chore(release): bump version to v1.1.8

- Move preset apply handler from span.preset-name to div.filter-preset so
  clicking anywhere on the tile triggers the preset, not just the label text.
- Add whitespace heuristic in showToast() to skip translate() for plain
  messages that are already translated at the call site. This prevents
  i18next from logging 'Translation key not found' for pre-translated
  strings like 'Preset "name" applied'.

.agents/skills/lora-manager-runtime-context/SKILL.md

@@ -0,0 +1,69 @@
+---
+name: lora-manager-runtime-context
+description: Inspect ComfyUI LoRA Manager runtime configuration and local diagnostic state. Use when debugging LoRA Manager issues that require locating or reading settings.json, active library paths, model metadata JSON sidecars, recipe metadata JSON files, example image folders, SQLite caches, symlink maps, download history, aria2 state, or other cache files under the LoRA Manager user config directory.
+---
+
+# LoRA Manager Runtime Context
+
+## Core Rules
+
+- Treat runtime state as local user data. Prefer read-only inspection unless the user explicitly asks for mutation.
+- Never print secret-like settings values. Redact keys containing `key`, `token`, `secret`, `password`, `auth`, or `credential`, including `civitai_api_key`.
+- Resolve paths from the runtime configuration before guessing. In this environment the settings file is normally `/home/miao/.config/ComfyUI-LoRA-Manager/settings.json`, but portable settings can override this through the repository `settings.json`.
+- Use the active library when selecting per-library caches and paths. Read `active_library` from settings; fall back to `default` if missing.
+- Normalize and expand `~` before comparing paths. Symlinks are common in this repo.
+
+## Quick Start
+
+Use the bundled helper for a safe first pass:
+
+```bash
+python .agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py summary
+python .agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py caches
+```
+
+The script redacts sensitive settings, opens SQLite databases read-only, and reports inaccessible or locked databases as warnings.
+
+For focused checks:
+
+```bash
+python .agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py recipes
+python .agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py model --path /path/to/model.safetensors
+python .agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py sqlite --db /path/to/cache.sqlite --limit 3
+```
+
+## Runtime Path Rules
+
+- Settings directory: use `py/utils/settings_paths.py`. Default platform path is `platformdirs.user_config_dir("ComfyUI-LoRA-Manager", appauthor=False)`.
+- Settings file: `<settings_dir>/settings.json`.
+- Cache root: `<settings_dir>/cache`.
+- Canonical cache files:
+  - Model cache: `cache/model/<active_library>.sqlite`.
+  - Recipe cache: `cache/recipe/<active_library>.sqlite`.
+  - Model update cache: `cache/model_update/<active_library>.sqlite`.
+  - Recipe FTS: `cache/fts/recipe_fts.sqlite`.
+  - Tag FTS: `cache/fts/tag_fts.sqlite`.
+  - Symlink map: `cache/symlink/symlink_map.json`.
+  - Download history: `cache/download_history/downloaded_versions.sqlite`.
+  - aria2 state: `cache/aria2/downloads.json`.
+- Legacy cache locations may exist; prefer canonical paths unless diagnosing migrations.
+
+## Data Location Rules
+
+- Model roots come from `settings.folder_paths` and the active library payload under `settings.libraries[active_library]`.
+- Model metadata JSON sidecars live next to the model file as `<model basename>.metadata.json`.
+- Recipes root is `settings.recipes_path` when it is a non-empty string. If empty, use the first configured LoRA root plus `/recipes`.
+- Recipe JSON files are named `*.recipe.json` under the recipes root and may be nested in folders.
+- Example image root is `settings.example_images_path`.
+- If multiple libraries are configured, example images are stored under `<example_images_path>/<sanitized_library>/<sha256>/`; otherwise they are under `<example_images_path>/<sha256>/`.
+
+## Useful Cache Tables
+
+- Model cache: `models`, `model_tags`, `hash_index`, `excluded_models`.
+- Recipe cache: `recipes`, `cache_metadata`.
+- Model update cache: `model_update_status`, `model_update_versions`.
+- Tag FTS cache: `tags`, `fts_metadata`, plus FTS internal tables.
+- Recipe FTS cache: `recipe_rowid`, `fts_metadata`, plus FTS internal tables.
+- Download history: `downloaded_model_versions`.
+
+Prefer querying only counts, schema, and a few sample rows unless the user asks for full output.

.agents/skills/lora-manager-runtime-context/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "LoRA Manager Runtime Context"
+  short_description: "Inspect LoRA Manager runtime state"
+  default_prompt: "Use $lora-manager-runtime-context to inspect LoRA Manager settings, metadata paths, and caches for debugging."

.agents/skills/lora-manager-runtime-context/scripts/inspect_runtime_context.py

@@ -0,0 +1,381 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import re
+import shutil
+import sqlite3
+import sys
+import tempfile
+from pathlib import Path
+from typing import Any
+
+SECRET_PATTERN = re.compile(r"(key|token|secret|password|auth|credential)", re.IGNORECASE)
+APP_NAME = "ComfyUI-LoRA-Manager"
+CACHE_SQLITE = {
+    "model": ("model", "{library}.sqlite"),
+    "recipe": ("recipe", "{library}.sqlite"),
+    "model_update": ("model_update", "{library}.sqlite"),
+    "recipe_fts": ("fts", "recipe_fts.sqlite"),
+    "tag_fts": ("fts", "tag_fts.sqlite"),
+    "download_history": ("download_history", "downloaded_versions.sqlite"),
+}
+CACHE_JSON = {
+    "symlink": ("symlink", "symlink_map.json"),
+    "aria2": ("aria2", "downloads.json"),
+}
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Inspect LoRA Manager runtime state read-only.")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    subparsers.add_parser("summary", help="Print redacted settings and resolved paths.")
+    subparsers.add_parser("caches", help="Print cache paths and SQLite table summaries.")
+    subparsers.add_parser("recipes", help="Print resolved recipes root and recipe JSON count.")
+
+    model_parser = subparsers.add_parser("model", help="Inspect a model metadata sidecar path.")
+    model_parser.add_argument("--path", required=True, help="Path to a model file or metadata JSON file.")
+
+    sqlite_parser = subparsers.add_parser("sqlite", help="Inspect a SQLite database read-only.")
+    sqlite_parser.add_argument("--db", required=True, help="Path to the SQLite database.")
+    sqlite_parser.add_argument("--limit", type=int, default=3, help="Rows to sample from each user table.")
+
+    args = parser.parse_args()
+    context = build_context()
+
+    if args.command == "summary":
+        print_json(summary_payload(context))
+    elif args.command == "caches":
+        print_json(caches_payload(context))
+    elif args.command == "recipes":
+        print_json(recipes_payload(context))
+    elif args.command == "model":
+        print_json(model_payload(args.path))
+    elif args.command == "sqlite":
+        print_json(sqlite_payload(Path(args.db).expanduser(), args.limit))
+    return 0
+
+
+def build_context() -> dict[str, Any]:
+    settings_path = resolve_settings_path()
+    settings = load_json(settings_path)
+    settings_dir = settings_path.parent
+    active_library = settings.get("active_library") or "default"
+    safe_library = sanitize_library_name(str(active_library))
+    cache_root = settings_dir / "cache"
+    return {
+        "settings_path": str(settings_path),
+        "settings_dir": str(settings_dir),
+        "settings": settings,
+        "active_library": active_library,
+        "safe_library": safe_library,
+        "cache_root": str(cache_root),
+        "cache_paths": resolve_cache_paths(cache_root, safe_library),
+    }
+
+
+def resolve_settings_path() -> Path:
+    repo_root = find_repo_root()
+    portable = repo_root / "settings.json"
+    if portable.exists():
+        payload = load_json(portable)
+        if isinstance(payload, dict) and payload.get("use_portable_settings") is True:
+            return portable
+
+    config_home = os.environ.get("XDG_CONFIG_HOME")
+    if config_home:
+        return Path(config_home).expanduser() / APP_NAME / "settings.json"
+    return Path.home() / ".config" / APP_NAME / "settings.json"
+
+
+def find_repo_root() -> Path:
+    current = Path(__file__).resolve()
+    for parent in current.parents:
+        if (parent / "py").is_dir() and (parent / "standalone.py").exists():
+            return parent
+    return Path.cwd()
+
+
+def load_json(path: Path) -> dict[str, Any]:
+    try:
+        with path.open("r", encoding="utf-8") as handle:
+            payload = json.load(handle)
+    except FileNotFoundError:
+        return {}
+    except json.JSONDecodeError as exc:
+        return {"_error": f"invalid JSON: {exc}"}
+    except OSError as exc:
+        return {"_error": f"unreadable: {exc}"}
+    return payload if isinstance(payload, dict) else {"_error": "JSON root is not an object"}
+
+
+def resolve_cache_paths(cache_root: Path, library: str) -> dict[str, str]:
+    paths: dict[str, str] = {}
+    for name, (subdir, filename) in CACHE_SQLITE.items():
+        paths[name] = str(cache_root / subdir / filename.format(library=library))
+    for name, (subdir, filename) in CACHE_JSON.items():
+        paths[name] = str(cache_root / subdir / filename)
+    return paths
+
+
+def summary_payload(context: dict[str, Any]) -> dict[str, Any]:
+    settings = context["settings"]
+    return {
+        "settings_path": context["settings_path"],
+        "settings_dir": context["settings_dir"],
+        "active_library": context["active_library"],
+        "settings": redact(settings),
+        "model_roots": model_roots(settings, context["active_library"]),
+        "recipes_root": str(resolve_recipes_root(settings, context["active_library"]) or ""),
+        "example_images": example_images_payload(settings, context["active_library"]),
+        "cache_root": context["cache_root"],
+        "cache_paths": context["cache_paths"],
+    }
+
+
+def caches_payload(context: dict[str, Any]) -> dict[str, Any]:
+    caches: dict[str, Any] = {}
+    for name, path_string in context["cache_paths"].items():
+        path = Path(path_string)
+        item: dict[str, Any] = {
+            "path": str(path),
+            "exists": path.exists(),
+            "size": path.stat().st_size if path.exists() else None,
+        }
+        if path.suffix == ".sqlite":
+            item["sqlite"] = sqlite_payload(path, limit=0)
+        elif path.suffix == ".json":
+            item["json"] = json_file_summary(path)
+        caches[name] = item
+    return {"active_library": context["active_library"], "caches": caches}
+
+
+def recipes_payload(context: dict[str, Any]) -> dict[str, Any]:
+    root = resolve_recipes_root(context["settings"], context["active_library"])
+    files: list[str] = []
+    if root and root.exists():
+        files = [str(path) for path in sorted(root.rglob("*.recipe.json"))[:20]]
+    return {
+        "recipes_root": str(root or ""),
+        "exists": bool(root and root.exists()),
+        "recipe_json_count": count_recipe_files(root),
+        "sample_recipe_json": files,
+        "recipe_cache": context["cache_paths"].get("recipe"),
+    }
+
+
+def model_payload(raw_path: str) -> dict[str, Any]:
+    path = Path(raw_path).expanduser()
+    metadata_path = path if path.name.endswith(".metadata.json") else path.with_suffix(".metadata.json")
+    payload = {
+        "input_path": str(path),
+        "metadata_path": str(metadata_path),
+        "model_exists": path.exists(),
+        "metadata_exists": metadata_path.exists(),
+    }
+    if metadata_path.exists():
+        data = load_json(metadata_path)
+        payload["metadata_summary"] = redact(summarize_value(data))
+    return payload
+
+
+def sqlite_payload(path: Path, limit: int = 3, allow_copy: bool = True) -> dict[str, Any]:
+    result: dict[str, Any] = {"path": str(path), "exists": path.exists(), "tables": {}}
+    if not path.exists():
+        return result
+    try:
+        conn = connect_sqlite_readonly(path)
+    except sqlite3.Error as exc:
+        result["error"] = str(exc)
+        return result
+    try:
+        table_rows = conn.execute(
+            "SELECT name FROM sqlite_master WHERE type='table' ORDER BY name"
+        ).fetchall()
+        for table_row in table_rows:
+            table = table_row["name"]
+            columns = [
+                row["name"]
+                for row in conn.execute(f"PRAGMA table_info({quote_identifier(table)})").fetchall()
+            ]
+            table_info: dict[str, Any] = {"columns": columns}
+            try:
+                table_info["count"] = conn.execute(
+                    f"SELECT COUNT(*) FROM {quote_identifier(table)}"
+                ).fetchone()[0]
+            except sqlite3.Error as exc:
+                table_info["count_error"] = str(exc)
+            if limit > 0 and columns and not is_internal_sqlite_table(table):
+                try:
+                    rows = conn.execute(
+                        f"SELECT * FROM {quote_identifier(table)} LIMIT ?", (limit,)
+                    ).fetchall()
+                    table_info["sample"] = [redact(dict(row)) for row in rows]
+                except sqlite3.Error as exc:
+                    table_info["sample_error"] = str(exc)
+            result["tables"][table] = table_info
+    except sqlite3.Error as exc:
+        fallback = sqlite_copy_payload(path, limit, str(exc)) if allow_copy else None
+        if fallback is not None:
+            result.update(fallback)
+        else:
+            result["error"] = str(exc)
+    finally:
+        conn.close()
+    return result
+
+
+def connect_sqlite_readonly(path: Path) -> sqlite3.Connection:
+    errors: list[str] = []
+    for query in ("mode=ro", "mode=ro&immutable=1"):
+        try:
+            conn = sqlite3.connect(f"file:{path}?{query}", uri=True)
+            conn.row_factory = sqlite3.Row
+            return conn
+        except sqlite3.Error as exc:
+            errors.append(f"{query}: {exc}")
+    raise sqlite3.OperationalError("; ".join(errors))
+
+
+def sqlite_copy_payload(path: Path, limit: int, original_error: str) -> dict[str, Any] | None:
+    try:
+        with tempfile.TemporaryDirectory(prefix="lm-cache-inspect-") as temp_dir:
+            copy_path = Path(temp_dir) / path.name
+            shutil.copy2(path, copy_path)
+            payload = sqlite_payload(copy_path, limit, allow_copy=False)
+            payload["path"] = str(path)
+            payload["inspected_copy"] = True
+            payload["original_error"] = original_error
+            return payload
+    except Exception:
+        return None
+
+
+def json_file_summary(path: Path) -> dict[str, Any]:
+    if not path.exists():
+        return {"exists": False}
+    data = load_json(path)
+    return {"exists": True, "summary": redact(summarize_value(data))}
+
+
+def model_roots(settings: dict[str, Any], active_library: str) -> dict[str, list[str]]:
+    roots: dict[str, list[str]] = {}
+    sources = [settings]
+    library = settings.get("libraries", {}).get(active_library)
+    if isinstance(library, dict):
+        sources.insert(0, library)
+    for source in sources:
+        folder_paths = source.get("folder_paths")
+        if isinstance(folder_paths, dict):
+            for key, value in folder_paths.items():
+                roots.setdefault(key, []).extend(normalize_path_list(value))
+    for default_key, folder_key in (
+        ("default_lora_root", "loras"),
+        ("default_checkpoint_root", "checkpoints"),
+        ("default_embedding_root", "embeddings"),
+        ("default_unet_root", "unet"),
+    ):
+        value = settings.get(default_key)
+        if isinstance(value, str) and value:
+            roots.setdefault(folder_key, []).append(expand_path(value))
+    return {key: dedupe(values) for key, values in roots.items()}
+
+
+def resolve_recipes_root(settings: dict[str, Any], active_library: str) -> Path | None:
+    recipes_path = settings.get("recipes_path")
+    library = settings.get("libraries", {}).get(active_library)
+    if isinstance(library, dict) and isinstance(library.get("recipes_path"), str):
+        recipes_path = library["recipes_path"] or recipes_path
+    if isinstance(recipes_path, str) and recipes_path.strip():
+        return Path(expand_path(recipes_path.strip()))
+    lora_roots = model_roots(settings, active_library).get("loras") or []
+    return Path(lora_roots[0]) / "recipes" if lora_roots else None
+
+
+def example_images_payload(settings: dict[str, Any], active_library: str) -> dict[str, Any]:
+    root = settings.get("example_images_path") or ""
+    libraries = settings.get("libraries")
+    library_count = len(libraries) if isinstance(libraries, dict) else 0
+    scoped = library_count > 1
+    root_path = Path(expand_path(root)) if isinstance(root, str) and root else None
+    library_root = root_path / sanitize_library_name(active_library) if root_path and scoped else root_path
+    return {
+        "root": str(root_path or ""),
+        "uses_library_scoped_folders": scoped,
+        "library_root": str(library_root or ""),
+    }
+
+
+def count_recipe_files(root: Path | None) -> int:
+    if not root or not root.exists():
+        return 0
+    return sum(1 for _ in root.rglob("*.recipe.json"))
+
+
+def normalize_path_list(value: Any) -> list[str]:
+    if isinstance(value, str):
+        return [expand_path(value)] if value else []
+    if isinstance(value, list):
+        return [expand_path(item) for item in value if isinstance(item, str) and item]
+    return []
+
+
+def expand_path(value: str) -> str:
+    return str(Path(value).expanduser().resolve(strict=False))
+
+
+def sanitize_library_name(name: str) -> str:
+    safe = re.sub(r"[^A-Za-z0-9_.-]", "_", name or "default")
+    return safe or "default"
+
+
+def dedupe(values: list[str]) -> list[str]:
+    seen: set[str] = set()
+    result: list[str] = []
+    for value in values:
+        if value not in seen:
+            result.append(value)
+            seen.add(value)
+    return result
+
+
+def redact(value: Any, key: str = "") -> Any:
+    if key and SECRET_PATTERN.search(key):
+        return "<redacted>"
+    if isinstance(value, dict):
+        return {str(k): redact(v, str(k)) for k, v in value.items()}
+    if isinstance(value, list):
+        return [redact(item) for item in value]
+    return value
+
+
+def summarize_value(value: Any) -> Any:
+    if isinstance(value, dict):
+        return {key: summarize_value(item) for key, item in value.items()}
+    if isinstance(value, list):
+        return {
+            "type": "array",
+            "length": len(value),
+            "first": summarize_value(value[0]) if value else None,
+        }
+    return value
+
+
+def quote_identifier(identifier: str) -> str:
+    return '"' + identifier.replace('"', '""') + '"'
+
+
+def is_internal_sqlite_table(table: str) -> bool:
+    return table.startswith("sqlite_") or table.endswith(("_data", "_idx", "_docsize", "_config", "_content"))
+
+
+def print_json(payload: Any) -> None:
+    json.dump(payload, sys.stdout, indent=2, ensure_ascii=False)
+    sys.stdout.write("\n")
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

.docs/batch-import-design.md

@@ -1,153 +0,0 @@
-# Recipe Batch Import Feature Design
-
-## Overview
-Enable users to import multiple images as recipes in a single operation, rather than processing them individually. This feature addresses the need for efficient bulk recipe creation from existing image collections.
-
-## Architecture
-
-```
-┌─────────────────────────────────────────────────────────────────┐
-│                        Frontend                                  │
-├─────────────────────────────────────────────────────────────────┤
-│  BatchImportManager.js                                          │
-│  ├── InputCollector (收集URL列表/目录路径)                        │
-│  ├── ConcurrencyController (自适应并发控制)                       │
-│  ├── ProgressTracker (进度追踪)                                   │
-│  └── ResultAggregator (结果汇总)                                  │
-├─────────────────────────────────────────────────────────────────┤
-│  batch_import_modal.html                                        │
-│  └── 批量导入UI组件                                              │
-├─────────────────────────────────────────────────────────────────┤
-│  batch_import_progress.css                                      │
-│  └── 进度显示样式                                                │
-└─────────────────────────────────────────────────────────────────┘
-                              │
-                              ▼
-┌─────────────────────────────────────────────────────────────────┐
-│                        Backend                                   │
-├─────────────────────────────────────────────────────────────────┤
-│  py/routes/handlers/recipe_handlers.py                          │
-│  ├── start_batch_import() - 启动批量导入                         │
-│  ├── get_batch_import_progress() - 查询进度                      │
-│  └── cancel_batch_import() - 取消导入                            │
-├─────────────────────────────────────────────────────────────────┤
-│  py/services/batch_import_service.py                            │
-│  ├── 自适应并发执行                                              │
-│  ├── 结果汇总                                                    │
-│  └── WebSocket进度广播                                           │
-└─────────────────────────────────────────────────────────────────┘
-```
-
-## API Endpoints
-
-| 端点 | 方法 | 说明 |
-|------|------|------|
-| `/api/lm/recipes/batch-import/start` | POST | 启动批量导入，返回 operation_id |
-| `/api/lm/recipes/batch-import/progress` | GET | 查询进度状态 |
-| `/api/lm/recipes/batch-import/cancel` | POST | 取消导入 |
-
-## Backend Implementation Details
-
-### BatchImportService
-
-Location: `py/services/batch_import_service.py`
-
-Key classes:
-- `BatchImportItem`: Dataclass for individual import item
-- `BatchImportProgress`: Dataclass for tracking progress
-- `BatchImportService`: Main service class
-
-Features:
-- Adaptive concurrency control (adjusts based on success/failure rate)
-- WebSocket progress broadcasting
-- Graceful error handling (individual failures don't stop the batch)
-- Result aggregation
-
-### WebSocket Message Format
-
-```json
-{
-    "type": "batch_import_progress",
-    "operation_id": "xxx",
-    "total": 50,
-    "completed": 23,
-    "success": 21,
-    "failed": 2,
-    "skipped": 0,
-    "current_item": "image_024.png",
-    "status": "running"
-}
-```
-
-### Input Types
-
-1. **URL List**: Array of URLs (http/https)
-2. **Local Paths**: Array of local file paths
-3. **Directory**: Path to directory with optional recursive flag
-
-### Error Handling
-
-- Invalid URLs/paths: Skip and record error
-- Download failures: Record error, continue
-- Metadata extraction failures: Mark as "no metadata"
-- Duplicate detection: Option to skip duplicates
-
-## Frontend Implementation Details (TODO)
-
-### UI Components
-
-1. **BatchImportModal**: Main modal with tabs for URLs/Directory input
-2. **ProgressDisplay**: Real-time progress bar and status
-3. **ResultsSummary**: Final results with success/failure breakdown
-
-### Adaptive Concurrency Controller
-
-```javascript
-class AdaptiveConcurrencyController {
-    constructor(options = {}) {
-        this.minConcurrency = options.minConcurrency || 1;
-        this.maxConcurrency = options.maxConcurrency || 5;
-        this.currentConcurrency = options.initialConcurrency || 3;
-    }
-
-    adjustConcurrency(taskDuration, success) {
-        if (success && taskDuration < 1000 && this.currentConcurrency < this.maxConcurrency) {
-            this.currentConcurrency = Math.min(this.currentConcurrency + 1, this.maxConcurrency);
-        }
-        if (!success || taskDuration > 10000) {
-            this.currentConcurrency = Math.max(this.currentConcurrency - 1, this.minConcurrency);
-        }
-        return this.currentConcurrency;
-    }
-}
-```
-
-## File Structure
-
-```
-Backend (implemented):
-├── py/services/batch_import_service.py            # 后端服务
-├── py/routes/handlers/batch_import_handler.py     # API处理器 (added to recipe_handlers.py)
-├── tests/services/test_batch_import_service.py    # 单元测试
-└── tests/routes/test_batch_import_routes.py       # API集成测试
-
-Frontend (TODO):
-├── static/js/managers/BatchImportManager.js       # 主管理器
-├── static/js/managers/batch/                       # 子模块
-│   ├── ConcurrencyController.js                    # 并发控制
-│   ├── ProgressTracker.js                          # 进度追踪
-│   └── ResultAggregator.js                         # 结果汇总
-├── static/css/components/batch-import-modal.css   # 样式
-└── templates/components/batch_import_modal.html    # Modal模板
-```
-
-## Implementation Status
-
-- [x] Backend BatchImportService
-- [x] Backend API handlers
-- [x] WebSocket progress broadcasting
-- [x] Unit tests
-- [x] Integration tests
-- [ ] Frontend BatchImportManager
-- [ ] Frontend UI components
-- [ ] E2E tests

.github/ISSUE_TEMPLATE/feature_request.md

@@ -13,8 +13,5 @@ A clear and concise description of what the problem is. Ex. I'm always frustrate
 **Describe the solution you'd like**
 A clear and concise description of what you want to happen.
 
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
 **Additional context**
 Add any other context or screenshots about the feature request here.

.gitignore

@@ -7,15 +7,24 @@ py/run_test.py
 .vscode/
 cache/
 civitai/
+stats/
+wildcards/
+backups/
+logs/
 node_modules/
 coverage/
 .coverage
 model_cache/
 
-# agent
+# agent / dev tooling
 .opencode/
 .claude/
+.sisyphus/
 .codex
+.omo
+reasonix.toml
+.reasonix/
+.codegraph/
 
 # Vue widgets development cache (but keep build output)
 vue-widgets/node_modules/
@@ -24,3 +33,10 @@ vue-widgets/dist/
 
 # Hypothesis test cache
 .hypothesis/
+
+# 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/

.omo/plans/embeddings-hybrid-approach.md

@@ -0,0 +1,181 @@
+# Embeddings Usage Tracking — Hybrid Approach (Plan C)
+
+> **Status**: Reference document for future implementation
+> **Current implementation**: Plan A (prompt text parsing only, see `usage_stats.py:_process_embeddings`)
+> **Next step**: Add Plan B as a supplement when edge-case coverage is needed
+
+## Problem
+
+Embeddings in ComfyUI are not loaded through dedicated ComfyUI nodes like LoRAs or
+Checkpoints. They are resolved during CLIP tokenization when the prompt text contains
+`embedding:<name>` syntax (see `comfy/sd1_clip.py:SDTokenizer.tokenize_with_weights`).
+
+This means the existing metadata_collector hook (which intercepts node execution via
+`_map_node_over_list`) cannot capture embeddings the same way it captures LoRAs and
+checkpoints — there is no "EmbeddingLoader" node to intercept.
+
+## Solution Architecture
+
+The hybrid approach combines **two complementary mechanisms** to capture embedding
+usage from all possible paths.
+
+```
+┌─────────────────────────────────────────────────────────┐
+│                 Plan A (已实现)                          │
+│                                                         │
+│  MetadataRegistry.prompt_metadata["prompts"]            │
+│       │                                                  │
+│       ▼                                                  │
+│  _process_embeddings()                                   │
+│       │                                                  │
+│       ├─ Iterate all prompt node texts                   │
+│       ├─ regex extract "embedding:<name>"                │
+│       ├─ resolve name → sha256 via EmbeddingScanner      │
+│       └─ UsageStats.stats["embeddings"][sha256]++        │
+│                                                         │
+│  Coverage: ~95% — all CLIPTextEncode/Flux/etc nodes     │
+│                                                         │
+│  Gap: Custom nodes that load embeddings programmatically │
+│       without putting embedding:name in prompt text      │
+└─────────────────────────────────────────────────────────┘
+
+                         +
+                         ↓  (future: enable Plan B when needed)
+
+┌─────────────────────────────────────────────────────────┐
+│                 Plan B (未来 — monkey-patch)              │
+│                                                         │
+│  comfy/sd1_clip.py:load_embed()                         │
+│       │                                                  │
+│       ▼                                                  │
+│  Monkey-patch intercepts EVERY embedding file load       │
+│       │                                                  │
+│       ├─ Records embedding_name + success/failure        │
+│       ├─ Associates with current prompt_id (via registry)│
+│       └─ Feeds into UsageStats same as Plan A            │
+│                                                         │
+│  Coverage: 100% — catches ALL embedding loads            │
+│                                                         │
+│  Cost: Requires patching into ComfyUI internals          │
+│        (sd1_clip.py, sdxl_clip.py, some text_encoders)   │
+└─────────────────────────────────────────────────────────┘
+```
+
+## Plan B Detail — Monkey-patch `load_embed`
+
+### Target Function
+
+**`comfy.sd1_clip.load_embed(embedding_name, embedding_directory, embedding_size, embed_key=None)`**
+at line 415 of `sd1_clip.py`.
+
+This is the **single choke point** for all embedding file loads in ComfyUI. Every
+CLIP variant (SD1, SDXL, SD3, Flux) calls this same function.
+
+### Implementation Sketch
+
+```python
+# In metadata_collector/metadata_hook.py (or a new module)
+import comfy.sd1_clip as sd1_clip
+
+_original_load_embed = sd1_clip.load_embed
+
+def _patched_load_embed(embedding_name, embedding_directory, embedding_size, embed_key=None):
+    result = _original_load_embed(
+        embedding_name, embedding_directory, embedding_size, embed_key
+    )
+    if result is not None:
+        _record_embedding_usage(embedding_name)
+    return result
+
+sd1_clip.load_embed = _patched_load_embed
+```
+
+### Prompt ID Association
+
+The challenge is associating the `load_embed` call with the current `prompt_id`.
+Options:
+
+1. **Thread-local / contextvar**: Store current `prompt_id` in a `contextvars.ContextVar`
+   that the metadata_collector sets at the start of each prompt execution.
+
+2. **MetadataRegistry singleton**: The MetadataRegistry already has `current_prompt_id`.
+   The patch can read it directly since both run in the same thread.
+
+3. **Lazy aggregation**: Instead of associating with prompt_id at load time, collect
+   all loaded embedding names in a global set during execution, then flush to
+   UsageStats after the prompt completes.
+
+### Files to Patch
+
+| File | Function | Coverage |
+|------|----------|----------|
+| `comfy/sd1_clip.py:415` | `load_embed()` | Primary — SD1.x, SDXL, SD3, Flux |
+| `comfy/sdxl_clip.py` | Not needed (calls `sd1_clip.SDTokenizer`) | — |
+| `comfy/text_encoders/sd3_clip.py` | Not needed (calls `sd1_clip.SDTokenizer`) | — |
+| `comfy/text_encoders/flux.py` | Not needed (calls `sd1_clip.SDTokenizer`) | — |
+
+The SD1 tokenizer is the base class for all CLIP variants' tokenizers, so patching
+`load_embed` covers them all.
+
+### Edge Cases
+
+| Edge Case | Plan A | Plan B |
+|-----------|--------|--------|
+| `embedding:name` in CLIPTextEncode | ✅ | ✅ |
+| `embedding:name` in CLIPTextEncodeFlux | ✅ | ✅ |
+| `embedding:name` in PromptLM (LoRA Manager) | ✅ | ✅ |
+| `embedding:name` in WAS_Text_to_Conditioning | ✅ | ✅ |
+| Custom node that loads embedding programmatically | ❌ | ✅ |
+| Embedding loaded multiple times in same prompt | ✅ (dedup via set) | ✅ (dedup via set) |
+| Embedding file not found | N/A | ✅ (can log) |
+| Embedding dimension mismatch | N/A | ✅ (can log) |
+| Text encoder with non-standard tokenizer (LLaMA, T5...) | Partial | ✅ (if it calls load_embed) |
+
+## Migration Path: Standalone → Hybrid
+
+### Phase 1 — Plan A (当前状态)
+- Prompt text parsing only
+- No monkey-patching required
+- Covers all standard workflows
+
+### Phase 2 — Enable Plan B (未来工作)
+1. Add monkey-patch of `load_embed` in `metadata_collector/metadata_hook.py` (alongside
+   the existing `_map_node_over_list` hook)
+2. Collect loaded embedding names in a `set()` on the registry
+3. In `UsageStats._process_embeddings()`, merge the Plan A results (from prompt text)
+   with the Plan B results (from the patch)
+4. Add `prompt_data` field on MetadataRegistry to store loaded embeddings per prompt
+
+### Deduplication
+
+```python
+# Merge Plan A + Plan B results in _process_embeddings
+plan_a_names = extract_from_prompt_texts(prompts_data)
+plan_b_names = registry.get_loaded_embeddings(prompt_id)
+
+all_names = plan_a_names | plan_b_names
+```
+
+## Testing the Hybrid
+
+| Scenario | What to verify |
+|----------|---------------|
+| Standard `embedding:name` in prompt | Plan A captures it |
+| Embedding loaded by custom node script | Plan B captures it |
+| Both paths fire for same embedding | No double-counting (dedup) |
+| Embedding name resolves to hash | EmbeddingScanner.get_hash_by_filename works |
+| No embedding scanner available | Graceful skip, no crash |
+| Missing embedding file | Plan B logs warning, Plan A skips gracefully |
+| Empty prompt | No crash, no entries |
+| Standalone mode | Both plans disabled gracefully |
+
+## Key Files Reference
+
+| File | Role |
+|------|------|
+| `py/utils/usage_stats.py` | Core — `_process_embeddings()` for Plan A |
+| `py/metadata_collector/constants.py` | `EMBEDDINGS` category constant |
+| `py/metadata_collector/metadata_hook.py` | Future — monkey-patch for Plan B |
+| `py/services/embedding_scanner.py` | Hash resolution service |
+| `py/routes/stats_routes.py` | Already handles `usage_data.get('embeddings', {})` |
+| `comfy/sd1_clip.py` (ComfyUI) | `load_embed()` — Plan B target |

AGENTS.md

@@ -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
 

__init__.py

@@ -15,6 +15,8 @@ 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.metadata_collector import init as init_metadata_collector
 except (
     ImportError
@@ -56,6 +58,10 @@ 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
     init_metadata_collector = importlib.import_module("py.metadata_collector").init
 
 NODE_CLASS_MAPPINGS = {
@@ -75,6 +81,8 @@ NODE_CLASS_MAPPINGS = {
     LoraPoolLM.NAME: LoraPoolLM,
     LoraRandomizerLM.NAME: LoraRandomizerLM,
     LoraCyclerLM.NAME: LoraCyclerLM,
+    LoraInfoLM.NAME: LoraInfoLM,
+    LoraSyntaxToPath.NAME: LoraSyntaxToPath,
 }
 
 WEB_DIRECTORY = "./web/comfyui"

docs/LM-Extension-Wiki.md

@@ -1,183 +0,0 @@
-## Overview
-
-The **LoRA Manager Civitai Extension** is a Browser extension designed to work seamlessly with [LoRA Manager](https://github.com/willmiao/ComfyUI-Lora-Manager) to significantly enhance your browsing experience on [Civitai](https://civitai.com). With this extension, you can:
-
-✅ Instantly see which models are already present in your local library  
-✅ Download new models with a single click  
-✅ Manage downloads efficiently with queue and parallel download support  
-✅ Keep your downloaded models automatically organized according to your custom settings    
-
-![Civitai Models page](https://github.com/willmiao/ComfyUI-Lora-Manager/blob/main/wiki-images/civitai-models-page.png) 
-
-**Update:** It now also supports browsing on [CivArchive](https://civarchive.com/) (formerly CivitaiArchive). 
-
-![CivArchive Models page](https://github.com/willmiao/ComfyUI-Lora-Manager/blob/main/wiki-images/civarchive-models-page.png)  
-
----
-
-## Why Supporter Access?
-
-LoRA Manager is built with love for the Stable Diffusion and ComfyUI communities. Your support makes it possible for me to keep improving and maintaining the tool full-time.
-
-Supporter-exclusive features help ensure the long-term sustainability of LoRA Manager, allowing continuous updates, new features, and better performance for everyone.
-
-Every contribution directly fuels development and keeps the core LoRA Manager free and open-source. In addition to monthly supporters, one-time donation supporters will also receive a license key, with the duration scaling according to the contribution amount. Thank you for helping keep this project alive and growing. ❤️
-
-
----
-
-## Installation
-
-### Supported Browsers & Installation Methods
-
-| Browser            | Installation Method                                                                 |
-|--------------------|-------------------------------------------------------------------------------------|
-| **Google Chrome**   | [Chrome Web Store link](https://chromewebstore.google.com/detail/capigligggeijgmocnaflanlbghnamgm?utm_source=item-share-cb) |
-| **Microsoft Edge**  | Install via Chrome Web Store (compatible)                                          |
-| **Brave Browser**   | Install via Chrome Web Store (compatible)                                          |
-| **Opera**           | Install via Chrome Web Store (compatible)                                          |
-| **Firefox**         | <div id="firefox-install" class="install-ok"><a href="https://github.com/willmiao/lm-civitai-extension-firefox/releases/latest/download/extension.xpi">📦 Install Firefox Extension (reviewed and verified by Mozilla)</a></div>             |
-
-For non-Chrome browsers (e.g., Microsoft Edge), you can typically install extensions from the Chrome Web Store by following these steps: open the extension’s Chrome Web Store page, click 'Get extension', then click 'Allow' when prompted to enable installations from other stores, and finally click 'Add extension' to complete the installation.
-
----
-
-## Privacy & Security
-
-I understand concerns around browser extensions and privacy, and I want to be fully transparent about how the **LM Civitai Extension** works:
-
-- **Reviewed and Verified**  
-  This extension has been **manually reviewed and approved by the Chrome Web Store**. The Firefox version uses the **exact same code** (only the packaging format differs) and has passed **Mozilla’s Add-on review**.
-
-- **Minimal Network Access**  
-  The only external server this extension connects to is:  
-  **`https://willmiao.shop`** — used solely for **license validation**.
-
-  It does **not collect, transmit, or store any personal or usage data**.  
-  No browsing history, no user IDs, no analytics, no hidden trackers.
-
-- **Local-Only Model Detection**  
-  Model detection and LoRA Manager communication all happen **locally** within your browser, directly interacting with your local LoRA Manager backend.
-
-I value your trust and are committed to keeping your local setup private and secure. If you have any questions, feel free to reach out!
-
----
-
-## How to Use
-
-After installing the extension, you'll automatically receive a **7-day trial** to explore all features.
-
-When the extension is correctly installed and your license is valid:
-
-- Open **Civitai**, and you'll see visual indicators added by the extension on model cards, showing:
-  - ✅ Models already present in your local library  
-  - ⬇️ A download button for models not in your library  
-
-Clicking the download button adds the corresponding model version to the download queue, waiting to be downloaded. You can set up to **5 models to download simultaneously**.
-
-### Visual Indicators Appear On:
-
-- **Home Page** — Featured models  
-- **Models Page**  
-- **Creator Profiles** — If the creator has set their models to be visible  
-- **Recommended Resources** — On individual model pages  
-
-### Version Buttons on Model Pages
-
-On a specific model page, visual indicators also appear on version buttons, showing which versions are already in your local library.
-
-**Starting from v0.4.8**, model pages use a dedicated download button for better compatibility. When switching to a specific version by clicking a version button:
-
-- The new **dedicated download button** directly triggers download via **LoRA Manager**
-- The **original download button** remains unchanged for standard browser downloads
-
-![Civitai Model Page](https://github.com/willmiao/ComfyUI-Lora-Manager/blob/main/wiki-images/civitai-model-page.png)
-
-### Hide Models Already in Library (Beta)
-
-**New in v0.4.8**: A new **Hide models already in library (Beta)** option makes it easier to focus on models you haven't added yet. It can be enabled from Settings, or toggled quickly using **Ctrl + Shift + H** (macOS: **Command + Shift + H**).
-
-### Resources on Image Pages — now shows in-library indicators for image resources plus one-click recipe import
-
-- **One-Click Import Civitai Image as Recipe** — Import any Civitai image as a recipe with a single click in the Resources Used panel.
-- **Auto-Queue Missing Assets** — In Settings you can decide if LoRAs or checkpoints referenced by that image should automatically be added to your download queue.
-- **More Accurate Metadata** — Importing directly from the page is faster than copying inside LM and keeps on-site tags and other metadata perfectly aligned.
-
-![Civitai Image Page](https://github.com/willmiao/ComfyUI-Lora-Manager/blob/main/wiki-images/civitai-image-page.jpg)
-
-[![alt](url)](https://github.com/user-attachments/assets/41fd4240-c949-4f83-bde7-8f3124c09494)
-
----
-
-## Model Download Location & LoRA Manager Settings
-
-To use the **one-click download function**, you must first set:
-
-- Your **Default LoRAs Root**  
-- Your **Default Checkpoints Root**  
-
-These are set within LoRA Manager's settings.
-
-When everything is configured, downloaded model files will be placed in:  
-
-`<Default_Models_Root>/<Base_Model_of_the_Model>/<First_Tag_of_the_Model>`
-
-
-### Update: Default Path Customization (2025-07-21)  
-
-A new setting to customize the default download path has been added in the nightly version. You can now personalize where models are saved when downloading via the LM Civitai Extension.
-
-![Default Path Customization](https://github.com/willmiao/ComfyUI-Lora-Manager/blob/main/wiki-images/default-path-customization.png)
-
-The previous YAML path mapping file will be deprecated—settings will now be unified in settings.json to simplify configuration.
-
----
-
-## Backend Port Configuration
-
-If your **ComfyUI** or **LoRA Manager** backend is running on a port **other than the default 8188**, you must configure the backend port in the extension's settings.
-
-After correctly setting and saving the port, you'll see in the extension's header area:  
-- A **Healthy** status with the tooltip:  `Connected to LoRA Manager on port xxxx`
-
-
----
-
-## Advanced Usage
-
-### Connecting to a Remote LoRA Manager
-
-If your LoRA Manager is running on another computer, you can still connect from your browser using port forwarding.
-
-> **Why can't you set a remote IP directly?**
->
-> For privacy and security, the extension only requests access to `http://127.0.0.1/*`. Supporting remote IPs would require much broader permissions, which may be rejected by browser stores and could raise user concerns.
-
-**Solution: Port Forwarding with `socat`**
-
-On your browser computer, run:
-
-`socat TCP-LISTEN:8188,bind=127.0.0.1,fork TCP:REMOTE.IP.ADDRESS.HERE:8188`
-
-- Replace `REMOTE.IP.ADDRESS.HERE` with the IP of the machine running LoRA Manager.
-- Adjust the port if needed.
-
-This lets the extension connect to `127.0.0.1:8188` as usual, with traffic forwarded to your remote server.
-
-_Thanks to user **Temikus** for sharing this solution!_
-
----
-
-## Roadmap
-
-The extension will evolve alongside **LoRA Manager** improvements. Planned features include:
-
-- [x] Support for **additional model types** (e.g., embeddings)
-- [x] One-click **Recipe Import**
-- [x] Display of in-library status for all resources in the **Resources Used** section of the image page
-- [x] One-click **Auto-organize Models**
-- [x] **Hide models already in library (Beta)** - Focus on models you haven't added yet
-
-**Stay tuned — and thank you for your support!**
-
----

docs/agent_skills.md

@@ -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` |

docs/comfyui-dual-mode-widgets.md

@@ -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

py/config.py

@@ -1,5 +1,6 @@
 import os
 import platform
+import posixpath
 import threading
 from pathlib import Path
 import folder_paths  # type: ignore
@@ -7,6 +8,8 @@ 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
@@ -25,21 +28,57 @@ standalone_mode = (
 logger = logging.getLogger(__name__)
 
 
+def _normalize_root_identity(path: str) -> str:
+    """Normalize a root path for comparisons across slash styles."""
+
+    normalized = posixpath.normpath(path.strip().replace("\\", "/"))
+    if len(normalized) >= 2 and normalized[1] == ":":
+        return normalized.lower()
+    return normalized
+
+
 def _resolve_valid_default_root(
-    current: str, primary_paths: List[str], name: str
+    current: str, primary_paths: List[str], allowed_paths: List[str], name: str
 ) -> str:
-    """Return a valid default root from the current primary path set."""
+    """Return a valid default root from the current primary/extra path set."""
 
     valid_paths = [path for path in primary_paths if isinstance(path, str) and path.strip()]
-    if not valid_paths:
-        return ""
+    fallback_paths: List[str] = []
+    seen: Set[str] = set()
+    for path in allowed_paths:
+        if not isinstance(path, str):
+            continue
+        stripped = path.strip()
+        if not stripped:
+            continue
+        identity = _normalize_root_identity(stripped)
+        if identity in seen:
+            continue
+        seen.add(identity)
+        fallback_paths.append(stripped)
 
-    if current in valid_paths:
+    allowed = {_normalize_root_identity(path) for path in fallback_paths}
+
+    if current and _normalize_root_identity(current) in allowed:
         return current
 
+    if not valid_paths:
+        if not fallback_paths:
+            return ""
+        if current:
+            logger.info(
+                "Repaired stale %s from '%s' to '%s' because it is not present in primary or extra roots",
+                name,
+                current,
+                fallback_paths[0],
+            )
+        else:
+            logger.info("Auto-setting %s to '%s'", name, fallback_paths[0])
+        return fallback_paths[0]
+
     if current:
         logger.info(
-            "Repaired stale %s from '%s' to '%s'",
+            "Repaired stale %s from '%s' to '%s' because it is not present in primary or extra roots",
             name,
             current,
             valid_paths[0],
@@ -135,6 +174,11 @@ class Config:
         self.extra_unet_roots: List[str] = []
         self.extra_embeddings_roots: List[str] = []
         self.recipes_path: str = ""
+
+        # Load extra folder paths from active library settings before symlink scan
+        # so both primary and extra paths are discovered in a single pass.
+        self._load_extra_paths_from_settings()
+
         # Scan symbolic links during initialization
         self._initialize_symlink_mappings()
 
@@ -142,6 +186,98 @@ class Config:
             # Save the paths to settings.json when running in ComfyUI mode
             self.save_folder_paths_to_settings()
 
+    def _load_extra_paths_from_settings(self) -> None:
+        """Read extra folder paths from the active library and apply them.
+
+        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 via ``folder_paths.get_folder_paths``.
+        """
+        try:
+            from .services.settings_manager import get_settings_manager
+
+            settings_manager = get_settings_manager()
+            library_name = settings_manager.get_active_library_name()
+            libraries = settings_manager.get_libraries()
+
+            if not library_name or library_name not in libraries:
+                return
+
+            library_config = libraries[library_name]
+            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
+
+            extra_lora = extra_folder_paths.get("loras", []) or []
+            extra_checkpoint = extra_folder_paths.get("checkpoints", []) or []
+            extra_unet = extra_folder_paths.get("unet", []) or []
+            extra_embedding = extra_folder_paths.get("embeddings", []) or []
+
+            if not any([extra_lora, extra_checkpoint, extra_unet, extra_embedding]):
+                return
+
+            filtered_extra_lora = self._filter_overlapping_extra_lora_paths(
+                self.loras_roots, extra_lora
+            )
+            self.extra_loras_roots = self._prepare_lora_paths(filtered_extra_lora)
+            (
+                _,
+                self.extra_checkpoints_roots,
+                self.extra_unet_roots,
+            ) = self._prepare_checkpoint_paths(extra_checkpoint, extra_unet)
+            self.extra_embeddings_roots = self._prepare_embedding_paths(
+                extra_embedding
+            )
+
+            if self.extra_loras_roots:
+                logger.info(
+                    "Found extra LoRA roots:"
+                    + "\n - "
+                    + "\n - ".join(self.extra_loras_roots)
+                )
+            if self.extra_checkpoints_roots:
+                logger.info(
+                    "Found extra checkpoint roots:"
+                    + "\n - "
+                    + "\n - ".join(self.extra_checkpoints_roots)
+                )
+            if self.extra_unet_roots:
+                logger.info(
+                    "Found extra diffusion model roots:"
+                    + "\n - "
+                    + "\n - ".join(self.extra_unet_roots)
+                )
+            if self.extra_embeddings_roots:
+                logger.info(
+                    "Found extra embedding roots:"
+                    + "\n - "
+                    + "\n - ".join(self.extra_embeddings_roots)
+                )
+
+            logger.info(
+                "Applied library settings for '%s' with extra paths: loras=%s, "
+                "checkpoints=%s, embeddings=%s",
+                library_name,
+                extra_lora,
+                extra_checkpoint,
+                extra_embedding,
+            )
+
+        except Exception as exc:
+            logger.debug(
+                "Could not load extra paths from library settings: %s", exc
+            )
+
     def save_folder_paths_to_settings(self):
         """Persist ComfyUI-derived folder paths to the multi-library settings."""
         try:
@@ -223,42 +359,120 @@ 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 []),
+                list(self.loras_roots or [])
+                + list(comfy_library.get("extra_folder_paths", {}).get("loras", []) or []),
                 "default_lora_root",
             )
 
             default_checkpoint_root = _resolve_valid_default_root(
                 comfy_library.get("default_checkpoint_root", ""),
                 list(self.checkpoints_roots or []),
+                list(self.checkpoints_roots or [])
+                + list(comfy_library.get("extra_folder_paths", {}).get("checkpoints", []) or []),
                 "default_checkpoint_root",
             )
 
             default_embedding_root = _resolve_valid_default_root(
                 comfy_library.get("default_embedding_root", ""),
                 list(self.embeddings_roots or []),
+                list(self.embeddings_roots or [])
+                + list(comfy_library.get("extra_folder_paths", {}).get("embeddings", []) or []),
                 "default_embedding_root",
             )
 
             metadata = dict(comfy_library.get("metadata", {}))
             metadata.setdefault("display_name", "ComfyUI")
             metadata["source"] = "comfyui"
+            extra_folder_paths = {}
+            if isinstance(comfy_library, Mapping):
+                existing_extra_paths = comfy_library.get("extra_folder_paths", {})
+                if isinstance(existing_extra_paths, Mapping):
+                    extra_folder_paths = {
+                        key: list(value) if isinstance(value, list) else []
+                        for key, value in existing_extra_paths.items()
+                    }
+
+            active_library_name = settings_service.get_active_library_name()
+            should_activate = (
+                active_library_name == "comfyui"
+                or self._should_activate_comfy_library(libraries, libraries_changed)
+            )
 
             settings_service.upsert_library(
                 "comfyui",
                 folder_paths=target_folder_paths,
+                extra_folder_paths=extra_folder_paths,
                 default_lora_root=default_lora_root,
                 default_checkpoint_root=default_checkpoint_root,
                 default_embedding_root=default_embedding_root,
                 metadata=metadata,
-                activate=True,
+                activate=should_activate,
             )
 
-            logger.info("Updated 'comfyui' library with current folder paths")
+            if should_activate:
+                logger.info("Updated 'comfyui' library with current folder paths")
+            else:
+                logger.info(
+                    "Updated 'comfyui' library with current folder paths without activating it"
+                )
         except Exception as e:
             logger.warning(f"Failed to save folder paths: {e}")
 
+    def _should_activate_comfy_library(
+        self, libraries: Mapping[str, Any], libraries_changed: bool
+    ) -> bool:
+        """Return whether startup sync should make the ComfyUI library active."""
+
+        if libraries_changed:
+            return True
+        if not libraries:
+            return True
+        return "comfyui" in libraries and len(libraries) == 1
+
     def _is_link(self, path: str) -> bool:
         try:
             if os.path.islink(path):
@@ -1210,4 +1424,20 @@ 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"
+if _CONFIG_SENTINEL in _sys.modules:
+    # Re-import: reuse the existing singleton from the sentinel.
+    config: Config = _sys.modules[_CONFIG_SENTINEL].config  # type: ignore[valid-type]
+else:
+    config: Config = Config()
+    # Register the sentinel so re-imports of py.config find us.
+    _sentinel_mod = _types.ModuleType(_CONFIG_SENTINEL)
+    _sentinel_mod.config = config
+    _sys.modules[_CONFIG_SENTINEL] = _sentinel_mod

py/lora_manager.py

@@ -33,6 +33,7 @@ from .utils.example_images_migration import ExampleImagesMigration
 from .services.websocket_manager import ws_manager
 from .services.example_images_cleanup_service import ExampleImagesCleanupService
 from .middleware.csp_middleware import relax_csp_for_remote_media
+from .middleware.error_middleware import api_json_error
 
 logger = logging.getLogger(__name__)
 
@@ -76,6 +77,11 @@ class LoraManager:
         """Initialize and register all routes using the new refactored architecture"""
         app = PromptServer.instance.app
 
+        # Register JSON error middleware for /api/* routes as the outermost
+        # middleware so it catches errors from all other middlewares.
+        if api_json_error not in app.middlewares:
+            app.middlewares.insert(0, api_json_error)
+
         if relax_csp_for_remote_media not in app.middlewares:
             # Ensure CSP relaxer executes after ComfyUI's block_external_middleware so it can
             # see and extend the restrictive header instead of being overwritten by it.
@@ -184,44 +190,15 @@ class LoraManager:
     async def _initialize_services(cls):
         """Initialize all services using the ServiceRegistry"""
         try:
-            # Apply library settings to load extra folder paths before scanning
-            # Only apply if extra paths haven't been loaded yet (preserves test mocks)
-            try:
-                from .services.settings_manager import get_settings_manager
-
-                settings_manager = get_settings_manager()
-                library_name = settings_manager.get_active_library_name()
-                libraries = settings_manager.get_libraries()
-                if library_name and library_name in libraries:
-                    library_config = libraries[library_name]
-                    # Only apply settings if extra paths are not already configured
-                    # This preserves values set by tests via monkeypatch
-                    extra_paths = library_config.get("extra_folder_paths", {})
-                    has_extra_paths = (
-                        config.extra_loras_roots
-                        or config.extra_checkpoints_roots
-                        or config.extra_unet_roots
-                        or config.extra_embeddings_roots
-                    )
-                    if not has_extra_paths and any(extra_paths.values()):
-                        config.apply_library_settings(library_config)
-                        logger.info(
-                            "Applied library settings for '%s' with extra paths: loras=%s, checkpoints=%s, embeddings=%s",
-                            library_name,
-                            extra_paths.get("loras", []),
-                            extra_paths.get("checkpoints", []),
-                            extra_paths.get("embeddings", []),
-                        )
-            except Exception as exc:
-                logger.warning(
-                    "Failed to apply library settings during initialization: %s", exc
-                )
-
             # Initialize CivitaiClient first to ensure it's ready for other services
             await ServiceRegistry.get_civitai_client()
 
             # Register DownloadManager with ServiceRegistry
             await ServiceRegistry.get_download_manager()
+
+            # Initialize DownloadQueueService for persistent queue/history
+            await ServiceRegistry.get_download_queue_service()
+
             await ServiceRegistry.get_backup_service()
 
             from .services.metadata_service import initialize_metadata_providers
@@ -231,6 +208,10 @@ 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()
@@ -459,5 +440,21 @@ class LoraManager:
         try:
             logger.info("LoRA Manager: Cleaning up services")
 
+            # Cancel any in-flight scanner initialization tasks so thread-pool
+            # workers (e.g. _initialize_cache_sync) can break out of their loops
+            # when the server shuts down (e.g. Ctrl+C on WSL).
+            for name in ("lora_scanner", "checkpoint_scanner", "embedding_scanner"):
+                scanner = ServiceRegistry.get_service_sync(name)
+                if scanner is not None and hasattr(scanner, "cancel_task"):
+                    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)

py/metadata_collector/constants.py

@@ -5,9 +5,10 @@ MODELS = "models"
 PROMPTS = "prompts"
 SAMPLING = "sampling"
 LORAS = "loras"
+EMBEDDINGS = "embeddings"
 SIZE = "size"
 IMAGES = "images"
 IS_SAMPLER = "is_sampler"  # New constant to mark sampler nodes
 
 # Complete list of categories to track
-METADATA_CATEGORIES = [MODELS, PROMPTS, SAMPLING, LORAS, SIZE, IMAGES]
+METADATA_CATEGORIES = [MODELS, PROMPTS, SAMPLING, LORAS, EMBEDDINGS, SIZE, IMAGES]

py/metadata_collector/metadata_processor.py

@@ -352,50 +352,101 @@ class MetadataProcessor:
         
         # Check if we have stored conditioning objects for this sampler
         if sampler_id in metadata.get(PROMPTS, {}) and (
-            "pos_conditioning" in metadata[PROMPTS][sampler_id] or 
-            "neg_conditioning" in metadata[PROMPTS][sampler_id]):
-            
+            "pos_conditioning" in metadata[PROMPTS][sampler_id] or
+            "neg_conditioning" in metadata[PROMPTS][sampler_id]
+        ):
             pos_conditioning = metadata[PROMPTS][sampler_id].get("pos_conditioning")
             neg_conditioning = metadata[PROMPTS][sampler_id].get("neg_conditioning")
-            
-            # Helper function to recursively find prompt text for a conditioning object
-            def find_prompt_text_for_conditioning(conditioning_obj, is_positive=True):
+
+            def extend_unique(target, values):
+                for value in values:
+                    if value and value not in target:
+                        target.append(value)
+
+            # Helper function to recursively find prompt texts for a conditioning object.
+            # Transform nodes can map one output conditioning to multiple source conditionings.
+            def find_prompt_texts_for_conditioning(
+                conditioning_obj, is_positive=True, visited=None
+            ):
                 if conditioning_obj is None:
-                    return ""
-                    
+                    return []
+
+                if visited is None:
+                    visited = set()
+
+                conditioning_id = id(conditioning_obj)
+                if conditioning_id in visited:
+                    return []
+                visited.add(conditioning_id)
+
+                prompt_texts = []
+
                 # Try to match conditioning objects with those stored by extractors
                 for prompt_node_id, prompt_data in metadata[PROMPTS].items():
-                    # For nodes with single conditioning output
-                    if "conditioning" in prompt_data:
-                        if id(prompt_data["conditioning"]) == id(conditioning_obj):
-                            return prompt_data.get("text", "")
-                    
-                    # For nodes with separate pos_conditioning and neg_conditioning outputs (like TSC_EfficientLoader)
-                    if is_positive and "positive_encoded" in prompt_data:
-                        if id(prompt_data["positive_encoded"]) == id(conditioning_obj):
-                            if "positive_text" in prompt_data:
-                                return prompt_data["positive_text"]
-                            else:
-                                orig_conditioning = prompt_data.get("orig_pos_cond", None)
-                                if orig_conditioning is not None:
-                                    # Recursively find the prompt text for the original conditioning
-                                    return find_prompt_text_for_conditioning(orig_conditioning, is_positive=True)
-                    
-                    if not is_positive and "negative_encoded" in prompt_data:
-                        if id(prompt_data["negative_encoded"]) == id(conditioning_obj):
-                            if "negative_text" in prompt_data:
-                                return prompt_data["negative_text"]
-                            else:
-                                orig_conditioning = prompt_data.get("orig_neg_cond", None)
-                                if orig_conditioning is not None:
-                                    # Recursively find the prompt text for the original conditioning
-                                    return find_prompt_text_for_conditioning(orig_conditioning, is_positive=False)
-                
-                return ""
-            
+                    if not isinstance(prompt_data, dict):
+                        continue
+
+                    # For CLIP text nodes with a single conditioning output.
+                    if id(prompt_data.get("conditioning")) == conditioning_id:
+                        text = prompt_data.get("text", "")
+                        if text:
+                            extend_unique(prompt_texts, [text])
+
+                    # Generic provenance for passthrough/transform/combine nodes.
+                    for source in prompt_data.get("conditioning_sources", []):
+                        if id(source.get("output")) != conditioning_id:
+                            continue
+                        for input_conditioning in source.get("inputs", []):
+                            extend_unique(
+                                prompt_texts,
+                                find_prompt_texts_for_conditioning(
+                                    input_conditioning, is_positive, visited
+                                ),
+                            )
+
+                    # For nodes with separate pos_conditioning and neg_conditioning outputs
+                    # like TSC_EfficientLoader and existing ControlNet-style metadata.
+                    if (
+                        is_positive
+                        and id(prompt_data.get("positive_encoded")) == conditioning_id
+                    ):
+                        if prompt_data.get("positive_text"):
+                            extend_unique(prompt_texts, [prompt_data["positive_text"]])
+                        else:
+                            extend_unique(
+                                prompt_texts,
+                                find_prompt_texts_for_conditioning(
+                                    prompt_data.get("orig_pos_cond"),
+                                    is_positive=True,
+                                    visited=visited,
+                                ),
+                            )
+
+                    if (
+                        not is_positive
+                        and id(prompt_data.get("negative_encoded")) == conditioning_id
+                    ):
+                        if prompt_data.get("negative_text"):
+                            extend_unique(prompt_texts, [prompt_data["negative_text"]])
+                        else:
+                            extend_unique(
+                                prompt_texts,
+                                find_prompt_texts_for_conditioning(
+                                    prompt_data.get("orig_neg_cond"),
+                                    is_positive=False,
+                                    visited=visited,
+                                ),
+                            )
+
+                return prompt_texts
+
             # Find prompt texts using the helper function
-            result["prompt"] = find_prompt_text_for_conditioning(pos_conditioning, is_positive=True)
-            result["negative_prompt"] = find_prompt_text_for_conditioning(neg_conditioning, is_positive=False)
+            result["prompt"] = ", ".join(
+                find_prompt_texts_for_conditioning(pos_conditioning, is_positive=True)
+            )
+            result["negative_prompt"] = ", ".join(
+                find_prompt_texts_for_conditioning(neg_conditioning, is_positive=False)
+            )
             
         return result
     
@@ -509,8 +560,14 @@ class MetadataProcessor:
         
         params["loras"] = " ".join(lora_parts)
         
-        # Set default clip_skip value
-        params["clip_skip"] = "1"  # Common default
+        # Extract clip_skip from any SAMPLING node that provides it
+        for sampler_info in metadata.get(SAMPLING, {}).values():
+            clip_skip = sampler_info.get("parameters", {}).get("clip_skip")
+            if clip_skip is not None:
+                params["clip_skip"] = clip_skip
+                break
+        if params["clip_skip"] is None:
+            params["clip_skip"] = "1"
         
         return params
     

py/metadata_collector/node_extractors.py

@@ -144,6 +144,118 @@ class TSCCheckpointLoaderExtractor(NodeMetadataExtractor):
                 metadata[PROMPTS][node_id]["positive_encoded"] = positive_conditioning
                 metadata[PROMPTS][node_id]["negative_encoded"] = negative_conditioning
 
+
+class EasyComfyLoaderExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        if "ckpt_name" in inputs:
+            _store_checkpoint_metadata(metadata, node_id, inputs["ckpt_name"])
+
+        # Only extract from optional_lora_stack — skip the single lora_name to
+        # avoid double-counting LoRAs that come through the LORA_STACK path.
+        active_loras = []
+        optional_lora_stack = inputs.get("optional_lora_stack")
+        if optional_lora_stack is not None and isinstance(optional_lora_stack, (list, tuple)):
+            for item in optional_lora_stack:
+                if isinstance(item, (list, tuple)) and len(item) >= 2:
+                    lora_path = item[0]
+                    model_strength = item[1]
+                    lora_name = os.path.splitext(os.path.basename(lora_path))[0]
+                    active_loras.append({
+                        "name": lora_name,
+                        "strength": model_strength
+                    })
+
+        if active_loras:
+            metadata[LORAS][node_id] = {
+                "lora_list": active_loras,
+                "node_id": node_id
+            }
+
+        positive_text = inputs.get("positive", "")
+        negative_text = inputs.get("negative", "")
+
+        if positive_text or negative_text:
+            if node_id not in metadata[PROMPTS]:
+                metadata[PROMPTS][node_id] = {"node_id": node_id}
+            metadata[PROMPTS][node_id]["positive_text"] = positive_text
+            metadata[PROMPTS][node_id]["negative_text"] = negative_text
+
+        if "clip_skip" in inputs:
+            clip_skip = inputs["clip_skip"]
+            if node_id not in metadata[SAMPLING]:
+                metadata[SAMPLING][node_id] = {"parameters": {}, "node_id": node_id}
+            metadata[SAMPLING][node_id]["parameters"]["clip_skip"] = clip_skip
+
+        width = inputs.get("empty_latent_width")
+        height = inputs.get("empty_latent_height")
+        if width is not None and height is not None:
+            if SIZE not in metadata:
+                metadata[SIZE] = {}
+            metadata[SIZE][node_id] = {
+                "width": int(width),
+                "height": int(height),
+                "node_id": node_id
+            }
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        # outputs: [(pipe_dict, model, vae), ...]
+        if not outputs or not isinstance(outputs, list) or len(outputs) == 0:
+            return
+        first_output = outputs[0]
+        if not isinstance(first_output, tuple) or len(first_output) < 1:
+            return
+        pipe = first_output[0]
+        if not isinstance(pipe, dict):
+            return
+
+        positive_conditioning = pipe.get("positive")
+        negative_conditioning = pipe.get("negative")
+
+        if positive_conditioning is not None or negative_conditioning is not None:
+            if node_id not in metadata[PROMPTS]:
+                metadata[PROMPTS][node_id] = {"node_id": node_id}
+            if positive_conditioning is not None:
+                metadata[PROMPTS][node_id]["positive_encoded"] = positive_conditioning
+            if negative_conditioning is not None:
+                metadata[PROMPTS][node_id]["negative_encoded"] = negative_conditioning
+
+
+class EasyPreSamplingExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        sampling_params = {}
+        for key in ("steps", "cfg", "sampler_name", "scheduler", "denoise", "seed"):
+            if key in inputs:
+                sampling_params[key] = inputs[key]
+
+        metadata[SAMPLING][node_id] = {
+            "parameters": sampling_params,
+            "node_id": node_id,
+            IS_SAMPLER: True
+        }
+
+
+class EasySeedExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs or "seed" not in inputs:
+            return
+
+        metadata[SAMPLING][node_id] = {
+            "parameters": {"seed": inputs["seed"]},
+            "node_id": node_id,
+            IS_SAMPLER: False
+        }
+
+
 class CLIPTextEncodeExtractor(NodeMetadataExtractor):
     @staticmethod
     def extract(node_id, inputs, outputs, metadata):
@@ -163,6 +275,251 @@ class CLIPTextEncodeExtractor(NodeMetadataExtractor):
                 conditioning = outputs[0][0]
                 metadata[PROMPTS][node_id]["conditioning"] = conditioning
 
+
+class MyOriginalWaifuTextExtractor(NodeMetadataExtractor):
+    """Extractor for ComfyUI-MyOriginalWaifu TextProvider nodes."""
+
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        positive_text = inputs.get("positive", "")
+        negative_text = inputs.get("negative", "")
+
+        if positive_text or negative_text:
+            metadata[PROMPTS][node_id] = {
+                "positive_text": positive_text,
+                "negative_text": negative_text,
+                "node_id": node_id,
+            }
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple or len(output_tuple) < 2:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        prompt_metadata["positive_text"] = output_tuple[0]
+        prompt_metadata["negative_text"] = output_tuple[1]
+
+
+class MyOriginalWaifuClipExtractor(NodeMetadataExtractor):
+    """Extractor for ComfyUI-MyOriginalWaifu ClipProvider nodes."""
+
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        positive_text = inputs.get("positive", "")
+        negative_text = inputs.get("negative", "")
+
+        if positive_text or negative_text:
+            metadata[PROMPTS][node_id] = {
+                "positive_text": positive_text,
+                "negative_text": negative_text,
+                "node_id": node_id,
+            }
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple or len(output_tuple) < 2:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        prompt_metadata["positive_encoded"] = output_tuple[0]
+        prompt_metadata["negative_encoded"] = output_tuple[1]
+
+
+def _ensure_prompt_metadata(metadata, node_id):
+    if node_id not in metadata[PROMPTS]:
+        metadata[PROMPTS][node_id] = {"node_id": node_id}
+    return metadata[PROMPTS][node_id]
+
+
+def _first_output_tuple(outputs):
+    if not outputs or not isinstance(outputs, list) or len(outputs) == 0:
+        return None
+    first_output = outputs[0]
+    if isinstance(first_output, tuple):
+        return first_output
+    return None
+
+
+def _record_conditioning_source(
+    metadata, node_id, output_conditioning, input_conditionings
+):
+    if output_conditioning is None:
+        return
+
+    sources = [
+        conditioning for conditioning in input_conditionings if conditioning is not None
+    ]
+    if not sources:
+        return
+
+    prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+    prompt_metadata.setdefault("conditioning_sources", []).append(
+        {
+            "output": output_conditioning,
+            "inputs": sources,
+        }
+    )
+
+
+def _get_variable_name(inputs):
+    for key in ("key", "name", "variable_name", "tag", "text"):
+        value = inputs.get(key)
+        if isinstance(value, str) and value:
+            return value
+    return None
+
+
+def _get_node_variable_name(metadata, node_id, inputs):
+    variable_name = _get_variable_name(inputs)
+    if variable_name:
+        return variable_name
+
+    prompt = metadata.get("current_prompt")
+    original_prompt = getattr(prompt, "original_prompt", None)
+    if not original_prompt or node_id not in original_prompt:
+        return None
+
+    node_data = original_prompt[node_id]
+    variable_name = _get_variable_name(node_data.get("inputs", {}))
+    if variable_name:
+        return variable_name
+
+    widgets_values = node_data.get("widgets_values", [])
+    if widgets_values and isinstance(widgets_values[0], str):
+        return widgets_values[0]
+
+    return None
+
+
+class ControlNetApplyAdvancedExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        if inputs.get("positive") is not None:
+            prompt_metadata["orig_pos_cond"] = inputs["positive"]
+        if inputs.get("negative") is not None:
+            prompt_metadata["orig_neg_cond"] = inputs["negative"]
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        positive_input = prompt_metadata.get("orig_pos_cond")
+        negative_input = prompt_metadata.get("orig_neg_cond")
+
+        if len(output_tuple) >= 1:
+            prompt_metadata["positive_encoded"] = output_tuple[0]
+            _record_conditioning_source(
+                metadata, node_id, output_tuple[0], [positive_input]
+            )
+        if len(output_tuple) >= 2:
+            prompt_metadata["negative_encoded"] = output_tuple[1]
+            _record_conditioning_source(
+                metadata, node_id, output_tuple[1], [negative_input]
+            )
+
+
+class ConditioningCombineExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        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])
+
+        if input_conditionings:
+            prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+            prompt_metadata["orig_conditionings"] = input_conditionings
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple or len(output_tuple) < 1:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        output_conditioning = output_tuple[0]
+        prompt_metadata["conditioning"] = output_conditioning
+        _record_conditioning_source(
+            metadata,
+            node_id,
+            output_conditioning,
+            prompt_metadata.get("orig_conditionings", []),
+        )
+
+
+class SetNodeExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        variable_name = _get_node_variable_name(metadata, node_id, inputs)
+        conditioning = inputs.get("CONDITIONING")
+        if conditioning is None:
+            conditioning = inputs.get("conditioning")
+        if conditioning is None:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        prompt_metadata["conditioning"] = conditioning
+        if variable_name:
+            prompt_metadata["variable_name"] = variable_name
+            metadata[PROMPTS].setdefault("__conditioning_variables__", {})[
+                variable_name
+            ] = conditioning
+
+
+class GetNodeExtractor(NodeMetadataExtractor):
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        variable_name = _get_node_variable_name(metadata, node_id, inputs or {})
+        if variable_name:
+            prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+            prompt_metadata["variable_name"] = variable_name
+
+    @staticmethod
+    def update(node_id, outputs, metadata):
+        output_tuple = _first_output_tuple(outputs)
+        if not output_tuple or len(output_tuple) < 1:
+            return
+
+        prompt_metadata = _ensure_prompt_metadata(metadata, node_id)
+        output_conditioning = output_tuple[0]
+        prompt_metadata["conditioning"] = output_conditioning
+
+        variable_name = prompt_metadata.get("variable_name")
+        if not variable_name:
+            return
+
+        input_conditioning = metadata[PROMPTS].get("__conditioning_variables__", {}).get(
+            variable_name
+        )
+        _record_conditioning_source(
+            metadata, node_id, output_conditioning, [input_conditioning]
+        )
+
 # Base Sampler Extractor to reduce code redundancy
 class BaseSamplerExtractor(NodeMetadataExtractor):
     """Base extractor for sampler nodes with common functionality"""
@@ -544,6 +901,55 @@ class LoraLoaderManagerExtractor(NodeMetadataExtractor):
                 "node_id": node_id
             }
 
+class LoraTextLoaderManagerExtractor(NodeMetadataExtractor):
+    """Extract LoRA metadata from LoraTextLoaderLM (LoRA Text Loader).
+
+    The node accepts a `lora_syntax` STRING containing <lora:name:strength> tags
+    (same format as the ComfyUI prompt), plus an optional `lora_stack`.
+    This extractor parses the syntax string using the same regex as the node.
+    """
+    @staticmethod
+    def extract(node_id, inputs, outputs, metadata):
+        if not inputs:
+            return
+
+        active_loras = []
+
+        # Process lora_stack if available (optional input)
+        if "lora_stack" in inputs:
+            lora_stack = inputs.get("lora_stack", [])
+            for item in lora_stack:
+                # lora_stack entries are (path, model_strength, clip_strength) tuples
+                if isinstance(item, (list, tuple)) and len(item) >= 2:
+                    lora_path = item[0]
+                    model_strength = item[1]
+                    lora_name = os.path.splitext(os.path.basename(lora_path))[0]
+                    active_loras.append({
+                        "name": lora_name,
+                        "strength": round(float(model_strength), 2)
+                    })
+
+        # Process lora_syntax string input
+        if "lora_syntax" in inputs:
+            lora_syntax = inputs.get("lora_syntax", "")
+            if lora_syntax and isinstance(lora_syntax, str):
+                pattern = r"<lora:([^:>]+):([^:>]+)(?::([^:>]+))?>"
+                matches = re.findall(pattern, lora_syntax, re.IGNORECASE)
+                for match in matches:
+                    lora_name = match[0]
+                    model_strength = float(match[1])
+                    active_loras.append({
+                        "name": lora_name,
+                        "strength": round(model_strength, 2)
+                    })
+
+        if active_loras:
+            metadata[LORAS][node_id] = {
+                "lora_list": active_loras,
+                "node_id": node_id
+            }
+
+
 class FluxGuidanceExtractor(NodeMetadataExtractor):
     @staticmethod
     def extract(node_id, inputs, outputs, metadata):
@@ -768,9 +1174,12 @@ NODE_EXTRACTORS = {
     "KSamplerSelect": KSamplerSelectExtractor,  # Add KSamplerSelect
     "BasicScheduler": BasicSchedulerExtractor,  # Add BasicScheduler
     "AlignYourStepsScheduler": BasicSchedulerExtractor,  # Add AlignYourStepsScheduler
+    # ComfyUI-Easy-Use pre-sampling / seed
+    "samplerSettings": EasyPreSamplingExtractor,  # easy preSampling
+    "easySeed": EasySeedExtractor,  # easy seed
     # Loaders
     "CheckpointLoaderSimple": CheckpointLoaderExtractor,
-    "comfyLoader": CheckpointLoaderExtractor,  # easy comfyLoader
+    "comfyLoader": EasyComfyLoaderExtractor,  # ComfyUI-Easy-Use easy comfyLoader
     "CheckpointLoaderSimpleWithImages": CheckpointLoaderExtractor,  # CheckpointLoader|pysssss
     "TSC_EfficientLoader": TSCCheckpointLoaderExtractor,  # Efficient Nodes
     "NunchakuFluxDiTLoader": NunchakuFluxDiTLoaderExtractor,  # ComfyUI-Nunchaku
@@ -780,10 +1189,13 @@ NODE_EXTRACTORS = {
     "GGUFLoaderKJ": KJNodesModelLoaderExtractor,  # KJNodes
     "DiffusionModelLoaderKJ": KJNodesModelLoaderExtractor,  # KJNodes
     "CheckpointLoaderKJ": CheckpointLoaderExtractor,  # KJNodes
+    "CheckpointLoaderLM": CheckpointLoaderExtractor,  # LoRA Manager
     "UNETLoader": UNETLoaderExtractor,          # Updated to use dedicated extractor
     "UnetLoaderGGUF": UNETLoaderExtractor,  # Updated to use dedicated extractor
+    "UNETLoaderLM": UNETLoaderExtractor,  # LoRA Manager
     "LoraLoader": LoraLoaderExtractor,
     "LoraLoaderLM": LoraLoaderManagerExtractor,
+    "LoraTextLoaderLM": LoraTextLoaderManagerExtractor,
     "RgthreePowerLoraLoader": RgthreePowerLoraLoaderExtractor,
     "TensorRTLoader": TensorRTLoaderExtractor,
     # Conditioning
@@ -796,6 +1208,12 @@ NODE_EXTRACTORS = {
     "smZ_CLIPTextEncode": CLIPTextEncodeExtractor,  # From https://github.com/shiimizu/ComfyUI_smZNodes
     "CR_ApplyControlNetStack": CR_ApplyControlNetStackExtractor,  # Add CR_ApplyControlNetStack
     "PCTextEncode": CLIPTextEncodeExtractor,  # From https://github.com/asagi4/comfyui-prompt-control
+    "TextProvider": MyOriginalWaifuTextExtractor,  # ComfyUI-MyOriginalWaifu
+    "ClipProvider": MyOriginalWaifuClipExtractor,  # ComfyUI-MyOriginalWaifu
+    "ControlNetApplyAdvanced": ControlNetApplyAdvancedExtractor,
+    "ConditioningCombine": ConditioningCombineExtractor,
+    "SetNode": SetNodeExtractor,
+    "GetNode": GetNodeExtractor,
     # Latent
     "EmptyLatentImage": ImageSizeExtractor,
     # Flux

py/metadata_ops/__init__.py

@@ -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[object, 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[object, 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

py/metadata_ops/__main__.py

@@ -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()

py/middleware/cache_middleware.py

@@ -16,6 +16,8 @@ IMG_EXTENSIONS = (
     ".tif",
     ".tiff",
     ".webp",
+    ".avif",
+    ".jxl",
     ".mp4"
 )
 

py/middleware/error_middleware.py

@@ -0,0 +1,76 @@
+"""JSON error middleware for API routes.
+
+Ensures all responses to /api/* requests return valid JSON that the
+browser-extension frontend can JSON.parse() without crashing, even when
+the route does not exist (404) or the handler raises an exception (500).
+
+Extension consumers call response.json() unconditionally — an HTML error
+page causes ``SyntaxError: unexpected end of data`` that leaks into the
+popup UI as a toast notification.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import Awaitable, Callable
+
+from aiohttp import web
+
+logger = logging.getLogger(__name__)
+
+
+@web.middleware
+async def api_json_error(
+    request: web.Request,
+    handler: Callable[[web.Request], Awaitable[web.Response]],
+) -> web.Response:
+    """Return JSON ``{"success": false, "error": "..."}`` for API errors.
+
+    Only intercepts paths starting with ``/api/`` — all other routes
+    (frontend pages, static files, WebSocket upgrades) pass through
+    unchanged.
+    """
+    if not request.path.startswith("/api/"):
+        return await handler(request)
+
+    try:
+        response = await handler(request)
+        return response
+    except web.HTTPException as exc:
+        # Let redirects (301, 302, 307, 308) propagate — they are not errors.
+        if exc.status < 400:
+            raise
+
+        # 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,
+            exc.status,
+            exc.reason,
+        )
+
+        return web.json_response(
+            {"success": False, "error": f"{exc.status}: {exc.reason}"},
+            status=exc.status,
+        )
+    except Exception as exc:
+        logger.error(
+            "API %s %s raised unhandled exception: %s",
+            request.method,
+            request.path,
+            exc,
+            exc_info=True,
+        )
+
+        return web.json_response(
+            {
+                "success": False,
+                "error": f"500: Internal Server Error ({type(exc).__name__})",
+            },
+            status=500,
+        )

py/nodes/lora_info.py

@@ -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)",
+}

py/nodes/lora_loader.py

@@ -1,6 +1,5 @@
 import importlib
 import logging
-import re
 
 import comfy.sd  # type: ignore
 import comfy.utils  # type: ignore
@@ -9,10 +8,12 @@ from ..utils.utils import get_lora_info_absolute
 from .utils import (
     FlexibleOptionalInputType,
     any_type,
+    apply_lora_syntax_format,
     detect_nunchaku_model_kind,
     extract_lora_name,
     get_loras_list,
     nunchaku_load_lora,
+    parse_lora_syntax,
 )
 
 logger = logging.getLogger(__name__)
@@ -52,7 +53,7 @@ def _collect_widget_entries(kwargs):
     for lora in get_loras_list(kwargs):
         if not lora.get("active", False):
             continue
-        lora_name = lora["name"]
+        lora_name = apply_lora_syntax_format(lora["name"])
         model_strength = float(lora["strength"])
         clip_strength = float(lora.get("clipStrength", model_strength))
         lora_path, trigger_words = get_lora_info_absolute(lora_name)
@@ -188,25 +189,10 @@ 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"],

py/nodes/lora_stacker.py

@@ -1,6 +1,6 @@
 import os
 from ..utils.utils import get_lora_info
-from .utils import FlexibleOptionalInputType, any_type, extract_lora_name, get_loras_list
+from .utils import FlexibleOptionalInputType, any_type, apply_lora_syntax_format, extract_lora_name, get_loras_list
 
 import logging
 
@@ -48,7 +48,7 @@ class LoraStackerLM:
             if not lora.get('active', False):
                 continue
                 
-            lora_name = lora['name']
+            lora_name = apply_lora_syntax_format(lora['name'])
             model_strength = float(lora['strength'])
             # Get clip strength - use model strength as default if not specified
             clip_strength = float(lora.get('clipStrength', model_strength))

py/nodes/lora_syntax_to_path.py

@@ -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),)

py/nodes/save_image.py

@@ -1,12 +1,17 @@
 import json
 import os
 import re
+import time
+import uuid
 from typing import Any, Dict, Optional
 import numpy as np
 import folder_paths  # type: ignore
 from ..services.service_registry import ServiceRegistry
 from ..metadata_collector.metadata_processor import MetadataProcessor
 from ..metadata_collector import get_metadata
+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 logging
@@ -86,6 +91,13 @@ class SaveImageLM:
                         "tooltip": "Adds an incremental counter to filenames to prevent overwriting previous images.",
                     },
                 ),
+                "save_as_recipe": (
+                    "BOOLEAN",
+                    {
+                        "default": False,
+                        "tooltip": "Also saves each generated image as a LoRA Manager recipe.",
+                    },
+                ),
             },
             "hidden": {
                 "id": "UNIQUE_ID",
@@ -286,7 +298,12 @@ class SaveImageLM:
             key = parts[0]
 
             if key == "seed" and "seed" in metadata_dict:
-                filename = filename.replace(segment, str(metadata_dict.get("seed", "")))
+                seed_value = metadata_dict.get("seed")
+                if seed_value is not None:
+                    filename = filename.replace(segment, str(seed_value))
+                else:
+                    # Fallback if seed was not captured by metadata collector
+                    filename = filename.replace(segment, "0")
             elif key == "width" and "size" in metadata_dict:
                 size = metadata_dict.get("size", "x")
                 w = size.split("x")[0] if isinstance(size, str) else size[0]
@@ -297,12 +314,14 @@ class SaveImageLM:
                 filename = filename.replace(segment, str(h))
             elif key == "pprompt" and "prompt" in metadata_dict:
                 prompt = metadata_dict.get("prompt", "").replace("\n", " ")
+                prompt = sanitize_folder_name(prompt)
                 if len(parts) >= 2:
                     length = int(parts[1])
                     prompt = prompt[:length]
                 filename = filename.replace(segment, prompt.strip())
             elif key == "nprompt" and "negative_prompt" in metadata_dict:
                 prompt = metadata_dict.get("negative_prompt", "").replace("\n", " ")
+                prompt = sanitize_folder_name(prompt)
                 if len(parts) >= 2:
                     length = int(parts[1])
                     prompt = prompt[:length]
@@ -316,6 +335,7 @@ class SaveImageLM:
                     model = "model_unavailable"
                 else:
                     model = os.path.splitext(os.path.basename(model_value))[0]
+                    model = sanitize_folder_name(model)
                 if len(parts) >= 2:
                     length = int(parts[1])
                     model = model[:length]
@@ -346,6 +366,203 @@ class SaveImageLM:
 
         return filename
 
+    @staticmethod
+    def _get_cached_model_by_name(scanner, name):
+        cache = getattr(scanner, "_cache", None)
+        if cache is None or not name:
+            return None
+
+        candidates = [
+            name,
+            os.path.basename(name),
+            os.path.splitext(os.path.basename(name))[0],
+        ]
+        for model in getattr(cache, "raw_data", []):
+            file_name = model.get("file_name")
+            if file_name in candidates:
+                return model
+        return None
+
+    def _build_recipe_loras(self, recipe_scanner, lora_stack):
+        lora_matches = re.findall(r"<lora:([^:]+):([^>]+)>", lora_stack or "")
+        lora_scanner = getattr(recipe_scanner, "_lora_scanner", None)
+        loras_data = []
+        base_model_counts = {}
+
+        for name, strength in lora_matches:
+            lora_info = self._get_cached_model_by_name(lora_scanner, name)
+            civitai = (lora_info or {}).get("civitai") or {}
+            civitai_model = civitai.get("model") or {}
+            try:
+                parsed_strength = float(strength)
+            except (TypeError, ValueError):
+                parsed_strength = 1.0
+
+            loras_data.append(
+                {
+                    "file_name": name,
+                    "strength": parsed_strength,
+                    "hash": ((lora_info or {}).get("sha256") or "").lower(),
+                    "modelVersionId": civitai.get("id", 0),
+                    "modelName": civitai_model.get("name", name) if lora_info else "",
+                    "modelVersionName": civitai.get("name", "") if lora_info else "",
+                    "isDeleted": False,
+                    "exclude": False,
+                }
+            )
+
+            base_model = (lora_info or {}).get("base_model")
+            if base_model:
+                base_model_counts[base_model] = base_model_counts.get(base_model, 0) + 1
+
+        return lora_matches, loras_data, base_model_counts
+
+    def _build_recipe_checkpoint(self, recipe_scanner, checkpoint_raw):
+        if not isinstance(checkpoint_raw, str) or not checkpoint_raw.strip():
+            return None
+
+        checkpoint_name = checkpoint_raw.strip()
+        file_name = os.path.splitext(os.path.basename(checkpoint_name))[0]
+        checkpoint_scanner = getattr(recipe_scanner, "_checkpoint_scanner", None)
+        checkpoint_info = self._get_cached_model_by_name(
+            checkpoint_scanner, checkpoint_name
+        )
+
+        if not checkpoint_info:
+            return {
+                "type": "checkpoint",
+                "name": checkpoint_name,
+                "file_name": file_name,
+                "hash": self.get_checkpoint_hash(checkpoint_name) or "",
+            }
+
+        civitai = checkpoint_info.get("civitai") or {}
+        civitai_model = civitai.get("model") or {}
+        file_path = checkpoint_info.get("file_path") or checkpoint_info.get("path") or ""
+        cached_file_name = (
+            checkpoint_info.get("file_name")
+            or (os.path.splitext(os.path.basename(file_path))[0] if file_path else "")
+            or file_name
+        )
+
+        return {
+            "type": "checkpoint",
+            "modelId": civitai_model.get("id", 0),
+            "modelVersionId": civitai.get("id", 0),
+            "name": civitai_model.get("name")
+            or checkpoint_info.get("model_name")
+            or checkpoint_name,
+            "version": civitai.get("name", ""),
+            "hash": (
+                checkpoint_info.get("sha256") or checkpoint_info.get("hash") or ""
+            ).lower(),
+            "file_name": cached_file_name,
+            "modelName": civitai_model.get("name", ""),
+            "modelVersionName": civitai.get("name", ""),
+            "baseModel": checkpoint_info.get("base_model")
+            or civitai.get("baseModel", ""),
+        }
+
+    @staticmethod
+    def _derive_recipe_name(lora_matches):
+        recipe_name_parts = [
+            f"{name.strip()}-{float(strength):.2f}" for name, strength in lora_matches[:3]
+        ]
+        return "_".join(recipe_name_parts) or "recipe"
+
+    @staticmethod
+    def _sync_recipe_cache(recipe_scanner, recipe_data, json_path):
+        cache = getattr(recipe_scanner, "_cache", None)
+        if cache is not None:
+            cache.raw_data.append(recipe_data)
+            cache.sorted_by_name = sorted(
+                cache.raw_data, key=lambda item: item.get("title", "").lower()
+            )
+            cache.sorted_by_date = sorted(
+                cache.raw_data,
+                key=lambda item: (
+                    item.get("modified", item.get("created_date", 0)),
+                    item.get("file_path", ""),
+                ),
+                reverse=True,
+            )
+            recipe_scanner._update_folder_metadata(cache)
+            recipe_scanner._update_fts_index_for_recipe(recipe_data, "add")
+
+        recipe_id = str(recipe_data.get("id", ""))
+        if recipe_id:
+            recipe_scanner._json_path_map[recipe_id] = json_path
+        persistent_cache = getattr(recipe_scanner, "_persistent_cache", None)
+        if persistent_cache:
+            persistent_cache.update_recipe(recipe_data, json_path)
+
+    def _save_image_as_recipe(self, file_path, metadata_dict):
+        if not metadata_dict:
+            raise ValueError("No generation metadata found")
+
+        recipe_scanner = ServiceRegistry.get_service_sync("recipe_scanner")
+        if recipe_scanner is None:
+            raise RuntimeError("Recipe scanner unavailable")
+
+        recipes_dir = recipe_scanner.recipes_dir
+        if not recipes_dir:
+            raise RuntimeError("Recipes directory unavailable")
+        os.makedirs(recipes_dir, exist_ok=True)
+
+        recipe_id = str(uuid.uuid4())
+        optimized_image, extension = ExifUtils.optimize_image(
+            image_data=file_path,
+            target_width=CARD_PREVIEW_WIDTH,
+            format="webp",
+            quality=85,
+            preserve_metadata=True,
+        )
+        image_path = os.path.normpath(os.path.join(recipes_dir, f"{recipe_id}{extension}"))
+        with open(image_path, "wb") as file_obj:
+            file_obj.write(optimized_image)
+
+        lora_stack = metadata_dict.get("loras", "")
+        lora_matches, loras_data, base_model_counts = self._build_recipe_loras(
+            recipe_scanner, lora_stack
+        )
+        checkpoint_entry = self._build_recipe_checkpoint(
+            recipe_scanner, metadata_dict.get("checkpoint")
+        )
+        most_common_base_model = (
+            max(base_model_counts.items(), key=lambda item: item[1])[0]
+            if base_model_counts
+            else ""
+        )
+        current_time = time.time()
+        recipe_data = {
+            "id": recipe_id,
+            "file_path": image_path,
+            "title": self._derive_recipe_name(lora_matches),
+            "modified": current_time,
+            "created_date": current_time,
+            "base_model": most_common_base_model
+            or (checkpoint_entry or {}).get("baseModel", ""),
+            "loras": loras_data,
+            "gen_params": {
+                key: value
+                for key, value in metadata_dict.items()
+                if key not in ["checkpoint", "loras"]
+            },
+            "loras_stack": lora_stack,
+            "fingerprint": calculate_recipe_fingerprint(loras_data),
+        }
+        if checkpoint_entry:
+            recipe_data["checkpoint"] = checkpoint_entry
+
+        json_path = os.path.normpath(
+            os.path.join(recipes_dir, f"{recipe_id}.recipe.json")
+        )
+        with open(json_path, "w", encoding="utf-8") as file_obj:
+            json.dump(recipe_data, file_obj, indent=4, ensure_ascii=False)
+
+        ExifUtils.append_recipe_metadata(image_path, recipe_data)
+        self._sync_recipe_cache(recipe_scanner, recipe_data, json_path)
+
     def save_images(
         self,
         images,
@@ -359,6 +576,7 @@ class SaveImageLM:
         embed_workflow=False,
         save_with_metadata=True,
         add_counter_to_filename=True,
+        save_as_recipe=False,
     ):
         """Save images with metadata"""
         results = []
@@ -390,7 +608,7 @@ class SaveImageLM:
             img = Image.fromarray(np.clip(img, 0, 255).astype(np.uint8))
 
             # Generate filename with counter if needed
-            base_filename = filename
+            base_filename = filename.replace("%batch_num%", str(i))
             if add_counter_to_filename:
                 # Use counter + i to ensure unique filenames for all images in batch
                 current_counter = counter + i
@@ -477,6 +695,14 @@ class SaveImageLM:
 
                     img.save(file_path, format="WEBP", **save_kwargs)
 
+                if save_as_recipe:
+                    try:
+                        self._save_image_as_recipe(file_path, metadata_dict)
+                    except Exception as e:
+                        logger.warning(
+                            "Failed to save image as recipe: %s", e, exc_info=True
+                        )
+
                 results.append(
                     {"filename": file, "subfolder": subfolder, "type": self.type}
                 )
@@ -499,6 +725,7 @@ class SaveImageLM:
         embed_workflow=False,
         save_with_metadata=True,
         add_counter_to_filename=True,
+        save_as_recipe=False,
     ):
         """Process and save image with metadata"""
         # Make sure the output directory exists
@@ -527,6 +754,7 @@ class SaveImageLM:
             embed_workflow,
             save_with_metadata,
             add_counter_to_filename,
+            save_as_recipe,
         )
 
         return {

py/nodes/trigger_word_toggle.py

@@ -76,6 +76,9 @@ class TriggerWordToggleLM:
         # Filter out empty strings and return as set
         return set(word for word in words if word)
 
+    def _group_has_child_items(self, item):
+        return isinstance(item, dict) and isinstance(item.get("items"), list)
+
     def process_trigger_words(
         self,
         id,
@@ -112,7 +115,11 @@ class TriggerWordToggleLM:
 
                 if isinstance(trigger_data, list):
                     if group_mode:
-                        if allow_strength_adjustment:
+                        if any(self._group_has_child_items(item) for item in trigger_data):
+                            filtered_groups = self._process_group_items(
+                                trigger_data, allow_strength_adjustment
+                            )
+                        elif allow_strength_adjustment:
                             parsed_items = [
                                 self._parse_trigger_item(
                                     item, allow_strength_adjustment
@@ -174,6 +181,41 @@ class TriggerWordToggleLM:
 
         return (filtered_triggers,)
 
+    def _process_group_items(self, trigger_data, allow_strength_adjustment):
+        filtered_groups = []
+
+        for item in trigger_data:
+            group = self._parse_trigger_item(item, allow_strength_adjustment)
+            if not group["text"] or not group["active"]:
+                continue
+
+            raw_items = item.get("items") if isinstance(item, dict) else None
+            if isinstance(raw_items, list):
+                active_items = []
+                for raw_item in raw_items:
+                    child = self._parse_trigger_item(
+                        raw_item, allow_strength_adjustment=False
+                    )
+                    if child["text"] and child["active"]:
+                        active_items.append(child["text"])
+
+                if not active_items:
+                    continue
+
+                group_text = ", ".join(active_items)
+            else:
+                group_text = group["text"]
+
+            filtered_groups.append(
+                self._format_word_output(
+                    group_text,
+                    group["strength"],
+                    allow_strength_adjustment,
+                )
+            )
+
+        return filtered_groups
+
     def _parse_trigger_item(self, item, allow_strength_adjustment):
         text = (item.get("text") or "").strip()
         active = bool(item.get("active", False))

py/nodes/utils.py

@@ -36,6 +36,7 @@ any_type = AnyType("*")
 
 # Common methods extracted from lora_loader.py and lora_stacker.py
 import os
+import re
 import logging
 import copy
 import sys
@@ -44,11 +45,48 @@ import folder_paths  # type: ignore
 logger = logging.getLogger(__name__)
 
 
+def get_lora_syntax_format():
+    try:
+        from ..services.settings_manager import get_settings_manager
+        return get_settings_manager().get("lora_syntax_format", "legacy")
+    except Exception:
+        return "legacy"
+
+
+def apply_lora_syntax_format(name):
+    fmt = get_lora_syntax_format()
+    if fmt == "legacy":
+        return name.replace("\\", "/").rstrip("/").split("/")[-1]
+    return name
+
+
 def extract_lora_name(lora_path):
-    """Extract the lora name from a lora path (e.g., 'IL\\aorunIllstrious.safetensors' -> 'aorunIllstrious')"""
-    # Get the basename without extension
-    basename = os.path.basename(lora_path)
-    return os.path.splitext(basename)[0]
+    normalized = lora_path.replace("\\", "/")
+    basename = os.path.basename(normalized)
+    name_no_ext = os.path.splitext(basename)[0]
+    dirname = os.path.dirname(normalized)
+    if dirname and dirname not in (".", "/") and not normalized.startswith("/"):
+        return apply_lora_syntax_format(f"{dirname}/{name_no_ext}")
+    return apply_lora_syntax_format(name_no_ext)
+
+
+def parse_lora_syntax(text: str) -> list[dict]:
+    """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):

py/nodes/wanvideo_lora_select.py

@@ -1,10 +1,22 @@
-import folder_paths # type: ignore
-from ..utils.utils import get_lora_info
+import os
+from ..utils.utils import get_lora_info_absolute
+from ..config import config
 from .utils import FlexibleOptionalInputType, any_type, get_loras_list
 import logging
 
 logger = logging.getLogger(__name__)
 
+
+def _relpath_within_loras(abs_path):
+    """Return abs_path relative to the first matching lora root, or basename as fallback."""
+    all_roots = list(config.loras_roots or []) + list(config.extra_loras_roots or [])
+    for root in all_roots:
+        try:
+            return os.path.relpath(abs_path, root)
+        except ValueError:
+            continue
+    return os.path.basename(abs_path)
+
 class WanVideoLoraSelectLM:
     NAME = "WanVideo Lora Select (LoraManager)"
     CATEGORY = "Lora Manager/stackers"
@@ -56,13 +68,13 @@ class WanVideoLoraSelectLM:
             clip_strength = float(lora.get('clipStrength', model_strength))
             
             # Get lora path and trigger words
-            lora_path, trigger_words = get_lora_info(lora_name)
+            lora_path, trigger_words = get_lora_info_absolute(lora_name)
             
             # Create lora item for WanVideo format
             lora_item = {
-                "path": folder_paths.get_full_path("loras", lora_path),
+                "path": lora_path,
                 "strength": model_strength,
-                "name": lora_path.split(".")[0],
+                "name": os.path.splitext(_relpath_within_loras(lora_path))[0],
                 "blocks": selected_blocks,
                 "layer_filter": layer_filter,
                 "low_mem_load": low_mem_load,

py/nodes/wanvideo_lora_select_from_text.py

@@ -1,11 +1,23 @@
-import folder_paths # type: ignore
-from ..utils.utils import get_lora_info
+import os
+from ..utils.utils import get_lora_info_absolute
+from ..config import config
 from .utils import any_type 
 import logging
 
 # 初始化日志记录器
 logger = logging.getLogger(__name__)
 
+
+def _relpath_within_loras(abs_path):
+    """Return abs_path relative to the first matching lora root, or basename as fallback."""
+    all_roots = list(config.loras_roots or []) + list(config.extra_loras_roots or [])
+    for root in all_roots:
+        try:
+            return os.path.relpath(abs_path, root)
+        except ValueError:
+            continue
+    return os.path.basename(abs_path)
+
 # 定义新节点的类
 class WanVideoLoraTextSelectLM:
     # 节点在UI中显示的名称
@@ -87,12 +99,12 @@ class WanVideoLoraTextSelectLM:
             else:
                 continue
 
-            lora_path, trigger_words = get_lora_info(lora_name_raw)
+            lora_path, trigger_words = get_lora_info_absolute(lora_name_raw)
 
             lora_item = {
-                "path": folder_paths.get_full_path("loras", lora_path),
+                "path": lora_path,
                 "strength": model_strength,
-                "name": lora_path.split(".")[0],
+                "name": os.path.splitext(_relpath_within_loras(lora_path))[0],
                 "blocks": selected_blocks,
                 "layer_filter": layer_filter,
                 "low_mem_load": low_mem_load,

py/recipes/base.py

@@ -7,7 +7,7 @@ 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
+from ..utils.constants import VALID_LORA_TYPES, VALID_CHECKPOINT_SUB_TYPES
 from ..utils.civitai_utils import rewrite_preview_url
 
 logger = logging.getLogger(__name__)
@@ -58,9 +58,52 @@ class RecipeMetadataParser(ABC):
             civitai_info, error_msg = civitai_info_tuple if isinstance(civitai_info_tuple, tuple) else (civitai_info_tuple, None)
             
             if not civitai_info or error_msg == "Model not found":
-                # Model not found or deleted
-                lora_entry['isDeleted'] = True
-                lora_entry['thumbnailUrl'] = '/loras_static/images/no-preview.png'
+                # CivitAI may fail to resolve a hash that is still being
+                # computed (known CivitAI issue). Before marking as deleted,
+                # try to reconcile with a local model that has the same
+                # filename and matching AutoV3 hash.
+                reconciled = False
+                file_name = lora_entry.get("file_name")
+                if file_name and recipe_scanner and hash_value:
+                    lora_scanner = getattr(recipe_scanner, "_lora_scanner", None)
+                    if lora_scanner:
+                        try:
+                            # Local import to avoid circular dependency:
+                            # base.py → file_utils → settings_manager → ...
+                            #  → recipe_scanner → enrichment → base.py
+                            from ..utils.file_utils import calculate_autov3  # fmt: skip
+                            cache = await lora_scanner.get_cached_data()
+                            for item in getattr(cache, "raw_data", []):
+                                if item.get("file_name") == file_name:
+                                    local_path = item.get("file_path")
+                                    if local_path and os.path.exists(local_path):
+                                        local_autov3 = calculate_autov3(local_path)
+                                        if local_autov3 and local_autov3 == hash_value:
+                                            lora_entry["existsLocally"] = True
+                                            lora_entry["localPath"] = local_path
+                                            lora_entry["hash"] = item.get("sha256", hash_value)
+                                            if "preview_url" in item:
+                                                lora_entry["thumbnailUrl"] = config.get_preview_static_url(item["preview_url"])
+                                            civ = item.get("civitai") or {}
+                                            if isinstance(civ, dict):
+                                                if civ.get("id") is not None:
+                                                    lora_entry["id"] = civ["id"]
+                                                if civ.get("modelId") is not None:
+                                                    lora_entry["modelId"] = civ["modelId"]
+                                                if civ.get("name"):
+                                                    lora_entry["version"] = civ["name"]
+                                                # model_name is the CivitAI model display
+                                                # name stored directly in the cache column.
+                                                cached_model_name = item.get("model_name")
+                                                if cached_model_name:
+                                                    lora_entry["name"] = cached_model_name
+                                            reconciled = True
+                                            break
+                        except Exception:
+                            pass
+                if not reconciled:
+                    lora_entry['isDeleted'] = True
+                    lora_entry['thumbnailUrl'] = '/loras_static/images/no-preview.png'
                 return lora_entry
                 
             # Get model type and validate
@@ -173,6 +216,20 @@ class RecipeMetadataParser(ABC):
                 checkpoint['isDeleted'] = True
                 return checkpoint
 
+            # Validate that the model type is actually a checkpoint.
+            # Unlike populate_lora_from_civitai which has this check,
+            # this function was missing type validation — allowing LoRA
+            # version data to be saved as the recipe's checkpoint when the
+            # wrong version ID was passed downstream (fixed in v2.7+).
+            model_type = civitai_data.get('model', {}).get('type', '').lower()
+            if model_type not in VALID_CHECKPOINT_SUB_TYPES:
+                logger.warning(
+                    f"Cannot populate checkpoint: model version {civitai_data.get('id')} "
+                    f"has type '{model_type}', expected one of {VALID_CHECKPOINT_SUB_TYPES}. "
+                    f"Skipping checkpoint enrichment."
+                )
+                return checkpoint
+
             if 'model' in civitai_data and 'name' in civitai_data['model']:
                 checkpoint['name'] = civitai_data['model']['name']
 

py/recipes/enrichment.py

@@ -1,11 +1,11 @@
 import logging
 import json
-import re
 import os
 from typing import Any, Dict, Optional
 from .merger import GenParamsMerger
 from .base import RecipeMetadataParser
 from ..services.metadata_service import get_default_metadata_provider
+from ..utils.civitai_utils import extract_civitai_image_id
 
 logger = logging.getLogger(__name__)
 
@@ -16,54 +16,65 @@ class RecipeEnricher:
     async def enrich_recipe(
         recipe: Dict[str, Any],
         civitai_client: Any,
-        request_params: Optional[Dict[str, Any]] = None
+        request_params: Optional[Dict[str, Any]] = None,
+        prefetched_civitai_meta_raw: Optional[Dict[str, Any]] = None,
+        prefetched_model_version_id: Optional[int] = None,
     ) -> bool:
         """
         Enrich a recipe dictionary in-place with metadata from Civitai and embedded params.
-        
+
         Args:
             recipe: The recipe dictionary to enrich. Must have 'gen_params' initialized.
             civitai_client: Authenticated Civitai client instance.
             request_params: (Optional) Parameters from a user request (e.g. import).
-            
+            prefetched_civitai_meta_raw: (Optional) Pre-fetched raw meta from Civitai
+                get_image_info, avoiding a duplicate API call.
+            prefetched_model_version_id: (Optional) Pre-fetched model version ID.
+
         Returns:
             bool: True if the recipe was modified, False otherwise.
         """
         updated = False
         gen_params = recipe.get("gen_params", {})
-        
-        # 1. Fetch Civitai Info if available
+
+        # 1. Obtain Civitai metadata
         civitai_meta = None
-        model_version_id = None
-        
-        source_url = recipe.get("source_url") or recipe.get("source_path", "")
-        
-        # Check if it's a Civitai image URL
-        image_id_match = re.search(r'civitai\.com/images/(\d+)', str(source_url))
-        if image_id_match:
-            image_id = image_id_match.group(1)
-            try:
-                image_info = await civitai_client.get_image_info(image_id)
-                if image_info:
-                    # Handle nested meta often found in Civitai API responses
-                    raw_meta = image_info.get("meta")
-                    if isinstance(raw_meta, dict):
-                        if "meta" in raw_meta and isinstance(raw_meta["meta"], dict):
-                            civitai_meta = raw_meta["meta"]
-                        else:
-                            civitai_meta = raw_meta
-                    
-                    model_version_id = image_info.get("modelVersionId")
-                    
-                    # If not at top level, check resources in meta
-                    if not model_version_id and civitai_meta:
-                        resources = civitai_meta.get("civitaiResources", [])
-                        for res in resources:
-                            if res.get("type") == "checkpoint":
-                                model_version_id = res.get("modelVersionId")
-                                break
-            except Exception as e:
-                logger.warning(f"Failed to fetch Civitai image info: {e}")
+        model_version_id = prefetched_model_version_id
+
+        source_path = recipe.get("source_path", "")
+
+        if prefetched_civitai_meta_raw is not None:
+            raw_meta = prefetched_civitai_meta_raw
+            if isinstance(raw_meta, dict):
+                if "meta" in raw_meta and isinstance(raw_meta["meta"], dict):
+                    civitai_meta = raw_meta["meta"]
+                else:
+                    civitai_meta = raw_meta
+        else:
+            image_id = extract_civitai_image_id(str(source_path))
+            if image_id:
+                try:
+                    image_info = await civitai_client.get_image_info(
+                        image_id, source_url=str(source_path)
+                    )
+                    if image_info:
+                        raw_meta = image_info.get("meta")
+                        if isinstance(raw_meta, dict):
+                            if "meta" in raw_meta and isinstance(raw_meta["meta"], dict):
+                                civitai_meta = raw_meta["meta"]
+                            else:
+                                civitai_meta = raw_meta
+
+                        model_version_id = image_info.get("modelVersionId")
+                except Exception as e:
+                    logger.warning(f"Failed to fetch Civitai image info: {e}")
+
+        if not model_version_id and civitai_meta:
+            resources = civitai_meta.get("civitaiResources", [])
+            for res in resources:
+                if res.get("type") == "checkpoint":
+                    model_version_id = res.get("modelVersionId")
+                    break
 
         # 2. Merge Parameters
         # Priority: request_params > civitai_meta > embedded (existing gen_params)
@@ -179,27 +190,42 @@ class RecipeEnricher:
             existing_cp = recipe.get("checkpoint")
             if existing_cp is None:
                 existing_cp = {}
+
+            # Extract baseModel from raw civitai_info before populate_checkpoint_from_civitai
+            # (populate may reject non-checkpoint types and lose this data)
+            base_model_from_civitai: str = ""
+            if isinstance(civitai_info, dict):
+                base_model_from_civitai = civitai_info.get("baseModel", "") or ""
+            elif isinstance(civitai_info, tuple) and len(civitai_info) > 0 and isinstance(civitai_info[0], dict):
+                base_model_from_civitai = civitai_info[0].get("baseModel", "") or ""
+
             checkpoint_data = await RecipeMetadataParser.populate_checkpoint_from_civitai(existing_cp, civitai_info)
-            # 1. First, resolve base_model using full data before we format it away
+
+            # 1. Resolve base_model from checkpoint_data first, then fall back to raw civitai_info
             current_base_model = recipe.get("base_model")
-            resolved_base_model = checkpoint_data.get("baseModel")
+            resolved_base_model = checkpoint_data.get("baseModel") or base_model_from_civitai
             if resolved_base_model:
-                # Update if empty OR if it matches our generic prefix but is less specific
                 is_generic = not current_base_model or current_base_model.lower() in ["flux", "sdxl", "sd15"]
                 if is_generic and resolved_base_model != current_base_model:
                     recipe["base_model"] = resolved_base_model
-            
-            # 2. Format according to requirements: type, modelId, modelVersionId, modelName, modelVersionName
-            formatted_checkpoint = {
-                "type": "checkpoint",
-                "modelId": checkpoint_data.get("modelId"),
-                "modelVersionId": checkpoint_data.get("id") or checkpoint_data.get("modelVersionId"),
-                "modelName": checkpoint_data.get("name"), # In base.py, 'name' is populated from civitai_data['model']['name']
-                "modelVersionName": checkpoint_data.get("version") # In base.py, 'version' is populated from civitai_data['name']
-            }
-            # Remove None values
-            recipe["checkpoint"] = {k: v for k, v in formatted_checkpoint.items() if v is not None}
-            
+
+            # 2. Only format and save checkpoint if it has real data (not just type after type rejection)
+            has_checkpoint_data = any([
+                checkpoint_data.get("modelId"),
+                checkpoint_data.get("id") or checkpoint_data.get("modelVersionId"),
+                checkpoint_data.get("name"),
+                checkpoint_data.get("version"),
+            ])
+            if has_checkpoint_data:
+                formatted_checkpoint = {
+                    "type": "checkpoint",
+                    "modelId": checkpoint_data.get("modelId"),
+                    "modelVersionId": checkpoint_data.get("id") or checkpoint_data.get("modelVersionId"),
+                    "modelName": checkpoint_data.get("name"),
+                    "modelVersionName": checkpoint_data.get("version"),
+                }
+                recipe["checkpoint"] = {k: v for k, v in formatted_checkpoint.items() if v is not None}
+
             return True
         else:
             # Fallback to name extraction if we don't already have one

py/recipes/parsers/automatic.py

@@ -123,24 +123,39 @@ class AutomaticMetadataParser(RecipeMetadataParser):
                         if model_hash_from_hashes:
                             metadata["model_hash"] = model_hash_from_hashes
                     
-                    # Extract Lora hashes in alternative format
+                    # Extract Lora hashes in alternative format.
+                    # Run unconditionally (not just as fallback) so that
+                    # non-empty hashes from Lora hashes fill in the gaps left
+                    # by empty values in the Hashes JSON dict.  Some WebUI
+                    # builds write real hash values only to Lora hashes and
+                    # leave the Hashes JSON values empty.
                     lora_hashes_match = re.search(self.LORA_HASHES_REGEX, params_section)
-                    if not hashes_match and lora_hashes_match:
+                    if lora_hashes_match:
                         try:
                             lora_hashes_str = lora_hashes_match.group(1)
                             lora_hash_entries = lora_hashes_str.split(', ')
-                            
-                            # Initialize hashes dict if it doesn't exist
-                            if "hashes" not in metadata:
-                                metadata["hashes"] = {}
-                                
+
                             # Parse each lora hash entry (format: "name: hash")
                             for entry in lora_hash_entries:
                                 if ': ' in entry:
                                     lora_name, lora_hash = entry.split(': ', 1)
-                                    # Add as lora type in the same format as regular hashes
-                                    metadata["hashes"][f"lora:{lora_name}"] = lora_hash.strip()
-                            
+                                    lora_hash = lora_hash.strip()
+                                    if not lora_hash:
+                                        # Skip entries without a hash value
+                                        continue
+                                    # Initialize hashes dict if it doesn't exist
+                                    if "hashes" not in metadata:
+                                        metadata["hashes"] = {}
+                                    # Add as lora type in the same format as
+                                    # regular hashes.  Only override an
+                                    # existing entry if its value is empty
+                                    # (Lora hashes is the more reliable
+                                    # source when Hashes JSON has blanks).
+                                    key = f"lora:{lora_name}"
+                                    existing = metadata["hashes"].get(key, "")
+                                    if not existing:
+                                        metadata["hashes"][key] = lora_hash
+
                             # Remove lora hashes from params section
                             params_section = params_section.replace(lora_hashes_match.group(0), '')
                         except Exception as e:
@@ -362,6 +377,12 @@ class AutomaticMetadataParser(RecipeMetadataParser):
                         # Only process lora or hypernet types
                         if not hash_key.startswith(("lora:", "hypernet:")):
                             continue
+                        
+                        # Skip entries without a hash value — they can't be
+                        # resolved via CivitAI and would only produce a
+                        # useless "Deleted" entry in the recipe.
+                        if not lora_hash:
+                            continue
                             
                         lora_type, lora_name = hash_key.split(':', 1)
                         
@@ -387,11 +408,7 @@ class AutomaticMetadataParser(RecipeMetadataParser):
                         # Try to get info from Civitai
                         if metadata_provider:
                             try:
-                                if lora_hash:
-                                    # If we have hash, use it for lookup
-                                    civitai_info = await metadata_provider.get_model_by_hash(lora_hash)
-                                else:
-                                    civitai_info = None
+                                civitai_info = await metadata_provider.get_model_by_hash(lora_hash)
                                 
                                 populated_entry = await self.populate_lora_from_civitai(
                                     lora_entry, 

py/recipes/parsers/civitai_image.py

@@ -6,6 +6,7 @@ from typing import Dict, Any, Union
 from ..base import RecipeMetadataParser
 from ..constants import GEN_PARAM_KEYS
 from ...services.metadata_service import get_default_metadata_provider
+from ...config import config
 
 logger = logging.getLogger(__name__)
 
@@ -73,7 +74,8 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
         return False
 
     async def parse_metadata(  # type: ignore[override]
-        self, user_comment, recipe_scanner=None, civitai_client=None
+        self, user_comment, recipe_scanner=None, civitai_client=None,
+        local_cache: dict[str, Any] | None = None,
     ) -> Dict[str, Any]:
         """Parse metadata from Civitai image format
 
@@ -81,6 +83,8 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
             user_comment: The metadata from the image (dict)
             recipe_scanner: Optional recipe scanner service
             civitai_client: Optional Civitai API client (deprecated, use metadata_provider instead)
+            local_cache: Optional dict mapping sha256/autov3 hash → scanner cache item.
+                         When provided, matching models skip CivitAI API calls.
 
         Returns:
             Dict containing parsed recipe data
@@ -185,8 +189,77 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
             # Process standard resources array
             if "resources" in metadata and isinstance(metadata["resources"], list):
                 for resource in metadata["resources"]:
+                    resource_type = resource.get("type", "lora")
+
+                    # Track resources with type "model" — these are checkpoint models.
+                    # The resources array is the most reliable source for checkpoint
+                    # 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 = {
+                            "id": 0,
+                            "modelId": 0,
+                            "name": resource.get("name", "Unknown Model"),
+                            "version": "",
+                            "type": resource.get("type", "model"),
+                            "existsLocally": False,
+                            "localPath": None,
+                            "file_name": resource.get("name", ""),
+                            "hash": resource.get("hash", "") or "",
+                            "thumbnailUrl": "/loras_static/images/no-preview.png",
+                            "baseModel": "",
+                            "size": 0,
+                            "downloadUrl": "",
+                            "isDeleted": False,
+                        }
+
+                        # 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
+                            if local_cached:
+                                self._populate_entry_from_cache(
+                                    checkpoint_entry, local_cached
+                                )
+                                bm = checkpoint_entry.get("baseModel", "")
+                                if bm and not result["base_model"]:
+                                    result["base_model"] = bm
+                            else:
+                                try:
+                                    civitai_info = (
+                                        await metadata_provider.get_model_by_hash(
+                                            cp_hash
+                                        )
+                                    )
+                                    civitai_data, error_msg = (
+                                        (civitai_info, None)
+                                        if not isinstance(civitai_info, tuple)
+                                        else civitai_info
+                                    )
+                                    if civitai_data and error_msg != "Model not found":
+                                        if 'model' in civitai_data and 'name' in civitai_data['model']:
+                                            checkpoint_entry['name'] = civitai_data['model']['name']
+                                        checkpoint_entry['id'] = civitai_data.get('id', 0)
+                                        checkpoint_entry['modelId'] = civitai_data.get('modelId', 0)
+                                        if 'name' in civitai_data:
+                                            checkpoint_entry['version'] = civitai_data['name']
+                                        base_model = civitai_data.get('baseModel', '')
+                                        if base_model:
+                                            checkpoint_entry['baseModel'] = base_model
+                                            if not result['base_model']:
+                                                result['base_model'] = base_model
+                                except Exception as e:
+                                    logger.error(
+                                        f"Error fetching checkpoint info for hash "
+                                        f"{cp_hash}: {e}"
+                                    )
+
+                        if result["model"] is None:
+                            result["model"] = checkpoint_entry
+                        continue
+
                     # Modified to process resources without a type field as potential LoRAs
-                    if resource.get("type", "lora") == "lora":
+                    if resource_type == "lora":
                         lora_hash = resource.get("hash", "")
 
                         # Try to get hash from the hashes field if not present in resource
@@ -220,34 +293,45 @@ 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)
+                        if lora_hash and metadata_provider:
+                            local_cached = local_cache.get(lora_hash) if local_cache else None
+                            if local_cached:
+                                self._populate_entry_from_cache(
+                                    lora_entry, local_cached
                                 )
-
-                                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  # 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"]:
+                                # Track by version ID for deduplication
+                                if lora_entry.get("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:
+                                        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:
@@ -430,11 +514,21 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
 
                         result["loras"].append(lora_entry)
 
-            # Process modelVersionIds from Civitai image API
-            # These are model version IDs returned at root level when meta doesn't contain resources
-            if "modelVersionIds" in metadata and isinstance(
-                metadata["modelVersionIds"], list
+            # Process modelVersionIds from Civitai image API.
+            # These are version IDs returned at root level of the API response.
+            # When resources or civitaiResources are already present in metadata
+            # (which they are when ?withMeta=true is passed), those sections have
+            # complete hash/type information — modelVersionIds is a fallback for
+            # when meta is null and only the flat ID list is available. Skipping
+            # it here avoids duplicates: the same file hash often resolves to
+            # different version IDs via hash lookup (resources) vs the original
+            # version ID in modelVersionIds, and both paths would create entries.
+            if (
+                "modelVersionIds" in metadata
+                and isinstance(metadata["modelVersionIds"], list)
+                and not result.get("loras")
             ):
+
                 for version_id in metadata["modelVersionIds"]:
                     version_id_str = str(version_id)
 
@@ -442,6 +536,13 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                     if version_id_str in added_loras:
                         continue
 
+                    # Skip if this version ID is already the recipe's checkpoint
+                    # (resolved earlier from embedded resources/Model hash,
+                    # avoiding a duplicate CivitAI API call).
+                    existing_model = result.get("model")
+                    if existing_model and str(existing_model.get("id")) == version_id_str:
+                        continue
+
                     # Initialize lora entry with version ID
                     lora_entry = {
                         "id": version_id,
@@ -475,9 +576,40 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
                             )
 
                             if populated_entry is None:
-                                continue  # Skip invalid LoRA types
+                                # Not a LoRA — try as checkpoint (only if we
+                                # don't already have one).  Reuses the same
+                                # civitai_info from the API call above so no
+                                # extra query is made.
+                                if result["model"] is None:
+                                    checkpoint_entry = {
+                                        "id": version_id,
+                                        "modelId": 0,
+                                        "name": "Unknown Model",
+                                        "version": "",
+                                        "type": "checkpoint",
+                                        "existsLocally": False,
+                                        "localPath": None,
+                                        "file_name": "",
+                                        "hash": "",
+                                        "thumbnailUrl": (
+                                            "/loras_static/images/no-preview.png"
+                                        ),
+                                        "baseModel": "",
+                                        "size": 0,
+                                        "downloadUrl": "",
+                                        "isDeleted": False,
+                                    }
+                                    cp_populated = await (
+                                        self.populate_checkpoint_from_civitai(
+                                            checkpoint_entry, civitai_info
+                                        )
+                                    )
+                                    if cp_populated.get("modelId"):
+                                        result["model"] = cp_populated
+                                continue  # Not a LoRA, don't add to loras
 
                             lora_entry = populated_entry
+
                         except Exception as e:
                             logger.error(
                                 f"Error fetching Civitai info for model version {version_id}: {e}"
@@ -625,3 +757,41 @@ class CivitaiApiMetadataParser(RecipeMetadataParser):
         except Exception as e:
             logger.error(f"Error parsing Civitai image metadata: {e}", exc_info=True)
             return {"error": str(e), "loras": []}
+
+    @staticmethod
+    def _populate_entry_from_cache(
+        entry: dict[str, Any],
+        cache_item: dict[str, Any],
+    ) -> None:
+        """Fill a lora/checkpoint entry from a scanner cache item.
+
+        Avoids CivitAI API calls for models that exist locally.
+        Mirrors the population logic in
+        ``RecipeMetadataParser.populate_lora_from_civitai()`` but operates
+        entirely on cached data.
+        """
+        civ = cache_item.get("civitai") or {}
+        if isinstance(civ, dict):
+            if civ.get("id") is not None:
+                entry["id"] = civ["id"]
+            if civ.get("modelId") is not None:
+                entry["modelId"] = civ["modelId"]
+            if civ.get("name"):
+                entry["version"] = civ["name"]
+            cached_name = cache_item.get("model_name")
+            if cached_name:
+                entry["name"] = cached_name
+        entry["existsLocally"] = True
+        local_path = cache_item.get("file_path")
+        if local_path:
+            entry["localPath"] = local_path
+        sha256 = cache_item.get("sha256")
+        if sha256:
+            entry["hash"] = sha256
+        if "preview_url" in cache_item:
+            entry["thumbnailUrl"] = config.get_preview_static_url(
+                cache_item["preview_url"]
+            )
+        base_model = cache_item.get("base_model", "")
+        if base_model:
+            entry["baseModel"] = base_model

py/routes/base_model_routes.py

@@ -251,7 +251,7 @@ 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") == "Model" and file.get("primary") is True), None)
+        return next((file for file in files if file.get("type") in ("Model", "Diffusion Model") and file.get("primary") is True), None)
 
     def get_handler(self, name: str) -> Callable[[web.Request], web.StreamResponse]:
         """Expose handlers for subclasses or tests."""

py/routes/handlers/agent_handlers.py

@@ -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,
+        )

py/routes/handlers/hf_handlers.py

@@ -0,0 +1,508 @@
+"""Handlers for Hugging Face model listing and download.
+
+Minimal MVP implementation — uses direct HTTP to the HF API for file
+listing and the project's existing aiohttp-based Downloader for
+downloading.  No huggingface_hub dependency required.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import re
+from typing import Any
+
+import aiohttp
+from aiohttp import web
+
+from ...config import config
+from ...services.downloader import (
+    DownloadProgress,
+    get_downloader,
+)
+from ...services.aria2_downloader import Aria2Downloader
+from ...services.settings_manager import get_settings_manager
+from ...services.service_registry import ServiceRegistry
+from ...services.websocket_manager import ws_manager
+from ...utils.constants import MODEL_FILE_EXTENSIONS
+from ...utils.metadata_manager import MetadataManager
+from ...utils.models import LoraMetadata, CheckpointMetadata, EmbeddingMetadata
+
+logger = logging.getLogger(__name__)
+
+_DEFAULT_MODEL_CLASS = LoraMetadata
+_DEFAULT_SCANNER_GETTER = "get_lora_scanner"
+
+# Shared aiohttp session for HF API calls (created on first use)
+_hf_api_session: aiohttp.ClientSession | None = None
+
+
+async def _get_hf_api_session() -> aiohttp.ClientSession:
+    """Get or create the shared aiohttp session for HF API calls."""
+    global _hf_api_session  # needed because we reassign the module-level name
+    if _hf_api_session is None or _hf_api_session.closed:
+        _hf_api_session = aiohttp.ClientSession(
+            headers={"User-Agent": "ComfyUI-LoRA-Manager/1.0"},
+            timeout=aiohttp.ClientTimeout(total=30),
+        )
+    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``).
+
+    The ``model_root`` value comes from the frontend's model-root dropdown,
+    which is populated from the current page's scanner roots.  By checking
+    which scanner's root list it belongs to, we avoid fragile heuristics
+    like substring-matching path names.
+    """
+    norm = os.path.normpath(model_root).replace(os.sep, "/")
+
+    # LoRA roots
+    for p in (config.loras_roots or []) + (config.extra_loras_roots or []):
+        if os.path.normpath(p).replace(os.sep, "/") == norm:
+            return LoraMetadata, "get_lora_scanner"
+
+    # Checkpoint / UNet roots
+    for p in (
+        (config.checkpoints_roots or [])
+        + (config.extra_checkpoints_roots or [])
+        + (config.unet_roots or [])
+        + (config.extra_unet_roots or [])
+    ):
+        if os.path.normpath(p).replace(os.sep, "/") == norm:
+            return CheckpointMetadata, "get_checkpoint_scanner"
+
+    # Embedding roots
+    for p in (config.embeddings_roots or []) + (config.extra_embeddings_roots or []):
+        if os.path.normpath(p).replace(os.sep, "/") == norm:
+            return EmbeddingMetadata, "get_embedding_scanner"
+
+    # Fallback — should not happen in normal use
+    logger.warning(
+        "Could not determine model type for root '%s'; defaulting to LoRA",
+        model_root,
+    )
+    return _DEFAULT_MODEL_CLASS, _DEFAULT_SCANNER_GETTER
+
+
+async def _save_hf_metadata(dest_path: str, repo: str, model_root: str) -> None:
+    """Create a proper .metadata.json and add the model to the scanner cache.
+
+    Uses ``MetadataManager.create_default_metadata()`` which computes the
+    SHA256 hash, extracts safetensors header metadata (base_model), and
+    produces a fully-populated ``LoraMetadata`` (or ``CheckpointMetadata`` /
+    ``EmbeddingMetadata``) object.  We then overlay HF-specific fields and
+    register the model in the in-memory scanner cache so it appears
+    immediately without a full filesystem walk.
+    """
+    try:
+        hf_url = f"https://huggingface.co/{repo}"
+        model_class, scanner_getter_name = _infer_model_type(model_root)
+
+        # 1. Create proper metadata (computes SHA256, reads safetensors headers)
+        metadata = await MetadataManager.create_default_metadata(
+            dest_path, model_class=model_class
+        )
+        if metadata is None:
+            logger.warning("create_default_metadata returned None for %s", dest_path)
+            return
+
+        # 2. Overlay HF-specific fields
+        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_dict)
+        logger.info("Saved HF metadata (with hf_url) for %s", dest_path)
+
+        # 4. Determine relative folder path for cache
+        #    model_root is an absolute path; dest_path is under it
+        folder = ""
+        if os.path.isabs(model_root) and dest_path.startswith(model_root):
+            rel = os.path.relpath(os.path.dirname(dest_path), model_root)
+            folder = rel.replace(os.sep, "/") if rel != "." else ""
+
+        # 5. Add to scanner cache (same as CivitAI's _execute_download does)
+        scanner_getter = getattr(ServiceRegistry, scanner_getter_name, None)
+        if scanner_getter is not None:
+            scanner = await scanner_getter()
+            if scanner is not None:
+                metadata_dict = metadata.to_dict()
+                metadata_dict["hf_url"] = hf_url
+                await scanner.add_model_to_cache(metadata_dict, folder)
+                logger.info("Added %s to scanner cache (folder=%s)", dest_path, folder)
+
+    except Exception as exc:
+        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.
+
+        Uses the HF tree API endpoint which returns accurate file sizes
+        (including LFS-tracked files), unlike the model info endpoint.
+        """
+        repo = request.query.get("repo", "").strip()
+        if not repo or "/" not in repo:
+            return web.json_response(
+                {"error": "Missing or invalid 'repo' parameter (expected user/repo)"},
+                status=400,
+            )
+
+        url = f"https://huggingface.co/api/models/{repo}/tree/main"
+
+        try:
+            session = await _get_hf_api_session()
+            async with session.get(url) as resp:
+                if resp.status == 404:
+                    return web.json_response(
+                        {"error": f"Repo '{repo}' not found"}, status=404
+                    )
+                if resp.status != 200:
+                    text = await resp.text()
+                    return web.json_response(
+                        {"error": f"HF API error {resp.status}: {text[:200]}"},
+                        status=resp.status,
+                    )
+                tree: list[dict[str, Any]] = await resp.json()
+        except Exception as exc:
+            logger.error("Failed to fetch HF repo files: %s", exc)
+            return web.json_response({"error": str(exc)}, status=502)
+
+        files: list[dict[str, Any]] = []
+        for entry in tree:
+            path: str = entry.get("path", "")
+            ext = os.path.splitext(path)[1].lower()
+            if ext not in MODEL_FILE_EXTENSIONS:
+                continue
+            size = entry.get("size", 0) or 0
+            if size == 0 and "lfs" in entry:
+                size = entry["lfs"].get("size", 0) or 0
+            files.append({
+                "filename": path,
+                "size": size,
+            })
+
+        files.sort(key=lambda f: f["size"], reverse=True)
+        return web.json_response(files)
+
+    async def download_hf_model(self, request: web.Request) -> web.Response:
+        """Download a single file from Hugging Face into the model directory.
+
+        POST JSON body::
+
+            {
+              "repo": "dx8152/Flux2-Klein-9B-Consistency",
+              "filename": "Flux2-Klein-9B-consistency-V2.safetensors",
+              "revision": "main",
+              "model_root": "loras",
+              "relative_path": "",
+              "use_default_paths": false,
+              "download_id": "optional-batch-id"
+            }
+
+        If ``download_id`` is provided, real-time progress (bytes, speed,
+        percentage) is broadcast via the WebSocket progress system, matching
+        the CivitAI download experience.
+
+        Respects the ``download_backend`` setting (``aria2`` or ``default``).
+        """
+        try:
+            payload: dict[str, Any] = await request.json()
+        except json.JSONDecodeError:
+            return web.json_response({"error": "Invalid JSON"}, status=400)
+
+        repo = (payload.get("repo") or "").strip()
+        filename = (payload.get("filename") or "").strip()
+        revision = (payload.get("revision") or "main").strip()
+        model_root = (payload.get("model_root") or "").strip()
+        relative_path = (payload.get("relative_path") or "").strip()
+        use_default_paths = bool(payload.get("use_default_paths", False))
+        download_id: str | None = payload.get("download_id")
+
+        logger.info(
+            "download_hf_model: repo=%s file=%s root=%s download_id=%s",
+            repo, filename, model_root, download_id,
+        )
+
+        if not repo or not filename:
+            return web.json_response(
+                {"error": "Missing required fields: 'repo' and 'filename'"}, status=400
+            )
+
+        # Validate repo format — must be user/repo_name
+        if repo.count("/") != 1 or not re.match(r"^[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+$", repo):
+            return web.json_response({"error": f"Invalid repo format: {repo}"}, status=400)
+        author, repo_name = repo.split("/", 1)
+        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 traversal
+        if ".." in filename:
+            return web.json_response({"error": "Invalid filename"}, status=400)
+
+        # Validate relative_path — must not be absolute or escape base directory
+        if relative_path:
+            if os.path.isabs(relative_path):
+                return web.json_response({"error": "relative_path must not be absolute"}, status=400)
+            if ".." in relative_path.split("/") or "\\" in relative_path:
+                return web.json_response({"error": "Invalid relative_path"}, status=400)
+
+        # 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:
+            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)
+        elif relative_path:
+            target_dir = os.path.join(base_dir, relative_path)
+        else:
+            target_dir = base_dir
+
+        # Strip HF repo subdirectory — "diffusion_models/xxx.safetensors"
+        # is an HF repo convention, not meaningful for local storage.
+        file_base = os.path.basename(filename)
+
+        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:
+            logger.info("download_hf_model: file already exists, skipping — %s", dest_path)
+            return web.json_response({
+                "success": True,
+                "message": f"File already exists: {dest_path}",
+                "path": dest_path,
+            })
+
+        # Build HF resolve URL
+        resolve_url = (
+            f"https://huggingface.co/{repo}/resolve/{revision}/{filename}"
+        )
+
+        # Set up progress callback if download_id is provided
+        progress_callback = None
+        if download_id:
+
+            async def _progress_callback(
+                progress: float | DownloadProgress,
+                snapshot: DownloadProgress | None = None,
+            ) -> None:
+                percent = 0.0
+                metrics = snapshot if isinstance(snapshot, DownloadProgress) else None
+
+                if isinstance(progress, DownloadProgress):
+                    percent = progress.percent_complete
+                    metrics = progress
+                elif isinstance(snapshot, DownloadProgress):
+                    percent = snapshot.percent_complete
+                else:
+                    percent = float(progress)
+
+                broadcast: dict[str, Any] = {
+                    "status": "progress",
+                    "progress": round(percent),
+                }
+                if metrics:
+                    broadcast["bytes_downloaded"] = metrics.bytes_downloaded
+                    broadcast["total_bytes"] = metrics.total_bytes
+                    broadcast["bytes_per_second"] = metrics.bytes_per_second
+
+                await ws_manager.broadcast_download_progress(download_id, broadcast)
+
+            progress_callback = _progress_callback
+
+        # Respect download backend setting (aria2 vs default)
+        download_backend = (
+            get_settings_manager().get("download_backend", "default")
+        )
+
+        if download_backend == "aria2":
+            aria2 = await Aria2Downloader.get_instance()
+            aid = download_id or f"hf_{repo}_{filename}"
+            try:
+                hf_success, hf_result = await aria2.download_file(
+                    url=resolve_url,
+                    save_path=dest_path,
+                    download_id=aid,
+                    progress_callback=progress_callback,
+                )
+                if hf_success:
+                    await _save_hf_metadata(dest_path, repo, model_root)
+                    return web.json_response({
+                        "success": True,
+                        "message": f"Downloaded to {dest_path}",
+                        "path": dest_path,
+                    })
+                else:
+                    return web.json_response(
+                        {"success": False, "error": hf_result or "aria2 download failed"},
+                        status=500,
+                    )
+            except Exception as exc:
+                logger.error("HF download (aria2) failed: %s", exc)
+                return web.json_response(
+                    {"success": False, "error": str(exc)}, status=500
+                )
+
+        # Default: use built-in aiohttp Downloader
+        downloader = await get_downloader()
+        try:
+            success, result = await downloader.download_file(
+                url=resolve_url,
+                save_path=dest_path,
+                use_auth=False,
+                allow_resume=True,
+                progress_callback=progress_callback,
+            )
+            if success:
+                await _save_hf_metadata(dest_path, repo, model_root)
+                return web.json_response({
+                    "success": True,
+                    "message": f"Downloaded to {result}",
+                    "path": result,
+                })
+            else:
+                return web.json_response(
+                    {"success": False, "error": result or "Download failed"},
+                    status=500,
+                )
+        except Exception as exc:
+            logger.error("HF download failed: %s", exc)
+            return web.json_response(
+                {"success": False, "error": str(exc)}, status=500
+            )

py/routes/handlers/model_handlers.py

@@ -16,6 +16,10 @@ import jinja2
 
 from ...config import config
 from ...services.download_coordinator import DownloadCoordinator
+from ...services.connectivity_guard import (
+    OFFLINE_FRIENDLY_MESSAGE,
+    is_expected_offline_error,
+)
 from ...services.metadata_sync_service import MetadataSyncService
 from ...services.model_file_service import ModelMoveService
 from ...services.preview_asset_service import PreviewAssetService
@@ -33,6 +37,7 @@ from ...services.use_cases import (
 )
 from ...services.websocket_manager import WebSocketManager
 from ...services.websocket_progress_callback import WebSocketProgressCallback
+from ...services.download_queue_service import DownloadQueueService
 from ...services.errors import RateLimitError, ResourceNotFoundError
 from ...utils.civitai_utils import resolve_license_payload
 from ...utils.file_utils import calculate_sha256
@@ -149,6 +154,14 @@ class ModelPageView:
                 )
                 self._template_env._i18n_filter_added = True  # type: ignore[attr-defined]
 
+            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,
                 "settings": self._settings,
@@ -156,6 +169,8 @@ 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:
@@ -198,11 +213,17 @@ class ModelListingHandler:
             result = await self._service.get_paginated_data(**params)
 
             format_start = time.perf_counter()
+            formatted_raw = [
+                await self._service.format_response(entry)
+                for entry in result["items"]
+            ]
+            # Filter out None entries returned for corrupted cache rows (issue #730).
+            # Note: "total" intentionally remains the pre-filter count to reflect
+            # the true number of models in the cache; corrupted entries are rare
+            # and adjusting total would cause pagination drift on every page.
+            formatted_items = [item for item in formatted_raw if item is not None]
             formatted_result = {
-                "items": [
-                    await self._service.format_response(item)
-                    for item in result["items"]
-                ],
+                "items": formatted_items,
                 "total": result["total"],
                 "page": result["page"],
                 "page_size": result["page_size"],
@@ -224,6 +245,48 @@ class ModelListingHandler:
             )
             return web.json_response({"error": str(exc)}, status=500)
 
+    async def get_excluded_models(self, request: web.Request) -> web.Response:
+        start_time = time.perf_counter()
+        try:
+            params = self._parse_common_params(request)
+            # group_by_model is meaningless for excluded view; strip it
+            params.pop("group_by_model", None)
+            result = await self._service.get_excluded_paginated_data(**params)
+
+            format_start = time.perf_counter()
+            formatted_raw = [
+                await self._service.format_response(entry)
+                for entry in result["items"]
+            ]
+            # Filter out None entries returned for corrupted cache rows (issue #730).
+            # "total" stays at the pre-filter count; see get_models for rationale.
+            formatted_items = [item for item in formatted_raw if item is not None]
+            formatted_result = {
+                "items": formatted_items,
+                "total": result["total"],
+                "page": result["page"],
+                "page_size": result["page_size"],
+                "total_pages": result["total_pages"],
+            }
+            format_duration = time.perf_counter() - format_start
+
+            duration = time.perf_counter() - start_time
+            self._logger.debug(
+                "Request for %s/excluded took %.3fs (formatting: %.3fs)",
+                self._service.model_type,
+                duration,
+                format_duration,
+            )
+            return web.json_response(formatted_result)
+        except Exception as exc:
+            self._logger.error(
+                "Error retrieving excluded %ss: %s",
+                self._service.model_type,
+                exc,
+                exc_info=True,
+            )
+            return web.json_response({"error": str(exc)}, status=500)
+
     def _parse_common_params(self, request: web.Request) -> Dict:
         page = int(request.query.get("page", "1"))
         page_size = min(int(request.query.get("page_size", "20")), 100)
@@ -261,6 +324,15 @@ class ModelListingHandler:
         for tag in exclude_tags:
             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"
+
         favorites_only = request.query.get("favorites_only", "false").lower() == "true"
 
         search_options = {
@@ -316,6 +388,19 @@ class ModelListingHandler:
             request.query.get("name_pattern_use_regex", "false").lower() == "true"
         )
 
+        # Group-by-model flag: deduplicate versions sharing the same civitai modelId
+        group_by_model = (
+            request.query.get("group_by_model", "false").lower() == "true"
+        )
+
+        # View-local-versions filter: show all local versions of a specific model
+        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
+
         return {
             "page": page,
             "page_size": page_size,
@@ -327,6 +412,7 @@ class ModelListingHandler:
             "fuzzy_search": fuzzy_search,
             "base_models": base_models,
             "tags": tag_filters,
+            "auto_tags": auto_tag_filters,
             "tag_logic": tag_logic,
             "search_options": search_options,
             "hash_filters": hash_filters,
@@ -338,6 +424,8 @@ class ModelListingHandler:
             "name_pattern_include": name_pattern_include,
             "name_pattern_exclude": name_pattern_exclude,
             "name_pattern_use_regex": name_pattern_use_regex,
+            "group_by_model": group_by_model,
+            "civitai_model_id": civitai_model_id,
             **self._parse_specific_params(request),
         }
 
@@ -392,6 +480,21 @@ class ModelManagementHandler:
             self._logger.error("Error excluding model: %s", exc, exc_info=True)
             return web.Response(text=str(exc), status=500)
 
+    async def unexclude_model(self, request: web.Request) -> web.Response:
+        try:
+            data = await request.json()
+            file_path = data.get("file_path")
+            if not file_path:
+                return web.Response(text="Model path is required", status=400)
+
+            result = await self._lifecycle_service.unexclude_model(file_path)
+            return web.json_response(result)
+        except ValueError as exc:
+            return web.json_response({"success": False, "error": str(exc)}, status=400)
+        except Exception as exc:
+            self._logger.error("Error restoring model: %s", exc, exc_info=True)
+            return web.Response(text=str(exc), status=500)
+
     async def fetch_civitai(self, request: web.Request) -> web.Response:
         try:
             data = await request.json()
@@ -450,9 +553,19 @@ class ModelManagementHandler:
             if not success:
                 return web.json_response({"success": False, "error": error})
 
-            formatted_metadata = await self._service.format_response(model_data)
-            return web.json_response({"success": True, "metadata": formatted_metadata})
+            formatted = await self._service.format_response(model_data)
+            if formatted is None:
+                return web.json_response(
+                    {"success": False, "error": "Model entry is corrupted (missing file_path)"},
+                    status=500,
+                )
+            return web.json_response({"success": True, "metadata": formatted})
         except Exception as exc:
+            if is_expected_offline_error(str(exc)):
+                return web.json_response(
+                    {"success": False, "error": OFFLINE_FRIENDLY_MESSAGE},
+                    status=503,
+                )
             self._logger.error("Error fetching from CivitAI: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
@@ -499,6 +612,11 @@ class ModelManagementHandler:
                 }
             )
         except Exception as exc:
+            if is_expected_offline_error(str(exc)):
+                return web.json_response(
+                    {"success": False, "error": OFFLINE_FRIENDLY_MESSAGE},
+                    status=503,
+                )
             self._logger.error("Error re-linking to CivitAI: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
@@ -713,7 +831,7 @@ class ModelManagementHandler:
 
             metadata_updates = {k: v for k, v in data.items() if k != "file_path"}
 
-            await self._metadata_sync.save_metadata_updates(
+            updated_metadata = await self._metadata_sync.save_metadata_updates(
                 file_path=file_path,
                 updates=metadata_updates,
                 metadata_loader=self._metadata_sync.load_local_metadata,
@@ -724,7 +842,12 @@ class ModelManagementHandler:
                 cache = await self._service.scanner.get_cached_data()
                 await cache.resort()
 
-            return web.json_response({"success": True})
+            from ...services.auto_tag_service import extract_auto_tags
+            auto_tags = extract_auto_tags(updated_metadata)
+
+            return web.json_response(
+                {"success": True, "auto_tags": auto_tags}
+            )
         except Exception as exc:
             self._logger.error("Error saving metadata: %s", exc, exc_info=True)
             return web.Response(text=str(exc), status=500)
@@ -741,14 +864,16 @@ class ModelManagementHandler:
             if not isinstance(new_tags, list):
                 return web.Response(text="Tags must be a list", status=400)
 
-            tags = await self._tag_update_service.add_tags(
+            tags, auto_tags = await self._tag_update_service.add_tags(
                 file_path=file_path,
                 new_tags=new_tags,
                 metadata_loader=self._metadata_sync.load_local_metadata,
                 update_cache=self._service.scanner.update_single_model_cache,
             )
 
-            return web.json_response({"success": True, "tags": tags})
+            return web.json_response(
+                {"success": True, "tags": tags, "auto_tags": auto_tags}
+            )
         except Exception as exc:
             self._logger.error("Error adding tags: %s", exc, exc_info=True)
             return web.Response(text=str(exc), status=500)
@@ -848,6 +973,8 @@ 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:
@@ -856,10 +983,26 @@ 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"))
-            if limit < 1 or limit > 100:
+            if limit < 0 or limit > 100:
                 limit = 20
             base_models = await self._service.get_base_models(limit)
             return web.json_response({"success": True, "base_models": base_models})
@@ -991,10 +1134,12 @@ class ModelQueryHandler:
                 # Sort: originals first, copies last
                 sorted_models = self._sort_duplicate_group(filtered)
 
-                # Format response
+                # Format response, filtering out corrupted entries (issue #730)
                 group = {"hash": sha256, "models": []}
                 for model in sorted_models:
-                    group["models"].append(await self._service.format_response(model))
+                    formatted = await self._service.format_response(model)
+                    if formatted is not None:
+                        group["models"].append(formatted)
 
                 # Only include groups with 2+ models after filtering
                 if len(group["models"]) > 1:
@@ -1095,6 +1240,12 @@ class ModelQueryHandler:
 
     async def find_filename_conflicts(self, request: web.Request) -> web.Response:
         try:
+            settings = get_settings_manager()
+            if settings.get("lora_syntax_format", "legacy") == "full":
+                return web.json_response(
+                    {"success": True, "conflicts": [], "count": 0}
+                )
+
             duplicates = self._service.find_duplicate_filenames()
             result = []
             cache = await self._service.scanner.get_cached_data()
@@ -1105,9 +1256,9 @@ class ModelQueryHandler:
                         (m for m in cache.raw_data if m["file_path"] == path), None
                     )
                     if model:
-                        group["models"].append(
-                            await self._service.format_response(model)
-                        )
+                        formatted = await self._service.format_response(model)
+                        if formatted is not None:
+                            group["models"].append(formatted)
                 hash_val = self._service.scanner.get_hash_by_filename(filename)
                 if hash_val:
                     main_path = self._service.get_path_by_hash(hash_val)
@@ -1117,9 +1268,9 @@ class ModelQueryHandler:
                             None,
                         )
                         if main_model:
-                            group["models"].insert(
-                                0, await self._service.format_response(main_model)
-                            )
+                            formatted = await self._service.format_response(main_model)
+                            if formatted is not None:
+                                group["models"].insert(0, formatted)
                 if group["models"]:
                     result.append(group)
             return web.json_response(
@@ -1142,9 +1293,13 @@ 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,
@@ -1180,9 +1335,28 @@ 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.
+                    try:
+                        settings = get_settings_manager()
+                        response_payload["use_new_license_icons"] = settings.get("use_new_license_icons", True)
+                    except Exception:
+                        pass
                 return web.json_response(response_payload)
             return web.json_response(
                 {
@@ -1384,6 +1558,21 @@ class ModelDownloadHandler:
             )
             return web.Response(status=500, text=str(exc))
 
+    async def skip_download_get(self, request: web.Request) -> web.Response:
+        try:
+            download_id = request.query.get("download_id")
+            if not download_id:
+                return web.json_response(
+                    {"success": False, "error": "Download ID is required"}, status=400
+                )
+            result = await self._download_coordinator.skip_download(download_id)
+            return web.json_response(result)
+        except Exception as exc:
+            self._logger.error(
+                "Error skipping download via GET: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
     async def cancel_download_get(self, request: web.Request) -> web.Response:
         try:
             download_id = request.query.get("download_id")
@@ -1464,6 +1653,303 @@ class ModelDownloadHandler:
             )
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
+    # ------------------------------------------------------------------
+    # Download queue / history handlers
+    # ------------------------------------------------------------------
+
+    async def get_download_queue(self, request: web.Request) -> web.Response:
+        try:
+            service = await DownloadQueueService.get_instance()
+            queue = await service.get_queue()
+            stats = await service.get_stats()
+            return web.json_response({"success": True, "queue": queue, "stats": stats})
+        except Exception as exc:
+            self._logger.error(
+                "Error getting download queue: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def add_to_download_queue(self, request: web.Request) -> web.Response:
+        try:
+            import uuid
+
+            download_id = request.query.get("download_id") or str(uuid.uuid4())
+            model_id_str = request.query.get("model_id")
+            model_version_id_str = request.query.get("model_version_id")
+            model_name = request.query.get("model_name", "")
+            version_name = request.query.get("version_name", "")
+            thumbnail_url = request.query.get("thumbnail_url", "")
+            source = request.query.get("source")
+            file_params_json = request.query.get("file_params")
+
+            model_id = int(model_id_str) if model_id_str else None
+            model_version_id = int(model_version_id_str) if model_version_id_str else None
+            file_params = json.loads(file_params_json) if file_params_json else None
+
+            service = await DownloadQueueService.get_instance()
+            item = await service.add_to_queue(
+                download_id=download_id,
+                model_id=model_id,
+                model_version_id=model_version_id,
+                model_name=model_name,
+                version_name=version_name,
+                thumbnail_url=thumbnail_url,
+                source=source,
+                file_params=file_params,
+            )
+            return web.json_response({"success": True, "item": item})
+        except Exception as exc:
+            self._logger.error(
+                "Error adding to download queue: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def remove_from_download_queue(self, request: web.Request) -> web.Response:
+        try:
+            download_id = request.query.get("download_id")
+            if not download_id:
+                return web.json_response(
+                    {"success": False, "error": "download_id is required"}, status=400
+                )
+
+            service = await DownloadQueueService.get_instance()
+            removed = await service.remove_from_queue(download_id)
+            return web.json_response({"success": removed})
+        except Exception as exc:
+            self._logger.error(
+                "Error removing from download queue: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def move_queue_item_to_top(self, request: web.Request) -> web.Response:
+        try:
+            download_id = request.query.get("download_id")
+            if not download_id:
+                return web.json_response(
+                    {"success": False, "error": "download_id is required"}, status=400
+                )
+
+            service = await DownloadQueueService.get_instance()
+            moved = await service.move_to_top(download_id)
+            return web.json_response({"success": moved})
+        except Exception as exc:
+            self._logger.error(
+                "Error moving queue item to top: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def move_queue_item_to_end(self, request: web.Request) -> web.Response:
+        try:
+            download_id = request.query.get("download_id")
+            if not download_id:
+                return web.json_response(
+                    {"success": False, "error": "download_id is required"}, status=400
+                )
+
+            service = await DownloadQueueService.get_instance()
+            moved = await service.move_to_end(download_id)
+            return web.json_response({"success": moved})
+        except Exception as exc:
+            self._logger.error(
+                "Error moving queue item to end: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def clear_download_queue(self, request: web.Request) -> web.Response:
+        try:
+            status_filter = request.query.get("status") or None
+            service = await DownloadQueueService.get_instance()
+            cleared = await service.clear_queue(status_filter=status_filter)
+            return web.json_response({"success": True, "cleared": cleared})
+        except Exception as exc:
+            self._logger.error(
+                "Error clearing download queue: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def get_download_history(self, request: web.Request) -> web.Response:
+        try:
+            limit = min(int(request.query.get("limit", "50")), 500)
+            offset = int(request.query.get("offset", "0"))
+            status_filter = request.query.get("status") or None
+            service = await DownloadQueueService.get_instance()
+            result = await service.get_history(
+                limit=limit, offset=offset, status_filter=status_filter
+            )
+            return web.json_response(
+                {
+                    "success": True,
+                    "items": result["items"],
+                    "total": result["total"],
+                    "limit": result["limit"],
+                    "offset": result["offset"],
+                }
+            )
+        except Exception as exc:
+            self._logger.error(
+                "Error getting download history: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def clear_download_history(self, request: web.Request) -> web.Response:
+        try:
+            status_filter = request.query.get("status") or None
+            service = await DownloadQueueService.get_instance()
+            cleared = await service.clear_history(status_filter=status_filter)
+            return web.json_response({"success": True, "cleared": cleared})
+        except Exception as exc:
+            self._logger.error(
+                "Error clearing download history: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def delete_download_history_item(self, request: web.Request) -> web.Response:
+        try:
+            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 or download_id is required"},
+                    status=400,
+                )
+
+            service = await DownloadQueueService.get_instance()
+            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(
+                "Error deleting download history item: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def retry_download_from_history(self, request: web.Request) -> web.Response:
+        try:
+            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 or download_id is required"},
+                    status=400,
+                )
+
+            service = await DownloadQueueService.get_instance()
+            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"},
+                    status=404,
+                )
+            return web.json_response({"success": True, "item": item})
+        except Exception as exc:
+            self._logger.error(
+                "Error retrying download from history: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def retry_all_failed_downloads(self, request: web.Request) -> web.Response:
+        try:
+            service = await DownloadQueueService.get_instance()
+            retry_count = await service.retry_all_failed()
+            return web.json_response({"success": True, "retry_count": retry_count})
+        except Exception as exc:
+            self._logger.error(
+                "Error retrying all failed downloads: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def complete_download_in_queue(self, request: web.Request) -> web.Response:
+        """Atomically move a download from queue to history with terminal status."""
+        try:
+            download_id = request.query.get("download_id")
+            if not download_id:
+                return web.json_response(
+                    {"success": False, "error": "download_id is required"}, status=400
+                )
+            status = request.query.get("status", "completed")
+            error = request.query.get("error")
+            file_path = request.query.get("file_path")
+            try:
+                bytes_downloaded = int(request.query.get("bytes_downloaded", "0"))
+            except (TypeError, ValueError):
+                bytes_downloaded = 0
+            total_bytes_raw = request.query.get("total_bytes")
+            total_bytes = int(total_bytes_raw) if total_bytes_raw else None
+            completed_at_raw = request.query.get("completed_at")
+            completed_at = float(completed_at_raw) if completed_at_raw else None
+
+            service = await DownloadQueueService.get_instance()
+            item = await service.complete_download(
+                download_id=download_id,
+                status=status,
+                error=error,
+                file_path=file_path,
+                bytes_downloaded=bytes_downloaded,
+                total_bytes=total_bytes,
+                completed_at=completed_at,
+            )
+            if item is None:
+                return web.json_response(
+                    {"success": False, "error": "Download not found in queue"}, status=404
+                )
+            return web.json_response({"success": True, "item": item})
+        except Exception as exc:
+            self._logger.error(
+                "Error completing download: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def get_download_stats(self, request: web.Request) -> web.Response:
+        try:
+            service = await DownloadQueueService.get_instance()
+            stats = await service.get_stats()
+            return web.json_response({"success": True, "stats": stats})
+        except Exception as exc:
+            self._logger.error(
+                "Error getting download stats: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def update_download_queue_status(self, request: web.Request) -> web.Response:
+        """Update the status of a queue item (non-terminal transitions).
+
+        Supported transitions include ``queued → downloading``,
+        ``downloading → paused``, ``paused → downloading``, etc.
+        Terminal transitions (``completed``, ``failed``, ``canceled``)
+        should use ``complete_download_in_queue`` instead.
+        """
+        try:
+            download_id = request.query.get("download_id")
+            status = request.query.get("status")
+            if not download_id or not status:
+                return web.json_response(
+                    {
+                        "success": False,
+                        "error": "download_id and status are required",
+                    },
+                    status=400,
+                )
+            service = await DownloadQueueService.get_instance()
+            updated = await service.update_status(download_id, status)
+            if not updated:
+                return web.json_response(
+                    {"success": False, "error": "Download not found in queue"},
+                    status=404,
+                )
+            return web.json_response({"success": True})
+        except Exception as exc:
+            self._logger.error(
+                "Error updating download queue status: %s", exc, exc_info=True
+            )
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
 
 class ModelCivitaiHandler:
     """CivitAI integration endpoints."""
@@ -1505,7 +1991,9 @@ class ModelCivitaiHandler:
             return web.json_response(result)
         except Exception as exc:
             self._logger.error(
-                "Error in fetch_all_civitai for %ss: %s", self._service.model_type, exc
+                "Error in fetch_all_civitai for %ss: %s",
+                self._service.model_type, exc,
+                exc_info=True,
             )
             return web.Response(text=str(exc), status=500)
 
@@ -1807,6 +2295,11 @@ class ModelUpdateHandler:
                 status=429,
             )
         except Exception as exc:  # pragma: no cover - defensive log
+            if is_expected_offline_error(str(exc)):
+                return web.json_response(
+                    {"success": False, "error": OFFLINE_FRIENDLY_MESSAGE},
+                    status=503,
+                )
             self._logger.error("Failed to fetch license info: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
@@ -1867,6 +2360,10 @@ class ModelUpdateHandler:
         if target_model_ids:
             target_model_ids = sorted(set(target_model_ids))
 
+        folder_path: Optional[str] = payload.get("folder_path")
+        if folder_path is not None and not isinstance(folder_path, str):
+            folder_path = None
+
         provider = await self._get_civitai_provider()
         if provider is None:
             return web.json_response(
@@ -1881,6 +2378,7 @@ class ModelUpdateHandler:
                 provider,
                 force_refresh=force_refresh,
                 target_model_ids=target_model_ids or None,
+                folder_path=folder_path,
             )
             if self._service.scanner.is_cancelled():
                 return web.json_response(
@@ -1895,15 +2393,29 @@ class ModelUpdateHandler:
                 {"success": False, "error": str(exc) or "Rate limited"}, status=429
             )
         except Exception as exc:  # pragma: no cover - defensive logging
-            self._logger.error(
-                "Failed to refresh model updates: %s", exc, exc_info=True
-            )
+            if is_expected_offline_error(str(exc)):
+                return web.json_response(
+                    {"success": False, "error": OFFLINE_FRIENDLY_MESSAGE},
+                    status=503,
+                )
+            self._logger.error("Failed to refresh model updates: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
+        hide_early_access = False
+        if self._settings is not None:
+            try:
+                hide_early_access = bool(
+                    self._settings.get("hide_early_access_updates", False)
+                )
+            except Exception:
+                pass
+
         serialized_records = []
         for record in records.values():
             has_update_fn = getattr(record, "has_update", None)
-            if callable(has_update_fn) and has_update_fn():
+            if callable(has_update_fn) and has_update_fn(
+                hide_early_access=hide_early_access
+            ):
                 serialized_records.append(self._serialize_record(record))
 
         return web.json_response(
@@ -2350,6 +2862,7 @@ class ModelUpdateHandler:
             "shouldIgnore": version.should_ignore,
             "earlyAccessEndsAt": version.early_access_ends_at,
             "isEarlyAccess": is_early_access,
+            "usageControl": version.usage_control,
             "filePath": context.get("file_path"),
             "fileName": context.get("file_name"),
         }
@@ -2437,8 +2950,10 @@ class ModelHandlerSet:
         return {
             "handle_models_page": self.page_view.handle,
             "get_models": self.listing.get_models,
+            "get_excluded_models": self.listing.get_excluded_models,
             "delete_model": self.management.delete_model,
             "exclude_model": self.management.exclude_model,
+            "unexclude_model": self.management.unexclude_model,
             "fetch_civitai": self.management.fetch_civitai,
             "fetch_all_civitai": self.civitai.fetch_all_civitai,
             "relink_civitai": self.management.relink_civitai,
@@ -2450,6 +2965,7 @@ 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,
@@ -2462,9 +2978,24 @@ class ModelHandlerSet:
             "download_model": self.download.download_model,
             "download_model_get": self.download.download_model_get,
             "cancel_download_get": self.download.cancel_download_get,
+            "skip_download_get": self.download.skip_download_get,
             "pause_download_get": self.download.pause_download_get,
             "resume_download_get": self.download.resume_download_get,
             "get_download_progress": self.download.get_download_progress,
+            "get_download_queue": self.download.get_download_queue,
+            "add_to_download_queue": self.download.add_to_download_queue,
+            "remove_from_download_queue": self.download.remove_from_download_queue,
+            "move_queue_item_to_top": self.download.move_queue_item_to_top,
+            "move_queue_item_to_end": self.download.move_queue_item_to_end,
+            "clear_download_queue": self.download.clear_download_queue,
+            "get_download_history": self.download.get_download_history,
+            "clear_download_history": self.download.clear_download_history,
+            "delete_download_history_item": self.download.delete_download_history_item,
+            "retry_download_from_history": self.download.retry_download_from_history,
+            "retry_all_failed_downloads": self.download.retry_all_failed_downloads,
+            "complete_download_in_queue": self.download.complete_download_in_queue,
+            "get_download_stats": self.download.get_download_stats,
+            "update_download_queue_status": self.download.update_download_queue_status,
             "get_civitai_versions": self.civitai.get_civitai_versions,
             "get_civitai_model_by_version": self.civitai.get_civitai_model_by_version,
             "get_civitai_model_by_hash": self.civitai.get_civitai_model_by_hash,

py/routes/handlers/preview_handlers.py

@@ -2,7 +2,9 @@
 
 from __future__ import annotations
 
+import asyncio
 import logging
+import mimetypes
 import urllib.parse
 from pathlib import Path
 
@@ -12,6 +14,12 @@ from ...config import config as global_config
 
 logger = logging.getLogger(__name__)
 
+_CHUNK_SIZE = 1024 * 1024  # 1 MB — balance between streaming iteration overhead and per-chunk memory
+
+# Video file extensions that bypass native sendfile on Windows
+# to avoid IOCP/ProactorEventLoop crashes during client disconnect.
+_VIDEO_EXTENSIONS = frozenset({".mp4", ".webm", ".mov", ".avi", ".mkv"})
+
 
 class PreviewHandler:
     """Serve preview assets for the active library at request time."""
@@ -46,10 +54,90 @@ 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 and content headers for us.
-        return web.FileResponse(path=resolved, chunk_size=256 * 1024)
+        # aiohttp's FileResponse handles range requests, content headers, and
+        # uses kernel sendfile (zero-copy DMA) on Linux/macOS. On Windows it
+        # uses IOCP-based _sendfile_native which can crash when the client
+        # disconnects mid-transfer during fast scrolling. The _stream_file()
+        # fallback is kept for a future compat toggle.
+        #
+        # Set explicit Cache-Control so the browser can cache video (and image)
+        # previews across VirtualScroller recycling cycles. Without this,
+        # Chrome does not cache 206 Partial Content responses for <video>
+        # elements, causing the same video to be re-downloaded on every scroll.
+        resp = web.FileResponse(path=resolved, chunk_size=_CHUNK_SIZE)
+        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:
+        """Stream a file chunk-by-chunk, bypassing native sendfile.
+
+        This avoids the Windows IOCP ``_sendfile_native`` crash that occurs
+        when the client disconnects during a large file transfer.
+        """
+        content_type, _ = mimetypes.guess_type(str(path))
+        if content_type is None:
+            content_type = "application/octet-stream"
+
+        file_size = path.stat().st_size
+        resp = web.StreamResponse()
+        resp.content_type = content_type
+        resp.content_length = file_size
+
+        # Allow browser caching: video previews rarely change during a session.
+        # The frontend already appends ?t={version} to bust cache on update.
+        resp.headers["Cache-Control"] = "public, max-age=86400"
+
+        await resp.prepare(request)
+
+        try:
+            with open(path, "rb") as f:
+                while True:
+                    chunk = f.read(_CHUNK_SIZE)
+                    if not chunk:
+                        break
+                    await resp.write(chunk)
+        except (ConnectionResetError, ConnectionAbortedError):
+            # Client disconnected during streaming — expected when scrolling
+            # rapidly through a library with animated previews.
+            pass
+        except OSError as exc:
+            logger.debug("I/O error streaming preview %s: %s", path, exc)
+
+        return resp
 
 
 __all__ = ["PreviewHandler"]

py/routes/misc_route_registrar.py

@@ -22,8 +22,11 @@ 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"),
     RouteDefinition("POST", "/api/lm/doctor/export-bundle", "export_doctor_bundle"),
     RouteDefinition("GET", "/api/lm/priority-tags", "get_priority_tags"),
     RouteDefinition("GET", "/api/lm/settings/libraries", "get_settings_libraries"),
@@ -36,12 +39,15 @@ 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"),
     RouteDefinition(
         "GET",
         "/api/lm/model-version-download-status",
@@ -89,6 +95,29 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition(
         "GET", "/api/lm/base-models/cache-status", "get_base_model_cache_status"
     ),
+    RouteDefinition(
+        "GET", "/api/lm/delete-model-version", "delete_model_version"
+    ),
+    # Hugging Face model endpoints
+    RouteDefinition(
+        "GET", "/api/lm/hf-repo-files", "get_hf_repo_files"
+    ),
+    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"
+    ),
 )
 
 

py/routes/misc_routes.py

@@ -39,6 +39,8 @@ from .handlers.misc_handlers import (
     build_service_registry_adapter,
 )
 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__)
@@ -136,6 +138,8 @@ class MiscRoutes:
         doctor = DoctorHandler(settings_service=self._settings)
         example_workflows = ExampleWorkflowsHandler()
         base_model = BaseModelHandlerSet()
+        hf_handler = HfHandler()
+        agent_handler = AgentHandler()
 
         return self._handler_set_factory(
             health=health,
@@ -155,6 +159,8 @@ class MiscRoutes:
             doctor=doctor,
             example_workflows=example_workflows,
             base_model=base_model,
+            hf_handler=hf_handler,
+            agent_handler=agent_handler,
         )
 
 

py/routes/model_route_registrar.py

@@ -22,8 +22,10 @@ class RouteDefinition:
 
 COMMON_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition("GET", "/api/lm/{prefix}/list", "get_models"),
+    RouteDefinition("GET", "/api/lm/{prefix}/excluded", "get_excluded_models"),
     RouteDefinition("POST", "/api/lm/{prefix}/delete", "delete_model"),
     RouteDefinition("POST", "/api/lm/{prefix}/exclude", "exclude_model"),
+    RouteDefinition("POST", "/api/lm/{prefix}/unexclude", "unexclude_model"),
     RouteDefinition("POST", "/api/lm/{prefix}/fetch-civitai", "fetch_civitai"),
     RouteDefinition("POST", "/api/lm/{prefix}/fetch-all-civitai", "fetch_all_civitai"),
     RouteDefinition("POST", "/api/lm/{prefix}/relink-civitai", "relink_civitai"),
@@ -44,6 +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"),
@@ -99,11 +102,46 @@ COMMON_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition("POST", "/api/lm/download-model", "download_model"),
     RouteDefinition("GET", "/api/lm/download-model-get", "download_model_get"),
     RouteDefinition("GET", "/api/lm/cancel-download-get", "cancel_download_get"),
+    RouteDefinition("GET", "/api/lm/skip-download", "skip_download_get"),
     RouteDefinition("GET", "/api/lm/pause-download", "pause_download_get"),
     RouteDefinition("GET", "/api/lm/resume-download", "resume_download_get"),
     RouteDefinition(
         "GET", "/api/lm/download-progress/{download_id}", "get_download_progress"
     ),
+    RouteDefinition("GET", "/api/lm/downloads/queue", "get_download_queue"),
+    RouteDefinition("GET", "/api/lm/downloads/queue/add", "add_to_download_queue"),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/remove", "remove_from_download_queue"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/move-to-top", "move_queue_item_to_top"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/move-to-end", "move_queue_item_to_end"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/clear", "clear_download_queue"
+    ),
+    RouteDefinition("GET", "/api/lm/downloads/history", "get_download_history"),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/history/clear", "clear_download_history"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/history/delete", "delete_download_history_item"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/history/retry", "retry_download_from_history"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/history/retry-all", "retry_all_failed_downloads"
+    ),
+    RouteDefinition("GET", "/api/lm/downloads/stats", "get_download_stats"),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/complete", "complete_download_in_queue"
+    ),
+    RouteDefinition(
+        "GET", "/api/lm/downloads/queue/status", "update_download_queue_status"
+    ),
     RouteDefinition("POST", "/api/lm/{prefix}/cancel-task", "cancel_task"),
     RouteDefinition("GET", "/{prefix}", "handle_models_page"),
 )

py/routes/recipe_route_registrar.py

@@ -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"),
@@ -58,6 +59,7 @@ ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition("POST", "/api/lm/recipes/repair", "repair_recipes"),
     RouteDefinition("POST", "/api/lm/recipes/cancel-repair", "cancel_repair"),
     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/batch-import/start", "start_batch_import"),
     RouteDefinition(
@@ -70,6 +72,16 @@ ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
         "POST", "/api/lm/recipes/batch-import/directory", "start_directory_import"
     ),
     RouteDefinition("POST", "/api/lm/recipes/browse-directory", "browse_directory"),
+    RouteDefinition(
+        "GET", "/api/lm/recipes/check-image-exists", "check_image_exists"
+    ),
+    RouteDefinition("GET", "/api/lm/recipes/import-from-url", "import_from_url"),
+    RouteDefinition(
+        "POST", "/api/lm/recipes/create-from-example", "create_from_example"
+    ),
+    RouteDefinition(
+        "POST", "/api/lm/recipe/{recipe_id}/reimport", "reimport_recipe"
+    ),
 )
 
 

py/routes/stats_routes.py

@@ -11,6 +11,8 @@ from ..config import config
 from ..services.settings_manager import get_settings_manager
 from ..services.server_i18n import server_i18n
 from ..services.service_registry import ServiceRegistry
+from ..services.model_query import normalize_sub_type, resolve_sub_type
+from ..utils.constants import VALID_LORA_SUB_TYPES, VALID_CHECKPOINT_SUB_TYPES
 from ..utils.usage_stats import UsageStats
 
 logger = logging.getLogger(__name__)
@@ -140,6 +142,21 @@ class StatsRoutes:
             # Get usage statistics
             usage_data = await self.usage_stats.get_stats()
             
+            # CivitAI model type distribution across all model types
+            # Use the same logic as the filter panel: normalize_sub_type(resolve_sub_type(entry))
+            # with sub-type validation per model type
+            model_types_counter: Counter[str] = Counter()
+            for entry in lora_cache.raw_data:
+                ntype = normalize_sub_type(resolve_sub_type(entry))
+                if ntype and ntype in VALID_LORA_SUB_TYPES:
+                    model_types_counter[ntype] += 1
+            for entry in checkpoint_cache.raw_data:
+                ntype = normalize_sub_type(resolve_sub_type(entry))
+                if ntype and ntype in VALID_CHECKPOINT_SUB_TYPES:
+                    model_types_counter[ntype] += 1
+            # Embeddings: always count as "embedding" regardless of CivitAI sub-type
+            model_types_counter['embedding'] = len(embedding_cache.raw_data)
+            
             return web.json_response({
                 'success': True,
                 'data': {
@@ -154,7 +171,8 @@ class StatsRoutes:
                     'total_generations': usage_data.get('total_executions', 0),
                     'unused_loras': self._count_unused_models(lora_cache.raw_data, usage_data.get('loras', {})),
                     'unused_checkpoints': self._count_unused_models(checkpoint_cache.raw_data, usage_data.get('checkpoints', {})),
-                    'unused_embeddings': self._count_unused_models(embedding_cache.raw_data, usage_data.get('embeddings', {}))
+                    'unused_embeddings': self._count_unused_models(embedding_cache.raw_data, usage_data.get('embeddings', {})),
+                    'model_types_distribution': dict(model_types_counter.most_common())
                 }
             })
             
@@ -459,9 +477,12 @@ class StatsRoutes:
                 if unused_lora_percent > 50:
                     insights.append({
                         'type': 'warning',
-                        'title': 'High Number of Unused LoRAs',
-                        'description': f'{unused_lora_percent:.1f}% of your LoRAs ({unused_loras}/{total_loras}) have never been used.',
-                        'suggestion': 'Consider organizing or archiving unused models to free up storage space.'
+                        'key': 'insights.unusedLoras.high',
+                        'params': {
+                            'percent': f'{unused_lora_percent:.1f}',
+                            'count': str(unused_loras),
+                            'total': str(total_loras)
+                        }
                     })
             
             if total_checkpoints > 0:
@@ -469,9 +490,12 @@ class StatsRoutes:
                 if unused_checkpoint_percent > 30:
                     insights.append({
                         'type': 'warning',
-                        'title': 'Unused Checkpoints Detected',
-                        'description': f'{unused_checkpoint_percent:.1f}% of your checkpoints ({unused_checkpoints}/{total_checkpoints}) have never been used.',
-                        'suggestion': 'Review and consider removing checkpoints you no longer need.'
+                        'key': 'insights.unusedCheckpoints.detected',
+                        'params': {
+                            'percent': f'{unused_checkpoint_percent:.1f}',
+                            'count': str(unused_checkpoints),
+                            'total': str(total_checkpoints)
+                        }
                     })
             
             if total_embeddings > 0:
@@ -479,9 +503,12 @@ class StatsRoutes:
                 if unused_embedding_percent > 50:
                     insights.append({
                         'type': 'warning',
-                        'title': 'High Number of Unused Embeddings',
-                        'description': f'{unused_embedding_percent:.1f}% of your embeddings ({unused_embeddings}/{total_embeddings}) have never been used.',
-                        'suggestion': 'Consider organizing or archiving unused embeddings to optimize your collection.'
+                        'key': 'insights.unusedEmbeddings.high',
+                        'params': {
+                            'percent': f'{unused_embedding_percent:.1f}',
+                            'count': str(unused_embeddings),
+                            'total': str(total_embeddings)
+                        }
                     })
             
             # Storage insights
@@ -492,18 +519,20 @@ class StatsRoutes:
             if total_size > 100 * 1024 * 1024 * 1024:  # 100GB
                 insights.append({
                     'type': 'info',
-                    'title': 'Large Collection Detected',
-                    'description': f'Your model collection is using {self._format_size(total_size)} of storage.',
-                    'suggestion': 'Consider using external storage or cloud solutions for better organization.'
+                    'key': 'insights.collection.large',
+                    'params': {
+                        'size': self._format_size(total_size)
+                    }
                 })
             
             # Recent activity insight
             if usage_data.get('total_executions', 0) > 100:
                 insights.append({
                     'type': 'success',
-                    'title': 'Active User',
-                    'description': f'You\'ve completed {usage_data["total_executions"]} generations so far!',
-                    'suggestion': 'Keep exploring and creating amazing content with your models.'
+                    'key': 'insights.activity.active',
+                    'params': {
+                        'count': str(usage_data['total_executions'])
+                    }
                 })
             
             return web.json_response({

py/routes/update_routes.py

@@ -1,7 +1,6 @@
 import os
 import logging
 import toml
-import git
 import zipfile
 import shutil
 import tempfile
@@ -11,11 +10,33 @@ from typing import Dict, List
 
 from ..utils.settings_paths import ensure_settings_file
 from ..services.downloader import get_downloader
+from ..services.service_registry import ServiceRegistry
 
 logger = logging.getLogger(__name__)
 
 NETWORK_EXCEPTIONS = (ClientError, OSError, asyncio.TimeoutError)
 
+# User-managed directories that live inside the plugin folder (portable
+# mode) and must survive a Git-based update. ``git clean -fd`` would
+# otherwise delete them because they are untracked and, in released tags,
+# not listed in ``.gitignore``. ``-e`` excludes a path from cleaning
+# regardless of whether it is ignored.
+_PRESERVE_DIRS = ('settings.json', 'civitai', 'wildcards', 'backups', 'stats', 'logs', 'cache', 'model_cache')
+
+
+def _clean_excludes() -> List[str]:
+    """Build the ``-e`` arguments for ``git clean`` from :data:`_PRESERVE_DIRS`."""
+    excludes: List[str] = []
+    for name in _PRESERVE_DIRS:
+        excludes.append('-e')
+        excludes.append(name)
+        # For directories, also exclude nested matches explicitly
+        # (``-e dir`` alone matches the dir entry; ``-e dir/**`` guards
+        # contents under all git versions as defense-in-depth).
+        excludes.append('-e')
+        excludes.append(f'{name}/**')
+    return excludes
+
 
 class UpdateRoutes:
     """Routes for handling plugin update checks"""
@@ -212,8 +233,19 @@ class UpdateRoutes:
 
             zip_path = tmp_zip_path
 
-            # Skip both settings.json, civitai and model cache folder
-            UpdateRoutes._clean_plugin_folder(plugin_root, skip_files=['settings.json', 'civitai', 'model_cache'])
+            # Close the downloaded-versions SQLite connection before cleaning,
+            # so that shutil.rmtree() does not fail on Windows (the process
+            # cannot delete a file with an outstanding open handle).
+            try:
+                history_svc = ServiceRegistry._services.get("downloaded_version_history_service")
+                if history_svc is not None:
+                    history_svc.close()
+                    logger.info("Closed downloaded-version history database connection")
+            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'])
 
             # Extract ZIP to temp dir
             with tempfile.TemporaryDirectory() as tmp_dir:
@@ -222,16 +254,17 @@ class UpdateRoutes:
                     # Find extracted folder (GitHub ZIP contains a root folder)
                     extracted_root = next(os.scandir(tmp_dir)).path
 
-                    # Copy files, skipping settings.json and civitai folder
+                    # Copy files, skipping user data that should be preserved
+                    skip_items = {'settings.json', 'civitai', 'wildcards', 'backups', 'stats'}
                     for item in os.listdir(extracted_root):
-                        if item == 'settings.json' or item == 'civitai':
+                        if item in skip_items:
                             continue
                         src = os.path.join(extracted_root, item)
                         dst = os.path.join(plugin_root, item)
                         if os.path.isdir(src):
                             if os.path.exists(dst):
                                 shutil.rmtree(dst)
-                            shutil.copytree(src, dst, ignore=shutil.ignore_patterns('settings.json', 'civitai'))
+                            shutil.copytree(src, dst, ignore=shutil.ignore_patterns(*skip_items))
                         else:
                             shutil.copy2(src, dst)
 
@@ -239,15 +272,17 @@ 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'}
                     for root, dirs, files in os.walk(extracted_root):
-                        # Skip civitai folder and its contents
+                        # Skip user data directories and their contents
                         rel_root = os.path.relpath(root, extracted_root)
-                        if rel_root == 'civitai' or rel_root.startswith('civitai' + os.sep):
+                        top_dir = rel_root.split(os.sep)[0] if rel_root != '.' else ''
+                        if top_dir in skip_tracked:
                             continue
                         for file in files:
                             rel_path = os.path.relpath(os.path.join(root, file), extracted_root)
-                            # Skip settings.json and any file under civitai
-                            if rel_path == 'settings.json' or rel_path.startswith('civitai' + os.sep):
+                            # Skip settings.json and any file under user data dirs
+                            if rel_path == 'settings.json' or rel_path.split(os.sep)[0] in skip_tracked:
                                 continue
                             tracking_files.append(rel_path.replace("\\", "/"))
                     with open(tracking_info_file, "w", encoding='utf-8') as file:
@@ -342,6 +377,17 @@ class UpdateRoutes:
         Returns:
             tuple: (success, new_version)
         """
+        try:
+            import git
+        except ImportError:
+            logger.error(
+                "GitPython is not available: the git executable was not found in PATH. "
+                "Install git or set $GIT_PYTHON_GIT_EXECUTABLE to the git binary path."
+            )
+            return False, ""
+
+        clean_excludes = _clean_excludes()
+
         try:
             # Open the Git repository
             repo = git.Repo(plugin_root)
@@ -353,8 +399,9 @@ class UpdateRoutes:
             if nightly:
                 # Reset to discard any local changes
                 repo.git.reset('--hard')
-                # Clean untracked files
-                repo.git.clean('-fd')
+                # Clean untracked files, but preserve user-managed directories
+                # (wildcards, backups, stats, civitai, caches, settings.json).
+                repo.git.clean('-fd', *clean_excludes)
                 
                 # Switch to main branch and pull latest
                 main_branch = 'main'
@@ -371,8 +418,9 @@ class UpdateRoutes:
             else:
                 # Reset to discard any local changes
                 repo.git.reset('--hard')
-                # Clean untracked files
-                repo.git.clean('-fd')
+                # Clean untracked files, but preserve user-managed directories
+                # (wildcards, backups, stats, civitai, caches, settings.json).
+                repo.git.clean('-fd', *clean_excludes)
                 
                 # Get latest release tag
                 tags = sorted(repo.tags, key=lambda t: t.commit.committed_datetime, reverse=True)
@@ -438,6 +486,7 @@ class UpdateRoutes:
             if not os.path.exists(os.path.join(plugin_root, '.git')):
                 return git_info
 
+            import git
             repo = git.Repo(plugin_root)
             commit = repo.head.commit
             git_info['commit_hash'] = commit.hexsha

py/services/agent/__init__.py

@@ -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",
+]

py/services/agent/agent_service.py

@@ -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:
+        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)

py/services/agent/post_processor.py

@@ -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 = 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 ""

py/services/agent/skill_definition.py

@@ -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

py/services/agent/skill_registry.py

@@ -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]:
+    """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

py/services/agent/skills/enrich_hf_metadata/prompt.md

@@ -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

py/services/aria2_downloader.py

@@ -0,0 +1,679 @@
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import os
+import secrets
+import shutil
+import socket
+from dataclasses import dataclass
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, Optional, Tuple
+
+import aiohttp
+
+from .downloader import DownloadProgress, get_downloader, is_ssl_cert_verify_error
+from .aria2_transfer_state import Aria2TransferStateStore
+from .settings_manager import get_settings_manager
+
+logger = logging.getLogger(__name__)
+
+def _try_certifi_ca_path() -> str | None:
+    """Return the certifi CA bundle path if available, else None."""
+    try:
+        import certifi  # type: ignore[import-untyped]
+
+        path = certifi.where()
+        if os.path.isfile(path):
+            logger.debug(
+                "aria2 --ca-certificate: using certifi CA bundle at %s", path
+            )
+            return path
+    except ImportError:
+        pass
+
+    logger.debug("aria2 --ca-certificate: certifi not available")
+    return None
+
+
+CIVITAI_DOWNLOAD_URL_PREFIXES = (
+    "https://civitai.com/api/download/",
+    "https://civitai.red/api/download/",
+)
+
+
+class Aria2Error(RuntimeError):
+    """Raised when aria2 integration fails."""
+
+
+@dataclass
+class Aria2Transfer:
+    """Track an aria2 download registered by the Python coordinator."""
+
+    gid: str
+    save_path: str
+
+
+class Aria2Downloader:
+    """Manage an aria2 RPC daemon for recommended model downloads."""
+
+    _instance = None
+    _lock = asyncio.Lock()
+
+    @classmethod
+    async def get_instance(cls) -> "Aria2Downloader":
+        async with cls._lock:
+            if cls._instance is None:
+                cls._instance = cls()
+            return cls._instance
+
+    def __init__(self) -> None:
+        if hasattr(self, "_initialized"):
+            return
+
+        self._initialized = True
+        self._process: Optional[asyncio.subprocess.Process] = None
+        self._rpc_port: Optional[int] = None
+        self._rpc_secret = ""
+        self._rpc_url = ""
+        self._rpc_session: Optional[aiohttp.ClientSession] = None
+        self._rpc_session_lock = asyncio.Lock()
+        self._process_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
+
+    @property
+    def is_running(self) -> bool:
+        return self._process is not None and self._process.returncode is None
+
+    async def download_file(
+        self,
+        url: str,
+        save_path: str,
+        *,
+        download_id: str,
+        progress_callback=None,
+        headers: Optional[Dict[str, str]] = None,
+    ) -> Tuple[bool, str]:
+        """Download a file using aria2 RPC and wait for completion."""
+
+        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
+
+        try:
+            while True:
+                status = await self._get_status_with_retry(download_id)
+                if status is None:
+                    return False, "aria2 download not found"
+
+                snapshot = self._build_progress_snapshot(status)
+                if progress_callback is not None:
+                    await self._dispatch_progress(progress_callback, snapshot)
+
+                state = status.get("status", "")
+                if state == "complete":
+                    completed_path = self._resolve_completed_path(status, save_path)
+                    return True, completed_path
+                if state == "error":
+                    return False, status.get("errorMessage") or "aria2 download failed"
+                if state == "removed":
+                    return False, "Download was cancelled"
+
+                await asyncio.sleep(self._poll_interval)
+        finally:
+            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
+    ) -> Optional[Dict[str, Any]]:
+        """Call get_status with retry for transient RPC failures.
+
+        Only retries on :exc:`Aria2Error` (RPC-level failure).  Returns
+        ``None`` immediately when the download_id is not tracked (a missing
+        transfer is not a transient condition, so retrying is pointless).
+
+        A single failed RPC call should not immediately fail the download,
+        because aria2 may be temporarily busy (e.g. finalizing multiple
+        concurrent downloads) and a retry will often succeed.
+        """
+        last_exc: Optional[Exception] = None
+        for attempt in range(max_retries):
+            try:
+                return await self.get_status(download_id)
+            except Aria2Error as exc:
+                last_exc = exc
+                if attempt < max_retries - 1:
+                    logger.warning(
+                        "aria2 get_status transient failure (attempt %d/%d) for %s: %s",
+                        attempt + 1, max_retries, download_id, exc,
+                    )
+                    await asyncio.sleep(retry_delay)
+        raise Aria2Error(
+            f"Failed to query aria2 download status after {max_retries} attempts: {last_exc}"
+        ) from last_exc
+
+    async def _schedule_download(
+        self,
+        url: str,
+        save_path: str,
+        *,
+        download_id: str,
+        headers: Optional[Dict[str, str]] = None,
+    ) -> str:
+        save_dir = os.path.dirname(save_path)
+        out_name = os.path.basename(save_path)
+
+        Path(save_dir).mkdir(parents=True, exist_ok=True)
+
+        resolved_url = url
+        request_headers = headers
+        if headers and url.startswith(CIVITAI_DOWNLOAD_URL_PREFIXES):
+            resolved_url = await self._resolve_authenticated_redirect_url(url, headers)
+            if resolved_url != url:
+                request_headers = None
+                logger.debug(
+                    "Resolved Civitai download %s to signed URL for aria2",
+                    download_id,
+                )
+
+        options: Dict[str, str] = {
+            "dir": save_dir,
+            "out": out_name,
+            "continue": "true",
+            "max-connection-per-server": "4",
+            "split": "4",
+            "min-split-size": "1M",
+            "allow-overwrite": "true",
+            "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()
+            ]
+
+        logger.debug(
+            "Submitting aria2 download %s -> %s (auth=%s, civitai_signed=%s)",
+            download_id,
+            save_path,
+            bool(request_headers),
+            resolved_url != url,
+        )
+
+        try:
+            gid = await self._rpc_call("aria2.addUri", [[resolved_url], options])
+        except Exception as exc:
+            raise Aria2Error(f"Failed to schedule aria2 download: {exc}") from exc
+
+        logger.debug("aria2 accepted download %s with gid %s", download_id, gid)
+        await self._state_store.upsert(
+            download_id,
+            {
+                "gid": gid,
+                "save_path": save_path,
+                "status": "downloading",
+                "url": url,
+            },
+        )
+        return gid
+
+    async def get_status(self, download_id: str) -> Optional[Dict[str, Any]]:
+        """Return the raw aria2 status payload for a known download."""
+
+        transfer = self._transfers.get(download_id)
+        if transfer is None:
+            return None
+
+        keys = [
+            "gid",
+            "status",
+            "totalLength",
+            "completedLength",
+            "downloadSpeed",
+            "errorMessage",
+            "files",
+        ]
+        try:
+            status = await self._rpc_call("aria2.tellStatus", [transfer.gid, keys])
+        except Exception as exc:
+            raise Aria2Error(f"Failed to query aria2 download status: {exc}") from exc
+
+        if isinstance(status, dict):
+            return status
+        return None
+
+    async def get_status_by_gid(self, gid: str) -> Optional[Dict[str, Any]]:
+        keys = [
+            "gid",
+            "status",
+            "totalLength",
+            "completedLength",
+            "downloadSpeed",
+            "errorMessage",
+            "files",
+        ]
+        try:
+            status = await self._rpc_call("aria2.tellStatus", [gid, keys])
+        except Exception as exc:
+            message = str(exc)
+            if "cannot be found" in message.lower() or "not found" in message.lower():
+                return None
+            raise Aria2Error(f"Failed to query aria2 download status: {exc}") from exc
+
+        if isinstance(status, dict):
+            return status
+        return None
+
+    async def restore_transfer(self, download_id: str, gid: str, save_path: str) -> None:
+        await self._ensure_process()
+        self._transfers[download_id] = Aria2Transfer(
+            gid=gid,
+            save_path=os.path.abspath(save_path),
+        )
+
+    async def reassign_transfer(
+        self, from_download_id: str, to_download_id: str
+    ) -> Optional[Aria2Transfer]:
+        transfer = self._transfers.get(from_download_id)
+        if transfer is None:
+            return None
+
+        self._transfers[to_download_id] = transfer
+        if from_download_id != to_download_id:
+            self._transfers.pop(from_download_id, None)
+        return transfer
+
+    async def has_transfer(self, download_id: str) -> bool:
+        return download_id in self._transfers
+
+    async def pause_download(self, download_id: str) -> Dict[str, Any]:
+        transfer = self._transfers.get(download_id)
+        if transfer is None:
+            return {"success": False, "error": "Download task not found"}
+
+        try:
+            await self._rpc_call("aria2.forcePause", [transfer.gid])
+        except Exception as exc:
+            return {"success": False, "error": str(exc)}
+
+        await self._state_store.upsert(download_id, {"status": "paused"})
+        return {"success": True, "message": "Download paused successfully"}
+
+    async def resume_download(self, download_id: str) -> Dict[str, Any]:
+        transfer = self._transfers.get(download_id)
+        if transfer is None:
+            return {"success": False, "error": "Download task not found"}
+
+        try:
+            await self._rpc_call("aria2.unpause", [transfer.gid])
+        except Exception as exc:
+            return {"success": False, "error": str(exc)}
+
+        await self._state_store.upsert(download_id, {"status": "downloading"})
+        return {"success": True, "message": "Download resumed successfully"}
+
+    async def cancel_download(self, download_id: str) -> Dict[str, Any]:
+        transfer = self._transfers.get(download_id)
+        if transfer is None:
+            return {"success": False, "error": "Download task not found"}
+
+        try:
+            await self._rpc_call("aria2.forceRemove", [transfer.gid])
+        except Exception as exc:
+            return {"success": False, "error": str(exc)}
+
+        await self._state_store.remove(download_id)
+        return {"success": True, "message": "Download cancelled successfully"}
+
+    async def close(self) -> None:
+        """Shut down the RPC process and session."""
+
+        # Cancel the background stderr reader first so it stops reading
+        # from the pipe before the subprocess is terminated.
+        if self._stderr_reader_task is not None:
+            self._stderr_reader_task.cancel()
+            try:
+                await asyncio.wait_for(self._stderr_reader_task, timeout=2.0)
+            except (asyncio.CancelledError, asyncio.TimeoutError):
+                pass
+            self._stderr_reader_task = None
+
+        if self._rpc_session is not None:
+            await self._rpc_session.close()
+            self._rpc_session = None
+
+        process = self._process
+        self._process = None
+        self._transfers.clear()
+
+        if process is None:
+            return
+
+        if process.returncode is None:
+            process.terminate()
+            try:
+                await asyncio.wait_for(process.wait(), timeout=5.0)
+            except asyncio.TimeoutError:
+                process.kill()
+                await process.wait()
+
+    async def _drain_stderr(self) -> None:
+        """Continuously drain aria2's stderr pipe so it never blocks.
+
+        When the 64 KB pipe buffer fills up, aria2's ``write()`` to stderr
+        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.
+        """
+        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)
+        except Exception:
+            pass
+
+    async def _dispatch_progress(self, callback, snapshot: DownloadProgress) -> None:
+        try:
+            result = callback(snapshot, snapshot)
+        except TypeError:
+            result = callback(snapshot.percent_complete)
+
+        if asyncio.iscoroutine(result):
+            await result
+        elif hasattr(result, "__await__"):
+            await result
+
+    def _build_progress_snapshot(self, status: Dict[str, Any]) -> DownloadProgress:
+        completed = self._parse_int(status.get("completedLength"))
+        total = self._parse_int(status.get("totalLength"))
+        speed = float(self._parse_int(status.get("downloadSpeed")))
+        percent = 0.0
+        if total > 0:
+            percent = (completed / total) * 100.0
+
+        return DownloadProgress(
+            percent_complete=max(0.0, min(percent, 100.0)),
+            bytes_downloaded=completed,
+            total_bytes=total or None,
+            bytes_per_second=speed,
+            timestamp=datetime.now().timestamp(),
+        )
+
+    def _resolve_completed_path(self, status: Dict[str, Any], default_path: str) -> str:
+        files = status.get("files")
+        if isinstance(files, list) and files:
+            first = files[0]
+            if isinstance(first, dict):
+                candidate = first.get("path")
+                if isinstance(candidate, str) and candidate:
+                    return candidate
+        return default_path
+
+    @staticmethod
+    def _parse_int(value: Any) -> int:
+        try:
+            return int(value)
+        except (TypeError, ValueError):
+            return 0
+
+    async def _resolve_authenticated_redirect_url(
+        self,
+        url: str,
+        headers: Dict[str, str],
+    ) -> str:
+        downloader = await get_downloader()
+        session = await downloader.session
+        request_headers = dict(downloader.default_headers)
+        request_headers.update(headers)
+        request_headers["Accept-Encoding"] = "identity"
+
+        try:
+            async with session.get(
+                url,
+                headers=request_headers,
+                allow_redirects=False,
+                proxy=downloader.proxy_url,
+            ) as response:
+                if response.status in {301, 302, 303, 307, 308}:
+                    location = response.headers.get("Location")
+                    if location:
+                        return location
+                    raise Aria2Error(
+                        "Authenticated Civitai redirect did not include a Location header"
+                    )
+
+                if response.status == 200:
+                    return url
+
+                body = await response.text()
+                raise Aria2Error(
+                    f"Failed to resolve authenticated Civitai redirect: status={response.status} body={body[:300]}"
+                )
+        except aiohttp.ClientError as exc:
+            if is_ssl_cert_verify_error(exc):
+                logger.error(
+                    "SSL certificate verification failed during Civitai redirect "
+                    "resolution for %s. This is usually caused by an outdated CA "
+                    "certificate bundle. Recommended fixes:\n"
+                    "  1. pip install --upgrade certifi\n"
+                    "  2. pip install pip-system-certs",
+                    url,
+                )
+            raise Aria2Error(
+                f"Failed to resolve authenticated Civitai redirect: {exc}"
+            ) from exc
+
+    async def _ensure_process(self) -> None:
+        async with self._process_lock:
+            if self.is_running and await self._ping():
+                return
+
+            await self.close()
+
+            executable = self._resolve_executable()
+            self._rpc_port = self._find_free_port()
+            self._rpc_secret = secrets.token_hex(16)
+            self._rpc_url = f"http://127.0.0.1:{self._rpc_port}/jsonrpc"
+
+            command = [
+                executable,
+                "--enable-rpc=true",
+                "--rpc-listen-all=false",
+                f"--rpc-listen-port={self._rpc_port}",
+                f"--rpc-secret={self._rpc_secret}",
+                "--check-certificate=true",
+                # Point aria2 at certifi's CA bundle when available so it uses
+                # the same certificate store as Python downloads.
+                *((
+                    f"--ca-certificate={ca_cert}",
+                ) if (ca_cert := _try_certifi_ca_path()) else ()),
+                "--allow-overwrite=true",
+                "--auto-file-renaming=false",
+                "--file-allocation=none",
+                "--max-concurrent-downloads=5",
+                "--continue=true",
+                "--daemon=false",
+                "--quiet=true",
+                f"--stop-with-process={os.getpid()}",
+            ]
+
+            logger.info("Starting aria2 RPC daemon from %s", executable)
+            self._process = await asyncio.create_subprocess_exec(
+                *command,
+                stdout=asyncio.subprocess.DEVNULL,
+                stderr=asyncio.subprocess.PIPE,
+            )
+
+            await self._wait_until_ready()
+
+            # Drain aria2's stderr in a background task so the pipe buffer
+            # never fills up.  If the pipe blocks, aria2 itself freezes and
+            # cannot respond to RPC — this was the root cause of the
+            # "Failed to query aria2 download status" timeout bug.
+            # Must start AFTER _wait_until_ready to avoid a race where the
+            # drain task consumes aria2's early-exit error message before
+            # _wait_until_ready can read it.
+            self._stderr_reader_task = asyncio.create_task(
+                self._drain_stderr()
+            )
+
+    def _resolve_executable(self) -> str:
+        settings = get_settings_manager()
+        configured_path = (settings.get("aria2c_path") or "").strip()
+        candidate = configured_path or "aria2c"
+
+        resolved = shutil.which(candidate)
+        if resolved:
+            return resolved
+
+        if configured_path and os.path.isfile(configured_path) and os.access(
+            configured_path, os.X_OK
+        ):
+            return configured_path
+
+        raise Aria2Error(
+            "aria2c executable was not found. Install aria2 or configure aria2c_path."
+        )
+
+    async def _wait_until_ready(self) -> None:
+        assert self._process is not None
+
+        start_time = asyncio.get_running_loop().time()
+        last_error = ""
+        while asyncio.get_running_loop().time() - start_time < 10.0:
+            if self._process.returncode is not None:
+                stderr_output = ""
+                if self._process.stderr is not None:
+                    try:
+                        stderr_output = (
+                            await asyncio.wait_for(self._process.stderr.read(), timeout=0.2)
+                        ).decode("utf-8", errors="replace")
+                    except Exception:
+                        stderr_output = ""
+                raise Aria2Error(
+                    f"aria2 RPC process exited early with code {self._process.returncode}: {stderr_output.strip()}"
+                )
+
+            try:
+                if await self._ping():
+                    return
+            except Exception as exc:  # pragma: no cover - startup race
+                last_error = str(exc)
+
+            await asyncio.sleep(0.2)
+
+        raise Aria2Error(
+            f"Timed out waiting for aria2 RPC to become ready{': ' + last_error if last_error else ''}"
+        )
+
+    async def _ping(self) -> bool:
+        try:
+            result = await self._rpc_call("aria2.getVersion", [])
+        except Exception:
+            return False
+
+        return isinstance(result, dict)
+
+    async def _rpc_call(self, method: str, params: list[Any]) -> Any:
+        if not self._rpc_url:
+            raise Aria2Error("aria2 RPC endpoint is not initialized")
+
+        session = await self._get_rpc_session()
+        payload = {
+            "jsonrpc": "2.0",
+            "id": secrets.token_hex(8),
+            "method": method,
+            "params": [f"token:{self._rpc_secret}", *params],
+        }
+
+        async with session.post(self._rpc_url, json=payload) as response:
+            text = await response.text()
+
+        try:
+            body = json.loads(text)
+        except json.JSONDecodeError:
+            body = None
+
+        if body is None:
+            if response.status != 200:
+                raise Aria2Error(
+                    f"aria2 RPC returned status {response.status} with non-JSON body: {text}"
+                )
+            raise Aria2Error(f"Invalid aria2 RPC response: {text}")
+
+        if "error" in body:
+            error = body["error"] or {}
+            code = error.get("code") if isinstance(error, dict) else None
+            message = error.get("message") if isinstance(error, dict) else str(error)
+            logger.error(
+                "aria2 RPC %s failed with HTTP %s, code=%s, message=%s",
+                method,
+                response.status,
+                code,
+                message,
+            )
+            status_message = (
+                f"aria2 RPC {method} failed with status {response.status}: {message}"
+                if response.status != 200
+                else message
+            )
+            raise Aria2Error(status_message or "Unknown aria2 RPC error")
+
+        if response.status != 200:
+            logger.error(
+                "aria2 RPC %s returned unexpected HTTP status %s without error payload: %s",
+                method,
+                response.status,
+                body,
+            )
+            raise Aria2Error(
+                f"aria2 RPC {method} returned unexpected status {response.status}"
+            )
+
+        return body.get("result")
+
+    async def _get_rpc_session(self) -> aiohttp.ClientSession:
+        if self._rpc_session is None or self._rpc_session.closed:
+            async with self._rpc_session_lock:
+                if self._rpc_session is None or self._rpc_session.closed:
+                    timeout = aiohttp.ClientTimeout(
+                        total=None, sock_connect=10, sock_read=60
+                    )
+                    self._rpc_session = aiohttp.ClientSession(timeout=timeout)
+        return self._rpc_session
+
+    @staticmethod
+    def _find_free_port() -> int:
+        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
+            sock.bind(("127.0.0.1", 0))
+            sock.listen(1)
+            return int(sock.getsockname()[1])
+
+
+async def get_aria2_downloader() -> Aria2Downloader:
+    """Get the singleton aria2 downloader."""
+
+    return await Aria2Downloader.get_instance()

py/services/aria2_transfer_state.py

@@ -0,0 +1,108 @@
+from __future__ import annotations
+
+import asyncio
+import json
+import os
+from copy import deepcopy
+from typing import Any, Dict, Optional
+
+from ..utils.cache_paths import get_cache_base_dir
+
+
+def get_aria2_state_path() -> str:
+    base_dir = get_cache_base_dir(create=True)
+    state_dir = os.path.join(base_dir, "aria2")
+    os.makedirs(state_dir, exist_ok=True)
+    return os.path.join(state_dir, "downloads.json")
+
+
+class Aria2TransferStateStore:
+    """Persist aria2 transfer metadata needed for restart recovery."""
+
+    _locks_by_path: Dict[str, asyncio.Lock] = {}
+
+    def __init__(self, state_path: Optional[str] = None) -> None:
+        self._state_path = os.path.abspath(state_path or get_aria2_state_path())
+        self._lock = self._locks_by_path.setdefault(self._state_path, asyncio.Lock())
+
+    def _read_all_unlocked(self) -> Dict[str, Dict[str, Any]]:
+        try:
+            with open(self._state_path, "r", encoding="utf-8") as handle:
+                data = json.load(handle)
+        except FileNotFoundError:
+            return {}
+        except json.JSONDecodeError:
+            return {}
+
+        if not isinstance(data, dict):
+            return {}
+
+        normalized: Dict[str, Dict[str, Any]] = {}
+        for download_id, entry in data.items():
+            if isinstance(download_id, str) and isinstance(entry, dict):
+                normalized[download_id] = entry
+        return normalized
+
+    def _write_all_unlocked(self, data: Dict[str, Dict[str, Any]]) -> None:
+        directory = os.path.dirname(self._state_path)
+        if directory:
+            os.makedirs(directory, exist_ok=True)
+
+        temp_path = f"{self._state_path}.tmp"
+        with open(temp_path, "w", encoding="utf-8") as handle:
+            json.dump(data, handle, ensure_ascii=True, indent=2, sort_keys=True)
+        os.replace(temp_path, self._state_path)
+
+    async def load_all(self) -> Dict[str, Dict[str, Any]]:
+        async with self._lock:
+            return deepcopy(self._read_all_unlocked())
+
+    async def get(self, download_id: str) -> Optional[Dict[str, Any]]:
+        async with self._lock:
+            return deepcopy(self._read_all_unlocked().get(download_id))
+
+    async def upsert(self, download_id: str, payload: Dict[str, Any]) -> Dict[str, Any]:
+        async with self._lock:
+            data = self._read_all_unlocked()
+            current = data.get(download_id, {})
+            current.update(payload)
+            data[download_id] = current
+            self._write_all_unlocked(data)
+            return deepcopy(current)
+
+    async def remove(self, download_id: str) -> None:
+        async with self._lock:
+            data = self._read_all_unlocked()
+            if download_id in data:
+                del data[download_id]
+                self._write_all_unlocked(data)
+
+    async def find_by_save_path(
+        self, save_path: str, *, exclude_download_id: Optional[str] = None
+    ) -> Optional[Dict[str, Any]]:
+        normalized_target = os.path.abspath(save_path)
+        async with self._lock:
+            data = self._read_all_unlocked()
+            for download_id, entry in data.items():
+                if exclude_download_id and download_id == exclude_download_id:
+                    continue
+                candidate = entry.get("save_path")
+                if isinstance(candidate, str) and os.path.abspath(candidate) == normalized_target:
+                    result = dict(entry)
+                    result["download_id"] = download_id
+                    return result
+        return None
+
+    async def reassign(self, from_download_id: str, to_download_id: str) -> Optional[Dict[str, Any]]:
+        async with self._lock:
+            data = self._read_all_unlocked()
+            existing = data.get(from_download_id)
+            if existing is None:
+                return None
+            updated = dict(existing)
+            updated["download_id"] = to_download_id
+            data[to_download_id] = updated
+            if from_download_id != to_download_id:
+                data.pop(from_download_id, None)
+            self._write_all_unlocked(data)
+            return deepcopy(updated)

py/services/auto_tag_service.py

@@ -0,0 +1,139 @@
+"""
+Auto-tag extraction service for model cards.
+
+Extracts implicit model attributes (HIGH/LOW, I2V/T2V/TI2V, Lightning, Turbo)
+from filename, base_model, and CivitAI version name — no manual tagging required.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Dict, List, Set
+
+# ── Tag category definitions ──────────────────────────────────────────
+# Each category maps a display label to a regex pattern.
+# Patterns are case-insensitive and matched against filename, base_model,
+# and civitai version name.
+
+# Use (?<![a-zA-Z0-9]) and (?![a-zA-Z0-9]) instead of \b because
+# Python's \b treats underscore as a word character, so \bHIGH\b
+# won't match '_HIGH_' in filenames.
+_B = r"(?<![a-zA-Z0-9])"   # left boundary
+_E = r"(?![a-zA-Z0-9])"    # right boundary
+
+AUTO_TAG_CATEGORIES: Dict[str, str] = {
+    "HIGH":      _B + r"HIGH" + _E,
+    "LOW":       _B + r"(?<!F)LOW" + _E,
+    "I2V":       _B + r"I2V" + _E,
+    "T2V":       _B + r"T2V" + _E,
+    "TI2V":      _B + r"TI2V" + _E,
+    "Lightning": _B + r"Lightning" + _E,
+    "Turbo":     _B + r"Turbo" + _E,
+}
+
+# Tags that belong to the "mode" group (HIGH/LOW)
+MODE_TAGS = {"HIGH", "LOW"}
+
+# Tags that belong to the "video mode" group (I2V/T2V/TI2V)
+VIDEO_MODE_TAGS = {"I2V", "T2V", "TI2V"}
+
+# Tags that belong to the "speed/optimization" group
+SPEED_TAGS = {"Lightning", "Turbo"}
+
+# ── Display category groups (for settings UI) ─────────────────────────
+
+AUTO_TAG_GROUPS = {
+    "mode":   {"HIGH", "LOW"},
+    "video":  {"I2V", "T2V", "TI2V"},
+    "speed":  {"Lightning", "Turbo"},
+}
+
+# Default enabled categories
+DEFAULT_ENABLED_GROUPS = {"mode", "video"}
+
+
+def _collect_sources(model_data: Dict) -> List[str]:
+    """Collect all text sources from model data for tag matching."""
+    sources: List[str] = []
+
+    file_name = model_data.get("file_name", "")
+    if file_name:
+        sources.append(file_name)
+
+    base_model = model_data.get("base_model", "")
+    if base_model:
+        sources.append(base_model)
+
+    civitai = model_data.get("civitai", {})
+    if isinstance(civitai, dict):
+        version_name = civitai.get("name", "")
+        if version_name:
+            sources.append(version_name)
+
+    return sources
+
+
+def extract_auto_tags(model_data: Dict) -> List[str]:
+    """Extract auto-detected tags from model metadata.
+
+    Uses a two-layer approach:
+      Layer 1 — Regex-based detection against filename, base_model, and
+                CivitAI version name.
+      Layer 2 — Merge in any user-defined tags that overlap with known
+                auto-tag categories. This provides a manual fallback when
+                auto-detection fails (e.g. "I2V HN" or unlabeled models).
+
+    HIGH/LOW tags are only returned when the base_model indicates a Wan
+    family model — no other model architecture uses this distinction.
+
+    Args:
+        model_data: Model metadata dict with keys:
+            file_name, base_model, civitai (with optional 'name' field),
+            tags (user-defined tag list, used as fallback).
+
+    Returns:
+        Sorted list of unique auto-tag strings (e.g. ["I2V"]).
+    """
+    sources = _collect_sources(model_data)
+    base_model = model_data.get("base_model", "")
+    is_wan = "wan" in base_model.lower()
+
+    found: Set[str] = set()
+
+    # ── Layer 1: regex-based detection ────────────────────────────
+    if sources:
+        for label, pattern in AUTO_TAG_CATEGORIES.items():
+            # HIGH/LOW are Wan-specific — skip for non-Wan to avoid noise
+            if label in ("HIGH", "LOW"):
+                if not is_wan:
+                    continue
+                # Use case-insensitive character class + case-sensitive boundary,
+                # so "HighNoise" (camelCase) matches but "highlight" doesn't.
+                # Boundary: not followed by lowercase letter (= word has ended).
+                ci = "".join(f"[{c.lower()}{c.upper()}]" for c in label)
+                if label == "LOW":
+                    regex = re.compile(r"(?<![Ff])" + ci + r"(?![a-z])")
+                else:
+                    regex = re.compile(ci + r"(?![a-z])")
+            else:
+                regex = re.compile(pattern, re.IGNORECASE)
+            for source in sources:
+                if regex.search(source):
+                    found.add(label)
+                    break
+
+    # ── Layer 2: user-defined tags as manual fallback ─────────────
+    # When auto-detection fails (abbreviated names like "Hi"/"Lo",
+    # "I2V HN", or unlabeled models), users can add canonical tags
+    # (HIGH, LOW, I2V, etc.) to the model's regular tags for correct
+    # badge display and filtering. Matching is case-insensitive so
+    # "high"/"High"/"HIGH" all resolve to the canonical label.
+    user_tags = model_data.get("tags")
+    if user_tags:
+        label_map = {label.lower(): label for label in AUTO_TAG_CATEGORIES}
+        for t in user_tags:
+            canonical = label_map.get(t.lower())
+            if canonical:
+                found.add(canonical)
+
+    return sorted(found)

py/services/backup_service.py

@@ -141,6 +141,16 @@ class BackupService:
                     )
                 )
 
+        stats_path = os.path.join(get_settings_dir(create=True), "stats", "lora_manager_stats.json")
+        if os.path.exists(stats_path):
+            targets.append(
+                (
+                    "usage_stats",
+                    "stats/lora_manager_stats.json",
+                    stats_path,
+                )
+            )
+
         return targets
 
     @staticmethod
@@ -348,6 +358,8 @@ class BackupService:
         if kind == "model_update":
             filename = os.path.basename(archive_member)
             return str(Path(get_cache_file_path(CacheType.MODEL_UPDATE, create_dir=True)).parent / filename)
+        if kind == "usage_stats":
+            return os.path.join(get_settings_dir(create=True), "stats", "lora_manager_stats.json")
         return None
 
     async def create_auto_snapshot_if_due(self) -> Optional[dict[str, Any]]:

py/services/base_model_service.py

@@ -20,6 +20,7 @@ from .model_query import (
     resolve_sub_type,
 )
 from .settings_manager import get_settings_manager
+from ..utils.civitai_utils import build_civitai_model_page_url
 
 logger = logging.getLogger(__name__)
 
@@ -76,6 +77,7 @@ class BaseModelService(ABC):
         base_models: list = None,
         model_types: list = None,
         tags: Optional[Dict[str, str]] = None,
+        auto_tags: Optional[Dict[str, str]] = None,
         search_options: dict = None,
         hash_filters: dict = None,
         favorites_only: bool = False,
@@ -94,9 +96,108 @@ class BaseModelService(ABC):
             sorted_data = await self._fetch_with_usage_sort(sort_params)
         else:
             sorted_data = await self.cache_repository.fetch_sorted(sort_params)
+        # Pre-compute auto_tags for every item — needed for both filtering
+        # and display. Computation is cheap (string regex on 2-3 fields).
+        from .auto_tag_service import extract_auto_tags
+        for item in sorted_data:
+            item["auto_tags"] = extract_auto_tags(item)
         fetch_duration = time.perf_counter() - t0
         initial_count = len(sorted_data)
 
+        # Optionally filter by civitai model ID (shows all local versions of a specific model)
+        civitai_model_id = kwargs.get("civitai_model_id")
+        if civitai_model_id is not None:
+            sorted_data = [
+                item for item in sorted_data
+                if self._extract_model_id(item) == civitai_model_id
+            ]
+            # VLM mode: always sort by version ID descending (newest version first),
+            # regardless of the current sort_by preference.
+            sorted_data.sort(
+                key=lambda x: self._extract_version_id(x) or 0,
+                reverse=True,
+            )
+
+        # Optionally group by civitai modelId, showing only the latest version per model
+        dedup_lost = 0
+        if kwargs.get("group_by_model") and civitai_model_id is None:
+            # Determine whether to further sub-group by base model
+            # When version_grouping is "same_base", versions with different
+            # base models are effectively different groups — the dedup key
+            # needs to include base_model so the version count and VLM flow
+            # stay consistent (card shows correct count for its base model).
+            ufs = self.settings.get("version_grouping", "same_base")
+            group_by_base = ufs == "same_base"
+
+            dedup_map = {}  # (modelId [,base_model]) -> (item, version_id)
+            version_counter = {}  # same-key -> count
+            standalone = []
+            for item in sorted_data:
+                mid = self._extract_model_id(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
+                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
+            # to avoid mutating cached dicts — the cache is shared across requests)
+            for key, (item, vid) in dedup_map.items():
+                item = dict(item)
+                item["version_count"] = version_counter[key]
+                dedup_map[key] = (item, vid)
+            dedup_lost = len(sorted_data) - (len(dedup_map) + len(standalone))
+            sorted_data = [entry[0] for entry in dedup_map.values()] + standalone
+
+        # Re-sort by version_count (grouped: after dedup; non-grouped: group internally, sort, expand)
+        if sort_params.key == "versions_count" and civitai_model_id is None:
+            reverse = sort_params.order == "desc"
+            if kwargs.get("group_by_model"):
+                # Grouped mode: items are already dedup'd with version_count attached
+                sorted_data.sort(
+                    key=lambda x: (
+                        x.get("version_count", 0),
+                        (x.get("model_name") or x.get("file_name") or "").lower(),
+                        x.get("file_path", "").lower(),
+                    ),
+                    reverse=reverse,
+                )
+            else:
+                # Non-grouped mode: group internally, sort groups by count, expand
+                # Respect the version_grouping setting (same logic as grouped dedup)
+                ufs = self.settings.get("version_grouping", "same_base")
+                group_by_base = ufs == "same_base"
+
+                model_groups: Dict[Any, List[Dict]] = {}
+                ungrouped_standalone: List[Dict] = []
+                for item in sorted_data:
+                    mid = self._extract_model_id(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
+                for items in model_groups.values():
+                    items.sort(
+                        key=lambda x: self._extract_version_id(x) or 0,
+                        reverse=True,
+                    )
+                # Sort groups by version count
+                sorted_groups = sorted(
+                    model_groups.values(),
+                    key=lambda items: len(items),
+                    reverse=reverse,
+                )
+                # Flatten: grouped items first, standalone items last
+                sorted_data = []
+                for items in sorted_groups:
+                    sorted_data.extend(items)
+                sorted_data.extend(ungrouped_standalone)
+
         t1 = time.perf_counter()
         if hash_filters:
             filtered_data = await self._apply_hash_filters(sorted_data, hash_filters)
@@ -109,6 +210,7 @@ class BaseModelService(ABC):
                 base_models=base_models,
                 model_types=model_types,
                 tags=tags,
+                auto_tags=auto_tags,
                 favorites_only=favorites_only,
                 search_options=search_options,
                 tag_logic=tag_logic,
@@ -164,7 +266,7 @@ class BaseModelService(ABC):
         overall_duration = time.perf_counter() - overall_start
         logger.debug(
             "%s.get_paginated_data took %.3fs (fetch: %.3fs, filter: %.3fs, update_filter: %.3fs, pagination: %.3fs, annotate: %.3fs). "
-            "Counts: initial=%d, post_filter=%d, final=%d",
+            "Counts: initial=%d, dedup=%d, post_filter=%d, final=%d",
             self.__class__.__name__,
             overall_duration,
             fetch_duration,
@@ -173,11 +275,63 @@ class BaseModelService(ABC):
             pagination_duration,
             annotate_duration,
             initial_count,
+            dedup_lost,
             post_filter_count,
             final_count,
         )
         return paginated
 
+    async def get_excluded_paginated_data(
+        self,
+        page: int,
+        page_size: int,
+        sort_by: str = "name",
+        search: str = None,
+        fuzzy_search: bool = False,
+        search_options: dict = None,
+        **kwargs,
+    ) -> Dict:
+        """Get paginated excluded model data."""
+        excluded_paths = list(self.scanner.get_excluded_models())
+        excluded_entries: List[Dict[str, Any]] = []
+        stale_paths: List[str] = []
+
+        for file_path in excluded_paths:
+            if not file_path or not os.path.exists(file_path):
+                stale_paths.append(file_path)
+                continue
+
+            entry = await self._build_excluded_entry(file_path)
+            if entry:
+                excluded_entries.append(entry)
+            else:
+                stale_paths.append(file_path)
+
+        if stale_paths:
+            current_excluded = getattr(self.scanner, "_excluded_models", None)
+            if isinstance(current_excluded, list):
+                stale_set = set(stale_paths)
+                self.scanner._excluded_models = [
+                    path for path in current_excluded if path not in stale_set
+                ]
+                persist_current_cache = getattr(self.scanner, "_persist_current_cache", None)
+                if callable(persist_current_cache):
+                    await persist_current_cache()
+
+        excluded_entries = self._sort_entries(excluded_entries, sort_by)
+
+        if search:
+            excluded_entries = await self._apply_search_filters(
+                excluded_entries,
+                search,
+                fuzzy_search,
+                search_options,
+            )
+
+        paginated = self._paginate(excluded_entries, page, page_size)
+        paginated["items"] = await self._annotate_update_flags(paginated["items"])
+        return paginated
+
     async def _fetch_with_usage_sort(self, sort_params):
         """Fetch data sorted by usage count (desc/asc)."""
         cache = await self.cache_repository.get_cache()
@@ -217,6 +371,62 @@ class BaseModelService(ABC):
         )
         return annotated
 
+    def _sort_entries(self, data: List[Dict[str, Any]], sort_by: str) -> List[Dict[str, Any]]:
+        sort_params = self.cache_repository.parse_sort(sort_by)
+        key_name = sort_params.key
+
+        if key_name == "date":
+            key_fn = lambda item: (
+                float(item.get("modified", 0.0) or 0.0),
+                (item.get("model_name") or item.get("file_name") or "").lower(),
+                item.get("file_path", "").lower(),
+            )
+        elif key_name == "size":
+            key_fn = lambda item: (
+                int(item.get("size", 0) or 0),
+                (item.get("model_name") or item.get("file_name") or "").lower(),
+                item.get("file_path", "").lower(),
+            )
+        elif key_name == "usage":
+            key_fn = lambda item: (
+                int(item.get("usage_count", 0) or 0),
+                (item.get("model_name") or item.get("file_name") or "").lower(),
+                item.get("file_path", "").lower(),
+            )
+        else:
+            key_fn = lambda item: (
+                (item.get("model_name") or item.get("file_name") or "").lower(),
+                item.get("file_path", "").lower(),
+            )
+
+        return sorted(data, key=key_fn, reverse=sort_params.order == "desc")
+
+    async def _build_excluded_entry(self, file_path: str) -> Optional[Dict[str, Any]]:
+        root_path = self.scanner._find_root_for_file(file_path)
+        if not root_path:
+            return None
+
+        metadata, should_skip = await MetadataManager.load_metadata(
+            file_path,
+            self.metadata_class,
+        )
+        if should_skip:
+            return None
+
+        if metadata is None:
+            metadata = await self.scanner._create_default_metadata(file_path)
+            if metadata is None:
+                return None
+
+        metadata = self.scanner.adjust_metadata(metadata, file_path, root_path)
+        folder = os.path.dirname(os.path.relpath(file_path, root_path)).replace(
+            os.path.sep, "/"
+        )
+        entry = self.scanner._build_cache_entry(metadata, folder=folder)
+        entry = self.scanner.adjust_cached_entry(entry)
+        entry["exclude"] = True
+        return entry
+
     async def _apply_hash_filters(
         self, data: List[Dict], hash_filters: Dict
     ) -> List[Dict]:
@@ -246,6 +456,7 @@ class BaseModelService(ABC):
         base_models: list = None,
         model_types: list = None,
         tags: Optional[Dict[str, str]] = None,
+        auto_tags: Optional[Dict[str, str]] = None,
         favorites_only: bool = False,
         search_options: dict = None,
         tag_logic: str = "any",
@@ -259,6 +470,7 @@ class BaseModelService(ABC):
             base_models=base_models,
             model_types=model_types,
             tags=tags,
+            auto_tags=auto_tags,
             favorites_only=favorites_only,
             search_options=normalized_options,
             tag_logic=tag_logic,
@@ -378,7 +590,7 @@ class BaseModelService(ABC):
         if not ordered_ids:
             return annotated
 
-        strategy_value = self.settings.get("update_flag_strategy")
+        strategy_value = self.settings.get("version_grouping")
         if isinstance(strategy_value, str) and strategy_value.strip():
             strategy = strategy_value.strip().lower()
         else:
@@ -579,8 +791,12 @@ class BaseModelService(ABC):
         }
 
     @abstractmethod
-    async def format_response(self, model_data: Dict) -> Dict:
-        """Format model data for API response - must be implemented by subclasses"""
+    async def format_response(self, model_data: Dict) -> Optional[Dict]:
+        """Format model data for API response - must be implemented by subclasses.
+
+        Subclasses should return None for corrupted entries so the handler
+        layer can filter them out. See issue #730.
+        """
         pass
 
     # Common service methods that delegate to scanner
@@ -588,6 +804,12 @@ class BaseModelService(ABC):
         """Get top tags sorted by frequency"""
         return await self.scanner.get_top_tags(limit)
 
+    async def search_tags(
+        self, query: str, limit: int = 50
+    ) -> List[Dict]:
+        """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]:
         """Get base models sorted by frequency"""
         return await self.scanner.get_base_models(limit)
@@ -739,13 +961,21 @@ 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]:
+        """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
 
@@ -753,30 +983,86 @@ class BaseModelService(ABC):
         """Get the static preview URL for a model file"""
         cache = await self.scanner.get_cached_data()
 
+        name_normalized = model_name.replace("\\", "/")
+        name_no_ext = name_normalized
+        for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+            if name_no_ext.lower().endswith(ext):
+                name_no_ext = name_no_ext[: -len(ext)]
+                break
+
+        has_path = "/" in name_no_ext
+        basename = os.path.basename(name_no_ext) if has_path else name_no_ext
+        best_fallback = None
+
         for model in cache.raw_data:
-            if model["file_name"] == model_name:
+            file_name = model.get("file_name", "")
+            folder = model.get("folder", "")
+            file_name_no_ext = file_name
+            for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+                if file_name_no_ext.lower().endswith(ext):
+                    file_name_no_ext = file_name_no_ext[: -len(ext)]
+                    break
+            path_name = f"{folder}/{file_name_no_ext}".replace("\\", "/") if folder else file_name_no_ext
+
+            if name_no_ext == file_name_no_ext or name_no_ext == path_name:
                 preview_url = model.get("preview_url")
                 if preview_url:
                     from ..config import config
 
                     return config.get_preview_static_url(preview_url)
 
+            if has_path and file_name_no_ext == basename:
+                if folder and name_no_ext.startswith(folder.replace("\\", "/") + "/"):
+                    best_fallback = model
+                elif best_fallback is None:
+                    best_fallback = model
+
+        if best_fallback:
+            preview_url = best_fallback.get("preview_url")
+            if preview_url:
+                from ..config import config
+
+                return config.get_preview_static_url(preview_url)
+
         return "/loras_static/images/no-preview.png"
 
     async def get_model_civitai_url(self, model_name: str) -> Dict[str, Optional[str]]:
         """Get the Civitai URL for a model file"""
         cache = await self.scanner.get_cached_data()
 
+        name_normalized = model_name.replace("\\", "/")
+        name_no_ext = name_normalized
+        for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+            if name_no_ext.lower().endswith(ext):
+                name_no_ext = name_no_ext[: -len(ext)]
+                break
+
+        has_path = "/" in name_no_ext
+        basename = os.path.basename(name_no_ext) if has_path else name_no_ext
+        best_fallback = None
+
         for model in cache.raw_data:
-            if model["file_name"] == model_name:
+            file_name = model.get("file_name", "")
+            folder = model.get("folder", "")
+            file_name_no_ext = file_name
+            for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+                if file_name_no_ext.lower().endswith(ext):
+                    file_name_no_ext = file_name_no_ext[: -len(ext)]
+                    break
+            path_name = f"{folder}/{file_name_no_ext}".replace("\\", "/") if folder else file_name_no_ext
+
+            if name_no_ext == file_name_no_ext or name_no_ext == path_name:
                 civitai_data = model.get("civitai", {})
                 model_id = civitai_data.get("modelId")
                 version_id = civitai_data.get("id")
 
                 if model_id:
-                    civitai_url = f"https://civitai.com/models/{model_id}"
-                    if version_id:
-                        civitai_url += f"?modelVersionId={version_id}"
+                    civitai_host = self.settings.get("civitai_host", "civitai.com")
+                    civitai_url = build_civitai_model_page_url(
+                        model_id,
+                        version_id,
+                        host=civitai_host,
+                    )
 
                     return {
                         "civitai_url": civitai_url,
@@ -784,6 +1070,27 @@ class BaseModelService(ABC):
                         "version_id": str(version_id) if version_id else None,
                     }
 
+            if has_path and file_name_no_ext == basename:
+                if folder and name_no_ext.startswith(folder.replace("\\", "/") + "/"):
+                    best_fallback = model
+                elif best_fallback is None:
+                    best_fallback = model
+
+        if best_fallback:
+            civitai_data = best_fallback.get("civitai", {})
+            model_id = civitai_data.get("modelId")
+            if model_id:
+                version_id = civitai_data.get("id")
+                civitai_host = self.settings.get("civitai_host", "civitai.com")
+                civitai_url = build_civitai_model_page_url(
+                    model_id, version_id, host=civitai_host
+                )
+                return {
+                    "civitai_url": civitai_url,
+                    "model_id": str(model_id),
+                    "version_id": str(version_id) if version_id else None,
+                }
+
         return {"civitai_url": None, "model_id": None, "version_id": None}
 
     async def get_model_metadata(self, file_path: str) -> Optional[Dict]:
@@ -791,12 +1098,41 @@ class BaseModelService(ABC):
 
         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
         )
         if should_skip or metadata is None:
             return None
+
+        # Prune stale example-image metadata entries whose files no longer
+        # exist on disk (e.g. a user deleted the files manually).
+        from ..utils.example_images_metadata import MetadataUpdater
+
+        was_modified = await MetadataUpdater.prune_stale_example_images(metadata)
+        if was_modified:
+            asyncio.create_task(
+                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]:

py/services/batch_import_service.py

@@ -224,7 +224,7 @@ class BatchImportService:
                 return False
 
             for recipe in getattr(cache, "raw_data", []):
-                source_path = recipe.get("source_path") or recipe.get("source_url")
+                source_path = recipe.get("source_path")
                 if source_path and source_path == source:
                     return True
             return False
@@ -523,6 +523,10 @@ class BatchImportService:
                 if payload.get("checkpoint"):
                     metadata["checkpoint"] = payload["checkpoint"]
 
+                nsfw = payload.get("preview_nsfw_level")
+                if isinstance(nsfw, int) and nsfw > 0:
+                    metadata["preview_nsfw_level"] = nsfw
+
                 image_bytes = None
                 image_base64 = payload.get("image_base64")
 

py/services/checkpoint_scanner.py

@@ -1,3 +1,4 @@
+import asyncio
 import json
 import logging
 import os
@@ -36,6 +37,9 @@ class CheckpointScanner(ModelScanner):
             file_extensions=file_extensions,
             hash_index=ModelHashIndex(),
         )
+        if not hasattr(self, "_hash_calculation_lock"):
+            self._hash_calculation_lock = asyncio.Lock()
+            self._hash_calculation_tasks: dict[str, asyncio.Task[Optional[str]]] = {}
 
     async def _create_default_metadata(
         self, file_path: str
@@ -88,7 +92,7 @@ class CheckpointScanner(ModelScanner):
             return None
 
     async def calculate_hash_for_model(self, file_path: str) -> Optional[str]:
-        """Calculate hash for a checkpoint on-demand.
+        """Calculate hash for a checkpoint on-demand with per-file singleflight.
 
         Args:
             file_path: Path to the model file
@@ -96,14 +100,73 @@ class CheckpointScanner(ModelScanner):
         Returns:
             SHA256 hash string, or None if calculation failed
         """
-        from ..utils.file_utils import calculate_sha256
-
         try:
             real_path = os.path.realpath(file_path)
             if not os.path.exists(real_path):
                 logger.error(f"File not found for hash calculation: {file_path}")
                 return None
 
+            metadata, _ = await MetadataManager.load_metadata(
+                file_path, self.model_class
+            )
+            if (
+                metadata is not None
+                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)
+                return metadata.sha256
+
+            async with self._hash_calculation_lock:
+                metadata, _ = await MetadataManager.load_metadata(
+                    file_path, self.model_class
+                )
+                if (
+                    metadata is not None
+                    and metadata.hash_status == "completed"
+                    and metadata.sha256
+                ):
+                    self._hash_index.add_entry(metadata.sha256.lower(), file_path)
+                    return metadata.sha256
+
+                task = self._hash_calculation_tasks.get(real_path)
+                if task is None:
+                    task = asyncio.create_task(
+                        self._run_hash_calculation_task(file_path, real_path)
+                    )
+                    self._hash_calculation_tasks[real_path] = task
+
+            return await asyncio.shield(task)
+
+        except Exception as e:
+            logger.error(f"Error calculating hash for {file_path}: {e}")
+            return None
+
+    async def _run_hash_calculation_task(
+        self, file_path: str, real_path: str
+    ) -> Optional[str]:
+        """Run a hash calculation task and remove it from the in-flight map."""
+        try:
+            return await self._calculate_hash_for_model_uncached(file_path, real_path)
+        finally:
+            task = asyncio.current_task()
+            async with self._hash_calculation_lock:
+                if self._hash_calculation_tasks.get(real_path) is task:
+                    del self._hash_calculation_tasks[real_path]
+
+    async def _calculate_hash_for_model_uncached(
+        self, file_path: str, real_path: str
+    ) -> Optional[str]:
+        """Calculate hash for a checkpoint without checking in-flight tasks."""
+        from ..utils.file_utils import calculate_sha256
+
+        try:
             # Load current metadata
             metadata, should_skip = await MetadataManager.load_metadata(
                 file_path, self.model_class
@@ -120,6 +183,9 @@ 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)
                 return metadata.sha256
 
             # Update status to calculating
@@ -138,6 +204,20 @@ class CheckpointScanner(ModelScanner):
             # Update hash index
             self._hash_index.add_entry(sha256.lower(), file_path)
 
+            # 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"
+                        break
+
             logger.info(f"Hash calculated for checkpoint: {file_path}")
             return sha256
 

py/services/checkpoint_service.py

@@ -1,8 +1,9 @@
 import os
 import logging
-from typing import Dict
+from typing import Dict, Optional
 
 from .base_model_service import BaseModelService
+from .auto_tag_service import extract_auto_tags
 from ..utils.models import CheckpointMetadata
 from ..config import config
 
@@ -20,20 +21,37 @@ class CheckpointService(BaseModelService):
         """
         super().__init__("checkpoint", scanner, CheckpointMetadata, update_service=update_service)
     
-    async def format_response(self, checkpoint_data: Dict) -> Dict:
-        """Format Checkpoint data for API response"""
+    async def format_response(self, checkpoint_data: Dict) -> Optional[Dict]:
+        """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")
+        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>"),
+            )
+            return None
+
         # Get sub_type from cache entry (new canonical field)
         sub_type = checkpoint_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 ""
+
         return {
-            "model_name": checkpoint_data["model_name"],
-            "file_name": checkpoint_data["file_name"],
+            "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", ""),
-            "folder": checkpoint_data["folder"],
+            "folder": folder,
             "sha256": checkpoint_data.get("sha256", ""),
-            "file_path": checkpoint_data["file_path"].replace(os.sep, "/"),
+            "file_path": file_path.replace(os.sep, "/"),
             "file_size": checkpoint_data.get("size", 0),
             "modified": checkpoint_data.get("modified", ""),
             "tags": checkpoint_data.get("tags", []),
@@ -42,9 +60,13 @@ class CheckpointService(BaseModelService):
             "notes": checkpoint_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)
+            "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", ""),
         }
     
     def find_duplicate_hashes(self) -> Dict:

py/services/civarchive_client.py

@@ -186,6 +186,22 @@ class CivArchiveClient:
         if "metadata" in file_data:
             transformed["metadata"] = file_data["metadata"]
 
+        # Infer metadata.format from filename extension
+        name = transformed.get("name")
+        if name and isinstance(name, str):
+            lower_name = name.lower()
+            if lower_name.endswith(".safetensors"):
+                inferred_format = "SafeTensor"
+            elif lower_name.endswith(".ckpt"):
+                inferred_format = "PickleTensor"
+            else:
+                inferred_format = None
+            if inferred_format:
+                if "metadata" not in transformed:
+                    transformed["metadata"] = {}
+                if isinstance(transformed["metadata"], dict):
+                    transformed["metadata"].setdefault("format", inferred_format)
+
         if file_data.get("modelVersionId") is not None:
             transformed["modelVersionId"] = file_data.get("modelVersionId")
         elif file_data.get("model_version_id") is not None:
@@ -213,6 +229,20 @@ class CivArchiveClient:
         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:
+            fname = f.get("name") or ""
+            if isinstance(fname, str):
+                lower = fname.lower()
+                if lower.endswith(".safetensors"):
+                    return 0
+                elif lower.endswith(".ckpt"):
+                    return 1
+            return 2
+
+        transformed_files.sort(key=_sort_key)
         return transformed_files
 
     def _transform_version(
@@ -274,6 +304,20 @@ 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
@@ -297,7 +341,7 @@ class CivArchiveClient:
             if resolved:
                 return resolved, None
 
-            logger.error("Error fetching version of CivArchive model by hash %s", model_hash[:10])
+            logger.debug("Error fetching version of CivArchive model by hash %s", model_hash[:10])
             return None, "No version data found"
 
         except RateLimitError:
@@ -387,7 +431,7 @@ class CivArchiveClient:
 
             if version_id is not None:
                 raw_id = version_data.get("id")
-                if raw_id != version_id:
+                if raw_id is not None and str(raw_id) != str(version_id):
                     logger.warning(
                         "Requested version %s doesn't match default version %s for model %s",
                         version_id,

py/services/civitai_base_model_service.py

@@ -30,7 +30,7 @@ class CivitaiBaseModelService:
     DEFAULT_CACHE_TTL = 7 * 24 * 60 * 60
 
     # Civitai API endpoint for enums
-    CIVITAI_ENUMS_URL = "https://civitai.com/api/v1/enums"
+    CIVITAI_ENUMS_URL = "https://civitai.red/api/v1/enums"
 
     @classmethod
     async def get_instance(cls) -> CivitaiBaseModelService:
@@ -193,6 +193,10 @@ class CivitaiBaseModelService:
             "zimageturbo": "ZIT",
             "zimagebase": "ZIB",
             "anima": "ANI",
+            "ernie": "ERNI",
+            "ernie turbo": "ETRB",
+            "nucleus": "NUCL",
+            "krea 2": "KR2",
             "svd": "SVD",
             "ltxv": "LTXV",
             "ltxv2": "LTV2",
@@ -209,6 +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:
@@ -388,6 +404,7 @@ class CivitaiBaseModelService:
                 "LTXV2",
                 "LTXV 2.3",
                 "CogVideoX",
+                "HappyHorse",
                 "Mochi",
                 "Hunyuan Video",
                 "Wan Video",
@@ -400,15 +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",
@@ -418,6 +445,11 @@ class CivitaiBaseModelService:
                 "Kolors",
                 "NoobAI",
                 "Anima",
+                "Ernie",
+                "Ernie Turbo",
+                "Nucleus",
+                "Krea 2",
+                "Upscaler",
             ],
         }
 

py/services/civitai_client.py

@@ -2,7 +2,13 @@ import asyncio
 import copy
 import logging
 import os
+from collections import OrderedDict
 from typing import Any, Optional, Dict, Tuple, List, Sequence
+from .connectivity_guard import (
+    OFFLINE_FRIENDLY_MESSAGE,
+    is_expected_offline_error,
+    is_offline_cooldown_error,
+)
 from .model_metadata_provider import (
     CivitaiModelMetadataProvider,
     ModelMetadataProviderManager,
@@ -39,7 +45,18 @@ class CivitaiClient:
             return
         self._initialized = True
 
-        self.base_url = "https://civitai.com/api/v1"
+        self.base_url = "https://civitai.red/api/v1"
+        # In-memory cache to avoid redundant get_model_version_info calls
+        # within the same import/scan flow. Only successful results are cached.
+        # 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]]
+        ] = OrderedDict()
+        self._MAX_CACHE_ENTRIES = 500
+
+    def _build_image_info_url(self, image_id: str) -> str:
+        return f"{self.base_url}/images?imageId={image_id}&nsfw=X&withMeta=true"
 
     async def _make_request(
         self,
@@ -49,20 +66,57 @@ class CivitaiClient:
         use_auth: bool = False,
         **kwargs,
     ) -> Tuple[bool, Dict | str]:
-        """Wrapper around downloader.make_request that surfaces rate limits."""
+        """Wrapper around downloader.make_request that surfaces rate limits,
+        with retry for transient server errors (5xx, Cloudflare 524, network flakiness)."""
 
-        downloader = await get_downloader()
-        success, result = await downloader.make_request(
-            method,
-            url,
-            use_auth=use_auth,
-            **kwargs,
-        )
-        if not success and isinstance(result, RateLimitError):
-            if result.provider is None:
-                result.provider = "civitai_api"
-            raise result
-        return success, result
+        max_retries = 3
+        for attempt in range(max_retries):
+            downloader = await get_downloader()
+            success, result = await downloader.make_request(
+                method,
+                url,
+                use_auth=use_auth,
+                **kwargs,
+            )
+            if success:
+                return True, result
+
+            if isinstance(result, RateLimitError):
+                if result.provider is None:
+                    result.provider = "civitai_api"
+                raise result
+
+            if is_offline_cooldown_error(result):
+                return False, OFFLINE_FRIENDLY_MESSAGE
+
+            # Transient server error — retry with exponential backoff
+            if self._is_transient_server_error(str(result)):
+                if attempt < max_retries - 1:
+                    wait = 2**attempt  # 1s, 2s, 4s
+                    logger.info(
+                        "Transient error on %s %s, retrying in %ds "
+                        "(attempt %d/%d): %s",
+                        method,
+                        url,
+                        wait,
+                        attempt + 1,
+                        max_retries,
+                        result,
+                    )
+                    await asyncio.sleep(wait)
+                    continue
+                logger.warning(
+                    "All %d retries exhausted for %s %s: %s",
+                    max_retries,
+                    method,
+                    url,
+                    result,
+                )
+                return False, result
+
+            return False, result
+
+        return False, "Unexpected error in _make_request"
 
     @staticmethod
     def _remove_comfy_metadata(model_version: Optional[Dict]) -> None:
@@ -121,6 +175,8 @@ class CivitaiClient:
             )
             if not success:
                 message = str(version)
+                if is_expected_offline_error(message):
+                    return None, OFFLINE_FRIENDLY_MESSAGE
                 if "not found" in message.lower():
                     return None, "Model not found"
 
@@ -161,6 +217,9 @@ class CivitaiClient:
                 return True
             return False
         except Exception as e:
+            if is_expected_offline_error(str(e)):
+                logger.debug("Preview download skipped due to offline state.")
+                return False
             logger.error(f"Download Error: {str(e)}")
             return False
 
@@ -186,11 +245,36 @@ class CivitaiClient:
 
         return _from_value(payload)
 
+    @staticmethod
+    def _is_transient_server_error(message: str) -> bool:
+        """Return True when the message indicates a transient upstream failure.
+
+        Recognises Cloudflare 524, generic 5xx, and connectivity-level flakiness
+        that should not be treated as a permanent failure.
+        """
+        normalized = message.lower()
+        if "status 5" in normalized or "status 524" in normalized:
+            return True
+        if any(
+            keyword in normalized
+            for keyword in (
+                "connection refused",
+                "connection reset",
+                "temporary failure",
+                "name resolution",
+                "connection closed",
+            )
+        ):
+            return True
+        return False
+
     async def get_model_versions(self, model_id: str) -> Optional[Dict]:
         """Get all versions of a model with local availability info"""
         try:
             success, result = await self._make_request(
-                "GET", f"{self.base_url}/models/{model_id}", use_auth=True
+                "GET",
+                f"{self.base_url}/models/{model_id}",
+                use_auth=True,
             )
             if success:
                 # Also return model type along with versions
@@ -202,7 +286,17 @@ class CivitaiClient:
             message = self._extract_error_message(result)
             if message and "not found" in message.lower():
                 raise ResourceNotFoundError(f"Resource not found for model {model_id}")
+            if is_expected_offline_error(message):
+                logger.info("Civitai request skipped: %s", OFFLINE_FRIENDLY_MESSAGE)
+                return None
             if message:
+                if self._is_transient_server_error(message):
+                    logger.info(
+                        "Transient server error for model %s: %s",
+                        model_id,
+                        message,
+                    )
+                    return None
                 raise RuntimeError(message)
             return None
         except RateLimitError:
@@ -237,7 +331,7 @@ class CivitaiClient:
                 "GET",
                 f"{self.base_url}/models",
                 use_auth=True,
-                params={"ids": query},
+                params={"ids": query, "nsfw": "true"},
             )
             if not success:
                 return None
@@ -316,6 +410,25 @@ class CivitaiClient:
             return None
 
         target_version = self._select_target_version(model_data, model_id, version_id)
+
+        # If modelVersions is empty (e.g. CivitAI cache lag for newly published
+        # models) but a specific version_id is known, fall back to fetching the
+        # version directly via the individual model-versions endpoint, then
+        # enrich it with the model-level data we already have.
+        if target_version is None and version_id is not None:
+            logger.info(
+                "modelVersions empty for model %s; falling back to direct "
+                "version lookup for %s",
+                model_id,
+                version_id,
+            )
+            version = await self._fetch_version_by_id(version_id)
+            if version:
+                self._enrich_version_with_model_data(version, model_data)
+                self._remove_comfy_metadata(version)
+                return version
+            return None
+
         if target_version is None:
             return None
 
@@ -346,10 +459,14 @@ class CivitaiClient:
 
     async def _fetch_model_data(self, model_id: int) -> Optional[Dict]:
         success, data = await self._make_request(
-            "GET", f"{self.base_url}/models/{model_id}", use_auth=True
+            "GET",
+            f"{self.base_url}/models/{model_id}",
+            use_auth=True,
         )
         if success:
             return data
+        if is_expected_offline_error(data):
+            return None
         logger.warning(f"Failed to fetch model data for model {model_id}")
         return None
 
@@ -358,10 +475,14 @@ class CivitaiClient:
             return None
 
         success, version = await self._make_request(
-            "GET", f"{self.base_url}/model-versions/{version_id}", use_auth=True
+            "GET",
+            f"{self.base_url}/model-versions/{version_id}",
+            use_auth=True,
         )
         if success:
             return version
+        if is_expected_offline_error(version):
+            return None
 
         logger.warning(f"Failed to fetch version by id {version_id}")
         return None
@@ -371,10 +492,14 @@ class CivitaiClient:
             return None
 
         success, version = await self._make_request(
-            "GET", f"{self.base_url}/model-versions/by-hash/{model_hash}", use_auth=True
+            "GET",
+            f"{self.base_url}/model-versions/by-hash/{model_hash}",
+            use_auth=True,
         )
         if success:
             return version
+        if is_expected_offline_error(version):
+            return None
 
         logger.warning(f"Failed to fetch version by hash {model_hash}")
         return None
@@ -450,20 +575,33 @@ class CivitaiClient:
                 - The model version data or None if not found
                 - An error message if there was an error, or None on success
         """
+        # In-memory cache avoids redundant API calls within the same
+        # import/scan flow (e.g. _resolve_base_model_from_checkpoint
+        # followed by _resolve_and_populate_checkpoint with the same id).
+        if version_id in self._version_info_cache:
+            logger.debug("Cache hit for model version info: %s", version_id)
+            self._version_info_cache.move_to_end(version_id)  # LRU bump
+            return self._version_info_cache[version_id]
+
         try:
             url = f"{self.base_url}/model-versions/{version_id}"
 
-            logger.debug(f"Resolving DNS for model version info: {url}")
+            logger.debug("Resolving Civitai model version info: %s", url)
             success, result = await self._make_request("GET", url, use_auth=True)
 
             if success:
-                logger.debug(
-                    f"Successfully fetched model version info for: {version_id}"
-                )
+                logger.debug("Successfully fetched model version info for: %s", version_id)
                 self._remove_comfy_metadata(result)
+                self._version_info_cache[version_id] = (result, None)
+                self._version_info_cache.move_to_end(version_id)
+                # Evict oldest entry when over capacity
+                if len(self._version_info_cache) > self._MAX_CACHE_ENTRIES:
+                    self._version_info_cache.popitem(last=False)
                 return result, None
 
             # Handle specific error cases
+            if is_expected_offline_error(result):
+                return None, OFFLINE_FRIENDLY_MESSAGE
             if "not found" in str(result):
                 error_msg = f"Model not found"
                 logger.warning(f"Model version not found: {version_id} - {error_msg}")
@@ -479,48 +617,67 @@ class CivitaiClient:
             logger.error(error_msg)
             return None, error_msg
 
-    async def get_image_info(self, image_id: str) -> Optional[Dict]:
+    async def get_image_info(
+        self, image_id: str, source_url: str | None = None
+    ) -> Optional[Dict]:
         """Fetch image information from Civitai API
 
         Args:
             image_id: The Civitai image ID
+            source_url: Original image page URL. Accepted for caller compatibility;
+                API requests always target ``civitai.red``.
 
         Returns:
             Optional[Dict]: The image data or None if not found
         """
         try:
-            url = f"{self.base_url}/images?imageId={image_id}&nsfw=X"
             requested_id = int(image_id)
-
-            logger.debug(f"Fetching image info for ID: {image_id}")
+            url = self._build_image_info_url(image_id)
             success, result = await self._make_request("GET", url, use_auth=True)
 
-            if success:
-                if result and "items" in result and isinstance(result["items"], list):
-                    items = result["items"]
-
-                    # First, try to find the item with matching ID
-                    for item in items:
-                        if isinstance(item, dict) and item.get("id") == requested_id:
-                            logger.debug(f"Successfully fetched image info for ID: {image_id}")
-                            return item
-
-                    # No matching ID found - log warning with details about returned items
-                    returned_ids = [
-                        item.get("id") for item in items
-                        if isinstance(item, dict) and "id" in item
-                    ]
-                    logger.warning(
-                        f"CivitAI API returned no matching image for requested ID {image_id}. "
-                        f"Returned {len(items)} item(s) with IDs: {returned_ids}. "
-                        f"This may indicate the image was deleted, hidden, or there is a database lag."
+            if not success:
+                if is_expected_offline_error(result):
+                    return None
+                if self._is_transient_server_error(str(result)):
+                    logger.info(
+                        "Transient server error fetching image info for ID %s: %s",
+                        image_id,
+                        result,
                     )
                     return None
-
-                logger.warning(f"No image found with ID: {image_id}")
+                logger.error(
+                    "Failed to fetch image info for ID %s from civitai.red: %s",
+                    image_id,
+                    result,
+                )
                 return None
 
-            logger.error(f"Failed to fetch image info for ID: {image_id}: {result}")
+            if result and "items" in result and isinstance(result["items"], list):
+                items = result["items"]
+
+                for item in items:
+                    if isinstance(item, dict) and item.get("id") == requested_id:
+                        logger.debug(
+                            "Successfully fetched image info for ID %s from civitai.red",
+                            image_id,
+                        )
+                        return item
+
+                returned_ids = [
+                    item.get("id")
+                    for item in items
+                    if isinstance(item, dict) and "id" in item
+                ]
+
+                logger.warning(
+                    "CivitAI API returned no matching image for requested ID %s from civitai.red. Returned %d item(s) with IDs: %s. This may indicate the image was deleted, hidden, or there is a database lag.",
+                    image_id,
+                    len(items),
+                    returned_ids,
+                )
+                return None
+
+            logger.warning("No image found with ID: %s", image_id)
             return None
         except RateLimitError:
             raise
@@ -533,16 +690,76 @@ class CivitaiClient:
             logger.error(error_msg)
             return None
 
+    async def get_model_versions_by_hashes(
+        self, hashes: List[str]
+    ) -> Optional[List[Dict]]:
+        """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
+        details including ``usageControl`` and ``earlyAccessEndsAt`` that are
+        not available from the model-level API.
+
+        Args:
+            hashes: List of SHA256 hashes (max 100 per batch; auto-split).
+
+        Returns:
+            List of version dicts or None on failure.
+        """
+        if not hashes:
+            return []
+
+        BATCH_SIZE = 100
+        all_versions: List[Dict] = []
+
+        for start in range(0, len(hashes), BATCH_SIZE):
+            batch = hashes[start : start + BATCH_SIZE]
+            try:
+                success, result = await self._make_request(
+                    "POST",
+                    f"{self.base_url}/model-versions/by-hash",
+                    use_auth=True,
+                    json=batch,
+                )
+                if not success:
+                    logger.warning(
+                        "Batch by-hash request failed for %d hashes: %s",
+                        len(batch),
+                        result,
+                    )
+                    continue
+
+                if isinstance(result, list):
+                    all_versions.extend(result)
+                else:
+                    logger.debug(
+                        "Unexpected by-hash response type: %s", type(result)
+                    )
+            except RateLimitError:
+                raise
+            except Exception as exc:  # pragma: no cover - defensive logging
+                logger.error(
+                    "Error fetching model versions by hashes: %s", exc
+                )
+
+        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."""
         if not username:
             return None
 
         try:
-            url = f"{self.base_url}/models?username={username}"
-            success, result = await self._make_request("GET", url, use_auth=True)
+            success, result = await self._make_request(
+                "GET",
+                f"{self.base_url}/models",
+                use_auth=True,
+                params={"username": username, "nsfw": "true"},
+            )
 
             if not success:
+                if is_expected_offline_error(result):
+                    logger.info("User model fetch skipped: %s", OFFLINE_FRIENDLY_MESSAGE)
+                    return None
                 logger.error("Failed to fetch models for %s: %s", username, result)
                 return None
 

py/services/connectivity_guard.py

@@ -0,0 +1,204 @@
+"""In-memory connectivity guard to suppress repeated network retries when offline."""
+
+from __future__ import annotations
+
+import asyncio
+import errno
+import logging
+import socket
+from dataclasses import dataclass
+from datetime import datetime, timedelta
+from typing import Any
+
+import aiohttp
+
+logger = logging.getLogger(__name__)
+
+OFFLINE_COOLDOWN_ERROR = "offline_cooldown"
+OFFLINE_FRIENDLY_MESSAGE = "Network offline, will retry automatically later"
+
+
+def is_offline_cooldown_error(value: Any) -> bool:
+    """Return True when a response payload represents guard short-circuit."""
+    return isinstance(value, str) and value == OFFLINE_COOLDOWN_ERROR
+
+
+def is_expected_offline_error(value: Any) -> bool:
+    """Return True when payload is an expected offline-related result."""
+    if is_offline_cooldown_error(value):
+        return True
+    if not isinstance(value, str):
+        return False
+    normalized = value.lower()
+    return "network offline" in normalized or "offline" in normalized
+
+
+class ConnectivityGuard:
+    """Tracks network failures and gates outbound requests during cooldown."""
+
+    _instance: "ConnectivityGuard | None" = None
+    _instance_lock = asyncio.Lock()
+
+    @classmethod
+    async def get_instance(cls) -> "ConnectivityGuard":
+        async with cls._instance_lock:
+            if cls._instance is None:
+                cls._instance = cls()
+            return cls._instance
+
+    def __init__(self) -> None:
+        if hasattr(self, "_initialized"):
+            return
+        self._initialized = True
+        self._default_destination = "__global__"
+        self._destination_states: dict[str, _DestinationState] = {
+            self._default_destination: _DestinationState()
+        }
+        self.base_backoff_seconds = 30
+        self.max_backoff_seconds = 300
+        self.failure_threshold = 3
+
+    @property
+    def online(self) -> bool:
+        return self._state_for_destination(None).online
+
+    @online.setter
+    def online(self, value: bool) -> None:
+        self._state_for_destination(None).online = value
+
+    @property
+    def failure_count(self) -> int:
+        return self._state_for_destination(None).failure_count
+
+    @failure_count.setter
+    def failure_count(self, value: int) -> None:
+        self._state_for_destination(None).failure_count = value
+
+    @property
+    def cooldown_until(self) -> datetime | None:
+        return self._state_for_destination(None).cooldown_until
+
+    @cooldown_until.setter
+    def cooldown_until(self, value: datetime | None) -> None:
+        self._state_for_destination(None).cooldown_until = value
+
+    def _now(self) -> datetime:
+        return datetime.now()
+
+    def _normalize_destination(self, destination: str | None) -> str:
+        if destination is None or not destination.strip():
+            return self._default_destination
+        return destination.lower().strip()
+
+    def _state_for_destination(self, destination: str | None) -> "_DestinationState":
+        destination_key = self._normalize_destination(destination)
+        if destination_key not in self._destination_states:
+            self._destination_states[destination_key] = _DestinationState()
+        return self._destination_states[destination_key]
+
+    def in_cooldown(self, destination: str | None = None) -> bool:
+        state = self._state_for_destination(destination)
+        if state.cooldown_until is None:
+            return False
+        return self._now() < state.cooldown_until
+
+    def cooldown_remaining_seconds(self, destination: str | None = None) -> float:
+        state = self._state_for_destination(destination)
+        if state.cooldown_until is None:
+            return 0.0
+        return max(0.0, (state.cooldown_until - self._now()).total_seconds())
+
+    def should_block_request(self, destination: str | None = None) -> bool:
+        return self.in_cooldown(destination)
+
+    def register_success(self, destination: str | None = None) -> None:
+        destination_key = self._normalize_destination(destination)
+        state = self._state_for_destination(destination_key)
+        was_offline = (not state.online) or state.cooldown_until is not None
+        state.online = True
+        state.failure_count = 0
+        state.cooldown_until = None
+        if was_offline:
+            logger.info(
+                "Connectivity restored for destination '%s'; requests resumed.",
+                destination_key,
+            )
+
+    def register_network_failure(
+        self, exc: Exception, destination: str | None = None
+    ) -> None:
+        destination_key = self._normalize_destination(destination)
+        state = self._state_for_destination(destination_key)
+        state.online = False
+        state.failure_count += 1
+
+        if state.failure_count < self.failure_threshold:
+            logger.debug(
+                "Network failure tracked for destination '%s' (%d/%d): %s",
+                destination_key,
+                state.failure_count,
+                self.failure_threshold,
+                exc,
+            )
+            return
+
+        retry_step = state.failure_count - self.failure_threshold
+        backoff = min(
+            self.max_backoff_seconds,
+            self.base_backoff_seconds * (2**retry_step),
+        )
+        should_log_warning = not self.in_cooldown(destination_key)
+        state.cooldown_until = self._now() + timedelta(seconds=backoff)
+
+        if should_log_warning:
+            logger.warning(
+                "Connectivity offline for destination '%s'; enter cooldown for %ss after %d network failures.",
+                destination_key,
+                int(backoff),
+                state.failure_count,
+            )
+        else:
+            logger.debug(
+                "Cooldown still active for destination '%s'; failure_count=%d, backoff=%ss.",
+                destination_key,
+                state.failure_count,
+                int(backoff),
+            )
+
+    @staticmethod
+    def is_network_unreachable_error(exc: Exception) -> bool:
+        """Return whether the exception should count as connectivity failure."""
+        if isinstance(exc, asyncio.CancelledError):
+            return False
+
+        if isinstance(
+            exc,
+            (
+                asyncio.TimeoutError,
+                TimeoutError,
+                ConnectionRefusedError,
+                socket.gaierror,
+                aiohttp.ServerTimeoutError,
+                aiohttp.ConnectionTimeoutError,
+                aiohttp.ClientConnectorError,
+                aiohttp.ClientConnectionError,
+            ),
+        ):
+            return True
+
+        if isinstance(exc, OSError) and exc.errno in {
+            errno.ENETUNREACH,
+            errno.EHOSTUNREACH,
+            errno.ETIMEDOUT,
+            errno.ECONNREFUSED,
+        }:
+            return True
+
+        return False
+
+
+@dataclass
+class _DestinationState:
+    online: bool = True
+    failure_count: int = 0
+    cooldown_until: datetime | None = None

py/services/download_coordinator.py

@@ -110,6 +110,23 @@ class DownloadCoordinator:
 
         return result
 
+    async def skip_download(self, download_id: str) -> Dict[str, Any]:
+        """Skip a download while preserving all partial files on disk."""
+        download_manager = await self._download_manager_factory()
+        result = await download_manager.skip_download(download_id)
+
+        await self._ws_manager.broadcast_download_progress(
+            download_id,
+            {
+                "status": "skipped",
+                "progress": 0,
+                "download_id": download_id,
+                "message": "Download skipped by user (partial files preserved)",
+            },
+        )
+
+        return result
+
     async def pause_download(self, download_id: str) -> Dict[str, Any]:
         """Pause an active download and notify listeners."""
 

py/services/download_queue_service.py

@@ -0,0 +1,906 @@
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import os
+import sqlite3
+import time
+from typing import Any, Optional
+
+from ..utils.cache_paths import get_cache_base_dir
+
+logger = logging.getLogger(__name__)
+
+
+def _resolve_database_path() -> str:
+    base_dir = get_cache_base_dir(create=True)
+    history_dir = os.path.join(base_dir, "download_history")
+    os.makedirs(history_dir, exist_ok=True)
+    return os.path.join(history_dir, "download_queue.sqlite")
+
+
+class DownloadQueueService:
+    """Persistent download queue and history manager backed by SQLite.
+
+    Provides a singleton interface for managing a download queue and
+    corresponding history table, both stored in a single SQLite database
+    under the cache directory.
+    """
+
+    _instance: Optional[DownloadQueueService] = None
+    _class_lock: asyncio.Lock = asyncio.Lock()
+
+    _SCHEMA = """
+        CREATE TABLE IF NOT EXISTS download_queue (
+            download_id TEXT PRIMARY KEY,
+            model_id INTEGER,
+            model_version_id INTEGER,
+            model_name TEXT NOT NULL DEFAULT '',
+            version_name TEXT DEFAULT '',
+            thumbnail_url TEXT DEFAULT '',
+            source TEXT,
+            file_params TEXT,
+            status TEXT NOT NULL DEFAULT 'queued',
+            priority INTEGER DEFAULT 0,
+            progress INTEGER DEFAULT 0,
+            bytes_downloaded INTEGER DEFAULT 0,
+            total_bytes INTEGER,
+            bytes_per_second REAL DEFAULT 0.0,
+            error TEXT,
+            file_path TEXT,
+            added_at REAL NOT NULL,
+            started_at REAL,
+            completed_at REAL
+        );
+        CREATE INDEX IF NOT EXISTS idx_dq_status ON download_queue(status);
+        CREATE INDEX IF NOT EXISTS idx_dq_added ON download_queue(added_at);
+
+        CREATE TABLE IF NOT EXISTS download_history (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            download_id TEXT,
+            model_id INTEGER,
+            model_version_id INTEGER,
+            model_name TEXT NOT NULL DEFAULT '',
+            version_name TEXT DEFAULT '',
+            thumbnail_url TEXT DEFAULT '',
+            status TEXT NOT NULL,
+            error TEXT,
+            file_path TEXT,
+            bytes_downloaded INTEGER DEFAULT 0,
+            total_bytes INTEGER,
+            completed_at REAL NOT NULL,
+            is_already_exists INTEGER DEFAULT 0
+        );
+        CREATE INDEX IF NOT EXISTS idx_dh_completed ON download_history(completed_at DESC);
+        CREATE INDEX IF NOT EXISTS idx_dh_status ON download_history(status);
+        CREATE UNIQUE INDEX IF NOT EXISTS idx_dh_download_id
+            ON download_history(download_id) WHERE download_id IS NOT NULL;
+    """
+
+    @classmethod
+    async def get_instance(cls) -> DownloadQueueService:
+        """Return the singleton instance, creating it if necessary."""
+        async with cls._class_lock:
+            if cls._instance is None:
+                cls._instance = cls()
+                await cls._instance.deduplicate()
+            return cls._instance
+
+    def __init__(self, db_path: Optional[str] = None) -> None:
+        self._db_path = db_path or _resolve_database_path()
+        self._lock = asyncio.Lock()
+        self._conn: Optional[sqlite3.Connection] = None
+        self._schema_initialized = False
+        self._ensure_directory()
+        self._initialize_schema()
+
+    def _ensure_directory(self) -> None:
+        directory = os.path.dirname(self._db_path)
+        if directory:
+            os.makedirs(directory, exist_ok=True)
+
+    def _connect(self) -> sqlite3.Connection:
+        conn = sqlite3.connect(self._db_path, check_same_thread=False)
+        conn.row_factory = sqlite3.Row
+        return conn
+
+    def _get_conn(self) -> sqlite3.Connection:
+        if self._conn is None:
+            self._conn = sqlite3.connect(self._db_path, check_same_thread=False)
+            self._conn.row_factory = sqlite3.Row
+        return self._conn
+
+    def _initialize_schema(self) -> None:
+        if self._schema_initialized:
+            return
+        with self._connect() as conn:
+            conn.executescript(self._SCHEMA)
+            conn.commit()
+        self._schema_initialized = True
+
+    def get_database_path(self) -> str:
+        """Return the resolved database file path."""
+        return self._db_path
+
+    def close(self) -> None:
+        """Close the persistent SQLite connection, if open.
+
+        This is called before plugin update operations to release the
+        database file lock on Windows, allowing ``shutil.rmtree()`` to
+        succeed when the cache resides inside the plugin directory.
+        """
+        if self._conn is not None:
+            try:
+                self._conn.close()
+            except Exception:
+                pass
+            finally:
+                self._conn = None
+
+    # ------------------------------------------------------------------
+    # Queue methods
+    # ------------------------------------------------------------------
+
+    async def add_to_queue(
+        self,
+        download_id: str,
+        model_id: Optional[int] = None,
+        model_version_id: Optional[int] = None,
+        model_name: str = "",
+        version_name: str = "",
+        thumbnail_url: str = "",
+        source: Optional[str] = None,
+        file_params: Optional[dict[str, Any]] = None,
+    ) -> dict[str, Any]:
+        """Insert a new download into the queue.
+
+        Returns the inserted row as a dict (or an empty dict if the
+        download_id already exists in the queue or has a terminal
+        record in history).
+        """
+        now = time.time()
+        file_params_json = json.dumps(file_params) if file_params is not None else None
+
+        async with self._lock:
+            conn = self._get_conn()
+
+            # Reject download_ids that already have a terminal record in history.
+            history_row = conn.execute(
+                "SELECT 1 FROM download_history WHERE download_id = ? LIMIT 1",
+                (download_id,),
+            ).fetchone()
+            if history_row is not None:
+                return {}
+
+            conn.execute(
+                """
+                INSERT OR IGNORE INTO download_queue (
+                    download_id, model_id, model_version_id, model_name,
+                    version_name, thumbnail_url, source, file_params,
+                    status, priority, added_at
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 'queued', 0, ?)
+                """,
+                (
+                    download_id,
+                    model_id,
+                    model_version_id,
+                    model_name,
+                    version_name,
+                    thumbnail_url,
+                    source,
+                    file_params_json,
+                    now,
+                ),
+            )
+            conn.commit()
+            row = conn.execute(
+                "SELECT * FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            ).fetchone()
+
+        return dict(row) if row else {}
+
+    async def get_queue(self) -> list[dict[str, Any]]:
+        """Return all items in the queue ordered by priority then added time."""
+        async with self._lock:
+            conn = self._get_conn()
+            rows = conn.execute(
+                "SELECT * FROM download_queue ORDER BY priority DESC, added_at ASC"
+            ).fetchall()
+        return [dict(row) for row in rows]
+
+    async def get_queued_count(self) -> int:
+        """Return the number of items with status ``'queued'``."""
+        async with self._lock:
+            conn = self._get_conn()
+            row = conn.execute(
+                "SELECT COUNT(*) AS cnt FROM download_queue WHERE status = 'queued'"
+            ).fetchone()
+        return row["cnt"] if row else 0
+
+    async def update_status(
+        self,
+        download_id: str,
+        status: str,
+        **extra: Any,
+    ) -> bool:
+        """Update the status and/or extra fields of a queue item.
+
+        Accepted extra keyword arguments:
+        ``progress``, ``error``, ``file_path``, ``bytes_downloaded``,
+        ``total_bytes``, ``bytes_per_second``.
+
+        Returns ``True`` if a row was updated.
+        """
+        allowed_extra = {
+            "progress",
+            "error",
+            "file_path",
+            "bytes_downloaded",
+            "total_bytes",
+            "bytes_per_second",
+        }
+
+        set_clauses: list[str] = ["status = ?"]
+        params: list[Any] = [status]
+        now = time.time()
+
+        if status in ("downloading",):
+            set_clauses.append("started_at = COALESCE(started_at, ?)")
+            params.append(now)
+        if status in ("completed", "failed", "canceled"):
+            set_clauses.append("completed_at = ?")
+            params.append(now)
+
+        for key, value in extra.items():
+            if key in allowed_extra:
+                set_clauses.append(f"{key} = ?")
+                params.append(value)
+
+        params.append(download_id)
+
+        async with self._lock:
+            conn = self._get_conn()
+            cursor = conn.execute(
+                f"UPDATE download_queue SET {', '.join(set_clauses)} "
+                "WHERE download_id = ?",
+                params,
+            )
+            conn.commit()
+        return cursor.rowcount > 0
+
+    async def remove_from_queue(self, download_id: str) -> bool:
+        """Remove a single item from the queue by download_id.
+
+        Returns ``True`` if a row was deleted.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            cursor = conn.execute(
+                "DELETE FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            )
+            conn.commit()
+        return cursor.rowcount > 0
+
+    async def move_to_top(self, download_id: str) -> bool:
+        """Move an item to the front of the queue (highest priority).
+
+        Returns ``True`` if the item was found and updated.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            row = conn.execute(
+                "SELECT priority FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            ).fetchone()
+            if row is None:
+                return False
+
+            max_row = conn.execute(
+                "SELECT MAX(priority) AS mx FROM download_queue"
+            ).fetchone()
+            max_priority: int = max_row["mx"] if max_row["mx"] is not None else 0
+
+            conn.execute(
+                "UPDATE download_queue SET priority = ? WHERE download_id = ?",
+                (max_priority + 1, download_id),
+            )
+            conn.commit()
+        return True
+
+    async def move_to_end(self, download_id: str) -> bool:
+        """Move an item to the end of the queue (lowest priority).
+
+        Returns ``True`` if the item was found and updated.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            row = conn.execute(
+                "SELECT priority FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            ).fetchone()
+            if row is None:
+                return False
+
+            min_row = conn.execute(
+                "SELECT MIN(priority) AS mn FROM download_queue"
+            ).fetchone()
+            min_priority: int = min_row["mn"] if min_row["mn"] is not None else 0
+
+            conn.execute(
+                "UPDATE download_queue SET priority = ? WHERE download_id = ?",
+                (min_priority - 1, download_id),
+            )
+            conn.commit()
+        return True
+
+    async def clear_queue(self, status_filter: Optional[str] = None) -> int:
+        """Remove items from the queue.
+
+        When *status_filter* is provided only items with that status are
+        deleted.  Returns the number of deleted rows.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            if status_filter is not None:
+                cursor = conn.execute(
+                    "DELETE FROM download_queue WHERE status = ?",
+                    (status_filter,),
+                )
+            else:
+                cursor = conn.execute("DELETE FROM download_queue")
+            conn.commit()
+        return cursor.rowcount
+
+    async def complete_download(
+        self,
+        download_id: str,
+        status: str = "completed",
+        error: Optional[str] = None,
+        file_path: Optional[str] = None,
+        bytes_downloaded: int = 0,
+        total_bytes: Optional[int] = None,
+        completed_at: Optional[float] = None,
+    ) -> Optional[dict[str, Any]]:
+        """Atomically move a download from the queue into the history table.
+
+        Looks up the queue record by ``download_id``, deletes it from the
+        queue, and inserts a corresponding history entry with the given
+        terminal status (``completed``, ``failed``, or ``canceled``).
+
+        When *completed_at* is provided it is used as the completion
+        timestamp; otherwise ``time.time()`` is used.
+
+        Returns the original queue record (before deletion) on success,
+        or ``None`` if the download was not found in the queue.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            row = conn.execute(
+                "SELECT * FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            ).fetchone()
+            if row is None:
+                return None
+
+            now = completed_at if completed_at is not None else time.time()
+            conn.execute(
+                "DELETE FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            )
+            conn.execute(
+                """
+                INSERT OR IGNORE INTO download_history (
+                    download_id, model_id, model_version_id, model_name,
+                    version_name, thumbnail_url, status, error, file_path,
+                    bytes_downloaded, total_bytes, completed_at
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                """,
+                (
+                    row["download_id"],
+                    row["model_id"],
+                    row["model_version_id"],
+                    row["model_name"],
+                    row["version_name"],
+                    row["thumbnail_url"],
+                    status,
+                    error,
+                    file_path,
+                    bytes_downloaded,
+                    total_bytes,
+                    now,
+                ),
+            )
+            conn.commit()
+        return dict(row)
+
+    async def pop_next_download(self) -> Optional[dict[str, Any]]:
+        """Atomically fetch and mark the next queued item as ``downloading``.
+
+        The item with the highest priority (and earliest ``added_at``
+        among ties) whose status is ``'queued'`` is selected, set to
+        ``'downloading'``, and returned as a dict.  Returns ``None`` if
+        the queue is empty.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            row = conn.execute(
+                """
+                SELECT * FROM download_queue
+                WHERE status = 'queued'
+                ORDER BY priority DESC, added_at ASC
+                LIMIT 1
+                """
+            ).fetchone()
+            if row is None:
+                return None
+
+            download_id = row["download_id"]
+            now = time.time()
+            conn.execute(
+                "UPDATE download_queue SET status = 'downloading', "
+                "started_at = COALESCE(started_at, ?) "
+                "WHERE download_id = ?",
+                (now, download_id),
+            )
+            conn.commit()
+            updated = conn.execute(
+                "SELECT * FROM download_queue WHERE download_id = ?",
+                (download_id,),
+            ).fetchone()
+
+        return dict(updated) if updated else None
+
+    # ------------------------------------------------------------------
+    # History methods
+    # ------------------------------------------------------------------
+
+    async def add_to_history(
+        self,
+        download_id: Optional[str] = None,
+        model_id: Optional[int] = None,
+        model_version_id: Optional[int] = None,
+        model_name: str = "",
+        version_name: str = "",
+        thumbnail_url: str = "",
+        status: str = "completed",
+        error: Optional[str] = None,
+        file_path: Optional[str] = None,
+        bytes_downloaded: int = 0,
+        total_bytes: Optional[int] = None,
+        is_already_exists: int = 0,
+    ) -> int:
+        """Insert a record into the download history.
+
+        Returns the ``id`` (AUTOINCREMENT primary key) of the newly
+        inserted row.
+        """
+        now = time.time()
+
+        async with self._lock:
+            conn = self._get_conn()
+            cursor = conn.execute(
+                """
+                INSERT INTO download_history (
+                    download_id, model_id, model_version_id, model_name,
+                    version_name, thumbnail_url, status, error, file_path,
+                    bytes_downloaded, total_bytes, completed_at, is_already_exists
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                """,
+                (
+                    download_id,
+                    model_id,
+                    model_version_id,
+                    model_name,
+                    version_name,
+                    thumbnail_url,
+                    status,
+                    error,
+                    file_path,
+                    bytes_downloaded,
+                    total_bytes,
+                    now,
+                    is_already_exists,
+                ),
+            )
+            conn.commit()
+        return cursor.lastrowid or 0
+
+    async def get_history(
+        self,
+        limit: int = 50,
+        offset: int = 0,
+        status_filter: Optional[str] = None,
+    ) -> dict[str, Any]:
+        """Return a page of download history entries.
+
+        Returns a dict with keys ``items``, ``total``, ``limit``, and
+        ``offset``.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+
+            if status_filter is not None:
+                count_row = conn.execute(
+                    "SELECT COUNT(*) AS cnt FROM download_history WHERE status = ?",
+                    (status_filter,),
+                ).fetchone()
+                rows = conn.execute(
+                    "SELECT * FROM download_history WHERE status = ? "
+                    "ORDER BY completed_at DESC LIMIT ? OFFSET ?",
+                    (status_filter, limit, offset),
+                ).fetchall()
+            else:
+                count_row = conn.execute(
+                    "SELECT COUNT(*) AS cnt FROM download_history"
+                ).fetchone()
+                rows = conn.execute(
+                    "SELECT * FROM download_history "
+                    "ORDER BY completed_at DESC LIMIT ? OFFSET ?",
+                    (limit, offset),
+                ).fetchall()
+
+        return {
+            "items": [dict(row) for row in rows],
+            "total": count_row["cnt"] if count_row else 0,
+            "limit": limit,
+            "offset": offset,
+        }
+
+    async def delete_history_item(
+        self, id: Optional[int] = None, download_id: Optional[str] = None
+    ) -> bool:
+        """Delete a single history entry by *download_id* (preferred) or *id*.
+
+        Returns ``True`` if a row was deleted.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            if download_id:
+                cursor = conn.execute(
+                    "DELETE FROM download_history WHERE download_id = ?",
+                    (download_id,),
+                )
+            elif id is not None:
+                cursor = conn.execute(
+                    "DELETE FROM download_history WHERE id = ?",
+                    (id,),
+                )
+            else:
+                return False
+            conn.commit()
+        return cursor.rowcount > 0
+
+    async def clear_history(
+        self,
+        status_filter: Optional[str] = None,
+        before_timestamp: Optional[float] = None,
+    ) -> int:
+        """Remove history entries matching the optional filters.
+
+        Both ``status_filter`` and ``before_timestamp`` can be combined
+        (AND logic).  Returns the number of deleted rows.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+
+            clauses: list[str] = []
+            params: list[Any] = []
+
+            if status_filter is not None:
+                clauses.append("status = ?")
+                params.append(status_filter)
+            if before_timestamp is not None:
+                clauses.append("completed_at < ?")
+                params.append(before_timestamp)
+
+            where = ""
+            if clauses:
+                where = " WHERE " + " AND ".join(clauses)
+
+            cursor = conn.execute(
+                f"DELETE FROM download_history{where}",
+                params,
+            )
+            conn.commit()
+        return cursor.rowcount
+
+    async def get_history_count(self, status_filter: Optional[str] = None) -> int:
+        """Return the number of history entries, optionally filtered by status."""
+        async with self._lock:
+            conn = self._get_conn()
+            if status_filter is not None:
+                row = conn.execute(
+                    "SELECT COUNT(*) AS cnt FROM download_history WHERE status = ?",
+                    (status_filter,),
+                ).fetchone()
+            else:
+                row = conn.execute(
+                    "SELECT COUNT(*) AS cnt FROM download_history"
+                ).fetchone()
+        return row["cnt"] if row else 0
+
+    # ------------------------------------------------------------------
+    # Retry
+    # ------------------------------------------------------------------
+
+    async def retry_from_history(
+        self,
+        item_id: Optional[int] = None,
+        download_id: Optional[str] = None,
+    ) -> Optional[dict[str, Any]]:
+        """Re-queue a failed or canceled download from history.
+
+        Looks up the history record by *download_id* (preferred) or
+        *item_id*.  If the status is ``failed`` or ``canceled`` a new
+        queue entry is created with the same model metadata and a fresh
+        download id, and the original history entry is **deleted** to
+        prevent exponential growth when the retried item is later
+        canceled or fails again and re-retried.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            if download_id:
+                row = conn.execute(
+                    "SELECT * FROM download_history WHERE download_id = ?",
+                    (download_id,),
+                ).fetchone()
+            elif item_id is not None:
+                row = conn.execute(
+                    "SELECT * FROM download_history WHERE id = ?",
+                    (item_id,),
+                ).fetchone()
+            else:
+                return None
+            if row is None:
+                return None
+            status = str(row["status"])
+            if status not in ("failed", "canceled"):
+                return None
+
+            import uuid
+
+            new_id = str(uuid.uuid4())
+            now = time.time()
+            conn.execute(
+                """
+                INSERT INTO download_queue (
+                    download_id, model_id, model_version_id, model_name,
+                    version_name, thumbnail_url, source, file_params,
+                    status, priority, added_at
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, NULL, 'queued', 0, ?)
+                """,
+                (
+                    new_id,
+                    row["model_id"],
+                    row["model_version_id"],
+                    row["model_name"],
+                    row["version_name"],
+                    row["thumbnail_url"],
+                    "retry",
+                    now,
+                ),
+            )
+            conn.execute(
+                "DELETE FROM download_history WHERE id = ?",
+                (row["id"],),
+            )
+            conn.commit()
+            queued = conn.execute(
+                "SELECT * FROM download_queue WHERE download_id = ?",
+                (new_id,),
+            ).fetchone()
+
+        return dict(queued) if queued else None
+
+    async def retry_all_failed(self) -> int:
+        """Re-queue all failed and canceled downloads from history.
+
+        Each history entry is **deleted** after being re-queued so that
+        repeated retry-all calls do not cause exponential growth.
+
+        Returns the number of items that were re-queued.
+        """
+        async with self._lock:
+            conn = self._get_conn()
+            rows = conn.execute(
+                "SELECT * FROM download_history WHERE status IN ('failed', 'canceled')"
+            ).fetchall()
+            if not rows:
+                return 0
+
+            import uuid
+
+            now = time.time()
+            count = 0
+            for row in rows:
+                new_id = str(uuid.uuid4())
+                conn.execute(
+                    """
+                    INSERT INTO download_queue (
+                        download_id, model_id, model_version_id, model_name,
+                        version_name, thumbnail_url, source, file_params,
+                        status, priority, added_at
+                    ) VALUES (?, ?, ?, ?, ?, ?, ?, NULL, 'queued', 0, ?)
+                    """,
+                    (
+                        new_id,
+                        row["model_id"],
+                        row["model_version_id"],
+                        row["model_name"],
+                        row["version_name"],
+                        row["thumbnail_url"],
+                        "retry",
+                        now,
+                    ),
+                )
+                conn.execute(
+                    "DELETE FROM download_history WHERE id = ?",
+                    (row["id"],),
+                )
+                count += 1
+            conn.commit()
+
+        return count
+
+    # ------------------------------------------------------------------
+    # Stats
+    # ------------------------------------------------------------------
+
+    async def get_stats(self) -> dict[str, int]:
+        """Return aggregate counts across both tables.
+
+        Returns a dict with keys ``queued``, ``downloading``, ``paused``
+        (all from the queue table) and ``completed``, ``failed``,
+        ``canceled`` (all from the history table).
+        """
+        async with self._lock:
+            conn = self._get_conn()
+
+            queue_rows = conn.execute(
+                "SELECT status, COUNT(*) AS cnt FROM download_queue GROUP BY status"
+            ).fetchall()
+            queue_stats: dict[str, int] = {}
+            for row in queue_rows:
+                queue_stats[str(row["status"])] = row["cnt"]
+
+            history_rows = conn.execute(
+                "SELECT status, COUNT(*) AS cnt FROM download_history GROUP BY status"
+            ).fetchall()
+            history_stats: dict[str, int] = {}
+            for row in history_rows:
+                history_stats[str(row["status"])] = row["cnt"]
+
+        return {
+            "queued": queue_stats.get("queued", 0),
+            "downloading": queue_stats.get("downloading", 0),
+            "paused": queue_stats.get("paused", 0),
+            "completed": history_stats.get("completed", 0),
+            "failed": history_stats.get("failed", 0),
+            "canceled": history_stats.get("canceled", 0),
+        }
+
+    # ------------------------------------------------------------------
+    # Deduplication (one-time cleanup for bug #980)
+    # ------------------------------------------------------------------
+
+    async def deduplicate(self) -> dict[str, int]:
+        """Remove duplicate entries caused by the retry-amplification bug.
+
+        The bug (issue #980) caused the same download to appear N times in
+        both the queue and history tables when ``retry_all_failed`` was
+        called repeatedly without deleting the original history rows.
+
+        This method is called **once** when the singleton is first created.
+        It is idempotent — after the first run there will be no duplicates
+        to remove, so subsequent calls are a no-op.
+
+        Returns a dict with the count of removed rows per table.
+        """
+        result: dict[str, int] = {
+            "removed_history": 0,
+            "removed_queue": 0,
+            "removed_orphan_queue": 0,
+        }
+
+        async with self._lock:
+            conn = self._get_conn()
+
+            # 1. History: for each (model_id, model_version_id, status) triplet
+            #    keep only the row with the highest id (most recently inserted).
+            conn.execute("""
+                DELETE FROM download_history
+                WHERE id NOT IN (
+                    SELECT MAX(id)
+                    FROM download_history
+                    GROUP BY model_id, model_version_id, status
+                )
+            """)
+            result["removed_history"] = conn.execute(
+                "SELECT changes()"
+            ).fetchone()[0]
+
+            # 2. Cross-status dedup: for each (model_id, model_version_id),
+            #    keep only the entry with the highest-priority terminal status.
+            #    Priority: completed (3) > failed (2) > canceled (1).
+            #    This prevents the same model version from having both a
+            #    'failed' and a 'canceled' entry (or a 'completed' alongside
+            #    either) after the bug-created duplicates are removed.
+            conn.execute("""
+                DELETE FROM download_history
+                WHERE id NOT IN (
+                    SELECT dh.id
+                    FROM download_history dh
+                    INNER JOIN (
+                        SELECT model_id, model_version_id,
+                               MAX(CASE status
+                                   WHEN 'completed' THEN 3
+                                   WHEN 'failed' THEN 2
+                                   WHEN 'canceled' THEN 1
+                                   ELSE 0
+                               END) AS best_prio
+                        FROM download_history
+                        GROUP BY model_id, model_version_id
+                    ) best
+                    ON dh.model_id = best.model_id
+                   AND dh.model_version_id = best.model_version_id
+                   AND CASE dh.status
+                           WHEN 'completed' THEN 3
+                           WHEN 'failed' THEN 2
+                           WHEN 'canceled' THEN 1
+                           ELSE 0
+                       END = best.best_prio
+                    GROUP BY dh.model_id, dh.model_version_id
+                    HAVING dh.id = MAX(dh.id)
+                )
+            """)
+            result["removed_history"] += conn.execute(
+                "SELECT changes()"
+            ).fetchone()[0]
+
+            # 3. Queue: for each (model_id, model_version_id) keep only the
+            #    row with the latest added_at (most recently enqueued).
+            conn.execute("""
+                DELETE FROM download_queue
+                WHERE rowid NOT IN (
+                    SELECT MAX(rowid)
+                    FROM download_queue
+                    WHERE status IN ('queued', 'downloading', 'paused', 'waiting')
+                    GROUP BY model_id, model_version_id
+                )
+                AND status IN ('queued', 'downloading', 'paused', 'waiting')
+            """)
+            result["removed_queue"] = conn.execute(
+                "SELECT changes()"
+            ).fetchone()[0]
+
+            # 4. Remove orphaned queue entries — items that were re-queued
+            #    (source='retry') but whose model version already has a
+            #    terminal history entry. These are artifacts of the buggy
+            #    retry cycle that were never cleaned up.
+            conn.execute("""
+                DELETE FROM download_queue
+                WHERE source = 'retry'
+                AND (model_id, model_version_id) IN (
+                    SELECT model_id, model_version_id
+                    FROM download_history
+                    WHERE status IN ('failed', 'canceled')
+                )
+                AND status IN ('queued', 'waiting')
+            """)
+            result["removed_orphan_queue"] = conn.execute(
+                "SELECT changes()"
+            ).fetchone()[0]
+
+            conn.commit()
+
+        logger.info(
+            "Deduplicate: removed %s history rows, %s queue rows, "
+            "%s orphaned queue rows",
+            result["removed_history"],
+            result["removed_queue"],
+            result["removed_orphan_queue"],
+        )
+        return result

py/services/downloaded_version_history_service.py

@@ -64,6 +64,7 @@ class DownloadedVersionHistoryService:
         self._db_path = db_path or _resolve_database_path()
         self._settings = settings_manager or get_settings_manager()
         self._lock = asyncio.Lock()
+        self._conn: sqlite3.Connection | None = None
         self._schema_initialized = False
         self._ensure_directory()
         self._initialize_schema()
@@ -78,6 +79,12 @@ class DownloadedVersionHistoryService:
         conn.row_factory = sqlite3.Row
         return conn
 
+    def _get_conn(self) -> sqlite3.Connection:
+        if self._conn is None:
+            self._conn = sqlite3.connect(self._db_path, check_same_thread=False)
+            self._conn.row_factory = sqlite3.Row
+        return self._conn
+
     def _initialize_schema(self) -> None:
         if self._schema_initialized:
             return
@@ -89,6 +96,21 @@ class DownloadedVersionHistoryService:
     def get_database_path(self) -> str:
         return self._db_path
 
+    def close(self) -> None:
+        """Close the persistent SQLite connection, if open.
+
+        This is called before plugin update operations to release the
+        database file lock on Windows, allowing ``shutil.rmtree()`` to
+        succeed when the cache resides inside the plugin directory.
+        """
+        if self._conn is not None:
+            try:
+                self._conn.close()
+            except Exception:
+                pass
+            finally:
+                self._conn = None
+
     def _get_active_library_name(self) -> str | None:
         try:
             value = self._settings.get_active_library_name()
@@ -116,33 +138,33 @@ class DownloadedVersionHistoryService:
         timestamp = time.time()
 
         async with self._lock:
-            with self._connect() as conn:
-                conn.execute(
-                    """
-                    INSERT INTO downloaded_model_versions (
-                        model_type, version_id, model_id, first_seen_at, last_seen_at,
-                        source, last_file_path, last_library_name, is_deleted_override
-                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
-                    ON CONFLICT(model_type, version_id) DO UPDATE SET
-                        model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
-                        last_seen_at = excluded.last_seen_at,
-                        source = excluded.source,
-                        last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
-                        last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
-                        is_deleted_override = 0
-                    """,
-                    (
-                        normalized_type,
-                        normalized_version_id,
-                        normalized_model_id,
-                        timestamp,
-                        timestamp,
-                        source,
-                        file_path,
-                        active_library_name,
-                    ),
-                )
-                conn.commit()
+            conn = self._get_conn()
+            conn.execute(
+                """
+                INSERT INTO downloaded_model_versions (
+                    model_type, version_id, model_id, first_seen_at, last_seen_at,
+                    source, last_file_path, last_library_name, is_deleted_override
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
+                ON CONFLICT(model_type, version_id) DO UPDATE SET
+                    model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
+                    last_seen_at = excluded.last_seen_at,
+                    source = excluded.source,
+                    last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
+                    last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
+                    is_deleted_override = 0
+                """,
+                (
+                    normalized_type,
+                    normalized_version_id,
+                    normalized_model_id,
+                    timestamp,
+                    timestamp,
+                    source,
+                    file_path,
+                    active_library_name,
+                ),
+            )
+            conn.commit()
 
     async def mark_downloaded_bulk(
         self,
@@ -180,26 +202,26 @@ class DownloadedVersionHistoryService:
             return
 
         async with self._lock:
-            with self._connect() as conn:
-                conn.executemany(
-                    """
-                    INSERT INTO downloaded_model_versions (
-                        model_type, version_id, model_id, first_seen_at, last_seen_at,
-                        source, last_file_path, last_library_name, is_deleted_override
-                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
-                    ON CONFLICT(model_type, version_id) DO UPDATE SET
-                        model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
-                        last_seen_at = excluded.last_seen_at,
-                        source = excluded.source,
-                        last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
-                        last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
-                        is_deleted_override = 0
-                    """,
-                    payload,
-                )
-                conn.commit()
+            conn = self._get_conn()
+            conn.executemany(
+                """
+                INSERT INTO downloaded_model_versions (
+                    model_type, version_id, model_id, first_seen_at, last_seen_at,
+                    source, last_file_path, last_library_name, is_deleted_override
+                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, 0)
+                ON CONFLICT(model_type, version_id) DO UPDATE SET
+                    model_id = COALESCE(excluded.model_id, downloaded_model_versions.model_id),
+                    last_seen_at = excluded.last_seen_at,
+                    source = excluded.source,
+                    last_file_path = COALESCE(excluded.last_file_path, downloaded_model_versions.last_file_path),
+                    last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
+                    is_deleted_override = 0
+                """,
+                payload,
+            )
+            conn.commit()
 
-    async def mark_not_downloaded(self, model_type: str, version_id: int) -> None:
+    async def mark_as_deleted(self, model_type: str, version_id: int) -> None:
         normalized_type = _normalize_model_type(model_type)
         normalized_version_id = _normalize_int(version_id)
         if normalized_type is None or normalized_version_id is None:
@@ -208,28 +230,28 @@ class DownloadedVersionHistoryService:
         timestamp = time.time()
 
         async with self._lock:
-            with self._connect() as conn:
-                conn.execute(
-                    """
-                    INSERT INTO downloaded_model_versions (
-                        model_type, version_id, model_id, first_seen_at, last_seen_at,
-                        source, last_file_path, last_library_name, is_deleted_override
-                    ) VALUES (?, ?, NULL, ?, ?, 'manual', NULL, ?, 1)
-                    ON CONFLICT(model_type, version_id) DO UPDATE SET
-                        last_seen_at = excluded.last_seen_at,
-                        source = excluded.source,
-                        last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
-                        is_deleted_override = 1
-                    """,
-                    (
-                        normalized_type,
-                        normalized_version_id,
-                        timestamp,
-                        timestamp,
-                        self._get_active_library_name(),
-                    ),
-                )
-                conn.commit()
+            conn = self._get_conn()
+            conn.execute(
+                """
+                INSERT INTO downloaded_model_versions (
+                    model_type, version_id, model_id, first_seen_at, last_seen_at,
+                    source, last_file_path, last_library_name, is_deleted_override
+                ) VALUES (?, ?, NULL, ?, ?, 'manual', NULL, ?, 1)
+                ON CONFLICT(model_type, version_id) DO UPDATE SET
+                    last_seen_at = excluded.last_seen_at,
+                    source = excluded.source,
+                    last_library_name = COALESCE(excluded.last_library_name, downloaded_model_versions.last_library_name),
+                    is_deleted_override = 1
+                """,
+                (
+                    normalized_type,
+                    normalized_version_id,
+                    timestamp,
+                    timestamp,
+                    self._get_active_library_name(),
+                ),
+            )
+            conn.commit()
 
     async def has_been_downloaded(self, model_type: str, version_id: int) -> bool:
         normalized_type = _normalize_model_type(model_type)
@@ -238,15 +260,15 @@ class DownloadedVersionHistoryService:
             return False
 
         async with self._lock:
-            with self._connect() as conn:
-                row = conn.execute(
-                    """
-                    SELECT is_deleted_override
-                    FROM downloaded_model_versions
-                    WHERE model_type = ? AND version_id = ?
-                    """,
-                    (normalized_type, normalized_version_id),
-                ).fetchone()
+            conn = self._get_conn()
+            row = conn.execute(
+                """
+                SELECT is_deleted_override
+                FROM downloaded_model_versions
+                WHERE model_type = ? AND version_id = ?
+                """,
+                (normalized_type, normalized_version_id),
+            ).fetchone()
         return bool(row) and not bool(row["is_deleted_override"])
 
     async def get_downloaded_version_ids(
@@ -258,16 +280,16 @@ class DownloadedVersionHistoryService:
             return []
 
         async with self._lock:
-            with self._connect() as conn:
-                rows = conn.execute(
-                    """
-                    SELECT version_id
-                    FROM downloaded_model_versions
-                    WHERE model_type = ? AND model_id = ? AND is_deleted_override = 0
-                    ORDER BY version_id ASC
-                    """,
-                    (normalized_type, normalized_model_id),
-                ).fetchall()
+            conn = self._get_conn()
+            rows = conn.execute(
+                """
+                SELECT version_id
+                FROM downloaded_model_versions
+                WHERE model_type = ? AND model_id = ? AND is_deleted_override = 0
+                ORDER BY version_id ASC
+                """,
+                (normalized_type, normalized_model_id),
+            ).fetchall()
         return [int(row["version_id"]) for row in rows]
 
     async def get_downloaded_version_ids_bulk(
@@ -291,17 +313,17 @@ class DownloadedVersionHistoryService:
         params: list[object] = [normalized_type, *normalized_model_ids]
 
         async with self._lock:
-            with self._connect() as conn:
-                rows = conn.execute(
-                    f"""
-                    SELECT model_id, version_id
-                    FROM downloaded_model_versions
-                    WHERE model_type = ?
-                      AND model_id IN ({placeholders})
-                      AND is_deleted_override = 0
-                    """,
-                    params,
-                ).fetchall()
+            conn = self._get_conn()
+            rows = conn.execute(
+                f"""
+                SELECT model_id, version_id
+                FROM downloaded_model_versions
+                WHERE model_type = ?
+                  AND model_id IN ({placeholders})
+                  AND is_deleted_override = 0
+                """,
+                params,
+            ).fetchall()
 
         result: dict[int, set[int]] = {}
         for row in rows:

py/services/downloader.py

@@ -13,18 +13,63 @@ This module provides a centralized download service with:
 import os
 import logging
 import asyncio
+import ssl
 import aiohttp
 from collections import deque
 from dataclasses import dataclass
 from datetime import datetime, timedelta
 from email.utils import parsedate_to_datetime
+from urllib.parse import urlparse
 from typing import Optional, Dict, Tuple, Callable, Union, Awaitable
 from ..services.settings_manager import get_settings_manager
+from .connectivity_guard import (
+    OFFLINE_COOLDOWN_ERROR,
+    OFFLINE_FRIENDLY_MESSAGE,
+    ConnectivityGuard,
+)
 from .errors import RateLimitError
 
 logger = logging.getLogger(__name__)
 
 
+def is_ssl_cert_verify_error(exc: BaseException) -> bool:
+    """Check if an exception represents an SSL certificate verification failure.
+
+    Matches ``ssl.SSLCertVerificationError``, ``aiohttp.ClientConnectorCertificateError``
+    (which wraps the former), and falls back to the standard OpenSSL error text.
+    """
+    if isinstance(exc, ssl.SSLCertVerificationError):
+        return True
+    cert_error = getattr(exc, "certificate_error", None)
+    if isinstance(cert_error, ssl.SSLCertVerificationError):
+        return True
+    return "CERTIFICATE_VERIFY_FAILED" in str(exc)
+
+
+def _parse_retry_after(value: str) -> int:
+    """Parse a Retry-After header value into seconds.
+
+    Supports both integer seconds and HTTP-date formats.
+    Returns a default of 60 seconds on invalid/missing input.
+    """
+    if not value or not value.strip():
+        return 60
+
+    value = value.strip()
+    try:
+        return max(1, int(value))
+    except ValueError:
+        pass
+
+    try:
+        parsed = parsedate_to_datetime(value)
+        now = datetime.now().astimezone()
+        delta = (parsed - now).total_seconds()
+        return max(1, int(delta))
+    except (ValueError, OverflowError, OSError):
+        return 60
+
+
 @dataclass(frozen=True)
 class DownloadProgress:
     """Snapshot of a download transfer at a moment in time."""
@@ -138,7 +183,7 @@ class Downloader:
         self.chunk_size = (
             16 * 1024 * 1024
         )  # 16MB chunks to balance I/O reduction and memory usage
-        self.max_retries = 5
+        self.max_retries = self._resolve_max_retries()
         self.base_delay = 2.0  # Base delay for exponential backoff
         self.session_timeout = 300  # 5 minutes
         self.stall_timeout = self._resolve_stall_timeout()
@@ -192,6 +237,18 @@ class Downloader:
 
         return max(30.0, timeout_value)
 
+    def _resolve_max_retries(self) -> int:
+        """Determine max retry count from environment while preserving defaults."""
+        default_retries = 5
+        raw_value = os.environ.get("COMFYUI_DOWNLOAD_MAX_RETRIES")
+
+        try:
+            retries = int(raw_value)
+        except (TypeError, ValueError):
+            retries = default_retries
+
+        return max(0, retries)
+
     def _should_refresh_session(self) -> bool:
         """Check if session should be refreshed"""
         if self._session is None:
@@ -213,17 +270,19 @@ class Downloader:
 
         Note: This is private and caller MUST hold self._session_lock.
         """
-        # Close existing session if any
-        if self._session is not None:
-            try:
-                await self._session.close()
-            except Exception as e:  # pragma: no cover
-                logger.warning(f"Error closing previous session: {e}")
-            finally:
-                self._session = None
+        # Snapshot and clear old session reference before creating the new
+        # one.  This ensures self._session is always valid (or None, which
+        # triggers a fresh creation) and avoids a race where concurrent
+        # requests hold a reference to a session whose connector has been
+        # torn down by a premature close() call — the root cause of the
+        # intermittent "NoneType has no attribute connect" crash.
+        old_session = self._session
+        self._session = None
 
         # Check for app-level proxy settings
-        proxy_url = None
+        proxy_url = None  # http(s) proxy, passed via the per-request `proxy=` kwarg
+        socks_proxy_url = None  # SOCKS proxy, handled via aiohttp-socks connector
+        app_proxy_active = False
         settings_manager = get_settings_manager()
         if settings_manager.get("proxy_enabled", False):
             proxy_host = settings_manager.get("proxy_host", "").strip()
@@ -235,9 +294,19 @@ class Downloader:
             if proxy_host and proxy_port:
                 # Build proxy URL
                 if proxy_username and proxy_password:
-                    proxy_url = f"{proxy_type}://{proxy_username}:{proxy_password}@{proxy_host}:{proxy_port}"
+                    full_proxy_url = f"{proxy_type}://{proxy_username}:{proxy_password}@{proxy_host}:{proxy_port}"
                 else:
-                    proxy_url = f"{proxy_type}://{proxy_host}:{proxy_port}"
+                    full_proxy_url = f"{proxy_type}://{proxy_host}:{proxy_port}"
+
+                app_proxy_active = True
+                # aiohttp cannot tunnel SOCKS via the per-request `proxy=` kwarg
+                # (it would send HTTP to the SOCKS port and fail parsing the
+                # SOCKS handshake reply). SOCKS must be handled by an
+                # aiohttp-socks ProxyConnector instead.
+                if proxy_type.startswith("socks"):
+                    socks_proxy_url = full_proxy_url
+                else:
+                    proxy_url = full_proxy_url
 
                 logger.debug(
                     f"Using app-level proxy: {proxy_type}://{proxy_host}:{proxy_port}"
@@ -247,14 +316,41 @@ class Downloader:
             logger.debug(
                 "Proxy mode: system-level proxy (trust_env) will be used if configured in environment."
             )
+        # Build SSL context: prefer certifi's CA bundle for broader
+        # CA coverage across different Python environments (especially
+        # embedded/compatibility Python builds).
+        try:
+            import certifi  # type: ignore[import-untyped]
+
+            ca_path = certifi.where()
+            ssl_context = ssl.create_default_context(cafile=ca_path)
+            logger.debug("SSL: using certifi CA bundle at %s", ca_path)
+        except (ImportError, FileNotFoundError, ValueError, OSError):
+            ssl_context = ssl.create_default_context()
+            logger.debug("SSL: certifi unavailable; using system default CA bundle")
+
         # Optimize TCP connection parameters
-        connector = aiohttp.TCPConnector(
-            ssl=True,
+        connector_kwargs = dict(
+            ssl=ssl_context,
             limit=8,  # Concurrent connections
             ttl_dns_cache=300,  # DNS cache timeout
             force_close=False,  # Keep connections for reuse
             enable_cleanup_closed=True,
         )
+        if socks_proxy_url:
+            # Route all traffic through the SOCKS proxy via aiohttp-socks. The
+            # connector tunnels every connection, so no per-request `proxy=` is
+            # used (and must not be — see self._proxy_url below).
+            try:
+                from aiohttp_socks import ProxyConnector
+            except ImportError as e:  # pragma: no cover
+                raise RuntimeError(
+                    "A SOCKS proxy is configured but the 'aiohttp-socks' package "
+                    "is not installed. Install it with: pip install aiohttp-socks"
+                ) from e
+            connector = ProxyConnector.from_url(socks_proxy_url, **connector_kwargs)
+        else:
+            connector = aiohttp.TCPConnector(**connector_kwargs)
 
         # Configure timeout parameters
         timeout = aiohttp.ClientTimeout(
@@ -265,15 +361,24 @@ class Downloader:
 
         self._session = aiohttp.ClientSession(
             connector=connector,
-            trust_env=proxy_url
-            is None,  # Only use system proxy if no app-level proxy is set
+            # Only fall back to system/env proxy when no app-level proxy is active
+            trust_env=not app_proxy_active,
             timeout=timeout,
         )
 
-        # Store proxy URL for use in requests
+        # Store proxy URL for per-request use. Stays None for SOCKS because the
+        # ProxyConnector already tunnels everything; passing proxy= for SOCKS
+        # would re-trigger the original aiohttp parse error.
         self._proxy_url = proxy_url
         self._session_created_at = datetime.now()
 
+        # Close the previous session now that the replacement is live.
+        if old_session is not None:
+            try:
+                await old_session.close()
+            except Exception as e:  # pragma: no cover
+                logger.warning(f"Error closing previous session: {e}")
+
         logger.debug(
             "Created new HTTP session with proxy settings. App-level proxy: %s, System-level proxy (trust_env): %s",
             bool(proxy_url),
@@ -334,6 +439,7 @@ class Downloader:
             logger.info(f"Resuming download from offset {resume_offset} bytes")
 
         total_size = 0
+        range_redirect_retry_urls: set[str] = set()
 
         while retry_count <= self.max_retries:
             try:
@@ -372,6 +478,23 @@ class Downloader:
                     if response.status == 200:
                         # Full content response
                         if resume_offset > 0:
+                            redirected_url = str(response.url)
+                            if (
+                                allow_resume
+                                and response.history
+                                and redirected_url
+                                and redirected_url != url
+                                and redirected_url not in range_redirect_retry_urls
+                            ):
+                                range_redirect_retry_urls.add(redirected_url)
+                                logger.info(
+                                    "Range request was not honored after redirect; retrying final URL directly: %s",
+                                    redirected_url,
+                                )
+                                url = redirected_url
+                                response.release()
+                                continue
+
                             # Server doesn't support ranges, restart from beginning
                             logger.warning(
                                 "Server doesn't support range requests, restarting download"
@@ -571,37 +694,53 @@ class Downloader:
                     expected_size = total_size if total_size > 0 else None
 
                     integrity_error: Optional[str] = None
+                    resumable_incomplete = False
                     if final_size <= 0:
                         integrity_error = "Downloaded file is empty"
                     elif expected_size is not None and final_size != expected_size:
                         integrity_error = f"File size mismatch. Expected: {expected_size}, Got: {final_size}"
+                        resumable_incomplete = (
+                            allow_resume
+                            and part_path != save_path
+                            and final_size > 0
+                            and final_size < expected_size
+                        )
 
                     if integrity_error is not None:
-                        logger.error(
+                        log_fn = logger.warning if resumable_incomplete else logger.error
+                        log_fn(
                             "Download integrity check failed for %s: %s",
                             save_path,
                             integrity_error,
                         )
 
-                        # Remove the corrupted payload so future attempts start fresh
-                        if os.path.exists(part_path):
-                            try:
-                                os.remove(part_path)
-                            except OSError as remove_error:
-                                logger.warning(
-                                    "Failed to delete corrupted download %s: %s",
-                                    part_path,
-                                    remove_error,
-                                )
-                        if part_path != save_path and os.path.exists(save_path):
-                            try:
-                                os.remove(save_path)
-                            except OSError as remove_error:
-                                logger.warning(
-                                    "Failed to delete target file %s after integrity error: %s",
-                                    save_path,
-                                    remove_error,
-                                )
+                        if resumable_incomplete:
+                            logger.info(
+                                "Preserving incomplete download for resume: %s (%s/%s bytes)",
+                                part_path,
+                                final_size,
+                                expected_size,
+                            )
+                        else:
+                            # Remove corrupted payloads that cannot be safely resumed.
+                            if os.path.exists(part_path):
+                                try:
+                                    os.remove(part_path)
+                                except OSError as remove_error:
+                                    logger.warning(
+                                        "Failed to delete corrupted download %s: %s",
+                                        part_path,
+                                        remove_error,
+                                    )
+                            if part_path != save_path and os.path.exists(save_path):
+                                try:
+                                    os.remove(save_path)
+                                except OSError as remove_error:
+                                    logger.warning(
+                                        "Failed to delete target file %s after integrity error: %s",
+                                        save_path,
+                                        remove_error,
+                                    )
 
                         retry_count += 1
                         if retry_count <= self.max_retries:
@@ -611,9 +750,18 @@ class Downloader:
                                 delay,
                             )
                             await asyncio.sleep(delay)
-                            resume_offset = 0
-                            total_size = 0
-                            await self._create_session()
+                            if resumable_incomplete and os.path.exists(part_path):
+                                resume_offset = os.path.getsize(part_path)
+                                total_size = expected_size or 0
+                                logger.info(
+                                    "Will resume incomplete download from byte %s",
+                                    resume_offset,
+                                )
+                            else:
+                                resume_offset = 0
+                                total_size = 0
+                            async with self._session_lock:
+                                await self._create_session()
                             continue
 
                         return False, integrity_error
@@ -676,6 +824,17 @@ class Downloader:
                 DownloadRestartRequested,
             ) as e:
                 retry_count += 1
+
+                if is_ssl_cert_verify_error(e):
+                    logger.error(
+                        "SSL certificate verification failed when connecting to %s. "
+                        "This is usually caused by an outdated CA certificate bundle "
+                        "in the Python environment. Recommended fixes:\n"
+                        "  1. pip install --upgrade certifi\n"
+                        "  2. pip install pip-system-certs",
+                        url,
+                    )
+
                 logger.warning(
                     f"Network error during download (attempt {retry_count}/{self.max_retries + 1}): {e}"
                 )
@@ -692,7 +851,8 @@ class Downloader:
                         logger.info(f"Will resume from byte {resume_offset}")
 
                     # Refresh session to get new connection
-                    await self._create_session()
+                    async with self._session_lock:
+                        await self._create_session()
                     continue
                 else:
                     logger.error(f"Max retries exceeded for download: {e}")
@@ -743,6 +903,11 @@ class Downloader:
         Returns:
             Tuple[bool, Union[bytes, str], Optional[Dict]]: (success, content or error message, response headers if requested)
         """
+        guard = await ConnectivityGuard.get_instance()
+        destination = self._guard_destination(url)
+        if guard.should_block_request(destination):
+            return False, OFFLINE_FRIENDLY_MESSAGE, None
+
         try:
             session = await self.session
             # Debug log for proxy mode at request time
@@ -765,6 +930,7 @@ class Downloader:
             ) as response:
                 if response.status == 200:
                     content = await response.read()
+                    guard.register_success(destination)
                     if return_headers:
                         return True, content, dict(response.headers)
                     else:
@@ -778,11 +944,30 @@ class Downloader:
                 elif response.status == 404:
                     error_msg = "File not found"
                     return False, error_msg, None
+                elif response.status == 429:
+                    raw_retry_after = response.headers.get("Retry-After")
+                    retry_after = _parse_retry_after(raw_retry_after or "")
+                    if raw_retry_after:
+                        logger.warning(
+                            "Rate limited (429) for %s, Retry-After: %ss", url, retry_after
+                        )
+                    else:
+                        logger.warning(
+                            "Rate limited (429) for %s, no Retry-After header; defaulting to %ss",
+                            url, retry_after,
+                        )
+                    return False, f"Rate limited (429), retry after {retry_after}s", None
                 else:
                     error_msg = f"Download failed with status {response.status}"
                     return False, error_msg, None
 
         except Exception as e:
+            if guard.is_network_unreachable_error(e):
+                guard.register_network_failure(e, destination)
+                if guard.should_block_request(destination):
+                    return False, OFFLINE_FRIENDLY_MESSAGE, None
+                logger.debug("Network unavailable during memory download: %s", e)
+                return False, str(e), None
             logger.error(f"Error downloading to memory from {url}: {e}")
             return False, str(e), None
 
@@ -803,6 +988,11 @@ class Downloader:
         Returns:
             Tuple[bool, Union[Dict, str]]: (success, headers dict or error message)
         """
+        guard = await ConnectivityGuard.get_instance()
+        destination = self._guard_destination(url)
+        if guard.should_block_request(destination):
+            return False, OFFLINE_COOLDOWN_ERROR
+
         try:
             session = await self.session
             # Debug log for proxy mode at request time
@@ -824,11 +1014,18 @@ class Downloader:
                 url, headers=headers, proxy=self.proxy_url
             ) as response:
                 if response.status == 200:
+                    guard.register_success(destination)
                     return True, dict(response.headers)
                 else:
                     return False, f"Head request failed with status {response.status}"
 
         except Exception as e:
+            if guard.is_network_unreachable_error(e):
+                guard.register_network_failure(e, destination)
+                if guard.should_block_request(destination):
+                    return False, OFFLINE_COOLDOWN_ERROR
+                logger.debug("Network unavailable during header probe: %s", e)
+                return False, str(e)
             logger.error(f"Error getting headers from {url}: {e}")
             return False, str(e)
 
@@ -853,6 +1050,11 @@ class Downloader:
         Returns:
             Tuple[bool, Union[Dict, str]]: (success, response data or error message)
         """
+        guard = await ConnectivityGuard.get_instance()
+        destination = self._guard_destination(url)
+        if guard.should_block_request(destination):
+            return False, OFFLINE_COOLDOWN_ERROR
+
         try:
             session = await self.session
             # Debug log for proxy mode at request time
@@ -876,6 +1078,7 @@ class Downloader:
                 method, url, headers=headers, **kwargs
             ) as response:
                 if response.status == 200:
+                    guard.register_success(destination)
                     # Try to parse as JSON, fall back to text
                     try:
                         data = await response.json()
@@ -906,6 +1109,12 @@ class Downloader:
                     return False, f"Request failed with status {response.status}"
 
         except Exception as e:
+            if guard.is_network_unreachable_error(e):
+                guard.register_network_failure(e, destination)
+                if guard.should_block_request(destination):
+                    return False, OFFLINE_COOLDOWN_ERROR
+                logger.debug("Network unavailable for %s %s: %s", method, url, e)
+                return False, str(e)
             logger.error(f"Error making {method} request to {url}: {e}")
             return False, str(e)
 
@@ -956,6 +1165,14 @@ class Downloader:
         delta = retry_datetime - datetime.now(tz=retry_datetime.tzinfo)
         return max(0.0, delta.total_seconds())
 
+    @staticmethod
+    def _guard_destination(url: str) -> str:
+        """Build per-destination connectivity guard scope from request URL."""
+        parsed_url = urlparse(url)
+        if parsed_url.hostname:
+            return parsed_url.hostname.lower()
+        return "unknown"
+
 
 # Global instance accessor
 async def get_downloader() -> Downloader:

py/services/embedding_service.py

@@ -1,8 +1,9 @@
 import os
 import logging
-from typing import Dict
+from typing import Dict, Optional
 
 from .base_model_service import BaseModelService
+from .auto_tag_service import extract_auto_tags
 from ..utils.models import EmbeddingMetadata
 from ..config import config
 
@@ -20,20 +21,37 @@ class EmbeddingService(BaseModelService):
         """
         super().__init__("embedding", scanner, EmbeddingMetadata, update_service=update_service)
     
-    async def format_response(self, embedding_data: Dict) -> Dict:
-        """Format Embedding data for API response"""
+    async def format_response(self, embedding_data: Dict) -> Optional[Dict]:
+        """Format Embedding 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 = embedding_data.get("file_path")
+        if not file_path or not isinstance(file_path, str):
+            logger.warning(
+                "Skipping corrupted embedding entry (missing file_path): %s",
+                embedding_data.get("file_name", "<unknown>"),
+            )
+            return None
+
         # Get sub_type from cache entry (new canonical field)
         sub_type = embedding_data.get("sub_type", "embedding")
-        
+
+        file_name = embedding_data.get("file_name") or ""
+        model_name = embedding_data.get("model_name") or file_name
+        folder = embedding_data.get("folder") or ""
+
         return {
-            "model_name": embedding_data["model_name"],
-            "file_name": embedding_data["file_name"],
+            "model_name": model_name,
+            "file_name": file_name,
             "preview_url": config.get_preview_static_url(embedding_data.get("preview_url", "")),
             "preview_nsfw_level": embedding_data.get("preview_nsfw_level", 0),
             "base_model": embedding_data.get("base_model", ""),
-            "folder": embedding_data["folder"],
+            "folder": folder,
             "sha256": embedding_data.get("sha256", ""),
-            "file_path": embedding_data["file_path"].replace(os.sep, "/"),
+            "file_path": file_path.replace(os.sep, "/"),
             "file_size": embedding_data.get("size", 0),
             "modified": embedding_data.get("modified", ""),
             "tags": embedding_data.get("tags", []),
@@ -42,9 +60,13 @@ class EmbeddingService(BaseModelService):
             "notes": embedding_data.get("notes", ""),
             "sub_type": sub_type,
             "favorite": embedding_data.get("favorite", False),
+            "exclude": bool(embedding_data.get("exclude", False)),
             "update_available": bool(embedding_data.get("update_available", False)),
             "skip_metadata_refresh": bool(embedding_data.get("skip_metadata_refresh", False)),
-            "civitai": self.filter_civitai_data(embedding_data.get("civitai", {}), minimal=True)
+            "civitai": self.filter_civitai_data(embedding_data.get("civitai", {}), minimal=True),
+            "auto_tags": embedding_data.get("auto_tags") or extract_auto_tags(embedding_data),
+            "version_count": embedding_data.get("version_count"),
+            "hf_url": embedding_data.get("hf_url", ""),
         }
     
     def find_duplicate_hashes(self) -> Dict:

py/services/errors.py

@@ -25,3 +25,21 @@ class ResourceNotFoundError(RuntimeError):
 
     pass
 
+
+class LLMNotConfiguredError(RuntimeError):
+    """Raised when an LLM-dependent operation is attempted but no provider is configured."""
+
+    pass
+
+
+class LLMRateLimitError(RateLimitError):
+    """Raised when the LLM provider rejects a request due to rate limiting."""
+
+    pass
+
+
+class LLMResponseError(RuntimeError):
+    """Raised when the LLM returns an unparseable or schema-invalid response."""
+
+    pass
+

py/services/llm_service.py

@@ -0,0 +1,695 @@
+"""Centralized LLM API client with BYOK (bring-your-own-key) provider support.
+
+Reads provider configuration from :class:`SettingsManager` and makes
+OpenAI-compatible ``/chat/completions`` calls.  Supports any provider that
+implements the OpenAI Chat Completions API surface area (OpenAI, Ollama,
+vLLM, LM Studio, etc.).
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+from typing import Any, Dict, List, Optional
+
+import aiohttp
+
+from .errors import LLMNotConfiguredError, LLMRateLimitError, LLMResponseError
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# Model catalog sourced from opencode's maintained model registry.
+# maps provider_id -> list of model IDs.
+# ---------------------------------------------------------------------------
+_MODEL_CATALOG_URL = "https://models.dev/api.json"
+
+# In-memory cache: maps provider slug -> list of model ID strings.
+_catalog_cache: Optional[Dict[str, List[str]]] = None
+
+# Per-model max output token limits parsed from the catalog.
+# ``{provider_id: {model_id: max_output_tokens}}``.
+_model_output_limits: Dict[str, Dict[str, int]] = {}
+
+_CATALOG_TIMEOUT = aiohttp.ClientTimeout(total=30)
+
+
+async def _load_model_catalog() -> Dict[str, List[str]]:
+    """Fetch and parse the model catalog.
+
+    Returns ``{provider_id: [model_id, ...]}`` and also populates
+    :data:`_model_output_limits` with per-model ``limit.output`` values
+    for use by :func:`_get_model_max_output`.
+
+    The JSON at ``_MODEL_CATALOG_URL`` is a dict keyed by provider slug; each
+    value has a ``models`` sub-dict keyed by model ID.  The result is cached
+    in memory after the first successful fetch.
+    Subsequent calls return the cached data immediately.
+    """
+    global _catalog_cache, _model_output_limits
+    if _catalog_cache is not None:
+        return _catalog_cache
+
+    try:
+        async with aiohttp.ClientSession(timeout=_CATALOG_TIMEOUT) as session:
+            async with session.get(_MODEL_CATALOG_URL) as resp:
+                if resp.status != 200:
+                    logger.warning("Model catalog returned HTTP %s", resp.status)
+                    return _catalog_cache or {}
+                data = await resp.json()
+    except (aiohttp.ClientError, asyncio.TimeoutError, json.JSONDecodeError) as exc:
+        logger.warning("Failed to fetch model catalog: %s", exc)
+        return _catalog_cache or {}
+
+    if not isinstance(data, dict):
+        logger.warning("Model catalog is not a dict, got %s", type(data).__name__)
+        return _catalog_cache or {}
+
+    result: Dict[str, List[str]] = {}
+    output_limits: Dict[str, Dict[str, int]] = {}
+    for provider_id, provider_info in data.items():
+        if not isinstance(provider_info, dict):
+            continue
+        models_dict = provider_info.get("models")
+        if not isinstance(models_dict, dict):
+            continue
+        model_ids: List[str] = []
+        provider_limits: Dict[str, int] = {}
+        for mid, model_info in models_dict.items():
+            if not isinstance(mid, str):
+                continue
+            model_ids.append(mid)
+            if isinstance(model_info, dict):
+                limit = model_info.get("limit")
+                if isinstance(limit, dict):
+                    output = limit.get("output")
+                    if isinstance(output, (int, float)) and output > 0:
+                        provider_limits[mid] = int(output)
+        if model_ids:
+            result[provider_id] = model_ids
+        if provider_limits:
+            output_limits[provider_id] = provider_limits
+
+    _catalog_cache = result
+    _model_output_limits = output_limits
+    logger.debug(
+        "Loaded model catalog: %d providers, %d total models "
+        "(%d providers have output limits)",
+        len(result),
+        sum(len(m) for m in result.values()),
+        len(output_limits),
+    )
+    return result
+
+
+def _get_model_max_output(provider: str, model: str) -> Optional[int]:
+    """Return the model's max output token limit from the catalog, or ``None``.
+
+    Returns ``None`` when the provider or model is not found in the catalog
+    (e.g. local Ollama models, custom models, or user-typed model names).
+    Callers should fall back to a safe default.
+    """
+    return _model_output_limits.get(provider, {}).get(model)
+
+
+# Short timeout for Ollama's local API
+_OLLAMA_API_TIMEOUT = aiohttp.ClientTimeout(total=8)
+
+
+async def fetch_ollama_models(api_base: str) -> List[str]:
+    """Fetch locally available models from a running Ollama instance.
+
+    Uses Ollama's OpenAI-compatible ``GET {api_base}/models`` endpoint.
+    Returns an empty list if Ollama is not reachable (not running).
+    """
+    url = f"{api_base.rstrip('/')}/models"
+    try:
+        async with aiohttp.ClientSession(timeout=_OLLAMA_API_TIMEOUT) as session:
+            async with session.get(url) as resp:
+                if resp.status != 200:
+                    logger.debug("Ollama API returned HTTP %s from %s", resp.status, api_base)
+                    return []
+                data = await resp.json()
+    except (aiohttp.ClientError, asyncio.TimeoutError, json.JSONDecodeError) as exc:
+        logger.debug("Ollama not reachable at %s: %s", api_base, exc)
+        return []
+
+    raw = data.get("data") if isinstance(data, dict) else None
+    if not isinstance(raw, list):
+        return []
+
+    return [
+        str(entry["id"]) for entry in raw
+        if isinstance(entry, dict) and isinstance(entry.get("id"), str)
+    ]
+
+
+async def get_provider_model_ids(provider_id: str) -> List[str]:
+    """Return the list of known model IDs for *provider_id* from the catalog.
+
+    The catalog is loaded on first call and cached thereafter.  If the
+    provider is not found an empty list is returned (never raises).
+    """
+    catalog = await _load_model_catalog()
+    return catalog.get(provider_id, [])
+
+
+async def get_all_provider_models(
+    provider_ids: List[str],
+) -> Dict[str, List[str]]:
+    """Return model lists for a subset of providers in one call.
+
+    Loads the catalog (cached) and returns only the requested providers.
+    Handy for embedding lightweight data into the template context.
+    """
+    catalog = await _load_model_catalog()
+    return {
+        pid: catalog.get(pid, [])
+        for pid in provider_ids
+    }
+
+
+# Provider preset definitions.
+# Each entry contains display metadata and defaults for the UI.
+# The key is the internal provider id stored in ``llm_provider``.
+# Models are NOT listed here — they come from the opencode model catalog at
+# runtime (see :func:`get_provider_model_ids`).
+PROVIDER_PRESETS: Dict[str, Dict[str, Any]] = {
+    "openai": {
+        "name": "OpenAI",
+        "api_base": "https://api.openai.com/v1",
+        "requires_key": True,
+    },
+    "ollama": {
+        "name": "Ollama (local)",
+        "api_base": "http://localhost:11434/v1",
+        "requires_key": False,
+    },
+    "deepseek": {
+        "name": "DeepSeek",
+        "api_base": "https://api.deepseek.com/v1",
+        "requires_key": True,
+    },
+    "groq": {
+        "name": "Groq",
+        "api_base": "https://api.groq.com/openai/v1",
+        "requires_key": True,
+    },
+    "openrouter": {
+        "name": "OpenRouter",
+        "api_base": "https://openrouter.ai/api/v1",
+        "requires_key": True,
+    },
+    "opencode-go": {
+        "name": "OpenCode Go",
+        "api_base": "https://opencode.ai/zen/go/v1",
+        "requires_key": True,
+    },
+    # "custom" is handled specially (no preset api_base, requires user input)
+}
+
+# Legacy lookup derived from PROVIDER_PRESETS for backward compat.
+_PROVIDER_DEFAULTS: Dict[str, str] = {
+    pid: info["api_base"]
+    for pid, info in PROVIDER_PRESETS.items()
+    if info.get("api_base")
+}
+
+# Request timeout for LLM calls (seconds)
+_LLM_TIMEOUT = aiohttp.ClientTimeout(total=120)
+
+
+class LLMService:
+    """Centralized LLM API client.
+
+    All LLM-based enrichment features call through this service so
+    that BYOK config, retry logic, and error handling live in one place.
+    """
+
+    _instance: Optional["LLMService"] = None
+    _lock: asyncio.Lock = asyncio.Lock()
+
+    def __init__(self, settings_service) -> None:
+        self._settings = settings_service
+
+    # ------------------------------------------------------------------
+    # Singleton access
+    # ------------------------------------------------------------------
+
+    @classmethod
+    async def get_instance(cls) -> "LLMService":
+        """Return the lazily-initialised global ``LLMService`` instance."""
+
+        if cls._instance is None:
+            async with cls._lock:
+                if cls._instance is None:
+                    from .settings_manager import get_settings_manager
+
+                    cls._instance = cls(get_settings_manager())
+                    # Start preloading the model catalog in the background so
+                    # the settings UI never blocks on it.  The catalog is
+                    # cached after the first fetch (see _load_model_catalog).
+                    asyncio.create_task(_load_model_catalog())
+        return cls._instance
+
+    @classmethod
+    def reset_instance(cls) -> None:
+        """Reset the cached singleton — primarily for tests."""
+
+        cls._instance = None
+
+    # ------------------------------------------------------------------
+    # Configuration helpers
+    # ------------------------------------------------------------------
+
+    def _get_config(self) -> Dict[str, Any]:
+        """Read the current LLM configuration from settings."""
+
+        return {
+            "provider": self._settings.get("llm_provider", "openai"),
+            "api_key": self._settings.get("llm_api_key", ""),
+            "api_base": self._settings.get("llm_api_base", ""),
+            "model": self._settings.get("llm_model", ""),
+        }
+
+    @staticmethod
+    def _provider_requires_key(provider: str) -> bool:
+        """Return ``False`` when the given provider id does not need an API key."""
+        preset = PROVIDER_PRESETS.get(provider, {})
+        return bool(preset.get("requires_key", True))
+
+    def is_configured(self) -> bool:
+        """Return ``True`` when the LLM provider is minimally configured.
+
+        A provider is considered configured when ``llm_model`` is set,
+        an API key is configured for providers that require one (e.g.
+        Ollama does not), and an API base URL is set for providers that
+        have no preset default (e.g. ``custom``).
+        """
+
+        cfg = self._get_config()
+        has_model = bool(cfg["model"])
+        has_key = bool(cfg["api_key"]) or not self._provider_requires_key(cfg["provider"])
+        has_base = bool(cfg["api_base"]) or bool(_PROVIDER_DEFAULTS.get(cfg["provider"]))
+        return has_model and has_key and has_base
+
+    def _resolve_api_base(self, provider: str, api_base: str) -> str:
+        """Resolve the API base URL for the given provider.
+
+        If ``api_base`` is explicitly set (non-empty), it takes priority.
+        Otherwise the default from :data:`PROVIDER_PRESETS` is used.
+        """
+
+        if api_base:
+            return api_base.rstrip("/")
+        return _PROVIDER_DEFAULTS.get(provider, "").rstrip("/")
+
+    def _build_headers(self, api_key: str) -> Dict[str, str]:
+        """Build HTTP headers for the LLM API request."""
+
+        headers = {"Content-Type": "application/json"}
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+        return headers
+
+    def _ensure_configured(self) -> Dict[str, Any]:
+        """Validate configuration and return it, or raise.
+
+        A provider is considered configured when ``llm_model`` is set,
+        an API key is configured for providers that require one, and
+        an API base URL is set for providers without a preset default.
+        """
+
+        cfg = self._get_config()
+        has_model = bool(cfg["model"])
+        needs_key = self._provider_requires_key(cfg["provider"])
+        has_key = bool(cfg["api_key"]) or not needs_key
+        has_base = bool(cfg["api_base"]) or bool(_PROVIDER_DEFAULTS.get(cfg["provider"]))
+        if not (has_model and has_key and has_base):
+            parts = []
+            if not has_model:
+                parts.append("No LLM model specified")
+            if not has_key and needs_key:
+                parts.append("No LLM API key configured")
+            if not has_base:
+                parts.append(
+                    f"No API base URL for provider '{cfg['provider']}'"
+                )
+            detail = "; ".join(parts) if parts else "LLM provider is not configured"
+            raise LLMNotConfiguredError(
+                f"{detail}. Configure it in Settings → AI Provider."
+            )
+        return cfg
+
+    # ------------------------------------------------------------------
+    # Core API call
+    # ------------------------------------------------------------------
+
+    async def chat_completion(
+        self,
+        *,
+        messages: List[Dict[str, str]],
+        model: Optional[str] = None,
+        temperature: float = 0.3,
+        response_format: Optional[Dict[str, Any]] = None,
+        max_tokens: Optional[int] = None,
+        retry_on_rate_limit: bool = True,
+    ) -> Dict[str, Any]:
+        """Call the configured LLM provider's ``/chat/completions`` endpoint.
+
+        Args:
+            messages: OpenAI-format message list
+            model: Override the configured model name
+            temperature: Sampling temperature
+            response_format: Optional ``{"type": "json_object"}`` for structured output
+            max_tokens: Optional max output tokens
+            retry_on_rate_limit: Retry once after a 429 with backoff
+
+        Returns:
+            Dict with ``content`` (str), ``usage`` (dict), ``model`` (str)
+
+        Raises:
+            LLMNotConfiguredError: Provider not enabled / missing config
+            LLMRateLimitError: Rate limited and retry exhausted
+            LLMResponseError: Non-200 response or parse failure
+        """
+
+        cfg = self._ensure_configured()
+        api_base = self._resolve_api_base(cfg["provider"], cfg["api_base"])
+        model_name = model or cfg["model"]
+
+        is_ollama = cfg["provider"] == "ollama"
+
+        if is_ollama:
+            # Use Ollama's native /api/chat endpoint which does NOT expose
+            # a separate reasoning/thinking field (the model's full output
+            # lands directly in message.content).  The OpenAI-compatible
+            # endpoint splits thinking into the "reasoning" field, making
+            # content empty when thinking consumes all available tokens.
+            base = api_base.rstrip("/")
+            if base.endswith("/v1"):
+                base = base[:-3]
+            url = f"{base}/api/chat"
+        else:
+            url = f"{api_base}/chat/completions"
+
+        payload: Dict[str, Any]
+        if is_ollama:
+            payload = {
+                "model": model_name,
+                "messages": messages,
+                "stream": False,
+                # Suppress separate thinking trace — thinking still happens
+                # internally (accuracy preserved) but output goes directly to
+                # message.content instead of being split across content +
+                # thinking.  Without this the model can exhaust num_predict
+                # on thinking alone and leave content empty.
+                "think": False,
+                "options": {
+                    "temperature": temperature,
+                    # 8K context is sufficient for metadata enrichment
+                    # (prompt ~2-5K, output ~0.2-1K tokens).  The old 32K
+                    # value was excessive for this use case and increased
+                    # Ollama VRAM usage unnecessarily.
+                    "num_ctx": 8192,
+                },
+            }
+            if response_format is not None:
+                payload["format"] = "json"
+            if max_tokens is not None:
+                payload["options"]["num_predict"] = max_tokens
+        else:
+            payload = {
+                "model": model_name,
+                "messages": messages,
+                "temperature": temperature,
+            }
+            if response_format is not None:
+                payload["response_format"] = response_format
+            if max_tokens is not None:
+                payload["max_tokens"] = max_tokens
+
+        if is_ollama:
+            logger.info(
+                "Ollama request: model=%s num_ctx=%s num_predict=%s format=%s think=%s",
+                payload.get("model"),
+                payload.get("options", {}).get("num_ctx"),
+                payload.get("options", {}).get("num_predict"),
+                payload.get("format", "none"),
+                payload.get("think"),
+            )
+
+        headers = self._build_headers(cfg["api_key"])
+
+        attempt = 0
+        max_attempts = 2 if retry_on_rate_limit else 1
+        while attempt < max_attempts:
+            attempt += 1
+            try:
+                async with aiohttp.ClientSession(timeout=_LLM_TIMEOUT) as session:
+                    async with session.post(
+                        url, json=payload, headers=headers
+                    ) as resp:
+                        if resp.status == 429:
+                            if attempt < max_attempts:
+                                retry_after = float(
+                                    resp.headers.get("Retry-After", "5")
+                                )
+                                logger.warning(
+                                    "LLM rate limited, retrying after %.1fs",
+                                    retry_after,
+                                )
+                                await asyncio.sleep(retry_after)
+                                continue
+                            raise LLMRateLimitError(
+                                f"LLM provider rate limited (HTTP 429)",
+                                provider=cfg["provider"],
+                            )
+
+                        if resp.status != 200:
+                            body = await resp.text()
+                            raise LLMResponseError(
+                                f"LLM API returned HTTP {resp.status}: "
+                                f"{body[:500]}"
+                            )
+
+                        data = await resp.json()
+
+            except aiohttp.ClientError as exc:
+                raise LLMResponseError(f"Network error calling LLM API: {exc}") from exc
+
+            # Parse response
+            try:
+                if is_ollama:
+                    content = (data.get("message") or {}).get("content") or ""
+                    usage = {"completion_tokens": data.get("eval_count", 0)}
+                    finish_reason = data.get("done_reason", "")
+                    if not content:
+                        logger.warning(
+                            "LLM returned empty content. Provider=ollama, "
+                            "done_reason=%s, eval_count=%s",
+                            finish_reason,
+                            data.get("eval_count", 0),
+                        )
+                else:
+                    content = data["choices"][0]["message"].get("content") or ""
+                    usage = data.get("usage", {})
+                    if not content:
+                        logger.warning(
+                            "LLM returned empty content. Full response truncated: %s",
+                            json.dumps(data, ensure_ascii=False)[:1000],
+                        )
+                return {
+                    "content": content,
+                    "usage": usage,
+                    "model": data.get("model", model_name),
+                }
+            except (KeyError, IndexError) as exc:
+                raise LLMResponseError(
+                    f"Unexpected LLM response structure: {json.dumps(data)[:500]}"
+                ) from exc
+
+        # Should not reach here, but satisfy type checker
+        raise LLMRateLimitError("Rate limit retry exhausted", provider=cfg["provider"])
+
+    # ------------------------------------------------------------------
+    # Structured output convenience
+    # ------------------------------------------------------------------
+
+    async def chat_completion_json(
+        self,
+        *,
+        system_prompt: str,
+        user_prompt: str,
+        model: Optional[str] = None,
+        temperature: float = 0.3,
+        max_tokens: Optional[int] = None,
+    ) -> Dict[str, Any]:
+        """Call the LLM with ``response_format=json_object`` and return parsed JSON.
+
+        ``max_tokens`` is resolved in this order:
+        1. Explicit caller-supplied ``max_tokens``
+        2. Per-model ``limit.output`` from the model catalog
+        3. A safe default of 4096 (sufficient for metadata enrichment)
+
+        If the response content is empty or not valid JSON, attempts
+        :func:`_try_salvage_json` before raising.
+
+        Args:
+            system_prompt: System-level instructions
+            user_prompt: User-level query
+            model: Override the configured model name
+            temperature: Sampling temperature
+            max_tokens: Optional max output tokens
+
+        Returns:
+            Parsed JSON dict from the LLM response
+
+        Raises:
+            LLMNotConfiguredError: Provider not configured
+            LLMRateLimitError: Rate limited
+            LLMResponseError: Empty response or JSON parse failure
+        """
+
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_prompt},
+        ]
+
+        # Resolve max_tokens: caller override → catalog lookup → safe default
+        if max_tokens is None:
+            cfg = self._get_config()
+            effective_max = _get_model_max_output(cfg["provider"], cfg["model"])
+        else:
+            effective_max = max_tokens
+        if effective_max is None:
+            effective_max = 4096
+
+        result = await self.chat_completion(
+            messages=messages,
+            model=model,
+            temperature=temperature,
+            response_format={"type": "json_object"},
+            max_tokens=effective_max,
+        )
+
+        content = result.get("content", "") or ""
+        if not content:
+            raise LLMResponseError(
+                "LLM returned empty content in json_object mode. "
+                f"Raw response: {json.dumps(result)[:500]}"
+            )
+
+        try:
+            parsed = json.loads(content)
+            logger.debug(
+                "LLM raw content: %s",
+                json.dumps(parsed, ensure_ascii=False)[:2000],
+            )
+            return parsed
+        except (json.JSONDecodeError, TypeError) as exc:
+            logger.info(
+                "LLM raw response (first 800 chars): %s",
+                content[:800],
+            )
+
+        # Last resort: attempt to salvage partial/truncated JSON
+        salvaged = _try_salvage_json(content)
+        if salvaged is not None:
+            logger.warning(
+                "LLM JSON salvaged from partial content (%d chars raw)",
+                len(content),
+            )
+            return salvaged
+
+        raise LLMResponseError(
+            f"LLM response could not be parsed as JSON: {content[:200]}"
+        )
+
+
+def _try_salvage_json(raw: str) -> Dict[str, Any] | None:
+    """Attempt to repair and parse a truncated JSON string.
+
+    Handles common truncation patterns:
+
+    * Incomplete string value at the end (``"foo`` → ``"foo"``)
+    * Missing closing ``}`` or ``]`` (respecting nesting order)
+    * Trailing comma before closing bracket
+    * Extra text after the JSON object (e.g. markdown fences)
+
+    Returns the parsed dict on success, ``None`` if repair is impossible.
+    """
+    if not raw:
+        return None
+
+    text = raw.strip()
+
+    # Strip markdown fences if the LLM wrapped the JSON
+    if text.startswith("```"):
+        end = text.find("\n")
+        text = text[end + 1:] if end != -1 else text[3:]
+    if text.endswith("```"):
+        text = text[:-3].rstrip()
+
+    # Find the first '{' and strip everything before it
+    start = text.find("{")
+    if start == -1:
+        return None
+    text = text[start:]
+
+    # Try to close an incomplete string at the end (e.g. ``"https://huggingf``)
+    # Pattern: ends mid-string (last quote is open)
+    if text.count('"') % 2 == 1:
+        text += '"'
+
+    # Ensure trailing commas before closing braces work
+    text = _strip_trailing_commas(text)
+
+    # Walk through the text character by character to find unclosed
+    # brackets and close them in the correct (LIFO) order.
+    # We ignore brackets inside quoted strings.
+    stack: list[str] = []
+    in_string = False
+    escape = False
+    for ch in text:
+        if escape:
+            escape = False
+            continue
+        if ch == "\\":
+            escape = True
+            continue
+        if ch == '"':
+            in_string = not in_string
+            continue
+        if in_string:
+            continue
+        if ch in ("{", "["):
+            stack.append(ch)
+        elif ch == "}":
+            if stack and stack[-1] == "{":
+                stack.pop()
+            else:
+                return None  # Unmatched closer — unrecoverable
+        elif ch == "]":
+            if stack and stack[-1] == "[":
+                stack.pop()
+            else:
+                return None
+
+    # Close remaining open brackets in reverse order
+    for opener in reversed(stack):
+        text += "}" if opener == "{" else "]"
+
+    try:
+        return json.loads(text)
+    except (json.JSONDecodeError, ValueError):
+        return None
+
+
+def _strip_trailing_commas(text: str) -> str:
+    """Remove commas that appear before a closing brace/bracket."""
+    import re as _re
+    text = _re.sub(r",\s*}", "}", text)
+    text = _re.sub(r",\s*]", "]", text)
+    return text

py/services/lora_service.py

@@ -5,6 +5,7 @@ from typing import Dict, List, Optional
 
 from .base_model_service import BaseModelService
 from .model_query import resolve_sub_type
+from .auto_tag_service import extract_auto_tags
 from ..utils.models import LoraMetadata
 from ..config import config
 
@@ -23,23 +24,41 @@ class LoraService(BaseModelService):
         """
         super().__init__("lora", scanner, LoraMetadata, update_service=update_service)
 
-    async def format_response(self, lora_data: Dict) -> Dict:
-        """Format LoRA data for API response"""
+    async def format_response(self, lora_data: Dict) -> Optional[Dict]:
+        """Format LoRA data for API response.
+
+        Returns None when the entry is missing critical fields (corrupted cache
+        row), so the handler layer can filter it out instead of crashing the
+        whole listing request. See issue #730.
+        """
+        # Guard against corrupted cache entries missing critical fields
+        file_path = lora_data.get("file_path")
+        if not file_path or not isinstance(file_path, str):
+            logger.warning(
+                "Skipping corrupted LoRA entry (missing file_path): %s",
+                lora_data.get("file_name", "<unknown>"),
+            )
+            return None
+
         # Resolve sub_type using priority: sub_type > model_type > civitai.model.type > default
         # Normalize to lowercase for consistent API responses
         sub_type = resolve_sub_type(lora_data).lower()
 
+        file_name = lora_data.get("file_name") or ""
+        model_name = lora_data.get("model_name") or file_name
+        folder = lora_data.get("folder") or ""
+
         return {
-            "model_name": lora_data["model_name"],
-            "file_name": lora_data["file_name"],
+            "model_name": model_name,
+            "file_name": file_name,
             "preview_url": config.get_preview_static_url(
                 lora_data.get("preview_url", "")
             ),
             "preview_nsfw_level": lora_data.get("preview_nsfw_level", 0),
             "base_model": lora_data.get("base_model", ""),
-            "folder": lora_data["folder"],
+            "folder": folder,
             "sha256": lora_data.get("sha256", ""),
-            "file_path": lora_data["file_path"].replace(os.sep, "/"),
+            "file_path": file_path.replace(os.sep, "/"),
             "file_size": lora_data.get("size", 0),
             "modified": lora_data.get("modified", ""),
             "tags": lora_data.get("tags", []),
@@ -48,6 +67,7 @@ class LoraService(BaseModelService):
             "usage_tips": lora_data.get("usage_tips", ""),
             "notes": lora_data.get("notes", ""),
             "favorite": lora_data.get("favorite", False),
+            "exclude": bool(lora_data.get("exclude", False)),
             "update_available": bool(lora_data.get("update_available", False)),
             "skip_metadata_refresh": bool(
                 lora_data.get("skip_metadata_refresh", False)
@@ -56,6 +76,9 @@ class LoraService(BaseModelService):
             "civitai": self.filter_civitai_data(
                 lora_data.get("civitai", {}), minimal=True
             ),
+            "auto_tags": lora_data.get("auto_tags") or extract_auto_tags(lora_data),
+            "version_count": lora_data.get("version_count"),
+            "hf_url": lora_data.get("hf_url", ""),
         }
 
     async def _apply_specific_filters(self, data: List[Dict], **kwargs) -> List[Dict]:
@@ -248,12 +271,16 @@ class LoraService(BaseModelService):
         return letters
 
     async def get_lora_trigger_words(self, lora_name: str) -> List[str]:
-        """Get trigger words for a specific LoRA file"""
+        """Get trigger words for a specific LoRA file.
+
+        Supports both simple names and full-path syntax.
+        """
         cache = await self.scanner.get_cached_data()
 
         for lora in cache.raw_data:
-            if lora["file_name"] == lora_name:
-                civitai_data = lora.get("civitai", {})
+            file_name = lora.get("file_name", "")
+            if file_name == lora_name or lora_name.endswith("/" + file_name) or lora_name.endswith("\\" + file_name):
+                civitai_data = lora.get("civitai") or {}
                 return civitai_data.get("trainedWords", [])
 
         return []
@@ -309,8 +336,23 @@ class LoraService(BaseModelService):
         """Return cached raw metadata for a LoRA matching the given filename."""
         cache = await self.scanner.get_cached_data(force_refresh=False)
 
+        fn_normalized = filename.replace("\\", "/")
+        fn_no_ext = fn_normalized
+        for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+            if fn_no_ext.lower().endswith(ext):
+                fn_no_ext = fn_no_ext[: -len(ext)]
+                break
+
         for lora in cache.raw_data if cache else []:
-            if lora.get("file_name") == filename:
+            file_name = lora.get("file_name", "")
+            folder = lora.get("folder", "")
+            file_name_no_ext = file_name
+            for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+                if file_name_no_ext.lower().endswith(ext):
+                    file_name_no_ext = file_name_no_ext[: -len(ext)]
+                    break
+            path_name = f"{folder}/{file_name_no_ext}".replace("\\", "/") if folder else file_name_no_ext
+            if fn_no_ext in (file_name_no_ext, path_name):
                 return lora
 
         return None
@@ -398,7 +440,10 @@ class LoraService(BaseModelService):
             locked_loras = locked_loras[:target_count]
 
         # Filter out locked LoRAs from available pool
-        locked_names = {lora["name"] for lora in locked_loras}
+        locked_names = {
+            os.path.basename(lora["name"]) if "/" in str(lora.get("name", "")) else lora["name"]
+            for lora in locked_loras
+        }
         available_pool = [
             l for l in available_loras if l["file_name"] not in locked_names
         ]
@@ -453,7 +498,7 @@ class LoraService(BaseModelService):
 
             result_loras.append(
                 {
-                    "name": lora["file_name"],
+                    "name": f"{lora['folder']}/{lora['file_name']}" if lora.get("folder") else lora["file_name"],
                     "strength": model_str,
                     "clipStrength": clip_str,
                     "active": True,
@@ -669,8 +714,9 @@ class LoraService(BaseModelService):
         # Return minimal data needed for cycling
         return [
             {
-                "file_name": lora["file_name"],
+                "file_name": f"{lora['folder']}/{lora['file_name']}" if lora.get("folder") else lora["file_name"],
                 "model_name": lora.get("model_name", lora["file_name"]),
+                "folder": lora.get("folder", ""),
             }
             for lora in available_loras
         ]

py/services/metadata_service.py

@@ -15,6 +15,17 @@ from .service_registry import ServiceRegistry
 
 logger = logging.getLogger(__name__)
 
+_PROVIDER_DISPLAY_NAMES = {
+    "civitai_api": "CivitAI",
+    "civarchive_api": "CivArchive",
+    "sqlite": "Archive DB",
+}
+
+_PRESET_PROVIDER_ORDERS = {
+    "civitai_archive_sqlite": ["civitai_api", "civarchive_api", "sqlite"],
+    "civitai_sqlite_archive": ["civitai_api", "sqlite", "civarchive_api"],
+}
+
 async def initialize_metadata_providers():
     """Initialize and configure all metadata providers based on settings"""
     provider_manager = await ModelMetadataProviderManager.get_instance()
@@ -26,7 +37,9 @@ async def initialize_metadata_providers():
     # Get settings
     settings_manager = get_settings_manager()
     enable_archive_db = settings_manager.get('enable_metadata_archive_db', False)
-    
+    enable_civarchive_api = settings_manager.get('enable_civarchive_api', True)
+    provider_order = settings_manager.get('metadata_provider_order', 'civitai_archive_sqlite')
+
     providers = []
     
     # Initialize archive database provider if enabled
@@ -59,27 +72,48 @@ async def initialize_metadata_providers():
     except Exception as e:
         logger.error(f"Failed to initialize Civitai API metadata provider: {e}")
 
-    # Register CivArchive provider, and all add to fallback providers
-    try:
-        civarchive_client = await ServiceRegistry.get_civarchive_client()
-        civarchive_provider = CivArchiveModelMetadataProvider(civarchive_client)
-        provider_manager.register_provider('civarchive_api', civarchive_provider)
-        providers.append(('civarchive_api', civarchive_provider))
-        logger.debug("CivArchive metadata provider registered (also included in fallback)")
-    except Exception as e:
-        logger.error(f"Failed to initialize CivArchive metadata provider: {e}")
+    # Register CivArchive provider when enabled. Civitai API is always
+    # preferred (better metadata); CivArchive mainly recovers metadata for
+    # models deleted from Civitai, so it can be turned off to avoid its long
+    # rate-limit windows entirely.
+    if enable_civarchive_api:
+        try:
+            civarchive_client = await ServiceRegistry.get_civarchive_client()
+            civarchive_provider = CivArchiveModelMetadataProvider(civarchive_client)
+            provider_manager.register_provider('civarchive_api', civarchive_provider)
+            providers.append(('civarchive_api', civarchive_provider))
+            logger.debug("CivArchive metadata provider registered (also included in fallback)")
+        except Exception as e:
+            logger.error(f"Failed to initialize CivArchive metadata provider: {e}")
+    else:
+        logger.debug("CivArchive metadata provider disabled by setting 'enable_civarchive_api'")
+
+    # Preset fallback orderings (see module-level _PRESET_PROVIDER_ORDERS).
+    # civitai_api is always first (better metadata); the remaining providers
+    # are arranged by the configured preset.  Providers that are not
+    # registered (disabled/unavailable) are simply skipped, so each preset
+    # degrades gracefully.
+    desired_order = _PRESET_PROVIDER_ORDERS.get(
+        provider_order, _PRESET_PROVIDER_ORDERS["civitai_archive_sqlite"]
+    )
 
     # Set up fallback provider based on available providers
     if len(providers) > 1:
-        # Always use Civitai API (it has better metadata), then CivArchive API, then Archive DB
         ordered_providers: list[tuple[str, ModelMetadataProvider]] = []
-        ordered_providers.extend([p for p in providers if p[0] == 'civitai_api'])
-        ordered_providers.extend([p for p in providers if p[0] == 'civarchive_api'])
-        ordered_providers.extend([p for p in providers if p[0] == 'sqlite'])
-        
+        for name in desired_order:
+            ordered_providers.extend([p for p in providers if p[0] == name])
+        # Include any provider not covered by the preset (defensive) at the end
+        for p in providers:
+            if p not in ordered_providers:
+                ordered_providers.append(p)
+
         if ordered_providers:
             fallback_provider = FallbackMetadataProvider(ordered_providers)
             provider_manager.register_provider('fallback', fallback_provider, is_default=True)
+            logger.debug(
+                "Metadata fallback provider order: %s",
+                ", ".join(name for name, _ in ordered_providers),
+            )
     elif len(providers) == 1:
         # Only one provider available, set it as default
         provider_name, provider = providers[0]
@@ -96,11 +130,30 @@ async def update_metadata_providers():
         # Get current settings
         settings_manager = get_settings_manager()
         enable_archive_db = settings_manager.get('enable_metadata_archive_db', False)
+        enable_civarchive_api = settings_manager.get('enable_civarchive_api', True)
+        provider_order = settings_manager.get('metadata_provider_order', 'civitai_archive_sqlite')
         
         # Reinitialize all providers with new settings
         provider_manager = await initialize_metadata_providers()
         
-        logger.info(f"Updated metadata providers, archive_db enabled: {enable_archive_db}")
+        # Build effective provider chain for logging (use actually-registered
+        # providers, not just settings, so a failed init is reflected correctly)
+        registered = set(provider_manager.providers.keys())
+        desired = _PRESET_PROVIDER_ORDERS.get(
+            provider_order, _PRESET_PROVIDER_ORDERS["civitai_archive_sqlite"]
+        )
+        chain = " → ".join(
+            _PROVIDER_DISPLAY_NAMES[p]
+            for p in desired
+            if p in registered and p in _PROVIDER_DISPLAY_NAMES
+        )
+        
+        logger.info(
+            "Updated metadata providers: archive_db=%s, civarchive_api=%s, chain=%s",
+            enable_archive_db,
+            enable_civarchive_api,
+            chain,
+        )
         return provider_manager
     except Exception as e:
         logger.error(f"Failed to update metadata providers: {e}")

py/services/metadata_sync_service.py

@@ -11,6 +11,7 @@ from typing import Any, Awaitable, Callable, Dict, Iterable, Optional
 from ..services.settings_manager import SettingsManager
 from ..utils.civitai_utils import resolve_license_payload
 from ..utils.model_utils import determine_base_model
+from .connectivity_guard import OFFLINE_FRIENDLY_MESSAGE, is_expected_offline_error
 from .errors import RateLimitError
 
 logger = logging.getLogger(__name__)
@@ -208,20 +209,40 @@ class MetadataSyncService:
                         error_msg = "CivitAI model is deleted and no archive provider is available"
                     return False, error_msg
             else:
-                provider_attempts.append((None, await self._get_default_provider()))
+                is_hf_source = bool(model_data.get("hf_url"))
+                if is_hf_source:
+                    # HF-sourced model: only check CivitAI API directly.
+                    # CivArchive is almost guaranteed to have no record, and
+                    # hitting it wastes rate-limit budget.
+                    # Use a distinct provider name ("civitai_api" not None) so
+                    # downstream code does NOT interpret a "Model not found"
+                    # response as civitai_api_not_found — which would mark the
+                    # model civitai_deleted=True when it was never on CivitAI.
+                    try:
+                        provider_attempts.append(("civitai_api", await self._get_provider("civitai_api")))
+                    except Exception as exc:  # pragma: no cover - provider resolution fault
+                        logger.debug("Unable to resolve civitai_api provider: %s", exc)
+                if not provider_attempts:
+                    provider_attempts.append((None, await self._get_default_provider()))
 
             civitai_metadata: Optional[Dict[str, Any]] = None
             metadata_provider: Optional[MetadataProviderProtocol] = None
             provider_used: Optional[str] = None
             last_error: Optional[str] = None
             civitai_api_not_found = False
+            any_rate_limited = False
 
             for provider_name, provider in provider_attempts:
                 try:
                     civitai_metadata_candidate, error = await provider.get_model_by_hash(sha256)
                 except RateLimitError as exc:
-                    exc.provider = exc.provider or (provider_name or provider.__class__.__name__)
-                    raise
+                    logger.warning(
+                        "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                        provider_name or provider.__class__.__name__,
+                        exc.retry_after or 0,
+                    )
+                    any_rate_limited = True
+                    continue
                 except Exception as exc:  # pragma: no cover - defensive logging
                     logger.error("Provider %s failed for hash %s: %s", provider_name, sha256, exc)
                     civitai_metadata_candidate, error = None, str(exc)
@@ -257,6 +278,14 @@ class MetadataSyncService:
                     model_data["last_checked_at"] = datetime.now().timestamp()
                     needs_save = True
 
+                # When the model was already classified as "not on CivitAI" via
+                # .metadata.json (civitai_deleted=True) but the SQLite cache is
+                # stale (because the pre-fix code never persisted these flags),
+                # ensure the flags are written to the scanner cache + SQLite.
+                if not needs_save and model_data.get("civitai_deleted") is True:
+                    model_data["last_checked_at"] = datetime.now().timestamp()
+                    needs_save = True
+
                 # Save metadata if any state was updated
                 if needs_save:
                     data_to_save = model_data.copy()
@@ -265,6 +294,7 @@ class MetadataSyncService:
                     if "last_checked_at" not in data_to_save:
                         data_to_save["last_checked_at"] = datetime.now().timestamp()
                     await self._metadata_manager.save_metadata(file_path, data_to_save)
+                    await update_cache_func(file_path, file_path, data_to_save)
 
                 default_error = (
                     "CivitAI model is deleted and metadata archive DB is not enabled"
@@ -274,11 +304,19 @@ class MetadataSyncService:
                     else "No provider returned metadata"
                 )
 
+                resolved_error = last_error or default_error
+                if any_rate_limited and "Rate limited" not in resolved_error:
+                    resolved_error = "Rate limited"
+                if is_expected_offline_error(resolved_error):
+                    resolved_error = OFFLINE_FRIENDLY_MESSAGE
+
                 error_msg = (
-                    f"Error fetching metadata: {last_error or default_error} "
-                    f"(model_name={model_data.get('model_name', '')})"
+                    f"Error fetching metadata: {resolved_error} "
+                    f"(file={os.path.basename(file_path)}, sha256={sha256})"
                 )
-                logger.error(error_msg)
+                # Use case layer (BulkMetadataRefreshUseCase) logs failed models at WARNING level,
+                # so this level is demoted to DEBUG to avoid duplicate user-visible logging.
+                logger.debug(error_msg)
                 return False, error_msg
 
             model_data["from_civitai"] = True
@@ -347,6 +385,9 @@ class MetadataSyncService:
             return False, error_msg
         except Exception as exc:  # pragma: no cover - error path
             error_msg = f"Error fetching metadata: {exc}"
+            if is_expected_offline_error(str(exc)):
+                logger.info(OFFLINE_FRIENDLY_MESSAGE)
+                return False, OFFLINE_FRIENDLY_MESSAGE
             logger.error(error_msg, exc_info=True)
             return False, error_msg
 
@@ -400,7 +441,18 @@ class MetadataSyncService:
         metadata = await metadata_loader(metadata_path)
 
         for key, value in updates.items():
-            if isinstance(value, dict) and isinstance(metadata.get(key), dict):
+            if key == "tags" and isinstance(value, list):
+                # Normalize tags: trim, lowercase, deduplicate
+                normalized = []
+                seen = set()
+                for tag in value:
+                    if isinstance(tag, str):
+                        t = tag.strip().lower()
+                        if t and t not in seen:
+                            normalized.append(t)
+                            seen.add(t)
+                metadata[key] = normalized
+            elif isinstance(value, dict) and isinstance(metadata.get(key), dict):
                 metadata[key].update(value)
             else:
                 metadata[key] = value

py/services/model_cache.py

@@ -18,6 +18,8 @@ SUPPORTED_SORT_MODES = [
     ('size', 'desc'),
     ('usage', 'asc'),
     ('usage', 'desc'),
+    ('versions_count', 'asc'),
+    ('versions_count', 'desc'),
 ]
 # Is this in use?
 
@@ -263,6 +265,17 @@ class ModelCache:
                 ),
                 reverse=reverse
             )
+        elif sort_key == 'versions_count':
+            # Pre-dedup sort: fall back to name sort.
+            # Actual re-sort by version_count happens in get_paginated_data after dedup.
+            result = natsorted(
+                data,
+                key=lambda x: (
+                    self._get_display_name(x).lower(),
+                    x.get('file_path', '').lower()
+                ),
+                reverse=reverse
+            )
         else:
             # Fallback: no sort
             result = list(data)
@@ -324,4 +337,25 @@ class ModelCache:
             else:
                 return False  # Model not found
                     
-            return True
+            return True
+
+    async def clear_preview_by_path(self, preview_file_path: str) -> int:
+        """Clear ``preview_url`` for every cached entry referencing a file path.
+
+        When a preview file has been deleted from disk, this removes its
+        reference from all matching cache entries so the next list-API
+        response returns an empty ``preview_url`` instead of a stale URL
+        that produces 404s.
+
+        Returns the number of entries that were updated.
+        """
+        normalized = preview_file_path.replace("\\", "/")
+        cleared = 0
+        async with self._lock:
+            for item in self.raw_data:
+                cached_url = item.get("preview_url", "")
+                if cached_url.replace("\\", "/") == normalized:
+                    item["preview_url"] = ""
+                    item["preview_nsfw_level"] = 0
+                    cleared += 1
+        return cleared

py/services/model_hash_index.py

@@ -7,6 +7,7 @@ class ModelHashIndex:
     def __init__(self):
         self._hash_to_path: Dict[str, str] = {}
         self._filename_to_hash: Dict[str, str] = {}
+        self._autov2_to_path: Dict[str, str] = {}
         # New data structures for tracking duplicates
         self._duplicate_hashes: Dict[str, List[str]] = {}  # sha256 -> list of paths
         self._duplicate_filenames: Dict[str, List[str]] = {}  # filename -> list of paths
@@ -63,6 +64,9 @@ class ModelHashIndex:
         # Add new mappings
         self._hash_to_path[sha256] = file_path
         self._filename_to_hash[filename] = sha256
+        # AutoV2 = first 10 chars of SHA256
+        if len(sha256) >= 10:
+            self._autov2_to_path[sha256[:10]] = file_path
     
     def _get_filename_from_path(self, file_path: str) -> str:
         """Extract filename without extension from path"""
@@ -79,6 +83,12 @@ class ModelHashIndex:
                     hash_val = h
                     break
         
+        if hash_val is None:
+            for h, paths in self._duplicate_hashes.items():
+                if file_path in paths:
+                    hash_val = h
+                    break
+        
         # If we didn't find a hash, nothing to do
         if not hash_val:
             return
@@ -151,7 +161,12 @@ class ModelHashIndex:
                 del self._duplicate_filenames[filename]
                 if filename in self._filename_to_hash:
                     del self._filename_to_hash[filename]
-    
+
+        # Remove from AutoV2 index
+        autov2_keys_to_remove = [k for k, v in self._autov2_to_path.items() if v == file_path]
+        for k in autov2_keys_to_remove:
+            del self._autov2_to_path[k]
+
     def remove_by_hash(self, sha256: str) -> None:
         """Remove entry by hash"""
         sha256 = sha256.lower()
@@ -171,6 +186,10 @@ class ModelHashIndex:
         # Remove hash-to-path mapping
         del self._hash_to_path[sha256]
         
+        autov2_key = sha256[:10]
+        if autov2_key in self._autov2_to_path:
+            del self._autov2_to_path[autov2_key]
+        
         # Update filename-to-hash and duplicate filenames for all paths
         for path_to_remove in paths_to_remove:
             fname = self._get_filename_from_path(path_to_remove)
@@ -189,13 +208,24 @@ class ModelHashIndex:
                     # If only one entry remains, it's no longer a duplicate
                     del self._duplicate_filenames[fname]
     
-    def has_hash(self, sha256: str) -> bool:
-        """Check if hash exists in index"""
-        return sha256.lower() in self._hash_to_path
-    
-    def get_path(self, sha256: str) -> Optional[str]:
-        """Get file path for a hash"""
-        return self._hash_to_path.get(sha256.lower())
+    def has_hash(self, hash_value: str) -> bool:
+        """Check if hash exists in index (SHA256 or AutoV2)"""
+        normalized = hash_value.lower()
+        if normalized in self._hash_to_path:
+            return True
+        if len(normalized) == 10:
+            return normalized in self._autov2_to_path
+        return False
+
+    def get_path(self, hash_value: str) -> Optional[str]:
+        """Get file path for a hash (SHA256 or AutoV2)"""
+        normalized = hash_value.lower()
+        path = self._hash_to_path.get(normalized)
+        if path is not None:
+            return path
+        if len(normalized) == 10:
+            return self._autov2_to_path.get(normalized)
+        return None
     
     def get_hash(self, file_path: str) -> Optional[str]:
         """Get hash for a file path"""
@@ -203,13 +233,16 @@ class ModelHashIndex:
         return self._filename_to_hash.get(filename)
     
     def get_hash_by_filename(self, filename: str) -> Optional[str]:
-        """Get hash for a filename without extension"""
+        """Get hash for a filename (bare basename or path-prefixed name)"""
+        if "/" in filename or "\\" in filename:
+            filename = os.path.splitext(os.path.basename(filename.replace("\\", "/")))[0]
         return self._filename_to_hash.get(filename)
     
     def clear(self) -> None:
         """Clear all entries"""
         self._hash_to_path.clear()
         self._filename_to_hash.clear()
+        self._autov2_to_path.clear()
         self._duplicate_hashes.clear()
         self._duplicate_filenames.clear()
     

py/services/model_lifecycle_service.py

@@ -8,6 +8,7 @@ from typing import Any, Awaitable, Callable, Dict, Iterable, List, Mapping, Opti
 
 from ..services.service_registry import ServiceRegistry
 from ..utils.constants import PREVIEW_EXTENSIONS
+from ..utils.metadata_manager import MetadataManager
 
 logger = logging.getLogger(__name__)
 
@@ -110,6 +111,11 @@ class ModelLifecycleService:
             self._scanner._hash_index.remove_by_path(file_path)
 
         await self._sync_update_for_model(model_id)
+
+        persist_current_cache = getattr(self._scanner, "_persist_current_cache", None)
+        if callable(persist_current_cache):
+            await persist_current_cache()
+
         return {"success": True, "deleted_files": deleted_files}
 
     @staticmethod
@@ -207,11 +213,56 @@ class ModelLifecycleService:
 
         excluded = getattr(self._scanner, "_excluded_models", None)
         if isinstance(excluded, list):
-            excluded.append(file_path)
+            if file_path not in excluded:
+                excluded.append(file_path)
+
+        persist_current_cache = getattr(self._scanner, "_persist_current_cache", None)
+        if callable(persist_current_cache):
+            await persist_current_cache()
 
         message = f"Model {os.path.basename(file_path)} excluded"
         return {"success": True, "message": message}
 
+    async def unexclude_model(self, file_path: str) -> Dict[str, object]:
+        """Restore a previously excluded model to the active cache."""
+
+        if not file_path:
+            raise ValueError("Model path is required")
+
+        if not os.path.exists(file_path):
+            raise ValueError("Model file does not exist")
+
+        metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
+        metadata_payload = await self._metadata_loader(metadata_path)
+        metadata_payload["exclude"] = False
+
+        await self._metadata_manager.save_metadata(file_path, metadata_payload)
+
+        metadata, should_skip = await MetadataManager.load_metadata(
+            file_path,
+            self._scanner.model_class,
+        )
+        if should_skip:
+            metadata = None
+        if metadata is None:
+            metadata = metadata_payload
+
+        excluded = getattr(self._scanner, "_excluded_models", None)
+        if isinstance(excluded, list):
+            self._scanner._excluded_models = [
+                path for path in excluded if path != file_path
+            ]
+
+        await self._scanner.update_single_model_cache(
+            file_path,
+            file_path,
+            metadata,
+            recalculate_type=True,
+        )
+
+        message = f"Model {os.path.basename(file_path)} restored"
+        return {"success": True, "message": message}
+
     async def bulk_delete_models(self, file_paths: Iterable[str]) -> Dict[str, object]:
         """Delete a collection of models via the scanner bulk operation."""
 

py/services/model_metadata_provider.py

@@ -5,7 +5,7 @@ import logging
 import random
 from typing import Optional, Dict, Tuple, Any, List, Sequence
 from .downloader import get_downloader
-from .errors import RateLimitError
+from .errors import RateLimitError, ResourceNotFoundError
 
 try:
     from bs4 import BeautifulSoup
@@ -65,7 +65,14 @@ class _RateLimitRetryHelper:
                 return await func(*args, **kwargs)
             except RateLimitError as exc:
                 attempt += 1
-                if attempt >= self._retry_limit:
+
+                # Determine effective retry limit based on rate-limit magnitude
+                effective_retry_limit = self._retry_limit  # default: 3
+                if exc.retry_after is not None and exc.retry_after >= 120.0:
+                    # Long rate-limit window (>=2 min) — retries are futile
+                    effective_retry_limit = 1  # total 1 attempt = 0 retries
+
+                if attempt >= effective_retry_limit:
                     exc.provider = exc.provider or label
                     raise
 
@@ -81,7 +88,11 @@ class _RateLimitRetryHelper:
 
     def _calculate_delay(self, retry_after: Optional[float], attempt: int) -> float:
         if retry_after is not None:
-            return min(self._max_delay, max(0.0, retry_after))
+            # Cap at 1800s (30 min) as a safety ceiling. The old 30s cap was
+            # too low — CivArchive can return retry_after ~1500s, causing all
+            # retries to fail. A generous ceiling protects against pathological
+            # server values while still respecting the server's guidance.
+            return min(1800.0, max(0.0, retry_after))
 
         base_delay = self._base_delay * (2 ** max(0, attempt - 1))
         jitter_span = base_delay * self._jitter_ratio
@@ -108,6 +119,18 @@ class ModelMetadataProvider(ABC):
     ) -> Optional[Dict[int, Dict]]:
         """Fetch model versions for multiple model ids when supported."""
         raise NotImplementedError
+
+    async def get_model_versions_by_hashes(
+        self, hashes: List[str]
+    ) -> Optional[List[Dict]]:
+        """Fetch full version details for multiple SHA256 hashes.
+
+        Used specifically to retrieve ``usageControl`` which is only
+        available from the per-version / by-hash API, not from model-level
+        responses.  Providers that cannot resolve hashes should let the
+        default ``NotImplementedError`` propagate.
+        """
+        raise NotImplementedError
         
     @abstractmethod
     async def get_model_version(self, model_id: int = None, version_id: int = None) -> Optional[Dict]:
@@ -140,6 +163,11 @@ class CivitaiModelMetadataProvider(ModelMetadataProvider):
         self, model_ids: Sequence[int]
     ) -> Optional[Dict[int, Dict]]:
         return await self.client.get_model_versions_bulk(model_ids)
+
+    async def get_model_versions_by_hashes(
+        self, hashes: List[str]
+    ) -> Optional[List[Dict]]:
+        return await self.client.get_model_versions_by_hashes(hashes)
         
     async def get_model_version(self, model_id: int = None, version_id: int = None) -> Optional[Dict]:
         return await self.client.get_model_version(model_id, version_id)
@@ -457,14 +485,19 @@ class FallbackMetadataProvider(ModelMetadataProvider):
                 if result:
                     return result, error
             except RateLimitError as exc:
-                exc.provider = exc.provider or label
-                raise exc
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
             except Exception as e:
                 logger.debug("Provider %s failed for get_model_by_hash: %s", label, e)
                 continue
         return None, "Model not found"
 
     async def get_model_versions(self, model_id: str) -> Optional[Dict]:
+        not_found_confirmed = False
         for provider, label in self._iter_providers():
             try:
                 result = await self._call_with_rate_limit(
@@ -475,8 +508,20 @@ class FallbackMetadataProvider(ModelMetadataProvider):
                 if result:
                     return result
             except RateLimitError as exc:
-                exc.provider = exc.provider or label
-                raise exc
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
+            except ResourceNotFoundError:
+                not_found_confirmed = True
+                logger.debug(
+                    "Provider %s reports model %s as not found",
+                    label,
+                    model_id,
+                )
+                continue
             except Exception as e:
                 logger.debug("Provider %s failed for get_model_versions: %s", label, e)
                 continue
@@ -494,8 +539,12 @@ class FallbackMetadataProvider(ModelMetadataProvider):
                 if result:
                     return result
             except RateLimitError as exc:
-                exc.provider = exc.provider or label
-                raise exc
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
             except Exception as e:
                 logger.debug("Provider %s failed for get_model_version: %s", label, e)
                 continue
@@ -512,13 +561,47 @@ class FallbackMetadataProvider(ModelMetadataProvider):
                 if result:
                     return result, error
             except RateLimitError as exc:
-                exc.provider = exc.provider or label
-                raise exc
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
             except Exception as e:
                 logger.debug("Provider %s failed for get_model_version_info: %s", label, e)
                 continue
         return None, "No provider could retrieve the data"
 
+    async def get_model_versions_by_hashes(
+        self, hashes: List[str]
+    ) -> Optional[List[Dict]]:
+        for provider, label in self._iter_providers():
+            try:
+                result = await self._call_with_rate_limit(
+                    label,
+                    provider.get_model_versions_by_hashes,
+                    hashes,
+                )
+                if result is not None:
+                    return result
+            except NotImplementedError:
+                continue
+            except RateLimitError as exc:
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
+            except Exception as e:
+                logger.debug(
+                    "Provider %s failed for get_model_versions_by_hashes: %s",
+                    label,
+                    e,
+                )
+                continue
+        return None
+
     async def get_user_models(self, username: str) -> Optional[List[Dict]]:
         for provider, label in self._iter_providers():
             try:
@@ -530,8 +613,12 @@ class FallbackMetadataProvider(ModelMetadataProvider):
                 if result is not None:
                     return result
             except RateLimitError as exc:
-                exc.provider = exc.provider or label
-                raise exc
+                logger.warning(
+                    "Provider %s is rate-limited (retry_after=%.0fs); skipping to next provider",
+                    label,
+                    exc.retry_after or 0,
+                )
+                continue
             except Exception as e:
                 logger.debug("Provider %s failed for get_user_models: %s", label, e)
                 continue
@@ -593,6 +680,15 @@ class RateLimitRetryingProvider(ModelMetadataProvider):
             model_ids,
         )
 
+    async def get_model_versions_by_hashes(
+        self, hashes: List[str]
+    ) -> Optional[List[Dict]]:
+        return await self._rate_limit_helper.run(
+            self._label,
+            self._provider.get_model_versions_by_hashes,
+            hashes,
+        )
+
     async def get_model_version(self, model_id: int = None, version_id: int = None) -> Optional[Dict]:
         return await self._rate_limit_helper.run(
             self._label,
@@ -669,6 +765,17 @@ class ModelMetadataProviderManager:
         provider = self._get_provider(provider_name)
         return await provider.get_model_version_info(version_id)
 
+    async def get_model_versions_by_hashes(
+        self,
+        hashes: List[str],
+        provider_name: str = None,
+    ) -> Optional[List[Dict]]:
+        provider = self._get_provider(provider_name)
+        try:
+            return await provider.get_model_versions_by_hashes(hashes)
+        except NotImplementedError:
+            return None
+
     async def get_user_models(self, username: str, provider_name: str = None) -> Optional[List[Dict]]:
         """Fetch models owned by the specified user"""
         provider = self._get_provider(provider_name)

py/services/model_query.py

@@ -96,6 +96,7 @@ class FilterCriteria:
     folder_exclude: Optional[Sequence[str]] = None
     base_models: Optional[Sequence[str]] = None
     tags: Optional[Dict[str, str]] = None
+    auto_tags: Optional[Dict[str, str]] = None
     favorites_only: bool = False
     search_options: Optional[Dict[str, Any]] = None
     model_types: Optional[Sequence[str]] = None
@@ -293,12 +294,14 @@ class ModelFilterSet:
                 for tag, state in tag_filters.items():
                     if not tag:
                         continue
+                    # Normalize to lowercase for case-insensitive matching
+                    normalized = tag.strip().lower()
                     if state == "exclude":
-                        exclude_tags.add(tag)
+                        exclude_tags.add(normalized)
                     else:
-                        include_tags.add(tag)
+                        include_tags.add(normalized)
             else:
-                include_tags = {tag for tag in tag_filters if tag}
+                include_tags = {tag.strip().lower() for tag in tag_filters if tag}
 
             if include_tags:
                 tag_logic = criteria.tag_logic.lower() if criteria.tag_logic else "any"
@@ -317,13 +320,17 @@ class ModelFilterSet:
                                 return True
                             # Otherwise, check if all non-special tags match
                             if non_special_tags:
-                                return all(tag in (item_tags or []) for tag in non_special_tags)
+                                # Case-insensitive: normalize item tags too
+                                normalized_item_tags = {t.strip().lower() for t in (item_tags or []) if isinstance(t, str)}
+                                return all(tag in normalized_item_tags for tag in non_special_tags)
                             return True
-                        # Normal case: all tags must match
-                        return all(tag in (item_tags or []) for tag in non_special_tags)
+                        # Normal case: all tags must match (case-insensitive)
+                        normalized_item_tags = {t.strip().lower() for t in (item_tags or []) if isinstance(t, str)}
+                        return all(tag in normalized_item_tags for tag in non_special_tags)
                     else:
-                        # OR logic (default): item must have ANY include tag
-                        return any(tag in include_tags for tag in (item_tags or []))
+                        # OR logic (default): item must have ANY include tag (case-insensitive)
+                        normalized_item_tags = {t.strip().lower() for t in (item_tags or []) if isinstance(t, str)}
+                        return bool(normalized_item_tags & include_tags)
 
                 items = [item for item in items if matches_include(item.get("tags"))]
 
@@ -332,7 +339,9 @@ class ModelFilterSet:
                 def matches_exclude(item_tags):
                     if not item_tags and "__no_tags__" in exclude_tags:
                         return True
-                    return any(tag in exclude_tags for tag in (item_tags or []))
+                    # Case-insensitive: normalize item tags
+                    normalized_item_tags = {t.strip().lower() for t in (item_tags or []) if isinstance(t, str)}
+                    return bool(normalized_item_tags & exclude_tags)
 
                 items = [
                     item for item in items if not matches_exclude(item.get("tags"))
@@ -359,10 +368,37 @@ class ModelFilterSet:
                 ]
             model_types_duration = time.perf_counter() - t0
 
+        auto_tags_duration = 0
+        auto_tag_filters = criteria.auto_tags or {}
+        if auto_tag_filters:
+            t0 = time.perf_counter()
+            include_at = set()
+            exclude_at = set()
+            for tag, state in auto_tag_filters.items():
+                if not tag:
+                    continue
+                if state == "exclude":
+                    exclude_at.add(tag)
+                else:
+                    include_at.add(tag)
+
+            if include_at:
+                items = [
+                    item for item in items
+                    if any(tag in include_at for tag in (item.get("auto_tags") or []))
+                ]
+
+            if exclude_at:
+                items = [
+                    item for item in items
+                    if not any(tag in exclude_at for tag in (item.get("auto_tags") or []))
+                ]
+            auto_tags_duration = time.perf_counter() - t0
+
         duration = time.perf_counter() - overall_start
         if duration > 0.1:  # Only log if it's potentially slow
             logger.debug(
-                "ModelFilterSet.apply took %.3fs (sfw: %.3fs, fav: %.3fs, folder: %.3fs, base: %.3fs, tags: %.3fs, types: %.3fs). "
+                "ModelFilterSet.apply took %.3fs (sfw: %.3fs, fav: %.3fs, folder: %.3fs, base: %.3fs, tags: %.3fs, types: %.3fs, auto_tags: %.3fs). "
                 "Count: %d -> %d",
                 duration,
                 sfw_duration,
@@ -371,6 +407,7 @@ class ModelFilterSet:
                 base_models_duration,
                 tags_duration,
                 model_types_duration,
+                auto_tags_duration,
                 initial_count,
                 len(items),
             )

py/services/model_scanner.py

@@ -9,7 +9,7 @@ from typing import Any, Awaitable, Callable, Dict, List, Mapping, Optional, Set,
 
 from ..utils.models import BaseModelMetadata
 from ..config import config
-from ..utils.file_utils import find_preview_file, get_preview_extension
+from ..utils.file_utils import find_preview_file, get_preview_extension, calculate_sha256
 from ..utils.metadata_manager import MetadataManager
 from ..utils.civitai_utils import resolve_license_info
 from .model_cache import ModelCache
@@ -227,6 +227,11 @@ class ModelScanner:
 
         entry: Dict[str, Any] = {
             'file_path': normalized_path,
+            # file_name is always stored WITHOUT extension (e.g. "OWSMianne_ANIMA_V1",
+            # not "OWSMianne_ANIMA_V1.safetensors"). All upstream population points
+            # (MetadataManager, from_civitai_info, download manager, etc.) strip the
+            # extension via os.path.splitext before writing. Code consuming this field
+            # should match against names that are likewise extension-free.
             'file_name': get_value('file_name', '') or '',
             'model_name': get_value('model_name', '') or '',
             'folder': normalized_folder,
@@ -248,6 +253,7 @@ class ModelScanner:
             'civitai': civitai_slim,
             'civitai_deleted': bool(get_value('civitai_deleted', False)),
             'skip_metadata_refresh': bool(get_value('skip_metadata_refresh', False)),
+            'hf_url': get_value('hf_url', '') or '',
         }
 
         license_source: Dict[str, Any] = {}
@@ -476,11 +482,20 @@ class ModelScanner:
             for tag in adjusted_item.get('tags') or []:
                 tags_count[tag] = tags_count.get(tag, 0) + 1
 
-        # Validate cache entries and check health
+        # Validate cache entries and check health.
+        # Always use the validated/repaired entries — even when there are no
+        # invalid entries, auto_repair may have filled in missing optional
+        # fields (model_name, file_name, folder) with safe defaults on a copied
+        # working_entry.  Without this unconditional replacement the repaired
+        # copies are discarded and None values propagate to format_response.
+        # See issue #730.
         valid_entries, invalid_entries = CacheEntryValidator.validate_batch(
             adjusted_raw_data, auto_repair=True
         )
 
+        # Always use the validated entries (repaired copies)
+        adjusted_raw_data = valid_entries
+
         if invalid_entries:
             monitor = CacheHealthMonitor()
             report = monitor.check_health(adjusted_raw_data, auto_repair=True)
@@ -532,6 +547,13 @@ class ModelScanner:
         if not scan_result or not getattr(self, '_persistent_cache', None):
             return
 
+        if self.is_cancelled():
+            logger.info(
+                f"{self.model_type.capitalize()} Scanner: Skipping _save_persistent_cache "
+                "after cancellation"
+            )
+            return
+
         hash_snapshot = self._build_hash_index_snapshot(scan_result.hash_index)
         loop = asyncio.get_event_loop()
         try:
@@ -705,14 +727,20 @@ class ModelScanner:
             # Determine the page type based on model type
             # Scan for new data
             scan_result = await self._gather_model_data()
-            await self._apply_scan_result(scan_result)
-            await self._save_persistent_cache(scan_result)
-            await self._sync_download_history(scan_result.raw_data, source='scan')
+            if not self.is_cancelled():
+                await self._apply_scan_result(scan_result)
+                await self._save_persistent_cache(scan_result)
+                await self._sync_download_history(scan_result.raw_data, source='scan')
 
-            logger.info(
-                f"{self.model_type.capitalize()} Scanner: Cache initialization completed in {time.time() - start_time:.2f} seconds, "
-                f"found {len(scan_result.raw_data)} models"
-            )
+                logger.info(
+                    f"{self.model_type.capitalize()} Scanner: Cache initialization completed in {time.time() - start_time:.2f} seconds, "
+                    f"found {len(scan_result.raw_data)} models"
+                )
+            else:
+                logger.info(
+                    f"{self.model_type.capitalize()} Scanner: Cache initialization cancelled "
+                    f"after {time.time() - start_time:.2f} seconds"
+                )
         except Exception as e:
             logger.error(f"{self.model_type.capitalize()} Scanner: Error initializing cache: {e}")
             # Ensure cache is at least an empty structure on error
@@ -1067,19 +1095,27 @@ class ModelScanner:
 
         model_data = self._build_cache_entry(metadata, folder=normalized_folder)
 
+        # Compute SHA256 hash when metadata provided none (e.g., CivitAI API response has empty hashes).
+        # Respect hash_status='pending' (set by CheckpointScanner for large models) to defer
+        # hash calculation until on-demand — avoids reading entire checkpoint files at startup.
+        hash_status = model_data.get('hash_status', '')
+        if not model_data.get('sha256') and hash_status != 'pending' and file_path:
+            try:
+                logger.info(f"Computing SHA256 hash for {file_path} (was empty from metadata)")
+                sha256 = await calculate_sha256(file_path)
+                if sha256:
+                    model_data['sha256'] = sha256.lower()
+                    if isinstance(metadata, BaseModelMetadata):
+                        metadata.sha256 = sha256.lower()
+                    await MetadataManager.save_metadata(file_path, metadata)
+            except Exception as e:
+                logger.error(f"Failed to compute SHA256 for {file_path}: {e}")
+
         # Skip excluded models
         if model_data.get('exclude', False):
             excluded_models.append(model_data['file_path'])
             return None
 
-        # Check for duplicate filename before adding to hash index
-        # filename = os.path.splitext(os.path.basename(file_path))[0]
-        # existing_hash = hash_index.get_hash_by_filename(filename)
-        # if existing_hash and existing_hash != model_data.get('sha256', '').lower():
-        #     existing_path = hash_index.get_path(existing_hash)
-        #     if existing_path and existing_path != file_path:
-        #         logger.warning(f"Duplicate filename detected: '{filename}' - files: '{existing_path}' and '{file_path}'")
-
         return model_data
 
     async def _apply_scan_result(self, scan_result: CacheBuildResult) -> None:
@@ -1088,6 +1124,13 @@ class ModelScanner:
         if scan_result is None:
             return
 
+        if self.is_cancelled():
+            logger.info(
+                f"{self.model_type.capitalize()} Scanner: Skipping _apply_scan_result "
+                "after cancellation"
+            )
+            return
+
         self._hash_index = scan_result.hash_index
         self._tags_count = dict(scan_result.tags_count)
         self._excluded_models = list(scan_result.excluded_models)
@@ -1105,6 +1148,39 @@ class ModelScanner:
 
         await self._cache.resort()
 
+        self._log_duplicate_filename_summary()
+
+    def _log_duplicate_filename_summary(self) -> None:
+        """Log a batched summary of duplicate filename conflicts once per scan."""
+        # Duplicate filename detection is only relevant for LoRAs, which use
+        # basename-only syntax (<lora:name:strength>). Checkpoints and embeddings
+        # use full relative paths for resolution, so conflicts are not ambiguous.
+        if self._hash_index is None or self.model_type != "lora":
+            return
+
+        # When full path syntax is active, duplicate filenames across subfolders
+        # are fully qualified, so there is no ambiguity — skip the warning.
+        if get_settings_manager().get("lora_syntax_format", "legacy") == "full":
+            return
+
+        duplicates = self._hash_index.get_duplicate_filenames()
+        if not duplicates:
+            return
+
+        total_files = sum(len(paths) for paths in duplicates.values())
+        conflict_count = len(duplicates)
+        model_type_label = self.model_type or "model"
+
+        logger.warning(
+            "Duplicate filename conflict detected: %d %s filename(s) "
+            "are shared by %d files total, causing ambiguity in %s resolution. "
+            "Open the Doctor panel to resolve one-click.",
+            conflict_count,
+            model_type_label,
+            total_files,
+            model_type_label.capitalize(),
+        )
+
     async def _sync_download_history(
         self,
         raw_data: List[Mapping[str, Any]],
@@ -1456,6 +1532,15 @@ class ModelScanner:
                 file_path_override=normalized_new_path,
             )
 
+            # Ensure sha256 is populated even when metadata doesn't have it
+            if not cache_entry.get('sha256') and normalized_new_path and os.path.exists(normalized_new_path):
+                try:
+                    sha256 = await calculate_sha256(normalized_new_path)
+                    if sha256:
+                        cache_entry['sha256'] = sha256.lower()
+                except Exception as e:
+                    logger.error(f"Failed to compute SHA256 for {normalized_new_path}: {e}")
+
             if recalculate_type:
                 cache_entry = self.adjust_cached_entry(cache_entry)
 
@@ -1481,6 +1566,218 @@ class ModelScanner:
 
         return cache_entry if metadata else True
         
+    async def sync_cache_from_metadata(
+        self, file_path: str, metadata_dict: Dict[str, Any]
+    ) -> bool:
+        """Opportunistically sync in-memory and persistent caches from metadata.
+
+        Builds a prospective cache entry from *metadata_dict* (deserialized
+        ``.metadata.json`` content) and compares it against the current cache
+        entry.  When the two are already identical this method returns
+        ``False`` without touching anything — avoiding the overhead of
+        ``update_single_model_cache``, which always removes and re-inserts
+        the entry, triggers a full resort, and persists via the heavyweight
+        ``save_cache()``.
+
+        When differences are detected the update is applied **in-place** with
+        targeted operations:
+
+        * The existing ``raw_data`` entry is modified rather than removed and
+          re-appended (O(1) instead of O(n)).
+        * Tag counts and the hash index are updated incrementally.
+        * The version index is rebuilt only for the affected entry.
+        * ``resort()`` is called **only** when a sort-relevant field changed
+          (``model_name`` / ``file_name`` for name-sort, ``modified`` for
+          date-sort, ``size`` for size-sort).
+        * The persistent (SQLite) cache receives a targeted single-row update
+          via :meth:`PersistentModelCache.update_single_model` rather than a
+          full-table ``save_cache()``.
+
+        Returns:
+            ``True`` if any cache update was performed, ``False`` if the
+            caches were already in sync.
+
+        .. note::
+
+            This is a **best-effort** operation.  Failures are logged but
+            never propagated — callers should fire-and-forget via
+            :func:`asyncio.create_task`.
+        """
+        try:
+            return await self._sync_cache_from_metadata_impl(
+                file_path, metadata_dict
+            )
+        except Exception:
+            logger.warning(
+                "sync_cache_from_metadata failed for %s",
+                file_path,
+                exc_info=True,
+            )
+            return False
+
+    async def _sync_cache_from_metadata_impl(
+        self, file_path: str, metadata_dict: Dict[str, Any]
+    ) -> bool:
+        cache = await self.get_cached_data()
+
+        # Locate the existing cache entry -----------------------------------
+        existing_idx: Optional[int] = None
+        existing_entry: Optional[Dict[str, Any]] = None
+        for i, item in enumerate(cache.raw_data):
+            if item.get("file_path") == file_path:
+                existing_entry = item
+                existing_idx = i
+                break
+
+        # Build the desired entry from metadata ------------------------------
+        folder_value = (
+            existing_entry.get("folder", "")
+            if existing_entry
+            else self._calculate_folder(file_path)
+        )
+        desired_entry = self._build_cache_entry(
+            metadata_dict,
+            folder=folder_value,
+            file_path_override=file_path,
+        )
+
+        # Ensure sha256 is populated (defensive — metadata should have it)
+        if (
+            not desired_entry.get("sha256")
+            and file_path
+            and os.path.exists(file_path)
+        ):
+            try:
+                sha256 = await calculate_sha256(file_path)
+                if sha256:
+                    desired_entry["sha256"] = sha256.lower()
+            except Exception:
+                pass
+
+        # Not in cache at all — delegate to the full update path ------------
+        if existing_entry is None:
+            result = await self.update_single_model_cache(
+                file_path, file_path, metadata_dict
+            )
+            return bool(result)
+
+        # Compare — skip everything if already in sync -----------------------
+        if not self._cache_entries_differ(existing_entry, desired_entry):
+            return False
+
+        # Re-validate: the cache may have been replaced concurrently
+        # (e.g. by _apply_scan_result).  Use identity check, not equality,
+        # so we detect when the raw_data list was swapped out from under us.
+        if self._cache is None or not any(
+            item is existing_entry for item in self._cache.raw_data
+        ):
+            return False
+
+        # ---- Differences detected: apply targeted, in-place updates --------
+
+        # Snapshot old values for delta computations
+        old_tags = list(existing_entry.get("tags") or [])
+        old_sha256: str = existing_entry.get("sha256", "") or ""
+        old_model_name: str = existing_entry.get("model_name", "") or ""
+        old_file_name: str = existing_entry.get("file_name", "") or ""
+        old_modified: float = float(existing_entry.get("modified", 0.0) or 0.0)
+        old_size: int = int(existing_entry.get("size", 0) or 0)
+        old_civitai = existing_entry.get("civitai")
+
+        # ---- In-place update of the cache entry ----
+        existing_entry.clear()
+        existing_entry.update(desired_entry)
+
+        # ---- Incremental tag count update ----
+        new_tags: set = set(desired_entry.get("tags") or [])
+        old_tag_set: set = set(old_tags)
+        for tag in old_tag_set - new_tags:
+            current = self._tags_count.get(tag, 0)
+            if current <= 1:
+                self._tags_count.pop(tag, None)
+            else:
+                self._tags_count[tag] = current - 1
+        for tag in new_tags - old_tag_set:
+            self._tags_count[tag] = self._tags_count.get(tag, 0) + 1
+
+        # ---- Incremental hash index update ----
+        new_sha = (desired_entry.get("sha256", "") or "").lower()
+        old_sha = (old_sha256 or "").lower()
+        if new_sha != old_sha:
+            if old_sha:
+                self._hash_index.remove_by_path(file_path)
+            if new_sha:
+                self._hash_index.add_entry(new_sha, file_path)
+
+        # ---- Incremental version index update ----
+        new_civitai = desired_entry.get("civitai")
+        if old_civitai != new_civitai:
+            temp_old = {
+                "file_path": file_path,
+                "file_name": old_file_name,
+                "civitai": old_civitai,
+            }
+            cache.remove_from_version_index(temp_old)
+            cache.add_to_version_index(existing_entry)
+
+        # ---- Conditional resort (only when sort-key fields changed) ----
+        need_resort = False
+        _last = cache._last_sort
+        sort_key: Optional[str] = _last[0] if _last != (None, None) else None
+        if sort_key == "name":
+            if (
+                old_model_name != desired_entry.get("model_name", "")
+                or old_file_name != desired_entry.get("file_name", "")
+            ):
+                need_resort = True
+        elif sort_key == "date":
+            if old_modified != float(desired_entry.get("modified", 0.0) or 0.0):
+                need_resort = True
+        elif sort_key == "size":
+            if old_size != int(desired_entry.get("size", 0) or 0):
+                need_resort = True
+
+        if need_resort:
+            await cache.resort()
+
+        # ---- Targeted SQL update (single row, not full save_cache) ----
+        persistent = getattr(self, "_persistent_cache", None)
+        if persistent is not None:
+            old_item_for_sql: Dict[str, Any] = {
+                "file_path": file_path,
+                "tags": old_tags,
+                "sha256": old_sha256,
+            }
+            await asyncio.get_event_loop().run_in_executor(
+                None,
+                persistent.update_single_model,
+                self.model_type,
+                desired_entry,
+                old_item_for_sql,
+            )
+
+        return True
+
+    @staticmethod
+    def _cache_entries_differ(a: Dict[str, Any], b: Dict[str, Any]) -> bool:
+        """Return ``True`` when two cache-entry dicts differ in any field.
+
+        Tag lists are compared order-insensitively; all other keys use
+        standard equality.
+        """
+        a_tags = sorted(a.get("tags") or [])
+        b_tags = sorted(b.get("tags") or [])
+        if a_tags != b_tags:
+            return True
+
+        all_keys = set(a.keys()) | set(b.keys())
+        for key in all_keys:
+            if key == "tags":
+                continue
+            if a.get(key) != b.get(key):
+                return True
+        return False
+
     def has_hash(self, sha256: str) -> bool:
         """Check if a model with given hash exists"""
         return self._hash_index.has_hash(sha256.lower())
@@ -1533,9 +1830,34 @@ class ModelScanner:
         if limit == 0:
             return sorted_tags
         return sorted_tags[:limit]
-        
+
+    async def search_tags(
+        self, query: str, limit: int = 50
+    ) -> List[Dict[str, any]]:
+        """Search tags by case-insensitive substring match, sorted by count.
+
+        If query is empty, behaves like get_top_tags (returns top ``limit``
+        tags). If limit is 0, all matching tags are returned.
+        """
+        await self.get_cached_data()
+
+        normalized_query = (query or "").strip().lower()
+        if not normalized_query:
+            return await self.get_top_tags(limit if limit > 0 else 20)
+
+        matched = [
+            {"tag": tag, "count": count}
+            for tag, count in self._tags_count.items()
+            if normalized_query in tag.lower()
+        ]
+        matched.sort(key=lambda x: x["count"], reverse=True)
+
+        if limit == 0:
+            return matched
+        return matched[:limit]
+
     async def get_base_models(self, limit: int = 20) -> List[Dict[str, any]]:
-        """Get base models sorted by frequency"""
+        """Get base models sorted by count. If limit is 0, return all."""
         cache = await self.get_cached_data()
         
         base_model_counts = {}
@@ -1546,19 +1868,48 @@ class ModelScanner:
         
         sorted_models = [{'name': model, 'count': count} for model, count in base_model_counts.items()]
         sorted_models.sort(key=lambda x: x['count'], reverse=True)
-        
+
+        if limit == 0:
+            return sorted_models
         return sorted_models[:limit]
         
     async def get_model_info_by_name(self, name):
         """Get model information by name"""
         try:
             cache = await self.get_cached_data()
-            
+
+            name_normalized = name.replace("\\", "/")
+            name_no_ext = name_normalized
+            for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+                if name_no_ext.lower().endswith(ext):
+                    name_no_ext = name_no_ext[: -len(ext)]
+                    break
+
+            has_path = "/" in name_no_ext
+            basename = os.path.basename(name_no_ext) if has_path else name_no_ext
+            best_fallback = None
+
             for model in cache.raw_data:
-                if model.get("file_name") == name:
+                file_name = model.get("file_name", "")
+                folder = model.get("folder", "")
+                file_name_no_ext = file_name
+                for ext in (".safetensors", ".ckpt", ".pt", ".bin"):
+                    if file_name_no_ext.lower().endswith(ext):
+                        file_name_no_ext = file_name_no_ext[: -len(ext)]
+                        break
+                path_name = f"{folder}/{file_name_no_ext}".replace("\\", "/") if folder else file_name_no_ext
+
+                if name_no_ext == file_name_no_ext or name_no_ext == path_name:
                     return model
-                    
-            return None
+
+                if has_path and file_name_no_ext == basename:
+                    if folder and name_no_ext.startswith(folder.replace("\\", "/") + "/"):
+                        best_fallback = model
+                    elif best_fallback is None:
+                        best_fallback = model
+
+            return best_fallback
+
         except Exception as e:
             logger.error(f"Error getting model info by name: {e}", exc_info=True)
             return None
@@ -1685,6 +2036,13 @@ class ModelScanner:
         """
         if not file_paths or self._cache is None:
             return False
+
+        if self.is_cancelled():
+            logger.info(
+                f"{self.model_type.capitalize()} Scanner: Skipping cache update "
+                "after cancelled bulk delete"
+            )
+            return False
             
         try:
             # Get all models that need to be removed from cache

py/services/model_update_service.py

@@ -69,6 +69,7 @@ class ModelVersionRecord:
     early_access_ends_at: Optional[str] = None
     sort_index: int = 0
     is_early_access: bool = False
+    usage_control: Optional[str] = None  # "Download", "Generation", "InternalGeneration"
 
 
 @dataclass
@@ -101,11 +102,14 @@ class ModelUpdateRecord:
 
         return [version.version_id for version in self.versions if version.is_in_library]
 
-    def has_update(self, hide_early_access: bool = False) -> bool:
+    def has_update(
+        self, hide_early_access: bool = False, hide_non_downloadable: bool = True
+    ) -> bool:
         """Return True when a non-ignored remote version newer than the newest local copy is available.
 
         Args:
             hide_early_access: If True, exclude early access versions from update check.
+            hide_non_downloadable: If True, exclude versions that don't allow downloads.
         """
 
         if self.should_ignore_model:
@@ -121,6 +125,7 @@ class ModelUpdateRecord:
                 not version.is_in_library
                 and not version.should_ignore
                 and not (hide_early_access and ModelUpdateRecord._is_early_access_active(version))
+                and not (hide_non_downloadable and not ModelUpdateRecord._is_downloadable(version))
                 for version in self.versions
             )
 
@@ -129,6 +134,8 @@ class ModelUpdateRecord:
                 continue
             if hide_early_access and ModelUpdateRecord._is_early_access_active(version):
                 continue
+            if hide_non_downloadable and not ModelUpdateRecord._is_downloadable(version):
+                continue
             if version.version_id > max_in_library:
                 return True
         return False
@@ -155,11 +162,18 @@ class ModelUpdateRecord:
         # Phase 1: Basic EA flag from bulk API
         return version.is_early_access
 
+    @staticmethod
+    def _is_downloadable(version: ModelVersionRecord) -> bool:
+        if version.usage_control is None:
+            return True
+        return version.usage_control == "Download"
+
     def has_update_for_base(
         self,
         local_version_id: Optional[int],
         local_base_model: Optional[str],
         hide_early_access: bool = False,
+        hide_non_downloadable: bool = True,
     ) -> bool:
         """Return True when a newer remote version with the same base model exists.
 
@@ -167,6 +181,7 @@ class ModelUpdateRecord:
             local_version_id: The current local version id.
             local_base_model: The base model to filter by.
             hide_early_access: If True, exclude early access versions from update check.
+            hide_non_downloadable: If True, exclude versions that don't allow downloads.
         """
 
         if self.should_ignore_model:
@@ -197,6 +212,8 @@ class ModelUpdateRecord:
                 continue
             if hide_early_access and ModelUpdateRecord._is_early_access_active(version):
                 continue
+            if hide_non_downloadable and not ModelUpdateRecord._is_downloadable(version):
+                continue
             version_base = _normalize_base_model(version.base_model)
             if version_base != normalized_base:
                 continue
@@ -209,6 +226,8 @@ class ModelUpdateRecord:
 class ModelUpdateService:
     """Persist and query remote model version metadata."""
 
+    _SQLITE_MAX_VARIABLES = 500
+
     _SCHEMA = """
         PRAGMA foreign_keys = ON;
         CREATE TABLE IF NOT EXISTS model_update_status (
@@ -228,6 +247,7 @@ class ModelUpdateService:
             preview_url TEXT,
             is_in_library INTEGER NOT NULL DEFAULT 0,
             should_ignore INTEGER NOT NULL DEFAULT 0,
+            usage_control TEXT,
             PRIMARY KEY (model_id, version_id),
             FOREIGN KEY(model_id) REFERENCES model_update_status(model_id) ON DELETE CASCADE
         );
@@ -463,6 +483,10 @@ class ModelUpdateService:
                 "ALTER TABLE model_update_versions "
                 "ADD COLUMN is_early_access INTEGER NOT NULL DEFAULT 0"
             ),
+            "usage_control": (
+                "ALTER TABLE model_update_versions "
+                "ADD COLUMN usage_control TEXT"
+            ),
         }
 
         for column, statement in migrations.items():
@@ -665,6 +689,7 @@ class ModelUpdateService:
         *,
         force_refresh: bool = False,
         target_model_ids: Optional[Sequence[int]] = None,
+        folder_path: Optional[str] = None,
     ) -> Dict[int, ModelUpdateRecord]:
         """Refresh update information for every model present in the cache."""
         scanner.reset_cancellation()
@@ -679,6 +704,7 @@ class ModelUpdateService:
         local_versions = await self._collect_local_versions(
             scanner,
             target_model_ids=target_filter,
+            folder_path=folder_path,
         )
         total_models = len(local_versions)
         if total_models == 0:
@@ -698,6 +724,16 @@ class ModelUpdateService:
             "Refreshing update metadata for %d %s models", total_models, model_type
         )
 
+        # When filtering by folder, also collect the cross-folder version set
+        # so that versions already present in other folders are not reported
+        # as available updates. See issue #997.
+        all_local_versions: Optional[Dict[int, List[int]]] = None
+        if folder_path is not None:
+            all_local_versions = await self._collect_local_versions(
+                scanner,
+                target_model_ids=target_filter,
+            )
+
         results: Dict[int, ModelUpdateRecord] = {}
         prefetched: Dict[int, Mapping] = {}
 
@@ -736,6 +772,12 @@ class ModelUpdateService:
         for index, (model_id, version_ids) in enumerate(
             local_versions.items(), start=1
         ):
+            # Use cross-folder version IDs for is_in_library if available
+            all_vids: Sequence[int] = (
+                all_local_versions.get(model_id, [])
+                if all_local_versions is not None
+                else version_ids
+            )
             record = await self._refresh_single_model(
                 model_type,
                 model_id,
@@ -743,6 +785,7 @@ class ModelUpdateService:
                 metadata_provider,
                 force_refresh=force_refresh,
                 prefetched_response=prefetched.get(model_id),
+                all_local_version_ids=all_vids,
             )
             if scanner.is_cancelled():
                 logger.info(f"{model_type.capitalize()} Update Service: Refresh cancelled by user")
@@ -938,8 +981,16 @@ class ModelUpdateService:
         *,
         force_refresh: bool = False,
         prefetched_response: Optional[Mapping] = None,
+        all_local_version_ids: Optional[Sequence[int]] = None,
     ) -> Optional[ModelUpdateRecord]:
         normalized_local = self._normalize_sequence(local_versions)
+        # When folder-filtering, this carries the cross-folder version set
+        # for is_in_library; otherwise it falls back to normalized_local.
+        normalized_all = (
+            self._normalize_sequence(all_local_version_ids)
+            if all_local_version_ids is not None
+            else normalized_local
+        )
         now = time.time()
         async with self._lock:
             existing = self._get_record(model_type, model_id)
@@ -947,6 +998,7 @@ class ModelUpdateService:
                 record = self._merge_with_local_versions(
                     existing,
                     normalized_local,
+                    all_local_version_ids=normalized_all,
                 )
                 self._upsert_record(record)
                 return record
@@ -965,18 +1017,22 @@ class ModelUpdateService:
                 fallback_attempted = True
                 try:
                     response = await metadata_provider.get_model_versions(model_id)
+                    if response is not None:
+                        await self._enrich_version_entries(
+                            metadata_provider,
+                            {model_id: response},
+                        )
                 except RateLimitError:
                     raise
                 except ResourceNotFoundError as exc:
                     fallback_error_message = str(exc) or "resource not found"
                     mark_model_as_ignored = True
                 except Exception as exc:  # pragma: no cover - defensive log
-                    logger.error(
+                    logger.warning(
                         "Failed to fetch versions for model %s (%s): %s",
                         model_id,
                         model_type,
                         exc,
-                        exc_info=True,
                     )
                     fallback_error_message = str(exc)
             if response is not None:
@@ -1018,6 +1074,7 @@ class ModelUpdateService:
                 record = self._merge_with_local_versions(
                     existing,
                     normalized_local,
+                    all_local_version_ids=normalized_all,
                 )
                 self._upsert_record(record)
                 return record
@@ -1029,6 +1086,7 @@ class ModelUpdateService:
                     model_type=model_type,
                     model_id=model_id,
                     last_checked_at=now,
+                    all_local_version_ids=normalized_all,
                 )
                 record = replace(record, should_ignore_model=True)
                 self._upsert_record(record)
@@ -1047,6 +1105,7 @@ class ModelUpdateService:
                     fetched_versions,
                     existing,
                     now,
+                    all_local_version_ids=normalized_all,
                 )
             else:
                 record = self._merge_with_local_versions(
@@ -1055,10 +1114,141 @@ class ModelUpdateService:
                     model_type=model_type,
                     model_id=model_id,
                     last_checked_at=existing.last_checked_at if existing else None,
+                    all_local_version_ids=normalized_all,
                 )
             self._upsert_record(record)
             return record
 
+    async def _enrich_version_entries(
+        self,
+        metadata_provider,
+        responses_by_model_id: Dict[int, Mapping],
+    ) -> None:
+        """Enrich version entries with ``usageControl`` via batch hash endpoint.
+
+        The model-level API does not include ``usageControl`` on version
+        entries. This method collects SHA256 hashes from every version's
+        primary model file, calls ``POST /api/v1/model-versions/by-hash``
+        (up to 100 hashes per request), and injects ``usageControl`` +
+        ``earlyAccessEndsAt`` into each version entry dict in-place.
+        """
+        if not metadata_provider or not responses_by_model_id:
+            return
+
+        hashes_by_version: Dict[int, str] = {}
+        for response in responses_by_model_id.values():
+            hashes_by_version.update(
+                self._collect_hashes_from_response(response)
+            )
+
+        if not hashes_by_version:
+            return
+
+        version_ids_by_hash: Dict[str, List[int]] = {}
+        for version_id, sha256 in hashes_by_version.items():
+            version_ids_by_hash.setdefault(sha256, []).append(version_id)
+
+        all_hashes = list(version_ids_by_hash.keys())
+        BATCH_SIZE = 100
+
+        enrichment: Dict[int, Dict] = {}
+        try:
+            for start in range(0, len(all_hashes), BATCH_SIZE):
+                batch = all_hashes[start : start + BATCH_SIZE]
+                try:
+                    enriched = await metadata_provider.get_model_versions_by_hashes(
+                        batch
+                    )
+                except NotImplementedError:
+                    return
+                except RateLimitError:
+                    raise
+                except Exception:
+                    continue
+
+                if not enriched:
+                    continue
+
+                for entry in enriched:
+                    if not isinstance(entry, dict):
+                        continue
+                    version_id = entry.get("id")
+                    if version_id is None:
+                        continue
+                    enrichment[version_id] = {
+                        "usageControl": _normalize_string(
+                            entry.get("usageControl")
+                        ),
+                        "earlyAccessEndsAt": _normalize_string(
+                            entry.get("earlyAccessEndsAt")
+                        ),
+                    }
+        except RateLimitError:
+            raise
+
+        if not enrichment:
+            return
+
+        for response in responses_by_model_id.values():
+            versions = response.get("modelVersions")
+            if not isinstance(versions, list):
+                continue
+            for version in versions:
+                if not isinstance(version, dict):
+                    continue
+                version_id = version.get("id")
+                if version_id not in enrichment:
+                    continue
+                extra = enrichment[version_id]
+                if extra.get("usageControl") and not version.get("usageControl"):
+                    version["usageControl"] = extra["usageControl"]
+                if extra.get("earlyAccessEndsAt") and not version.get(
+                    "earlyAccessEndsAt"
+                ):
+                    version["earlyAccessEndsAt"] = extra["earlyAccessEndsAt"]
+
+    @staticmethod
+    def _collect_hashes_from_response(response: Mapping) -> Dict[int, str]:
+        """Extract ``{version_id: sha256}`` from a model-level API response.
+
+        Returns an empty dict if the response structure is unexpected.
+        """
+        result: Dict[int, str] = {}
+        versions = response.get("modelVersions")
+        if not isinstance(versions, list):
+            return result
+        for entry in versions:
+            if not isinstance(entry, dict):
+                continue
+            version_id = _normalize_int(entry.get("id"))
+            if version_id is None:
+                continue
+            sha256 = ModelUpdateService._extract_sha256_from_version_entry(entry)
+            if sha256:
+                result[version_id] = sha256
+        return result
+
+    @staticmethod
+    def _extract_sha256_from_version_entry(entry: Mapping) -> Optional[str]:
+        """Return the SHA256 hash from the primary model file of a version entry."""
+        files = entry.get("files")
+        if not isinstance(files, list):
+            return None
+        for file_info in files:
+            if not isinstance(file_info, dict):
+                continue
+            if file_info.get("type") != "Model":
+                continue
+            primary = file_info.get("primary")
+            if primary is not True and str(primary).strip().lower() != "true":
+                continue
+            hashes = file_info.get("hashes")
+            if isinstance(hashes, dict):
+                sha256 = hashes.get("SHA256")
+                if sha256:
+                    return sha256
+        return None
+
     async def _fetch_model_versions_bulk(
         self,
         metadata_provider,
@@ -1110,6 +1300,7 @@ class ModelUpdateService:
             len(aggregated),
             provider_name,
         )
+        await self._enrich_version_entries(metadata_provider, aggregated)
         return aggregated
 
     async def _collect_local_versions(
@@ -1117,6 +1308,7 @@ class ModelUpdateService:
         scanner,
         *,
         target_model_ids: Optional[Sequence[int]] = None,
+        folder_path: Optional[str] = None,
     ) -> Dict[int, List[int]]:
         cache = await scanner.get_cached_data()
         mapping: Dict[int, set[int]] = {}
@@ -1129,7 +1321,19 @@ class ModelUpdateService:
             if not target_set:
                 return {}
 
+        normalized_folder = None
+        if folder_path is not None:
+            normalized_folder = folder_path.replace("\\", "/").strip("/")
+
         for item in cache.raw_data:
+            # Apply folder filter first (cheapest check)
+            if normalized_folder is not None:
+                if not isinstance(item, dict):
+                    continue
+                item_folder = (item.get("folder") or "").replace("\\", "/").strip("/")
+                if item_folder != normalized_folder and not item_folder.startswith(normalized_folder + "/"):
+                    continue
+
             civitai = item.get("civitai") if isinstance(item, dict) else None
             if not isinstance(civitai, dict):
                 continue
@@ -1148,12 +1352,20 @@ class ModelUpdateService:
         existing: Optional[ModelUpdateRecord],
         normalized_local: Sequence[int],
         *,
+        all_local_version_ids: Optional[Sequence[int]] = None,
         model_type: Optional[str] = None,
         model_id: Optional[int] = None,
         last_checked_at: Optional[float] = None,
         version_info: Optional[Mapping] = None,
     ) -> ModelUpdateRecord:
         local_set = set(normalized_local)
+        # When folder-filtering, also consider versions in other folders
+        # as in-library so they are not reported as available updates.
+        effective_local_set: set[int] = (
+            local_set | set(all_local_version_ids)
+            if all_local_version_ids is not None
+            else local_set
+        )
         versions: List[ModelVersionRecord] = []
         ignore_map: Dict[int, bool] = {}
         if existing:
@@ -1165,7 +1377,7 @@ class ModelUpdateService:
                 versions.append(
                     replace(
                         version,
-                        is_in_library=version.version_id in local_set,
+                        is_in_library=version.version_id in effective_local_set,
                     )
                 )
         elif model_type is None or model_id is None:
@@ -1212,8 +1424,17 @@ class ModelUpdateService:
         remote_versions: Sequence[ModelVersionRecord],
         existing: Optional[ModelUpdateRecord],
         timestamp: float,
+        *,
+        all_local_version_ids: Optional[Sequence[int]] = None,
     ) -> ModelUpdateRecord:
         local_set = set(local_versions)
+        # When folder-filtering, also consider versions in other folders
+        # as in-library so they are not reported as available updates.
+        effective_local_set: set[int] = (
+            local_set | set(all_local_version_ids)
+            if all_local_version_ids is not None
+            else local_set
+        )
         ignore_map = {version.version_id: version.should_ignore for version in existing.versions} if existing else {}
         preview_map = {version.version_id: version.preview_url for version in existing.versions} if existing else {}
         sort_map = {version.version_id: version.sort_index for version in existing.versions} if existing else {}
@@ -1232,11 +1453,12 @@ class ModelUpdateService:
                     released_at=remote_version.released_at,
                     size_bytes=remote_version.size_bytes,
                     preview_url=remote_version.preview_url or preview_map.get(version_id),
-                    is_in_library=version_id in local_set,
+                    is_in_library=version_id in effective_local_set,
                     should_ignore=ignore_map.get(version_id, remote_version.should_ignore),
                     sort_index=sort_map.get(version_id, index),
                     early_access_ends_at=remote_version.early_access_ends_at,
                     is_early_access=remote_version.is_early_access,
+                    usage_control=remote_version.usage_control,
                 )
             )
 
@@ -1335,6 +1557,7 @@ class ModelUpdateService:
         # Check availability field from bulk API for basic EA detection
         availability = _normalize_string(entry.get("availability"))
         is_early_access = availability == "EarlyAccess"
+        usage_control = _normalize_string(entry.get("usageControl"))
 
         return ModelVersionRecord(
             version_id=version_id,
@@ -1348,6 +1571,7 @@ class ModelUpdateService:
             early_access_ends_at=early_access_ends_at,
             sort_index=index,
             is_early_access=is_early_access,
+            usage_control=usage_control,
         )
 
     def _extract_size_bytes(self, files) -> Optional[int]:
@@ -1439,33 +1663,41 @@ class ModelUpdateService:
         if not model_ids:
             return {}
 
-        params = tuple(model_ids)
-        placeholders = ",".join("?" for _ in params)
+        ids = list(model_ids)
+        status_rows: list = []
+        version_rows: list = []
 
         with self._connect() as conn:
-            status_rows = conn.execute(
-                f"""
-                SELECT model_id, model_type, last_checked_at, should_ignore_model
-                FROM model_update_status
-                WHERE model_id IN ({placeholders})
-                """,
-                params,
-            ).fetchall()
+            for start in range(0, len(ids), self._SQLITE_MAX_VARIABLES):
+                chunk = tuple(ids[start : start + self._SQLITE_MAX_VARIABLES])
+                placeholders = ",".join("?" for _ in chunk)
+
+                chunk_status = conn.execute(
+                    f"""
+                    SELECT model_id, model_type, last_checked_at, should_ignore_model
+                    FROM model_update_status
+                    WHERE model_id IN ({placeholders})
+                    """,
+                    chunk,
+                ).fetchall()
+                status_rows.extend(chunk_status)
+
+                chunk_versions = conn.execute(
+                    f"""
+                    SELECT model_id, version_id, sort_index, name, base_model, released_at,
+                           size_bytes, preview_url, is_in_library, should_ignore, early_access_ends_at,
+                           is_early_access, usage_control
+                    FROM model_update_versions
+                    WHERE model_id IN ({placeholders})
+                    ORDER BY model_id ASC, sort_index ASC, version_id ASC
+                    """,
+                    chunk,
+                ).fetchall()
+                version_rows.extend(chunk_versions)
+
             if not status_rows:
                 return {}
 
-            version_rows = conn.execute(
-                f"""
-                SELECT model_id, version_id, sort_index, name, base_model, released_at,
-                       size_bytes, preview_url, is_in_library, should_ignore, early_access_ends_at,
-                       is_early_access
-                FROM model_update_versions
-                WHERE model_id IN ({placeholders})
-                ORDER BY model_id ASC, sort_index ASC, version_id ASC
-                """,
-                params,
-            ).fetchall()
-
         versions_by_model: Dict[int, List[ModelVersionRecord]] = {}
         for row in version_rows:
             model_id = int(row["model_id"])
@@ -1482,6 +1714,7 @@ class ModelUpdateService:
                     early_access_ends_at=row["early_access_ends_at"],
                     sort_index=_normalize_int(row["sort_index"]) or 0,
                     is_early_access=bool(row["is_early_access"]),
+                    usage_control=row["usage_control"],
                 )
             )
 
@@ -1538,8 +1771,8 @@ class ModelUpdateService:
                     INSERT INTO model_update_versions (
                         version_id, model_id, sort_index, name, base_model, released_at,
                         size_bytes, preview_url, is_in_library, should_ignore, early_access_ends_at,
-                        is_early_access
-                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                        is_early_access, usage_control
+                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
                     """,
                     (
                         version.version_id,
@@ -1554,6 +1787,7 @@ class ModelUpdateService:
                         1 if version.should_ignore else 0,
                         version.early_access_ends_at,
                         1 if version.is_early_access else 0,
+                        version.usage_control,
                     ),
                 )
             conn.commit()

py/services/persistent_model_cache.py

@@ -57,6 +57,7 @@ class PersistentModelCache:
         "db_checked",
         "last_checked_at",
         "hash_status",
+        "hf_url",
     )
     _MODEL_UPDATE_COLUMNS: Tuple[str, ...] = _MODEL_COLUMNS[2:]
     _instances: Dict[str, "PersistentModelCache"] = {}
@@ -165,8 +166,8 @@ class PersistentModelCache:
 
             item = {
                 "file_path": file_path,
-                "file_name": row["file_name"],
-                "model_name": row["model_name"],
+                "file_name": row["file_name"] or "",
+                "model_name": row["model_name"] or "",
                 "folder": row["folder"] or "",
                 "size": row["size"] or 0,
                 "modified": row["modified"] or 0.0,
@@ -188,6 +189,7 @@ class PersistentModelCache:
                 "skip_metadata_refresh": bool(row["skip_metadata_refresh"]),
                 "license_flags": int(license_value),
                 "hash_status": row["hash_status"] or "completed",
+                "hf_url": row["hf_url"] or "",
             }
             raw_data.append(item)
 
@@ -452,6 +454,7 @@ class PersistentModelCache:
                             db_checked INTEGER,
                             last_checked_at REAL,
                             hash_status TEXT,
+                            hf_url TEXT DEFAULT '',
                             PRIMARY KEY (model_type, file_path)
                         );
 
@@ -500,6 +503,7 @@ class PersistentModelCache:
             # Persisting without explicit flags should assume CivitAI's documented defaults (0b111001 == 57).
             "license_flags": f"INTEGER DEFAULT {DEFAULT_LICENSE_FLAGS}",
             "hash_status": "TEXT DEFAULT 'completed'",
+            "hf_url": "TEXT DEFAULT ''",
         }
 
         for column, definition in required_columns.items():
@@ -548,19 +552,19 @@ class PersistentModelCache:
         return (
             model_type,
             item.get("file_path"),
-            item.get("file_name"),
-            item.get("model_name"),
-            item.get("folder"),
+            item.get("file_name") or "",
+            item.get("model_name") or "",
+            item.get("folder") or "",
             int(item.get("size") or 0),
             float(item.get("modified") or 0.0),
             (item.get("sha256") or "").lower() or None,
-            item.get("base_model"),
-            item.get("preview_url"),
+            item.get("base_model") or "",
+            item.get("preview_url") or "",
             int(item.get("preview_nsfw_level") or 0),
             1 if item.get("from_civitai", True) else 0,
             1 if item.get("favorite") else 0,
-            item.get("notes"),
-            item.get("usage_tips"),
+            item.get("notes") or "",
+            item.get("usage_tips") or "",
             metadata_source,
             civitai.get("id"),
             civitai.get("modelId"),
@@ -575,6 +579,7 @@ class PersistentModelCache:
             1 if item.get("db_checked") else 0,
             float(item.get("last_checked_at") or 0.0),
             item.get("hash_status", "completed"),
+            item.get("hf_url") or "",
         )
 
     def _insert_model_sql(self) -> str:
@@ -582,6 +587,95 @@ class PersistentModelCache:
         placeholders = ", ".join(["?"] * len(self._MODEL_COLUMNS))
         return f"INSERT INTO models ({columns}) VALUES ({placeholders})"
 
+    def update_single_model(
+        self,
+        model_type: str,
+        new_item: Dict,
+        old_item: Optional[Dict] = None,
+    ) -> None:
+        """Update a single model row in the persistent cache.
+
+        A lightweight alternative to :meth:`save_cache` that performs a targeted
+        DELETE + INSERT for the model row and computes incremental tag / hash-index
+        deltas from *old_item*.  When *old_item* is omitted the previous tags and
+        hash are not cleaned up (callers should only omit it for brand-new entries).
+
+        All operations run inside a single transaction so readers see a consistent
+        view.
+        """
+        if not self.is_enabled():
+            return
+        if not self._schema_initialized:
+            self._initialize_schema()
+        if not self._schema_initialized:
+            return
+
+        file_path: Optional[str] = new_item.get("file_path")
+        if not file_path:
+            return
+
+        try:
+            with self._db_lock:
+                conn = self._connect()
+                try:
+                    conn.execute("PRAGMA foreign_keys = ON")
+                    conn.execute("BEGIN")
+
+                    # --- model row (DELETE + INSERT = upsert) ---
+                    conn.execute(
+                        "DELETE FROM models WHERE model_type = ? AND file_path = ?",
+                        (model_type, file_path),
+                    )
+                    row = self._prepare_model_row(model_type, new_item)
+                    conn.execute(self._insert_model_sql(), row)
+
+                    # --- tags ---
+                    new_tags: set = set(new_item.get("tags") or [])
+                    old_tags: set = set(old_item.get("tags") or []) if old_item else set()
+                    tags_to_delete = old_tags - new_tags
+                    tags_to_insert = new_tags - old_tags
+
+                    if tags_to_delete:
+                        conn.executemany(
+                            "DELETE FROM model_tags WHERE model_type = ? AND file_path = ? AND tag = ?",
+                            [(model_type, file_path, t) for t in tags_to_delete],
+                        )
+                    if tags_to_insert:
+                        conn.executemany(
+                            "INSERT INTO model_tags (model_type, file_path, tag) VALUES (?, ?, ?)",
+                            [(model_type, file_path, t) for t in tags_to_insert],
+                        )
+
+                    # --- hash_index ---
+                    new_sha: Optional[str] = (new_item.get("sha256") or "").lower() or None
+                    old_sha: Optional[str] = (
+                        (old_item.get("sha256") or "").lower() or None
+                    ) if old_item else None
+                    if new_sha != old_sha:
+                        if old_sha:
+                            conn.execute(
+                                "DELETE FROM hash_index WHERE model_type = ? AND sha256 = ? AND file_path = ?",
+                                (model_type, old_sha, file_path),
+                            )
+                        if new_sha:
+                            conn.execute(
+                                "INSERT OR IGNORE INTO hash_index (model_type, sha256, file_path) VALUES (?, ?, ?)",
+                                (model_type, new_sha, file_path),
+                            )
+
+                    conn.execute("COMMIT")
+                except Exception:
+                    conn.execute("ROLLBACK")
+                    raise
+                finally:
+                    conn.close()
+        except Exception as exc:
+            logger.warning(
+                "Failed to update single model in persistent cache (%s): %s",
+                file_path,
+                exc,
+            )
+
     def _load_tags(self, conn: sqlite3.Connection, model_type: str) -> Dict[str, List[str]]:
         tag_rows = conn.execute(
             "SELECT file_path, tag FROM model_tags WHERE model_type = ?",

py/services/persistent_recipe_cache.py

@@ -12,7 +12,7 @@ import logging
 import os
 import sqlite3
 import threading
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Dict, List, Optional, Set, Tuple
 
 from ..utils.cache_paths import CacheType, resolve_cache_path_with_migration
@@ -26,6 +26,8 @@ class PersistedRecipeData:
 
     raw_data: List[Dict]
     file_stats: Dict[str, Tuple[float, int]]  # json_path -> (mtime, size)
+    image_id_map: Dict[str, str] = field(default_factory=dict)
+    """Precomputed mapping of civitai image_id → recipe_id."""
 
 
 class PersistentRecipeCache:
@@ -38,6 +40,7 @@ class PersistentRecipeCache:
         "json_path",
         "title",
         "folder",
+        "source_path",
         "base_model",
         "fingerprint",
         "created_date",
@@ -115,6 +118,20 @@ class PersistentRecipeCache:
                     if not rows:
                         return None
 
+                    # Restore precomputed image_id_map if available
+                    image_id_map: Dict[str, str] = {}
+                    try:
+                        meta_row = conn.execute(
+                            "SELECT value FROM cache_metadata WHERE key = ?",
+                            ("image_id_map",),
+                        ).fetchone()
+                        if meta_row:
+                            parsed = json.loads(meta_row["value"])
+                            if isinstance(parsed, dict):
+                                image_id_map = parsed
+                    except Exception:
+                        pass  # missing or corrupt — rebuilt on next cache refresh
+
                 finally:
                     conn.close()
         except FileNotFoundError:
@@ -137,14 +154,24 @@ class PersistentRecipeCache:
                     row["file_size"] or 0,
                 )
 
-        return PersistedRecipeData(raw_data=raw_data, file_stats=file_stats)
+        return PersistedRecipeData(
+            raw_data=raw_data,
+            file_stats=file_stats,
+            image_id_map=image_id_map,
+        )
 
-    def save_cache(self, recipes: List[Dict], json_paths: Optional[Dict[str, str]] = None) -> None:
+    def save_cache(
+        self,
+        recipes: List[Dict],
+        json_paths: Optional[Dict[str, str]] = None,
+        image_id_map: Optional[Dict[str, str]] = None,
+    ) -> None:
         """Save all recipes to SQLite cache.
 
         Args:
             recipes: List of recipe dictionaries to persist.
             json_paths: Optional mapping of recipe_id -> json_path for file stats.
+            image_id_map: Optional precomputed civitai image_id → recipe_id mapping.
         """
         if not self.is_enabled():
             return
@@ -185,6 +212,12 @@ class PersistentRecipeCache:
                             recipe_rows,
                         )
 
+                    # Persist image_id_map for O(1) lookups on cache load
+                    conn.execute(
+                        "INSERT OR REPLACE INTO cache_metadata (key, value) VALUES (?, ?)",
+                        ("image_id_map", json.dumps(image_id_map or {})),
+                    )
+
                     conn.commit()
                     logger.debug("Persisted %d recipes to cache", len(recipe_rows))
                 finally:
@@ -272,6 +305,29 @@ class PersistentRecipeCache:
         except Exception as exc:
             logger.debug("Failed to remove recipe %s from cache: %s", recipe_id, exc)
 
+    def save_image_id_map(self, image_id_map: Dict[str, str]) -> None:
+        """Persist the image_id_map to cache_metadata without rewriting the full cache.
+
+        This is called after ``add_recipe`` / ``remove_recipe`` mutations so
+        the persistent copy does not go stale between full ``save_cache`` calls.
+        """
+        if not self.is_enabled() or not self._schema_initialized:
+            return
+
+        try:
+            with self._db_lock:
+                conn = self._connect()
+                try:
+                    conn.execute(
+                        "INSERT OR REPLACE INTO cache_metadata (key, value) VALUES (?, ?)",
+                        ("image_id_map", json.dumps(image_id_map)),
+                    )
+                    conn.commit()
+                finally:
+                    conn.close()
+        except Exception as exc:
+            logger.debug("Failed to persist image_id_map: %s", exc)
+
     def get_indexed_recipe_ids(self) -> Set[str]:
         """Return all recipe IDs in the cache.
 
@@ -334,6 +390,7 @@ class PersistentRecipeCache:
                             json_path TEXT,
                             title TEXT,
                             folder TEXT,
+                            source_path TEXT,
                             base_model TEXT,
                             fingerprint TEXT,
                             created_date REAL,
@@ -358,6 +415,13 @@ class PersistentRecipeCache:
                         );
                         """
                     )
+                    # Migration: add source_path column to existing databases
+                    try:
+                        conn.execute(
+                            "ALTER TABLE recipes ADD COLUMN source_path TEXT"
+                        )
+                    except Exception:
+                        pass  # column already exists
                     conn.commit()
                 self._schema_initialized = True
             except Exception as exc:
@@ -406,6 +470,7 @@ class PersistentRecipeCache:
             json_path,
             recipe.get("title"),
             recipe.get("folder"),
+            recipe.get("source_path"),
             recipe.get("base_model"),
             recipe.get("fingerprint"),
             float(recipe.get("created_date") or 0.0),
@@ -456,6 +521,7 @@ class PersistentRecipeCache:
             "file_path": row["file_path"] or "",
             "title": row["title"] or "",
             "folder": row["folder"] or "",
+            "source_path": row["source_path"] or "",
             "base_model": row["base_model"] or "",
             "fingerprint": row["fingerprint"] or "",
             "created_date": row["created_date"] or 0.0,

py/services/recipe_cache.py

@@ -1,7 +1,6 @@
 import asyncio
 from typing import Iterable, List, Dict, Optional
-from dataclasses import dataclass
-from operator import itemgetter
+from dataclasses import dataclass, field
 from natsort import natsorted
 
 
@@ -14,6 +13,15 @@ class RecipeCache:
     sorted_by_date: List[Dict]
     folders: List[str] | None = None
     folder_tree: Dict | None = None
+    image_id_map: Dict[str, str] = field(default_factory=dict)
+    """Mapping of civitai image_id → recipe_id, precomputed at cache build time.
+
+    Built once during cache initialization (O(n)) so that
+    ``check_image_exists`` and ``import_from_url`` duplicate checks
+    can look up image_id in O(1) instead of scanning all recipes.
+    Recipes imported from local files have no valid civitai image_id
+    and are naturally excluded from this map.
+    """
 
     def __post_init__(self):
         self._lock = asyncio.Lock()
@@ -140,5 +148,10 @@ class RecipeCache:
         )
         if not name_only:
             self.sorted_by_date = sorted(
-                self.raw_data, key=itemgetter("created_date", "file_path"), reverse=True
+                self.raw_data,
+                key=lambda x: (
+                    x.get("modified", x.get("created_date", 0)),
+                    x.get("file_path", ""),
+                ),
+                reverse=True,
             )