_validation_failed``) when an active entry
+    references a LoRA that is not available locally — mirroring how built-in
+    loader nodes flag missing models before execution starts.
+
+    Returns:
+        None when every active entry resolves to an existing local file,
+        otherwise a descriptive error string listing the missing LoRAs.
+        Verification failures (e.g. scanner not ready) are treated as valid
+        so queueing is never blocked by validation machinery itself.
+    """
+    # Missing/empty loras input is always valid; skip get_loras_list so it
+    # does not log a warning for the None case on every queue.
+    if not kwargs.get("loras"):
+        return None
+    loras = get_loras_list(kwargs)
+    active_names = []
+    for lora in loras:
+        if not isinstance(lora, dict):
+            continue
+        if not lora.get("active", False):
+            continue
+        active_names.append(apply_lora_syntax_format(str(lora.get("name") or "")))
+    try:
+        missing = _find_missing_loras(active_names)
+    except Exception:
+        logger.exception("Failed to validate LoRA entries against the local library")
+        return None
+    if not missing:
+        return None
+    return "Missing LoRA(s) in local library: " + ", ".join(missing)
+
+
 def load_state_dict_in_safetensors(path, device="cpu", filter_prefix=""):
    """Simplified version of load_state_dict_in_safetensors that just loads from a local path"""
    import safetensors.torch
@@ -1,7 +1,7 @@
 import os
 from ..utils.utils import get_lora_info_absolute
 from ..config import config
-from .utils import FlexibleOptionalInputType, any_type, get_loras_list
+from .utils import FlexibleOptionalInputType, any_type, get_loras_list, validate_lora_entries
 import logging

 logger = logging.getLogger(__name__)
@@ -35,6 +35,11 @@ class WanVideoLoraSelectLM:
            "optional": FlexibleOptionalInputType(any_type),
        }

+    @classmethod
+    def VALIDATE_INPUTS(cls, loras=None):
+        """Queue-time validation: reject missing local LoRAs before execution."""
+        return validate_lora_entries({"loras": loras}) or True
+
    RETURN_TYPES = ("WANVIDLORA", "STRING", "STRING")
    RETURN_NAMES = ("lora", "trigger_words", "active_loras")
    FUNCTION = "process_loras"
@@ -1,3 +1,7 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 """Base classes for recipe parsers."""

 import json
@@ -7,7 +11,7 @@ import re
 from typing import Dict, List, Any, Optional, Tuple
 from abc import ABC, abstractmethod
 from ..config import config
-from ..utils.constants import VALID_LORA_TYPES, VALID_CHECKPOINT_SUB_TYPES
+from ..utils.constants import MODEL_WEIGHT_FILE_TYPES, VALID_LORA_TYPES, VALID_CHECKPOINT_SUB_TYPES
 from ..utils.civitai_utils import rewrite_preview_url

 logger = logging.getLogger(__name__)
@@ -38,7 +42,7 @@ class RecipeMetadataParser(ABC):
        pass
    
    @staticmethod
-    async def populate_lora_from_civitai(lora_entry: Dict[str, Any], civitai_info_tuple: Tuple[Dict[str, Any], Optional[str]], 
+    async def populate_lora_from_civitai(lora_entry: Dict[str, Any], civitai_info_tuple: Tuple[Dict[str, Any] | None, str | None] | Dict[str, Any],
                                         recipe_scanner=None, base_model_counts=None, hash_value=None) -> Optional[Dict[str, Any]]:
        """
        Populate a lora entry with information from Civitai API response
@@ -151,9 +155,9 @@ class RecipeMetadataParser(ABC):
            
            # Process file information if available
            if 'files' in civitai_info:
-                # Find the primary model file (type="Model" and primary=true) in the files list
+                # Find the primary model file (weights-type and primary=true) in the files list
                model_file = next((file for file in civitai_info.get('files', []) 
-                                    if file.get('type') == 'Model' and file.get('primary') == True), None)
+                                    if file.get('type') in MODEL_WEIGHT_FILE_TYPES and file.get('primary') == True), None)
                
                if model_file:
                    # Get size
@@ -175,10 +179,18 @@ class RecipeMetadataParser(ABC):
                                lora_entry['localPath'] = local_path
                                lora_entry['file_name'] = os.path.splitext(os.path.basename(local_path))[0]
                                
-                                # Get thumbnail from local preview if available
+                                # Get thumbnail from local preview if available.
+                                # Match the cache item by local path first (get_path_by_hash
+                                # cascade: 10-char autov2 / 12-char autov3), then by hash.
                                lora_cache = await lora_scanner.get_cached_data()
-                                lora_item = next((item for item in lora_cache.raw_data 
-                                                    if item['sha256'].lower() == lora_entry['hash'].lower()), None)
+                                h = (lora_entry.get("hash") or "").lower()
+                                lora_item = next((item for item in lora_cache.raw_data
+                                                  if (item.get("file_path") or "") == local_path), None)
+                                if lora_item is None:
+                                    lora_item = next((item for item in lora_cache.raw_data
+                                                      if (item.get("sha256") or "").lower() == h
+                                                      or (item.get("autov3") or "").lower() == h
+                                                      or (item.get("sha256") or "")[:10].lower() == h), None)
                                if lora_item and 'preview_url' in lora_item:
                                    lora_entry['thumbnailUrl'] = config.get_preview_static_url(lora_item['preview_url'])
                            except Exception as e:
@@ -194,7 +206,7 @@ class RecipeMetadataParser(ABC):
        return lora_entry
    
    @staticmethod
-    async def populate_checkpoint_from_civitai(checkpoint: Dict[str, Any], civitai_info: Dict[str, Any]) -> Dict[str, Any]:
+    async def populate_checkpoint_from_civitai(checkpoint: Dict[str, Any], civitai_info: Dict[str, Any] | Tuple[Dict[str, Any] | None, str | None] | None) -> Dict[str, Any]:
        """
        Populate checkpoint information from Civitai API response
        
@@ -249,11 +261,21 @@ class RecipeMetadataParser(ABC):
            checkpoint['id'] = civitai_data.get('id', 0)

            if 'files' in civitai_data:
+                # Prefer the file CivitAI marked primary; fall back to any
+                # weights-type file (providers without primary flags).
                model_file = next(
                    (
                        file
                        for file in civitai_data.get('files', [])
-                        if file.get('type') == 'Model'
+                        if file.get('type') in MODEL_WEIGHT_FILE_TYPES
+                        and file.get('primary') is True
+                    ),
+                    None,
+                ) or next(
+                    (
+                        file
+                        for file in civitai_data.get('files', [])
+                        if file.get('type') in MODEL_WEIGHT_FILE_TYPES
                    ),
                    None,
                )
@@ -1,3 +1,7 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 import logging
 import json
 import os
@@ -1,6 +1,7 @@
 """Factory for creating recipe metadata parsers."""

 import logging
+from typing import Any
 from .parsers import (
    RecipeFormatParser,
    ComfyMetadataParser,
@@ -31,7 +32,8 @@ class RecipeParserFactory:
        # First, try CivitaiApiMetadataParser for dict input
        if isinstance(metadata, dict):
            try:
-                if CivitaiApiMetadataParser().is_metadata_matching(metadata):
+                user_comment: Any = metadata
+                if CivitaiApiMetadataParser().is_metadata_matching(user_comment):
                    return CivitaiApiMetadataParser()
            except Exception as e:
                logger.debug(f"CivitaiApiMetadataParser check failed: {e}")
@@ -52,7 +52,7 @@ class AutomaticMetadataParser(RecipeMetadataParser):
                    negative_and_params = ""
            
            # Initialize metadata
-            metadata = {
+            metadata: Dict[str, Any] = {
                "prompt": prompt,
                "loras": []
            }
@@ -4,7 +4,7 @@ import json
 import logging
 from typing import Dict, Any, Union
 from ..base import RecipeMetadataParser
-from ..constants import GEN_PARAM_KEYS
+from ..constants import GEN_PARAM_KEYS, VALID_LORA_TYPES
 from ...services.metadata_service import get_default_metadata_provider
 from ...config import config

@@ -14,15 +14,16 @@ logger = logging.getLogger(__name__)
 class CivitaiApiMetadataParser(RecipeMetadataParser):
    """Parser for Civitai image metadata format"""

-    def is_metadata_matching(self, metadata) -> bool:
+    def is_metadata_matching(self, user_comment) -> bool:
        """Check if the metadata matches the Civitai image metadata format

        Args:
-            metadata: The metadata from the image (dict)
+            user_comment: The metadata from the image (dict)

        Returns:
            bool: True if this parser can handle the metadata
        """
+        metadata = user_comment
        if not metadata or not isinstance(metadata, dict):
            return False

@@ -73,7 +74,7 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):

        return False

-    async def parse_metadata(  # type: ignore[override]
+    async def parse_metadata(  # pyright: ignore[reportIncompatibleMethodOverride]
        self, user_comment, recipe_scanner=None, civitai_client=None,
        local_cache: dict[str, Any] | None = None,
    ) -> Dict[str, Any]:
@@ -89,8 +90,7 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
        Returns:
            Dict containing parsed recipe data
        """
-        metadata: Dict[str, Any] = user_comment  # type: ignore[assignment]
-        metadata = user_comment
+        metadata: Dict[str, Any] = user_comment
        try:
            # Get metadata provider instead of using civitai_client directly
            metadata_provider = await get_default_metadata_provider()
@@ -116,7 +116,7 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                    metadata = inner_meta

            # Initialize result structure
-            result = {
+            result: Dict[str, Any] = {
                "base_model": None,
                "loras": [],
                "model": None,
@@ -125,10 +125,10 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
            }

            # Track already added LoRAs to prevent duplicates
-            added_loras = {}  # key: model_version_id or hash, value: index in result["loras"]
+            added_loras: Dict[str, Any] = {}  # key: model_version_id or hash, value: index in result["loras"]

            # Extract hash information from hashes field for LoRA matching
-            lora_hashes = {}
+            lora_hashes: Dict[str, Any] = {}
            if "hashes" in metadata and isinstance(metadata["hashes"], dict):
                for key, hash_value in metadata["hashes"].items():
                    key_str = str(key)
@@ -184,7 +184,7 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                            if model_info:
                                result["base_model"] = model_info.get("baseModel", "")

-            base_model_counts = {}
+            base_model_counts: Dict[str, int] = {}

            # Process standard resources array
            if "resources" in metadata and isinstance(metadata["resources"], list):
@@ -196,7 +196,7 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                    # identification because it has an explicit type field and hash,
                    # unlike modelVersionIds which is a flat list with no type info.
                    if resource_type == "model":
-                        checkpoint_entry = {
+                        checkpoint_entry: Dict[str, Any] = {
                            "id": 0,
                            "modelId": 0,
                            "name": resource.get("name", "Unknown Model"),
@@ -216,7 +216,8 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                        # Try to look up base model from the checkpoint hash
                        cp_hash = checkpoint_entry.get("hash")
                        if cp_hash and metadata_provider:
-                            local_cached = local_cache.get(cp_hash) if local_cache else None
+                            # local_cache keys are stored lowercase
+                            local_cached = local_cache.get(cp_hash.lower()) if local_cache else None
                            if local_cached:
                                self._populate_entry_from_cache(
                                    checkpoint_entry, local_cached
@@ -294,8 +295,15 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):

                        # Try to get info from Civitai if hash is available
                        if lora_hash and metadata_provider:
-                            local_cached = local_cache.get(lora_hash) if local_cache else None
+                            # local_cache keys are stored lowercase
+                            local_cached = local_cache.get(lora_hash.lower()) if local_cache else None
                            if local_cached:
+                                cached_type = self._cache_item_model_type(local_cached)
+                                if cached_type and cached_type not in VALID_LORA_TYPES:
+                                    logger.debug(
+                                        f"Skipping non-LoRA cache item for hash {lora_hash}"
+                                    )
+                                    continue
                                self._populate_entry_from_cache(
                                    lora_entry, local_cached
                                )
@@ -304,6 +312,12 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                                    added_loras[str(lora_entry["id"])] = len(
                                        result["loras"]
                                    )
+                                # Mirror base.py:150-151 counts for API-path loras
+                                bm = local_cached.get("base_model") or ""
+                                if bm:
+                                    base_model_counts[bm] = base_model_counts.get(
+                                        bm, 0
+                                    ) + 1
                            else:
                                try:
                                    civitai_info = (
@@ -649,30 +663,47 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                }

                if metadata_provider:
-                    try:
-                        civitai_info = await metadata_provider.get_model_by_hash(
-                            lora_hash
-                        )
-
-                        populated_entry = await self.populate_lora_from_civitai(
-                            lora_entry,
-                            civitai_info,
-                            recipe_scanner,
-                            base_model_counts,
-                            lora_hash,
-                        )
-
-                        if populated_entry is None:
+                    # local_cache keys are stored lowercase
+                    local_cached = local_cache.get(lora_hash.lower()) if local_cache else None
+                    if local_cached:
+                        cached_type = self._cache_item_model_type(local_cached)
+                        if cached_type and cached_type not in VALID_LORA_TYPES:
+                            logger.debug(
+                                f"Skipping non-LoRA cache item for hash {lora_hash}"
+                            )
                            continue
-
-                        lora_entry = populated_entry
-
+                        self._populate_entry_from_cache(lora_entry, local_cached)
+                        # Mirror base.py:150-151 counts for API-path loras
+                        bm = local_cached.get("base_model") or ""
+                        if bm:
+                            base_model_counts[bm] = base_model_counts.get(bm, 0) + 1
                        if "id" in lora_entry and lora_entry["id"]:
                            added_loras[str(lora_entry["id"])] = len(result["loras"])
-                    except Exception as e:
-                        logger.error(
-                            f"Error fetching Civitai info for LoRA hash {lora_hash}: {e}"
-                        )
+                    else:
+                        try:
+                            civitai_info = await metadata_provider.get_model_by_hash(
+                                lora_hash
+                            )
+
+                            populated_entry = await self.populate_lora_from_civitai(
+                                lora_entry,
+                                civitai_info,
+                                recipe_scanner,
+                                base_model_counts,
+                                lora_hash,
+                            )
+
+                            if populated_entry is None:
+                                continue
+
+                            lora_entry = populated_entry
+
+                            if "id" in lora_entry and lora_entry["id"]:
+                                added_loras[str(lora_entry["id"])] = len(result["loras"])
+                        except Exception as e:
+                            logger.error(
+                                f"Error fetching Civitai info for LoRA hash {lora_hash}: {e}"
+                            )

                added_loras[lora_hash] = len(result["loras"])
                result["loras"].append(lora_entry)
@@ -711,32 +742,51 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):

                # Try to get info from Civitai if hash is available
                if lora_entry["hash"] and metadata_provider:
-                    try:
-                        civitai_info = await metadata_provider.get_model_by_hash(
-                            lora_hash
-                        )
-
-                        populated_entry = await self.populate_lora_from_civitai(
-                            lora_entry,
-                            civitai_info,
-                            recipe_scanner,
-                            base_model_counts,
-                            lora_hash,
-                        )
-
-                        if populated_entry is None:
+                    # local_cache keys are stored lowercase
+                    local_cached = local_cache.get(lora_hash.lower()) if local_cache else None
+                    if local_cached:
+                        cached_type = self._cache_item_model_type(local_cached)
+                        if cached_type and cached_type not in VALID_LORA_TYPES:
+                            logger.debug(
+                                f"Skipping non-LoRA cache item for hash {lora_hash}"
+                            )
                            lora_index += 1
-                            continue  # Skip invalid LoRA types
-
-                        lora_entry = populated_entry
-
+                            continue  # Skip non-LoRA cache items
+                        self._populate_entry_from_cache(lora_entry, local_cached)
+                        # Mirror base.py:150-151 counts for API-path loras
+                        bm = local_cached.get("base_model") or ""
+                        if bm:
+                            base_model_counts[bm] = base_model_counts.get(bm, 0) + 1
                        # If we have a version ID from Civitai, track it for deduplication
                        if "id" in lora_entry and lora_entry["id"]:
                            added_loras[str(lora_entry["id"])] = len(result["loras"])
-                    except Exception as e:
-                        logger.error(
-                            f"Error fetching Civitai info for LoRA hash {lora_entry['hash']}: {e}"
-                        )
+                    else:
+                        try:
+                            civitai_info = await metadata_provider.get_model_by_hash(
+                                lora_hash
+                            )
+
+                            populated_entry = await self.populate_lora_from_civitai(
+                                lora_entry,
+                                civitai_info,
+                                recipe_scanner,
+                                base_model_counts,
+                                lora_hash,
+                            )
+
+                            if populated_entry is None:
+                                lora_index += 1
+                                continue  # Skip invalid LoRA types
+
+                            lora_entry = populated_entry
+
+                            # If we have a version ID from Civitai, track it for deduplication
+                            if "id" in lora_entry and lora_entry["id"]:
+                                added_loras[str(lora_entry["id"])] = len(result["loras"])
+                        except Exception as e:
+                            logger.error(
+                                f"Error fetching Civitai info for LoRA hash {lora_entry['hash']}: {e}"
+                            )

                # Track by hash if we have it
                if lora_hash:
@@ -795,3 +845,14 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
        base_model = cache_item.get("base_model", "")
        if base_model:
            entry["baseModel"] = base_model
+
+    @staticmethod
+    def _cache_item_model_type(cache_item: dict[str, Any]) -> str:
+        """Lowercased civitai.model.type of a cache item, or '' when unknown."""
+        civ = cache_item.get("civitai")
+        if not isinstance(civ, dict):
+            return ""
+        model_info = civ.get("model")
+        if not isinstance(model_info, dict):
+            return ""
+        return (model_info.get("type") or "").lower()
@@ -30,7 +30,7 @@ class MetaFormatParser(RecipeMetadataParser):
            prompt = parts[0].strip()
            
            # Initialize metadata
-            metadata = {"prompt": prompt, "loras": []}
+            metadata: Dict[str, Any] = {"prompt": prompt, "loras": []}
            
            # Extract negative prompt and parameters if available
            if len(parts) > 1:
@@ -91,7 +91,15 @@ class RecipeFormatParser(RecipeMetadataParser):
                        exists_locally = lora_scanner.has_hash(lora['hash'])
                        if exists_locally:
                            lora_cache = await lora_scanner.get_cached_data()
-                            lora_item = next((item for item in lora_cache.raw_data if item['sha256'].lower() == lora['hash'].lower()), None)
+                            # Cascade match: full sha256, stored autov3, or autov2 (sha256[:10]).
+                            h = (lora.get('hash') or '').lower()
+                            lora_item = next(
+                                (item for item in lora_cache.raw_data
+                                 if (item.get("sha256") or "").lower() == h
+                                 or (item.get("autov3") or "").lower() == h
+                                 or (item.get("sha256") or "")[:10].lower() == h),
+                                None
+                            )
                            if lora_item:
                                lora_entry['existsLocally'] = True
                                lora_entry['inLibrary'] = True
@@ -148,7 +156,7 @@ class RecipeFormatParser(RecipeMetadataParser):
            checkpoint_data = recipe_metadata.get('checkpoint') or {}
            if isinstance(checkpoint_data, dict) and checkpoint_data:
                version_id = checkpoint_data.get('modelVersionId') or checkpoint_data.get('id')
-                checkpoint_entry = {
+                checkpoint_entry: Dict[str, Any] = {
                    'id': version_id or 0,
                    'modelId': checkpoint_data.get('modelId', 0),
                    'name': checkpoint_data.get('name', 'Unknown Checkpoint'),
@@ -2,7 +2,7 @@ from __future__ import annotations

 import logging
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Callable, Dict, Mapping
+from typing import TYPE_CHECKING, Awaitable, Callable, Dict, Mapping

 import jinja2
 from aiohttp import web
@@ -30,6 +30,7 @@ from ..services.websocket_progress_callback import (
    WebSocketProgressCallback,
 )
 from ..utils.exif_utils import ExifUtils
+from ..utils.constants import MODEL_WEIGHT_FILE_TYPES
 from ..utils.metadata_manager import MetadataManager
 from .model_route_registrar import COMMON_ROUTE_DEFINITIONS, ModelRouteRegistrar
 from .handlers.model_handlers import (
@@ -84,7 +85,7 @@ class BaseModelRoutes(ABC):
        self.metadata_progress_callback = WebSocketBroadcastCallback()

        self._handler_set: ModelHandlerSet | None = None
-        self._handler_mapping: Dict[str, Callable[[web.Request], web.StreamResponse]] | None = None
+        self._handler_mapping: Dict[str, Callable[[web.Request], Awaitable[web.Response]]] | None = None

        self._preview_service = PreviewAssetService(
            metadata_manager=MetadataManager,
@@ -131,7 +132,7 @@ class BaseModelRoutes(ABC):
        self._handler_set = None
        self._handler_mapping = None

-    def _ensure_handler_mapping(self) -> Mapping[str, Callable[[web.Request], web.StreamResponse]]:
+    def _ensure_handler_mapping(self) -> Mapping[str, Callable[[web.Request], Awaitable[web.StreamResponse]]]:
        if self._handler_mapping is None:
            handler_set = self._create_handler_set()
            self._handler_set = handler_set
@@ -220,7 +221,7 @@ class BaseModelRoutes(ABC):
        )

    @property
-    def route_handlers(self) -> Mapping[str, Callable[[web.Request], web.StreamResponse]]:
+    def route_handlers(self) -> Mapping[str, Callable[[web.Request], Awaitable[web.StreamResponse]]]:
        return self._ensure_handler_mapping()

    def setup_routes(self, app: web.Application, prefix: str) -> None:
@@ -237,7 +238,7 @@ class BaseModelRoutes(ABC):
        """Setup model-specific routes."""
        raise NotImplementedError

-    def _parse_specific_params(self, request: web.Request) -> Dict:
+    def _parse_specific_params(self, request: web.Request) -> Dict[str, Any]:
        """Parse model-specific parameters - to be overridden by subclasses."""
        return {}

@@ -251,9 +252,9 @@ class BaseModelRoutes(ABC):

    def _find_model_file(self, files):
        """Find the appropriate model file from the files list - can be overridden by subclasses."""
-        return next((file for file in files if file.get("type") in ("Model", "Diffusion Model") and file.get("primary") is True), None)
+        return next((file for file in files if file.get("type") in MODEL_WEIGHT_FILE_TYPES and file.get("primary") is True), None)

-    def get_handler(self, name: str) -> Callable[[web.Request], web.StreamResponse]:
+    def get_handler(self, name: str) -> Callable[[web.Request], Awaitable[web.StreamResponse]]:
        """Expose handlers for subclasses or tests."""
        return self._ensure_handler_mapping()[name]

@@ -285,7 +286,7 @@ class BaseModelRoutes(ABC):
            )
        return self.model_lifecycle_service

-    def _make_handler_proxy(self, name: str) -> Callable[[web.Request], web.StreamResponse]:
+    def _make_handler_proxy(self, name: str) -> Callable[[web.Request], Awaitable[web.StreamResponse]]:
        async def proxy(request: web.Request) -> web.StreamResponse:
            try:
                handler = self.get_handler(name)
@@ -4,7 +4,7 @@ from __future__ import annotations

 import logging
 import os
-from typing import Callable, Mapping
+from typing import Awaitable, Callable, Mapping

 import jinja2
 from aiohttp import web
@@ -61,7 +61,9 @@ class BaseRecipeRoutes:
        self._i18n_registered = False
        self._startup_hooks_registered = False
        self._handler_set: RecipeHandlerSet | None = None
-        self._handler_mapping: dict[str, Callable] | None = None
+        self._handler_mapping: Mapping[
+            str, Callable[[web.Request], Awaitable[web.StreamResponse]]
+        ] | None = None

    async def attach_dependencies(self, app: web.Application | None = None) -> None:
        """Resolve shared services from the registry."""
@@ -84,7 +86,9 @@ class BaseRecipeRoutes:
        app.on_startup.append(self.attach_dependencies)
        self._startup_hooks_registered = True

-    def to_route_mapping(self) -> Mapping[str, Callable]:
+    def to_route_mapping(
+        self,
+    ) -> Mapping[str, Callable[[web.Request], Awaitable[web.StreamResponse]]]:
        """Return a mapping of handler name to coroutine for registrar binding."""

        if self._handler_mapping is None:
@@ -124,17 +128,17 @@ class BaseRecipeRoutes:
            or os.environ.get("HF_HUB_DISABLE_TELEMETRY", "0") == "0"
        )
        if not standalone_mode:
-            from ..metadata_collector import get_metadata  # type: ignore[import-not-found]
-            from ..metadata_collector.metadata_processor import (  # type: ignore[import-not-found]
+            from ..metadata_collector import get_metadata  # pyright: ignore[reportMissingImports]
+            from ..metadata_collector.metadata_processor import (  # pyright: ignore[reportMissingImports]
                MetadataProcessor,
            )
-            from ..metadata_collector.metadata_registry import (  # type: ignore[import-not-found]
+            from ..metadata_collector.metadata_registry import (  # pyright: ignore[reportMissingImports]
                MetadataRegistry,
            )
        else:  # pragma: no cover - optional dependency path
-            get_metadata = None  # type: ignore[assignment]
-            MetadataProcessor = None  # type: ignore[assignment]
-            MetadataRegistry = None  # type: ignore[assignment]
+            get_metadata = None  # pyright: ignore[reportAssignmentType]
+            MetadataProcessor = None  # pyright: ignore[reportAssignmentType]
+            MetadataRegistry = None  # pyright: ignore[reportAssignmentType]

        analysis_service = RecipeAnalysisService(
            exif_utils=ExifUtils,
@@ -1,5 +1,5 @@
 import logging
-from typing import Dict, List, Set
+from typing import Any, Dict, List, Set
 from aiohttp import web

 from .base_model_routes import BaseModelRoutes
@@ -28,13 +28,13 @@ class CheckpointRoutes(BaseModelRoutes):
        # Attach service dependencies
        self.attach_service(self.service)
    
-    def setup_routes(self, app: web.Application):
+    def setup_routes(self, app: web.Application, prefix: str = "checkpoints"):
        """Setup Checkpoint routes"""
        # Schedule service initialization on app startup
        app.on_startup.append(lambda _: self.initialize_services())
-        
+
        # Setup common routes with 'checkpoints' prefix (includes page route)
-        super().setup_routes(app, 'checkpoints')
+        super().setup_routes(app, prefix)
    
    def setup_specific_routes(self, registrar: ModelRouteRegistrar, prefix: str):
        """Setup Checkpoint-specific routes"""
@@ -53,9 +53,9 @@ class CheckpointRoutes(BaseModelRoutes):
        """Get expected model types string for error messages"""
        return "Checkpoint"

-    def _parse_specific_params(self, request: web.Request) -> Dict:
+    def _parse_specific_params(self, request: web.Request) -> Dict[str, Any]:
        """Parse Checkpoint-specific parameters"""
-        params: Dict = {}
+        params: Dict[str, Any] = {}

        if 'checkpoint_hash' in request.query:
            params['hash_filters'] = {'single_hash': request.query['checkpoint_hash'].lower()}
@@ -70,7 +70,7 @@ class CheckpointRoutes(BaseModelRoutes):
        """Get detailed information for a specific checkpoint by name"""
        try:
            name = request.match_info.get('name', '')
-            checkpoint_info = await self.service.get_model_info_by_name(name)
+            checkpoint_info = await self.service.get_model_info_by_name(name)  # pyright: ignore[reportAttributeAccessIssue]
            
            if checkpoint_info:
                return web.json_response(checkpoint_info)
@@ -89,7 +89,7 @@ class CheckpointRoutes(BaseModelRoutes):
            roots.extend(config.checkpoints_roots or [])
            roots.extend(config.extra_checkpoints_roots or [])
            # Remove duplicates while preserving order
-            seen: set = set()
+            seen: set[str] = set()
            unique_roots: List[str] = []
            for root in roots:
                if root and root not in seen:
@@ -114,7 +114,7 @@ class CheckpointRoutes(BaseModelRoutes):
            roots.extend(config.unet_roots or [])
            roots.extend(config.extra_unet_roots or [])
            # Remove duplicates while preserving order
-            seen: set = set()
+            seen: set[str] = set()
            unique_roots: List[str] = []
            for root in roots:
                if root and root not in seen:
@@ -26,13 +26,13 @@ class EmbeddingRoutes(BaseModelRoutes):
        # Attach service dependencies
        self.attach_service(self.service)
    
-    def setup_routes(self, app: web.Application):
+    def setup_routes(self, app: web.Application, prefix: str = "embeddings"):
        """Setup Embedding routes"""
        # Schedule service initialization on app startup
        app.on_startup.append(lambda _: self.initialize_services())
-        
+
        # Setup common routes with 'embeddings' prefix (includes page route)
-        super().setup_routes(app, 'embeddings')
+        super().setup_routes(app, prefix)
    
    def setup_specific_routes(self, registrar: ModelRouteRegistrar, prefix: str):
        """Setup Embedding-specific routes"""
@@ -51,7 +51,7 @@ class EmbeddingRoutes(BaseModelRoutes):
        """Get detailed information for a specific embedding by name"""
        try:
            name = request.match_info.get('name', '')
-            embedding_info = await self.service.get_model_info_by_name(name)
+            embedding_info = await self.service.get_model_info_by_name(name)  # pyright: ignore[reportAttributeAccessIssue]
            
            if embedding_info:
                return web.json_response(embedding_info)
@@ -1,7 +1,7 @@
 from __future__ import annotations

 import logging
-from typing import Callable, Mapping
+from typing import Any, Awaitable, Callable, Mapping

 from aiohttp import web

@@ -35,7 +35,7 @@ class ExampleImagesRoutes:
        *,
        ws_manager,
        download_manager: DownloadManager | None = None,
-        processor=ExampleImagesProcessor,
+        processor: Any = ExampleImagesProcessor,
        file_manager=ExampleImagesFileManager,
        cleanup_service: ExampleImagesCleanupService | None = None,
    ) -> None:
@@ -46,7 +46,9 @@ class ExampleImagesRoutes:
        self._file_manager = file_manager
        self._cleanup_service = cleanup_service or ExampleImagesCleanupService()
        self._handler_set: ExampleImagesHandlerSet | None = None
-        self._handler_mapping: Mapping[str, Callable[[web.Request], web.StreamResponse]] | None = None
+        self._handler_mapping: Mapping[
+            str, Callable[[web.Request], Awaitable[web.StreamResponse]]
+        ] | None = None

    @classmethod
    def setup_routes(cls, app: web.Application, *, ws_manager) -> None:
@@ -61,7 +63,9 @@ class ExampleImagesRoutes:
        registrar = ExampleImagesRouteRegistrar(app)
        registrar.register_routes(self.to_route_mapping())

-    def to_route_mapping(self) -> Mapping[str, Callable[[web.Request], web.StreamResponse]]:
+    def to_route_mapping(
+        self,
+    ) -> Mapping[str, Callable[[web.Request], Awaitable[web.StreamResponse]]]:
        """Return the registrar-compatible mapping of handler names to callables."""

        if self._handler_mapping is None:
@@ -0,0 +1,165 @@
+"""HTTP route handlers for agent skill endpoints.
+
+These handlers expose the :class:`AgentService` via HTTP, allowing the
+frontend to list available skills and execute them on selected models.
+Progress is reported via WebSocket broadcast.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+from typing import Any, Dict
+
+from aiohttp import web
+
+from ...services.agent import AgentService, AgentProgressReporter
+from ...services.llm_service import LLMNotConfiguredError
+
+logger = logging.getLogger(__name__)
+
+
+class AgentHandler:
+    """HTTP handler for agent skill operations."""
+
+    def __init__(self, agent_service: AgentService | None = None) -> None:
+        self._agent_service = agent_service
+
+    async def _ensure_service(self) -> AgentService:
+        if self._agent_service is None:
+            self._agent_service = await AgentService.get_instance()
+        return self._agent_service
+
+    # ------------------------------------------------------------------
+    # GET /api/lm/agent/skills
+    # ------------------------------------------------------------------
+
+    async def get_agent_skills(self, request: web.Request) -> web.Response:
+        """Return a list of available agent skills."""
+
+        service = await self._ensure_service()
+        skills = await service.list_skills()
+        return web.json_response({"skills": skills})
+
+    # ------------------------------------------------------------------
+    # POST /api/lm/agent/execute/{skill_name}
+    # ------------------------------------------------------------------
+
+    async def execute_agent_skill(self, request: web.Request) -> web.Response:
+        """Execute an agent skill on the provided model paths.
+
+        Request body::
+
+            {"model_paths": ["/path/to/model1.safetensors", ...], "options": {}}
+
+        Returns immediately with a task ID.  Execution runs in the
+        background; progress and completion are pushed via WebSocket
+        events of type ``agent_progress``.
+        """
+
+        skill_name = request.match_info.get("skill_name", "")
+        if not skill_name:
+            return web.json_response(
+                {"error": "Skill name is required"}, status=400
+            )
+
+        try:
+            body = await request.json()
+        except Exception:
+            return web.json_response(
+                {"error": "Invalid JSON body"}, status=400
+            )
+
+        model_paths = body.get("model_paths", [])
+        if not model_paths or not isinstance(model_paths, list):
+            return web.json_response(
+                {"error": "model_paths must be a non-empty array"},
+                status=400,
+            )
+
+        service = await self._ensure_service()
+
+        # Validate LLM configuration early for skills that need it
+        # (fail fast rather than after starting background work)
+        try:
+            from ...services.llm_service import LLMService
+
+            llm = await LLMService.get_instance()
+            if not llm.is_configured():
+                return web.json_response(
+                    {
+                        "error": "LLM provider is not configured. "
+                        "Enable it in Settings → AI Provider.",
+                    },
+                    status=400,
+                )
+        except Exception as exc:
+            logger.error("Failed to check LLM configuration: %s", exc)
+
+        # Launch execution in the background
+        progress_reporter = AgentProgressReporter()
+        logger.info(
+            "LLM enrichment '%s' starting for %d model(s)",
+            skill_name, len(model_paths),
+        )
+
+        async def _run() -> None:
+            try:
+                result = await service.execute_skill(
+                    skill_name=skill_name,
+                    input_data={"model_paths": model_paths},
+                    progress_callback=progress_reporter,
+                )
+                logger.info(
+                    "LLM enrichment '%s' finished: success=%s, summary='%s', errors=%s",
+                    skill_name, result.success, result.summary, result.errors,
+                )
+            except LLMNotConfiguredError as exc:
+                logger.warning("LLM enrichment '%s' not configured: %s", skill_name, exc)
+                await progress_reporter.on_progress(
+                    {
+                        "type": "agent_progress",
+                        "skill": skill_name,
+                        "status": "error",
+                        "error": str(exc),
+                    }
+                )
+            except Exception as exc:
+                logger.error("LLM enrichment '%s' failed: %s", skill_name, exc, exc_info=True)
+                await progress_reporter.on_progress(
+                    {
+                        "type": "agent_progress",
+                        "skill": skill_name,
+                        "status": "error",
+                        "error": str(exc),
+                    }
+                )
+
+        # Fire and forget — progress comes via WebSocket
+        asyncio.create_task(_run())
+
+        return web.json_response(
+            {
+                "status": "started",
+                "skill": skill_name,
+                "model_count": len(model_paths),
+            }
+        )
+
+    # ------------------------------------------------------------------
+    # POST /api/lm/agent/cancel
+    # ------------------------------------------------------------------
+
+    async def cancel_agent_skill(self, request: web.Request) -> web.Response:
+        """Cancel a running agent skill.
+
+        NOTE: Cancellation is a stub for now — the AgentService processes
+        models sequentially and does not yet support mid-execution
+        cancellation.  This endpoint exists for API completeness.
+        """
+
+        # TODO: implement cooperative cancellation in AgentService
+        return web.json_response(
+            {"status": "acknowledged", "note": "Cancellation not yet implemented"},
+            status=200,
+        )
@@ -3,7 +3,7 @@ from __future__ import annotations

 import logging
 from dataclasses import dataclass
-from typing import Callable, Mapping
+from typing import Awaitable, Callable, Mapping

 from aiohttp import web

@@ -170,7 +170,7 @@ class ExampleImagesHandlerSet:
    management: ExampleImagesManagementHandler
    files: ExampleImagesFileHandler

-    def to_route_mapping(self) -> Mapping[str, Callable[[web.Request], web.StreamResponse]]:
+    def to_route_mapping(self) -> Mapping[str, Callable[[web.Request], Awaitable[web.StreamResponse]]]:
        """Flatten handler methods into the registrar mapping."""

        return {
@@ -49,6 +49,14 @@ async def _get_hf_api_session() -> aiohttp.ClientSession:
    return _hf_api_session


+async def close_hf_api_session() -> None:
+    """Close the shared HF API session, if it was ever created."""
+    global _hf_api_session
+    if _hf_api_session is not None and not _hf_api_session.closed:
+        await _hf_api_session.close()
+        _hf_api_session = None
+
+
 def _infer_model_type(model_root: str) -> tuple[Any, str]:
    """Determine model class and scanner by matching ``model_root`` against the
    configured root paths for each model type (from ``Config``).
@@ -114,8 +122,12 @@ async def _save_hf_metadata(dest_path: str, repo: str, model_root: str) -> None:
        metadata._unknown_fields["hf_url"] = hf_url
        metadata.from_civitai = False  # HF models are not from CivitAI

+        metadata_dict = metadata.to_dict()
+        if "trainedWords" in metadata_dict and not metadata_dict["trainedWords"]:
+            del metadata_dict["trainedWords"]
+
        # 3. Save metadata atomically
-        await MetadataManager.save_metadata(dest_path, metadata)
+        await MetadataManager.save_metadata(dest_path, metadata_dict)
        logger.info("Saved HF metadata (with hf_url) for %s", dest_path)

        # 4. Determine relative folder path for cache
@@ -139,9 +151,117 @@ async def _save_hf_metadata(dest_path: str, repo: str, model_root: str) -> None:
        logger.warning("Failed to save HF metadata for %s: %s", dest_path, exc)


+def _find_matching_root(dest_dir: str) -> str | None:
+    """Walk up *dest_dir* to find which configured scanner root it belongs to."""
+    norm = os.path.normpath(dest_dir).replace(os.sep, "/")
+    all_roots = []
+    for root_list in (
+        config.loras_roots or [],
+        config.extra_loras_roots or [],
+        config.checkpoints_roots or [],
+        config.extra_checkpoints_roots or [],
+        config.unet_roots or [],
+        config.extra_unet_roots or [],
+        config.embeddings_roots or [],
+        config.extra_embeddings_roots or [],
+    ):
+        all_roots.extend([os.path.normpath(p).replace(os.sep, "/") for p in root_list])
+    # Find the longest matching prefix
+    match: str | None = None
+    for root in all_roots:
+        if norm.startswith(root):
+            if match is None or len(root) > len(match):
+                match = root
+    return match
+
+
+async def _add_to_scanner_cache(dest_path: str, metadata: dict[str, Any]) -> None:
+    model_dir = os.path.dirname(dest_path)
+    model_root = _find_matching_root(model_dir)
+    if not model_root:
+        raise ValueError(f"File path {dest_path} is not within any configured scanner root")
+    scanner_getter_name = _infer_model_type(model_root)[1]
+    scanner_getter = getattr(ServiceRegistry, scanner_getter_name, None)
+    if scanner_getter is None:
+        raise RuntimeError(f"Scanner getter '{scanner_getter_name}' not found in ServiceRegistry")
+    scanner = await scanner_getter()
+    if scanner is None:
+        raise RuntimeError(f"Scanner '{scanner_getter_name}' returned None")
+    await scanner.update_single_model_cache(dest_path, dest_path, metadata)
+
+
 class HfHandler:
    """Handle Hugging Face model browsing and download."""

+    async def set_hf_url(self, request: web.Request) -> web.Response:
+        try:
+            payload: dict[str, Any] = await request.json()
+        except json.JSONDecodeError:
+            return web.json_response({"success": False, "error": "Invalid JSON"}, status=400)
+
+        file_path = (payload.get("file_path") or "").strip()
+        hf_url = (payload.get("hf_url") or "").strip()
+
+        if not file_path or not hf_url:
+            return web.json_response(
+                {"success": False, "error": "Missing required fields: 'file_path' and 'hf_url'"},
+                status=400,
+            )
+
+        m = re.match(r"^https?://huggingface\.co/([^/]+/[^/]+)/?$", hf_url)
+        if not m:
+            return web.json_response(
+                {
+                    "success": False,
+                    "error": "Invalid HuggingFace URL. Expected format: https://huggingface.co/user/repo",
+                },
+                status=400,
+            )
+
+        if not os.path.isfile(file_path):
+            return web.json_response(
+                {"success": False, "error": f"File not found: {file_path}"},
+                status=404,
+            )
+
+        model_root = _find_matching_root(os.path.dirname(file_path))
+        if not model_root:
+            return web.json_response(
+                {
+                    "success": False,
+                    "error": "File is not within any configured model directory. Cannot link to HuggingFace.",
+                },
+                status=400,
+            )
+
+        try:
+            existing = await MetadataManager.load_metadata_payload(file_path)
+            if existing.get("hf_url") == hf_url:
+                return web.json_response({
+                    "success": True,
+                    "message": "hf_url already set",
+                    "hf_url": hf_url,
+                })
+
+            existing["hf_url"] = hf_url
+            existing["from_civitai"] = False
+            await MetadataManager.save_metadata(file_path, existing)
+
+            await _add_to_scanner_cache(file_path, existing)
+
+            logger.info("Set hf_url=%s for %s", hf_url, file_path)
+            return web.json_response({
+                "success": True,
+                "message": f"hf_url set to {hf_url}",
+                "hf_url": hf_url,
+            })
+        except Exception as exc:
+            logger.error("Failed to set hf_url for %s: %s", file_path, exc)
+            return web.json_response(
+                {"success": False, "error": str(exc)},
+                status=500,
+            )
+
    async def get_hf_repo_files(self, request: web.Request) -> web.Response:
        """List model-weight files from a HF repo with real file sizes.

@@ -243,8 +363,8 @@ class HfHandler:
        if ".." in (author, repo_name) or "." in (author, repo_name):
            return web.json_response({"error": f"Invalid repo format: {repo}"}, status=400)

-        # Validate filename — must not contain path separators or ..
-        if "/" in filename or "\\" in filename or ".." in filename:
+        # Validate filename — must not contain path traversal
+        if ".." in filename:
            return web.json_response({"error": "Invalid filename"}, status=400)

        # Validate relative_path — must not be absolute or escape base directory
@@ -254,35 +374,17 @@ class HfHandler:
            if ".." in relative_path.split("/") or "\\" in relative_path:
                return web.json_response({"error": "Invalid relative_path"}, status=400)

-        # Validate model_root — must not contain path traversal
-        if not os.path.isabs(model_root):
-            # For relative model_root, check it doesn't escape
-            resolved_model_root = os.path.realpath(
-                os.path.join(os.getcwd(), "models", model_root)
-            )
+        # Use model_root directly as the base directory — same approach as
+        # CivitAI's download path (download_manager.py).  No realpath, no
+        # allowed-roots validation, no path-traversal check; those are
+        # unnecessary when the frontend sends the path from its own dropdown
+        # (populated from scanner roots).  Using the "business path" directly
+        # keeps dest_path consistent with scanner roots so that later folder
+        # derivation (in _save_hf_metadata) works correctly.
+        if os.path.isabs(model_root):
+            base_dir = os.path.normpath(model_root)
        else:
-            resolved_model_root = os.path.realpath(model_root)
-
-        # Verify model_root is within a configured scanner root
-        allowed_roots = set()
-        for root_list in (
-            config.loras_roots or [],
-            config.extra_loras_roots or [],
-            config.checkpoints_roots or [],
-            config.extra_checkpoints_roots or [],
-            config.unet_roots or [],
-            config.extra_unet_roots or [],
-            config.embeddings_roots or [],
-            config.extra_embeddings_roots or [],
-        ):
-            for r in root_list:
-                allowed_roots.add(os.path.realpath(r))
-
-        if not any(resolved_model_root == root or resolved_model_root.startswith(root + os.sep) for root in allowed_roots):
-            logger.warning("Invalid model_root rejected: %s", model_root)
-            return web.json_response({"error": f"Invalid model_root: {model_root}"}, status=400)
-
-        base_dir = resolved_model_root
+            base_dir = os.path.normpath(os.path.join(os.getcwd(), "models", model_root))

        if use_default_paths:
            target_dir = os.path.join(base_dir, "huggingface", author, repo_name)
@@ -291,15 +393,12 @@ class HfHandler:
        else:
            target_dir = base_dir

-        os.makedirs(target_dir, exist_ok=True)
-        dest_path = os.path.join(target_dir, filename)
+        # Strip HF repo subdirectory — "diffusion_models/xxx.safetensors"
+        # is an HF repo convention, not meaningful for local storage.
+        file_base = os.path.basename(filename)

-        # Resolve symlinks and check for path traversal escape
-        real_dest = os.path.realpath(dest_path)
-        real_base = os.path.realpath(target_dir)
-        if not real_dest.startswith(real_base + os.sep):
-            logger.warning("Path traversal blocked: %s -> %s", dest_path, real_dest)
-            return web.json_response({"error": "Path traversal detected"}, status=400)
+        os.makedirs(target_dir, exist_ok=True)
+        dest_path = os.path.join(target_dir, file_base)

        # Check if already exists (simple skip)
        if os.path.exists(dest_path) and os.path.getsize(dest_path) > 0:
@@ -38,6 +38,12 @@ from ...services.settings_manager import get_settings_manager
 from ...services.websocket_manager import ws_manager
 from ...services.downloader import get_downloader
 from ...services.errors import ResourceNotFoundError
+from ...services.llm_service import (
+    PROVIDER_PRESETS,
+    fetch_ollama_models,
+    get_all_provider_models,
+    get_provider_model_ids,
+)
 from ...services.cache_health_monitor import CacheHealthMonitor, CacheHealthStatus
 from ...utils.models import BaseModelMetadata
 from ...utils.constants import (
@@ -49,6 +55,7 @@ from ...utils.constants import (
    VALID_LORA_TYPES,
 )
 from .hf_handlers import HfHandler
+from .agent_handlers import AgentHandler
 from ...utils.civitai_utils import rewrite_preview_url
 from ...utils.example_images_paths import (
    find_non_compliant_items_in_example_images_root,
@@ -269,7 +276,7 @@ def _collect_comfyui_session_logs(
 ) -> dict[str, Any]:
    if log_entries is None:
        try:
-            import app.logger as comfy_logger
+            import app.logger as comfy_logger  # pyright: ignore[reportMissingImports]

            log_entries = list(comfy_logger.get_logs() or [])
        except Exception as exc:  # pragma: no cover - environment dependent
@@ -415,10 +422,10 @@ class PromptServerProtocol(Protocol):
    """Subset of PromptServer used by the handlers."""

    instance: "PromptServerProtocol"
-    sockets: dict  # maps clientId (sid) → WebSocketResponse
+    sockets: dict[str, Any]  # maps clientId (sid) → WebSocketResponse

    def send_sync(
-        self, event: str, payload: dict | None = None, sid: str | None = None
+        self, event: str, payload: dict[str, Any] | None = None, sid: str | None = None
    ) -> None:  # pragma: no cover - protocol
        ...

@@ -436,7 +443,12 @@ class UsageStatsFactory(Protocol):
 class MetadataProviderProtocol(Protocol):
    async def get_model_versions(
        self, model_id: int
-    ) -> dict | None:  # pragma: no cover - protocol
+    ) -> dict[str, Any] | None:  # pragma: no cover - protocol
+        ...
+
+    async def get_user_models(
+        self, username: str, cursor: str | None = None
+    ) -> Any:  # pragma: no cover - protocol
        ...


@@ -459,16 +471,16 @@ class MetadataArchiveManagerProtocol(Protocol):
 class BackupServiceProtocol(Protocol):
    async def create_snapshot(
        self, *, snapshot_type: str = "manual", persist: bool = False
-    ) -> dict:  # pragma: no cover - protocol
+    ) -> dict[str, Any]:  # pragma: no cover - protocol
        ...

-    async def restore_snapshot(self, archive_path: str) -> dict:  # pragma: no cover - protocol
+    async def restore_snapshot(self, archive_path: str) -> dict[str, Any]:  # pragma: no cover - protocol
        ...

-    def get_status(self) -> dict:  # pragma: no cover - protocol
+    def get_status(self) -> dict[str, Any]:  # pragma: no cover - protocol
        ...

-    def get_available_snapshots(self) -> list[dict]:  # pragma: no cover - protocol
+    def get_available_snapshots(self) -> list[dict[str, Any]]:  # pragma: no cover - protocol
        ...


@@ -484,7 +496,7 @@ class NodeRegistry:
    def __init__(self) -> None:
        self._lock = asyncio.Lock()
        # sid → {unique_id → node_info}
-        self._tab_nodes: Dict[str, Dict[str, dict]] = {}
+        self._tab_nodes: Dict[str, Dict[str, dict[str, Any]]] = {}
        self._ready = asyncio.Event()
        self._waiting_clients: set[str] = set()

@@ -497,7 +509,7 @@ class NodeRegistry:
    # Helpers to build one node dict (extracted so it's reused for each tab)
    # ------------------------------------------------------------------
    @staticmethod
-    def _build_node_dict(node: dict) -> dict:
+    def _build_node_dict(node: dict[str, Any]) -> dict[str, Any]:
        node_id = node["node_id"]
        graph_id = str(node["graph_id"])
        unique_id = f"{graph_id}:{node_id}"
@@ -506,11 +518,11 @@ class NodeRegistry:
        bgcolor = node.get("bgcolor") or DEFAULT_NODE_COLOR

        raw_capabilities = node.get("capabilities")
-        capabilities: dict = {}
+        capabilities: dict[str, Any] = {}
        if isinstance(raw_capabilities, dict):
            capabilities = dict(raw_capabilities)

-        raw_widget_names: list | None = node.get("widget_names")
+        raw_widget_names: list[Any] | None = node.get("widget_names")
        if not isinstance(raw_widget_names, list):
            capability_widget_names = capabilities.get("widget_names")
            raw_widget_names = (
@@ -558,20 +570,26 @@ class NodeRegistry:
    # ------------------------------------------------------------------
    # Public API
    # ------------------------------------------------------------------
-    async def register_nodes(self, sid: str, nodes: list[dict]) -> None:
+    async def register_nodes(self, sid: str, nodes: list[dict[str, Any]]) -> None:
        """Register/replace the node list for a single ComfyUI tab (identified by *sid*)."""
-        tab_nodes: dict[str, dict] = {}
+        tab_nodes: dict[str, dict[str, Any]] = {}
        for node in nodes:
            nd = self._build_node_dict(node)
            tab_nodes[nd["unique_id"]] = nd

        async with self._lock:
+            prev_count = len(self._tab_nodes.get(sid, {}))
            self._tab_nodes[sid] = tab_nodes
            self._waiting_clients.discard(sid)
            if not self._waiting_clients:
                self._ready.set()
+            total_tabs = len(self._tab_nodes)

-        logger.debug("Registered %s nodes from client %s", len(nodes), sid)
+        if len(nodes) != prev_count or len(nodes) > 0:
+            logger.debug(
+                "[LM:Registry] stored %s nodes (was %s) for client %s (total tabs: %s)",
+                len(nodes), prev_count, sid, total_tabs,
+            )

    def prepare_for_refresh(self, active_sids: list[str]) -> None:
        """Set the list of client IDs we expect to hear from during the next refresh cycle."""
@@ -589,18 +607,25 @@ class NodeRegistry:
        except asyncio.TimeoutError:
            return False

-    async def get_merged_registry(self, active_sids: set[str] | None = None) -> dict:
+    async def get_merged_registry(self, active_sids: set[str] | None = None) -> dict[str, Any]:
        """Return the union of all known tab nodes, pruning any tab that is no
        longer connected."""
        async with self._lock:
            # Garbage-collect stale entries (disconnected tabs)
+            stale_sids = []
            if active_sids is not None:
                for sid in list(self._tab_nodes):
                    if sid not in active_sids:
+                        stale_sids.append(sid)
                        del self._tab_nodes[sid]
+            if stale_sids:
+                logger.debug(
+                    "[LM:Registry] GC pruned %s disconnected tabs: %s",
+                    len(stale_sids), stale_sids,
+                )

-            merged: dict[str, dict] = {}
-            tab_info: dict[str, dict] = {}
+            merged: dict[str, dict[str, Any]] = {}
+            tab_info: dict[str, dict[str, Any]] = {}
            for sid, nodes in self._tab_nodes.items():
                tab_info[sid] = {
                    "node_count": len(nodes),
@@ -633,7 +658,7 @@ class SupportersHandler:
    def __init__(self, logger: logging.Logger | None = None) -> None:
        self._logger = logger or logging.getLogger(__name__)

-    def _load_supporters(self) -> dict:
+    def _load_supporters(self) -> dict[str, Any]:
        """Load supporters data from JSON file."""
        try:
            current_file = os.path.abspath(__file__)
@@ -1209,10 +1234,8 @@ class DoctorHandler:
        settings_snapshot = _sanitize_sensitive_data(
            getattr(self._settings, "settings", {}) or {}
        )
-        startup_messages_getter = getattr(self._settings, "get_startup_messages", None)
-        startup_messages = (
-            list(startup_messages_getter()) if callable(startup_messages_getter) else []
-        )
+        startup_messages_getter: Any = getattr(self._settings, "get_startup_messages", None)
+        startup_messages = list(startup_messages_getter()) if startup_messages_getter else []

        environment = {
            "app_version": app_version,
@@ -1399,8 +1422,9 @@ class SettingsHandler:
            "libraries",
            "active_library",
            # Sensitive — never expose the actual value to the frontend;
-            # frontend receives a boolean instead (civitai_api_key_set).
+            # frontend receives a boolean instead (*_set).
            "civitai_api_key",
+            "llm_api_key",
        }
    )

@@ -1418,7 +1442,7 @@ class SettingsHandler:
        *,
        settings_service=None,
        metadata_provider_updater: Callable[
-            [], Awaitable[None]
+            [], Awaitable[Any]
        ] = update_metadata_providers,
        downloader_factory: Callable[
            [], Awaitable[DownloaderProtocol]
@@ -1458,11 +1482,13 @@ class SettingsHandler:
            # Sensitive fields: only expose a boolean indicating whether set
            raw_key = self._settings.get("civitai_api_key")
            response_data["civitai_api_key_set"] = bool(raw_key)
+            raw_llm_key = self._settings.get("llm_api_key")
+            response_data["llm_api_key_set"] = bool(raw_llm_key)
            settings_file = getattr(self._settings, "settings_file", None)
            if settings_file:
                response_data["settings_file"] = settings_file
-            messages_getter = getattr(self._settings, "get_startup_messages", None)
-            messages = list(messages_getter()) if callable(messages_getter) else []
+            messages_getter: Any = getattr(self._settings, "get_startup_messages", None)
+            messages = list(messages_getter()) if messages_getter else []
            return web.json_response(
                {
                    "success": True,
@@ -1539,6 +1565,11 @@ class SettingsHandler:
                            {"success": False, "error": validation_error}
                        )

+                if key == "update_channel" and value not in ("release", "nightly"):
+                    return web.json_response(
+                        {"success": False, "error": "update_channel must be 'release' or 'nightly'"}
+                    )
+
                if value == "__DELETE__" and key in (
                    "proxy_username",
                    "proxy_password",
@@ -1547,7 +1578,11 @@ class SettingsHandler:
                else:
                    self._settings.set(key, value)

-                if key == "enable_metadata_archive_db":
+                if key in (
+                    "enable_metadata_archive_db",
+                    "enable_civarchive_api",
+                    "metadata_provider_order",
+                ):
                    await self._metadata_provider_updater()

                if key in self._PROXY_KEYS:
@@ -1562,6 +1597,42 @@ class SettingsHandler:
            logger.error("Error updating settings: %s", exc, exc_info=True)
            return web.Response(status=500, text=str(exc))

+    async def get_llm_models(self, request: web.Request) -> web.Response:
+        """Return the model list for a provider.
+
+        For ``ollama`` the list is fetched live from the local Ollama API
+        (only models actually pulled locally are shown).  For all other
+        providers the opencode model catalog is used.
+
+        Query parameters:
+            provider (required): Internal provider id (``openai``, ``ollama``, etc.).
+
+        Returns:
+            ``{"success": true, "models": ["gpt-4o", ...]}``.
+        """
+        provider_id = request.query.get("provider", "").strip()
+        if not provider_id:
+            return web.json_response(
+                {"success": False, "error": "provider query parameter is required", "models": []},
+                status=400,
+            )
+
+        try:
+            if provider_id == "ollama":
+                api_base = request.query.get("api_base", "").strip() or self._settings.get("llm_api_base", "")
+                if not api_base:
+                    api_base = "http://localhost:11434/v1"
+                models = await fetch_ollama_models(api_base)
+            else:
+                models = await get_provider_model_ids(provider_id)
+            return web.json_response({"success": True, "models": models})
+        except Exception as exc:
+            logger.warning("get_llm_models failed for %s: %s", provider_id, exc)
+            return web.json_response(
+                {"success": False, "error": str(exc), "models": []},
+                status=500,
+            )
+
    def _validate_example_images_path(self, folder_path: str) -> str | None:
        if not os.path.exists(folder_path):
            return f"Path does not exist: {folder_path}"
@@ -1584,6 +1655,20 @@ class SettingsHandler:
    def _is_dedicated_example_images_folder(self, folder_path: str) -> bool:
        return is_valid_example_images_root(folder_path)

+    async def get_provider_models(self, request: web.Request) -> web.Response:
+        """Return the model catalog for all preset providers.
+
+        This endpoint is called asynchronously by the settings UI so that
+        page rendering never blocks on the remote model catalog fetch.
+        """
+        catalog_provider_ids = [p for p in PROVIDER_PRESETS if p != "custom"]
+        try:
+            provider_models = await get_all_provider_models(catalog_provider_ids)
+            return web.json_response({"success": True, "models": provider_models})
+        except Exception as exc:
+            logger.warning("Failed to fetch provider models: %s", exc)
+            return web.json_response({"success": False, "models": {}, "error": str(exc)})
+

 class UsageStatsHandler:
    def __init__(self, usage_stats_factory: UsageStatsFactory = UsageStats) -> None:
@@ -1711,6 +1796,124 @@ class LoraCodeHandler:
            logger.error("Failed to update lora code: %s", exc, exc_info=True)
            return web.json_response({"success": False, "error": str(exc)}, status=500)

+    async def get_update_lora_code(self, request: web.Request) -> web.Response:
+        """GET version of update_lora_code — reads parameters from query string.
+
+        Query params:
+          lora_code (required)  — the LoRA syntax to send
+          mode     (optional)   — "append" (default) or "replace"
+          node_id  (repeatable) — target node id(s), e.g. node_id=3&node_id=5
+          node_ids (optional)   — JSON-encoded array for complex references with graph_id:
+                                   [{"node_id":3,"graph_id":"g1"}, ...]
+        """
+        try:
+            node_ids_raw = request.query.get("node_ids")
+            node_id_list = request.query.getall("node_id", [])
+            lora_code = request.query.get("lora_code", "")
+            mode = request.query.get("mode", "append")
+
+            if not lora_code:
+                return web.json_response(
+                    {"success": False, "error": "Missing lora_code parameter"},
+                    status=400,
+                )
+
+            node_ids = None
+            if node_ids_raw:
+                try:
+                    node_ids = json.loads(node_ids_raw)
+                except (json.JSONDecodeError, TypeError):
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a valid JSON array"},
+                        status=400,
+                    )
+                if not isinstance(node_ids, list) or not node_ids:
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a non-empty JSON array"},
+                        status=400,
+                    )
+            elif node_id_list:
+                node_ids = node_id_list
+
+            results = []
+            if node_ids is None:
+                try:
+                    self._prompt_server.instance.send_sync(
+                        "lora_code_update",
+                        {"id": -1, "lora_code": lora_code, "mode": mode},
+                    )
+                    results.append({"node_id": "broadcast", "success": True})
+                except Exception as exc:  # pragma: no cover - defensive logging
+                    logger.error("Error broadcasting lora code: %s", exc)
+                    results.append(
+                        {"node_id": "broadcast", "success": False, "error": str(exc)}
+                    )
+            else:
+                for entry in node_ids:
+                    node_identifier = entry
+                    graph_identifier = None
+                    if isinstance(entry, dict):
+                        node_identifier = entry.get("node_id")
+                        graph_identifier = entry.get("graph_id")
+
+                    if node_identifier is None:
+                        results.append(
+                            {
+                                "node_id": node_identifier,
+                                "graph_id": graph_identifier,
+                                "success": False,
+                                "error": "Missing node_id parameter",
+                            }
+                        )
+                        continue
+
+                    try:
+                        parsed_node_id = int(node_identifier)
+                    except (TypeError, ValueError):
+                        parsed_node_id = node_identifier
+
+                    payload = {
+                        "id": parsed_node_id,
+                        "lora_code": lora_code,
+                        "mode": mode,
+                    }
+
+                    if graph_identifier is not None:
+                        payload["graph_id"] = str(graph_identifier)
+
+                    try:
+                        self._prompt_server.instance.send_sync(
+                            "lora_code_update",
+                            payload,
+                        )
+                        results.append(
+                            {
+                                "node_id": parsed_node_id,
+                                "graph_id": payload.get("graph_id"),
+                                "success": True,
+                            }
+                        )
+                    except Exception as exc:  # pragma: no cover - defensive logging
+                        logger.error(
+                            "Error sending lora code to node %s (graph %s): %s",
+                            parsed_node_id,
+                            graph_identifier,
+                            exc,
+                        )
+                        results.append(
+                            {
+                                "node_id": parsed_node_id,
+                                "graph_id": payload.get("graph_id"),
+                                "success": False,
+                                "error": str(exc),
+                            }
+                        )
+
+            return web.json_response({"success": True, "results": results})
+        except Exception as exc:  # pragma: no cover - defensive logging
+            logger.error("Failed to update lora code (GET): %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+

 class TrainedWordsHandler:
    async def get_trained_words(self, request: web.Request) -> web.Response:
@@ -1805,11 +2008,11 @@ async def _noop_backup_service() -> None:

@dataclass
 class ServiceRegistryAdapter:
-    get_lora_scanner: Callable[[], Awaitable]
-    get_checkpoint_scanner: Callable[[], Awaitable]
-    get_embedding_scanner: Callable[[], Awaitable]
-    get_downloaded_version_history_service: Callable[[], Awaitable]
-    get_backup_service: Callable[[], Awaitable] = _noop_backup_service
+    get_lora_scanner: Callable[[], Awaitable[Any]]
+    get_checkpoint_scanner: Callable[[], Awaitable[Any]]
+    get_embedding_scanner: Callable[[], Awaitable[Any]]
+    get_downloaded_version_history_service: Callable[[], Awaitable[Any]]
+    get_backup_service: Callable[[], Awaitable[Any]] = _noop_backup_service


 class ModelLibraryHandler:
@@ -1850,8 +2053,8 @@ class ModelLibraryHandler:
        return await self._service_registry.get_downloaded_version_history_service()

    @staticmethod
-    def _with_downloaded_flag(versions: list[dict]) -> list[dict]:
-        enriched: list[dict] = []
+    def _with_downloaded_flag(versions: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        enriched: list[dict[str, Any]] = []
        for version in versions:
            entry = dict(version)
            entry.setdefault("hasBeenDownloaded", True)
@@ -2044,7 +2247,7 @@ class ModelLibraryHandler:
            checkpoint_scanner = await self._service_registry.get_checkpoint_scanner()
            embedding_scanner = await self._service_registry.get_embedding_scanner()

-            results: list[dict] = []
+            results: list[dict[str, Any]] = []
            for model_id in model_ids:
                lora_versions = await lora_scanner.get_model_versions_by_id(model_id)
                if lora_versions:
@@ -2153,7 +2356,7 @@ class ModelLibraryHandler:
                )

            try:
-                model_version_id = int(data.get("modelVersionId"))
+                model_version_id = int(data.get("modelVersionId"))  # pyright: ignore[reportArgumentType]
            except (TypeError, ValueError):
                return web.json_response(
                    {"success": False, "error": "Parameter modelVersionId must be an integer"},
@@ -2265,10 +2468,11 @@ class ModelLibraryHandler:
                "checkpoint": checkpoint_scanner,
                "embedding": embedding_scanner,
            }
-            scanner = scanner_map.get(found_type)
+            scanner = scanner_map.get(found_type or "")
            if scanner:
-                persist = getattr(scanner, "_persist_current_cache", None)
-                if callable(persist):
+                scanner.bump_cache_version()
+                persist: Any = getattr(scanner, "_persist_current_cache", None)
+                if persist:
                    await persist()

            history_service = await self._get_download_history_service()
@@ -2390,6 +2594,8 @@ class ModelLibraryHandler:
                    status=400,
                )

+            cursor = request.query.get("cursor")
+
            metadata_provider = await self._metadata_provider_factory()
            if not metadata_provider:
                return web.json_response(
@@ -2398,7 +2604,7 @@ class ModelLibraryHandler:
                )

            try:
-                models = await metadata_provider.get_user_models(username)
+                result = await metadata_provider.get_user_models(username, cursor)
            except NotImplementedError:
                return web.json_response(
                    {
@@ -2408,14 +2614,35 @@ class ModelLibraryHandler:
                    status=501,
                )

-            if models is None:
+            if result is None:
                return web.json_response(
                    {"success": False, "error": "Failed to fetch user models"},
                    status=502,
                )

+            if isinstance(result, dict):
+                models = result.get("items")
+                next_cursor = result.get("nextCursor")
+            else:
+                # Defensive: tolerate providers that still return a raw list
+                models = result
+                next_cursor = None
+
            if not isinstance(models, list):
                models = []
+            if next_cursor is not None and not isinstance(next_cursor, str):
+                next_cursor = str(next_cursor)
+
+            estimated_total = None
+            if cursor is None:
+                get_count = getattr(metadata_provider, "get_creator_model_count", None)
+                if get_count is not None:
+                    try:
+                        estimated_total = await get_count(username)
+                    except Exception:  # best-effort only
+                        estimated_total = None
+                if not isinstance(estimated_total, int):
+                    estimated_total = None

            lora_scanner = await self._service_registry.get_lora_scanner()
            checkpoint_scanner = await self._service_registry.get_checkpoint_scanner()
@@ -2426,15 +2653,16 @@ class ModelLibraryHandler:
            }
            lora_type_aliases = {model_type.lower() for model_type in VALID_LORA_TYPES}

-            type_scanner_map: Dict[str, object | None] = {
+            type_scanner_map: Dict[str, Any] = {
                **{alias: lora_scanner for alias in lora_type_aliases},
                "checkpoint": checkpoint_scanner,
                "textualinversion": embedding_scanner,
            }

-            versions: list[dict] = []
+            versions: list[dict[str, Any]] = []
            history_service = await self._get_download_history_service()
            model_ids: list[int] = []
+            model_count = 0
            for model in models:
                try:
                    model_ids.append(int(model.get("id")))
@@ -2468,6 +2696,8 @@ class ModelLibraryHandler:
                if model_type not in normalized_allowed_types:
                    continue

+                model_count += 1
+
                scanner = type_scanner_map.get(model_type)
                if scanner is None:
                    return web.json_response(
@@ -2481,6 +2711,8 @@ class ModelLibraryHandler:
                tags_value = model.get("tags")
                tags = tags_value if isinstance(tags_value, list) else []
                model_id = model.get("id")
+                if model_id is None:
+                    continue
                try:
                    model_id_int = int(model_id)
                except (TypeError, ValueError):
@@ -2496,6 +2728,8 @@ class ModelLibraryHandler:
                        continue

                    version_id = version.get("id")
+                    if version_id is None:
+                        continue
                    try:
                        version_id_int = int(version_id)
                    except (TypeError, ValueError):
@@ -2533,7 +2767,15 @@ class ModelLibraryHandler:
                    )

            return web.json_response(
-                {"success": True, "username": username, "versions": versions}
+                {
+                    "success": True,
+                    "username": username,
+                    "versions": versions,
+                    "modelCount": model_count,
+                    "nextCursor": next_cursor,
+                    "hasMore": next_cursor is not None,
+                    "estimatedTotal": estimated_total,
+                }
            )
        except Exception as exc:  # pragma: no cover - defensive logging
            logger.error("Failed to get Civitai user models: %s", exc, exc_info=True)
@@ -2549,7 +2791,7 @@ class MetadataArchiveHandler:
        ] = get_metadata_archive_manager,
        settings_service=None,
        metadata_provider_updater: Callable[
-            [], Awaitable[None]
+            [], Awaitable[Any]
        ] = update_metadata_providers,
    ) -> None:
        self._metadata_archive_manager_factory = metadata_archive_manager_factory
@@ -2696,7 +2938,7 @@ class BackupHandler:

            if request.content_type.startswith("multipart/"):
                reader = await request.multipart()
-                field = await reader.next()
+                field: Any = await reader.next()
                uploaded = False
                while field is not None:
                    if getattr(field, "filename", None):
@@ -3056,6 +3298,8 @@ class NodeRegistryHandler:
        self._node_registry = node_registry
        self._prompt_server = prompt_server
        self._standalone_mode = standalone_mode
+        self._refresh_lock = asyncio.Lock()
+        self._last_slow_path_ts: float = 0.0

    async def register_nodes(self, request: web.Request) -> web.Response:
        try:
@@ -3102,7 +3346,12 @@ class NodeRegistryHandler:
                    )
                graph_name = node.get("graph_name")
                try:
-                    node["node_id"] = int(node_id)
+                    # Handle compound node IDs from expanded group subgraphs,
+                    # e.g. "252:0" → 0 (parent scope is already in graph_id)
+                    if isinstance(node_id, str) and ":" in node_id:
+                        node["node_id"] = int(node_id.rsplit(":", 1)[-1])
+                    else:
+                        node["node_id"] = int(node_id)
                except (TypeError, ValueError):
                    return web.json_response(
                        {
@@ -3143,42 +3392,101 @@ class NodeRegistryHandler:
                    status=503,
                )

-            # Snapshot of currently-connected ComfyUI tabs
-            active_sids = list(self._prompt_server.instance.sockets.keys())
-            self._node_registry.prepare_for_refresh(active_sids)
-
-            try:
-                self._prompt_server.instance.send_sync("lora_registry_refresh", {})
-                logger.debug(
-                    "Sent registry refresh request (expecting %s clients)", len(active_sids)
-                )
-            except Exception as exc:
-                logger.error("Failed to send registry refresh message: %s", exc)
-                return web.json_response(
-                    {
-                        "success": False,
-                        "error": "Communication Error",
-                        "message": f"Failed to communicate with ComfyUI frontend: {exc}",
-                    },
-                    status=500,
-                )
-
-            if not await self._node_registry.wait_for_all(timeout=2.0):
-                logger.warning(
-                    "Registry refresh timeout after 2s (%s/%s clients responded)",
-                    len(active_sids) - self._node_registry.pending_client_count,
-                    len(active_sids),
-                )
-
-            # Re-read current sockets after the wait: a tab may have connected
-            # while we were waiting, and we don't want to garbage-collect it.
            current_sids = set(self._prompt_server.instance.sockets.keys())
+
+            # Fast path: if the frontend has already pushed node data (via
+            # afterConfigureGraph / graphChanged hooks), return it immediately
+            # without triggering a WebSocket round-trip.
            registry_info = await self._node_registry.get_merged_registry(
                active_sids=current_sids
            )
+            if registry_info["tab_count"] > 0:
+                logger.debug(
+                    "[LM:Registry] fast path: %s nodes across %s tabs %s",
+                    registry_info["node_count"],
+                    registry_info["tab_count"],
+                    dict(registry_info.get("tabs", {})),
+                )
+                return web.json_response({"success": True, "data": registry_info})
+
+            # Slow path: registry is empty — trigger refresh via WebSocket.
+            # Serialize with an async lock so concurrent callers don't all
+            # trigger separate WS refresh cycles.  The second caller will
+            # re-check the fast path and (usually) find populated data.
+            async with self._refresh_lock:
+                # Re-check after acquiring the lock — another concurrent call
+                # may have populated the cache while we were waiting.
+                registry_info = await self._node_registry.get_merged_registry(
+                    active_sids=current_sids
+                )
+                if registry_info["tab_count"] > 0:
+                    logger.debug(
+                        "[LM:Registry] fast path after lock wait: %s nodes across %s tabs",
+                        registry_info["node_count"],
+                        registry_info["tab_count"],
+                    )
+                    return web.json_response({"success": True, "data": registry_info})
+
+                # Cooldown: if the slow path ran recently (< 2 s) and
+                # returned empty, skip another WS round-trip.
+                elapsed = time.monotonic() - self._last_slow_path_ts
+                if elapsed < 2.0:
+                    logger.debug(
+                        "[LM:Registry] slow path cooldown (%.1fs since last refresh), returning empty",
+                        elapsed,
+                    )
+                    return web.json_response(
+                        {
+                            "success": False,
+                            "error": "Empty Registry",
+                            "message": "No workflow nodes found — ensure ComfyUI is open and the extension is loaded.",
+                        },
+                        status=408,
+                    )
+
+                logger.debug(
+                    "[LM:Registry] slow path: cache empty, triggering WS refresh (%s connected tabs: %s)",
+                    len(current_sids), list(current_sids)[:5],
+                )
+                active_sids = list(current_sids)
+                self._node_registry.prepare_for_refresh(active_sids)
+
+                try:
+                    self._prompt_server.instance.send_sync("lora_registry_refresh", {})
+                    logger.debug(
+                        "Sent registry refresh request (expecting %s clients)", len(active_sids)
+                    )
+                except Exception as exc:
+                    logger.error("Failed to send registry refresh message: %s", exc)
+                    return web.json_response(
+                        {
+                            "success": False,
+                            "error": "Communication Error",
+                            "message": f"Failed to communicate with ComfyUI frontend: {exc}",
+                        },
+                        status=500,
+                    )
+
+                if not await self._node_registry.wait_for_all(timeout=0.5):
+                    logger.warning(
+                        "Registry refresh timeout after 0.5s (%s/%s clients responded)",
+                        len(active_sids) - self._node_registry.pending_client_count,
+                        len(active_sids),
+                    )
+
+                # Re-read current sockets after the wait: a tab may have connected
+                # while we were waiting, and we don't want to garbage-collect it.
+                current_sids = set(self._prompt_server.instance.sockets.keys())
+                registry_info = await self._node_registry.get_merged_registry(
+                    active_sids=current_sids
+                )
+                self._last_slow_path_ts = time.monotonic()

            if registry_info["node_count"] == 0:
-                logger.warning("No nodes registered after refresh")
+                logger.debug(
+                    "[LM:Registry] refresh OK — %s connected tab(s) but 0 compatible nodes found",
+                    registry_info["tab_count"],
+                )
                return web.json_response(
                    {
                        "success": False,
@@ -3214,7 +3522,7 @@ class NodeRegistryHandler:
                    status=400,
                )

-            if not isinstance(value, str) or not value:
+            if value is None or (isinstance(value, str) and not value):
                return web.json_response(
                    {"success": False, "error": "Missing value parameter"}, status=400
                )
@@ -3249,7 +3557,7 @@ class NodeRegistryHandler:
                except (TypeError, ValueError):
                    parsed_node_id = node_identifier

-                payload: dict = {
+                payload: dict[str, Any] = {
                    "id": parsed_node_id,
                    "value": value,
                    "mode": mode,
@@ -3292,6 +3600,130 @@ class NodeRegistryHandler:
            logger.error("Failed to update node widget: %s", exc, exc_info=True)
            return web.json_response({"success": False, "error": str(exc)}, status=500)

+    async def get_update_node_widget(self, request: web.Request) -> web.Response:
+        """GET version of update_node_widget — reads parameters from query string.
+
+        Query params:
+          widget_name  (optional)   — the widget name to update (required unless action is set)
+          action       (optional)   — alternative action, e.g. "inject_text" (required unless widget_name is set)
+          value        (required)   — the value to set
+          mode         (optional)   — "replace" (default) or "append"
+          node_id      (repeatable) — target node id(s), e.g. node_id=3&node_id=5
+          node_ids     (optional)   — JSON-encoded array for complex references:
+                                       [{"node_id":3,"graph_id":"g1"}, ...]
+        """
+        try:
+            widget_name = request.query.get("widget_name")
+            action = request.query.get("action")
+            value = request.query.get("value")
+            mode = request.query.get("mode", "replace")
+            node_ids_raw = request.query.get("node_ids")
+            node_id_list = request.query.getall("node_id", [])
+
+            if not action and (not isinstance(widget_name, str) or not widget_name):
+                return web.json_response(
+                    {
+                        "success": False,
+                        "error": "Missing parameter: provide either 'action' or 'widget_name'",
+                    },
+                    status=400,
+                )
+
+            if value is None or (isinstance(value, str) and not value):
+                return web.json_response(
+                    {"success": False, "error": "Missing value parameter"}, status=400
+                )
+
+            node_ids = None
+            if node_ids_raw:
+                try:
+                    node_ids = json.loads(node_ids_raw)
+                except (json.JSONDecodeError, TypeError):
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a valid JSON array"},
+                        status=400,
+                    )
+                if not isinstance(node_ids, list) or not node_ids:
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a non-empty JSON array"},
+                        status=400,
+                    )
+            elif node_id_list:
+                node_ids = node_id_list
+
+            if not isinstance(node_ids, list) or not node_ids:
+                return web.json_response(
+                    {"success": False, "error": "node_ids must be a non-empty list"},
+                    status=400,
+                )
+
+            results = []
+            for entry in node_ids:
+                node_identifier = entry
+                graph_identifier = None
+                if isinstance(entry, dict):
+                    node_identifier = entry.get("node_id")
+                    graph_identifier = entry.get("graph_id")
+
+                if node_identifier is None:
+                    results.append(
+                        {
+                            "node_id": node_identifier,
+                            "graph_id": graph_identifier,
+                            "success": False,
+                            "error": "Missing node_id parameter",
+                        }
+                    )
+                    continue
+
+                try:
+                    parsed_node_id = int(node_identifier)
+                except (TypeError, ValueError):
+                    parsed_node_id = node_identifier
+
+                payload: dict[str, Any] = {
+                    "id": parsed_node_id,
+                    "value": value,
+                    "mode": mode,
+                }
+                if action:
+                    payload["action"] = action
+                if widget_name:
+                    payload["widget_name"] = widget_name
+
+                if graph_identifier is not None:
+                    payload["graph_id"] = str(graph_identifier)
+
+                try:
+                    self._prompt_server.instance.send_sync("lm_widget_update", payload)
+                    results.append(
+                        {
+                            "node_id": parsed_node_id,
+                            "graph_id": payload.get("graph_id"),
+                            "success": True,
+                        }
+                    )
+                except Exception as exc:  # pragma: no cover - defensive logging
+                    logger.error(
+                        "Error sending widget update to node %s (graph %s): %s",
+                        parsed_node_id,
+                        graph_identifier,
+                        exc,
+                    )
+                    results.append(
+                        {
+                            "node_id": parsed_node_id,
+                            "graph_id": payload.get("graph_id"),
+                            "success": False,
+                            "error": str(exc),
+                        }
+                    )
+
+            return web.json_response({"success": True, "results": results})
+        except Exception as exc:  # pragma: no cover - defensive logging
+            logger.error("Failed to update node widget (GET): %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+

 class MiscHandlerSet:
    """Aggregate handlers into a lookup compatible with the registrar."""
@@ -3316,7 +3748,8 @@ class MiscHandlerSet:
        doctor: DoctorHandler,
        example_workflows: ExampleWorkflowsHandler,
        base_model: BaseModelHandlerSet,
-        hf_handler: HfHandler | None = None,
+        hf_handler: Any = None,
+        agent_handler: Any = None,
    ) -> None:
        self.health = health
        self.settings = settings
@@ -3336,6 +3769,7 @@ class MiscHandlerSet:
        self.example_workflows = example_workflows
        self.base_model = base_model
        self.hf_handler = hf_handler
+        self.agent_handler = agent_handler

    def to_route_mapping(
        self,
@@ -3351,13 +3785,17 @@ class MiscHandlerSet:
            "get_priority_tags": self.settings.get_priority_tags,
            "get_settings_libraries": self.settings.get_libraries,
            "activate_library": self.settings.activate_library,
+            "get_llm_models": self.settings.get_llm_models,
+            "get_provider_models": self.settings.get_provider_models,
            "update_usage_stats": self.usage_stats.update_usage_stats,
            "get_usage_stats": self.usage_stats.get_usage_stats,
            "update_lora_code": self.lora_code.update_lora_code,
+            "get_update_lora_code": self.lora_code.get_update_lora_code,
            "get_trained_words": self.trained_words.get_trained_words,
            "get_model_example_files": self.model_examples.get_model_example_files,
            "register_nodes": self.node_registry.register_nodes,
            "update_node_widget": self.node_registry.update_node_widget,
+            "get_update_node_widget": self.node_registry.get_update_node_widget,
            "get_registry": self.node_registry.get_registry,
            "check_model_exists": self.model_library.check_model_exists,
            "check_models_exist": self.model_library.check_models_exist,
@@ -3384,6 +3822,11 @@ class MiscHandlerSet:
            # Hugging Face handlers
            "get_hf_repo_files": self.hf_handler.get_hf_repo_files,
            "download_hf_model": self.hf_handler.download_hf_model,
+            "set_hf_url": self.hf_handler.set_hf_url,
+            # Agent skill handlers
+            "get_agent_skills": self.agent_handler.get_agent_skills,
+            "execute_agent_skill": self.agent_handler.execute_agent_skill,
+            "cancel_agent_skill": self.agent_handler.cancel_agent_skill,
            # Base model handlers
            "get_base_models": self.base_model.get_base_models,
            "refresh_base_models": self.base_model.refresh_base_models,
@@ -51,6 +51,29 @@ LICENSE_FIELDS = (
 )


+_broadcast_models_changed_tasks: set = set()
+
+
+def _broadcast_models_changed() -> None:
+    """Notify connected clients that the local model library changed.
+
+    The ComfyUI graph page listens for this event to invalidate its cached
+    model availability data (loras widget missing-model cues / error flags)
+    without waiting for the cache TTL to expire.
+    """
+    try:
+        from ...services.websocket_manager import ws_manager
+
+        task = asyncio.create_task(ws_manager.broadcast({"type": "models_changed"}))
+        # Keep a reference so the task is not garbage-collected mid-await.
+        _broadcast_models_changed_tasks.add(task)
+        task.add_done_callback(_broadcast_models_changed_tasks.discard)
+    except Exception:
+        logging.getLogger(__name__).debug(
+            "Failed to broadcast models_changed", exc_info=True
+        )
+
+
 class ModelPageView:
    """Render the HTML view for model listings."""

@@ -71,7 +94,7 @@ class ModelPageView:
        self._server_i18n = server_i18n
        self._logger = logger

-    def _load_supporters(self) -> dict:
+    def _load_supporters(self) -> dict[str, Any]:
        """Load supporters data from JSON file."""
        try:
            current_file = os.path.abspath(__file__)
@@ -152,7 +175,15 @@ class ModelPageView:
                self._template_env.filters["t"] = (
                    self._server_i18n.create_template_filter()
                )
-                self._template_env._i18n_filter_added = True  # type: ignore[attr-defined]
+                self._template_env._i18n_filter_added = True  # pyright: ignore[reportAttributeAccessIssue]
+
+            from ...services.llm_service import PROVIDER_PRESETS
+
+            # Provider presets are embedded directly (local, no await needed).
+            # Provider model catalogs are fetched asynchronously by the
+            # frontend via GET /api/lm/llm/provider-models so page rendering
+            # never blocks on the remote model catalog (which can take up to
+            # 30s on cold cache).

            template_context = {
                "is_initializing": is_initializing,
@@ -161,6 +192,8 @@ class ModelPageView:
                "folders": [],
                "t": self._server_i18n.get_translation,
                "version": self._get_app_version(),
+                "provider_presets_json": json.dumps(PROVIDER_PRESETS),
+                "provider_models_json": "{}",
            }

            if not is_initializing:
@@ -189,7 +222,7 @@ class ModelListingHandler:
        self,
        *,
        service,
-        parse_specific_params: Callable[[web.Request], Dict],
+        parse_specific_params: Callable[[web.Request], Dict[str, Any]],
        logger: logging.Logger,
    ) -> None:
        self._service = service
@@ -277,7 +310,7 @@ class ModelListingHandler:
            )
            return web.json_response({"error": str(exc)}, status=500)

-    def _parse_common_params(self, request: web.Request) -> Dict:
+    def _parse_common_params(self, request: web.Request) -> Dict[str, Any]:
        page = int(request.query.get("page", "1"))
        page_size = min(int(request.query.get("page_size", "20")), 100)
        sort_by = request.query.get("sort_by", "name")
@@ -384,12 +417,14 @@ class ModelListingHandler:
        )

        # View-local-versions filter: show all local versions of a specific model
+        # Accepts either a CivitAI modelId (int) or a HF group key like "hf:user/repo"
        civitai_model_id = request.query.get("civitai_model_id")
        if civitai_model_id is not None:
            try:
                civitai_model_id = int(civitai_model_id)
            except (TypeError, ValueError):
-                civitai_model_id = None
+                # Keep as string — could be an HF group key (e.g. "hf:user/repo")
+                pass

        return {
            "page": page,
@@ -448,6 +483,7 @@ class ModelManagementHandler:
                return web.Response(text="Model path is required", status=400)

            result = await self._lifecycle_service.delete_model(file_path)
+            _broadcast_models_changed()
            return web.json_response(result)
        except ValueError as exc:
            return web.json_response({"success": False, "error": str(exc)}, status=400)
@@ -527,6 +563,7 @@ class ModelManagementHandler:
                    # Update model_data with new hash
                    model_data["sha256"] = sha256
                    model_data["hash_status"] = "completed"
+                    hash_status = "completed"
                else:
                    return web.json_response(
                        {"success": False, "error": "No SHA256 hash found"}, status=400
@@ -534,6 +571,32 @@ class ModelManagementHandler:

            await MetadataManager.hydrate_model_data(model_data)

+            # hydrate_model_data replaces model_data with .metadata.json content,
+            # which may lack sha256. Restore from cache and persist the fix.
+            if not model_data.get("sha256"):
+                if sha256:
+                    model_data["sha256"] = sha256
+                    model_data["hash_status"] = model_data.get("hash_status", hash_status)
+                    data_to_save = model_data.copy()
+                    data_to_save.pop("folder", None)
+                    await MetadataManager.save_metadata(file_path, data_to_save)
+                else:
+                    sha256 = await calculate_sha256(file_path)
+                    if sha256:
+                        model_data["sha256"] = sha256.lower()
+                        model_data["hash_status"] = "completed"
+                        data_to_save = model_data.copy()
+                        data_to_save.pop("folder", None)
+                        await MetadataManager.save_metadata(file_path, data_to_save)
+                    else:
+                        return web.json_response(
+                            {
+                                "success": False,
+                                "error": "Failed to compute SHA256 hash for model",
+                            },
+                            status=500,
+                        )
+
            success, error = await self._metadata_sync.fetch_and_update_model(
                sha256=model_data["sha256"],
                file_path=file_path,
@@ -556,7 +619,12 @@ class ModelManagementHandler:
                    {"success": False, "error": OFFLINE_FRIENDLY_MESSAGE},
                    status=503,
                )
-            self._logger.error("Error fetching from CivitAI: %s", exc, exc_info=True)
+            self._logger.error(
+                "Error fetching from CivitAI for %s: %s",
+                locals().get("file_path", "unknown"),
+                exc,
+                exc_info=True,
+            )
            return web.json_response({"success": False, "error": str(exc)}, status=500)

    async def relink_civitai(self, request: web.Request) -> web.Response:
@@ -614,7 +682,7 @@ class ModelManagementHandler:
        try:
            reader = await request.multipart()

-            field = await reader.next()
+            field: Any = await reader.next()
            if field is None or field.name != "preview_file":
                raise ValueError("Expected 'preview_file' field")
            content_type = field.headers.get("Content-Type", "image/png")
@@ -656,7 +724,7 @@ class ModelManagementHandler:
                {
                    "success": True,
                    "preview_url": config.get_preview_static_url(
-                        result["preview_path"]
+                        str(result["preview_path"])
                    ),
                    "preview_nsfw_level": result["preview_nsfw_level"],
                }
@@ -737,7 +805,7 @@ class ModelManagementHandler:

            result = await self._preview_service.replace_preview(
                model_path=model_path,
-                preview_data=preview_data,
+                preview_data=preview_bytes,
                content_type=content_type,
                original_filename=original_filename,
                nsfw_level=nsfw_level,
@@ -749,7 +817,7 @@ class ModelManagementHandler:
                {
                    "success": True,
                    "preview_url": config.get_preview_static_url(
-                        result["preview_path"]
+                        str(result["preview_path"])
                    ),
                    "preview_nsfw_level": result["preview_nsfw_level"],
                }
@@ -887,6 +955,8 @@ class ModelManagementHandler:
                file_path=file_path, new_file_name=new_file_name
            )

+            _broadcast_models_changed()
+
            return web.json_response(
                {
                    **result,
@@ -915,6 +985,7 @@ class ModelManagementHandler:
                )

            result = await self._lifecycle_service.bulk_delete_models(file_paths)
+            _broadcast_models_changed()
            return web.json_response(result)
        except ValueError as exc:
            return web.json_response({"success": False, "error": str(exc)}, status=400)
@@ -963,6 +1034,8 @@ class ModelQueryHandler:
            limit = int(request.query.get("limit", "20"))
            if limit < 0:
                limit = 20
+            elif limit > 200:
+                limit = 20
            top_tags = await self._service.get_top_tags(limit)
            return web.json_response({"success": True, "tags": top_tags})
        except Exception as exc:
@@ -971,6 +1044,22 @@ class ModelQueryHandler:
                {"success": False, "error": "Internal server error"}, status=500
            )

+    async def search_tags(self, request: web.Request) -> web.Response:
+        try:
+            query = request.query.get("q", "")
+            limit = int(request.query.get("limit", "20"))
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+            tags = await self._service.search_tags(query, limit)
+            return web.json_response({"success": True, "tags": tags})
+        except Exception as exc:
+            self._logger.error("Error searching tags: %s", exc, exc_info=True)
+            return web.json_response(
+                {"success": False, "error": "Internal server error"}, status=500
+            )
+
    async def get_base_models(self, request: web.Request) -> web.Response:
        try:
            limit = int(request.query.get("limit", "20"))
@@ -999,6 +1088,7 @@ class ModelQueryHandler:
            await self._service.scan_models(
                force_refresh=True, rebuild_cache=full_rebuild
            )
+            _broadcast_models_changed()
            if self._service.scanner.is_cancelled():
                return web.json_response(
                    {
@@ -1265,9 +1355,13 @@ class ModelQueryHandler:
                    text=f"{self._service.model_type.capitalize()} file name is required",
                    status=400,
                )
-            notes = await self._service.get_model_notes(model_name)
-            if notes is not None:
-                return web.json_response({"success": True, "notes": notes})
+            result = await self._service.get_model_notes(model_name)
+            if result is not None:
+                return web.json_response({
+                    "success": True,
+                    "notes": result["notes"],
+                    "file_path": result["file_path"],
+                })
            return web.json_response(
                {
                    "success": False,
@@ -1303,9 +1397,20 @@ class ModelQueryHandler:
                }
                if include_license_flags:
                    model_data = await self._service.get_model_info_by_name(model_name)
-                    license_flags = (model_data or {}).get("license_flags")
-                    if license_flags is not None:
-                        response_payload["license_flags"] = int(license_flags)
+                    # Only return license_flags when real CivitAI model license
+                    # data exists. This mirrors ModelModal's guard
+                    # (modelData?.civitai?.model) so the preview tooltip never
+                    # shows misleading license icons for HF or other models
+                    # without actual license metadata.
+                    civitai_data = (model_data or {}).get("civitai") or {}
+                    has_license_data = (
+                        isinstance(civitai_data, dict)
+                        and isinstance(civitai_data.get("model"), dict)
+                    )
+                    if has_license_data:
+                        license_flags = (model_data or {}).get("license_flags")
+                        if license_flags is not None:
+                            response_payload["license_flags"] = int(license_flags)
                    # Include the user's license icon style preference so the
                    # ComfyUI tooltip can pick the right set without a separate
                    # API call.
@@ -1411,8 +1516,73 @@ class ModelQueryHandler:
            search = request.query.get("search", "").strip()
            limit = min(int(request.query.get("limit", "15")), 100)
            offset = max(0, int(request.query.get("offset", "0")))
+
+            folder = request.query.get("folder")
+            recursive = request.query.get("recursive", "true").lower() == "true"
+            base_models = list(request.query.getall("base_model", []))
+            model_types = list(request.query.getall("model_type", []))
+
+            tag_filters: Dict[str, str] = {}
+            for tag in request.query.getall("tag_include", []):
+                if tag:
+                    tag_filters[tag] = "include"
+            for tag in request.query.getall("tag_exclude", []):
+                if tag:
+                    tag_filters[tag] = "exclude"
+
+            auto_tag_filters: Dict[str, str] = {}
+            for tag in request.query.getall("auto_tag_include", []):
+                if tag:
+                    auto_tag_filters[tag] = "include"
+            for tag in request.query.getall("auto_tag_exclude", []):
+                if tag:
+                    auto_tag_filters[tag] = "exclude"
+
+            tag_logic = request.query.get("tag_logic", "any").lower()
+            if tag_logic not in ("any", "all"):
+                tag_logic = "any"
+
+            credit_required = request.query.get("credit_required")
+            if credit_required is not None:
+                credit_required = credit_required.lower() not in ("false", "0", "")
+
+            allow_selling_generated_content = request.query.get(
+                "allow_selling_generated_content"
+            )
+            if allow_selling_generated_content is not None:
+                allow_selling_generated_content = (
+                    allow_selling_generated_content.lower() not in ("false", "0", "")
+                )
+
+            # The presence of the recursive param (always sent by the loras
+            # widget when filter mode is on) signals that the filter pipeline
+            # must run even when no concrete filter is set, so global settings
+            # like show_only_sfw stay consistent with the list endpoint.
+            apply_filters = (
+                "recursive" in request.query
+                or folder is not None
+                or bool(base_models)
+                or bool(model_types)
+                or bool(tag_filters)
+                or bool(auto_tag_filters)
+                or credit_required is not None
+                or allow_selling_generated_content is not None
+            )
+
            matching_paths = await self._service.search_relative_paths(
-                search, limit, offset
+                search,
+                limit,
+                offset,
+                folder=folder,
+                recursive=recursive,
+                base_models=base_models,
+                model_types=model_types,
+                tags=tag_filters,
+                auto_tags=auto_tag_filters,
+                tag_logic=tag_logic,
+                credit_required=credit_required,
+                allow_selling_generated_content=allow_selling_generated_content,
+                apply_filters=apply_filters,
            )
            return web.json_response(
                {"success": True, "relative_paths": matching_paths}
@@ -1762,14 +1932,20 @@ class ModelDownloadHandler:

    async def delete_download_history_item(self, request: web.Request) -> web.Response:
        try:
-            item_id = int(request.query.get("id", "0"))
-            if not item_id:
+            download_id = request.query.get("download_id")
+            id_str = request.query.get("id")
+            item_id = int(id_str) if id_str else None
+
+            if not download_id and not item_id:
                return web.json_response(
-                    {"success": False, "error": "id is required"}, status=400
+                    {"success": False, "error": "id or download_id is required"},
+                    status=400,
                )

            service = await DownloadQueueService.get_instance()
-            deleted = await service.delete_history_item(item_id)
+            deleted = await service.delete_history_item(
+                id=item_id, download_id=download_id
+            )
            return web.json_response({"success": deleted})
        except Exception as exc:
            self._logger.error(
@@ -1779,14 +1955,20 @@ class ModelDownloadHandler:

    async def retry_download_from_history(self, request: web.Request) -> web.Response:
        try:
-            item_id = int(request.query.get("id", "0"))
-            if not item_id:
+            download_id = request.query.get("download_id")
+            id_str = request.query.get("id")
+            item_id = int(id_str) if id_str else None
+
+            if not download_id and not item_id:
                return web.json_response(
-                    {"success": False, "error": "id is required"}, status=400
+                    {"success": False, "error": "id or download_id is required"},
+                    status=400,
                )

            service = await DownloadQueueService.get_instance()
-            item = await service.retry_from_history(item_id)
+            item = await service.retry_from_history(
+                item_id=item_id, download_id=download_id
+            )
            if item is None:
                return web.json_response(
                    {"success": False, "error": "History item not found or not retryable"},
@@ -1906,7 +2088,7 @@ class ModelCivitaiHandler:
        settings_service: SettingsManager,
        ws_manager: WebSocketManager,
        logger: logging.Logger,
-        metadata_provider_factory: Callable[[], Awaitable],
+        metadata_provider_factory: Callable[[], Awaitable[Any]],
        validate_model_type: Callable[[str], bool],
        expected_model_types: Callable[[], str],
        find_model_file: Callable[
@@ -1971,7 +2153,7 @@ class ModelCivitaiHandler:
                downloaded_version_ids = set(
                    await history_service.get_downloaded_version_ids(
                        self._service.model_type,
-                        model_id,
+                        int(model_id),
                    )
                )
            except Exception as exc:  # pragma: no cover - defensive logging
@@ -2081,6 +2263,8 @@ class ModelMoveHandler:
            result = await self._move_service.move_model(
                file_path, target_path, use_default_paths=use_default_paths
            )
+            if result.get("success"):
+                _broadcast_models_changed()
            status = 200 if result.get("success") else 500
            return web.json_response(result, status=status)
        except Exception as exc:
@@ -2100,6 +2284,8 @@ class ModelMoveHandler:
            result = await self._move_service.move_models_bulk(
                file_paths, target_path, use_default_paths=use_default_paths
            )
+            if result.get("success"):
+                _broadcast_models_changed()
            return web.json_response(result)
        except Exception as exc:
            self._logger.error("Error moving models in bulk: %s", exc, exc_info=True)
@@ -2145,6 +2331,7 @@ class ModelAutoOrganizeHandler:
                progress_callback=self._progress_callback,
                exclusion_patterns=exclusion_patterns,
            )
+            _broadcast_models_changed()
            return web.json_response(result.to_dict())
        except AutoOrganizeInProgressError:
            return web.json_response(
@@ -2248,8 +2435,8 @@ class ModelUpdateHandler:
            self._logger.error("Failed to fetch license info: %s", exc, exc_info=True)
            return web.json_response({"success": False, "error": str(exc)}, status=500)

-        updated: List[Dict[str, str]] = []
-        errors: List[Dict[str, str]] = []
+        updated: List[Dict[str, Any]] = []
+        errors: List[Dict[str, Any]] = []
        for model_id in model_ids:
            license_payload = license_map.get(model_id)
            if not license_payload:
@@ -2262,6 +2449,7 @@ class ModelUpdateHandler:
                model_section = civitai_section.get("model")
                if not isinstance(model_section, Mapping):
                    model_section = {}
+                model_section = dict(model_section)
                model_section.update(resolved_payload)
                civitai_section["model"] = model_section
                metadata_payload["civitai"] = civitai_section
@@ -2277,7 +2465,7 @@ class ModelUpdateHandler:
                    )
                    errors.append({"filePath": metadata_path, "error": str(exc)})

-        response_payload = {"success": True, "updated": updated}
+        response_payload: Dict[str, Any] = {"success": True, "updated": updated}
        missing_model_ids = [mid for mid in model_ids if mid not in license_map]
        if missing_model_ids:
            response_payload["missingModelIds"] = missing_model_ids
@@ -2626,6 +2814,7 @@ class ModelUpdateHandler:
            civitai_payload = metadata_payload.get("civitai")
            if not isinstance(civitai_payload, Mapping):
                civitai_payload = {}
+            civitai_payload = dict(civitai_payload)

            model_payload = civitai_payload.get("model")
            if not isinstance(model_payload, Mapping):
@@ -2670,7 +2859,7 @@ class ModelUpdateHandler:

        return aggregated

-    def _extract_target_model_ids(self, payload: Dict) -> Optional[List[int]]:
+    def _extract_target_model_ids(self, payload: Dict[str, Any]) -> Optional[List[int]]:
        if not isinstance(payload, Mapping):
            return None

@@ -2698,7 +2887,7 @@ class ModelUpdateHandler:
            return {}

        to_dict = getattr(metadata, "to_dict", None)
-        if callable(to_dict):
+        if to_dict:
            try:
                return to_dict()
            except Exception:
@@ -2709,7 +2898,7 @@ class ModelUpdateHandler:

        return {}

-    async def _read_json(self, request: web.Request) -> Dict:
+    async def _read_json(self, request: web.Request) -> Dict[str, Any]:
        if not request.can_read_body:
            return {}
        try:
@@ -2741,7 +2930,7 @@ class ModelUpdateHandler:
        record,
        *,
        version_context: Optional[Dict[int, Dict[str, Any]]] = None,
-    ) -> Dict:
+    ) -> Dict[str, Any]:
        context = version_context or {}
        # Check user setting for hiding early access versions
        hide_early_access = False
@@ -2770,7 +2959,7 @@ class ModelUpdateHandler:
    @staticmethod
    def _serialize_version(
        version, context: Optional[Dict[str, Any]]
-    ) -> Dict:
+    ) -> Dict[str, Any]:
        context = context or {}
        preview_override = context.get("preview_override")
        preview_url = (
@@ -2910,6 +3099,7 @@ class ModelHandlerSet:
            "bulk_delete_models": self.management.bulk_delete_models,
            "verify_duplicates": self.management.verify_duplicates,
            "get_top_tags": self.query.get_top_tags,
+            "search_tags": self.query.search_tags,
            "get_base_models": self.query.get_base_models,
            "get_model_types": self.query.get_model_types,
            "scan_models": self.query.scan_models,
@@ -0,0 +1,323 @@
+"""Handler for the pending-delete undo endpoint.
+
+Restores a staged delete batch (models or recipes) via
+``PendingDeleteService.undo`` and then repairs the affected library caches:
+the model cache entry is restored from the manifest's ``model_snapshot``
+(including the version index and hash index), tag counts are re-incremented,
+and the recipe cache is re-populated via ``RecipeScanner.add_recipe``.
+
+The per-type scanner is resolved from the manifest's ``model_type`` page value
+through the SAME ServiceRegistry getters the model route registrars use
+(lora/checkpoint/embedding) - never a hardcoded lora scanner.
+"""
+
+from __future__ import annotations
+
+import inspect
+import json
+import logging
+import os
+import re
+from typing import Any, Awaitable, Callable, Dict, List, Optional, Set, cast
+
+from aiohttp import web
+
+from ...services.pending_delete_service import get_pending_delete_service
+from .model_handlers import _broadcast_models_changed
+
+logger = logging.getLogger(__name__)
+
+# Manifest ``model_type`` page values -> ServiceRegistry scanner getter names.
+# The model route registrars resolve per-type scanners via these getters
+# (lora_routes / checkpoint_routes / embedding_routes); undo must do the same
+# so the CORRECT cache is restored for the deleted model's type.
+_MODEL_TYPE_GETTER_NAMES: Dict[str, str] = {
+    "loras": "get_lora_scanner",
+    "checkpoints": "get_checkpoint_scanner",
+    "embeddings": "get_embedding_scanner",
+}
+
+# Staged batch ids are ``uuid.uuid4().hex`` (32 lowercase hex chars). The id is
+# joined into filesystem paths by ``_find_batch_dir``, so reject anything that
+# does not match this exact shape (blocks path-traversal via batch_id).
+_BATCH_ID_RE = re.compile(r"^[0-9a-f]{32}$")
+
+
+class PendingDeleteHandler:
+    """Handle undo requests for staged model/recipe deletions."""
+
+    def __init__(
+        self,
+        *,
+        service_factory: Callable[[], Awaitable[Any]] = get_pending_delete_service,
+        scanner_getter: Optional[Callable[[str], Awaitable[Any]]] = None,
+        recipe_scanner_getter: Optional[Callable[[], Awaitable[Any]]] = None,
+    ) -> None:
+        self._service_factory: Callable[[], Awaitable[Any]] = service_factory
+        self._scanner_getter: Callable[[str], Awaitable[Any]] = (
+            scanner_getter or self._resolve_scanner
+        )
+        self._recipe_scanner_getter: Callable[[], Awaitable[Any]] = (
+            recipe_scanner_getter or self._resolve_recipe_scanner
+        )
+
+    @staticmethod
+    async def _resolve_scanner(model_type: str) -> Any:
+        """Resolve the per-type scanner for a manifest ``model_type``.
+
+        The getter is looked up on the ServiceRegistry module namespace at call
+        time so tests (and the registry stubs) can patch it.
+        """
+        from ...services import service_registry
+
+        getter_name = _MODEL_TYPE_GETTER_NAMES.get(model_type)
+        if getter_name is None:
+            raise ValueError(f"Unknown model type: {model_type}")
+        getter = getattr(service_registry.ServiceRegistry, getter_name, None)
+        if not callable(getter):
+            raise ValueError(f"No scanner getter for model type: {model_type}")
+        scanner = await cast(Callable[[], Awaitable[Any]], getter)()
+        if scanner is None:
+            raise ValueError(f"No scanner registered for model type: {model_type}")
+        return scanner
+
+    @staticmethod
+    async def _resolve_recipe_scanner() -> Any:
+        """Resolve the recipe scanner via the ServiceRegistry module namespace."""
+        from ...services import service_registry
+
+        getter = getattr(service_registry.ServiceRegistry, "get_recipe_scanner", None)
+        if not callable(getter):
+            raise ValueError("Recipe scanner getter unavailable")
+        scanner = await cast(Callable[[], Awaitable[Any]], getter)()
+        if scanner is None:
+            raise ValueError("No recipe scanner registered")
+        return scanner
+
+    async def undo_delete(self, request: web.Request) -> web.Response:
+        """Restore a staged batch and its library cache entry.
+
+        Body: ``{"batch_id": str}``. On success returns
+        ``{"success": True, "restored": [<original paths>], "kind": kind}``.
+        Expired/unknown batches and occupied target paths -> 404.
+        """
+        try:
+            data = await request.json()
+        except Exception:
+            return web.json_response(
+                {"success": False, "error": "Invalid JSON body"}, status=400
+            )
+        if not isinstance(data, dict):
+            return web.json_response(
+                {"success": False, "error": "Invalid JSON body"}, status=400
+            )
+        batch_id = data.get("batch_id")
+        if not batch_id or not isinstance(batch_id, str):
+            return web.json_response(
+                {"success": False, "error": "batch_id is required"}, status=400
+            )
+        if not _BATCH_ID_RE.fullmatch(batch_id):
+            # batch_id is joined into a path by _find_batch_dir - restrict to
+            # the exact staged-id shape so traversal payloads get 400.
+            return web.json_response(
+                {"success": False, "error": "Invalid batch_id"}, status=400
+            )
+
+        service = await self._service_factory()
+        try:
+            # Read the manifest BEFORE undo: undo() removes the batch dir.
+            manifest = await self._read_staged_manifest(service, batch_id)
+            result = await service.undo(batch_id)
+        except ValueError as exc:
+            return web.json_response({"success": False, "error": str(exc)}, status=404)
+        except Exception as exc:
+            logger.error("Unexpected error undoing batch %s: %s", batch_id, exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+        kind = result.get("kind")
+        try:
+            if kind == "model":
+                if manifest is not None:
+                    await self._restore_model_cache(manifest)
+                else:
+                    # undo() raises when the manifest is missing, so this only
+                    # happens defensively - files are restored regardless.
+                    logger.warning(
+                        "Manifest missing after undo of %s; skipping cache restore",
+                        batch_id,
+                    )
+                _broadcast_models_changed()
+            elif kind == "recipe":
+                # Recipe undo is client-refresh only: re-add to the scanner
+                # cache, no models_changed broadcast.
+                if manifest is not None:
+                    await self._restore_recipe_cache(result, manifest)
+                else:
+                    logger.warning(
+                        "Manifest missing after undo of %s; skipping cache restore",
+                        batch_id,
+                    )
+        except Exception as exc:
+            # Files are already restored; only the cache restoration failed.
+            logger.error(
+                "Cache restoration failed after undo of %s: %s",
+                batch_id,
+                exc,
+                exc_info=True,
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+        return web.json_response(
+            {
+                "success": True,
+                "restored": result.get("restored", []),
+                "kind": kind,
+            }
+        )
+
+    @staticmethod
+    async def _read_staged_manifest(
+        service: Any, batch_id: str
+    ) -> Optional[Dict[str, Any]]:
+        """Locate and read the batch manifest while it still exists on disk."""
+        batch_dir = await service._find_batch_dir(batch_id)
+        if not batch_dir:
+            return None
+        manifest_path = os.path.join(batch_dir, "manifest.json")
+        try:
+            with open(manifest_path, "r", encoding="utf-8") as handle:
+                payload = json.load(handle)
+        except (OSError, json.JSONDecodeError) as exc:
+            logger.debug("Failed to read manifest for batch %s: %s", batch_id, exc)
+            return None
+        return payload if isinstance(payload, dict) else None
+
+    async def _restore_model_cache(self, manifest: Dict[str, Any]) -> None:
+        """Re-add every deleted model's cache entry from the manifest.
+
+        Each main-file entry carries the deleted model's ``snapshot`` (added at
+        stage time), so a merged bulk manifest holds ALL snapshots - undo must
+        restore every one, not just the top-level winner's. Old-format
+        manifests without entry snapshots fall back to the top-level
+        ``model_snapshot`` (backward compat / single-delete path).
+        """
+        model_type = manifest.get("model_type")
+        if not model_type or not isinstance(model_type, str):
+            raise ValueError(f"Manifest carries no model_type: {manifest.get('batch_id')}")
+        scanner = await self._scanner_getter(model_type)
+
+        # Collect one snapshot per distinct file_path from the entry snapshots.
+        snapshots: List[Dict[str, Any]] = []
+        seen: Set[str] = set()
+        for entry in manifest.get("entries") or []:
+            snapshot = entry.get("snapshot")
+            if not isinstance(snapshot, dict):
+                continue
+            file_path = snapshot.get("file_path")
+            if not file_path or not isinstance(file_path, str):
+                continue
+            if file_path in seen:
+                continue
+            seen.add(file_path)
+            snapshots.append(snapshot)
+
+        if not snapshots:
+            # Backward compat: pre-F3 manifests carry only the top-level
+            # model_snapshot (single-delete path, unchanged behavior).
+            top = manifest.get("model_snapshot")
+            if isinstance(top, dict) and top.get("file_path"):
+                snapshots = [top]
+            else:
+                logger.warning(
+                    "Manifest %s has no restorable model snapshot; skipping cache restore",
+                    manifest.get("batch_id"),
+                )
+                return
+
+        cache = await scanner.get_cached_data()
+        if cache is None:
+            logger.warning(
+                "Scanner cache unavailable for %s; skipping cache restore", model_type
+            )
+            return
+
+        for snapshot in snapshots:
+            file_path = str(snapshot["file_path"])
+            # A rescan between delete and undo may have re-added a stale entry
+            # for this path - drop it so exactly one (the snapshot) remains.
+            cache.raw_data = [
+                item for item in cache.raw_data if item.get("file_path") != file_path
+            ]
+
+            # Restore tag counts (mirror of the bulk-delete decrement in
+            # _batch_update_cache_for_deleted_models: undo re-increments).
+            tags = snapshot.get("tags")
+            if isinstance(tags, list):
+                for tag in tags:
+                    if not isinstance(tag, str) or not tag:
+                        continue
+                    scanner._tags_count[tag] = scanner._tags_count.get(tag, 0) + 1
+
+            cache.raw_data.append(dict(snapshot))
+
+            # Re-register the path in the hash index (add_entry guards a
+            # missing sha256 internally; still guard defensively here).
+            sha256 = snapshot.get("sha256") or ""
+            autov3 = snapshot.get("autov3")
+            hash_index = getattr(scanner, "_hash_index", None)
+            if hash_index is not None and sha256 and file_path:
+                hash_index.add_entry(sha256, file_path, autov3)
+
+        # Follow the bulk-delete cache-update pattern ONCE after all entries,
+        # including the explicit version-index rebuild so the version index
+        # does not go stale.
+        cache.rebuild_version_index()
+        await cache.resort()
+
+        scanner.bump_cache_version()
+
+        persist = getattr(scanner, "_persist_current_cache", None)
+        if callable(persist):
+            result = persist()
+            if inspect.isawaitable(result):
+                await result
+
+    async def _restore_recipe_cache(
+        self, result: Dict[str, Any], manifest: Dict[str, Any]
+    ) -> None:
+        """Re-add a restored recipe via ``RecipeScanner.add_recipe``.
+
+        The recipe JSON embeds the full recipe_data (incl. id/file_path);
+        ``add_recipe`` only READS the ``_json_path_map`` so the forced frontend
+        refresh self-heals any transient path-map gap.
+        """
+        restored = result.get("restored") or []
+        json_path = next(
+            (p for p in restored if isinstance(p, str) and p.endswith(".json")),
+            None,
+        )
+        if not json_path or not os.path.exists(json_path):
+            # Defensive fallback to the manifest's recipe_snapshot file_path.
+            snapshot = manifest.get("recipe_snapshot") or {}
+            fallback = snapshot.get("file_path")
+            if fallback and os.path.exists(fallback):
+                json_path = fallback
+            else:
+                logger.warning(
+                    "Restored recipe JSON not found in %s; skipping cache restore",
+                    restored,
+                )
+                return
+        try:
+            with open(json_path, "r", encoding="utf-8") as handle:
+                recipe_data = json.load(handle)
+        except (OSError, json.JSONDecodeError) as exc:
+            logger.warning("Failed to load restored recipe JSON %s: %s", json_path, exc)
+            return
+        if not isinstance(recipe_data, dict):
+            return
+        recipe_scanner = await self._recipe_scanner_getter()
+        await recipe_scanner.add_recipe(recipe_data)
+
+
+__all__ = ["PendingDeleteHandler"]
@@ -2,6 +2,7 @@

 from __future__ import annotations

+import asyncio
 import logging
 import mimetypes
 import urllib.parse
@@ -53,6 +54,7 @@ class PreviewHandler:

        if not resolved.is_file():
            logger.debug("Preview file not found at %s", str(resolved))
+            asyncio.create_task(self._cleanup_stale_preview_url(normalized))
            raise web.HTTPNotFound(text="Preview file not found")

        # aiohttp's FileResponse handles range requests, content headers, and
@@ -69,6 +71,35 @@ class PreviewHandler:
        resp.headers["Cache-Control"] = "public, max-age=86400"
        return resp

+    async def _cleanup_stale_preview_url(self, normalized_preview_path: str) -> None:
+        """Fire-and-forget: clear stale preview_url from all model caches.
+
+        When a preview file is no longer on disk, remove its reference from
+        every cached entry so subsequent list API responses return an empty
+        ``preview_url``, letting the frontend show the no-preview placeholder.
+        """
+        try:
+            from ...services.service_registry import ServiceRegistry
+
+            for service_name in ("lora_scanner", "checkpoint_scanner", "embedding_scanner"):
+                scanner = ServiceRegistry.get_service_sync(service_name)
+                if scanner is None or not hasattr(scanner, "_cache"):
+                    continue
+                cache = getattr(scanner, "_cache", None)
+                if cache is None or not hasattr(cache, "clear_preview_by_path"):
+                    continue
+                cleared = await cache.clear_preview_by_path(normalized_preview_path)
+                if cleared and hasattr(scanner, "_persist_current_cache"):
+                    await scanner._persist_current_cache()
+                    logger.info(
+                        "Cleared stale preview_url for %d %s entries (%s)",
+                        cleared,
+                        service_name,
+                        normalized_preview_path,
+                    )
+        except Exception as exc:
+            logger.debug("Failed to clean up stale preview_url: %s", exc)
+
    async def _stream_file(
        self, request: web.Request, path: Path
    ) -> web.StreamResponse:
@@ -10,7 +10,7 @@ import asyncio
 import tempfile
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Awaitable, Callable, Dict, List, Mapping, Optional
+from typing import Any, Awaitable, Callable, Dict, List, Mapping, Optional, Tuple

 from aiohttp import web

@@ -44,6 +44,22 @@ EnsureDependenciesCallable = Callable[[], Awaitable[None]]
 RecipeScannerGetter = Callable[[], Any]
 CivitaiClientGetter = Callable[[], Any]

+# Cap concurrent preview-dimension reads across requests. With a cold LRU
+# cache one page can touch up to page_size image files; 16 balances SSD and
+# HDD throughput without starving the event loop.
+_DIMS_READ_SEMAPHORE = asyncio.Semaphore(16)
+
+
+async def _read_preview_dims(path: str) -> Optional[Tuple[int, int]]:
+    """Read preview dimensions off the event loop under the concurrency cap.
+
+    PIL I/O runs in a worker thread so it never blocks the event loop, and the
+    semaphore bounds how many files are opened at once even when many list
+    requests land together.
+    """
+    async with _DIMS_READ_SEMAPHORE:
+        return await asyncio.to_thread(ExifUtils.get_image_dimensions, path)
+

@dataclass(frozen=True)
 class RecipeHandlerSet:
@@ -72,6 +88,7 @@ class RecipeHandlerSet:
            "save_recipe": self.management.save_recipe,
            "delete_recipe": self.management.delete_recipe,
            "get_top_tags": self.query.get_top_tags,
+            "search_tags": self.query.search_tags,
            "get_base_models": self.query.get_base_models,
            "get_roots": self.query.get_roots,
            "get_folders": self.query.get_folders,
@@ -95,6 +112,11 @@ class RecipeHandlerSet:
            "repair_recipe": self.management.repair_recipe,
            "repair_recipes_bulk": self.management.repair_recipes_bulk,
            "get_repair_progress": self.management.get_repair_progress,
+            "rematch_recipes": self.management.rematch_recipes,
+            "cancel_rematch": self.management.cancel_rematch,
+            "rematch_recipe": self.management.rematch_recipe,
+            "rematch_recipes_bulk": self.management.rematch_recipes_bulk,
+            "get_rematch_progress": self.management.get_rematch_progress,
            "start_batch_import": self.batch_import.start_batch_import,
            "get_batch_import_progress": self.batch_import.get_batch_import_progress,
            "cancel_batch_import": self.batch_import.cancel_batch_import,
@@ -245,7 +267,8 @@ class RecipeListingHandler:
                recursive=recursive,
            )

-            for item in result.get("items", []):
+            items = result.get("items", [])
+            for item in items:
                file_path = item.get("file_path")
                if file_path:
                    item["file_url"] = self.format_recipe_file_url(file_path)
@@ -254,6 +277,26 @@ class RecipeListingHandler:
                item.setdefault("loras", [])
                item.setdefault("base_model", "")

+            # Batch preview dimension reads with asyncio.gather. The previous
+            # loop awaited asyncio.to_thread once per item, so a page_size=100
+            # request submitted 100 sequential thread calls (50-300ms cold-page
+            # latency). gather runs them concurrently while the semaphore caps
+            # disk opens; dimensions stay omitted (not null) when a preview has
+            # no readable size (video, missing file).
+            to_read = [
+                (i, item.get("file_path"))
+                for i, item in enumerate(items)
+                if item.get("file_path")
+            ]
+            if to_read:
+                dims_list = await asyncio.gather(
+                    *(_read_preview_dims(path) for _, path in to_read)
+                )
+                for (idx, _), dims in zip(to_read, dims_list):
+                    if dims:
+                        item = items[idx]
+                        item["width"], item["height"] = dims
+
            return web.json_response(result)
        except Exception as exc:
            self._logger.error("Error retrieving recipes: %s", exc, exc_info=True)
@@ -317,12 +360,11 @@ class RecipeQueryHandler:
                raise RuntimeError("Recipe scanner unavailable")

            limit = int(request.query.get("limit", "20"))
-            cache = await recipe_scanner.get_cached_data()
-
-            tag_counts: Dict[str, int] = {}
-            for recipe in getattr(cache, "raw_data", []):
-                for tag in recipe.get("tags", []) or []:
-                    tag_counts[tag] = tag_counts.get(tag, 0) + 1
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+            tag_counts = await self._get_recipe_tag_counts(recipe_scanner)

            sorted_tags = [
                {"tag": tag, "count": count} for tag, count in tag_counts.items()
@@ -333,6 +375,55 @@ class RecipeQueryHandler:
            self._logger.error("Error retrieving top tags: %s", exc, exc_info=True)
            return web.json_response({"success": False, "error": str(exc)}, status=500)

+    async def search_tags(self, request: web.Request) -> web.Response:
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                raise RuntimeError("Recipe scanner unavailable")
+
+            query = request.query.get("q", "")
+            limit = int(request.query.get("limit", "20"))
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+
+            tag_counts = await self._get_recipe_tag_counts(recipe_scanner)
+            normalized_query = (query or "").strip().lower()
+            if not normalized_query:
+                sorted_tags = [
+                    {"tag": tag, "count": count} for tag, count in tag_counts.items()
+                ]
+                sorted_tags.sort(key=lambda entry: entry["count"], reverse=True)
+                return web.json_response(
+                    {"success": True, "tags": sorted_tags[: (limit if limit > 0 else 20)]}
+                )
+
+            matched = [
+                {"tag": tag, "count": count}
+                for tag, count in tag_counts.items()
+                if normalized_query in tag.lower()
+            ]
+            matched.sort(key=lambda entry: entry["count"], reverse=True)
+            if limit == 0:
+                result = matched
+            else:
+                result = matched[:limit]
+            return web.json_response({"success": True, "tags": result})
+        except Exception as exc:
+            self._logger.error("Error searching recipe tags: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def _get_recipe_tag_counts(self, recipe_scanner) -> Dict[str, int]:
+        """Compute tag->count mapping from cached recipe data."""
+        cache = await recipe_scanner.get_cached_data()
+        tag_counts: Dict[str, int] = {}
+        for recipe in getattr(cache, "raw_data", []):
+            for tag in recipe.get("tags", []) or []:
+                tag_counts[tag] = tag_counts.get(tag, 0) + 1
+        return tag_counts
+
    async def get_base_models(self, request: web.Request) -> web.Response:
        try:
            await self._ensure_dependencies_ready()
@@ -489,7 +580,12 @@ class RecipeQueryHandler:
            if recipe_scanner is None:
                raise RuntimeError("Recipe scanner unavailable")

-            fingerprint_groups = await recipe_scanner.find_all_duplicate_recipes()
+            include_prompt = (
+                request.query.get("include_prompt", "false").lower() in ("1", "true")
+            )
+            fingerprint_groups = await recipe_scanner.find_all_duplicate_recipes(
+                include_prompt=include_prompt
+            )
            url_groups = await recipe_scanner.find_duplicate_recipes_by_source()
            response_data = []

@@ -522,6 +618,7 @@ class RecipeQueryHandler:
                    response_data.append(
                        {
                            "type": "fingerprint",
+                            "key": f"g-{len(response_data) + 1}",
                            "fingerprint": fingerprint,
                            "count": len(recipes),
                            "recipes": recipes,
@@ -557,6 +654,7 @@ class RecipeQueryHandler:
                    response_data.append(
                        {
                            "type": "source_path",
+                            "key": f"g-{len(response_data) + 1}",
                            "fingerprint": url,
                            "count": len(recipes),
                            "recipes": recipes,
@@ -801,6 +899,159 @@ class RecipeManagementHandler:
            self._logger.error("Error repairing single recipe: %s", exc, exc_info=True)
            return web.json_response({"success": False, "error": str(exc)}, status=500)

+    async def rematch_recipes(self, request: web.Request) -> web.Response:
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                return web.json_response(
+                    {"success": False, "error": "Recipe scanner unavailable"},
+                    status=503,
+                )
+
+            # Mutual exclusion: a global rematch cannot start while a rematch
+            # OR a repair is already running — both mutate recipes under the
+            # same mutation lock.
+            if (
+                self._ws_manager.is_recipe_rematch_running()
+                or self._ws_manager.is_recipe_repair_running()
+            ):
+                return web.json_response(
+                    {"success": False, "error": "Recipe rematch already in progress"},
+                    status=409,
+                )
+
+            recipe_scanner.reset_cancellation()
+
+            async def progress_callback(data):
+                await self._ws_manager.broadcast_recipe_rematch_progress(data)
+
+            # Run in background to avoid timeout
+            async def run_rematch():
+                try:
+                    await recipe_scanner.rematch_all_recipes(
+                        progress_callback=progress_callback
+                    )
+                except Exception as e:
+                    self._logger.error(
+                        f"Error in recipe rematch task: {e}", exc_info=True
+                    )
+                    await self._ws_manager.broadcast_recipe_rematch_progress(
+                        {"status": "error", "error": str(e)}
+                    )
+                finally:
+                    # Keep the final status for a while so the UI can see it
+                    await asyncio.sleep(5)
+                    self._ws_manager.cleanup_recipe_rematch_progress()
+
+            asyncio.create_task(run_rematch())
+
+            return web.json_response(
+                {"success": True, "message": "Recipe rematch started"}
+            )
+        except Exception as exc:
+            self._logger.error("Error starting recipe rematch: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def cancel_rematch(self, request: web.Request) -> web.Response:
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                return web.json_response(
+                    {"success": False, "error": "Recipe scanner unavailable"},
+                    status=503,
+                )
+
+            recipe_scanner.cancel_task()
+            return web.json_response(
+                {"success": True, "message": "Cancellation requested"}
+            )
+        except Exception as exc:
+            self._logger.error("Error cancelling recipe rematch: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def rematch_recipes_bulk(self, request: web.Request) -> web.Response:
+        """Rematch deleted resources for multiple recipes by their IDs.
+
+        Accepts a JSON body with a "recipe_ids" array. The per-recipe loop is
+        delegated to the scanner's rematch_recipes_bulk; this handler only
+        parses the request and returns the scanner's summary.
+        """
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                return web.json_response(
+                    {"success": False, "error": "Recipe scanner unavailable"},
+                    status=503,
+                )
+
+            # A bulk rematch must not queue behind a running global rematch's
+            # mutation lock.
+            if self._ws_manager.is_recipe_rematch_running():
+                return web.json_response(
+                    {"success": False, "error": "Recipe rematch already in progress"},
+                    status=409,
+                )
+
+            data = await request.json()
+            recipe_ids = data.get("recipe_ids", [])
+            if not recipe_ids:
+                return web.json_response(
+                    {"success": False, "error": "recipe_ids are required"},
+                    status=400,
+                )
+
+            result = await recipe_scanner.rematch_recipes_bulk(recipe_ids)
+            return web.json_response(result)
+        except Exception as exc:
+            self._logger.error(
+                "Error performing bulk rematch: %s", exc, exc_info=True
+            )
+            return web.json_response(
+                {"success": False, "error": str(exc)}, status=500
+            )
+
+    async def rematch_recipe(self, request: web.Request) -> web.Response:
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                return web.json_response(
+                    {"success": False, "error": "Recipe scanner unavailable"},
+                    status=503,
+                )
+
+            # Reject per-recipe rematches while a global run is in progress so
+            # they do not queue behind the mutation lock.
+            if self._ws_manager.is_recipe_rematch_running():
+                return web.json_response(
+                    {"success": False, "error": "Recipe rematch already in progress"},
+                    status=409,
+                )
+
+            recipe_id = request.match_info["recipe_id"]
+            result = await recipe_scanner.rematch_recipe_by_id(recipe_id)
+            return web.json_response(result)
+        except RecipeNotFoundError as exc:
+            return web.json_response({"success": False, "error": str(exc)}, status=404)
+        except Exception as exc:
+            self._logger.error("Error rematching single recipe: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def get_rematch_progress(self, request: web.Request) -> web.Response:
+        try:
+            progress = self._ws_manager.get_recipe_rematch_progress()
+            if progress:
+                return web.json_response({"success": True, "progress": progress})
+            return web.json_response(
+                {"success": False, "message": "No rematch in progress"}, status=404
+            )
+        except Exception as exc:
+            self._logger.error("Error getting rematch progress: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
    async def reimport_recipe(self, request: web.Request) -> web.Response:
        """Delete a recipe and re-import it from its source URL.

@@ -996,10 +1247,10 @@ class RecipeManagementHandler:
        *,
        image_url: str,
        name: str,
-        lora_entries: list,
-        checkpoint_entry: dict,
-        gen_params_request: dict,
-        tags: list,
+        lora_entries: list[Any],
+        checkpoint_entry: Dict[str, Any] | None,
+        gen_params_request: Dict[str, Any] | None,
+        tags: list[Any],
        base_model: str,
        source_path: str,
    ) -> web.Response:
@@ -1032,6 +1283,12 @@ class RecipeManagementHandler:
            _original_image_url,
        ) = await self._download_remote_media(image_url)

+        # Build a version-cached map of local model hashes to cache items so
+        # CivitaiApiMetadataParser can skip CivitAI API calls for models that
+        # exist on disk. Built once and shared by every parse pass below.
+        local_cache = await recipe_scanner.build_local_hash_cache()
+        from ...recipes.parsers.civitai_image import CivitaiApiMetadataParser
+
        # Extract embedded EXIF metadata (offloaded to thread pool in this call)
        embedded_gen_params = {}
        parsed_embedded = None
@@ -1053,9 +1310,16 @@ class RecipeManagementHandler:
                        )
                    )
                    if parser:
-                        parsed_embedded = await parser.parse_metadata(
-                            raw_embedded, recipe_scanner=recipe_scanner
-                        )
+                        if isinstance(parser, CivitaiApiMetadataParser):
+                            parsed_embedded = await parser.parse_metadata(
+                                raw_embedded,
+                                recipe_scanner=recipe_scanner,
+                                local_cache=local_cache,
+                            )
+                        else:
+                            parsed_embedded = await parser.parse_metadata(
+                                raw_embedded, recipe_scanner=recipe_scanner
+                            )
                        if parsed_embedded and "gen_params" in parsed_embedded:
                            embedded_gen_params = parsed_embedded["gen_params"]
                    else:
@@ -1086,9 +1350,16 @@ class RecipeManagementHandler:
                    civitai_inner_meta
                )
                if parser:
-                    civitai_parsed = await parser.parse_metadata(
-                        civitai_inner_meta, recipe_scanner=recipe_scanner
-                    )
+                    if isinstance(parser, CivitaiApiMetadataParser):
+                        civitai_parsed = await parser.parse_metadata(
+                            civitai_inner_meta,
+                            recipe_scanner=recipe_scanner,
+                            local_cache=local_cache,
+                        )
+                    else:
+                        civitai_parsed = await parser.parse_metadata(
+                            civitai_inner_meta, recipe_scanner=recipe_scanner
+                        )
                    if civitai_parsed and "gen_params" in civitai_parsed:
                        # Merge: API gen_params override EXIF at field level,
                        # EXIF fills in fields the API doesn't have.
@@ -1592,7 +1863,7 @@ class RecipeManagementHandler:
            if not provider:
                return ""

-            version_info = await provider.get_model_version_info(version_id)
+            version_info = await provider.get_model_version_info(str(version_id))
            if isinstance(version_info, tuple):
                version_info = version_info[0]

@@ -1712,6 +1983,12 @@ class RecipeManagementHandler:
            await self._download_remote_media(image_url)
        )

+        # Build a version-cached map of local model hashes to cache items so
+        # CivitaiApiMetadataParser can skip CivitAI API calls for models that
+        # exist on disk. Built once and shared by every parse pass below.
+        local_cache = await recipe_scanner.build_local_hash_cache()
+        from ...recipes.parsers.civitai_image import CivitaiApiMetadataParser
+
        # Extract embedded EXIF metadata
        embedded_gen_params = {}
        parsed_embedded = None
@@ -1733,9 +2010,16 @@ class RecipeManagementHandler:
                        )
                    )
                    if parser:
-                        parsed_embedded = await parser.parse_metadata(
-                            raw_embedded, recipe_scanner=recipe_scanner
-                        )
+                        if isinstance(parser, CivitaiApiMetadataParser):
+                            parsed_embedded = await parser.parse_metadata(
+                                raw_embedded,
+                                recipe_scanner=recipe_scanner,
+                                local_cache=local_cache,
+                            )
+                        else:
+                            parsed_embedded = await parser.parse_metadata(
+                                raw_embedded, recipe_scanner=recipe_scanner
+                            )
                        if parsed_embedded and "gen_params" in parsed_embedded:
                            embedded_gen_params = parsed_embedded["gen_params"]
            finally:
@@ -1773,9 +2057,16 @@ class RecipeManagementHandler:
                                )
                            )
                            if parser:
-                                parsed_embedded = await parser.parse_metadata(
-                                    raw_orig, recipe_scanner=recipe_scanner
-                                )
+                                if isinstance(parser, CivitaiApiMetadataParser):
+                                    parsed_embedded = await parser.parse_metadata(
+                                        raw_orig,
+                                        recipe_scanner=recipe_scanner,
+                                        local_cache=local_cache,
+                                    )
+                                else:
+                                    parsed_embedded = await parser.parse_metadata(
+                                        raw_orig, recipe_scanner=recipe_scanner
+                                    )
                                if (
                                    parsed_embedded
                                    and "gen_params" in parsed_embedded
@@ -1809,9 +2100,16 @@ class RecipeManagementHandler:
                    civitai_inner_meta
                )
                if parser:
-                    civitai_parsed = await parser.parse_metadata(
-                        civitai_inner_meta, recipe_scanner=recipe_scanner
-                    )
+                    if isinstance(parser, CivitaiApiMetadataParser):
+                        civitai_parsed = await parser.parse_metadata(
+                            civitai_inner_meta,
+                            recipe_scanner=recipe_scanner,
+                            local_cache=local_cache,
+                        )
+                    else:
+                        civitai_parsed = await parser.parse_metadata(
+                            civitai_inner_meta, recipe_scanner=recipe_scanner
+                        )
                    if civitai_parsed and "gen_params" in civitai_parsed:
                        # Merge: API gen_params override EXIF at field level,
                        # EXIF fills in fields the API doesn't have.
@@ -2023,33 +2321,44 @@ class RecipeManagementHandler:
            parsed_input = {**image_data, **inner_meta}
            parsed_input.pop("meta", None)

-            # Build a local cache of {hash → cache_item} so the parser can
-            # skip CivitAI API calls for models that exist on disk.
-            local_cache: Dict[str, Dict[str, Any]] = {}
-            lora_scanner = getattr(recipe_scanner, "_lora_scanner", None)
-            if lora_scanner and model_hash:
-                try:
-                    parent_cache_data = await lora_scanner.get_cached_data()
-                    for item in getattr(parent_cache_data, "raw_data", []):
-                        if item.get("sha256", "").lower() == model_hash.lower():
-                            local_cache[model_hash.lower()] = item
-                            # Compute AutoV3 so the parser can also match on
-                            # that hash type (CivitAI metadata resources use
-                            # AutoV3).
-                            file_path = item.get("file_path")
-                            if file_path and os.path.exists(file_path):
-                                try:
-                                    from ...utils.file_utils import (
-                                        calculate_autov3,
-                                    )
-                                    autov3 = calculate_autov3(file_path)
-                                    if autov3:
-                                        local_cache[autov3.lower()] = item
-                                except Exception:
-                                    pass
-                            break
-                except Exception:
-                    pass
+            # Build the shared local hash cache so the parser can skip CivitAI
+            # API calls for models that exist on disk.
+            local_cache: Dict[str, Dict[str, Any]] = (
+                await recipe_scanner.build_local_hash_cache()
+            )
+
+            # Bounded supplement for un-backfilled parents. The shared builder
+            # never computes autov3; when the parent model exists on disk but
+            # its cached entry has no stored AutoV3, compute it for that single
+            # file and register the AutoV3 key so the parser can also match on
+            # that hash type (CivitAI metadata resources use AutoV3). This runs
+            # whenever the parent is found with an empty autov3, independent of
+            # whether the sha256 key is already present in the shared cache.
+            if model_hash:
+                lora_scanner = getattr(recipe_scanner, "_lora_scanner", None)
+                if lora_scanner:
+                    try:
+                        parent_cache_data = await lora_scanner.get_cached_data()
+                        for item in getattr(parent_cache_data, "raw_data", []):
+                            if item.get("sha256", "").lower() == model_hash.lower():
+                                autov3 = (item.get("autov3") or "").lower()
+                                if not autov3:
+                                    file_path = item.get("file_path")
+                                    if file_path and os.path.exists(file_path):
+                                        try:
+                                            from ...utils.file_utils import (
+                                                calculate_autov3,
+                                            )
+                                            autov3 = (
+                                                calculate_autov3(file_path) or ""
+                                            ).lower()
+                                        except Exception:
+                                            pass
+                                if autov3:
+                                    local_cache[autov3] = item
+                                break
+                    except Exception:
+                        pass

            parser = self._analysis_service._recipe_parser_factory.create_parser(
                parsed_input
@@ -2081,10 +2390,10 @@ class RecipeManagementHandler:
            parent_model_id: int | None = None
            parent_version_name: str | None = None
            parent_model_name: str | None = None
-            # Prefer sha256 key; fall back to any cached entry.
+            # Resolve the parent strictly by its sha256 key. There is no
+            # arbitrary fallback: with a full-library cache, picking any entry
+            # would corrupt the isDeleted reconciliation below.
            parent_item = local_cache.get(model_hash.lower()) if model_hash else None
-            if parent_item is None and local_cache:
-                parent_item = next(iter(local_cache.values()))
            if parent_item:
                civ = parent_item.get("civitai") or {}
                if isinstance(civ, dict):
@@ -2218,6 +2527,31 @@ class RecipeManagementHandler:
                        "Failed to download image for recipe: %s", exc
                    )

+            # Fallback: try to locate a custom image on disk using model_hash + image id
+            if image_bytes is None:
+                image_id = image_data.get("id") or ""
+                if image_id and model_hash:
+                    from ...utils.example_images_paths import get_model_folder
+                    model_folder = get_model_folder(model_hash)
+                    if model_folder and os.path.exists(model_folder):
+                        for fname in os.listdir(model_folder):
+                            if f"custom_{image_id}" in fname:
+                                ext = os.path.splitext(fname)[1].lower()
+                                if ext not in (".jpg", ".jpeg", ".png", ".webp", ".gif"):
+                                    continue
+                                fpath = os.path.join(model_folder, fname)
+                                if os.path.isfile(fpath):
+                                    try:
+                                        with open(fpath, "rb") as f:
+                                            image_bytes = f.read()
+                                        extension = ext
+                                    except Exception as exc:
+                                        self._logger.warning(
+                                            "Failed to read custom image file %s: %s",
+                                            fpath, exc,
+                                        )
+                                break
+
            prompt = (
                (parsed.get("gen_params") or {}).get("prompt") or ""
            )
@@ -2275,7 +2609,7 @@ class RecipeAnalysisHandler:
            content_type = request.headers.get("Content-Type", "")
            if "multipart/form-data" in content_type:
                reader = await request.multipart()
-                field = await reader.next()
+                field: Any = await reader.next()
                if field is None or field.name != "image":
                    raise RecipeValidationError("No image field found")
                image_chunks = bytearray()
@@ -1,8 +1,8 @@
 import asyncio
 import logging
 from aiohttp import web
-from typing import Dict
-from server import PromptServer  # type: ignore
+from typing import Any, Dict
+from server import PromptServer  # pyright: ignore[reportMissingImports]

 from .base_model_routes import BaseModelRoutes
 from .model_route_registrar import ModelRouteRegistrar
@@ -31,13 +31,13 @@ class LoraRoutes(BaseModelRoutes):
        # Attach service dependencies
        self.attach_service(self.service)

-    def setup_routes(self, app: web.Application):
+    def setup_routes(self, app: web.Application, prefix: str = "loras"):
        """Setup LoRA routes"""
        # Schedule service initialization on app startup
        app.on_startup.append(lambda _: self.initialize_services())

        # Setup common routes with 'loras' prefix (includes page route)
-        super().setup_routes(app, "loras")
+        super().setup_routes(app, prefix)

    def setup_specific_routes(self, registrar: ModelRouteRegistrar, prefix: str):
        """Setup LoRA-specific routes"""
@@ -73,7 +73,7 @@ class LoraRoutes(BaseModelRoutes):
            "POST", "/api/lm/{prefix}/get_trigger_words", prefix, self.get_trigger_words
        )

-    def _parse_specific_params(self, request: web.Request) -> Dict:
+    def _parse_specific_params(self, request: web.Request) -> Dict[str, Any]:
        """Parse LoRA-specific parameters"""
        params = {}

@@ -119,25 +119,6 @@ class LoraRoutes(BaseModelRoutes):
            logger.error(f"Error getting letter counts: {e}")
            return web.json_response({"success": False, "error": str(e)}, status=500)

-    async def get_lora_notes(self, request: web.Request) -> web.Response:
-        """Get notes for a specific LoRA file"""
-        try:
-            lora_name = request.query.get("name")
-            if not lora_name:
-                return web.Response(text="Lora file name is required", status=400)
-
-            notes = await self.service.get_lora_notes(lora_name)
-            if notes is not None:
-                return web.json_response({"success": True, "notes": notes})
-            else:
-                return web.json_response(
-                    {"success": False, "error": "LoRA not found in cache"}, status=404
-                )
-
-        except Exception as e:
-            logger.error(f"Error getting lora notes: {e}", exc_info=True)
-            return web.json_response({"success": False, "error": str(e)}, status=500)
-
    async def get_lora_trigger_words(self, request: web.Request) -> web.Response:
        """Get trigger words for a specific LoRA file"""
        try:
@@ -168,52 +149,6 @@ class LoraRoutes(BaseModelRoutes):
            logger.error(f"Error getting lora usage tips by path: {e}", exc_info=True)
            return web.json_response({"success": False, "error": str(e)}, status=500)

-    async def get_lora_preview_url(self, request: web.Request) -> web.Response:
-        """Get the static preview URL for a LoRA file"""
-        try:
-            lora_name = request.query.get("name")
-            if not lora_name:
-                return web.Response(text="Lora file name is required", status=400)
-
-            preview_url = await self.service.get_lora_preview_url(lora_name)
-            if preview_url:
-                return web.json_response({"success": True, "preview_url": preview_url})
-            else:
-                return web.json_response(
-                    {
-                        "success": False,
-                        "error": "No preview URL found for the specified lora",
-                    },
-                    status=404,
-                )
-
-        except Exception as e:
-            logger.error(f"Error getting lora preview URL: {e}", exc_info=True)
-            return web.json_response({"success": False, "error": str(e)}, status=500)
-
-    async def get_lora_civitai_url(self, request: web.Request) -> web.Response:
-        """Get the Civitai URL for a LoRA file"""
-        try:
-            lora_name = request.query.get("name")
-            if not lora_name:
-                return web.Response(text="Lora file name is required", status=400)
-
-            result = await self.service.get_lora_civitai_url(lora_name)
-            if result["civitai_url"]:
-                return web.json_response({"success": True, **result})
-            else:
-                return web.json_response(
-                    {
-                        "success": False,
-                        "error": "No Civitai data found for the specified lora",
-                    },
-                    status=404,
-                )
-
-        except Exception as e:
-            logger.error(f"Error getting lora Civitai URL: {e}", exc_info=True)
-            return web.json_response({"success": False, "error": str(e)}, status=500)
-
    async def get_random_loras(self, request: web.Request) -> web.Response:
        """Get random LoRAs based on filters and strength ranges"""
        try:
@@ -337,7 +272,7 @@ class LoraRoutes(BaseModelRoutes):
                    graph_identifier = entry.get("graph_id")

                try:
-                    parsed_node_id = int(node_identifier)
+                    parsed_node_id = int(node_identifier)  # pyright: ignore[reportArgumentType]
                except (TypeError, ValueError):
                    parsed_node_id = node_identifier

@@ -5,7 +5,7 @@ miscellaneous endpoints share a consistent registration flow.
 """

 from dataclasses import dataclass
-from typing import Callable, Iterable, Mapping
+from typing import Any, Callable, Iterable, Mapping

 from aiohttp import web

@@ -22,6 +22,8 @@ class RouteDefinition:
 MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
    RouteDefinition("GET", "/api/lm/settings", "get_settings"),
    RouteDefinition("POST", "/api/lm/settings", "update_settings"),
+    RouteDefinition("GET", "/api/lm/llm/models", "get_llm_models"),
+    RouteDefinition("GET", "/api/lm/llm/provider-models", "get_provider_models"),
    RouteDefinition("GET", "/api/lm/doctor/diagnostics", "get_doctor_diagnostics"),
    RouteDefinition("POST", "/api/lm/doctor/repair-cache", "repair_doctor_cache"),
    RouteDefinition("POST", "/api/lm/doctor/resolve-filename-conflicts", "resolve_doctor_filename_conflicts"),
@@ -37,10 +39,12 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
    RouteDefinition("POST", "/api/lm/update-usage-stats", "update_usage_stats"),
    RouteDefinition("GET", "/api/lm/get-usage-stats", "get_usage_stats"),
    RouteDefinition("POST", "/api/lm/update-lora-code", "update_lora_code"),
+    RouteDefinition("GET", "/api/lm/update-lora-code", "get_update_lora_code"),
    RouteDefinition("GET", "/api/lm/trained-words", "get_trained_words"),
    RouteDefinition("GET", "/api/lm/model-example-files", "get_model_example_files"),
    RouteDefinition("POST", "/api/lm/register-nodes", "register_nodes"),
    RouteDefinition("POST", "/api/lm/update-node-widget", "update_node_widget"),
+    RouteDefinition("GET", "/api/lm/update-node-widget", "get_update_node_widget"),
    RouteDefinition("GET", "/api/lm/get-registry", "get_registry"),
    RouteDefinition("GET", "/api/lm/check-model-exists", "check_model_exists"),
    RouteDefinition("GET", "/api/lm/check-models-exist", "check_models_exist"),
@@ -101,6 +105,19 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
    RouteDefinition(
        "POST", "/api/lm/download-hf-model", "download_hf_model"
    ),
+    RouteDefinition(
+        "POST", "/api/lm/set-hf-url", "set_hf_url"
+    ),
+    # Agent skill endpoints
+    RouteDefinition(
+        "GET", "/api/lm/agent/skills", "get_agent_skills"
+    ),
+    RouteDefinition(
+        "POST", "/api/lm/agent/execute/{skill_name}", "execute_agent_skill"
+    ),
+    RouteDefinition(
+        "POST", "/api/lm/agent/cancel", "cancel_agent_skill"
+    ),
 )


@@ -130,7 +147,7 @@ class MiscRouteRegistrar:
                handler_lookup[definition.handler_name],
            )

-    def _bind(self, method: str, path: str, handler: Callable) -> None:
+    def _bind(self, method: str, path: str, handler: Callable[..., Any]) -> None:
        add_method_name = self._METHOD_MAP[method.upper()]
        add_method = getattr(self._app.router, add_method_name)
        add_method(path, handler)
@@ -7,7 +7,7 @@ import os
 from typing import Awaitable, Callable, Mapping

 from aiohttp import web
-from server import PromptServer  # type: ignore
+from server import PromptServer  # pyright: ignore[reportMissingImports]

 from ..services.metadata_service import (
    get_metadata_archive_manager,
@@ -40,6 +40,7 @@ from .handlers.misc_handlers import (
 )
 from .handlers.base_model_handlers import BaseModelHandlerSet
 from .handlers.hf_handlers import HfHandler
+from .handlers.agent_handlers import AgentHandler
 from .misc_route_registrar import MiscRouteRegistrar

 logger = logging.getLogger(__name__)
@@ -138,6 +139,7 @@ class MiscRoutes:
        example_workflows = ExampleWorkflowsHandler()
        base_model = BaseModelHandlerSet()
        hf_handler = HfHandler()
+        agent_handler = AgentHandler()

        return self._handler_set_factory(
            health=health,
@@ -158,6 +160,7 @@ class MiscRoutes:
            example_workflows=example_workflows,
            base_model=base_model,
            hf_handler=hf_handler,
+            agent_handler=agent_handler,
        )


@@ -3,7 +3,7 @@
 from __future__ import annotations

 from dataclasses import dataclass
-from typing import Callable, Iterable, Mapping
+from typing import Any, Callable, Iterable, Mapping

 from aiohttp import web

@@ -46,6 +46,7 @@ COMMON_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
        "GET", "/api/lm/{prefix}/auto-organize-progress", "get_auto_organize_progress"
    ),
    RouteDefinition("GET", "/api/lm/{prefix}/top-tags", "get_top_tags"),
+    RouteDefinition("GET", "/api/lm/{prefix}/search-tags", "search_tags"),
    RouteDefinition("GET", "/api/lm/{prefix}/base-models", "get_base_models"),
    RouteDefinition("GET", "/api/lm/{prefix}/model-types", "get_model_types"),
    RouteDefinition("GET", "/api/lm/{prefix}/scan", "scan_models"),
@@ -173,15 +174,15 @@ class ModelRouteRegistrar:
                handler_lookup[definition.handler_name],
            )

-    def add_route(self, method: str, path: str, handler: Callable) -> None:
+    def add_route(self, method: str, path: str, handler: Callable[..., Any]) -> None:
        self._bind_route(method, path, handler)

    def add_prefixed_route(
-        self, method: str, path_template: str, prefix: str, handler: Callable
+        self, method: str, path_template: str, prefix: str, handler: Callable[..., Any]
    ) -> None:
        self._bind_route(method, path_template.replace("{prefix}", prefix), handler)

-    def _bind_route(self, method: str, path: str, handler: Callable) -> None:
+    def _bind_route(self, method: str, path: str, handler: Callable[..., Any]) -> None:
        add_method_name = self._METHOD_MAP[method.upper()]
        add_method = getattr(self._app.router, add_method_name)
        add_method(path, handler)
@@ -0,0 +1,25 @@
+"""Route controller for the pending-delete undo endpoint."""
+
+from __future__ import annotations
+
+from aiohttp import web
+
+from .handlers.pending_delete_handler import PendingDeleteHandler
+
+
+class PendingDeleteRoutes:
+    """Shared route controller mirroring MiscRoutes/UpdateRoutes.
+
+    Registered ONCE per mode (py/lora_manager.py, standalone.py); NEVER through
+    the per-model-type ModelRouteRegistrar, which is instantiated per model
+    type and would register this non-prefixed route three times.
+    """
+
+    @staticmethod
+    def setup_routes(app: web.Application) -> None:
+        """Register the shared undo-delete endpoint."""
+        handler = PendingDeleteHandler()
+        _ = app.router.add_post("/api/lm/undo-delete", handler.undo_delete)
+
+
+__all__ = ["PendingDeleteRoutes"]
@@ -3,7 +3,7 @@
 from __future__ import annotations

 from dataclasses import dataclass
-from typing import Callable, Mapping
+from typing import Any, Callable, Mapping

 from aiohttp import web

@@ -29,6 +29,7 @@ ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
    RouteDefinition("POST", "/api/lm/recipes/save", "save_recipe"),
    RouteDefinition("DELETE", "/api/lm/recipe/{recipe_id}", "delete_recipe"),
    RouteDefinition("GET", "/api/lm/recipes/top-tags", "get_top_tags"),
+    RouteDefinition("GET", "/api/lm/recipes/search-tags", "search_tags"),
    RouteDefinition("GET", "/api/lm/recipes/base-models", "get_base_models"),
    RouteDefinition("GET", "/api/lm/recipes/roots", "get_roots"),
    RouteDefinition("GET", "/api/lm/recipes/folders", "get_folders"),
@@ -60,6 +61,11 @@ ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
    RouteDefinition("POST", "/api/lm/recipe/{recipe_id}/repair", "repair_recipe"),
    RouteDefinition("POST", "/api/lm/recipes/repair-bulk", "repair_recipes_bulk"),
    RouteDefinition("GET", "/api/lm/recipes/repair-progress", "get_repair_progress"),
+    RouteDefinition("POST", "/api/lm/recipes/rematch", "rematch_recipes"),
+    RouteDefinition("POST", "/api/lm/recipes/rematch-bulk", "rematch_recipes_bulk"),
+    RouteDefinition("POST", "/api/lm/recipe/{recipe_id}/rematch", "rematch_recipe"),
+    RouteDefinition("POST", "/api/lm/recipes/cancel-rematch", "cancel_rematch"),
+    RouteDefinition("GET", "/api/lm/recipes/rematch-progress", "get_rematch_progress"),
    RouteDefinition("POST", "/api/lm/recipes/batch-import/start", "start_batch_import"),
    RouteDefinition(
        "GET", "/api/lm/recipes/batch-import/progress", "get_batch_import_progress"
@@ -104,7 +110,7 @@ class RecipeRouteRegistrar:
            handler = handler_lookup[definition.handler_name]
            self._bind_route(definition.method, definition.path, handler)

-    def _bind_route(self, method: str, path: str, handler: Callable) -> None:
+    def _bind_route(self, method: str, path: str, handler: Callable[..., Any]) -> None:
        add_method_name = self._METHOD_MAP[method.upper()]
        add_method = getattr(self._app.router, add_method_name)
        add_method(path, handler)
@@ -40,10 +40,11 @@ class StatsRoutes:
    """Route handlers for Statistics page and API endpoints"""
    
    def __init__(self):
-        self.lora_scanner = None
-        self.checkpoint_scanner = None
-        self.embedding_scanner = None
-        self.usage_stats = None
+        self.lora_scanner: Any = None
+        self.checkpoint_scanner: Any = None
+        self.embedding_scanner: Any = None
+        self.usage_stats: Any = None
+        self._i18n_filter_added = False
        self.template_env = jinja2.Environment(
            loader=jinja2.FileSystemLoader(config.templates_path),
            autoescape=True
@@ -95,9 +96,9 @@ class StatsRoutes:
            server_i18n.set_locale(user_language)
            
            # 为模板环境添加i18n过滤器
-            if not hasattr(self.template_env, '_i18n_filter_added'):
+            if not self._i18n_filter_added:
                self.template_env.filters['t'] = server_i18n.create_template_filter()
-                self.template_env._i18n_filter_added = True
+                self._i18n_filter_added = True

            template = self.template_env.get_template('statistics.html')
            rendered = template.render(
@@ -549,7 +550,7 @@ class StatsRoutes:
                'error': str(e)
            }, status=500)

-    def _count_unused_models(self, models: List[Dict], usage_data: Dict) -> int:
+    def _count_unused_models(self, models: List[Dict[str, Any]], usage_data: Dict[str, Any]) -> int:
        """Count models that have never been used"""
        used_hashes = set(usage_data.keys())
        unused_count = 0
@@ -560,7 +561,7 @@ class StatsRoutes:
                
        return unused_count

-    def _get_top_used_models(self, usage_data: Dict, model_map: Dict, limit: int) -> List[Dict]:
+    def _get_top_used_models(self, usage_data: Dict[str, Any], model_map: Dict[str, Any], limit: int) -> List[Dict[str, Any]]:
        """Get top used models with their metadata"""
        sorted_usage = sorted(usage_data.items(), key=lambda x: x[1].get('total', 0), reverse=True)
        
@@ -578,7 +579,7 @@ class StatsRoutes:
        
        return top_models

-    def _get_usage_timeline(self, usage_data: Dict, days: int) -> List[Dict]:
+    def _get_usage_timeline(self, usage_data: Dict[str, Any], days: int) -> List[Dict[str, Any]]:
        """Get usage timeline for the past N days"""
        timeline = []
        today = datetime.now()
@@ -614,7 +615,7 @@ class StatsRoutes:
        
        return list(reversed(timeline))  # Oldest to newest

-    def _format_size(self, size_bytes: int) -> str:
+    def _format_size(self, size_bytes: float) -> str:
        """Format file size in human readable format"""
        for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
            if size_bytes < 1024.0:
@@ -6,7 +6,7 @@ import shutil
 import tempfile
 import asyncio
 from aiohttp import web, ClientError
-from typing import Dict, List
+from typing import Any, Dict, List, cast

 from ..utils.settings_paths import ensure_settings_file
 from ..services.downloader import get_downloader
@@ -38,6 +38,84 @@ def _clean_excludes() -> List[str]:
    return excludes


+def _stage_preserved_items(plugin_root: str) -> tuple[str, list[str]]:
+    """Move preserved user-data items to a temp directory outside *plugin_root*.
+
+    This ensures that ``git reset --hard``, ``git clean -fd``, and ZIP-based
+    replacement cannot touch these files even when ``-e`` exclusion patterns
+    are mishandled (e.g. on Windows where forward-slash patterns may not
+    match backslash-prefixed paths in some Git builds, or where file locks
+    prevent deletion/recreation).
+
+    Returns:
+        ``(backup_root, staged_names)``: the temp directory path and the
+        list of item names that were successfully moved.
+    """
+    backup_root = tempfile.mkdtemp(prefix='lora_manager_update_')
+    staged: list[str] = []
+    for name in _PRESERVE_DIRS:
+        src = os.path.join(plugin_root, name)
+        if not os.path.lexists(src):
+            continue
+        dst = os.path.join(backup_root, name)
+        try:
+            shutil.move(src, dst)
+            staged.append(name)
+            logger.debug("Staged '%s' for update safety", name)
+        except OSError:
+            # ``shutil.move`` may fail on Windows if a file handle inside
+            # the directory is still open (e.g. a SQLite WAL file). Fall
+            # back to copy-then-remove.
+            logger.debug("Move failed for '%s', falling back to copy", name)
+            try:
+                if os.path.isdir(src) and not os.path.islink(src):
+                    shutil.copytree(src, dst, symlinks=True)
+                    shutil.rmtree(src, ignore_errors=True)
+                else:
+                    shutil.copy2(src, dst)
+                    os.remove(src)
+                staged.append(name)
+                logger.info("Copied (then removed) '%s' for update safety", name)
+            except Exception as exc:
+                logger.warning(
+                    "Could not stage '%s': %s (will rely on git -e / skip lists)", name, exc
+                )
+    return backup_root, staged
+
+
+def _restore_preserved_items(plugin_root: str, backup_root: str, staged: list[str]) -> None:
+    """Move staged items back from *backup_root* into *plugin_root*.
+
+    Any leftover placeholder at the destination (created by git checkout or
+    ZIP extraction) is removed before the move.
+    """
+    for name in staged:
+        src = os.path.join(backup_root, name)
+        dst = os.path.join(plugin_root, name)
+        try:
+            if os.path.lexists(dst):
+                if os.path.isdir(dst) and not os.path.islink(dst):
+                    shutil.rmtree(dst, ignore_errors=True)
+                else:
+                    os.remove(dst)
+            shutil.move(src, dst)
+            logger.debug("Restored '%s' after update", name)
+        except OSError:
+            logger.debug("Move failed restoring '%s', falling back to copy", name)
+            try:
+                if os.path.isdir(src) and not os.path.islink(src):
+                    shutil.copytree(src, dst, symlinks=True, dirs_exist_ok=True)
+                    shutil.rmtree(src, ignore_errors=True)
+                else:
+                    shutil.copy2(src, dst)
+                    os.remove(src)
+                logger.info("Copied '%s' back after update", name)
+            except Exception as exc:
+                logger.error("Failed to restore '%s': %s", name, exc)
+    shutil.rmtree(backup_root, ignore_errors=True)
+
+
+
 class UpdateRoutes:
    """Routes for handling plugin update checks"""
    
@@ -47,6 +125,7 @@ class UpdateRoutes:
        app.router.add_get('/api/lm/check-updates', UpdateRoutes.check_updates)
        app.router.add_get('/api/lm/version-info', UpdateRoutes.get_version_info)
        app.router.add_post('/api/lm/perform-update', UpdateRoutes.perform_update)
+        app.router.add_post('/api/lm/switch-channel', UpdateRoutes.switch_channel)
    
    @staticmethod
    async def check_updates(request):
@@ -65,10 +144,17 @@ class UpdateRoutes:

            # Fetch remote version from GitHub
            if nightly:
-                remote_version, changelog = await UpdateRoutes._get_nightly_version()
-                releases = None
+                local_hash = git_info.get('short_hash', '')
+                nightly_version, releases_result = await asyncio.gather(
+                    UpdateRoutes._get_nightly_version(local_hash),
+                    UpdateRoutes._get_remote_version()
+                )
+                remote_version, _, behind_by, commit_date = nightly_version
+                _, changelog, releases = releases_result
            else:
                remote_version, changelog, releases = await UpdateRoutes._get_remote_version()
+                behind_by = 0
+                commit_date = ''
            
            # Compare versions
            if nightly:
@@ -81,6 +167,10 @@ class UpdateRoutes:
                    remote_version.replace('v', '')
                )
            
+            current_dir = os.path.dirname(os.path.abspath(__file__))
+            plugin_root = os.path.dirname(os.path.dirname(current_dir))
+            has_git = os.path.exists(os.path.join(plugin_root, '.git'))
+
            response_data = {
                'success': True,
                'current_version': local_version,
@@ -88,13 +178,13 @@ class UpdateRoutes:
                'update_available': update_available,
                'changelog': changelog,
                'git_info': git_info,
-                'nightly': nightly
+                'nightly': nightly,
+                'has_git': has_git,
+                'releases': releases,
+                'behind_by': behind_by,
+                'commit_date': commit_date
            }
            
-            # Include releases list for stable mode
-            if releases is not None:
-                response_data['releases'] = releases
-            
            return web.json_response(response_data)
            
        except NETWORK_EXCEPTIONS as e:
@@ -126,9 +216,14 @@ class UpdateRoutes:
            # Format: version-short_hash
            version_string = f"{local_version}-{short_hash}"
            
+            current_dir = os.path.dirname(os.path.abspath(__file__))
+            plugin_root = os.path.dirname(os.path.dirname(current_dir))
+            has_git = os.path.exists(os.path.join(plugin_root, '.git'))
+
            return web.json_response({
                'success': True,
-                'version': version_string
+                'version': version_string,
+                'has_git': has_git
            })
            
        except Exception as e:
@@ -156,20 +251,22 @@ class UpdateRoutes:
            if os.path.exists(settings_path):
                with open(settings_path, 'r', encoding='utf-8') as f:
                    settings_backup = f.read()
-                logger.info("Backed up settings.json")
+                logger.debug("Backed up settings.json (%d bytes)", len(settings_backup))

-            git_folder = os.path.join(plugin_root, '.git')
-            if os.path.exists(git_folder):
-                # Git update
-                success, new_version = await UpdateRoutes._perform_git_update(plugin_root, nightly)
-            else:
-                # Fallback: Download ZIP and replace files
-                success, new_version = await UpdateRoutes._download_and_replace_zip(plugin_root)
+            staged_backup_dir, staged_items = _stage_preserved_items(plugin_root)
+            try:
+                git_folder = os.path.join(plugin_root, '.git')
+                if os.path.exists(git_folder):
+                    success, new_version = await UpdateRoutes._perform_git_update(plugin_root, nightly)
+                else:
+                    success, new_version = await UpdateRoutes._download_and_replace_zip(plugin_root)
+            finally:
+                _restore_preserved_items(plugin_root, staged_backup_dir, staged_items)

            if settings_backup and success:
                with open(settings_path, 'w', encoding='utf-8') as f:
                    f.write(settings_backup)
-                logger.info("Restored settings.json")
+                logger.debug("Restored settings.json content (%d bytes)", len(settings_backup))

            if success:
                return web.json_response({
@@ -190,6 +287,164 @@ class UpdateRoutes:
                'error': str(e)
            })

+    @staticmethod
+    async def switch_channel(request):
+        """
+        Switch between release and nightly update channels.
+
+        ZIP/CNR install → Nightly: git init + checkout main (one-way upgrade)
+        Git install → Release:   git checkout latest tag (.git preserved)
+        ZIP/CNR install → Release: ZIP download (no .git, stays in ZIP mode)
+        Git install → Nightly:   git checkout main + pull
+        """
+        try:
+            body = await request.json() if request.has_body else {}
+            channel = body.get('channel', '')
+
+            if channel not in ('release', 'nightly'):
+                return web.json_response({
+                    'success': False,
+                    'error': f'Invalid channel: {channel}. Must be "release" or "nightly".'
+                })
+
+            current_dir = os.path.dirname(os.path.abspath(__file__))
+            plugin_root = os.path.dirname(os.path.dirname(current_dir))
+
+            settings_path = ensure_settings_file(logger)
+            settings_backup = None
+            if os.path.exists(settings_path):
+                with open(settings_path, 'r', encoding='utf-8') as f:
+                    settings_backup = f.read()
+                logger.debug("Backed up settings.json before channel switch (%d bytes)", len(settings_backup))
+
+            staged_backup_dir, staged_items = _stage_preserved_items(plugin_root)
+            try:
+                git_folder = os.path.join(plugin_root, '.git')
+
+                if channel == 'nightly':
+                    git_backup = None
+                    if os.path.exists(git_folder):
+                        git_backup = UpdateRoutes._backup_git(git_folder, 'nightly')
+
+                    success = False
+                    new_version = ''
+                    try:
+                        if os.path.exists(git_folder):
+                            success, new_version = await UpdateRoutes._perform_git_update(
+                                plugin_root, nightly=True
+                            )
+                        else:
+                            success, new_version = UpdateRoutes._init_git_repo(plugin_root)
+                    finally:
+                        UpdateRoutes._restore_git(git_backup, git_folder, success, 'nightly')
+                else:
+                    success = False
+                    new_version = ''
+                    if os.path.exists(git_folder):
+                        success, new_version = await UpdateRoutes._perform_git_update(
+                            plugin_root, nightly=False
+                        )
+                    else:
+                        tracking_file = os.path.join(plugin_root, '.tracking')
+                        if os.path.exists(tracking_file):
+                            os.remove(tracking_file)
+                        success, new_version = await UpdateRoutes._download_and_replace_zip(plugin_root)
+            finally:
+                _restore_preserved_items(plugin_root, staged_backup_dir, staged_items)
+
+            if settings_backup and success:
+                with open(settings_path, 'w', encoding='utf-8') as f:
+                    f.write(settings_backup)
+                logger.debug("Restored settings.json content after channel switch (%d bytes)", len(settings_backup))
+
+            if success:
+                return web.json_response({
+                    'success': True,
+                    'channel': channel,
+                    'new_version': new_version,
+                    'message': f'Switched to {channel} channel'
+                })
+            else:
+                return web.json_response({
+                    'success': False,
+                    'error': f'Failed to switch to {channel} channel'
+                })
+
+        except Exception as e:
+            logger.error("Failed to switch channel: %s", e, exc_info=True)
+            return web.json_response({
+                'success': False,
+                'error': str(e)
+            })
+
+    @staticmethod
+    def _init_git_repo(plugin_root: str) -> tuple[bool, str]:
+        """
+        Initialize a Git repository in a ZIP-installed plugin folder.
+        Clones the remote history and checks out main branch.
+        """
+        try:
+            import git
+        except ImportError:
+            logger.error(
+                "GitPython is not available: cannot initialize git repo. "
+                "Install git or set $GIT_PYTHON_GIT_EXECUTABLE to the git binary path."
+            )
+            return False, ""
+
+        clean_excludes = _clean_excludes()
+
+        try:
+            repo = git.Repo.init(plugin_root)
+            origin = repo.create_remote(
+                'origin',
+                'https://github.com/willmiao/ComfyUI-Lora-Manager.git'
+            )
+            origin.fetch()
+
+            repo.create_head('main', origin.refs.main)
+            repo.git.checkout('main', '--force')
+            repo.git.reset('--hard')
+            repo.git.clean('-fd', *clean_excludes)
+
+            tracking_file = os.path.join(plugin_root, '.tracking')
+            if os.path.exists(tracking_file):
+                os.remove(tracking_file)
+                logger.info("Removed .tracking file (now in git mode)")
+
+            new_version = f"main-{repo.head.commit.hexsha[:7]}"
+            logger.info("Initialized git repo on main branch: %s", new_version)
+            return True, new_version
+
+        except Exception as e:
+            logger.error("Failed to initialize git repo: %s", e, exc_info=True)
+            return False, ""
+
+    @staticmethod
+    def _backup_git(git_folder, label):
+        try:
+            backup_dir = tempfile.mkdtemp()
+            backup = os.path.join(backup_dir, '.git')
+            shutil.copytree(git_folder, backup)
+            logger.info("Backed up .git before switching to %s", label)
+            return backup
+        except Exception as e:
+            logger.error("Failed to backup .git before %s switch: %s", label, e)
+            return None
+
+    @staticmethod
+    def _restore_git(git_backup, git_folder, success, label):
+        if git_backup and not success:
+            try:
+                if os.path.exists(git_folder):
+                    shutil.rmtree(git_folder)
+                shutil.copytree(git_backup, git_folder)
+                logger.info("Restored .git after failed %s switch", label)
+            except Exception as e:
+                logger.error("Failed to restore .git after %s switch: %s", label, e)
+        if git_backup:
+            shutil.rmtree(os.path.dirname(git_backup), ignore_errors=True)
+
    @staticmethod
    async def _download_and_replace_zip(plugin_root: str) -> tuple[bool, str]:
        """
@@ -212,9 +467,10 @@ class UpdateRoutes:
            if not success:
                logger.error(f"Failed to fetch release info: {data}")
                return False, ""
-            
-            zip_url = data.get("zipball_url")
-            version = data.get("tag_name", "unknown")
+
+            release_payload = cast(dict[str, Any], data)
+            zip_url = release_payload.get("zipball_url", "")
+            version = release_payload.get("tag_name", "unknown")

            # Download ZIP to temporary file
            with tempfile.NamedTemporaryFile(delete=False, suffix=".zip") as tmp_zip:
@@ -244,8 +500,7 @@ class UpdateRoutes:
            except Exception:
                logger.debug("Could not close downloaded-version history database", exc_info=True)

-            # Skip settings.json, civitai, model cache and runtime cache folders
-            UpdateRoutes._clean_plugin_folder(plugin_root, skip_files=['settings.json', 'civitai', 'model_cache', 'cache', 'wildcards', 'backups', 'stats'])
+            UpdateRoutes._clean_plugin_folder(plugin_root, skip_files=list(_PRESERVE_DIRS))

            # Extract ZIP to temp dir
            with tempfile.TemporaryDirectory() as tmp_dir:
@@ -255,7 +510,7 @@ class UpdateRoutes:
                    extracted_root = next(os.scandir(tmp_dir)).path

                    # Copy files, skipping user data that should be preserved
-                    skip_items = {'settings.json', 'civitai', 'wildcards', 'backups', 'stats'}
+                    skip_items = set(_PRESERVE_DIRS)
                    for item in os.listdir(extracted_root):
                        if item in skip_items:
                            continue
@@ -272,7 +527,7 @@ class UpdateRoutes:
                    # for ComfyUI Manager to work properly
                    tracking_info_file = os.path.join(plugin_root, '.tracking')
                    tracking_files = []
-                    skip_tracked = {'civitai', 'wildcards', 'backups', 'stats'}
+                    skip_tracked = set(_PRESERVE_DIRS) - {'settings.json'}
                    for root, dirs, files in os.walk(extracted_root):
                        # Skip user data directories and their contents
                        rel_root = os.path.relpath(root, extracted_root)
@@ -295,7 +550,8 @@ class UpdateRoutes:
        except Exception as e:
            logger.error(f"ZIP update failed: {e}", exc_info=True)
            return False, ""
-        
+
+    @staticmethod
    def _clean_plugin_folder(plugin_root, skip_files=None):
        skip_files = skip_files or []
        for item in os.listdir(plugin_root):
@@ -308,41 +564,56 @@ class UpdateRoutes:
                os.remove(path)
    
    @staticmethod
-    async def _get_nightly_version() -> tuple[str, List[str]]:
-        """
-        Fetch latest commit from main branch
-        """
+    async def _get_nightly_version(local_hash: str = "") -> tuple[str, List[str], int, str]:
        repo_owner = "willmiao"
        repo_name = "ComfyUI-Lora-Manager"
-        
-        # Use GitHub API to fetch the latest commit from main branch
+
        github_url = f"https://api.github.com/repos/{repo_owner}/{repo_name}/commits/main"
-        
+
        try:
            downloader = await get_downloader()
-            success, data = await downloader.make_request('GET', github_url, custom_headers={'Accept': 'application/vnd.github+json'})
-            
+            success, data = await downloader.make_request(
+                'GET', github_url,
+                custom_headers={'Accept': 'application/vnd.github+json'}
+            )
+
            if not success:
-                logger.warning(f"Failed to fetch GitHub commit: {data}")
-                return "main", []
-            
-            commit_sha = data.get('sha', '')[:7]  # Short hash
-            commit_message = data.get('commit', {}).get('message', '')
-            
-            # Format as "main-{short_hash}"
+                logger.warning("Failed to fetch GitHub commit: %s", data)
+                return "main", [], 0, ""
+
+            commit_payload = cast(dict[str, Any], data)
+            commit_sha = commit_payload.get('sha', '')[:7]
+            commit_message = commit_payload.get('commit', {}).get('message', '')
+            commit_date = commit_payload.get('commit', {}).get('committer', {}).get('date', '')[:10]
+
            version = f"main-{commit_sha}"
-            
-            # Use commit message as changelog
            changelog = [commit_message] if commit_message else []
-            
-            return version, changelog
-        
+
+            behind_by = 0
+            if local_hash and local_hash not in ('unknown', 'stable'):
+                compare_url = (
+                    f"https://api.github.com/repos/{repo_owner}/{repo_name}"
+                    f"/compare/{local_hash}...main"
+                )
+                c_ok, c_data = await downloader.make_request(
+                    'GET', compare_url,
+                    custom_headers={'Accept': 'application/vnd.github+json'}
+                )
+                if c_ok:
+                    compare_payload = cast(dict[str, Any], c_data)
+                    if compare_payload.get('status') in ('ahead', 'diverged'):
+                        behind_by = compare_payload.get('ahead_by', 0)
+                    else:
+                        behind_by = compare_payload.get('behind_by', 0)
+
+            return version, changelog, behind_by, commit_date
+
        except NETWORK_EXCEPTIONS as e:
            logger.warning("Unable to reach GitHub for nightly version: %s", e)
-            return "main", []
+            return "main", [], 0, ""
        except Exception as e:
-            logger.error(f"Error fetching nightly version: {e}", exc_info=True)
-            return "main", []
+            logger.error("Error fetching nightly version: %s", e, exc_info=True)
+            return "main", [], 0, ""
    
    @staticmethod
    def _compare_nightly_versions(local_git_info: Dict[str, str], remote_version: str) -> bool:
@@ -438,7 +709,7 @@ class UpdateRoutes:
            logger.info(f"Successfully updated to {new_version}")
            return True, new_version
            
-        except git.exc.GitError as e:
+        except git.exc.GitError as e:  # pyright: ignore[reportAttributeAccessIssue]
            logger.error(f"Git error during update: {e}")
            return False, ""
        except Exception as e:
@@ -499,7 +770,7 @@ class UpdateRoutes:
        return git_info
    
    @staticmethod
-    async def _get_remote_version() -> tuple[str, List[str], List[Dict]]:
+    async def _get_remote_version() -> tuple[str, List[str], List[Dict[str, Any]]]:
        """
        Fetch remote version from GitHub
        Returns:
@@ -521,7 +792,7 @@ class UpdateRoutes:
            
            # Parse releases
            releases = []
-            for i, release in enumerate(data):
+            for i, release in enumerate(cast(list[dict[str, Any]], data)):
                version = release.get('tag_name', '')
                if not version.startswith('v'):
                    version = f"v{version}"
@@ -0,0 +1,27 @@
+"""LLM-powered metadata enrichment pipeline infrastructure.
+
+This package provides the orchestration layer for LLM-powered features.
+Skills define *what* to do (prompt template).  The :class:`AgentService`
+handles *how* (LLM calls, context gathering, validation, progress).
+
+NOTE: The current implementation is a code-driven pipeline, not a true
+agent loop.  Future agent orchestration (LLM-driven tool selection) will
+live alongside this package with its own namespace.
+"""
+
+from __future__ import annotations
+
+from .skill_definition import SkillDefinition, SkillPermissions
+from .skill_registry import SkillRegistry
+from .agent_service import AgentService, AgentProgressReporter, SkillResult
+from .post_processor import PostProcessor
+
+__all__ = [
+    "AgentProgressReporter",
+    "AgentService",
+    "PostProcessor",
+    "SkillDefinition",
+    "SkillPermissions",
+    "SkillRegistry",
+    "SkillResult",
+]
@@ -0,0 +1,489 @@
+"""Pipeline orchestration service.
+
+The :class:`AgentService` coordinates LLM-powered pipeline execution:
+
+1. Look up the pipeline definition in :class:`SkillRegistry`
+2. Validate input against its ``input_schema``
+3. Prepare context via :mod:`~py.metadata_ops` (read metadata, list base models, fetch HF README)
+4. If ``llm_required``: call :class:`LLMService` with the rendered prompt
+5. Post-process via :class:`PostProcessor` (delegates I/O to :mod:`~py.metadata_ops`)
+6. Broadcast progress and completion via :class:`WebSocketManager`
+
+Pipeline definitions (*skills*) describe *what* to do (prompt template).
+The AgentService handles *how* (LLM calls, context gathering, validation,
+progress).
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import re
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+
+import aiohttp
+
+import os
+
+from ...config import config
+from ..llm_service import LLMService
+from ..websocket_manager import ws_manager
+from .post_processor import PostProcessor
+from .skill_registry import SkillRegistry
+from .skills.enrich_hf_metadata.readme_processor import (
+    clean_readme_for_llm,
+    extract_relevant_section,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class AgentProgressReporter:
+    """Protocol-compatible progress reporter backed by WebSocket broadcast."""
+
+    async def on_progress(self, payload: Dict[str, Any]) -> None:
+        await ws_manager.broadcast(payload)
+
+
+@dataclass
+class SkillResult:
+    """Outcome of a skill execution."""
+
+    success: bool
+    updated_models: List[Dict[str, Any]] = field(default_factory=list)
+    errors: List[str] = field(default_factory=list)
+    summary: str = ""
+
+
+def _validate_schema(data: Any, schema: Dict[str, Any], path: str = "") -> List[str]:
+    """Minimal JSON schema validator.
+
+    Supports a subset of JSON Schema: ``type``, ``properties``, ``required``,
+    ``items``, ``enum``.  Returns a list of error messages (empty = valid).
+    """
+
+    errors: List[str] = []
+    if not schema:
+        return errors
+
+    expected_type = schema.get("type")
+    if expected_type:
+        type_map = {
+            "string": str,
+            "number": (int, float),
+            "integer": int,
+            "boolean": bool,
+            "array": list,
+            "object": dict,
+            "null": type(None),
+        }
+        expected_py = type_map.get(expected_type)
+        if expected_py is not None and not isinstance(data, expected_py):
+            errors.append(f"{path or 'root'}: expected {expected_type}, got {type(data).__name__}")
+            return errors
+
+    if expected_type == "object" and isinstance(data, dict):
+        properties = schema.get("properties", {})
+        required = schema.get("required", [])
+        for req_key in required:
+            if req_key not in data:
+                errors.append(f"{path or 'root'}: missing required property '{req_key}'")
+        for key, value in data.items():
+            if key in properties:
+                errors.extend(_validate_schema(value, properties[key], f"{path}.{key}"))
+
+    if expected_type == "array" and isinstance(data, list):
+        items_schema = schema.get("items")
+        if items_schema:
+            for i, item in enumerate(data):
+                errors.extend(_validate_schema(item, items_schema, f"{path}[{i}]"))
+
+    if "enum" in schema and data not in schema["enum"]:
+        errors.append(f"{path or 'root'}: value '{data}' not in enum {schema['enum']}")
+
+    return errors
+
+
+# ------------------------------------------------------------------
+# Prompt template rendering
+# ------------------------------------------------------------------
+
+
+def _render_prompt(template: str, variables: Dict[str, Any]) -> str:
+    """Render a prompt template with ``{{variable}}`` placeholders.
+
+    Uses simple regex substitution — no Jinja2 dependency needed.
+    """
+
+    def replace(match: re.Match[str]) -> str:
+        key = match.group(1).strip()
+        value = variables.get(key, "")
+        if isinstance(value, (dict, list)):
+            return json.dumps(value, ensure_ascii=False, indent=2)
+        return str(value)
+
+    return re.sub(r"\{\{(\w+)\}\}", replace, template)
+
+
+class AgentService:
+    """Orchestrate agent skill execution.
+
+    Usage::
+
+        service = await AgentService.get_instance()
+        result = await service.execute_skill(
+            skill_name="enrich_hf_metadata",
+            input_data={"model_paths": ["/path/to/model.safetensors"]},
+            progress_callback=AgentProgressReporter(),
+        )
+    """
+
+    _instance: Optional["AgentService"] = None
+    _lock: asyncio.Lock = asyncio.Lock()
+
+    def __init__(
+        self,
+        *,
+        skill_registry: Optional[SkillRegistry] = None,
+        llm_service: Optional[LLMService] = None,
+    ) -> None:
+        self._registry = skill_registry
+        self._llm_service = llm_service
+
+    @classmethod
+    async def get_instance(cls) -> "AgentService":
+        """Return the lazily-initialised global ``AgentService``."""
+
+        if cls._instance is None:
+            async with cls._lock:
+                if cls._instance is None:
+                    cls._instance = cls(
+                        skill_registry=await SkillRegistry.get_instance(),
+                        llm_service=await LLMService.get_instance(),
+                    )
+        return cls._instance
+
+    @classmethod
+    def reset_instance(cls) -> None:
+        """Reset the cached singleton — primarily for tests."""
+
+        cls._instance = None
+
+    async def _ensure_registry(self) -> SkillRegistry:
+        if self._registry is None:
+            self._registry = await SkillRegistry.get_instance()
+        return self._registry
+
+    async def _ensure_llm(self) -> LLMService:
+        if self._llm_service is None:
+            self._llm_service = await LLMService.get_instance()
+        return self._llm_service
+
+    async def list_skills(self) -> List[Dict[str, Any]]:
+        """Return a JSON-serialisable list of available skills."""
+
+        registry = await self._ensure_registry()
+        return [
+            {
+                "name": s.name,
+                "title": s.title,
+                "description": s.description,
+                "llm_required": s.llm_required,
+                "model_type_filter": s.model_type_filter,
+            }
+            for s in registry.list_skills()
+        ]
+
+    async def execute_skill(
+        self,
+        *,
+        skill_name: str,
+        input_data: Dict[str, Any],
+        progress_callback: Optional[AgentProgressReporter] = None,
+    ) -> SkillResult:
+        """Execute a pipeline (skill) on the given models.
+
+        Args:
+            skill_name: Name of the pipeline to execute
+            input_data: Input validated against the pipeline's ``input_schema``
+            progress_callback: Optional WebSocket progress reporter
+
+        Returns:
+            :class:`SkillResult` with success status and updated model info
+        """
+
+        registry = await self._ensure_registry()
+        skill = registry.get_skill(skill_name)
+        if skill is None:
+            return SkillResult(
+                success=False,
+                errors=[f"Skill not found: {skill_name}"],
+                summary=f"Skill '{skill_name}' does not exist",
+            )
+
+        input_errors = _validate_schema(input_data, skill.input_schema)
+        if input_errors:
+            return SkillResult(
+                success=False,
+                errors=input_errors,
+                summary=f"Invalid input: {'; '.join(input_errors)}",
+            )
+
+        model_paths = input_data.get("model_paths", [])
+        if not model_paths:
+            return SkillResult(
+                success=False,
+                errors=["No model_paths provided"],
+                summary="No models to process",
+            )
+
+        total = len(model_paths)
+        processed = 0
+        success_count = 0
+        skipped_count = 0
+        updated_models: List[Dict[str, Any]] = []
+        errors: List[str] = []
+        post_processor = PostProcessor()
+
+        await self._emit_progress(
+            progress_callback, skill_name, status="started",
+            total=total, processed=0, success=0,
+        )
+
+        llm = await self._ensure_llm()
+        llm_configured = llm.is_configured() if skill.llm_required else True
+
+        for model_path in model_paths:
+            model_filename = os.path.basename(model_path)
+            logger.info(
+                "[%s] [%d/%d] %s",
+                skill_name, processed + 1, total, model_filename,
+            )
+            updated_data: Dict[str, Any] = {}
+            skip_model = False
+            try:
+                from ...metadata_ops import read_metadata
+                metadata = await read_metadata(model_path)
+
+                # Fast-fail: enrich_hf_metadata requires hf_url to have HF README context
+                if skill_name == "enrich_hf_metadata" and not metadata.get("hf_url", ""):
+                    logger.info(
+                        "[%s] SKIP %s — no hf_url in metadata",
+                        skill_name, model_filename,
+                    )
+                    skipped_count += 1
+                    skip_model = True
+
+                if not skip_model:
+                    prompt_vars: Dict[str, Any] = {"model_path": model_path}
+                    if skill.llm_required and llm_configured:
+                        prompt_vars = await self._build_prompt_context(
+                            skill_name, model_path, metadata, registry, llm,
+                        )
+
+                    llm_response: Optional[Dict[str, Any]] = None
+                    if skill.llm_required and llm_configured:
+                        prompt_template = registry.load_prompt(skill_name)
+                        rendered = _render_prompt(prompt_template, prompt_vars)
+                        llm_response = await llm.chat_completion_json(
+                            system_prompt=prompt_vars.get(
+                                "system_prompt",
+                                "You are a helpful assistant that extracts structured metadata.",
+                            ),
+                            user_prompt=rendered,
+                        )
+                        if llm_response:
+                            logger.info(
+                                "[%s] [%d/%d] %s → base_model=%s confidence=%s",
+                                skill_name, processed + 1, total, model_filename,
+                                (llm_response.get("base_model") or "?")[:50],
+                                llm_response.get("confidence", "?"),
+                            )
+
+                    model_result = await post_processor.process(
+                        skill_name=skill_name,
+                        model_path=model_path,
+                        llm_output=llm_response or {},
+                        metadata=metadata,
+                        readme_content=prompt_vars.get("readme_content_full", ""),
+                    )
+
+                    if model_result.get("success", True):
+                        success_count += 1
+                        uf = model_result.get("updated_fields", [])
+                        if uf:
+                            updated_models.append({"path": model_path, "updated_fields": uf})
+                        updated_data = model_result.get("updates", {})
+                        if "preview_url" in updated_data and updated_data["preview_url"]:
+                            updated_data["preview_url"] = config.get_preview_static_url(
+                                updated_data["preview_url"]
+                            )
+                    else:
+                        errors.extend(
+                            model_result.get("errors", [model_result.get("error", "Unknown error")])
+                        )
+
+            except Exception as exc:
+                logger.error("Skill %s failed for %s: %s", skill_name, model_path, exc)
+                errors.append(f"{model_path}: {exc}")
+
+            processed += 1
+            await self._emit_progress(
+                progress_callback, skill_name, status="processing",
+                total=total, processed=processed, success=success_count,
+                skipped=skipped_count,
+                current_path=model_path,
+                updated_data=updated_data,
+            )
+
+        result = SkillResult(
+            success=success_count > 0,
+            updated_models=updated_models,
+            errors=errors,
+            summary=f"Processed {processed}/{total} models, {success_count} succeeded, {skipped_count} skipped",
+        )
+
+        await self._emit_progress(
+            progress_callback, skill_name, status="completed",
+            total=total, processed=processed, success=success_count,
+            skipped=skipped_count,
+            updated_models=updated_models, errors=errors, summary=result.summary,
+        )
+
+        return result
+
+    # ------------------------------------------------------------------
+    # Base model grouping (keeps the prompt compact)
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _format_base_models(models: List[str]) -> str:
+        """Format the base model list as a flat, one-per-line list.
+
+        Attempts to group by family consistently degraded LLM extraction
+        accuracy — the LLM finds individual model names harder to spot
+        in comma-separated groups than in a simple ``- Name`` list.
+        """
+        return "\n".join(f"- {m}" for m in models)
+
+    async def _build_prompt_context(
+        self,
+        skill_name: str,
+        model_path: str,
+        metadata: Dict[str, Any],
+        registry: SkillRegistry,
+        llm: Any,
+    ) -> Dict[str, Any]:
+        """Gather variables for the skill's prompt template.
+
+        Reads metadata, fetches the HF README (if applicable), lists available
+        base models, loads user priority tags, and returns a dict that maps to
+        ``{{variable}}`` placeholders in ``prompt.md``.
+        """
+        from ...metadata_ops import identify_model_type, list_base_models
+        from ..settings_manager import SettingsManager
+
+        context: Dict[str, Any] = {
+            "model_path": model_path,
+            "model_basename": "",
+            "hf_url": "",
+            "repo": "",
+            "readme_content": "",
+            "readme_content_full": "",
+            "current_metadata": {},
+            "base_models": [],
+            "priority_tags": "",
+        }
+
+        # Extract model basename (filename without extension) for the LLM
+        # to use when locating the matching section in collection repos.
+        raw_basename = os.path.splitext(os.path.basename(model_path))[0]
+        context["model_basename"] = raw_basename or ""
+
+        context["current_metadata"] = {
+            "file_name": metadata.get("file_name", ""),
+            "base_model": metadata.get("base_model", ""),
+            "tags": metadata.get("tags", []),
+            "modelDescription": metadata.get("modelDescription", ""),
+            "trainedWords": metadata.get("trainedWords", []),
+            "sha256": (metadata.get("sha256") or "")[:16] + "..." if metadata.get("sha256") else "",
+            "size": metadata.get("size", 0),
+        }
+
+        hf_url = metadata.get("hf_url", "")
+        context["hf_url"] = hf_url
+        repo = self._extract_repo_from_url(hf_url) if hf_url else ""
+        context["repo"] = repo or ""
+        if repo:
+            readme = await self._fetch_readme(repo)
+            # Trim README to the section relevant to this model file
+            # (collection repos often have multiple models in one README).
+            if readme and raw_basename:
+                trimmed = extract_relevant_section(readme, raw_basename)
+                cleaned = clean_readme_for_llm(trimmed) if trimmed else ""
+            else:
+                cleaned = clean_readme_for_llm(readme) if readme else ""
+            context["readme_content"] = cleaned if cleaned else "(README not available)"
+            context["readme_content_full"] = readme or ""
+
+        try:
+            raw_models = await list_base_models()
+            context["base_models"] = self._format_base_models(raw_models)
+        except Exception as exc:
+            logger.debug("Failed to list base models: %s", exc)
+            context["base_models"] = "</not available>"
+
+        # Determine model type and load the corresponding priority_tags
+        try:
+            model_type = await identify_model_type(model_path)
+            context["model_type"] = model_type
+            settings = SettingsManager()
+            priority_config = settings.get_priority_tag_config()
+            context["priority_tags"] = priority_config.get(model_type, "")
+        except Exception as exc:
+            logger.debug("Failed to load priority tags: %s", exc)
+            context["model_type"] = "lora"
+            context["priority_tags"] = ""
+
+        return context
+
+    @staticmethod
+    def _extract_repo_from_url(hf_url: str) -> Optional[str]:
+        """Extract ``user/repo`` from a HuggingFace URL."""
+        if not hf_url:
+            return None
+        m = re.match(r"https?://huggingface\.co/([^/]+/[^/]+)", hf_url)
+        return m.group(1) if m else None
+
+    @staticmethod
+    async def _fetch_readme(repo: str) -> str:
+        """Fetch README.md from HuggingFace (tries ``main``, then ``master``)."""
+        async with aiohttp.ClientSession(
+            headers={"User-Agent": "ComfyUI-LoRA-Manager/1.0"},
+            timeout=aiohttp.ClientTimeout(total=30),
+        ) as session:
+            for branch in ("main", "master"):
+                url = f"https://huggingface.co/{repo}/raw/{branch}/README.md"
+                try:
+                    async with session.get(url) as resp:
+                        if resp.status == 200:
+                            return await resp.text()
+                except Exception as exc:
+                    logger.debug("Failed to fetch README from %s: %s", url, exc)
+        return ""
+
+    async def _emit_progress(
+        self,
+        callback: Optional[AgentProgressReporter],
+        skill_name: str,
+        *,
+        status: str,
+        **extra: Any,
+    ) -> None:
+        """Send a progress update via WebSocket (if callback is set)."""
+        payload: Dict[str, Any] = {"type": "agent_progress", "skill": skill_name, "status": status}
+        payload.update(extra)
+        if callback is not None:
+            await callback.on_progress(payload)
@@ -0,0 +1,336 @@
+"""Post-processing engine for skill pipeline outputs.
+
+The :class:`PostProcessor` takes the LLM's structured JSON output and applies
+it to a model's on-disk metadata via the :mod:`~py.metadata_ops` functions.
+
+It handles all the skill-specific business logic — conditions, transformations,
+and orchestration of multiple side-effects (write metadata, download preview,
+refresh cache).  All actual I/O is delegated to :mod:`~py.metadata_ops`.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import re
+from datetime import datetime, timezone
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class PostProcessor:
+    """Deterministic post-processor for skill pipeline outputs.
+
+    Usage (called by :class:`~py.services.agent.agent_service.AgentService`)::
+
+        processor = PostProcessor()
+        result = await processor.process(
+            skill_name="enrich_hf_metadata",
+            model_path="/path/to/model.safetensors",
+            llm_output={...},
+            metadata={...},    # from metadata_ops.read_metadata()
+        )
+    """
+
+    async def process(
+        self,
+        *,
+        skill_name: str,
+        model_path: str,
+        llm_output: Dict[str, Any],
+        metadata: Dict[str, Any],
+        readme_content: str = "",
+    ) -> Dict[str, Any]:
+        """Route *llm_output* to the correct skill post-processor.
+
+        *readme_content* is optional raw markdown content (e.g. HF README)
+        that is converted to HTML and stored as ``modelDescription`` for
+        the description tab.
+
+        Returns a dict with keys ``success`` (bool), ``updated_fields`` (list),
+        ``preview_downloaded`` (bool), and ``errors`` (list).
+        """
+        if skill_name == "enrich_hf_metadata":
+            return await self._process_enrich_hf_metadata(
+                model_path, llm_output, metadata, readme_content,
+            )
+        return {
+            "success": False,
+            "updated_fields": [],
+            "errors": [f"No post-processor registered for skill: {skill_name}"],
+        }
+
+    # ------------------------------------------------------------------
+    # enrich_hf_metadata
+    # ------------------------------------------------------------------
+
+    async def _process_enrich_hf_metadata(
+        self,
+        model_path: str,
+        llm_output: Dict[str, Any],
+        metadata: Dict[str, Any],
+        readme_content: str = "",
+    ) -> Dict[str, Any]:
+        from ...metadata_ops import (
+            apply_metadata_updates,
+            download_preview,
+            refresh_cache,
+        )
+        from .skills.enrich_hf_metadata.readme_processor import (
+            convert_readme_to_html,
+            extract_gallery_images,
+            extract_gallery_table_images,
+            extract_relevant_section,
+            extract_simple_markdown_images,
+            extract_html_img_tags,
+            extract_repo_from_hf_url,
+        )
+
+        updated_fields: List[str] = []
+        preview_downloaded = False
+
+        # -- Determine whether this is an HF-sourced model -----------------
+        is_hf_model = not metadata.get("from_civitai", True)
+
+        # -- Collect updates -----------------------------------------------
+        updates: Dict[str, Any] = {}
+
+        # base_model
+        new_base = (llm_output.get("base_model") or "").strip()
+        current_base = metadata.get("base_model", "") or ""
+        if new_base and self._should_overwrite(current_base, is_hf_model):
+            updates["base_model"] = new_base
+
+        # trigger words → civitai.trainedWords
+        new_triggers = llm_output.get("trigger_words", [])
+        trigger_words_empty = True
+        if isinstance(new_triggers, list):
+            cleaned = [t.strip() for t in new_triggers if t.strip()]
+            cleaned = [t for t in cleaned if t.lower() not in ("none", "null", "n/a")]
+            trigger_words_empty = not cleaned
+            current_civitai = metadata.get("civitai") or {}
+            current_triggers = current_civitai.get("trainedWords") or []
+            if self._should_overwrite_list(current_triggers, is_hf_model):
+                trig_civitai = dict(current_civitai)
+                if "civitai" in updates and isinstance(updates["civitai"], dict):
+                    trig_civitai.update(updates["civitai"])
+                trig_civitai["trainedWords"] = cleaned
+                updates["civitai"] = trig_civitai
+
+        # modelDescription — from raw README content (converted to HTML)
+        if readme_content and is_hf_model:
+            converted = convert_readme_to_html(readme_content)
+            if converted:
+                updates["modelDescription"] = converted
+
+        # short_description → civitai.description (for "About this version")
+        short_desc = (llm_output.get("short_description") or "").strip()
+        if short_desc and is_hf_model:
+            current_civitai = metadata.get("civitai") or {}
+            desc_civitai = dict(current_civitai)
+            if "civitai" in updates and isinstance(updates["civitai"], dict):
+                desc_civitai.update(updates["civitai"])
+            desc_civitai["description"] = short_desc
+            updates["civitai"] = desc_civitai
+
+        # gallery images → civitai.images (from YAML frontmatter widget entries
+        # and Sample Gallery markdown tables in the README body)
+        gallery_images: List[Dict[str, Any]] = []
+        if readme_content and is_hf_model:
+            hf_url = metadata.get("hf_url", "") or ""
+            repo = extract_repo_from_hf_url(hf_url)
+            if repo:
+                rec_w = llm_output.get("recommended_width") or 0
+                rec_h = llm_output.get("recommended_height") or 0
+
+                # 1. Widget images (YAML frontmatter)
+                gallery = extract_gallery_images(
+                    readme_content, repo,
+                    default_width=rec_w, default_height=rec_h,
+                )
+
+                # 2. Sample Gallery table images (markdown body), deduplicated
+                existing_urls = {img["url"] for img in gallery if img.get("url")}
+                table_images = extract_gallery_table_images(
+                    readme_content, repo,
+                    existing_urls=existing_urls,
+                    default_width=rec_w, default_height=rec_h,
+                )
+                existing_urls.update(img["url"] for img in table_images if img.get("url"))
+
+                # 3. Simple markdown images `![alt](url)` in the body
+                simple_images = extract_simple_markdown_images(
+                    readme_content, repo,
+                    existing_urls=existing_urls,
+                    default_width=rec_w, default_height=rec_h,
+                )
+                existing_urls.update(img["url"] for img in simple_images if img.get("url"))
+
+                # 4. HTML `<img>` tags (used by many collection repos)
+                html_images = extract_html_img_tags(
+                    readme_content, repo,
+                    existing_urls=existing_urls,
+                    default_width=rec_w, default_height=rec_h,
+                )
+
+                all_images = gallery + table_images + simple_images + html_images
+                if all_images:
+                    gallery_images = all_images
+                    current_civitai = metadata.get("civitai") or {}
+                    gallery_civitai = dict(current_civitai)
+                    if "civitai" in updates and isinstance(updates["civitai"], dict):
+                        gallery_civitai.update(updates["civitai"])
+                    gallery_civitai["images"] = all_images
+                    updates["civitai"] = gallery_civitai
+
+        # tags
+        new_tags = llm_output.get("tags", [])
+        if isinstance(new_tags, list) and new_tags:
+            existing_tags = metadata.get("tags") or []
+            merged = self._merge_tags(existing_tags, new_tags)
+            if len(merged) > len(existing_tags) or is_hf_model:
+                updates["tags"] = merged
+
+        # metadata_source & llm_enriched_at (always set)
+        updates["metadata_source"] = "agent:enrich_hf_metadata"
+        updates["llm_enriched_at"] = datetime.now(timezone.utc).isoformat()
+
+        # Store LLM confidence in metadata so it's accessible for evaluation
+        raw_confidence = (llm_output.get("confidence") or "").strip()
+        if raw_confidence:
+            updates["_llm_confidence"] = raw_confidence
+
+        # Fallback: extract instance_prompt from YAML frontmatter when the LLM
+        # returned empty trigger words but the README has instance_prompt.
+        if trigger_words_empty:
+            instance_prompt = _extract_yaml_instance_prompt(readme_content)
+            if instance_prompt:
+                current_civitai = metadata.get("civitai") or {}
+                trig_civitai = dict(current_civitai)
+                if "civitai" in updates and isinstance(updates["civitai"], dict):
+                    trig_civitai.update(updates["civitai"])
+                trig_civitai["trainedWords"] = [instance_prompt]
+                updates["civitai"] = trig_civitai
+
+        preview_remote_url = (llm_output.get("preview_url") or "").strip()
+        # Fallback: if the LLM couldn't find a preview image in the cleaned
+        # README, find the first gallery image from the *model-specific
+        # section* of the README (not the repo-wide first image, which
+        # belongs to a different model in collection repos).
+        if not preview_remote_url and readme_content and is_hf_model:
+            model_basename = os.path.splitext(os.path.basename(model_path))[0]
+            relevant_section = extract_relevant_section(
+                readme_content, model_basename,
+            )
+            if relevant_section and relevant_section != readme_content:
+                for img in gallery_images:
+                    img_url = img.get("url", "")
+                    if img_url and img_url in relevant_section:
+                        preview_remote_url = img_url
+                        break
+        # Last resort: use the first gallery image from the full README.
+        if not preview_remote_url and gallery_images:
+            preview_remote_url = gallery_images[0].get("url", "")
+        current_preview = metadata.get("preview_url") or ""
+        if preview_remote_url and not (current_preview and os.path.exists(current_preview)):
+            local_path = await download_preview(model_path, preview_remote_url)
+            if local_path:
+                preview_downloaded = True
+                updates["preview_url"] = local_path
+
+        # notes — plain-text summary of usage info from the LLM
+        new_notes = (llm_output.get("notes") or "").strip()
+        if new_notes:
+            updates["notes"] = new_notes
+
+        # usage_tips — JSON string (e.g. {"strength_min":0.85,"strength_max":1.4})
+        raw_tips = (llm_output.get("usage_tips") or "").strip()
+        if raw_tips and raw_tips != "{}":
+            try:
+                json.loads(raw_tips)
+                updates["usage_tips"] = raw_tips
+            except (json.JSONDecodeError, TypeError):
+                logger.warning(
+                    "LLM returned invalid usage_tips JSON: %s", raw_tips[:200]
+                )
+
+        if updates:
+            updated_fields = await apply_metadata_updates(model_path, updates)
+
+        # -- Refresh scanner cache ------------------------------------------
+        if updated_fields or preview_downloaded:
+            await refresh_cache(model_path)
+
+        return {
+            "success": True,
+            "updated_fields": updated_fields,
+            "preview_downloaded": preview_downloaded,
+            "updates": updates,
+            "errors": [],
+        }
+
+    # ------------------------------------------------------------------
+    # Helpers
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _should_overwrite(current_value: str, is_hf_model: bool) -> bool:
+        """Return ``True`` when a scalar field should be overwritten."""
+        return is_hf_model or not current_value or current_value.lower() in (
+            "", "unknown",
+        )
+
+    @staticmethod
+    def _should_overwrite_list(current_list: List[str], is_hf_model: bool) -> bool:
+        """Return ``True`` when a list field should be overwritten."""
+        return is_hf_model or not current_list
+
+    @staticmethod
+    def _merge_tags(existing: List[str], new: List[str]) -> List[str]:
+        """Merge *new* tags into *existing*, all lowercased.
+
+        This matches the behaviour of :class:`TagUpdateService` which
+        normalises every tag to lowercase for case-insensitive dedup.
+        """
+        merged: List[str] = []
+        seen: set[str] = set()
+        for tag in list(existing) + list(new):
+            t = tag.strip().lower()
+            if t and t not in seen:
+                merged.append(t)
+                seen.add(t)
+        return merged
+
+
+# ------------------------------------------------------------------
+# Module-level helpers
+# ------------------------------------------------------------------
+
+
+def _extract_yaml_instance_prompt(readme_content: str) -> str:
+    """Extract ``instance_prompt`` from the YAML frontmatter of a HF README.
+
+    Returns the prompt text, or empty string if not found.  Handles
+    ``null`` / ``~`` YAML null values by returning empty string.
+    """
+    if not readme_content or not readme_content.startswith("---"):
+        return ""
+
+    # Find end of frontmatter
+    end = readme_content.find("---", 3)
+    if end == -1:
+        return ""
+    frontmatter = readme_content[3:end]
+
+    for line in frontmatter.split("\n"):
+        line = line.strip()
+        m = re.match(r"^instance_prompt:\s*(.*)", line)
+        if m:
+            val = m.group(1).strip().strip('"').strip("'")
+            if val.lower() in ("null", "~", "none", ""):
+                return ""
+            return val
+
+    return ""
@@ -0,0 +1,45 @@
+"""Skill definition data structures.
+
+Each skill is described by a :class:`SkillDefinition` that declares its
+input/output schemas, whether it needs an LLM call, and what permissions
+its post-processor has.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Tuple
+
+
+@dataclass(frozen=True)
+class SkillPermissions:
+    """Declarative permission scope for a skill's post-processor.
+
+    These are auditable constraints — the :class:`AgentService` checks them
+    before invoking the handler.  They are defense-in-depth, not a sandbox.
+    """
+
+    write_metadata: bool = True
+    write_previews: bool = True
+    network_domains: Tuple[str, ...] = ()
+
+
+@dataclass(frozen=True)
+class SkillDefinition:
+    """Immutable description of an agent skill."""
+
+    name: str
+    title: str
+    description: str
+    llm_required: bool
+    input_schema: Dict[str, Any] = field(default_factory=dict)
+    output_schema: Dict[str, Any] = field(default_factory=dict)
+    model_type_filter: Optional[List[str]] = None
+    permissions: SkillPermissions = field(default_factory=SkillPermissions)
+
+    def applies_to_model_type(self, model_type: str) -> bool:
+        """Return ``True`` if this skill can run on the given model type."""
+
+        if self.model_type_filter is None:
+            return True
+        return model_type in self.model_type_filter
@@ -0,0 +1,210 @@
+"""Discovery and loading of prompt-based skills.
+
+Skills live in ``py/services/agent/skills/<name>/`` directories.  Each
+directory must contain a ``prompt.md`` file with YAML frontmatter::
+
+    ---
+    name: my_skill
+    title: "My Skill"
+    description: "What this skill does"
+    llm_required: true
+    ---
+
+    Prompt template with ``{{variable}}`` placeholders.
+
+Legacy ``SKILL.md`` files are also supported for backward compatibility.
+
+The registry scans the skills directory on first access and caches results.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import re
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+import yaml
+
+from .skill_definition import SkillDefinition, SkillPermissions
+
+logger = logging.getLogger(__name__)
+
+# Directory where built-in skills are stored
+_SKILLS_DIR = Path(__file__).parent / "skills"
+
+#: Preferred file names for prompt definition files (tried in order).
+#: ``prompt.md`` is the current convention; ``SKILL.md`` is the legacy name
+#: kept for backward compatibility.
+_PROMPT_FILE_NAMES: tuple[str, ...] = ("prompt.md", "SKILL.md")
+
+
+# ---------------------------------------------------------------------------
+# Frontmatter parser
+# ---------------------------------------------------------------------------
+
+_FRONTMATTER_RE = re.compile(
+    r"^---\s*\n(.*?\n)---\s*\n?(.*)", re.DOTALL
+)
+
+
+def _parse_skill_file(path: Path) -> tuple[dict[str, Any], str]:
+    """Read a prompt definition file (``prompt.md`` or legacy ``SKILL.md``) and
+    return (frontmatter_dict, body_text).
+
+    Raises ``ValueError`` if the file lacks valid YAML frontmatter.
+    """
+    text = path.read_text(encoding="utf-8")
+    m = _FRONTMATTER_RE.match(text)
+    if not m:
+        raise ValueError(f"Missing or invalid YAML frontmatter in {path}")
+    frontmatter = yaml.safe_load(m.group(1))
+    if not isinstance(frontmatter, dict):
+        raise ValueError(f"Frontmatter in {path} is not a mapping")
+    body = m.group(2).strip()
+    return frontmatter, body
+
+
+class SkillRegistry:
+    """Discover and load agent skills from the filesystem."""
+
+    _instance: Optional["SkillRegistry"] = None
+    _lock: asyncio.Lock = asyncio.Lock()
+
+    def __init__(self, skills_dir: Path = _SKILLS_DIR) -> None:
+        self._skills_dir = skills_dir
+        self._skills: Dict[str, SkillDefinition] = {}
+        self._loaded: bool = False
+
+    # ------------------------------------------------------------------
+    # Singleton access
+    # ------------------------------------------------------------------
+
+    @classmethod
+    async def get_instance(cls) -> "SkillRegistry":
+        """Return the lazily-initialised global ``SkillRegistry``."""
+
+        if cls._instance is None:
+            async with cls._lock:
+                if cls._instance is None:
+                    registry = cls()
+                    registry._discover()
+                    cls._instance = registry
+        return cls._instance
+
+    @classmethod
+    def reset_instance(cls) -> None:
+        """Reset the cached singleton — primarily for tests."""
+
+        cls._instance = None
+
+    # ------------------------------------------------------------------
+    # Discovery
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _find_prompt_file(skill_dir: Path) -> Path | None:
+        """Return the first prompt definition file that exists in *skill_dir*.
+
+        Tries ``_PROMPT_FILE_NAMES`` in order so that new conventions
+        (``prompt.md``) take precedence while legacy ``SKILL.md`` files
+        still load without changes.
+        """
+        for name in _PROMPT_FILE_NAMES:
+            candidate = skill_dir / name
+            if candidate.exists():
+                return candidate
+        return None
+
+    def _discover(self) -> None:
+        """Scan the skills directory and load all valid skill definitions."""
+
+        self._skills.clear()
+        if not self._skills_dir.is_dir():
+            logger.warning("Skills directory does not exist: %s", self._skills_dir)
+            self._loaded = True
+            return
+
+        for entry in sorted(self._skills_dir.iterdir()):
+            if not entry.is_dir():
+                continue
+            prompt_file = self._find_prompt_file(entry)
+            if prompt_file is None:
+                continue
+            try:
+                definition = self._load_skill_definition(prompt_file)
+                if definition is not None:
+                    self._skills[definition.name] = definition
+                    logger.debug("Loaded skill: %s", definition.name)
+            except Exception as exc:
+                logger.warning("Failed to load skill from %s: %s", prompt_file, exc)
+
+        self._loaded = True
+        logger.info("Discovered %d prompt-based skills", len(self._skills))
+
+    def _load_skill_definition(self, path: Path) -> Optional[SkillDefinition]:
+        """Parse a prompt definition file's frontmatter into a
+        :class:`SkillDefinition`."""
+
+        try:
+            data, _body = _parse_skill_file(path)
+        except (ValueError, yaml.YAMLError) as exc:
+            logger.warning("Failed to parse prompt file %s: %s", path, exc)
+            return None
+
+        if "name" not in data:
+            logger.warning("Prompt file %s missing required 'name' field", path)
+            return None
+
+        perm_data = data.get("permissions", {})
+        permissions = SkillPermissions(
+            write_metadata=perm_data.get("write_metadata", True),
+            write_previews=perm_data.get("write_previews", True),
+            network_domains=tuple(perm_data.get("network_domains", [])),
+        )
+
+        return SkillDefinition(
+            name=data["name"],
+            title=data.get("title", data["name"]),
+            description=data.get("description", ""),
+            llm_required=data.get("llm_required", False),
+            input_schema=data.get("input_schema", {}),
+            output_schema=data.get("output_schema", {}),
+            model_type_filter=data.get("model_type_filter"),
+            permissions=permissions,
+        )
+
+    # ------------------------------------------------------------------
+    # Public API
+    # ------------------------------------------------------------------
+
+    def list_skills(self) -> List[SkillDefinition]:
+        """Return all discovered skill definitions."""
+
+        if not self._loaded:
+            self._discover()
+        return list(self._skills.values())
+
+    def get_skill(self, name: str) -> Optional[SkillDefinition]:
+        """Return the skill definition for ``name``, or ``None`` if not found."""
+
+        if not self._loaded:
+            self._discover()
+        return self._skills.get(name)
+
+    def load_prompt(self, name: str) -> str:
+        """Load and return the prompt template body for the named skill."""
+
+        skill_dir = self._skills_dir / name
+        skill_path = self._find_prompt_file(skill_dir)
+        if skill_path is None:
+            raise FileNotFoundError(
+                f"Prompt file not found for skill '{name}' in {skill_dir} "
+                f"(tried {list(_PROMPT_FILE_NAMES)})"
+            )
+        try:
+            _frontmatter, body = _parse_skill_file(skill_path)
+            return body
+        except (ValueError, yaml.YAMLError) as exc:
+            raise ValueError(f"Failed to parse prompt from {skill_path}: {exc}") from exc
@@ -0,0 +1,165 @@
+---
+name: enrich_hf_metadata
+title: "Enrich Metadata from HuggingFace"
+description: >
+  Parse the HuggingFace model card via LLM to extract description, trigger
+  words, base model, tags, and preview image URL.
+llm_required: true
+---
+
+You are an expert assistant for AI image generation models. Your task is to extract structured metadata from a HuggingFace model card (README.md).
+
+## Model Information
+
+- **Repository**: {{hf_url}}
+- **Model file path**: {{model_path}}
+- **Model filename**: {{model_basename}}
+- **Repository ID**: {{repo}}
+
+## Current Metadata (may be incomplete)
+
+```json
+{{current_metadata}}
+```
+
+## User Priority Tags Reference
+
+The user has configured the following list of **meaningful tag categories** for this model type (`{{model_type}}`):
+
+```
+{{priority_tags}}
+```
+
+These are the subjects, styles, and concepts the user considers useful for categorization. Use this list as a **reference** when evaluating tags (see the **tags** section below).
+
+## Available Base Models
+
+The following base models are currently valid in this system.  Use the EXACT
+name listed — do not invent aliases or modify variant suffixes.
+
+{{base_models}}
+
+## HuggingFace README Content
+
+```
+{{readme_content}}
+```
+
+## Extraction Instructions
+
+Extract the following information from the README content above:
+
+### base_model
+The base model this model was trained on. Use EXACTLY one of the names from the **Available Base Models** list above. Do not invent new names or use aliases.
+
+Check the YAML frontmatter for ``base_model:`` first. If the frontmatter has no ``base_model:``, look at the **model filename** (``{{model_basename}}``), YAML ``tags:``, README title and first paragraph for clues — the base model family is often embedded in the name
+
+### trigger_words
+The trigger words or activation prompts needed to use this LoRA. Look for:
+- `instance_prompt:` in the YAML frontmatter
+- Phrases like "trigger word:", "trigger:", "use this prompt:", "activation prompt:"
+- In collection repos: the trigger section **specific to this model file** (look near matching download links or anchor IDs)
+- Example prompts at the start (usually the first word or phrase before any description)
+Return as an array of strings. If none found, return an empty array `[]`. **Never** return `["None"]` or any placeholder value — a truly empty list means no trigger words exist.
+
+### short_description
+A concise 1-2 sentence summary of what this model does. Extract from the "Model description" section or the first paragraph.  For collection repos, focus on the **specific model version** matching `{{model_basename}}`, not the repo as a whole.  Return empty string if the README is too minimal.
+
+### tags
+3-8 relevant tags for categorizing this model. **Quality over quantity.**
+
+Sources to consider:
+- The YAML frontmatter `tags:` list (filter out technical ones — see below)
+- The subject, style, character, or concept the model represents
+- The model filename itself may give clues (e.g. "pokemon", "anime", "pixelart")
+
+**Critical filtering rules — apply them strictly:**
+
+1. **Exclude technical/generic tags.** Reject any tag that describes the model's **training methodology, framework, architecture, or modality** rather than its content. Examples to exclude: `text-to-image`, `diffusers`, `lora`, `dreambooth`, `diffusers-training`, `flux`, `sdxl`, `checkpoint`, `pytorch`, `safetensors`, `fine-tuning`, `stable-diffusion`, and any variant of these.
+
+2. **Cross-reference against the priority_tags reference.** Only include a tag if it meaningfully describes what the model actually creates (subject, style, character type) and is semantically close to one of the priority_tags. If none of the README's tags match meaningful categories, prefer returning a smaller set or an empty array over including low-value tags.
+
+3. **All lowercase, no spaces, no hyphens** (use single words like `"photorealistic"`, `"anime"`, `"character"`).
+
+Return empty array if no meaningful content tags remain after filtering.
+
+### recommended_width, recommended_height
+The recommended image generation resolution for this model, in pixels. Look for sections like "Best Dimensions", "Recommended size", "Suggested resolution", or similar phrasing in the README. Prefer the explicitly marked "Best" or default resolution. If the table/list has multiple entries (e.g. "768 x 1024 (Best)" and "1024 x 1024 (Default)"), use the one marked "Best". Return integers. If no resolution can be determined, return 0 for both.
+
+### preview_url
+The URL of the most suitable preview image from the README. Look for:
+- Image tags near the section matching the model filename (`{{model_basename}}`)
+- The YAML frontmatter `widget:` section (which often has `output.url` fields)
+- In collection repos: the sample images listed **under the section** for this specific model version
+- Generic `![alt](url)` in the body
+Choose the first image that appears to be a generation example (not a logo or diagram). Construct the absolute URL as `https://huggingface.co/{{repo}}/resolve/main/{filename}`. If no suitable image is found, return an empty string.
+
+### notes
+A plain-text summary of the model card's key practical usage information. Combine trigger words, style modifiers, recommended parameters (steps, CFG, resolution, sampler), and any setup tips into a readable paragraph.  For collection repos, focus on the **specific model version** matching `{{model_basename}}`.  Return empty string if the README has no useful usage info.
+
+### usage_tips
+A JSON string with structured usage recommendations. Extract from the README any explicit ranges or recommended values (e.g. "Set LoRA strength: **0.85 - 1.4**", "CLIP strength: 0.5"). Possible fields (include only those you can determine):
+
+```json
+{
+  "strength_min": 0.85,
+  "strength_max": 1.4,
+  "strength_range": "0.85-1.4",
+  "strength": 0.6,
+  "clip_strength": 0.5,
+  "clip_skip": 2
+}
+```
+
+Return the JSON string (e.g. `'{"strength_min":0.85,"strength_max":1.4}'`). Return `"{}"` if nothing useful is found.
+
+### confidence
+Your confidence level in the extracted data:
+- "high" — most fields were explicitly stated in the README
+- "medium" — some fields were inferred from context
+- "low" — most fields are guesses based on limited information
+
+## Important: Handling Collection Repos (multiple model files)
+
+Many HuggingFace repos contain **multiple model files** in a single repository
+(e.g. a "LoRA collection" with different styles/characters in separate files).
+
+The model file currently being enriched is: **`{{model_basename}}`**
+
+To find the correct section in the README:
+
+1. **Search for download links** containing the filename — the surrounding paragraph is your section.
+2. **Search for anchor IDs** (`<a id="...">`) or section headings whose text matches words from the filename.
+3. **Search for HTML headings** (`<h1>`, `<h2>`, `<span>`) containing parts of the filename.
+4. If no match is found, use the full README as usual — the model may be the only one in the repo.
+
+When a matching section IS found, prefer metadata from that section.
+When no section matches (e.g. single-model repos or repos without per-file sections),
+extract metadata from the full README normally.  Do not return empty data just
+because the filename doesn't appear in the README.
+
+## Output Format
+
+Return ONLY a JSON object with exactly these fields (no markdown fences, no extra text):
+
+```json
+{
+  "model_path": "{{model_path}}",
+  "base_model": "<canonical name or empty string>",
+  "trigger_words": ["<word1>", "<word2>"],
+  "short_description": "<1-2 sentence summary>",
+  "tags": ["<tag1>", "<tag2>"],
+  "recommended_width": 768,
+  "recommended_height": 1024,
+  "preview_url": "<image URL or empty string>",
+  "notes": "<plain-text usage summary or empty string>",
+  "usage_tips": "<JSON string like '{\"strength_min\":0.85,\"strength_max\":1.4}' or '{}'>",
+  "confidence": "<high|medium|low>"
+}
+```
+
+Important:
+- Only include the JSON object, no other text
+- If a field cannot be determined, use an empty string or empty array
+- Do not fabricate information not supported by the README
+- Never use placeholder values like `"None"` or `"unknown"` for missing data — use empty string or empty array
@@ -1,3 +1,7 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 from __future__ import annotations

 import asyncio
@@ -7,6 +11,7 @@ import os
 import secrets
 import shutil
 import socket
+import time
 from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
@@ -20,10 +25,43 @@ from .settings_manager import get_settings_manager

 logger = logging.getLogger(__name__)

+# Maximum times the download poll loop will re-schedule a transfer after it
+# is lost (daemon restart / RPC outage) before failing the download.
+MAX_TRANSFER_RECOVERY_ATTEMPTS = 2
+
+# stderr lines matching these markers indicate a disk write failure inside
+# aria2 (piece cache flush or raw file write).  They are promoted to INFO so
+# the root cause (disk full, permission denied, file locked by another
+# process, ...) is visible in the default logs; all other stderr output stays
+# at DEBUG to avoid noise.
+_DISK_WRITE_ERROR_MARKERS = (
+    # aria2 wrapper messages (write disk cache flush path)
+    "write disk cache flush failure",
+    "error when trying to flush write cache",
+    "failed to write into the file",
+    "failed to open the file",
+    "failed to seek the file",
+    # underlying root-cause phrases reported via "cause: ..." (POSIX + Windows)
+    "no space left on device",
+    "not enough space on the disk",
+    "input/output error",
+    "permission denied",
+    "access is denied",
+    "disk quota exceeded",
+    "used by another process",
+    "sharing violation",
+)
+
+# Minimum interval between INFO-level reports of the same stderr line so a
+# repeated failure (e.g. aria2 retrying against a full disk) does not spam
+# the log.
+STDERR_ERROR_REPORT_INTERVAL = 60.0
+
+
 def _try_certifi_ca_path() -> str | None:
    """Return the certifi CA bundle path if available, else None."""
    try:
-        import certifi  # type: ignore[import-untyped]
+        import certifi  # pyright: ignore[reportMissingTypeStubs]

        path = certifi.where()
        if os.path.isfile(path):
@@ -81,10 +119,12 @@ class Aria2Downloader:
        self._rpc_session: Optional[aiohttp.ClientSession] = None
        self._rpc_session_lock = asyncio.Lock()
        self._process_lock = asyncio.Lock()
+        self._register_lock = asyncio.Lock()
        self._transfers: Dict[str, Aria2Transfer] = {}
        self._poll_interval = 0.5
        self._state_store = Aria2TransferStateStore()
-        self._stderr_reader_task: Optional[asyncio.Task] = None
+        self._stderr_reader_task: Optional[asyncio.Task[Any]] = None
+        self._stderr_error_report: Dict[str, float] = {}

    @property
    def is_running(self) -> bool:
@@ -99,26 +139,58 @@ class Aria2Downloader:
        progress_callback=None,
        headers: Optional[Dict[str, str]] = None,
    ) -> Tuple[bool, str]:
-        """Download a file using aria2 RPC and wait for completion."""
+        """Download a file using aria2 RPC and wait for completion.
+
+        The poll loop is self-healing: when the in-memory transfer entry
+        disappears (e.g. another download restarted the daemon and
+        ``close()`` cleared ``_transfers``) or the RPC becomes unreachable,
+        the transfer is re-scheduled with ``continue=true`` so the download
+        resumes from the on-disk ``.aria2`` control file. Recovery is bounded
+        by ``MAX_TRANSFER_RECOVERY_ATTEMPTS``.
+        """

        await self._ensure_process()
        save_path = os.path.abspath(save_path)
-        transfer = self._transfers.get(download_id)
-        if transfer is None or os.path.abspath(transfer.save_path) != save_path:
-            gid = await self._schedule_download(
-                url,
-                save_path,
-                download_id=download_id,
-                headers=headers,
-            )
-            transfer = Aria2Transfer(gid=gid, save_path=save_path)
-            self._transfers[download_id] = transfer

+        async with self._register_lock:
+            transfer = self._transfers.get(download_id)
+            if transfer is None or os.path.abspath(transfer.save_path) != save_path:
+                transfer = await self._register_transfer(
+                    url,
+                    save_path,
+                    download_id=download_id,
+                    headers=headers,
+                )
+
+        recovery_attempts = 0
        try:
            while True:
-                status = await self._get_status_with_retry(download_id)
+                try:
+                    status = await self._get_status_with_retry(download_id)
+                except Aria2Error:
+                    status = None
+
                if status is None:
-                    return False, "aria2 download not found"
+                    if recovery_attempts >= MAX_TRANSFER_RECOVERY_ATTEMPTS:
+                        return False, "aria2 download not found"
+                    recovery_attempts += 1
+                    logger.warning(
+                        "aria2 transfer %s lost; re-scheduling with resume "
+                        "(attempt %d/%d)",
+                        download_id,
+                        recovery_attempts,
+                        MAX_TRANSFER_RECOVERY_ATTEMPTS,
+                    )
+                    await asyncio.sleep(1.0)
+                    await self._ensure_process()
+                    async with self._register_lock:
+                        transfer = await self._register_transfer(
+                            url,
+                            save_path,
+                            download_id=download_id,
+                            headers=headers,
+                        )
+                    continue

                snapshot = self._build_progress_snapshot(status)
                if progress_callback is not None:
@@ -135,7 +207,9 @@ class Aria2Downloader:

                await asyncio.sleep(self._poll_interval)
        finally:
-            self._transfers.pop(download_id, None)
+            current = self._transfers.get(download_id)
+            if current is not None and current.gid == transfer.gid:
+                self._transfers.pop(download_id, None)

    async def _get_status_with_retry(
        self, download_id: str, *, max_retries: int = 4, retry_delay: float = 3.0
@@ -190,7 +264,7 @@ class Aria2Downloader:
                    download_id,
                )

-        options: Dict[str, str] = {
+        options: Dict[str, Any] = {
            "dir": save_dir,
            "out": out_name,
            "continue": "true",
@@ -201,6 +275,13 @@ class Aria2Downloader:
            "auto-file-renaming": "false",
            "file-allocation": "none",
        }
+
+        # Pass proxy to aria2 so the actual file transfer goes through the
+        # same proxy used by the aiohttp-based URL resolution step above.
+        downloader = await get_downloader()
+        if downloader.proxy_url:
+            options["all-proxy"] = downloader.proxy_url
+
        if request_headers:
            options["header"] = [
                f"{key}: {value}" for key, value in request_headers.items()
@@ -231,6 +312,25 @@ class Aria2Downloader:
        )
        return gid

+    async def _register_transfer(
+        self,
+        url: str,
+        save_path: str,
+        *,
+        download_id: str,
+        headers: Optional[Dict[str, str]] = None,
+    ) -> Aria2Transfer:
+        """Schedule a download and track it in the in-memory transfer registry."""
+        gid = await self._schedule_download(
+            url,
+            save_path,
+            download_id=download_id,
+            headers=headers,
+        )
+        transfer = Aria2Transfer(gid=gid, save_path=os.path.abspath(save_path))
+        self._transfers[download_id] = transfer
+        return transfer
+
    async def get_status(self, download_id: str) -> Optional[Dict[str, Any]]:
        """Return the raw aria2 status payload for a known download."""

@@ -378,16 +478,51 @@ class Aria2Downloader:
        blocks, which freezes the entire ``aria2c`` process — including its
        RPC handler.  This background task reads lines from stderr as they
        arrive and forwards them to Python's logger.
+
+        Lines that indicate a disk write failure (e.g. the "cause: No space
+        left on device" line that follows "Write disk cache flush failure")
+        are promoted to INFO so the root cause is visible without enabling
+        debug logging; every other line stays at DEBUG to avoid noise.
        """
        try:
            assert self._process is not None and self._process.stderr is not None
            async for line in self._process.stderr:
                text = line.decode("utf-8", errors="replace").rstrip()
                if text:
-                    logger.debug("aria2 stderr: %s", text)
+                    if self._is_disk_write_error(text):
+                        self._report_stderr_error(text)
+                    else:
+                        logger.debug("aria2 stderr: %s", text)
        except Exception:
            pass

+    @staticmethod
+    def _is_disk_write_error(text: str) -> bool:
+        lowered = text.lower()
+        return any(marker in lowered for marker in _DISK_WRITE_ERROR_MARKERS)
+
+    def _report_stderr_error(self, text: str) -> None:
+        """INFO-log a disk write failure line, rate-limited per line text.
+
+        aria2 re-emits the same error chain on every poll/retry while the
+        underlying condition persists; only the first occurrence within
+        ``STDERR_ERROR_REPORT_INTERVAL`` seconds is promoted to INFO.
+        """
+        now = time.monotonic()
+        last = self._stderr_error_report.get(text)
+        if last is not None and now - last < STDERR_ERROR_REPORT_INTERVAL:
+            logger.debug("aria2 stderr (repeated disk write error): %s", text)
+            return
+        # Drop entries older than the window so the map stays bounded even
+        # during a long disk-full episode (piece indexes change per line).
+        self._stderr_error_report = {
+            line: timestamp
+            for line, timestamp in self._stderr_error_report.items()
+            if now - timestamp < STDERR_ERROR_REPORT_INTERVAL
+        }
+        self._stderr_error_report[text] = now
+        logger.info("aria2 disk write failure: %s", text)
+
    async def _dispatch_progress(self, callback, snapshot: DownloadProgress) -> None:
        try:
            result = callback(snapshot, snapshot)
@@ -8,7 +8,7 @@ from filename, base_model, and CivitAI version name — no manual tagging requir
 from __future__ import annotations

 import re
-from typing import Dict, List, Set
+from typing import Any, Dict, List, Set

 # ── Tag category definitions ──────────────────────────────────────────
 # Each category maps a display label to a regex pattern.
@@ -52,7 +52,7 @@ AUTO_TAG_GROUPS = {
 DEFAULT_ENABLED_GROUPS = {"mode", "video"}


-def _collect_sources(model_data: Dict) -> List[str]:
+def _collect_sources(model_data: Dict[str, Any]) -> List[str]:
    """Collect all text sources from model data for tag matching."""
    sources: List[str] = []

@@ -73,7 +73,7 @@ def _collect_sources(model_data: Dict) -> List[str]:
    return sources


-def extract_auto_tags(model_data: Dict) -> List[str]:
+def extract_auto_tags(model_data: Dict[str, Any]) -> List[str]:
    """Extract auto-detected tags from model metadata.

    Uses a two-layer approach:
@@ -0,0 +1,144 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
+"""Backfill the AutoV3 checked state for models loaded from a persisted snapshot.
+
+The SQLite persistent cache predates the AutoV3 feature, so entries hydrated
+from it have a NULL ``autov3`` column (the "not checked yet" state). This
+service computes the embedded AutoV3 hash for each such model — once per
+process — and persists it through the scanner's single write path
+(:meth:`ModelScanner.update_autov3_for_model`), marking every visited row so a
+subsequent run finds nothing left to do.
+
+Three-state contract honored here:
+
+- ``NULL`` (sqlite) / absent (dict)  = not checked yet  → backfill computes it
+- ``''`` (sqlite/dict) / JSON null   = checked, no value available → never recompute
+- 12-char lowercase hex              = value → never recompute
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import os
+import threading
+from typing import TYPE_CHECKING, Optional
+
+if TYPE_CHECKING:  # pragma: no cover - type-check only; runtime imports are local
+    from .model_scanner import ModelScanner
+
+logger = logging.getLogger(__name__)
+
+
+def _resolve_autov3(file_path: str) -> str:
+    """Resolve the AutoV3 hash for a model file.
+
+    Prefers the Civitai AutoV3 reported for the file whose SHA256 matches
+    (the authoritative value for recipe matching); falls back to the embedded
+    safetensors header hash. Returns ``''`` when neither is available.
+    """
+    try:
+        metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
+        if os.path.exists(metadata_path):
+            with open(metadata_path, "r", encoding="utf-8") as handle:
+                payload = json.load(handle)
+            if isinstance(payload, dict):
+                from ..utils.models import autov3_from_civitai_files  # local import avoids cycles
+
+                sha256 = (payload.get("sha256") or "").lower()
+                civitai_autov3 = autov3_from_civitai_files(payload.get("civitai"), sha256)
+                if civitai_autov3:
+                    return civitai_autov3
+    except Exception:
+        pass
+    from ..utils.file_utils import calculate_autov3  # local import avoids cycles
+
+    return calculate_autov3(file_path) or ""
+
+
+class Autov3BackfillService:
+    """Compute and persist AutoV3 hashes for models missing a checked state."""
+
+    _instance: Optional["Autov3BackfillService"] = None
+    _instance_lock = threading.Lock()
+
+    def __init__(self) -> None:
+        # Re-entrancy guard per model type: scanners for different model types
+        # initialize concurrently (lora_manager.py), so a global guard would
+        # silently skip every type but the first to start. Each model type
+        # runs its own backfill; a duplicate trigger for the same type no-ops.
+        self._running_types: set[str] = set()
+
+    @classmethod
+    def get_instance(cls) -> "Autov3BackfillService":
+        """Return the process-wide singleton instance."""
+        if cls._instance is None:
+            with cls._instance_lock:
+                if cls._instance is None:
+                    cls._instance = cls()
+        return cls._instance
+
+    async def backfill(self, scanner: "ModelScanner") -> int:
+        """Compute AutoV3 for every un-checked model of ``scanner.model_type``.
+
+        Each candidate file is read once via :func:`~py.utils.file_utils.calculate_autov3`
+        (cheap: safetensors header only) and the result is persisted through
+        ``scanner.update_autov3_for_model``. Files that no longer exist on
+        disk are skipped — they are intentionally NOT marked, because scanner
+        cleanup removes the stale row later.
+
+        Returns:
+            The number of models successfully updated. Never raises; on any
+            failure a warning is logged and ``0`` is returned. A duplicate
+            trigger for a model type that is already being backfilled returns
+            ``0`` immediately; different model types run concurrently.
+        """
+        model_type = scanner.model_type
+        if model_type in self._running_types:
+            return 0
+        self._running_types.add(model_type)
+        try:
+            # Local imports avoid import cycles at module load time.
+            from .persistent_model_cache import get_persistent_cache
+            from ..utils.file_utils import calculate_autov3
+
+            persistent = getattr(scanner, "_persistent_cache", None) or get_persistent_cache()
+            paths = persistent.get_models_missing_autov3(model_type)
+
+            loop = asyncio.get_running_loop()
+            count = 0
+            for path in paths:
+                # A file that no longer exists must not be marked; scanner
+                # cleanup removes the stale row later. The existence check and
+                # hash resolution run in the executor so the loop stays
+                # responsive to API requests while the backfill iterates a
+                # large library.
+                if not await loop.run_in_executor(None, os.path.exists, path):
+                    continue
+                autov3 = await loop.run_in_executor(None, _resolve_autov3, path)
+                if await scanner.update_autov3_for_model(model_type, path, autov3):
+                    count += 1
+
+            if paths:
+                logger.info(
+                    "AutoV3 backfill: updated %d/%d models for %s",
+                    count,
+                    len(paths),
+                    model_type,
+                )
+            else:
+                # Steady state after the first run: nothing left to backfill.
+                logger.debug("AutoV3 backfill: nothing to process for %s", model_type)
+            return count
+        except Exception as exc:
+            logger.warning(
+                "AutoV3 backfill failed for %s: %s",
+                getattr(scanner, "model_type", "?"),
+                exc,
+            )
+            return 0
+        finally:
+            self._running_types.discard(model_type)
@@ -1,3 +1,7 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 from __future__ import annotations

 import asyncio
@@ -1,7 +1,8 @@
 from abc import ABC, abstractmethod
 import asyncio
 import re
-from typing import Any, Dict, List, Optional, Type, TYPE_CHECKING
+import random
+from typing import Any, Awaitable, Dict, List, Optional, Type, Union, TYPE_CHECKING, cast
 import logging
 import os
 import time
@@ -69,24 +70,24 @@ class BaseModelService(ABC):
        page: int,
        page_size: int,
        sort_by: str = "name",
-        folder: str = None,
-        folder_include: list = None,
-        folder_exclude: list = None,
-        search: str = None,
+        folder: str | None = None,
+        folder_include: list[str] | None = None,
+        folder_exclude: list[str] | None = None,
+        search: str | None = None,
        fuzzy_search: bool = False,
-        base_models: list = None,
-        model_types: list = None,
+        base_models: list[str] | None = None,
+        model_types: list[str] | None = None,
        tags: Optional[Dict[str, str]] = None,
        auto_tags: Optional[Dict[str, str]] = None,
-        search_options: dict = None,
-        hash_filters: dict = None,
+        search_options: dict[str, Any] | None = None,
+        hash_filters: dict[str, Any] | None = None,
        favorites_only: bool = False,
        update_available_only: bool = False,
        credit_required: Optional[bool] = None,
        allow_selling_generated_content: Optional[bool] = None,
        tag_logic: str = "any",
        **kwargs,
-    ) -> Dict:
+    ) -> Dict[str, Any]:
        """Get paginated and filtered model data"""
        overall_start = time.perf_counter()

@@ -109,12 +110,15 @@ class BaseModelService(ABC):
        if civitai_model_id is not None:
            sorted_data = [
                item for item in sorted_data
-                if self._extract_model_id(item) == civitai_model_id
+                if self._extract_group_key(item) == civitai_model_id
            ]
            # VLM mode: always sort by version ID descending (newest version first),
            # regardless of the current sort_by preference.
+            # Fall back to modified timestamp for non-CivitAI sources.
            sorted_data.sort(
-                key=lambda x: self._extract_version_id(x) or 0,
+                key=lambda x: self._extract_version_id(x)
+                or x.get("modified", 0)
+                or 0,
                reverse=True,
            )

@@ -129,18 +133,21 @@ class BaseModelService(ABC):
            ufs = self.settings.get("version_grouping", "same_base")
            group_by_base = ufs == "same_base"

-            dedup_map = {}  # (modelId [,base_model]) -> (item, version_id)
+            dedup_map = {}  # (modelId [,base_model]) -> (item, version_or_modified)
            version_counter = {}  # same-key -> count
            standalone = []
            for item in sorted_data:
-                mid = self._extract_model_id(item)
+                mid = self._extract_group_key(item)
                if mid is None:
                    standalone.append(item)
                    continue
                key = (mid, item.get("base_model") or "") if group_by_base else mid
                # Count all versions per key
                version_counter[key] = version_counter.get(key, 0) + 1
-                vid = self._extract_version_id(item) or 0
+                # Prefer CivitAI version_id; fall back to modified timestamp
+                vid = self._extract_version_id(item)
+                if vid is None:
+                    vid = item.get("modified", 0) or 0
                if key not in dedup_map or vid > dedup_map[key][1]:
                    dedup_map[key] = (item, vid)
            # Attach version_count to each surviving grouped item (shallow copy
@@ -171,19 +178,22 @@ class BaseModelService(ABC):
                ufs = self.settings.get("version_grouping", "same_base")
                group_by_base = ufs == "same_base"

-                model_groups: Dict[Any, List[Dict]] = {}
-                ungrouped_standalone: List[Dict] = []
+                model_groups: Dict[Any, List[Dict[str, Any]]] = {}
+                ungrouped_standalone: List[Dict[str, Any]] = []
                for item in sorted_data:
-                    mid = self._extract_model_id(item)
+                    mid = self._extract_group_key(item)
                    if mid is None:
                        ungrouped_standalone.append(item)
                        continue
                    key = (mid, item.get("base_model") or "") if group_by_base else mid
                    model_groups.setdefault(key, []).append(item)
-                # Sort versions within each group by version id descending
+                # Sort versions within each group by version id (descending);
+                # fall back to modified timestamp for non-CivitAI sources.
                for items in model_groups.values():
                    items.sort(
-                        key=lambda x: self._extract_version_id(x) or 0,
+                        key=lambda x: self._extract_version_id(x)
+                        or x.get("modified", 0)
+                        or 0,
                        reverse=True,
                    )
                # Sort groups by version count
@@ -239,7 +249,7 @@ class BaseModelService(ABC):
        filter_duration = time.perf_counter() - t1
        post_filter_count = len(filtered_data)

-        annotated_for_filter: Optional[List[Dict]] = None
+        annotated_for_filter: Optional[List[Dict[str, Any]]] = None
        t2 = time.perf_counter()
        if update_available_only:
            annotated_for_filter = await self._annotate_update_flags(filtered_data)
@@ -286,11 +296,11 @@ class BaseModelService(ABC):
        page: int,
        page_size: int,
        sort_by: str = "name",
-        search: str = None,
+        search: str | None = None,
        fuzzy_search: bool = False,
-        search_options: dict = None,
+        search_options: dict[str, Any] | None = None,
        **kwargs,
-    ) -> Dict:
+    ) -> Dict[str, Any]:
        """Get paginated excluded model data."""
        excluded_paths = list(self.scanner.get_excluded_models())
        excluded_entries: List[Dict[str, Any]] = []
@@ -316,7 +326,7 @@ class BaseModelService(ABC):
                ]
                persist_current_cache = getattr(self.scanner, "_persist_current_cache", None)
                if callable(persist_current_cache):
-                    await persist_current_cache()
+                    await cast(Awaitable[Any], persist_current_cache())

        excluded_entries = self._sort_entries(excluded_entries, sort_by)

@@ -381,6 +391,12 @@ class BaseModelService(ABC):
                (item.get("model_name") or item.get("file_name") or "").lower(),
                item.get("file_path", "").lower(),
            )
+        elif key_name == "random":
+            # Seeded random shuffle: same seed -> same order (stable pagination)
+            rng = random.Random(sort_params.seed or "random")
+            result = list(data)
+            rng.shuffle(result)
+            return result
        elif key_name == "size":
            key_fn = lambda item: (
                int(item.get("size", 0) or 0),
@@ -428,39 +444,50 @@ class BaseModelService(ABC):
        return entry

    async def _apply_hash_filters(
-        self, data: List[Dict], hash_filters: Dict
-    ) -> List[Dict]:
-        """Apply hash-based filtering"""
+        self, data: List[Dict[str, Any]], hash_filters: Dict[str, Any]
+    ) -> List[Dict[str, Any]]:
+        """Apply hash-based filtering (SHA256 and AutoV3)."""
+
+        def matches_hash_set(item: Dict[str, Any], hash_set: set[str]) -> bool:
+            """Check whether an item matches any hash in the set.
+
+            Compares the item's ``sha256`` field and its non-empty ``autov3``
+            field, both case-insensitively.
+            """
+            if item.get("sha256", "").lower() in hash_set:
+                return True
+            autov3 = item.get("autov3", "")
+            return bool(autov3) and autov3.lower() in hash_set
+
        single_hash = hash_filters.get("single_hash")
        multiple_hashes = hash_filters.get("multiple_hashes")

        if single_hash:
-            # Filter by single hash
-            single_hash = single_hash.lower()
+            # Filter by single hash (SHA256 or AutoV3)
            return [
-                item for item in data if item.get("sha256", "").lower() == single_hash
+                item for item in data if matches_hash_set(item, {single_hash.lower()})
            ]
        elif multiple_hashes:
-            # Filter by multiple hashes
-            hash_set = set(hash.lower() for hash in multiple_hashes)
-            return [item for item in data if item.get("sha256", "").lower() in hash_set]
+            # Filter by multiple hashes (SHA256 or AutoV3)
+            hash_set = {hash.lower() for hash in multiple_hashes}
+            return [item for item in data if matches_hash_set(item, hash_set)]

        return data

    async def _apply_common_filters(
        self,
-        data: List[Dict],
-        folder: str = None,
-        folder_include: list = None,
-        folder_exclude: list = None,
-        base_models: list = None,
-        model_types: list = None,
+        data: List[Dict[str, Any]],
+        folder: str | None = None,
+        folder_include: list[str] | None = None,
+        folder_exclude: list[str] | None = None,
+        base_models: list[str] | None = None,
+        model_types: list[str] | None = None,
        tags: Optional[Dict[str, str]] = None,
        auto_tags: Optional[Dict[str, str]] = None,
        favorites_only: bool = False,
-        search_options: dict = None,
+        search_options: dict[str, Any] | None = None,
        tag_logic: str = "any",
-    ) -> List[Dict]:
+    ) -> List[Dict[str, Any]]:
        """Apply common filters that work across all model types"""
        normalized_options = self.search_strategy.normalize_options(search_options)
        criteria = FilterCriteria(
@@ -479,24 +506,24 @@ class BaseModelService(ABC):

    async def _apply_search_filters(
        self,
-        data: List[Dict],
+        data: List[Dict[str, Any]],
        search: str,
        fuzzy_search: bool,
-        search_options: dict,
-    ) -> List[Dict]:
+        search_options: dict[str, Any] | None,
+    ) -> List[Dict[str, Any]]:
        """Apply search filtering"""
        normalized_options = self.search_strategy.normalize_options(search_options)
        return self.search_strategy.apply(
            data, search, normalized_options, fuzzy_search
        )

-    async def _apply_specific_filters(self, data: List[Dict], **kwargs) -> List[Dict]:
+    async def _apply_specific_filters(self, data: List[Dict[str, Any]], **kwargs) -> List[Dict[str, Any]]:
        """Apply model-specific filters - to be overridden by subclasses if needed"""
        return data

    async def _apply_credit_required_filter(
-        self, data: List[Dict], credit_required: bool
-    ) -> List[Dict]:
+        self, data: List[Dict[str, Any]], credit_required: bool
+    ) -> List[Dict[str, Any]]:
        """Apply credit required filtering based on license_flags.

        Args:
@@ -526,8 +553,8 @@ class BaseModelService(ABC):
        return filtered_data

    async def _apply_allow_selling_filter(
-        self, data: List[Dict], allow_selling: bool
-    ) -> List[Dict]:
+        self, data: List[Dict[str, Any]], allow_selling: bool
+    ) -> List[Dict[str, Any]]:
        """Apply allow selling generated content filtering based on license_flags.

        Args:
@@ -559,8 +586,8 @@ class BaseModelService(ABC):

    async def _annotate_update_flags(
        self,
-        items: List[Dict],
-    ) -> List[Dict]:
+        items: List[Dict[str, Any]],
+    ) -> List[Dict[str, Any]]:
        """Attach an update_available flag to each response item.

        Items without a civitai model id default to False.
@@ -575,7 +602,7 @@ class BaseModelService(ABC):
                item["update_available"] = False
            return annotated

-        id_to_items: Dict[int, List[Dict]] = {}
+        id_to_items: Dict[int, List[Dict[str, Any]]] = {}
        ordered_ids: List[int] = []
        for item in annotated:
            model_id = self._extract_model_id(item)
@@ -612,7 +639,7 @@ class BaseModelService(ABC):
            record_method = getattr(self.update_service, "get_records_bulk", None)
            if callable(record_method):
                try:
-                    records = await record_method(self.model_type, ordered_ids)
+                    records = await cast(Awaitable[Any], record_method(self.model_type, ordered_ids))
                    resolved = {
                        model_id: record.has_update(hide_early_access=hide_early_access)
                        for model_id, record in records.items()
@@ -632,11 +659,11 @@ class BaseModelService(ABC):
            bulk_method = getattr(self.update_service, "has_updates_bulk", None)
            if callable(bulk_method):
                try:
-                    resolved = await bulk_method(
+                    resolved = await cast(Awaitable[Any], bulk_method(
                        self.model_type,
                        ordered_ids,
                        hide_early_access=hide_early_access,
-                    )
+                    ))
                except Exception as exc:
                    logger.error(
                        "Failed to resolve update status in bulk for %s models (%s): %s",
@@ -698,7 +725,34 @@ class BaseModelService(ABC):
        return annotated

    @staticmethod
-    def _extract_model_id(item: Dict) -> Optional[int]:
+    def _extract_hf_group_key(item: Dict[str, Any]) -> Optional[str]:
+        """Extract `hf:{owner}/{repo}` from item's ``hf_url``, or None."""
+        hf_url = item.get("hf_url") if isinstance(item, dict) else None
+        if not hf_url or not isinstance(hf_url, str):
+            return None
+        m = re.match(
+            r"https?://huggingface\.co/([^/]+/[^/]+)", hf_url.strip()
+        )
+        if not m:
+            return None
+        return f"hf:{m.group(1)}"
+
+    @staticmethod
+    def _extract_group_key(item: Dict[str, Any]) -> Union[int, str, None]:
+        """Return the group identity key: CivitAI modelId (int) or HF repo (str).
+
+        Preference order:
+        1. CivitAI ``modelId`` (int)
+        2. HF repo identity ``hf:{owner}/{repo}`` (str)
+        3. ``None`` (no known grouping source)
+        """
+        mid = BaseModelService._extract_model_id(item)
+        if mid is not None:
+            return mid
+        return BaseModelService._extract_hf_group_key(item)
+
+    @staticmethod
+    def _extract_model_id(item: Dict[str, Any]) -> Optional[int]:
        civitai = item.get("civitai") if isinstance(item, dict) else None
        if not isinstance(civitai, dict):
            return None
@@ -711,7 +765,7 @@ class BaseModelService(ABC):
            return None

    @staticmethod
-    def _extract_version_id(item: Dict) -> Optional[int]:
+    def _extract_version_id(item: Dict[str, Any]) -> Optional[int]:
        civitai = item.get("civitai") if isinstance(item, dict) else None
        if not isinstance(civitai, dict):
            return None
@@ -724,7 +778,7 @@ class BaseModelService(ABC):
            return None

    @staticmethod
-    def _extract_base_model(item: Dict) -> Optional[str]:
+    def _extract_base_model(item: Dict[str, Any]) -> Optional[str]:
        value = item.get("base_model")
        if value is None:
            return None
@@ -776,7 +830,7 @@ class BaseModelService(ABC):

        return highest_by_base

-    def _paginate(self, data: List[Dict], page: int, page_size: int) -> Dict:
+    def _paginate(self, data: List[Dict[str, Any]], page: int, page_size: int) -> Dict[str, Any]:
        """Apply pagination to filtered data"""
        total_items = len(data)
        start_idx = (page - 1) * page_size
@@ -791,7 +845,7 @@ class BaseModelService(ABC):
        }

    @abstractmethod
-    async def format_response(self, model_data: Dict) -> Optional[Dict]:
+    async def format_response(self, model_data: Dict[str, Any]) -> Optional[Dict[str, Any]]:
        """Format model data for API response - must be implemented by subclasses.

        Subclasses should return None for corrupted entries so the handler
@@ -800,11 +854,17 @@ class BaseModelService(ABC):
        pass

    # Common service methods that delegate to scanner
-    async def get_top_tags(self, limit: int = 20) -> List[Dict]:
+    async def get_top_tags(self, limit: int = 20) -> List[Dict[str, Any]]:
        """Get top tags sorted by frequency"""
        return await self.scanner.get_top_tags(limit)

-    async def get_base_models(self, limit: int = 20) -> List[Dict]:
+    async def search_tags(
+        self, query: str, limit: int = 50
+    ) -> List[Dict[str, Any]]:
+        """Search tags by substring, sorted by frequency"""
+        return await self.scanner.search_tags(query, limit)
+
+    async def get_base_models(self, limit: int = 20) -> List[Dict[str, Any]]:
        """Get base models sorted by frequency"""
        return await self.scanner.get_base_models(limit)

@@ -871,7 +931,7 @@ class BaseModelService(ABC):
        """Get model root directories"""
        return self.scanner.get_model_roots()

-    def filter_civitai_data(self, data: Dict, minimal: bool = False) -> Dict:
+    def filter_civitai_data(self, data: Dict[str, Any], minimal: bool = False) -> Dict[str, Any]:
        """Filter relevant fields from CivitAI data"""
        if not data:
            return {}
@@ -897,7 +957,7 @@ class BaseModelService(ABC):
        )
        return {k: data[k] for k in fields if k in data}

-    async def get_folder_tree(self, model_root: str) -> Dict:
+    async def get_folder_tree(self, model_root: str) -> Dict[str, Any]:
        """Get hierarchical folder tree for a specific model root"""
        cache = await self.scanner.get_cached_data()

@@ -926,7 +986,7 @@ class BaseModelService(ABC):

        return tree

-    async def get_unified_folder_tree(self) -> Dict:
+    async def get_unified_folder_tree(self) -> Dict[str, Any]:
        """Get unified folder tree across all model roots"""
        cache = await self.scanner.get_cached_data()

@@ -955,13 +1015,21 @@ class BaseModelService(ABC):

        return unified_tree

-    async def get_model_notes(self, model_name: str) -> Optional[str]:
-        """Get notes for a specific model file"""
+    async def get_model_notes(self, model_name: str) -> Optional[dict[str, Any]]:
+        """Get notes and file_path for a specific model file.
+
+        Supports both simple names (``OWSMianne_ANIMA_V1``) and full-path
+        syntax (``Anima/character/OWSMianne_ANIMA_V1``).
+        """
        cache = await self.scanner.get_cached_data()

        for model in cache.raw_data:
-            if model["file_name"] == model_name:
-                return model.get("notes", "")
+            file_name = model.get("file_name", "")
+            if file_name == model_name or model_name.endswith("/" + file_name) or model_name.endswith("\\" + file_name):
+                return {
+                    "notes": model.get("notes", ""),
+                    "file_path": model.get("file_path", ""),
+                }

        return None

@@ -1079,11 +1147,16 @@ class BaseModelService(ABC):

        return {"civitai_url": None, "model_id": None, "version_id": None}

-    async def get_model_metadata(self, file_path: str) -> Optional[Dict]:
+    async def get_model_metadata(self, file_path: str) -> Optional[Dict[str, Any]]:
        """Load full metadata for a single model.

        Listing/search endpoints return lightweight cache entries; this method performs
        a lazy read of the on-disk metadata snapshot when callers need full detail.
+
+        As a beneficial side effect, the in-memory and persistent caches are
+        opportunistically synchronised with the on-disk metadata — this keeps the
+        caches fresh even when a ``.metadata.json`` file was edited outside of the
+        normal save path (e.g. manually or by an external script).
        """
        metadata, should_skip = await MetadataManager.load_metadata(
            file_path, self.metadata_class
@@ -1101,6 +1174,19 @@ class BaseModelService(ABC):
                MetadataManager.save_metadata(file_path, metadata)
            )

+        # Opportunistically sync the in-memory + persistent caches.
+        # The .metadata.json disk read is already paid for; the sync only
+        # performs work when the cache is actually stale, and uses targeted,
+        # in-place operations to minimise overhead even with large model sets.
+        #
+        # Fire-and-forget by design: the task is intentionally untracked.
+        # sync_cache_from_metadata handles its own errors internally.
+        asyncio.create_task(
+            self.scanner.sync_cache_from_metadata(
+                file_path, metadata.to_dict()
+            )
+        )
+
        return self.filter_civitai_data(metadata.to_dict().get("civitai", {}))

    async def get_model_description(self, file_path: str) -> Optional[str]:
@@ -1157,7 +1243,7 @@ class BaseModelService(ABC):
        return True

    @staticmethod
-    def _relative_path_sort_key(relative_path: str, include_terms: List[str]) -> tuple:
+    def _relative_path_sort_key(relative_path: str, include_terms: List[str]) -> tuple[int, int, int, str]:
        """Sort paths by how well they satisfy the include tokens.

        Sorts based on path without extension for consistent ordering.
@@ -1184,19 +1270,87 @@ class BaseModelService(ABC):
        )

    async def search_relative_paths(
-        self, search_term: str, limit: int = 15, offset: int = 0
+        self,
+        search_term: str,
+        limit: int = 15,
+        offset: int = 0,
+        *,
+        folder: Optional[str] = None,
+        folder_include: Optional[list[str]] = None,
+        folder_exclude: Optional[list[str]] = None,
+        base_models: Optional[list[str]] = None,
+        model_types: Optional[list[str]] = None,
+        tags: Optional[dict[str, str]] = None,
+        auto_tags: Optional[dict[str, str]] = None,
+        tag_logic: str = "any",
+        credit_required: Optional[bool] = None,
+        allow_selling_generated_content: Optional[bool] = None,
+        recursive: bool = True,
+        apply_filters: bool = False,
    ) -> List[str]:
-        """Search model relative file paths for autocomplete functionality"""
+        """Search model relative file paths for autocomplete functionality.
+
+        Optional filter kwargs mirror the filters used by the list endpoint
+        (/api/lm/{prefix}/list). When no filter kwargs are provided the
+        behavior is identical to plain token-based path matching.
+        """
        cache = await self.scanner.get_cached_data()
        include_terms, exclude_terms = self._parse_search_tokens(search_term)

+        data = cache.raw_data
+        has_filters = any(
+            [
+                apply_filters,
+                folder is not None,
+                folder_include,
+                folder_exclude,
+                base_models,
+                model_types,
+                tags,
+                auto_tags,
+                credit_required is not None,
+                allow_selling_generated_content is not None,
+            ]
+        )
+        if has_filters:
+            # Auto-tags are not stored in the scanner cache — they are computed
+            # on the fly. Pre-compute them only when an auto-tag filter is
+            # active to avoid mutating cache entries unnecessarily.
+            if auto_tags:
+                from .auto_tag_service import extract_auto_tags
+
+                for item in data:
+                    if not item.get("auto_tags"):
+                        item["auto_tags"] = extract_auto_tags(item)
+
+            criteria = FilterCriteria(
+                folder=folder,
+                folder_include=folder_include,
+                folder_exclude=folder_exclude,
+                base_models=base_models,
+                model_types=model_types,
+                tags=tags,
+                auto_tags=auto_tags,
+                search_options={"recursive": recursive},
+                tag_logic=tag_logic,
+            )
+            data = self.filter_set.apply(data, criteria)
+            if credit_required is not None:
+                data = await self._apply_credit_required_filter(
+                    data, credit_required
+                )
+            if allow_selling_generated_content is not None:
+                data = await self._apply_allow_selling_filter(
+                    data, allow_selling_generated_content
+                )
+
        matching_paths = []

        # Get model roots for path calculation
        model_roots = self.scanner.get_model_roots()

        # Collect all matching paths first (needed for proper sorting and offset)
-        for model in cache.raw_data:
+        for model in data:
            file_path = model.get("file_path", "")
            if not file_path:
                continue
@@ -59,6 +59,7 @@ class CacheEntryValidator:
        'notes': ('', False),
        'usage_tips': ('', False),
        'hash_status': ('completed', False),
+        'autov3': (None, False),
    }

    @classmethod
@@ -119,8 +120,13 @@ class CacheEntryValidator:
                if is_required:
                    errors.append(f"Required field '{field_name}' is missing or None")
                if auto_repair:
-                    working_entry[field_name] = cls._get_default_copy(default_value)
-                    repaired = True
+                    # A missing optional field whose default is None is already
+                    # semantically equal to its default (e.g. autov3: absent
+                    # means "not checked") — writing None back is a no-op, not
+                    # a repair.
+                    if default_value is not None:
+                        working_entry[field_name] = cls._get_default_copy(default_value)
+                        repaired = True
                continue

            # Validate field type and value
@@ -175,6 +181,15 @@ class CacheEntryValidator:
                    # that invalidates the entry, but we also don't mark it repaired.
                    pass

+        # Normalize autov3 to lowercase if needed (optional field, never stripped).
+        autov3 = working_entry.get('autov3')
+        if isinstance(autov3, str) and autov3:
+            normalized_autov3 = autov3.lower()
+            if normalized_autov3 != autov3:
+                if auto_repair:
+                    working_entry['autov3'] = normalized_autov3
+                    repaired = True
+
        # Determine if entry is valid
        # Entry is valid if no critical required field errors remain after repair
        # Critical fields are file_path and sha256
@@ -242,6 +257,19 @@ class CacheEntryValidator:
        """
        expected_type = type(default_value)

+        # Special case: autov3 is optional with a three-state contract.
+        # None = not checked, "" = checked but unavailable, otherwise a
+        # 12-character hex string (case-insensitive here; normalized to
+        # lowercase separately).
+        if field_name == 'autov3':
+            if value is None or value == "":
+                return None
+            if not isinstance(value, str):
+                return f"Field 'autov3' should be string or None, got {type(value).__name__}"
+            if len(value) != 12 or any(c not in '0123456789abcdefABCDEF' for c in value):
+                return "Field 'autov3' should be a 12-character hex string"
+            return None
+
        # Special handling for numeric types
        if expected_type == int:
            if not isinstance(value, (int, float)):
@@ -1,3 +1,7 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 import asyncio
 import json
 import logging
@@ -6,10 +10,10 @@ from datetime import datetime
 from typing import Any, Dict, List, Optional

 from ..utils.models import CheckpointMetadata
-from ..utils.file_utils import find_preview_file, normalize_path
+from ..utils.file_utils import find_preview_file, normalize_path, calculate_autov3
 from ..utils.metadata_manager import MetadataManager
 from ..config import config
-from .model_scanner import ModelScanner
+from .model_scanner import ModelScanner, _is_excluded_dir
 from .model_hash_index import ModelHashIndex

 logger = logging.getLogger(__name__)
@@ -62,6 +66,11 @@ class CheckpointScanner(ModelScanner):
            # Find preview image
            preview_url = find_preview_file(base_name, dir_path)

+            # AutoV3 reads only the safetensors header, so it is cheap even for
+            # large checkpoints; record the checked state at creation time ("" =
+            # checked but unavailable).
+            autov3 = calculate_autov3(real_path)
+
            # Create metadata WITHOUT calculating hash
            metadata = CheckpointMetadata(
                file_name=base_name,
@@ -77,6 +86,7 @@ class CheckpointScanner(ModelScanner):
                sub_type="checkpoint",
                from_civitai=False,  # Mark as local model since no hash yet
                hash_status="pending",  # Mark hash as pending
+                autov3=autov3 or "",
            )

            # Save the created metadata
@@ -114,6 +124,17 @@ class CheckpointScanner(ModelScanner):
                and metadata.hash_status == "completed"
                and metadata.sha256
            ):
+                # Ensure the in-memory hash index is populated even when
+                # the hash was already computed and persisted to the metadata
+                # file.  Without this, usage tracking (and any other caller
+                # that queries get_hash_by_filename first) will miss on every
+                # lookup and keep calling back into this method, creating a
+                # tight loop that never populates the index.
+                self._hash_index.add_entry(
+                    metadata.sha256.lower(),
+                    file_path,
+                    getattr(metadata, "autov3", None) or None,
+                )
                return metadata.sha256

            async with self._hash_calculation_lock:
@@ -125,6 +146,11 @@ class CheckpointScanner(ModelScanner):
                    and metadata.hash_status == "completed"
                    and metadata.sha256
                ):
+                    self._hash_index.add_entry(
+                        metadata.sha256.lower(),
+                        file_path,
+                        getattr(metadata, "autov3", None) or None,
+                    )
                    return metadata.sha256

                task = self._hash_calculation_tasks.get(real_path)
@@ -175,6 +201,13 @@ class CheckpointScanner(ModelScanner):

            # Check if hash is already calculated
            if metadata.hash_status == "completed" and metadata.sha256:
+                # Populate the in-memory hash index even for pre-computed
+                # hashes, mirroring the fix in calculate_hash_for_model.
+                self._hash_index.add_entry(
+                    metadata.sha256.lower(),
+                    file_path,
+                    getattr(metadata, "autov3", None) or None,
+                )
                return metadata.sha256

            # Update status to calculating
@@ -191,7 +224,26 @@ class CheckpointScanner(ModelScanner):
            await MetadataManager.save_metadata(file_path, metadata)

            # Update hash index
-            self._hash_index.add_entry(sha256.lower(), file_path)
+            self._hash_index.add_entry(
+                sha256.lower(),
+                file_path,
+                getattr(metadata, "autov3", None) or None,
+            )
+
+            # Update the in-memory cache entry so that subsequent
+            # _persist_current_cache / _save_persistent_cache calls
+            # write the hash back to the SQLite models table.  Without
+            # this the hash only lives in the metadata file and the
+            # in-memory hash index, both of which are lost across
+            # restarts, causing the same re-computation loop on the
+            # next session.
+            if self._cache is not None and self._cache.raw_data:
+                for entry in self._cache.raw_data:
+                    if entry.get("file_path") == file_path:
+                        entry["sha256"] = sha256.lower()
+                        entry["hash_status"] = "completed"
+                        self.bump_cache_version()
+                        break

            logger.info(f"Hash calculated for checkpoint: {file_path}")
            return sha256
@@ -276,7 +328,8 @@ class CheckpointScanner(ModelScanner):
            if not os.path.exists(root_path):
                continue

-            for dirpath, _dirnames, filenames in os.walk(root_path):
+            for dirpath, dirnames, filenames in os.walk(root_path):
+                dirnames[:] = [d for d in dirnames if not _is_excluded_dir(d)]
                for filename in filenames:
                    if not filename.endswith(".metadata.json"):
                        continue
@@ -380,7 +433,7 @@ class CheckpointScanner(ModelScanner):
        roots.extend(config.extra_checkpoints_roots or [])
        roots.extend(config.extra_unet_roots or [])
        # Remove duplicates while preserving order
-        seen: set = set()
+        seen: set[str] = set()
        unique_roots: List[str] = []
        for root in roots:
            if root not in seen:
@@ -1,6 +1,6 @@
 import os
 import logging
-from typing import Dict, Optional
+from typing import Any, Dict, Optional

 from .base_model_service import BaseModelService
 from .auto_tag_service import extract_auto_tags
@@ -21,58 +21,58 @@ class CheckpointService(BaseModelService):
        """
        super().__init__("checkpoint", scanner, CheckpointMetadata, update_service=update_service)
    
-    async def format_response(self, checkpoint_data: Dict) -> Optional[Dict]:
+    async def format_response(self, model_data: Dict[str, Any]) -> Optional[Dict[str, Any]]:
        """Format Checkpoint data for API response.

        Returns None when the entry is missing critical fields (corrupted cache
        row), so the handler layer can filter it out. See issue #730.
        """
        # Guard against corrupted cache entries missing critical fields
-        file_path = checkpoint_data.get("file_path")
+        file_path = model_data.get("file_path")
        if not file_path or not isinstance(file_path, str):
            logger.warning(
                "Skipping corrupted checkpoint entry (missing file_path): %s",
-                checkpoint_data.get("file_name", "<unknown>"),
+                model_data.get("file_name", "<unknown>"),
            )
            return None

        # Get sub_type from cache entry (new canonical field)
-        sub_type = checkpoint_data.get("sub_type", "checkpoint")
+        sub_type = model_data.get("sub_type", "checkpoint")

-        file_name = checkpoint_data.get("file_name") or ""
-        model_name = checkpoint_data.get("model_name") or file_name
-        folder = checkpoint_data.get("folder") or ""
+        file_name = model_data.get("file_name") or ""
+        model_name = model_data.get("model_name") or file_name
+        folder = model_data.get("folder") or ""

        return {
            "model_name": model_name,
            "file_name": file_name,
-            "preview_url": config.get_preview_static_url(checkpoint_data.get("preview_url", "")),
-            "preview_nsfw_level": checkpoint_data.get("preview_nsfw_level", 0),
-            "base_model": checkpoint_data.get("base_model", ""),
+            "preview_url": config.get_preview_static_url(model_data.get("preview_url", "")),
+            "preview_nsfw_level": model_data.get("preview_nsfw_level", 0),
+            "base_model": model_data.get("base_model", ""),
            "folder": folder,
-            "sha256": checkpoint_data.get("sha256", ""),
+            "sha256": model_data.get("sha256", ""),
            "file_path": file_path.replace(os.sep, "/"),
-            "file_size": checkpoint_data.get("size", 0),
-            "modified": checkpoint_data.get("modified", ""),
-            "tags": checkpoint_data.get("tags", []),
-            "from_civitai": checkpoint_data.get("from_civitai", True),
-            "usage_count": checkpoint_data.get("usage_count", 0),
-            "notes": checkpoint_data.get("notes", ""),
+            "file_size": model_data.get("size", 0),
+            "modified": model_data.get("modified", ""),
+            "tags": model_data.get("tags", []),
+            "from_civitai": model_data.get("from_civitai", True),
+            "usage_count": model_data.get("usage_count", 0),
+            "notes": model_data.get("notes", ""),
            "sub_type": sub_type,
-            "favorite": checkpoint_data.get("favorite", False),
-            "exclude": bool(checkpoint_data.get("exclude", False)),
-            "update_available": bool(checkpoint_data.get("update_available", False)),
-            "skip_metadata_refresh": bool(checkpoint_data.get("skip_metadata_refresh", False)),
-            "civitai": self.filter_civitai_data(checkpoint_data.get("civitai", {}), minimal=True),
-            "auto_tags": checkpoint_data.get("auto_tags") or extract_auto_tags(checkpoint_data),
-            "version_count": checkpoint_data.get("version_count"),
-            "hf_url": checkpoint_data.get("hf_url", ""),
+            "favorite": model_data.get("favorite", False),
+            "exclude": bool(model_data.get("exclude", False)),
+            "update_available": bool(model_data.get("update_available", False)),
+            "skip_metadata_refresh": bool(model_data.get("skip_metadata_refresh", False)),
+            "civitai": self.filter_civitai_data(model_data.get("civitai", {}), minimal=True),
+            "auto_tags": model_data.get("auto_tags") or extract_auto_tags(model_data),
+            "version_count": model_data.get("version_count"),
+            "hf_url": model_data.get("hf_url", ""),
        }
    
-    def find_duplicate_hashes(self) -> Dict:
+    def find_duplicate_hashes(self) -> Dict[str, Any]:
        """Find Checkpoints with duplicate SHA256 hashes"""
        return self.scanner._hash_index.get_duplicate_hashes()
    
-    def find_duplicate_filenames(self) -> Dict:
+    def find_duplicate_filenames(self) -> Dict[str, Any]:
        """Find Checkpoints with conflicting filenames"""
        return self.scanner._hash_index.get_duplicate_filenames()
@@ -1,8 +1,12 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 import json
 import logging
 import asyncio
 from copy import deepcopy
-from typing import Optional, Dict, Tuple, List
+from typing import Any, Optional, Dict, Tuple, List, cast
 from .model_metadata_provider import CivArchiveModelMetadataProvider, ModelMetadataProviderManager
 from .downloader import get_downloader
 from .errors import RateLimitError
@@ -37,8 +41,8 @@ class CivArchiveClient:
    async def _request_json(
        self,
        path: str,
-        params: Optional[Dict[str, str]] = None
-    ) -> Tuple[Optional[Dict], Optional[str]]:
+        params: Optional[Dict[str, Any]] = None
+    ) -> Tuple[Optional[Dict[str, Any]], Optional[str]]:
        """Call CivArchive API and return JSON payload"""
        success, payload = await self._make_request(path, params=params)
        if not success:
@@ -52,12 +56,12 @@ class CivArchiveClient:
        self,
        path: str,
        *,
-        params: Optional[Dict[str, str]] = None,
-    ) -> Tuple[bool, Dict | str]:
+        params: Optional[Dict[str, Any]] = None,
+    ) -> Tuple[bool, Dict[str, Any] | str]:
        """Wrapper around downloader.make_request that surfaces rate limits."""

        downloader = await get_downloader()
-        kwargs: Dict[str, Dict[str, str]] = {}
+        kwargs: Dict[str, Dict[str, Any]] = {}
        if params:
            safe_params = {str(key): str(value) for key, value in params.items() if value is not None}
            if safe_params:
@@ -73,10 +77,11 @@ class CivArchiveClient:
            if payload.provider is None:
                payload.provider = "civarchive_api"
            raise payload
-        return success, payload
+        # RateLimitError is always raised above, so the returned payload is a dict or str.
+        return success, cast(Dict[str, Any] | str, payload)

    @staticmethod
-    def _normalize_payload(payload: Dict) -> Dict:
+    def _normalize_payload(payload: Dict[str, Any]) -> Dict[str, Any]:
        """Unwrap CivArchive responses that wrap content under a data key"""
        if not isinstance(payload, dict):
            return {}
@@ -86,12 +91,12 @@ class CivArchiveClient:
        return payload

    @staticmethod
-    def _split_context(payload: Dict) -> Tuple[Dict, Dict, List[Dict]]:
+    def _split_context(payload: Dict[str, Any]) -> Tuple[Dict[str, Any], Dict[str, Any], List[Dict[str, Any]]]:
        """Separate version payload from surrounding model context"""
        data = CivArchiveClient._normalize_payload(payload)
-        context: Dict = {}
-        fallback_files: List[Dict] = []
-        version: Dict = {}
+        context: Dict[str, Any] = {}
+        fallback_files: List[Dict[str, Any]] = []
+        version: Dict[str, Any] = {}

        for key, value in data.items():
            if key in {"version", "model"}:
@@ -115,7 +120,7 @@ class CivArchiveClient:
        return context, version, fallback_files

    @staticmethod
-    def _ensure_list(value) -> List:
+    def _ensure_list(value: Any) -> List[Any]:
        if isinstance(value, list):
            return value
        if value is None:
@@ -123,7 +128,7 @@ class CivArchiveClient:
        return [value]

    @staticmethod
-    def _build_model_info(context: Dict) -> Dict:
+    def _build_model_info(context: Dict[str, Any]) -> Dict[str, Any]:
        tags = context.get("tags")
        if not isinstance(tags, list):
            tags = list(tags) if isinstance(tags, (set, tuple)) else ([] if tags is None else [tags])
@@ -136,7 +141,7 @@ class CivArchiveClient:
        }

    @staticmethod
-    def _build_creator_info(context: Dict) -> Dict:
+    def _build_creator_info(context: Dict[str, Any]) -> Dict[str, Any]:
        username = context.get("creator_username") or context.get("username") or ""
        image = context.get("creator_image") or context.get("creator_avatar") or ""
        creator: Dict[str, Optional[str]] = {
@@ -150,7 +155,7 @@ class CivArchiveClient:
        return creator

    @staticmethod
-    def _transform_file_entry(file_data: Dict) -> Dict:
+    def _transform_file_entry(file_data: Dict[str, Any]) -> Dict[str, Any]:
        mirrors = file_data.get("mirrors") or []
        if not isinstance(mirrors, list):
            mirrors = [mirrors]
@@ -165,7 +170,7 @@ class CivArchiveClient:
        if not name and available_mirror:
            name = available_mirror.get("filename")

-        transformed: Dict = {
+        transformed: Dict[str, Any] = {
            "id": file_data.get("id"),
            "sizeKB": file_data.get("sizeKB"),
            "name": name,
@@ -216,23 +221,23 @@ class CivArchiveClient:

    def _transform_files(
        self,
-        files: Optional[List[Dict]],
-        fallback_files: Optional[List[Dict]] = None
-    ) -> List[Dict]:
-        candidates: List[Dict] = []
+        files: Optional[List[Dict[str, Any]]],
+        fallback_files: Optional[List[Dict[str, Any]]] = None
+    ) -> List[Dict[str, Any]]:
+        candidates: List[Dict[str, Any]] = []
        if isinstance(files, list) and files:
            candidates = files
        elif isinstance(fallback_files, list):
            candidates = fallback_files

-        transformed_files: List[Dict] = []
+        transformed_files: List[Dict[str, Any]] = []
        for file_data in candidates:
            if isinstance(file_data, dict):
                transformed_files.append(self._transform_file_entry(file_data))

        # Sort: .safetensors first, .ckpt second, others last
        # so the backend fallback (no file_params) prefers safetensors
-        def _sort_key(f: Dict) -> int:
+        def _sort_key(f: Dict[str, Any]) -> int:
            fname = f.get("name") or ""
            if isinstance(fname, str):
                lower = fname.lower()
@@ -247,10 +252,10 @@ class CivArchiveClient:

    def _transform_version(
        self,
-        context: Dict,
-        version: Dict,
-        fallback_files: Optional[List[Dict]] = None
-    ) -> Optional[Dict]:
+        context: Dict[str, Any],
+        version: Dict[str, Any],
+        fallback_files: Optional[List[Dict[str, Any]]] = None
+    ) -> Optional[Dict[str, Any]]:
        if not version:
            return None

@@ -291,7 +296,7 @@ class CivArchiveClient:

        return version_copy

-    async def _resolve_version_from_files(self, payload: Dict) -> Optional[Dict]:
+    async def _resolve_version_from_files(self, payload: Dict[str, Any]) -> Optional[Dict[str, Any]]:
        """Fallback to fetch version data when only file metadata is available"""
        data = self._normalize_payload(payload)
        files = data.get("files") or payload.get("files") or []
@@ -304,12 +309,26 @@ class CivArchiveClient:
            version_id = file_data.get("model_version_id") or file_data.get("modelVersionId")
            if model_id is None or version_id is None:
                continue
+            # CivitAI / CivArchive model IDs are small integers (typically ≤ 7
+            # digits).  Reject suspiciously large values that indicate the API
+            # returned a malformed payload (e.g. a hash reinterpreted as an ID)
+            # to avoid pointless HTTP 500 errors from CivArchive.
+            _MAX_VALID_CIVITAI_ID = 100_000_000
+            try:
+                if int(model_id) >= _MAX_VALID_CIVITAI_ID or int(version_id) >= _MAX_VALID_CIVITAI_ID:
+                    logger.debug(
+                        "Skipping implausible CivArchive model_id=%s / version_id=%s",
+                        model_id, version_id,
+                    )
+                    continue
+            except (TypeError, ValueError):
+                continue
            resolved = await self.get_model_version(model_id, version_id)
            if resolved:
                return resolved
        return None

-    async def get_model_by_hash(self, model_hash: str) -> Tuple[Optional[Dict], Optional[str]]:
+    async def get_model_by_hash(self, model_hash: str) -> Tuple[Optional[Dict[str, Any]], Optional[str]]:
        """Find model by SHA256 hash value using CivArchive API"""
        try:
            payload, error = await self._request_json(f"/sha256/{model_hash.lower()}")
@@ -318,12 +337,12 @@ class CivArchiveClient:
                    return None, "Model not found"
                return None, error

-            context, version_data, fallback_files = self._split_context(payload)
+            context, version_data, fallback_files = self._split_context(cast(Dict[str, Any], payload))
            transformed = self._transform_version(context, version_data, fallback_files)
            if transformed:
                return transformed, None

-            resolved = await self._resolve_version_from_files(payload)
+            resolved = await self._resolve_version_from_files(cast(Dict[str, Any], payload))
            if resolved:
                return resolved, None

@@ -336,7 +355,7 @@ class CivArchiveClient:
            logger.error(f"Error fetching CivArchive model by hash {model_hash[:10]}: {e}")
            return None, str(e)

-    async def get_model_versions(self, model_id: str) -> Optional[Dict]:
+    async def get_model_versions(self, model_id: str) -> Optional[Dict[str, Any]]:
        """Get all versions of a model using CivArchive API"""
        try:
            payload, error = await self._request_json(f"/models/{model_id}")
@@ -350,7 +369,7 @@ class CivArchiveClient:
            context, version_data, fallback_files = self._split_context(payload)

            versions_meta = data.get("versions") or []
-            transformed_versions: List[Dict] = []
+            transformed_versions: List[Dict[str, Any]] = []
            for meta in versions_meta:
                if not isinstance(meta, dict):
                    continue
@@ -367,7 +386,7 @@ class CivArchiveClient:
            if primary_version:
                transformed_versions.insert(0, primary_version)

-            ordered_versions: List[Dict] = []
+            ordered_versions: List[Dict[str, Any]] = []
            seen_ids = set()
            for version in transformed_versions:
                version_id = version.get("id")
@@ -388,7 +407,7 @@ class CivArchiveClient:
            logger.error(f"Error fetching CivArchive model versions for {model_id}: {e}")
            return None

-    async def get_model_version(self, model_id: int = None, version_id: int = None) -> Optional[Dict]:
+    async def get_model_version(self, model_id: int | str | None = None, version_id: int | str | None = None) -> Optional[Dict[str, Any]]:
        """Get specific model version using CivArchive API
        
        Args:
@@ -445,7 +464,7 @@ class CivArchiveClient:
            logger.error(f"Error fetching CivArchive model version via API {model_id}/{version_id}: {e}")
            return None

-    async def get_model_version_info(self, version_id: str) -> Tuple[Optional[Dict], Optional[str]]:
+    async def get_model_version_info(self, version_id: str) -> Tuple[Optional[Dict[str, Any]], Optional[str]]:
        """ Fetch model version metadata using a known bogus model lookup        
        CivArchive lacks a direct version lookup API, this uses a workaround (which we handle in the main model request now)
        
@@ -213,6 +213,18 @@ class CivitaiBaseModelService:
            "wan video 2.2 i2v-a14b": "WAN",
            "wan video 2.5 t2v": "WAN",
            "wan video 2.5 i2v": "WAN",
+            "wan video 2.7": "WAN",
+            "wan image 2.7": "WI27",
+            "ace audio": "ACE",
+            "boogu": "BOOG",
+            "grok": "GROK",
+            "happyhorse": "HAPP",
+            "hidream-o1": "HIO1",
+            "lens": "LENS",
+            "mai": "MAI",
+            "upscaler": "UPSC",
+            "ideogram 4.0": "ID40",
+            "qwen 2": "QWN2",
        }

        if lower_name in special_cases:
@@ -271,7 +283,7 @@ class CivitaiBaseModelService:
                return None

            if isinstance(result, str):
-                data = json.loads(result)
+                data: Any = json.loads(result)
            else:
                data = result

@@ -392,6 +404,7 @@ class CivitaiBaseModelService:
                "LTXV2",
                "LTXV 2.3",
                "CogVideoX",
+                "HappyHorse",
                "Mochi",
                "Hunyuan Video",
                "Wan Video",
@@ -404,15 +417,25 @@ class CivitaiBaseModelService:
                "Wan Video 2.2 I2V-A14B",
                "Wan Video 2.5 T2V",
                "Wan Video 2.5 I2V",
+                "Wan Image 2.7",
+                "Wan Video 2.7",
            ],
            "Other Models": [
+                "ACE Audio",
                "Illustrious",
                "Pony",
                "Pony V7",
+                "Boogu",
                "HiDream",
+                "HiDream-O1",
+                "Ideogram 4.0",
                "Qwen",
+                "Qwen 2",
                "AuraFlow",
                "Chroma",
+                "Grok",
+                "Lens",
+                "MAI",
                "ZImageTurbo",
                "ZImageBase",
                "PixArt a",
@@ -426,6 +449,7 @@ class CivitaiBaseModelService:
                "Ernie Turbo",
                "Nucleus",
                "Krea 2",
+                "Upscaler",
            ],
        }

@@ -1,9 +1,14 @@
+# pyright: reportImportCycles=false
+# Lazy (function-local) imports still count as static edges in basedpyright's
+# reportImportCycles, so the ServiceRegistry singleton pattern necessarily forms
+# import cycles. Breaking them would require an architectural refactor.
 import asyncio
 import copy
 import logging
 import os
+import time
 from collections import OrderedDict
-from typing import Any, Optional, Dict, Tuple, List, Sequence
+from typing import Any, Optional, Dict, Tuple, List, Sequence, cast
 from .connectivity_guard import (
    OFFLINE_FRIENDLY_MESSAGE,
    is_expected_offline_error,
@@ -16,9 +21,16 @@ from .model_metadata_provider import (
 from .downloader import get_downloader
 from .errors import RateLimitError, ResourceNotFoundError
 from ..utils.civitai_utils import resolve_license_payload
+from ..utils.constants import MODEL_WEIGHT_FILE_TYPES

 logger = logging.getLogger(__name__)

+# Best-effort cache for creator model counts, keyed by lowercase username.
+# Values are (monotonic timestamp, count or None); None results are cached
+# too so repeated failures don't hammer the API.
+_CREATOR_COUNT_CACHE_TTL_SECONDS = 600
+_creator_model_count_cache: Dict[str, Tuple[float, Optional[int]]] = {}
+

 class CivitaiClient:
    _instance = None
@@ -51,7 +63,7 @@ class CivitaiClient:
        # Uses OrderedDict with LRU eviction at MAX_CACHE_ENTRIES to prevent
        # unbounded growth in long-running server processes.
        self._version_info_cache: OrderedDict[
-            str, Tuple[Optional[Dict], Optional[str]]
+            str, Tuple[Optional[Dict[str, Any]], Optional[str]]
        ] = OrderedDict()
        self._MAX_CACHE_ENTRIES = 500

@@ -65,7 +77,7 @@ class CivitaiClient:
        *,
        use_auth: bool = False,
        **kwargs,
-    ) -> Tuple[bool, Dict | str]:
+    ) -> Tuple[bool, Dict[str, Any] | str]:
        """Wrapper around downloader.make_request that surfaces rate limits,
        with retry for transient server errors (5xx, Cloudflare 524, network flakiness)."""

@@ -79,7 +91,8 @@ class CivitaiClient:
                **kwargs,
            )
            if success:
-                return True, result
+                # RateLimitError is raised below; a successful result is dict or str.
+                return True, cast(Dict[str, Any] | str, result)

            if isinstance(result, RateLimitError):
                if result.provider is None:
@@ -119,7 +132,7 @@ class CivitaiClient:
        return False, "Unexpected error in _make_request"

    @staticmethod
-    def _remove_comfy_metadata(model_version: Optional[Dict]) -> None:
+    def _remove_comfy_metadata(model_version: Optional[Dict[str, Any]]) -> None:
        """Remove Comfy-specific metadata from model version images."""
        if not isinstance(model_version, dict):
            return
@@ -166,7 +179,7 @@ class CivitaiClient:

    async def get_model_by_hash(
        self, model_hash: str
-    ) -> Tuple[Optional[Dict], Optional[str]]:
+    ) -> Tuple[Optional[Dict[str, Any]], Optional[str]]:
        try:
            success, version = await self._make_request(
                "GET",
@@ -213,7 +226,7 @@ class CivitaiClient:
                # Ensure directory exists
                os.makedirs(os.path.dirname(save_path), exist_ok=True)
                with open(save_path, "wb") as f:
-                    f.write(content)
+                    f.write(content if isinstance(content, bytes) else content.encode("utf-8"))
                return True
            return False
        except Exception as e:
@@ -268,7 +281,7 @@ class CivitaiClient:
            return True
        return False

-    async def get_model_versions(self, model_id: str) -> Optional[Dict]:
+    async def get_model_versions(self, model_id: str) -> Optional[Dict[str, Any]]:
        """Get all versions of a model with local availability info"""
        try:
            success, result = await self._make_request(
@@ -276,7 +289,7 @@ class CivitaiClient:
                f"{self.base_url}/models/{model_id}",
                use_auth=True,
            )
-            if success:
+            if success and isinstance(result, dict):
                # Also return model type along with versions
                return {
                    "modelVersions": result.get("modelVersions", []),
@@ -310,7 +323,7 @@ class CivitaiClient:

    async def get_model_versions_bulk(
        self, model_ids: Sequence[int]
-    ) -> Optional[Dict[int, Dict]]:
+    ) -> Optional[Dict[int, Dict[str, Any]]]:
        """Fetch model metadata for multiple ids using the batch API."""

        deduped: Dict[int, None] = {}
@@ -340,13 +353,13 @@ class CivitaiClient:
            if not isinstance(items, list):
                return {}

-            payload: Dict[int, Dict] = {}
+            payload: Dict[int, Dict[str, Any]] = {}
            for item in items:
                if not isinstance(item, dict):
                    continue
                model_id = item.get("id")
                try:
-                    normalized_id = int(model_id)
+                    normalized_id = int(cast(Any, model_id))
                except (TypeError, ValueError):
                    continue
                payload[normalized_id] = {
@@ -366,8 +379,8 @@ class CivitaiClient:
            return None

    async def get_model_version(
-        self, model_id: int = None, version_id: int = None
-    ) -> Optional[Dict]:
+        self, model_id: int | None = None, version_id: int | None = None
+    ) -> Optional[Dict[str, Any]]:
        """Get specific model version with additional metadata."""
        try:
            if model_id is None and version_id is not None:
@@ -385,7 +398,7 @@ class CivitaiClient:
            logger.error(f"Error fetching model version: {e}")
            return None

-    async def _get_version_by_id_only(self, version_id: int) -> Optional[Dict]:
+    async def _get_version_by_id_only(self, version_id: int) -> Optional[Dict[str, Any]]:
        version = await self._fetch_version_by_id(version_id)
        if version is None:
            return None
@@ -404,7 +417,7 @@ class CivitaiClient:

    async def _get_version_with_model_id(
        self, model_id: int, version_id: Optional[int]
-    ) -> Optional[Dict]:
+    ) -> Optional[Dict[str, Any]]:
        model_data = await self._fetch_model_data(model_id)
        if not model_data:
            return None
@@ -457,20 +470,20 @@ class CivitaiClient:
        self._remove_comfy_metadata(version)
        return version

-    async def _fetch_model_data(self, model_id: int) -> Optional[Dict]:
+    async def _fetch_model_data(self, model_id: int) -> Optional[Dict[str, Any]]:
        success, data = await self._make_request(
            "GET",
            f"{self.base_url}/models/{model_id}",
            use_auth=True,
        )
-        if success:
+        if success and isinstance(data, dict):
            return data
        if is_expected_offline_error(data):
            return None
        logger.warning(f"Failed to fetch model data for model {model_id}")
        return None

-    async def _fetch_version_by_id(self, version_id: Optional[int]) -> Optional[Dict]:
+    async def _fetch_version_by_id(self, version_id: Optional[int]) -> Optional[Dict[str, Any]]:
        if version_id is None:
            return None

@@ -479,7 +492,7 @@ class CivitaiClient:
            f"{self.base_url}/model-versions/{version_id}",
            use_auth=True,
        )
-        if success:
+        if success and isinstance(version, dict):
            return version
        if is_expected_offline_error(version):
            return None
@@ -487,7 +500,7 @@ class CivitaiClient:
        logger.warning(f"Failed to fetch version by id {version_id}")
        return None

-    async def _fetch_version_by_hash(self, model_hash: Optional[str]) -> Optional[Dict]:
+    async def _fetch_version_by_hash(self, model_hash: Optional[str]) -> Optional[Dict[str, Any]]:
        if not model_hash:
            return None

@@ -496,7 +509,7 @@ class CivitaiClient:
            f"{self.base_url}/model-versions/by-hash/{model_hash}",
            use_auth=True,
        )
-        if success:
+        if success and isinstance(version, dict):
            return version
        if is_expected_offline_error(version):
            return None
@@ -505,8 +518,8 @@ class CivitaiClient:
        return None

    def _select_target_version(
-        self, model_data: Dict, model_id: int, version_id: Optional[int]
-    ) -> Optional[Dict]:
+        self, model_data: Dict[str, Any], model_id: int, version_id: Optional[int]
+    ) -> Optional[Dict[str, Any]]:
        model_versions = model_data.get("modelVersions", [])
        if not model_versions:
            logger.warning(f"No model versions found for model {model_id}")
@@ -525,18 +538,24 @@ class CivitaiClient:

        return model_versions[0]

-    def _extract_primary_model_hash(self, version_entry: Dict) -> Optional[str]:
+    def _extract_primary_model_hash(self, version_entry: Dict[str, Any]) -> Optional[str]:
+        # Prefer the generic "Model" file (most reliable version identity);
+        # fall back to any other weights-type primary.
        for file_info in version_entry.get("files", []):
            if file_info.get("type") == "Model" and file_info.get("primary"):
-                hashes = file_info.get("hashes", {})
-                model_hash = hashes.get("SHA256")
+                model_hash = (file_info.get("hashes", {}) or {}).get("SHA256")
+                if model_hash:
+                    return model_hash
+        for file_info in version_entry.get("files", []):
+            if file_info.get("type") in MODEL_WEIGHT_FILE_TYPES and file_info.get("primary"):
+                model_hash = (file_info.get("hashes", {}) or {}).get("SHA256")
                if model_hash:
                    return model_hash
        return None

    def _build_version_from_model_data(
-        self, version_entry: Dict, model_id: int, model_data: Dict
-    ) -> Dict:
+        self, version_entry: Dict[str, Any], model_id: int, model_data: Dict[str, Any]
+    ) -> Dict[str, Any]:
        version = copy.deepcopy(version_entry)
        version.pop("index", None)
        version["modelId"] = model_id
@@ -548,7 +567,7 @@ class CivitaiClient:
        }
        return version

-    def _enrich_version_with_model_data(self, version: Dict, model_data: Dict) -> None:
+    def _enrich_version_with_model_data(self, version: Dict[str, Any], model_data: Dict[str, Any]) -> None:
        model_info = version.get("model")
        if not isinstance(model_info, dict):
            model_info = {}
@@ -564,7 +583,7 @@ class CivitaiClient:

    async def get_model_version_info(
        self, version_id: str
-    ) -> Tuple[Optional[Dict], Optional[str]]:
+    ) -> Tuple[Optional[Dict[str, Any]], Optional[str]]:
        """Fetch model version metadata from Civitai

        Args:
@@ -589,7 +608,7 @@ class CivitaiClient:
            logger.debug("Resolving Civitai model version info: %s", url)
            success, result = await self._make_request("GET", url, use_auth=True)

-            if success:
+            if success and isinstance(result, dict):
                logger.debug("Successfully fetched model version info for: %s", version_id)
                self._remove_comfy_metadata(result)
                self._version_info_cache[version_id] = (result, None)
@@ -619,7 +638,7 @@ class CivitaiClient:

    async def get_image_info(
        self, image_id: str, source_url: str | None = None
-    ) -> Optional[Dict]:
+    ) -> Optional[Dict[str, Any]]:
        """Fetch image information from Civitai API

        Args:
@@ -652,7 +671,7 @@ class CivitaiClient:
                )
                return None

-            if result and "items" in result and isinstance(result["items"], list):
+            if isinstance(result, dict) and "items" in result and isinstance(result["items"], list):
                items = result["items"]

                for item in items:
@@ -692,7 +711,7 @@ class CivitaiClient:

    async def get_model_versions_by_hashes(
        self, hashes: List[str]
-    ) -> Optional[List[Dict]]:
+    ) -> Optional[List[Dict[str, Any]]]:
        """Fetch full version details for up to 100 SHA256 hashes via the batch endpoint.

        Uses POST /api/v1/model-versions/by-hash which returns full version
@@ -709,7 +728,7 @@ class CivitaiClient:
            return []

        BATCH_SIZE = 100
-        all_versions: List[Dict] = []
+        all_versions: List[Dict[str, Any]] = []

        for start in range(0, len(hashes), BATCH_SIZE):
            batch = hashes[start : start + BATCH_SIZE]
@@ -729,7 +748,7 @@ class CivitaiClient:
                    continue

                if isinstance(result, list):
-                    all_versions.extend(result)
+                    all_versions.extend(cast(Any, result))
                else:
                    logger.debug(
                        "Unexpected by-hash response type: %s", type(result)
@@ -743,17 +762,34 @@ class CivitaiClient:

        return all_versions if all_versions else None

-    async def get_user_models(self, username: str) -> Optional[List[Dict]]:
-        """Fetch all models for a specific Civitai user."""
+    async def get_user_models(
+        self, username: str, cursor: Optional[str] = None
+    ) -> Optional[Dict[str, Any]]:
+        """Fetch one page (up to 100 models) for a specific Civitai user.
+
+        Returns ``{"items": [...], "nextCursor": <str|None>}`` on success,
+        or None on failure. Pass ``cursor`` (from a previous response's
+        ``nextCursor``) to fetch subsequent pages.
+        """
        if not username:
            return None

+        params: Dict[str, Any] = {
+            "username": username,
+            "nsfw": "true",
+            "limit": 100,
+            "sort": "Newest",
+            "period": "AllTime",
+        }
+        if cursor:
+            params["cursor"] = cursor
+
        try:
            success, result = await self._make_request(
                "GET",
                f"{self.base_url}/models",
                use_auth=True,
-                params={"username": username, "nsfw": "true"},
+                params=params,
            )

            if not success:
@@ -765,7 +801,7 @@ class CivitaiClient:

            items = result.get("items") if isinstance(result, dict) else None
            if not isinstance(items, list):
-                return []
+                items = []

            for model in items:
                versions = model.get("modelVersions")
@@ -774,9 +810,68 @@ class CivitaiClient:
                for version in versions:
                    self._remove_comfy_metadata(version)

-            return items
+            next_cursor: Optional[str] = None
+            metadata = result.get("metadata") if isinstance(result, dict) else None
+            if isinstance(metadata, dict):
+                raw_cursor = metadata.get("nextCursor")
+                if raw_cursor is not None:
+                    next_cursor = str(raw_cursor)
+
+            return {"items": items, "nextCursor": next_cursor}
        except RateLimitError:
            raise
        except Exception as exc:  # pragma: no cover - defensive logging
            logger.error("Error fetching models for %s: %s", username, exc)
            return None
+
+    async def get_creator_model_count(self, username: str) -> Optional[int]:
+        """Best-effort lookup of a creator's published model count.
+
+        Uses the ``/creators`` endpoint (a contains-match query), picking the
+        entry whose username matches exactly (case-insensitive). Returns None
+        on any failure; never raises. Results (including None) are cached
+        for ``_CREATOR_COUNT_CACHE_TTL_SECONDS``.
+        """
+        if not username:
+            return None
+
+        cache_key = username.lower()
+        cached = _creator_model_count_cache.get(cache_key)
+        if cached is not None:
+            cached_at, cached_count = cached
+            if time.monotonic() - cached_at < _CREATOR_COUNT_CACHE_TTL_SECONDS:
+                return cached_count
+
+        count: Optional[int] = None
+        try:
+            success, result = await self._make_request(
+                "GET",
+                f"{self.base_url}/creators",
+                use_auth=True,
+                params={"query": username, "limit": 10},
+            )
+
+            if success and isinstance(result, dict):
+                creators = result.get("items")
+                if isinstance(creators, list):
+                    for creator in creators:
+                        if not isinstance(creator, dict):
+                            continue
+                        creator_name = creator.get("username")
+                        if not isinstance(creator_name, str):
+                            continue
+                        if creator_name.lower() != cache_key:
+                            continue
+                        model_count = creator.get("modelCount")
+                        if isinstance(model_count, (int, float)) and not isinstance(
+                            model_count, bool
+                        ):
+                            count = int(model_count)
+                        break
+        except Exception as exc:  # best-effort only, never propagate
+            logger.debug(
+                "Failed to fetch creator model count for %s: %s", username, exc
+            )
+
+        _creator_model_count_cache[cache_key] = (time.monotonic(), count)
+        return count
--- a/Show More
+++ b/Show More