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'.

.gitignore

@@ -36,3 +36,7 @@ vue-widgets/dist/
 
 # Working/research notes (not committed)
 .docs/
+
+# HF enrichment validation baseline snapshots (contain potentially
+# NSFW README content fetched from community model repos)
+tests/enrich_hf_validation/baselines/

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/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

locales/en.json

@@ -233,7 +233,7 @@
       "presetNamePlaceholder": "Preset name...",
       "baseModel": "Base Model",
       "baseModelSearchPlaceholder": "Search base models...",
-      "modelTags": "Tags (Top 20)",
+      "modelTags": "Tags",
       "modelTypes": "Model Types",
       "license": "License",
       "noCreditRequired": "No Credit Required",
@@ -241,6 +241,8 @@
       "allowSellingGeneratedContentTooltip": "Allow selling generated images",
       "noCreditRequiredTooltip": "Use the model without crediting the creator",
       "noTags": "No tags",
+      "tagSearchPlaceholder": "Search tags...",
+      "noTagMatches": "No tags match the current search.",
       "autoTags": "Auto Tags",
       "noBaseModelMatches": "No base models match the current search.",
       "clearAll": "Clear All Filters",
@@ -505,7 +507,9 @@
       "saveSuccess": "Extra folder paths updated. Restart required to apply changes.",
       "saveError": "Failed to update extra folder paths: {message}",
       "validation": {
-        "duplicatePath": "This path is already configured"
+        "duplicatePath": "This path is already configured",
+        "checkpointUnetOverlap": "Cannot use the same path for both checkpoints and diffusion models: {paths}",
+        "checkpointUnetOverlapInline": "This path is also used for a different model type. Use separate folders for checkpoints and diffusion models."
       }
     },
     "priorityTags": {
@@ -638,7 +642,13 @@
       "preparing": "Preparing download...",
       "connecting": "Connecting to download server...",
       "completed": "Completed",
-      "downloadComplete": "Download completed successfully"
+      "downloadComplete": "Download completed successfully",
+      "enableCivarchiveApi": "Enable CivArchive API as metadata provider",
+      "enableCivarchiveApiHelp": "When on, CivArchive API is used as a fallback source for model metadata (e.g. for models deleted from CivitAI). Turn off to avoid CivArchive rate limits entirely.",
+      "providerOrder": "Metadata provider fallback order",
+      "providerOrderHelp": "CivitAI API is always tried first. Choose the order of the remaining providers when looking up metadata.",
+      "providerOrderCivitaiArchiveSqlite": "CivitAI → CivArchive → Archive DB",
+      "providerOrderCivitaiSqliteArchive": "CivitAI → Archive DB → CivArchive"
     },
     "proxySettings": {
       "enableProxy": "Enable App-level Proxy",
@@ -661,10 +671,18 @@
     "aiProvider": {
       "title": "AI Provider",
       "provider": "Provider",
-      "providerHelp": "Choose your LLM provider. OpenAI and Ollama use preset API endpoints. Custom lets you specify any OpenAI-compatible endpoint.",
-      "custom": "Custom (OpenAI-compatible)",
+      "providerHelp": "Choose your LLM provider. Preset providers set the API base URL automatically. Custom lets you specify any OpenAI-compatible endpoint.",
+      "providerOptions": {
+        "openai": "OpenAI",
+        "ollama": "Ollama (local)",
+        "deepseek": "DeepSeek",
+        "groq": "Groq",
+        "openrouter": "OpenRouter",
+        "opencode-go": "OpenCode Go",
+        "custom": "Custom (OpenAI-compatible)"
+      },
       "apiBase": "API Base URL",
-      "apiBaseHelp": "The base URL for the LLM API (e.g. https://api.openai.com/v1). Leave empty to use the provider default.",
+      "apiBaseHelp": "The base URL for the LLM API. Select a preset or enter a custom URL. The dropdown shows presets for all supported providers.",
       "apiBasePlaceholder": "https://api.openai.com/v1",
       "apiKey": "API Key",
       "apiKeyHelp": "Your LLM provider API key. Stored locally, never sent to any server except your chosen LLM provider.",
@@ -673,7 +691,8 @@
       "apiKeyConfigured": "Configured",
       "apiKeySet": "Set up",
       "model": "Model",
-      "modelHelp": "The model name to use (e.g. deepseek-v4-flash, gemini-2.5-flash, gemma4:12b). Check your provider for available models."
+      "modelHelp": "The model to use. Select from the dropdown (fetched from your provider) or type a custom model name.",
+      "modelPlaceholder": "Select a model..."
     }
   },
   "loras": {
@@ -772,12 +791,14 @@
         "complete": "Auto-organize complete",
         "error": "Error: {error}"
       },
-      "enrichHfAgent": "Enrich Metadata (Agent)"
+      "enrichHfAgent": "Enrich HF Metadata (AI)"
     },
     "contextMenu": {
       "refreshMetadata": "Refresh Civitai Data",
       "checkUpdates": "Check Updates",
-      "relinkCivitai": "Re-link to Civitai",
+      "linkModel": "Link Model",
+      "linkCivitai": "Link to Civitai",
+      "linkHuggingFace": "Link to HuggingFace",
       "copySyntax": "Copy LoRA Syntax",
       "copyFilename": "Copy Model Filename",
       "copyRecipeSyntax": "Copy Recipe Syntax",
@@ -797,7 +818,7 @@
       "viewAllLoras": "View All LoRAs",
       "downloadMissingLoras": "Download Missing LoRAs",
       "deleteRecipe": "Delete Recipe",
-      "enrichHfAgent": "Enrich Metadata (Agent)"
+      "enrichHfAgent": "Enrich HF Metadata (AI)"
     }
   },
   "recipes": {
@@ -1194,7 +1215,9 @@
         "preparing": "Preparing download...",
         "downloadedPreview": "Downloaded preview image",
         "downloadingFile": "Downloading {type} file",
-        "finalizing": "Finalizing download..."
+        "finalizing": "Finalizing download...",
+        "cancelling": "Cancelling download...",
+        "cancelled": "Download cancelled"
       },
       "progress": {
         "currentFile": "Current file:",
@@ -1310,6 +1333,14 @@
       "pathPlaceholder": "Type folder path or select from tree below...",
       "root": "Root"
     },
+    "linkHuggingFace": {
+      "title": "Link to HuggingFace",
+      "infoText": "Paste the HuggingFace repository URL to associate this model with its source. This enables AI-powered metadata enrichment.",
+      "urlLabel": "HuggingFace Repository URL:",
+      "urlPlaceholder": "https://huggingface.co/user/repo",
+      "helpText": "Enter the full URL of the HuggingFace repository.",
+      "confirmAction": "Save & Link"
+    },
     "relinkCivitai": {
       "title": "Re-link to Civitai",
       "warning": "Warning:",
@@ -1994,7 +2025,8 @@
       "imagesCompleted": "Example images {action} completed",
       "imagesFailed": "Example images {action} failed",
       "loadError": "Error loading downloads: {message}",
-      "downloadError": "Download error: {message}"
+      "downloadError": "Download error: {message}",
+      "downloadStopped": "Download cancelled"
     },
     "import": {
       "folderTreeFailed": "Failed to load folder tree",
@@ -2039,6 +2071,8 @@
       "contentRatingFailed": "Failed to set content rating: {message}",
       "relinkSuccess": "Model successfully re-linked to Civitai",
       "relinkFailed": "Error: {message}",
+      "linkHfSuccess": "Model successfully linked to HuggingFace",
+      "linkHfFailed": "Error: {message}",
       "fetchMetadataFirst": "Please fetch metadata from CivitAI first",
       "noCivitaiInfo": "No CivitAI information available",
       "missingHash": "Model hash not available"

py/config.py

@@ -177,8 +177,7 @@ class Config:
 
         # Load extra folder paths from active library settings before symlink scan
         # so both primary and extra paths are discovered in a single pass.
-        if not standalone_mode:
-            self._load_extra_paths_from_settings()
+        self._load_extra_paths_from_settings()
 
         # Scan symbolic links during initialization
         self._initialize_symlink_mappings()
@@ -193,7 +192,7 @@ class Config:
         Called during ``Config.__init__`` before the symlink scan so both primary and
         extra paths are discovered in a single pass.  Mirrors the extra-path
         portion of ``_apply_library_paths`` without replacing the primary roots
-        that were already resolved from ComfyUI's ``folder_paths``.
+        that were already resolved via ``folder_paths.get_folder_paths``.
         """
         try:
             from .services.settings_manager import get_settings_manager
@@ -209,6 +208,12 @@ class Config:
             if not isinstance(library_config, dict):
                 return
 
+            # Always read recipes_path — it is independent of extra folder paths
+            # and must be set before any early returns below.
+            recipes_path = library_config.get("recipes_path", "")
+            if isinstance(recipes_path, str) and recipes_path:
+                self.recipes_path = recipes_path
+
             extra_folder_paths = library_config.get("extra_folder_paths")
             if not isinstance(extra_folder_paths, dict):
                 return
@@ -234,10 +239,6 @@ class Config:
                 extra_embedding
             )
 
-            recipes_path = library_config.get("recipes_path", "")
-            if isinstance(recipes_path, str) and recipes_path:
-                self.recipes_path = recipes_path
-
             if self.extra_loras_roots:
                 logger.info(
                     "Found extra LoRA roots:"
@@ -358,6 +359,47 @@ class Config:
                         "Failed to rename legacy 'default' library: %s", rename_error
                     )
 
+            # Clean up a stale "default" library entry that has no meaningful
+            # paths configured (e.g. leftover bootstrap artifact).  This only
+            # fires when "comfyui" already exists so we never delete the last
+            # remaining library.
+            if (
+                "default" in libraries
+                and "comfyui" in libraries
+                and isinstance(default_library, Mapping)
+            ):
+                default_folder_paths = _normalize_library_folder_paths(
+                    default_library
+                )
+                default_extra_paths = default_library.get("extra_folder_paths", {})
+                has_meaningful_paths = bool(default_folder_paths) or bool(
+                    default_extra_paths
+                ) or any(
+                    default_library.get(key)
+                    for key in (
+                        "default_lora_root",
+                        "default_checkpoint_root",
+                        "default_unet_root",
+                        "default_embedding_root",
+                        "recipes_path",
+                    )
+                )
+                if not has_meaningful_paths:
+                    try:
+                        settings_service.delete_library("default")
+                        libraries_changed = True
+                        logger.info(
+                            "Removed stale 'default' library entry "
+                            "with no meaningful paths configured"
+                        )
+                        libraries = settings_service.get_libraries()
+                        comfy_library = libraries.get("comfyui", {})
+                    except Exception as delete_error:
+                        logger.debug(
+                            "Failed to remove stale 'default' library: %s",
+                            delete_error,
+                        )
+
             default_lora_root = _resolve_valid_default_root(
                 comfy_library.get("default_lora_root", ""),
                 list(self.loras_roots or []),

py/lora_manager.py

@@ -208,6 +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()

py/metadata_ops/__init__.py

@@ -1,4 +1,4 @@
-"""Agent CLI — thin in-process wrappers around LoRA Manager internal services.
+"""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
@@ -7,15 +7,15 @@ risk of double import or circular dependencies.
 
 Usage (in-process, primary)::
 
-    from py.agent_cli import list_base_models, read_metadata
+    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.agent_cli base-models list
-    python -m py.agent_cli metadata read /path/to/model.safetensors
+    python -m py.metadata_ops base-models list
+    python -m py.metadata_ops metadata read /path/to/model.safetensors
 """
 
 from __future__ import annotations
@@ -32,23 +32,26 @@ logger = logging.getLogger(__name__)
 # Helpers
 # ---------------------------------------------------------------------------
 
-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_TYPE_MAP: dict[str, str] = {
+    "get_lora_scanner": "lora",
+    "get_checkpoint_scanner": "checkpoint",
+    "get_embedding_scanner": "embedding",
+}
 
-    Iterates all known scanner types and returns the first one whose cache
-    contains the given path.  Returns ``(None, None)`` when no scanner
-    claims the model.
+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 (
-        "get_lora_scanner",
-        "get_checkpoint_scanner",
-        "get_embedding_scanner",
-    ):
+    for getter_name in SCANNER_GETTER_NAMES:
         getter = getattr(ServiceRegistry, getter_name, None)
         if getter is None:
             continue
@@ -59,15 +62,31 @@ async def _find_scanner_for_model(
             cache = await scanner.get_cached_data()
             for entry in cache.raw_data:
                 if os.path.normpath(entry.get("file_path", "")) == normalized:
-                    return scanner, entry
+                    return scanner, entry, getter_name
         except Exception as exc:
             logger.debug(
                 "Scanner %s check failed for %s: %s",
-                getter_name,
-                model_path,
-                exc,
+                getter_name, model_path, exc,
             )
-    return None, None
+    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"
 
 
 # ---------------------------------------------------------------------------
@@ -76,38 +95,29 @@ async def _find_scanner_for_model(
 
 
 async def list_base_models(limit: int = 0) -> List[str]:
-    """Return deduplicated base model names from all model caches.
+    """Return all valid CivitAI base model names.
 
-    The result is ordered by frequency (most common first).  Pass
-    *limit* = 0 (default) for all models.
+    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.service_registry import ServiceRegistry
+    from ..services.civitai_base_model_service import (
+        CivitaiBaseModelService,
+    )
 
-    counts: Dict[str, int] = {}
-    for getter_name in (
-        "get_lora_scanner",
-        "get_checkpoint_scanner",
-        "get_embedding_scanner",
-    ):
-        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:
-                bm = entry.get("base_model")
-                if bm:
-                    counts[bm] = counts.get(bm, 0) + 1
-        except Exception as exc:
-            logger.debug("list_base_models scanner %s error: %s", getter_name, exc)
-
-    sorted_names = [name for name, _ in sorted(counts.items(), key=lambda x: -x[1])]
+    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 sorted_names[:limit]
-    return sorted_names
+        return names[:limit]
+    return names
 
 
 async def read_metadata(model_path: str) -> Dict[str, Any]:
@@ -153,17 +163,17 @@ async def download_preview(
     *,
     target_width: int = 480,
     quality: int = 85,
-) -> bool:
+) -> 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 ``True`` on success.
+    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 False
+        return None
 
     base_name = os.path.splitext(os.path.basename(model_path))[0]
     preview_dir = os.path.dirname(model_path)
@@ -186,8 +196,7 @@ async def download_preview(
             )
             with open(output_path, "wb") as f:
                 f.write(optimized_data)
-            logger.info("Preview downloaded and optimised for %s", model_path)
-            return True
+            return output_path
         except Exception as exc:
             logger.warning("Preview optimisation failed, saving raw: %s", exc)
             # Fall through to raw save
@@ -196,12 +205,11 @@ async def download_preview(
     try:
         ok, _ = await downloader.download_file(url, output_path, use_auth=False)
         if ok:
-            logger.info("Preview downloaded (fallback) for %s", model_path)
-            return True
+            return output_path
     except Exception as exc:
         logger.warning("Preview fallback download failed for %s: %s", model_path, exc)
 
-    return False
+    return None
 
 
 async def refresh_cache(model_path: str) -> bool:

py/metadata_ops/__main__.py

@@ -1,17 +1,12 @@
-"""Subprocess entry point for AgentCLI (debugging / external use).
+"""Subprocess entry point for ``metadata_ops`` (debugging / external use).
 
 Usage::
 
-    python -m py.agent_cli base-models list [--limit N]
-    python -m py.agent_cli metadata read <path>
-    python -m py.agent_cli metadata update <path> --json '{...}'
-    python -m py.agent_cli preview download <path> --url <url>
-    python -m py.agent_cli cache refresh <path>
-
-NOTE: This is an **optional** convenience wrapper.  The primary consumer of
-AgentCLI is the :mod:`AgentService` (in-process).  This entry point exists
-for manual debugging and future integration with subprocess-based agent
-frameworks.
+    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

py/middleware/error_middleware.py

@@ -41,7 +41,12 @@ async def api_json_error(
         if exc.status < 400:
             raise
 
-        logger.warning(
+        # Preview 404 is routine (file deleted from disk) — not worth a warning.
+        logger_method = logger.warning
+        if request.path.startswith("/api/lm/previews") and exc.status == 404:
+            logger_method = logger.debug
+
+        logger_method(
             "API %s %s returned HTTP %d: %s",
             request.method,
             request.path,

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
@@ -14,6 +13,7 @@ from .utils import (
     extract_lora_name,
     get_loras_list,
     nunchaku_load_lora,
+    parse_lora_syntax,
 )
 
 logger = logging.getLogger(__name__)
@@ -189,25 +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_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/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
@@ -69,6 +70,25 @@ def extract_lora_name(lora_path):
     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):
     """Helper to extract loras list from either old or new kwargs format"""
     if "loras" not in kwargs:

py/routes/handlers/agent_handlers.py

@@ -60,21 +60,21 @@ class AgentHandler:
         skill_name = request.match_info.get("skill_name", "")
         if not skill_name:
             return web.json_response(
-                {"error": "Skill name is required"}, status_code=400
+                {"error": "Skill name is required"}, status=400
             )
 
         try:
             body = await request.json()
         except Exception:
             return web.json_response(
-                {"error": "Invalid JSON body"}, status_code=400
+                {"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_code=400,
+                status=400,
             )
 
         service = await self._ensure_service()
@@ -99,12 +99,11 @@ class AgentHandler:
         # Launch execution in the background
         progress_reporter = AgentProgressReporter()
         logger.info(
-            "Agent skill '%s' starting for %d model(s) in background task",
+            "LLM enrichment '%s' starting for %d model(s)",
             skill_name, len(model_paths),
         )
 
         async def _run() -> None:
-            logger.info("_run background task started for skill '%s'", skill_name)
             try:
                 result = await service.execute_skill(
                     skill_name=skill_name,
@@ -112,11 +111,11 @@ class AgentHandler:
                     progress_callback=progress_reporter,
                 )
                 logger.info(
-                    "Agent skill '%s' finished: success=%s, summary='%s', errors=%s",
+                    "LLM enrichment '%s' finished: success=%s, summary='%s', errors=%s",
                     skill_name, result.success, result.summary, result.errors,
                 )
             except LLMNotConfiguredError as exc:
-                logger.warning("Agent skill '%s' not configured: %s", skill_name, exc)
+                logger.warning("LLM enrichment '%s' not configured: %s", skill_name, exc)
                 await progress_reporter.on_progress(
                     {
                         "type": "agent_progress",
@@ -126,7 +125,7 @@ class AgentHandler:
                     }
                 )
             except Exception as exc:
-                logger.error("Agent skill '%s' failed: %s", skill_name, exc, exc_info=True)
+                logger.error("LLM enrichment '%s' failed: %s", skill_name, exc, exc_info=True)
                 await progress_reporter.on_progress(
                     {
                         "type": "agent_progress",
@@ -137,8 +136,7 @@ class AgentHandler:
                 )
 
         # Fire and forget — progress comes via WebSocket
-        task = asyncio.create_task(_run())
-        logger.info("Agent skill '%s' background task created (id=%s)", skill_name, task)
+        asyncio.create_task(_run())
 
         return web.json_response(
             {
@@ -163,5 +161,5 @@ class AgentHandler:
         # TODO: implement cooperative cancellation in AgentService
         return web.json_response(
             {"status": "acknowledged", "note": "Cancellation not yet implemented"},
-            status_code=200,
+            status=200,
         )

py/routes/handlers/hf_handlers.py

@@ -122,8 +122,12 @@ async def _save_hf_metadata(dest_path: str, repo: str, model_root: str) -> None:
         metadata._unknown_fields["hf_url"] = hf_url
         metadata.from_civitai = False  # HF models are not from CivitAI
 
+        metadata_dict = metadata.to_dict()
+        if "trainedWords" in metadata_dict and not metadata_dict["trainedWords"]:
+            del metadata_dict["trainedWords"]
+
         # 3. Save metadata atomically
-        await MetadataManager.save_metadata(dest_path, metadata)
+        await MetadataManager.save_metadata(dest_path, metadata_dict)
         logger.info("Saved HF metadata (with hf_url) for %s", dest_path)
 
         # 4. Determine relative folder path for cache
@@ -147,9 +151,117 @@ async def _save_hf_metadata(dest_path: str, repo: str, model_root: str) -> None:
         logger.warning("Failed to save HF metadata for %s: %s", dest_path, exc)
 
 
+def _find_matching_root(dest_dir: str) -> str | None:
+    """Walk up *dest_dir* to find which configured scanner root it belongs to."""
+    norm = os.path.normpath(dest_dir).replace(os.sep, "/")
+    all_roots = []
+    for root_list in (
+        config.loras_roots or [],
+        config.extra_loras_roots or [],
+        config.checkpoints_roots or [],
+        config.extra_checkpoints_roots or [],
+        config.unet_roots or [],
+        config.extra_unet_roots or [],
+        config.embeddings_roots or [],
+        config.extra_embeddings_roots or [],
+    ):
+        all_roots.extend([os.path.normpath(p).replace(os.sep, "/") for p in root_list])
+    # Find the longest matching prefix
+    match: str | None = None
+    for root in all_roots:
+        if norm.startswith(root):
+            if match is None or len(root) > len(match):
+                match = root
+    return match
+
+
+async def _add_to_scanner_cache(dest_path: str, metadata: dict[str, Any]) -> None:
+    model_dir = os.path.dirname(dest_path)
+    model_root = _find_matching_root(model_dir)
+    if not model_root:
+        raise ValueError(f"File path {dest_path} is not within any configured scanner root")
+    scanner_getter_name = _infer_model_type(model_root)[1]
+    scanner_getter = getattr(ServiceRegistry, scanner_getter_name, None)
+    if scanner_getter is None:
+        raise RuntimeError(f"Scanner getter '{scanner_getter_name}' not found in ServiceRegistry")
+    scanner = await scanner_getter()
+    if scanner is None:
+        raise RuntimeError(f"Scanner '{scanner_getter_name}' returned None")
+    await scanner.update_single_model_cache(dest_path, dest_path, metadata)
+
+
 class HfHandler:
     """Handle Hugging Face model browsing and download."""
 
+    async def set_hf_url(self, request: web.Request) -> web.Response:
+        try:
+            payload: dict[str, Any] = await request.json()
+        except json.JSONDecodeError:
+            return web.json_response({"success": False, "error": "Invalid JSON"}, status=400)
+
+        file_path = (payload.get("file_path") or "").strip()
+        hf_url = (payload.get("hf_url") or "").strip()
+
+        if not file_path or not hf_url:
+            return web.json_response(
+                {"success": False, "error": "Missing required fields: 'file_path' and 'hf_url'"},
+                status=400,
+            )
+
+        m = re.match(r"^https?://huggingface\.co/([^/]+/[^/]+)/?$", hf_url)
+        if not m:
+            return web.json_response(
+                {
+                    "success": False,
+                    "error": "Invalid HuggingFace URL. Expected format: https://huggingface.co/user/repo",
+                },
+                status=400,
+            )
+
+        if not os.path.isfile(file_path):
+            return web.json_response(
+                {"success": False, "error": f"File not found: {file_path}"},
+                status=404,
+            )
+
+        model_root = _find_matching_root(os.path.dirname(file_path))
+        if not model_root:
+            return web.json_response(
+                {
+                    "success": False,
+                    "error": "File is not within any configured model directory. Cannot link to HuggingFace.",
+                },
+                status=400,
+            )
+
+        try:
+            existing = await MetadataManager.load_metadata_payload(file_path)
+            if existing.get("hf_url") == hf_url:
+                return web.json_response({
+                    "success": True,
+                    "message": "hf_url already set",
+                    "hf_url": hf_url,
+                })
+
+            existing["hf_url"] = hf_url
+            existing["from_civitai"] = False
+            await MetadataManager.save_metadata(file_path, existing)
+
+            await _add_to_scanner_cache(file_path, existing)
+
+            logger.info("Set hf_url=%s for %s", hf_url, file_path)
+            return web.json_response({
+                "success": True,
+                "message": f"hf_url set to {hf_url}",
+                "hf_url": hf_url,
+            })
+        except Exception as exc:
+            logger.error("Failed to set hf_url for %s: %s", file_path, exc)
+            return web.json_response(
+                {"success": False, "error": str(exc)},
+                status=500,
+            )
+
     async def get_hf_repo_files(self, request: web.Request) -> web.Response:
         """List model-weight files from a HF repo with real file sizes.
 
@@ -251,8 +363,8 @@ class HfHandler:
         if ".." in (author, repo_name) or "." in (author, repo_name):
             return web.json_response({"error": f"Invalid repo format: {repo}"}, status=400)
 
-        # Validate filename — must not contain path separators or ..
-        if "/" in filename or "\\" in filename or ".." in filename:
+        # Validate filename — must not contain path traversal
+        if ".." in filename:
             return web.json_response({"error": "Invalid filename"}, status=400)
 
         # Validate relative_path — must not be absolute or escape base directory
@@ -262,35 +374,17 @@ class HfHandler:
             if ".." in relative_path.split("/") or "\\" in relative_path:
                 return web.json_response({"error": "Invalid relative_path"}, status=400)
 
-        # Validate model_root — must not contain path traversal
-        if not os.path.isabs(model_root):
-            # For relative model_root, check it doesn't escape
-            resolved_model_root = os.path.realpath(
-                os.path.join(os.getcwd(), "models", model_root)
-            )
+        # Use model_root directly as the base directory — same approach as
+        # CivitAI's download path (download_manager.py).  No realpath, no
+        # allowed-roots validation, no path-traversal check; those are
+        # unnecessary when the frontend sends the path from its own dropdown
+        # (populated from scanner roots).  Using the "business path" directly
+        # keeps dest_path consistent with scanner roots so that later folder
+        # derivation (in _save_hf_metadata) works correctly.
+        if os.path.isabs(model_root):
+            base_dir = os.path.normpath(model_root)
         else:
-            resolved_model_root = os.path.realpath(model_root)
-
-        # Verify model_root is within a configured scanner root
-        allowed_roots = set()
-        for root_list in (
-            config.loras_roots or [],
-            config.extra_loras_roots or [],
-            config.checkpoints_roots or [],
-            config.extra_checkpoints_roots or [],
-            config.unet_roots or [],
-            config.extra_unet_roots or [],
-            config.embeddings_roots or [],
-            config.extra_embeddings_roots or [],
-        ):
-            for r in root_list:
-                allowed_roots.add(os.path.realpath(r))
-
-        if not any(resolved_model_root == root or resolved_model_root.startswith(root + os.sep) for root in allowed_roots):
-            logger.warning("Invalid model_root rejected: %s", model_root)
-            return web.json_response({"error": f"Invalid model_root: {model_root}"}, status=400)
-
-        base_dir = resolved_model_root
+            base_dir = os.path.normpath(os.path.join(os.getcwd(), "models", model_root))
 
         if use_default_paths:
             target_dir = os.path.join(base_dir, "huggingface", author, repo_name)
@@ -299,15 +393,12 @@ class HfHandler:
         else:
             target_dir = base_dir
 
-        os.makedirs(target_dir, exist_ok=True)
-        dest_path = os.path.join(target_dir, filename)
+        # Strip HF repo subdirectory — "diffusion_models/xxx.safetensors"
+        # is an HF repo convention, not meaningful for local storage.
+        file_base = os.path.basename(filename)
 
-        # Resolve symlinks and check for path traversal escape
-        real_dest = os.path.realpath(dest_path)
-        real_base = os.path.realpath(target_dir)
-        if not real_dest.startswith(real_base + os.sep):
-            logger.warning("Path traversal blocked: %s -> %s", dest_path, real_dest)
-            return web.json_response({"error": "Path traversal detected"}, status=400)
+        os.makedirs(target_dir, exist_ok=True)
+        dest_path = os.path.join(target_dir, file_base)
 
         # Check if already exists (simple skip)
         if os.path.exists(dest_path) and os.path.getsize(dest_path) > 0:

py/routes/handlers/misc_handlers.py

@@ -38,6 +38,12 @@ from ...services.settings_manager import get_settings_manager
 from ...services.websocket_manager import ws_manager
 from ...services.downloader import get_downloader
 from ...services.errors import ResourceNotFoundError
+from ...services.llm_service import (
+    PROVIDER_PRESETS,
+    fetch_ollama_models,
+    get_all_provider_models,
+    get_provider_model_ids,
+)
 from ...services.cache_health_monitor import CacheHealthMonitor, CacheHealthStatus
 from ...utils.models import BaseModelMetadata
 from ...utils.constants import (
@@ -567,12 +573,18 @@ class NodeRegistry:
             tab_nodes[nd["unique_id"]] = nd
 
         async with self._lock:
+            prev_count = len(self._tab_nodes.get(sid, {}))
             self._tab_nodes[sid] = tab_nodes
             self._waiting_clients.discard(sid)
             if not self._waiting_clients:
                 self._ready.set()
+            total_tabs = len(self._tab_nodes)
 
-        logger.debug("Registered %s nodes from client %s", len(nodes), sid)
+        if len(nodes) != prev_count or len(nodes) > 0:
+            logger.debug(
+                "[LM:Registry] stored %s nodes (was %s) for client %s (total tabs: %s)",
+                len(nodes), prev_count, sid, total_tabs,
+            )
 
     def prepare_for_refresh(self, active_sids: list[str]) -> None:
         """Set the list of client IDs we expect to hear from during the next refresh cycle."""
@@ -595,10 +607,17 @@ class NodeRegistry:
         longer connected."""
         async with self._lock:
             # Garbage-collect stale entries (disconnected tabs)
+            stale_sids = []
             if active_sids is not None:
                 for sid in list(self._tab_nodes):
                     if sid not in active_sids:
+                        stale_sids.append(sid)
                         del self._tab_nodes[sid]
+            if stale_sids:
+                logger.debug(
+                    "[LM:Registry] GC pruned %s disconnected tabs: %s",
+                    len(stale_sids), stale_sids,
+                )
 
             merged: dict[str, dict] = {}
             tab_info: dict[str, dict] = {}
@@ -1400,8 +1419,9 @@ class SettingsHandler:
             "libraries",
             "active_library",
             # Sensitive — never expose the actual value to the frontend;
-            # frontend receives a boolean instead (civitai_api_key_set).
+            # frontend receives a boolean instead (*_set).
             "civitai_api_key",
+            "llm_api_key",
         }
     )
 
@@ -1459,6 +1479,8 @@ class SettingsHandler:
             # Sensitive fields: only expose a boolean indicating whether set
             raw_key = self._settings.get("civitai_api_key")
             response_data["civitai_api_key_set"] = bool(raw_key)
+            raw_llm_key = self._settings.get("llm_api_key")
+            response_data["llm_api_key_set"] = bool(raw_llm_key)
             settings_file = getattr(self._settings, "settings_file", None)
             if settings_file:
                 response_data["settings_file"] = settings_file
@@ -1548,7 +1570,11 @@ class SettingsHandler:
                 else:
                     self._settings.set(key, value)
 
-                if key == "enable_metadata_archive_db":
+                if key in (
+                    "enable_metadata_archive_db",
+                    "enable_civarchive_api",
+                    "metadata_provider_order",
+                ):
                     await self._metadata_provider_updater()
 
                 if key in self._PROXY_KEYS:
@@ -1563,6 +1589,42 @@ class SettingsHandler:
             logger.error("Error updating settings: %s", exc, exc_info=True)
             return web.Response(status=500, text=str(exc))
 
+    async def get_llm_models(self, request: web.Request) -> web.Response:
+        """Return the model list for a provider.
+
+        For ``ollama`` the list is fetched live from the local Ollama API
+        (only models actually pulled locally are shown).  For all other
+        providers the opencode model catalog is used.
+
+        Query parameters:
+            provider (required): Internal provider id (``openai``, ``ollama``, etc.).
+
+        Returns:
+            ``{"success": true, "models": ["gpt-4o", ...]}``.
+        """
+        provider_id = request.query.get("provider", "").strip()
+        if not provider_id:
+            return web.json_response(
+                {"success": False, "error": "provider query parameter is required", "models": []},
+                status=400,
+            )
+
+        try:
+            if provider_id == "ollama":
+                api_base = request.query.get("api_base", "").strip() or self._settings.get("llm_api_base", "")
+                if not api_base:
+                    api_base = "http://localhost:11434/v1"
+                models = await fetch_ollama_models(api_base)
+            else:
+                models = await get_provider_model_ids(provider_id)
+            return web.json_response({"success": True, "models": models})
+        except Exception as exc:
+            logger.warning("get_llm_models failed for %s: %s", provider_id, exc)
+            return web.json_response(
+                {"success": False, "error": str(exc), "models": []},
+                status=500,
+            )
+
     def _validate_example_images_path(self, folder_path: str) -> str | None:
         if not os.path.exists(folder_path):
             return f"Path does not exist: {folder_path}"
@@ -1585,6 +1647,20 @@ class SettingsHandler:
     def _is_dedicated_example_images_folder(self, folder_path: str) -> bool:
         return is_valid_example_images_root(folder_path)
 
+    async def get_provider_models(self, request: web.Request) -> web.Response:
+        """Return the model catalog for all preset providers.
+
+        This endpoint is called asynchronously by the settings UI so that
+        page rendering never blocks on the remote model catalog fetch.
+        """
+        catalog_provider_ids = [p for p in PROVIDER_PRESETS if p != "custom"]
+        try:
+            provider_models = await get_all_provider_models(catalog_provider_ids)
+            return web.json_response({"success": True, "models": provider_models})
+        except Exception as exc:
+            logger.warning("Failed to fetch provider models: %s", exc)
+            return web.json_response({"success": False, "models": {}, "error": str(exc)})
+
 
 class UsageStatsHandler:
     def __init__(self, usage_stats_factory: UsageStatsFactory = UsageStats) -> None:
@@ -1712,6 +1788,124 @@ class LoraCodeHandler:
             logger.error("Failed to update lora code: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
+    async def get_update_lora_code(self, request: web.Request) -> web.Response:
+        """GET version of update_lora_code — reads parameters from query string.
+
+        Query params:
+          lora_code (required)  — the LoRA syntax to send
+          mode     (optional)   — "append" (default) or "replace"
+          node_id  (repeatable) — target node id(s), e.g. node_id=3&node_id=5
+          node_ids (optional)   — JSON-encoded array for complex references with graph_id:
+                                   [{"node_id":3,"graph_id":"g1"}, ...]
+        """
+        try:
+            node_ids_raw = request.query.get("node_ids")
+            node_id_list = request.query.getall("node_id", [])
+            lora_code = request.query.get("lora_code", "")
+            mode = request.query.get("mode", "append")
+
+            if not lora_code:
+                return web.json_response(
+                    {"success": False, "error": "Missing lora_code parameter"},
+                    status=400,
+                )
+
+            node_ids = None
+            if node_ids_raw:
+                try:
+                    node_ids = json.loads(node_ids_raw)
+                except (json.JSONDecodeError, TypeError):
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a valid JSON array"},
+                        status=400,
+                    )
+                if not isinstance(node_ids, list) or not node_ids:
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a non-empty JSON array"},
+                        status=400,
+                    )
+            elif node_id_list:
+                node_ids = node_id_list
+
+            results = []
+            if node_ids is None:
+                try:
+                    self._prompt_server.instance.send_sync(
+                        "lora_code_update",
+                        {"id": -1, "lora_code": lora_code, "mode": mode},
+                    )
+                    results.append({"node_id": "broadcast", "success": True})
+                except Exception as exc:  # pragma: no cover - defensive logging
+                    logger.error("Error broadcasting lora code: %s", exc)
+                    results.append(
+                        {"node_id": "broadcast", "success": False, "error": str(exc)}
+                    )
+            else:
+                for entry in node_ids:
+                    node_identifier = entry
+                    graph_identifier = None
+                    if isinstance(entry, dict):
+                        node_identifier = entry.get("node_id")
+                        graph_identifier = entry.get("graph_id")
+
+                    if node_identifier is None:
+                        results.append(
+                            {
+                                "node_id": node_identifier,
+                                "graph_id": graph_identifier,
+                                "success": False,
+                                "error": "Missing node_id parameter",
+                            }
+                        )
+                        continue
+
+                    try:
+                        parsed_node_id = int(node_identifier)
+                    except (TypeError, ValueError):
+                        parsed_node_id = node_identifier
+
+                    payload = {
+                        "id": parsed_node_id,
+                        "lora_code": lora_code,
+                        "mode": mode,
+                    }
+
+                    if graph_identifier is not None:
+                        payload["graph_id"] = str(graph_identifier)
+
+                    try:
+                        self._prompt_server.instance.send_sync(
+                            "lora_code_update",
+                            payload,
+                        )
+                        results.append(
+                            {
+                                "node_id": parsed_node_id,
+                                "graph_id": payload.get("graph_id"),
+                                "success": True,
+                            }
+                        )
+                    except Exception as exc:  # pragma: no cover - defensive logging
+                        logger.error(
+                            "Error sending lora code to node %s (graph %s): %s",
+                            parsed_node_id,
+                            graph_identifier,
+                            exc,
+                        )
+                        results.append(
+                            {
+                                "node_id": parsed_node_id,
+                                "graph_id": payload.get("graph_id"),
+                                "success": False,
+                                "error": str(exc),
+                            }
+                        )
+
+            return web.json_response({"success": True, "results": results})
+        except Exception as exc:  # pragma: no cover - defensive logging
+            logger.error("Failed to update lora code (GET): %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
 
 class TrainedWordsHandler:
     async def get_trained_words(self, request: web.Request) -> web.Response:
@@ -3057,6 +3251,8 @@ class NodeRegistryHandler:
         self._node_registry = node_registry
         self._prompt_server = prompt_server
         self._standalone_mode = standalone_mode
+        self._refresh_lock = asyncio.Lock()
+        self._last_slow_path_ts: float = 0.0
 
     async def register_nodes(self, request: web.Request) -> web.Response:
         try:
@@ -3103,7 +3299,12 @@ class NodeRegistryHandler:
                     )
                 graph_name = node.get("graph_name")
                 try:
-                    node["node_id"] = int(node_id)
+                    # Handle compound node IDs from expanded group subgraphs,
+                    # e.g. "252:0" → 0 (parent scope is already in graph_id)
+                    if isinstance(node_id, str) and ":" in node_id:
+                        node["node_id"] = int(node_id.rsplit(":", 1)[-1])
+                    else:
+                        node["node_id"] = int(node_id)
                 except (TypeError, ValueError):
                     return web.json_response(
                         {
@@ -3144,42 +3345,101 @@ class NodeRegistryHandler:
                     status=503,
                 )
 
-            # Snapshot of currently-connected ComfyUI tabs
-            active_sids = list(self._prompt_server.instance.sockets.keys())
-            self._node_registry.prepare_for_refresh(active_sids)
-
-            try:
-                self._prompt_server.instance.send_sync("lora_registry_refresh", {})
-                logger.debug(
-                    "Sent registry refresh request (expecting %s clients)", len(active_sids)
-                )
-            except Exception as exc:
-                logger.error("Failed to send registry refresh message: %s", exc)
-                return web.json_response(
-                    {
-                        "success": False,
-                        "error": "Communication Error",
-                        "message": f"Failed to communicate with ComfyUI frontend: {exc}",
-                    },
-                    status=500,
-                )
-
-            if not await self._node_registry.wait_for_all(timeout=2.0):
-                logger.warning(
-                    "Registry refresh timeout after 2s (%s/%s clients responded)",
-                    len(active_sids) - self._node_registry.pending_client_count,
-                    len(active_sids),
-                )
-
-            # Re-read current sockets after the wait: a tab may have connected
-            # while we were waiting, and we don't want to garbage-collect it.
             current_sids = set(self._prompt_server.instance.sockets.keys())
+
+            # Fast path: if the frontend has already pushed node data (via
+            # afterConfigureGraph / graphChanged hooks), return it immediately
+            # without triggering a WebSocket round-trip.
             registry_info = await self._node_registry.get_merged_registry(
                 active_sids=current_sids
             )
+            if registry_info["tab_count"] > 0:
+                logger.debug(
+                    "[LM:Registry] fast path: %s nodes across %s tabs %s",
+                    registry_info["node_count"],
+                    registry_info["tab_count"],
+                    dict(registry_info.get("tabs", {})),
+                )
+                return web.json_response({"success": True, "data": registry_info})
+
+            # Slow path: registry is empty — trigger refresh via WebSocket.
+            # Serialize with an async lock so concurrent callers don't all
+            # trigger separate WS refresh cycles.  The second caller will
+            # re-check the fast path and (usually) find populated data.
+            async with self._refresh_lock:
+                # Re-check after acquiring the lock — another concurrent call
+                # may have populated the cache while we were waiting.
+                registry_info = await self._node_registry.get_merged_registry(
+                    active_sids=current_sids
+                )
+                if registry_info["tab_count"] > 0:
+                    logger.debug(
+                        "[LM:Registry] fast path after lock wait: %s nodes across %s tabs",
+                        registry_info["node_count"],
+                        registry_info["tab_count"],
+                    )
+                    return web.json_response({"success": True, "data": registry_info})
+
+                # Cooldown: if the slow path ran recently (< 2 s) and
+                # returned empty, skip another WS round-trip.
+                elapsed = time.monotonic() - self._last_slow_path_ts
+                if elapsed < 2.0:
+                    logger.debug(
+                        "[LM:Registry] slow path cooldown (%.1fs since last refresh), returning empty",
+                        elapsed,
+                    )
+                    return web.json_response(
+                        {
+                            "success": False,
+                            "error": "Empty Registry",
+                            "message": "No workflow nodes found — ensure ComfyUI is open and the extension is loaded.",
+                        },
+                        status=408,
+                    )
+
+                logger.debug(
+                    "[LM:Registry] slow path: cache empty, triggering WS refresh (%s connected tabs: %s)",
+                    len(current_sids), list(current_sids)[:5],
+                )
+                active_sids = list(current_sids)
+                self._node_registry.prepare_for_refresh(active_sids)
+
+                try:
+                    self._prompt_server.instance.send_sync("lora_registry_refresh", {})
+                    logger.debug(
+                        "Sent registry refresh request (expecting %s clients)", len(active_sids)
+                    )
+                except Exception as exc:
+                    logger.error("Failed to send registry refresh message: %s", exc)
+                    return web.json_response(
+                        {
+                            "success": False,
+                            "error": "Communication Error",
+                            "message": f"Failed to communicate with ComfyUI frontend: {exc}",
+                        },
+                        status=500,
+                    )
+
+                if not await self._node_registry.wait_for_all(timeout=0.5):
+                    logger.warning(
+                        "Registry refresh timeout after 0.5s (%s/%s clients responded)",
+                        len(active_sids) - self._node_registry.pending_client_count,
+                        len(active_sids),
+                    )
+
+                # Re-read current sockets after the wait: a tab may have connected
+                # while we were waiting, and we don't want to garbage-collect it.
+                current_sids = set(self._prompt_server.instance.sockets.keys())
+                registry_info = await self._node_registry.get_merged_registry(
+                    active_sids=current_sids
+                )
+                self._last_slow_path_ts = time.monotonic()
 
             if registry_info["node_count"] == 0:
-                logger.warning("No nodes registered after refresh")
+                logger.debug(
+                    "[LM:Registry] refresh OK — %s connected tab(s) but 0 compatible nodes found",
+                    registry_info["tab_count"],
+                )
                 return web.json_response(
                     {
                         "success": False,
@@ -3215,7 +3475,7 @@ class NodeRegistryHandler:
                     status=400,
                 )
 
-            if not isinstance(value, str) or not value:
+            if value is None or (isinstance(value, str) and not value):
                 return web.json_response(
                     {"success": False, "error": "Missing value parameter"}, status=400
                 )
@@ -3293,6 +3553,130 @@ class NodeRegistryHandler:
             logger.error("Failed to update node widget: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
+    async def get_update_node_widget(self, request: web.Request) -> web.Response:
+        """GET version of update_node_widget — reads parameters from query string.
+
+        Query params:
+          widget_name  (optional)   — the widget name to update (required unless action is set)
+          action       (optional)   — alternative action, e.g. "inject_text" (required unless widget_name is set)
+          value        (required)   — the value to set
+          mode         (optional)   — "replace" (default) or "append"
+          node_id      (repeatable) — target node id(s), e.g. node_id=3&node_id=5
+          node_ids     (optional)   — JSON-encoded array for complex references:
+                                       [{"node_id":3,"graph_id":"g1"}, ...]
+        """
+        try:
+            widget_name = request.query.get("widget_name")
+            action = request.query.get("action")
+            value = request.query.get("value")
+            mode = request.query.get("mode", "replace")
+            node_ids_raw = request.query.get("node_ids")
+            node_id_list = request.query.getall("node_id", [])
+
+            if not action and (not isinstance(widget_name, str) or not widget_name):
+                return web.json_response(
+                    {
+                        "success": False,
+                        "error": "Missing parameter: provide either 'action' or 'widget_name'",
+                    },
+                    status=400,
+                )
+
+            if value is None or (isinstance(value, str) and not value):
+                return web.json_response(
+                    {"success": False, "error": "Missing value parameter"}, status=400
+                )
+
+            node_ids = None
+            if node_ids_raw:
+                try:
+                    node_ids = json.loads(node_ids_raw)
+                except (json.JSONDecodeError, TypeError):
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a valid JSON array"},
+                        status=400,
+                    )
+                if not isinstance(node_ids, list) or not node_ids:
+                    return web.json_response(
+                        {"success": False, "error": "node_ids must be a non-empty JSON array"},
+                        status=400,
+                    )
+            elif node_id_list:
+                node_ids = node_id_list
+
+            if not isinstance(node_ids, list) or not node_ids:
+                return web.json_response(
+                    {"success": False, "error": "node_ids must be a non-empty list"},
+                    status=400,
+                )
+
+            results = []
+            for entry in node_ids:
+                node_identifier = entry
+                graph_identifier = None
+                if isinstance(entry, dict):
+                    node_identifier = entry.get("node_id")
+                    graph_identifier = entry.get("graph_id")
+
+                if node_identifier is None:
+                    results.append(
+                        {
+                            "node_id": node_identifier,
+                            "graph_id": graph_identifier,
+                            "success": False,
+                            "error": "Missing node_id parameter",
+                        }
+                    )
+                    continue
+
+                try:
+                    parsed_node_id = int(node_identifier)
+                except (TypeError, ValueError):
+                    parsed_node_id = node_identifier
+
+                payload: dict = {
+                    "id": parsed_node_id,
+                    "value": value,
+                    "mode": mode,
+                }
+                if action:
+                    payload["action"] = action
+                if widget_name:
+                    payload["widget_name"] = widget_name
+
+                if graph_identifier is not None:
+                    payload["graph_id"] = str(graph_identifier)
+
+                try:
+                    self._prompt_server.instance.send_sync("lm_widget_update", payload)
+                    results.append(
+                        {
+                            "node_id": parsed_node_id,
+                            "graph_id": payload.get("graph_id"),
+                            "success": True,
+                        }
+                    )
+                except Exception as exc:  # pragma: no cover - defensive logging
+                    logger.error(
+                        "Error sending widget update to node %s (graph %s): %s",
+                        parsed_node_id,
+                        graph_identifier,
+                        exc,
+                    )
+                    results.append(
+                        {
+                            "node_id": parsed_node_id,
+                            "graph_id": payload.get("graph_id"),
+                            "success": False,
+                            "error": str(exc),
+                        }
+                    )
+
+            return web.json_response({"success": True, "results": results})
+        except Exception as exc:  # pragma: no cover - defensive logging
+            logger.error("Failed to update node widget (GET): %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
 
 class MiscHandlerSet:
     """Aggregate handlers into a lookup compatible with the registrar."""
@@ -3354,13 +3738,17 @@ class MiscHandlerSet:
             "get_priority_tags": self.settings.get_priority_tags,
             "get_settings_libraries": self.settings.get_libraries,
             "activate_library": self.settings.activate_library,
+            "get_llm_models": self.settings.get_llm_models,
+            "get_provider_models": self.settings.get_provider_models,
             "update_usage_stats": self.usage_stats.update_usage_stats,
             "get_usage_stats": self.usage_stats.get_usage_stats,
             "update_lora_code": self.lora_code.update_lora_code,
+            "get_update_lora_code": self.lora_code.get_update_lora_code,
             "get_trained_words": self.trained_words.get_trained_words,
             "get_model_example_files": self.model_examples.get_model_example_files,
             "register_nodes": self.node_registry.register_nodes,
             "update_node_widget": self.node_registry.update_node_widget,
+            "get_update_node_widget": self.node_registry.get_update_node_widget,
             "get_registry": self.node_registry.get_registry,
             "check_model_exists": self.model_library.check_model_exists,
             "check_models_exist": self.model_library.check_models_exist,
@@ -3387,6 +3775,7 @@ class MiscHandlerSet:
             # Hugging Face handlers
             "get_hf_repo_files": self.hf_handler.get_hf_repo_files,
             "download_hf_model": self.hf_handler.download_hf_model,
+            "set_hf_url": self.hf_handler.set_hf_url,
             # Agent skill handlers
             "get_agent_skills": self.agent_handler.get_agent_skills,
             "execute_agent_skill": self.agent_handler.execute_agent_skill,

py/routes/handlers/model_handlers.py

@@ -154,6 +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,
@@ -161,6 +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:
@@ -963,6 +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:
@@ -971,6 +983,22 @@ class ModelQueryHandler:
                 {"success": False, "error": "Internal server error"}, status=500
             )
 
+    async def search_tags(self, request: web.Request) -> web.Response:
+        try:
+            query = request.query.get("q", "")
+            limit = int(request.query.get("limit", "20"))
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+            tags = await self._service.search_tags(query, limit)
+            return web.json_response({"success": True, "tags": tags})
+        except Exception as exc:
+            self._logger.error("Error searching tags: %s", exc, exc_info=True)
+            return web.json_response(
+                {"success": False, "error": "Internal server error"}, status=500
+            )
+
     async def get_base_models(self, request: web.Request) -> web.Response:
         try:
             limit = int(request.query.get("limit", "20"))
@@ -1265,9 +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,
@@ -1303,9 +1335,20 @@ class ModelQueryHandler:
                 }
                 if include_license_flags:
                     model_data = await self._service.get_model_info_by_name(model_name)
-                    license_flags = (model_data or {}).get("license_flags")
-                    if license_flags is not None:
-                        response_payload["license_flags"] = int(license_flags)
+                    # Only return license_flags when real CivitAI model license
+                    # data exists. This mirrors ModelModal's guard
+                    # (modelData?.civitai?.model) so the preview tooltip never
+                    # shows misleading license icons for HF or other models
+                    # without actual license metadata.
+                    civitai_data = (model_data or {}).get("civitai") or {}
+                    has_license_data = (
+                        isinstance(civitai_data, dict)
+                        and isinstance(civitai_data.get("model"), dict)
+                    )
+                    if has_license_data:
+                        license_flags = (model_data or {}).get("license_flags")
+                        if license_flags is not None:
+                            response_payload["license_flags"] = int(license_flags)
                     # Include the user's license icon style preference so the
                     # ComfyUI tooltip can pick the right set without a separate
                     # API call.
@@ -1762,14 +1805,20 @@ class ModelDownloadHandler:
 
     async def delete_download_history_item(self, request: web.Request) -> web.Response:
         try:
-            item_id = int(request.query.get("id", "0"))
-            if not item_id:
+            download_id = request.query.get("download_id")
+            id_str = request.query.get("id")
+            item_id = int(id_str) if id_str else None
+
+            if not download_id and not item_id:
                 return web.json_response(
-                    {"success": False, "error": "id is required"}, status=400
+                    {"success": False, "error": "id or download_id is required"},
+                    status=400,
                 )
 
             service = await DownloadQueueService.get_instance()
-            deleted = await service.delete_history_item(item_id)
+            deleted = await service.delete_history_item(
+                id=item_id, download_id=download_id
+            )
             return web.json_response({"success": deleted})
         except Exception as exc:
             self._logger.error(
@@ -1779,14 +1828,20 @@ class ModelDownloadHandler:
 
     async def retry_download_from_history(self, request: web.Request) -> web.Response:
         try:
-            item_id = int(request.query.get("id", "0"))
-            if not item_id:
+            download_id = request.query.get("download_id")
+            id_str = request.query.get("id")
+            item_id = int(id_str) if id_str else None
+
+            if not download_id and not item_id:
                 return web.json_response(
-                    {"success": False, "error": "id is required"}, status=400
+                    {"success": False, "error": "id or download_id is required"},
+                    status=400,
                 )
 
             service = await DownloadQueueService.get_instance()
-            item = await service.retry_from_history(item_id)
+            item = await service.retry_from_history(
+                item_id=item_id, download_id=download_id
+            )
             if item is None:
                 return web.json_response(
                     {"success": False, "error": "History item not found or not retryable"},
@@ -2910,6 +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,

py/routes/handlers/preview_handlers.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import asyncio
 import logging
 import mimetypes
 import urllib.parse
@@ -53,6 +54,7 @@ class PreviewHandler:
 
         if not resolved.is_file():
             logger.debug("Preview file not found at %s", str(resolved))
+            asyncio.create_task(self._cleanup_stale_preview_url(normalized))
             raise web.HTTPNotFound(text="Preview file not found")
 
         # aiohttp's FileResponse handles range requests, content headers, and
@@ -69,6 +71,35 @@ class PreviewHandler:
         resp.headers["Cache-Control"] = "public, max-age=86400"
         return resp
 
+    async def _cleanup_stale_preview_url(self, normalized_preview_path: str) -> None:
+        """Fire-and-forget: clear stale preview_url from all model caches.
+
+        When a preview file is no longer on disk, remove its reference from
+        every cached entry so subsequent list API responses return an empty
+        ``preview_url``, letting the frontend show the no-preview placeholder.
+        """
+        try:
+            from ...services.service_registry import ServiceRegistry
+
+            for service_name in ("lora_scanner", "checkpoint_scanner", "embedding_scanner"):
+                scanner = ServiceRegistry.get_service_sync(service_name)
+                if scanner is None or not hasattr(scanner, "_cache"):
+                    continue
+                cache = getattr(scanner, "_cache", None)
+                if cache is None or not hasattr(cache, "clear_preview_by_path"):
+                    continue
+                cleared = await cache.clear_preview_by_path(normalized_preview_path)
+                if cleared and hasattr(scanner, "_persist_current_cache"):
+                    await scanner._persist_current_cache()
+                    logger.info(
+                        "Cleared stale preview_url for %d %s entries (%s)",
+                        cleared,
+                        service_name,
+                        normalized_preview_path,
+                    )
+        except Exception as exc:
+            logger.debug("Failed to clean up stale preview_url: %s", exc)
+
     async def _stream_file(
         self, request: web.Request, path: Path
     ) -> web.StreamResponse:

py/routes/handlers/recipe_handlers.py

@@ -72,6 +72,7 @@ class RecipeHandlerSet:
             "save_recipe": self.management.save_recipe,
             "delete_recipe": self.management.delete_recipe,
             "get_top_tags": self.query.get_top_tags,
+            "search_tags": self.query.search_tags,
             "get_base_models": self.query.get_base_models,
             "get_roots": self.query.get_roots,
             "get_folders": self.query.get_folders,
@@ -317,12 +318,11 @@ class RecipeQueryHandler:
                 raise RuntimeError("Recipe scanner unavailable")
 
             limit = int(request.query.get("limit", "20"))
-            cache = await recipe_scanner.get_cached_data()
-
-            tag_counts: Dict[str, int] = {}
-            for recipe in getattr(cache, "raw_data", []):
-                for tag in recipe.get("tags", []) or []:
-                    tag_counts[tag] = tag_counts.get(tag, 0) + 1
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+            tag_counts = await self._get_recipe_tag_counts(recipe_scanner)
 
             sorted_tags = [
                 {"tag": tag, "count": count} for tag, count in tag_counts.items()
@@ -333,6 +333,55 @@ class RecipeQueryHandler:
             self._logger.error("Error retrieving top tags: %s", exc, exc_info=True)
             return web.json_response({"success": False, "error": str(exc)}, status=500)
 
+    async def search_tags(self, request: web.Request) -> web.Response:
+        try:
+            await self._ensure_dependencies_ready()
+            recipe_scanner = self._recipe_scanner_getter()
+            if recipe_scanner is None:
+                raise RuntimeError("Recipe scanner unavailable")
+
+            query = request.query.get("q", "")
+            limit = int(request.query.get("limit", "20"))
+            if limit < 0:
+                limit = 20
+            elif limit > 200:
+                limit = 20
+
+            tag_counts = await self._get_recipe_tag_counts(recipe_scanner)
+            normalized_query = (query or "").strip().lower()
+            if not normalized_query:
+                sorted_tags = [
+                    {"tag": tag, "count": count} for tag, count in tag_counts.items()
+                ]
+                sorted_tags.sort(key=lambda entry: entry["count"], reverse=True)
+                return web.json_response(
+                    {"success": True, "tags": sorted_tags[: (limit if limit > 0 else 20)]}
+                )
+
+            matched = [
+                {"tag": tag, "count": count}
+                for tag, count in tag_counts.items()
+                if normalized_query in tag.lower()
+            ]
+            matched.sort(key=lambda entry: entry["count"], reverse=True)
+            if limit == 0:
+                result = matched
+            else:
+                result = matched[:limit]
+            return web.json_response({"success": True, "tags": result})
+        except Exception as exc:
+            self._logger.error("Error searching recipe tags: %s", exc, exc_info=True)
+            return web.json_response({"success": False, "error": str(exc)}, status=500)
+
+    async def _get_recipe_tag_counts(self, recipe_scanner) -> Dict[str, int]:
+        """Compute tag->count mapping from cached recipe data."""
+        cache = await recipe_scanner.get_cached_data()
+        tag_counts: Dict[str, int] = {}
+        for recipe in getattr(cache, "raw_data", []):
+            for tag in recipe.get("tags", []) or []:
+                tag_counts[tag] = tag_counts.get(tag, 0) + 1
+        return tag_counts
+
     async def get_base_models(self, request: web.Request) -> web.Response:
         try:
             await self._ensure_dependencies_ready()
@@ -2218,6 +2267,31 @@ class RecipeManagementHandler:
                         "Failed to download image for recipe: %s", exc
                     )
 
+            # Fallback: try to locate a custom image on disk using model_hash + image id
+            if image_bytes is None:
+                image_id = image_data.get("id") or ""
+                if image_id and model_hash:
+                    from ...utils.example_images_paths import get_model_folder
+                    model_folder = get_model_folder(model_hash)
+                    if model_folder and os.path.exists(model_folder):
+                        for fname in os.listdir(model_folder):
+                            if f"custom_{image_id}" in fname:
+                                ext = os.path.splitext(fname)[1].lower()
+                                if ext not in (".jpg", ".jpeg", ".png", ".webp", ".gif"):
+                                    continue
+                                fpath = os.path.join(model_folder, fname)
+                                if os.path.isfile(fpath):
+                                    try:
+                                        with open(fpath, "rb") as f:
+                                            image_bytes = f.read()
+                                        extension = ext
+                                    except Exception as exc:
+                                        self._logger.warning(
+                                            "Failed to read custom image file %s: %s",
+                                            fpath, exc,
+                                        )
+                                break
+
             prompt = (
                 (parsed.get("gen_params") or {}).get("prompt") or ""
             )

py/routes/misc_route_registrar.py

@@ -22,6 +22,8 @@ class RouteDefinition:
 MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition("GET", "/api/lm/settings", "get_settings"),
     RouteDefinition("POST", "/api/lm/settings", "update_settings"),
+    RouteDefinition("GET", "/api/lm/llm/models", "get_llm_models"),
+    RouteDefinition("GET", "/api/lm/llm/provider-models", "get_provider_models"),
     RouteDefinition("GET", "/api/lm/doctor/diagnostics", "get_doctor_diagnostics"),
     RouteDefinition("POST", "/api/lm/doctor/repair-cache", "repair_doctor_cache"),
     RouteDefinition("POST", "/api/lm/doctor/resolve-filename-conflicts", "resolve_doctor_filename_conflicts"),
@@ -37,10 +39,12 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition("POST", "/api/lm/update-usage-stats", "update_usage_stats"),
     RouteDefinition("GET", "/api/lm/get-usage-stats", "get_usage_stats"),
     RouteDefinition("POST", "/api/lm/update-lora-code", "update_lora_code"),
+    RouteDefinition("GET", "/api/lm/update-lora-code", "get_update_lora_code"),
     RouteDefinition("GET", "/api/lm/trained-words", "get_trained_words"),
     RouteDefinition("GET", "/api/lm/model-example-files", "get_model_example_files"),
     RouteDefinition("POST", "/api/lm/register-nodes", "register_nodes"),
     RouteDefinition("POST", "/api/lm/update-node-widget", "update_node_widget"),
+    RouteDefinition("GET", "/api/lm/update-node-widget", "get_update_node_widget"),
     RouteDefinition("GET", "/api/lm/get-registry", "get_registry"),
     RouteDefinition("GET", "/api/lm/check-model-exists", "check_model_exists"),
     RouteDefinition("GET", "/api/lm/check-models-exist", "check_models_exist"),
@@ -101,6 +105,9 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition(
         "POST", "/api/lm/download-hf-model", "download_hf_model"
     ),
+    RouteDefinition(
+        "POST", "/api/lm/set-hf-url", "set_hf_url"
+    ),
     # Agent skill endpoints
     RouteDefinition(
         "GET", "/api/lm/agent/skills", "get_agent_skills"

py/routes/model_route_registrar.py

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

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"),

py/services/agent/__init__.py

@@ -1,8 +1,12 @@
-"""Agent-powered skill system for LoRA Manager.
+"""LLM-powered metadata enrichment pipeline infrastructure.
 
-This package provides the orchestration layer for LLM/agent-powered features.
+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

py/services/agent/agent_service.py

@@ -1,16 +1,17 @@
-"""Agent orchestration service.
+"""Pipeline orchestration service.
 
-The :class:`AgentService` coordinates skill execution:
+The :class:`AgentService` coordinates LLM-powered pipeline execution:
 
-1. Look up the skill in :class:`SkillRegistry`
-2. Validate input against the skill's ``input_schema``
-3. Prepare context via :mod:`~py.agent_cli` (read metadata, list base models, fetch HF README)
+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.agent_cli`)
+5. Post-process via :class:`PostProcessor` (delegates I/O to :mod:`~py.metadata_ops`)
 6. Broadcast progress and completion via :class:`WebSocketManager`
 
-Skills define *what* to do (prompt template).  The AgentService handles *how*
-(LLM calls, context gathering, validation, progress).
+Pipeline definitions (*skills*) describe *what* to do (prompt template).
+The AgentService handles *how* (LLM calls, context gathering, validation,
+progress).
 """
 
 from __future__ import annotations
@@ -24,10 +25,17 @@ 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__)
 
@@ -195,11 +203,11 @@ class AgentService:
         input_data: Dict[str, Any],
         progress_callback: Optional[AgentProgressReporter] = None,
     ) -> SkillResult:
-        """Execute an agent skill.
+        """Execute a pipeline (skill) on the given models.
 
         Args:
-            skill_name: Name of the skill to execute
-            input_data: Input validated against the skill's ``input_schema``
+            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:
@@ -207,7 +215,6 @@ class AgentService:
         """
 
         registry = await self._ensure_registry()
-        logger.info("execute_skill '%s': looking up skill", skill_name)
         skill = registry.get_skill(skill_name)
         if skill is None:
             return SkillResult(
@@ -235,11 +242,11 @@ class AgentService:
         total = len(model_paths)
         processed = 0
         success_count = 0
+        skipped_count = 0
         updated_models: List[Dict[str, Any]] = []
         errors: List[str] = []
         post_processor = PostProcessor()
 
-        logger.info("execute_skill '%s': starting with %d model(s)", skill_name, total)
         await self._emit_progress(
             progress_callback, skill_name, status="started",
             total=total, processed=0, success=0,
@@ -249,52 +256,74 @@ class AgentService:
         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(
-                "execute_skill '%s': processing model %d/%d: %s",
-                skill_name, processed + 1, total, model_path,
+                "[%s] [%d/%d] %s",
+                skill_name, processed + 1, total, model_filename,
             )
+            updated_data: Dict[str, Any] = {}
+            skip_model = False
             try:
-                from ...agent_cli import read_metadata
+                from ...metadata_ops import read_metadata
                 metadata = await read_metadata(model_path)
 
-                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)
+                # 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(
-                        "execute_skill '%s': LLM call for %s (prompt=%d chars)",
-                        skill_name, model_path, len(rendered),
+                        "[%s] SKIP %s — no hf_url in metadata",
+                        skill_name, model_filename,
                     )
-                    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,
+                    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", ""),
                     )
 
-                model_result = await post_processor.process(
-                    skill_name=skill_name,
-                    model_path=model_path,
-                    llm_output=llm_response or {},
-                    metadata=metadata,
-                )
-
-                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})
-                else:
-                    errors.extend(
-                        model_result.get("errors", [model_result.get("error", "Unknown error")])
-                    )
+                    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)
@@ -304,25 +333,41 @@ class AgentService:
             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",
+            summary=f"Processed {processed}/{total} models, {success_count} succeeded, {skipped_count} skipped",
         )
 
-        logger.info("execute_skill '%s': done — %s", skill_name, result.summary)
         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,
@@ -334,20 +379,29 @@ class AgentService:
         """Gather variables for the skill's prompt template.
 
         Reads metadata, fetches the HF README (if applicable), lists available
-        base models, and returns a dict that maps to ``{{variable}}``
-        placeholders in ``prompt.md``.
+        base models, loads user priority tags, and returns a dict that maps to
+        ``{{variable}}`` placeholders in ``prompt.md``.
         """
-        from ...agent_cli import list_base_models
+        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", ""),
@@ -364,12 +418,34 @@ class AgentService:
         context["repo"] = repo or ""
         if repo:
             readme = await self._fetch_readme(repo)
-            context["readme_content"] = readme[:8000] if readme else "(README not available)"
+            # 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:
-            context["base_models"] = await list_base_models()
+            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
 

py/services/agent/post_processor.py

@@ -1,17 +1,19 @@
-"""Post-processing engine for agent skill outputs.
+"""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.agent_cli` functions.
+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.agent_cli`.
+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
 
@@ -19,7 +21,7 @@ logger = logging.getLogger(__name__)
 
 
 class PostProcessor:
-    """Deterministic post-processor for agent skill outputs.
+    """Deterministic post-processor for skill pipeline outputs.
 
     Usage (called by :class:`~py.services.agent.agent_service.AgentService`)::
 
@@ -28,7 +30,7 @@ class PostProcessor:
             skill_name="enrich_hf_metadata",
             model_path="/path/to/model.safetensors",
             llm_output={...},
-            metadata={...},    # from agent_cli.read_metadata()
+            metadata={...},    # from metadata_ops.read_metadata()
         )
     """
 
@@ -39,15 +41,20 @@ class PostProcessor:
         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,
+                model_path, llm_output, metadata, readme_content,
             )
         return {
             "success": False,
@@ -64,12 +71,22 @@ class PostProcessor:
         model_path: str,
         llm_output: Dict[str, Any],
         metadata: Dict[str, Any],
+        readme_content: str = "",
     ) -> Dict[str, Any]:
-        from ...agent_cli import (
+        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
@@ -86,23 +103,89 @@ class PostProcessor:
         if new_base and self._should_overwrite(current_base, is_hf_model):
             updates["base_model"] = new_base
 
-        # trainedWords / trigger words
+        # 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()]
-            if cleaned:
-                current_triggers = metadata.get("trainedWords") or []
-                if self._should_overwrite_list(current_triggers, is_hf_model):
-                    updates["trainedWords"] = cleaned
+            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
-        new_desc = (llm_output.get("description") or "").strip()
-        if new_desc:
-            current_desc = metadata.get("modelDescription", "") or ""
-            if self._should_overwrite(current_desc, is_hf_model):
-                updates["modelDescription"] = new_desc
+        # 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
 
-        # tags — merge with existing, deduplicate (case-insensitive)
+        # 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 []
@@ -114,16 +197,68 @@ class PostProcessor:
         updates["metadata_source"] = "agent:enrich_hf_metadata"
         updates["llm_enriched_at"] = datetime.now(timezone.utc).isoformat()
 
-        # -- Persist updates ------------------------------------------------
+        # 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)
 
-        # -- Download preview -----------------------------------------------
-        preview_url = (llm_output.get("preview_url") or "").strip()
-        current_preview = metadata.get("preview_url") or ""
-        if preview_url and not (current_preview and os.path.exists(current_preview)):
-            preview_downloaded = await download_preview(model_path, preview_url)
-
         # -- Refresh scanner cache ------------------------------------------
         if updated_fields or preview_downloaded:
             await refresh_cache(model_path)
@@ -132,6 +267,7 @@ class PostProcessor:
             "success": True,
             "updated_fields": updated_fields,
             "preview_downloaded": preview_downloaded,
+            "updates": updates,
             "errors": [],
         }
 
@@ -166,3 +302,35 @@ class PostProcessor:
                 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_registry.py

@@ -1,7 +1,7 @@
-"""Discovery and loading of agent skills.
+"""Discovery and loading of prompt-based skills.
 
 Skills live in ``py/services/agent/skills/<name>/`` directories.  Each
-directory must contain a ``SKILL.md`` file with YAML frontmatter::
+directory must contain a ``prompt.md`` file with YAML frontmatter::
 
     ---
     name: my_skill
@@ -12,6 +12,8 @@ directory must contain a ``SKILL.md`` file with YAML frontmatter::
 
     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.
 """
 
@@ -32,6 +34,11 @@ 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
@@ -43,7 +50,8 @@ _FRONTMATTER_RE = re.compile(
 
 
 def _parse_skill_file(path: Path) -> tuple[dict, str]:
-    """Read a ``SKILL.md`` file and return (frontmatter_dict, body_text).
+    """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.
     """
@@ -95,6 +103,20 @@ class SkillRegistry:
     # 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."""
 
@@ -107,31 +129,32 @@ class SkillRegistry:
         for entry in sorted(self._skills_dir.iterdir()):
             if not entry.is_dir():
                 continue
-            skill_md = entry / "SKILL.md"
-            if not skill_md.exists():
+            prompt_file = self._find_prompt_file(entry)
+            if prompt_file is None:
                 continue
             try:
-                definition = self._load_skill_definition(skill_md)
+                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", skill_md, exc)
+                logger.warning("Failed to load skill from %s: %s", prompt_file, exc)
 
         self._loaded = True
-        logger.info("Discovered %d agent skills", len(self._skills))
+        logger.info("Discovered %d prompt-based skills", len(self._skills))
 
     def _load_skill_definition(self, path: Path) -> Optional[SkillDefinition]:
-        """Parse a ``SKILL.md`` frontmatter into a :class:`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 SKILL.md %s: %s", path, exc)
+            logger.warning("Failed to parse prompt file %s: %s", path, exc)
             return None
 
         if "name" not in data:
-            logger.warning("SKILL.md missing required 'name' field: %s", path)
+            logger.warning("Prompt file %s missing required 'name' field", path)
             return None
 
         perm_data = data.get("permissions", {})
@@ -171,12 +194,15 @@ class SkillRegistry:
         return self._skills.get(name)
 
     def load_prompt(self, name: str) -> str:
-        """Load and return the prompt template body from a skill's ``SKILL.md``."""
+        """Load and return the prompt template body for the named skill."""
 
         skill_dir = self._skills_dir / name
-        skill_path = skill_dir / "SKILL.md"
-        if not skill_path.exists():
-            raise FileNotFoundError(f"SKILL.md not found: {skill_path}")
+        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

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

@@ -1,89 +0,0 @@
----
-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}}
-- **Repository ID**: {{repo}}
-
-## Current Metadata (may be incomplete)
-
-```json
-{{current_metadata}}
-```
-
-## Available Base Models
-
-The following base models are currently valid in this system:
-{{base_models}}
-
-## HuggingFace README Content
-
-```
-{{readme_content}}
-```
-
-## Extraction Instructions
-
-Extract the following information from the README content above:
-
-### base_model
-The base model this LoRA/checkpoint 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 (between --- markers) for `base_model:` first, then look at the description text and safetensors metadata. If you cannot determine it, return an empty string.
-
-### 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:"
-- 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.
-
-### description
-A concise 1-2 sentence summary of what this model does. Extract from the "Model description" section or the first paragraph. Return empty string if the README is too minimal.
-
-### tags
-3-8 relevant tags for categorizing this model. Extract from:
-- The YAML frontmatter `tags:` list (often contains excellent categorization tags)
-- The model type (e.g. "lora", "checkpoint", "flux", "sdxl")
-- The style/subject (e.g. "anime", "photorealistic", "style", "character")
-All lowercase, no spaces. Return empty array if none found.
-
-### preview_url
-The URL of the most suitable preview image from the README. Look for image tags (e.g. `![alt](url)`) and the YAML frontmatter `widget:` section (which often has `output.url` fields). 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.
-
-### 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
-
-## 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>"],
-  "description": "<1-2 sentence summary>",
-  "tags": ["<tag1>", "<tag2>"],
-  "preview_url": "<image URL or empty string>",
-  "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

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

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

py/services/base_model_service.py

@@ -804,6 +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)
@@ -955,13 +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
 
@@ -1084,6 +1098,11 @@ 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
@@ -1101,6 +1120,19 @@ class BaseModelService(ABC):
                 MetadataManager.save_metadata(file_path, metadata)
             )
 
+        # Opportunistically sync the in-memory + persistent caches.
+        # The .metadata.json disk read is already paid for; the sync only
+        # performs work when the cache is actually stale, and uses targeted,
+        # in-place operations to minimise overhead even with large model sets.
+        #
+        # Fire-and-forget by design: the task is intentionally untracked.
+        # sync_cache_from_metadata handles its own errors internally.
+        asyncio.create_task(
+            self.scanner.sync_cache_from_metadata(
+                file_path, metadata.to_dict()
+            )
+        )
+
         return self.filter_civitai_data(metadata.to_dict().get("civitai", {}))
 
     async def get_model_description(self, file_path: str) -> Optional[str]:

py/services/checkpoint_scanner.py

@@ -114,6 +114,13 @@ class CheckpointScanner(ModelScanner):
                 and metadata.hash_status == "completed"
                 and metadata.sha256
             ):
+                # Ensure the in-memory hash index is populated even when
+                # the hash was already computed and persisted to the metadata
+                # file.  Without this, usage tracking (and any other caller
+                # that queries get_hash_by_filename first) will miss on every
+                # lookup and keep calling back into this method, creating a
+                # tight loop that never populates the index.
+                self._hash_index.add_entry(metadata.sha256.lower(), file_path)
                 return metadata.sha256
 
             async with self._hash_calculation_lock:
@@ -125,6 +132,7 @@ class CheckpointScanner(ModelScanner):
                     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)
@@ -175,6 +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
@@ -193,6 +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/civarchive_client.py

@@ -304,6 +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

py/services/civitai_base_model_service.py

@@ -213,6 +213,18 @@ class CivitaiBaseModelService:
             "wan video 2.2 i2v-a14b": "WAN",
             "wan video 2.5 t2v": "WAN",
             "wan video 2.5 i2v": "WAN",
+            "wan video 2.7": "WAN",
+            "wan image 2.7": "WI27",
+            "ace audio": "ACE",
+            "boogu": "BOOG",
+            "grok": "GROK",
+            "happyhorse": "HAPP",
+            "hidream-o1": "HIO1",
+            "lens": "LENS",
+            "mai": "MAI",
+            "upscaler": "UPSC",
+            "ideogram 4.0": "ID40",
+            "qwen 2": "QWN2",
         }
 
         if lower_name in special_cases:
@@ -392,6 +404,7 @@ class CivitaiBaseModelService:
                 "LTXV2",
                 "LTXV 2.3",
                 "CogVideoX",
+                "HappyHorse",
                 "Mochi",
                 "Hunyuan Video",
                 "Wan Video",
@@ -404,15 +417,25 @@ class CivitaiBaseModelService:
                 "Wan Video 2.2 I2V-A14B",
                 "Wan Video 2.5 T2V",
                 "Wan Video 2.5 I2V",
+                "Wan Image 2.7",
+                "Wan Video 2.7",
             ],
             "Other Models": [
+                "ACE Audio",
                 "Illustrious",
                 "Pony",
                 "Pony V7",
+                "Boogu",
                 "HiDream",
+                "HiDream-O1",
+                "Ideogram 4.0",
                 "Qwen",
+                "Qwen 2",
                 "AuraFlow",
                 "Chroma",
+                "Grok",
+                "Lens",
+                "MAI",
                 "ZImageTurbo",
                 "ZImageBase",
                 "PixArt a",
@@ -426,6 +449,7 @@ class CivitaiBaseModelService:
                 "Ernie Turbo",
                 "Nucleus",
                 "Krea 2",
+                "Upscaler",
             ],
         }
 

py/services/download_manager.py

@@ -230,6 +230,12 @@ class DownloadManager:
         Returns:
             Dict with download result
         """
+        logger.debug(
+            "[download] download_from_civitai called: model_id=%s, model_version_id=%s, "
+            "source=%s, file_params=%s",
+            model_id, model_version_id, source, file_params,
+        )
+
         # Validate that at least one identifier is provided
         if not model_id and not model_version_id:
             return {
@@ -250,6 +256,7 @@ class DownloadManager:
             "source": source,
             "file_params": copy.deepcopy(file_params) if file_params is not None else None,
             "progress": 0,
+
             "status": "queued",
             "transfer_backend": self._get_model_download_backend(),
             "bytes_downloaded": 0,
@@ -289,8 +296,8 @@ class DownloadManager:
             return result
         except asyncio.CancelledError:
             return {
-                "success": False,
-                "error": "Download was cancelled",
+                "success": True,
+                "cancelled": True,
                 "download_id": task_id,
             }
         finally:
@@ -675,7 +682,10 @@ class DownloadManager:
                     u for u in download_urls if not u.startswith(CIVITAI_DOWNLOAD_URL_PREFIXES)
                 ]
                 download_urls = non_civitai_urls + civitai_urls
-        else:
+
+        # Fallback: when mirrors is empty or all mirrors have been deleted,
+        # use the file's downloadUrl directly (e.g. CivitAI download endpoint).
+        if not download_urls:
             download_url = file_info.get("downloadUrl")
             if download_url:
                 download_urls.append(normalize_civitai_download_url(download_url))
@@ -1421,14 +1431,35 @@ class DownloadManager:
 
             # If file_params is provided, try to find matching file
             if file_params and model_version_id:
+                target_file_id = file_params.get("id")
                 target_type = file_params.get("type", "Model")
-                target_format = file_params.get("format", "SafeTensor")
-                target_size = file_params.get("size", "full")
+                target_format = file_params.get("format")
+                target_size = file_params.get("size")
                 target_fp = file_params.get("fp")
                 is_primary = file_params.get("isPrimary", False)
 
-                if is_primary:
-                    # Find primary file
+                logger.debug(
+                    "[download] file_params received: id=%s, type=%s, format=%s, size=%s, fp=%s, isPrimary=%s, "
+                    "model_version_id=%s, total_files=%d",
+                    target_file_id, target_type, target_format, target_size, target_fp, is_primary,
+                    model_version_id, len(files),
+                )
+
+                if target_file_id:
+                    target_id_str = str(target_file_id)
+                    for f in files:
+                        f_id = f.get("id")
+                        if str(f_id) == target_id_str:
+                            file_info = f
+                            logger.debug(
+                                "[download] MATCH by ID: id=%s name='%s'",
+                                f_id, f.get("name"),
+                            )
+                            break
+                    if not file_info:
+                        logger.debug("[download] No file found with id=%s", target_file_id)
+
+                elif is_primary:
                     file_info = next(
                         (
                             f
@@ -1439,28 +1470,41 @@ class DownloadManager:
                         None,
                     )
                 else:
-                    # Match by metadata
+                    # Lenient metadata match: only compare fields present on both sides
                     for f in files:
                         f_type = f.get("type", "")
-                        f_meta = f.get("metadata", {})
-
-                        # Check type match
                         if f_type != target_type:
                             continue
 
-                        # Check metadata match
-                        if f_meta.get("format") != target_format:
+                        f_meta = f.get("metadata", {})
+                        f_format = f_meta.get("format") or f.get("format")
+                        f_size = f_meta.get("size") or f.get("size")
+                        f_fp = f_meta.get("fp") or f.get("fp")
+
+                        if target_format and f_format != target_format:
                             continue
-                        if f_meta.get("size") != target_size:
+                        if target_size and f_size and f_size != target_size:
                             continue
-                        if target_fp and f_meta.get("fp") != target_fp:
+                        if target_fp and f_fp and f_fp != target_fp:
                             continue
 
                         file_info = f
                         break
 
+                if not file_info:
+                    logger.debug(
+                        "[download] No match found via file_params — falling back to primary file lookup",
+                    )
+            elif not file_params:
+                logger.debug(
+                    "[download] No file_params provided (null/None) — will use primary file lookup. "
+                    "model_version_id=%s, total_files=%d",
+                    model_version_id, len(files),
+                )
+
             # Fallback to primary file if no match found
             if not file_info:
+                logger.debug("[download] Looking for primary file as fallback")
                 file_info = next(
                     (
                         f
@@ -1469,38 +1513,18 @@ class DownloadManager:
                     ),
                     None,
                 )
+                if file_info:
+                    logger.debug(
+                        "[download] Fallback primary file selected: id=%s, name=%s",
+                        file_info.get("id"), file_info.get("name"),
+                    )
+                else:
+                    logger.debug("[download] No primary file found in fallback lookup")
 
             if not file_info:
                 return {"success": False, "error": "No suitable file found in metadata"}
-            mirrors = file_info.get("mirrors") or []
-            download_urls = []
-            if mirrors:
-                for mirror in mirrors:
-                    if mirror.get("deletedAt") is None and mirror.get("url"):
-                        download_urls.append(
-                            normalize_civitai_download_url(mirror["url"])
-                        )
 
-                # When source is 'civarchive', prioritize non-Civitai URLs
-                # This avoids failed downloads from deleted Civitai models
-                if source == "civarchive" and len(download_urls) > 1:
-                    civitai_urls = [
-                        u
-                        for u in download_urls
-                        if u.startswith(CIVITAI_DOWNLOAD_URL_PREFIXES)
-                    ]
-                    non_civitai_urls = [
-                        u
-                        for u in download_urls
-                        if not u.startswith(CIVITAI_DOWNLOAD_URL_PREFIXES)
-                    ]
-                    download_urls = non_civitai_urls + civitai_urls
-            else:
-                download_url = file_info.get("downloadUrl")
-                if download_url:
-                    download_urls.append(
-                        normalize_civitai_download_url(download_url)
-                    )
+            download_urls = self._build_download_urls_from_file_info(file_info, source=source)
 
             if not download_urls:
                 return {"success": False, "error": "No mirror URL found"}

py/services/download_queue_service.py

@@ -74,6 +74,8 @@ class DownloadQueueService:
         );
         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
@@ -154,13 +156,23 @@ class DownloadQueueService:
         """Insert a new download into the queue.
 
         Returns the inserted row as a dict (or an empty dict if the
-        download_id already exists).
+        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 (
@@ -380,7 +392,7 @@ class DownloadQueueService:
             )
             conn.execute(
                 """
-                INSERT INTO download_history (
+                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
@@ -537,17 +549,27 @@ class DownloadQueueService:
             "offset": offset,
         }
 
-    async def delete_history_item(self, id: int) -> bool:
-        """Delete a single history entry by its *id*.
+    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()
-            cursor = conn.execute(
-                "DELETE FROM download_history WHERE id = ?",
-                (id,),
-            )
+            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
 
@@ -604,21 +626,34 @@ class DownloadQueueService:
     # Retry
     # ------------------------------------------------------------------
 
-    async def retry_from_history(self, item_id: int) -> Optional[dict[str, Any]]:
+    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 its primary key.  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.
+        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()
-            row = conn.execute(
-                "SELECT * FROM download_history WHERE id = ?",
-                (item_id,),
-            ).fetchone()
+            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"])
@@ -650,7 +685,7 @@ class DownloadQueueService:
             )
             conn.execute(
                 "DELETE FROM download_history WHERE id = ?",
-                (item_id,),
+                (row["id"],),
             )
             conn.commit()
             queued = conn.execute(

py/services/downloader.py

@@ -46,6 +46,30 @@ def is_ssl_cert_verify_error(exc: BaseException) -> bool:
     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."""
@@ -246,14 +270,14 @@ 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  # http(s) proxy, passed via the per-request `proxy=` kwarg
@@ -348,6 +372,13 @@ class Downloader:
         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),
@@ -729,7 +760,8 @@ class Downloader:
                             else:
                                 resume_offset = 0
                                 total_size = 0
-                            await self._create_session()
+                            async with self._session_lock:
+                                await self._create_session()
                             continue
 
                         return False, integrity_error
@@ -819,7 +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}")
@@ -911,6 +944,19 @@ 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

py/services/llm_service.py

@@ -19,11 +19,201 @@ from .errors import LLMNotConfiguredError, LLMRateLimitError, LLMResponseError
 
 logger = logging.getLogger(__name__)
 
-# Default API base URLs per provider
+# ---------------------------------------------------------------------------
+# 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] = {
-    "openai": "https://api.openai.com/v1",
-    "ollama": "http://localhost:11434/v1",
-    # "custom" requires an explicit llm_api_base from the user
+    pid: info["api_base"]
+    for pid, info in PROVIDER_PRESETS.items()
+    if info.get("api_base")
 }
 
 # Request timeout for LLM calls (seconds)
@@ -33,8 +223,8 @@ _LLM_TIMEOUT = aiohttp.ClientTimeout(total=120)
 class LLMService:
     """Centralized LLM API client.
 
-    All agent skills call LLMs through this service so that BYOK config,
-    retry logic, and error handling live in one place.
+    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
@@ -57,6 +247,10 @@ class LLMService:
                     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
@@ -79,20 +273,33 @@ class LLMService:
             "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 and
-        (for non-Ollama) an API key is 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 cfg["provider"] == "ollama"
-        return has_model and has_key
+        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."""
+        """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("/")
@@ -109,19 +316,26 @@ class LLMService:
     def _ensure_configured(self) -> Dict[str, Any]:
         """Validate configuration and return it, or raise.
 
-        A provider is considered configured when ``llm_model`` is set and
-        (for non-Ollama) an API key is configured.
+        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"])
-        has_key = bool(cfg["api_key"]) or cfg["provider"] == "ollama"
-        if not (has_model and has_key):
+        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 cfg["provider"] != "ollama":
+            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."
@@ -163,18 +377,68 @@ class LLMService:
 
         cfg = self._ensure_configured()
         api_base = self._resolve_api_base(cfg["provider"], cfg["api_base"])
-        url = f"{api_base}/chat/completions"
         model_name = model or cfg["model"]
 
-        payload: Dict[str, Any] = {
-            "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
+        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"])
 
@@ -217,8 +481,25 @@ class LLMService:
 
             # Parse response
             try:
-                content = data["choices"][0]["message"]["content"]
-                usage = data.get("usage", {})
+                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,
@@ -245,11 +526,15 @@ class LLMService:
         temperature: float = 0.3,
         max_tokens: Optional[int] = None,
     ) -> Dict[str, Any]:
-        """Call the LLM and return parsed JSON.
+        """Call the LLM with ``response_format=json_object`` and return parsed JSON.
 
-        Sends ``response_format: {"type": "json_object"}`` when the provider
-        supports it, and parses the response content as JSON.  If parsing
-        fails, retries once with a clarifying system message.
+        ``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
@@ -264,7 +549,7 @@ class LLMService:
         Raises:
             LLMNotConfiguredError: Provider not configured
             LLMRateLimitError: Rate limited
-            LLMResponseError: JSON parse failure after retry
+            LLMResponseError: Empty response or JSON parse failure
         """
 
         messages = [
@@ -272,50 +557,139 @@ class LLMService:
             {"role": "user", "content": user_prompt},
         ]
 
-        # First attempt with JSON mode
+        # 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=max_tokens,
+            max_tokens=effective_max,
         )
 
-        try:
-            return json.loads(result["content"])
-        except (json.JSONDecodeError, TypeError) as exc:
-            logger.warning(
-                "LLM JSON parse failed on first attempt: %s. Retrying.", exc
+        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]}"
             )
 
-        # Retry with explicit instruction to return valid JSON
-        retry_messages = messages + [
-            {
-                "role": "assistant",
-                "content": result["content"],
-            },
-            {
-                "role": "user",
-                "content": (
-                    "The previous response could not be parsed as JSON. "
-                    "Please respond with ONLY a valid JSON object, no "
-                    "markdown fences or extra text."
-                ),
-            },
-        ]
+        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],
+            )
 
-        result = await self.chat_completion(
-            messages=retry_messages,
-            model=model,
-            temperature=0.0,  # More deterministic for retry
-            response_format={"type": "json_object"},
-            max_tokens=max_tokens,
+        # 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]}"
         )
 
-        try:
-            return json.loads(result["content"])
-        except (json.JSONDecodeError, TypeError) as exc:
-            raise LLMResponseError(
-                f"LLM response could not be parsed as JSON after retry: {exc}\n"
-                f"Raw content: {result['content'][:500]}"
-            ) from exc
+
+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

@@ -271,12 +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 []

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

@@ -209,7 +209,21 @@ 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

py/services/model_cache.py

@@ -337,4 +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_scanner.py

@@ -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,
@@ -1561,6 +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())
@@ -1613,7 +1830,32 @@ 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 count. If limit is 0, return all."""
         cache = await self.get_cached_data()

py/services/persistent_model_cache.py

@@ -587,6 +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/recipe_cache.py

@@ -1,7 +1,6 @@
 import asyncio
 from typing import Iterable, List, Dict, Optional
 from dataclasses import dataclass, field
-from operator import itemgetter
 from natsort import natsorted
 
 
@@ -149,5 +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,
             )

py/services/recipes/persistence_service.py

@@ -216,11 +216,12 @@ class RecipePersistenceService:
             "preview_nsfw_level",
             "favorite",
             "gen_params",
+            "base_model",
         )
 
         if not any(key in updates for key in allowed_fields):
             raise RecipeValidationError(
-                "At least one field to update must be provided (title or tags or source_path or preview_nsfw_level or favorite or gen_params)"
+                "At least one field to update must be provided (title or tags or source_path or preview_nsfw_level or favorite or gen_params or base_model)"
             )
 
         if "gen_params" in updates and not isinstance(updates["gen_params"], dict):

py/services/settings_manager.py

@@ -65,6 +65,8 @@ DEFAULT_SETTINGS: Dict[str, Any] = {
     "onboarding_completed": False,
     "dismissed_banners": [],
     "enable_metadata_archive_db": False,
+    "enable_civarchive_api": True,
+    "metadata_provider_order": "civitai_archive_sqlite",
     "proxy_enabled": False,
     "proxy_host": "",
     "proxy_port": "",
@@ -152,6 +154,11 @@ class SettingsManager:
         self._check_environment_variables()
         self._collect_configuration_warnings()
 
+        if os.environ.get("LORA_MANAGER_PORTABLE", "0") == "1":
+            if not self.settings.get("use_portable_settings"):
+                self.settings["use_portable_settings"] = True
+                self._save_settings()
+
         if self._needs_initial_save:
             self._save_settings()
             self._needs_initial_save = False
@@ -625,12 +632,37 @@ class SettingsManager:
 
         return False
 
+    @staticmethod
+    def _normalize_path_set(paths: Iterable[str]) -> set[str]:
+        """Normalize an iterable of paths for set-based overlap comparison.
+
+        Resolves symlinks via ``os.path.realpath`` when the path exists on disk,
+        then applies ``os.path.normcase`` + ``os.path.normpath`` for consistent
+        cross-platform comparison.  Non-string / empty entries are skipped.
+        """
+        result: set[str] = set()
+        for p in paths:
+            if not isinstance(p, str):
+                continue
+            stripped = p.strip()
+            if not stripped:
+                continue
+            if os.path.exists(stripped):
+                stripped = os.path.normpath(os.path.realpath(stripped))
+            result.add(os.path.normcase(stripped))
+        return result
+
     def _validate_folder_paths(
         self,
         library_name: str,
         folder_paths: Mapping[str, Iterable[str]],
     ) -> None:
-        """Ensure folder paths do not overlap with other libraries."""
+        """Ensure folder paths do not overlap with other libraries.
+
+        Also detects checkpoints ↔ unet path overlap within the same library
+        (including via symlink resolution), which is a configuration error since
+        these model types must use separate physical folders.
+        """
         libraries = self.settings.get("libraries", {})
         normalized_new: Dict[str, Dict[str, str]] = {}
         for key, values in folder_paths.items():
@@ -668,6 +700,22 @@ class SettingsManager:
                         f"Folder path(s) {collisions} already assigned to library '{other_name}'"
                     )
 
+        # Checkpoints ↔ unet overlap within the same library
+        ckpt_paths = folder_paths.get("checkpoints", []) or []
+        unet_paths = folder_paths.get("unet", []) or []
+        if ckpt_paths and unet_paths:
+            ckpt_real = self._normalize_path_set(ckpt_paths)
+            unet_real = self._normalize_path_set(unet_paths)
+            overlap = ckpt_real & unet_real
+            if overlap:
+                collisions = ", ".join(sorted(overlap))
+                raise ValueError(
+                    f"Path(s) {collisions} are configured for both "
+                    f"'checkpoints' and 'unet' (diffusion models). "
+                    f"These model types must use separate physical folders. "
+                    f"Please remove one of the conflicting entries."
+                )
+
     def _update_active_library_entry(
         self,
         *,
@@ -1542,8 +1590,12 @@ class SettingsManager:
             portable_switch_pending = True
             self._prepare_portable_switch(value)
         if key == "folder_paths" and isinstance(value, Mapping):
+            active_name = self.get_active_library_name()
+            self._validate_folder_paths(active_name, value)
             self._update_active_library_entry(folder_paths=value)  # type: ignore[arg-type]
         elif key == "extra_folder_paths" and isinstance(value, Mapping):
+            active_name = self.get_active_library_name()
+            self._validate_folder_paths(active_name, value)
             self._update_active_library_entry(extra_folder_paths=value)  # type: ignore[arg-type]
         elif key == "default_lora_root":
             self._update_active_library_entry(default_lora_root=str(value))
@@ -1797,6 +1849,9 @@ class SettingsManager:
                 if key in self.settings:
                     minimal[key] = copy.deepcopy(self.settings[key])
 
+            if self.settings.get("use_portable_settings"):
+                minimal["use_portable_settings"] = True
+
             if self._seed_template:
                 for key, value in self._seed_template.items():
                     minimal.setdefault(key, copy.deepcopy(value))

py/services/use_cases/bulk_metadata_refresh_use_case.py

@@ -51,6 +51,10 @@ class BulkMetadataRefreshUseCase:
             if not model.get("skip_metadata_refresh", False)
             and not self._is_in_skip_path(model.get("folder", ""), skip_paths)
             and (not model.get("civitai") or not model["civitai"].get("id"))
+            # Skip models downloaded from Hugging Face — they are not on
+            # CivitAI / CivArchive.  Users can still refresh them individually
+            # via the right-click context menu.
+            and not model.get("hf_url", "")
             and not (
                 # Skip models confirmed not on CivitAI when no need to retry
                 model.get("from_civitai") is False

py/utils/constants.py

@@ -226,9 +226,21 @@ SUPPORTED_DOWNLOAD_SKIP_BASE_MODELS = frozenset(
         "Wan Video 2.5 I2V",
         "Hunyuan Video",
         "Anima",
+        "ACE Audio",
+        "Boogu",
         "Ernie",
         "Ernie Turbo",
-        "Nucleus",
+        "Grok",
+        "HappyHorse",
+        "HiDream-O1",
+        "Ideogram 4.0",
         "Krea 2",
+        "Lens",
+        "MAI",
+        "Nucleus",
+        "Qwen 2",
+        "Upscaler",
+        "Wan Image 2.7",
+        "Wan Video 2.7",
     ]
 )

py/utils/example_images_download_manager.py

@@ -72,6 +72,7 @@ class _DownloadProgress(dict):
             refreshed_models=set(),
             failed_models=set(),
             reprocessed_models=set(),
+            rate_limited_models=set(),
         )
 
     def snapshot(self) -> dict:
@@ -82,6 +83,7 @@ class _DownloadProgress(dict):
         snapshot["refreshed_models"] = list(self["refreshed_models"])
         snapshot["failed_models"] = list(self["failed_models"])
         snapshot["reprocessed_models"] = list(self.get("reprocessed_models", set()))
+        snapshot["rate_limited_models"] = list(self.get("rate_limited_models", set()))
         return snapshot
 
 
@@ -153,13 +155,15 @@ class DownloadManager:
         # Step 3: Load progress file (I/O operation, done outside lock)
         processed_models = set()
         failed_models = set()
+        rate_limited_models = set()
         
         try:
-            progress_file, processed_models, failed_models = await self._load_progress_file(output_dir)
+            progress_file, processed_models, failed_models, rate_limited_models = await self._load_progress_file(output_dir)
             logger.debug(
-                "Loaded previous progress, %s models already processed, %s models marked as failed",
+                "Loaded previous progress, %s models already processed, %s models marked as failed, %s models rate-limited",
                 len(processed_models),
                 len(failed_models),
+                len(rate_limited_models),
             )
         except Exception as e:
             logger.error(f"Failed to load progress file: {e}")
@@ -175,6 +179,7 @@ class DownloadManager:
                 self._progress.reset()
                 self._progress["processed_models"] = processed_models
                 self._progress["failed_models"] = failed_models
+                self._progress["rate_limited_models"] = rate_limited_models
                 self._stop_requested = False
                 self._progress["status"] = "running"
                 self._progress["start_time"] = time.time()
@@ -242,8 +247,8 @@ class DownloadManager:
             "status": self._progress.snapshot(),
         }
 
-    async def _load_progress_file(self, output_dir: str) -> tuple[str, set, set]:
-        """Load progress file from disk. Returns (progress_file_path, processed_models, failed_models).
+    async def _load_progress_file(self, output_dir: str) -> tuple[str, set, set, set]:
+        """Load progress file from disk. Returns (progress_file_path, processed_models, failed_models, rate_limited_models).
 
         This is a separate async method to allow running in executor to avoid blocking event loop.
         """
@@ -252,8 +257,12 @@ class DownloadManager:
             None, self._load_progress_file_sync, output_dir
         )
 
-    def _load_progress_file_sync(self, output_dir: str) -> tuple[str, set, set]:
-        """Synchronous implementation of progress file loading."""
+    def _load_progress_file_sync(self, output_dir: str) -> tuple[str, set, set, set]:
+        """Synchronous implementation of progress file loading.
+
+        Returns:
+            tuple: (progress_file_path, processed_models, failed_models, rate_limited_models)
+        """
         progress_file = os.path.join(output_dir, ".download_progress.json")
         progress_source = progress_file
 
@@ -289,6 +298,7 @@ class DownloadManager:
 
         processed_models = set()
         failed_models = set()
+        rate_limited_models = set()
 
         if os.path.exists(progress_source):
             try:
@@ -296,11 +306,11 @@ class DownloadManager:
                     saved_progress = json.load(f)
                     processed_models = set(saved_progress.get("processed_models", []))
                     failed_models = set(saved_progress.get("failed_models", []))
+                    rate_limited_models = set(saved_progress.get("rate_limited_models", []))
             except Exception:
-                # Return empty sets on error
                 pass
 
-        return progress_file, processed_models, failed_models
+        return progress_file, processed_models, failed_models, rate_limited_models
 
     def _load_progress_sets_sync(self, progress_file: str) -> tuple[set, set]:
         """Load only the processed and failed model sets from progress file.
@@ -732,11 +742,13 @@ class DownloadManager:
                     success,
                     is_stale,
                     failed_images,
+                    rate_limited_images,
                 ) = await ExampleImagesProcessor.download_model_images_with_tracking(
                     model_hash, model_name, images, model_dir, optimize, downloader
                 )
 
                 failed_urls: Set[str] = set(failed_images)
+                rate_limited_urls: Set[str] = set(rate_limited_images)
 
                 # If metadata is stale, try to refresh it
                 if is_stale and model_hash not in self._progress["refreshed_models"]:
@@ -760,6 +772,7 @@ class DownloadManager:
                             success,
                             _,
                             additional_failed,
+                            additional_rate_limited,
                         ) = await ExampleImagesProcessor.download_model_images_with_tracking(
                             model_hash,
                             model_name,
@@ -770,29 +783,50 @@ class DownloadManager:
                         )
 
                         failed_urls.update(additional_failed)
+                        rate_limited_urls.update(additional_rate_limited)
 
                     self._progress["refreshed_models"].add(model_hash)
 
-                if failed_urls:
+                # Separate permanent failures from rate-limited ones
+                permanent_failures = failed_urls - rate_limited_urls
+
+                if permanent_failures:
                     await self._remove_failed_images_from_metadata(
                         model_hash,
                         model_name,
                         model_dir,
-                        failed_urls,
+                        permanent_failures,
                         scanner,
                     )
 
-                if failed_urls:
+                if rate_limited_urls:
+                    self._progress["rate_limited_models"].add(model_hash)
+                    logger.warning(
+                        "%d example images for %s are rate-limited (429), will retry next time",
+                        len(rate_limited_urls),
+                        model_name,
+                    )
+                    # Clear failed_models so non-force runs can retry
+                    if force and model_hash in self._progress["failed_models"]:
+                        self._progress["failed_models"].discard(model_hash)
+                        logger.info(
+                            f"Removed {model_name} from failed_models after force retry with rate-limited images"
+                        )
+
+                if rate_limited_urls:
+                    # Don't mark as failed or fully processed — rate-limited
+                    # images will be retried next time.
+                    pass
+                elif permanent_failures:
                     self._progress["failed_models"].add(model_hash)
                     self._progress["processed_models"].add(model_hash)
                     logger.info(
                         "Removed %s failed example images for %s",
-                        len(failed_urls),
+                        len(permanent_failures),
                         model_name,
                     )
                 elif success:
                     self._progress["processed_models"].add(model_hash)
-                    # Remove from failed_models if force mode enabled and model was previously failed
                     if force and model_hash in self._progress["failed_models"]:
                         self._progress["failed_models"].discard(model_hash)
                         logger.info(
@@ -850,6 +884,7 @@ class DownloadManager:
                 "processed_models": list(self._progress["processed_models"]),
                 "refreshed_models": list(self._progress["refreshed_models"]),
                 "failed_models": list(self._progress["failed_models"]),
+                "rate_limited_models": list(self._progress.get("rate_limited_models", set())),
                 "completed": self._progress["completed"],
                 "total": self._progress["total"],
                 "last_update": time.time(),
@@ -1155,11 +1190,13 @@ class DownloadManager:
                     success,
                     is_stale,
                     failed_images,
+                    rate_limited_images,
                 ) = await ExampleImagesProcessor.download_model_images_with_tracking(
                     model_hash, model_name, images, model_dir, optimize, downloader
                 )
 
                 failed_urls: Set[str] = set(failed_images)
+                rate_limited_urls: Set[str] = set(rate_limited_images)
 
                 # If metadata is stale, try to refresh it
                 if is_stale and model_hash not in self._progress["refreshed_models"]:
@@ -1183,6 +1220,7 @@ class DownloadManager:
                             success,
                             _,
                             additional_failed_images,
+                            additional_rate_limited,
                         ) = await ExampleImagesProcessor.download_model_images_with_tracking(
                             model_hash,
                             model_name,
@@ -1192,21 +1230,35 @@ class DownloadManager:
                             downloader,
                         )
 
-                        # Combine failed images from both attempts
                         failed_urls.update(additional_failed_images)
+                        rate_limited_urls.update(additional_rate_limited)
 
                     self._progress["refreshed_models"].add(model_hash)
 
-                # For forced downloads, remove failed images from metadata
-                if failed_urls:
+                # Separate permanent failures from rate-limited ones
+                permanent_failures = failed_urls - rate_limited_urls
+
+                # Only remove permanently failed images from metadata
+                if permanent_failures:
                     await self._remove_failed_images_from_metadata(
-                        model_hash, model_name, model_dir, failed_urls, scanner
+                        model_hash, model_name, model_dir, permanent_failures, scanner
                     )
 
-                # Mark as processed
-                if (
-                    success or failed_urls
-                ):  # Mark as processed if we successfully downloaded some images or removed failed ones
+                if rate_limited_urls:
+                    self._progress["rate_limited_models"].add(model_hash)
+                    logger.warning(
+                        "%d example images for %s are rate-limited (429), will retry next time",
+                        len(rate_limited_urls),
+                        model_name,
+                    )
+
+                # Mark as processed only when no rate-limited images remain
+                if rate_limited_urls:
+                    pass
+                elif permanent_failures:
+                    self._progress["processed_models"].add(model_hash)
+                    self._progress["failed_models"].add(model_hash)
+                elif success:
                     self._progress["processed_models"].add(model_hash)
 
                 return True  # Return True to indicate a remote download happened
@@ -1229,15 +1281,20 @@ class DownloadManager:
         model_dir: str,
         failed_images: Iterable[str],
         scanner,
+        error_type: str = "not_found",
     ) -> None:
-        """Mark failed images in model metadata so they won't be retried."""
+        """Mark failed images in model metadata so they won't be retried.
+
+        Args:
+            error_type: Reason string stored in the image's ``downloadError`` field
+                        (default ``"not_found"``).
+        """
 
         failed_set: Set[str] = {url for url in failed_images if url}
         if not failed_set:
             return
 
         try:
-            # Get current model data
             model_data = await MetadataUpdater.get_updated_model(model_hash, scanner)
             if not model_data:
                 logger.warning(
@@ -1268,7 +1325,7 @@ class DownloadManager:
                     continue
 
                 image["downloadFailed"] = True
-                image.setdefault("downloadError", "not_found")
+                image.setdefault("downloadError", error_type)
                 logger.debug(
                     "Marked example image %s for %s as failed due to missing remote asset",
                     image_url,

py/utils/example_images_paths.py

@@ -113,6 +113,35 @@ def get_model_folder(model_hash: str, library_name: Optional[str] = None) -> str
                     exc,
                 )
                 return legacy_folder
+    elif not os.path.exists(resolved_folder):
+        # Reverse migration: when consolidating from multi-library to
+        # single-library mode (e.g. after "default" was cleaned up), look
+        # for existing example images inside library-named subdirectories
+        # and bring them back to the root level.
+        root = get_example_images_root()
+        if root:
+            try:
+                for entry in os.listdir(root):
+                    entry_path = os.path.join(root, entry)
+                    if not os.path.isdir(entry_path):
+                        continue
+                    if is_hash_folder(entry) or entry == "_deleted":
+                        continue
+                    if not _library_folder_has_only_hash_dirs(entry_path):
+                        continue
+                    legacy = os.path.join(entry_path, normalized_hash)
+                    if os.path.exists(legacy):
+                        shutil.move(legacy, resolved_folder)
+                        logger.info(
+                            "Consolidated example images from '%s' to '%s'",
+                            legacy, resolved_folder,
+                        )
+                        break
+            except OSError as exc:
+                logger.error(
+                    "Failed to consolidate example images during "
+                    "library merge: %s", exc,
+                )
 
     return resolved_folder
 

py/utils/example_images_processor.py

@@ -1,3 +1,4 @@
+import asyncio
 import logging
 import os
 import re
@@ -194,16 +195,22 @@ class ExampleImagesProcessor:
         
         return model_success, False  # (success, is_metadata_stale)
     
+    @staticmethod
+    def _extract_retry_after(error_message: str) -> int:
+        if not error_message:
+            return 60
+        match = re.search(r"retry after (\d+)s", str(error_message))
+        if match:
+            return max(1, int(match.group(1)))
+        return 60
+
     @staticmethod
     async def download_model_images_with_tracking(model_hash, model_name, model_images, model_dir, optimize, downloader):
-        """Download images for a single model with tracking of failed image URLs
-        
-        Returns:
-            tuple: (success, is_stale_metadata, failed_images) - whether download was successful, whether metadata is stale, list of failed image URLs
-        """
         model_success = True
         failed_images = []
-        
+        rate_limited_images = []
+        any_successful_download = False
+
         for i, image in enumerate(model_images):
             image_url = image.get('url')
             if not image_url:
@@ -221,64 +228,110 @@ class ExampleImagesProcessor:
             original_url = image_url
             if optimize and 'civitai.com' in image_url:
                 image_url = ExampleImagesProcessor.get_civitai_optimized_url(image_url)
-            
-            # Download the file first to determine the actual file type
-            try:
-                logger.debug(f"Downloading media file {i} for {model_name}")
-                
-                # Download using the unified downloader with headers
-                success, content, headers = await downloader.download_to_memory(
+
+            async def _attempt_download() -> tuple:
+                logger.debug("Downloading media file %s for %s", i, model_name)
+                return await downloader.download_to_memory(
                     image_url,
-                    use_auth=False,  # Example images don't need auth
-                    return_headers=True
+                    use_auth=False,
+                    return_headers=True,
                 )
-                
+
+            try:
+                success, content, headers = await _attempt_download()
+
                 if success:
-                    # Determine file extension from content or headers
                     media_ext = ExampleImagesProcessor._get_file_extension_from_content_or_headers(
                         content, headers, original_url, image.get("type")
                     )
-                    
-                    # Check if the detected file type is supported
                     is_image = media_ext in SUPPORTED_MEDIA_EXTENSIONS['images']
                     is_video = media_ext in SUPPORTED_MEDIA_EXTENSIONS['videos']
-                    
+
                     if not (is_image or is_video):
-                        logger.debug(f"Skipping unsupported file type: {media_ext}")
+                        logger.debug("Skipping unsupported file type: %s", media_ext)
                         continue
-                    
-                    # Use 0-based indexing with the detected extension
+
                     save_filename = f"image_{i}{media_ext}"
                     save_path = os.path.join(model_dir, save_filename)
-                    
-                    # Check if already downloaded
+
                     if os.path.exists(save_path):
-                        logger.debug(f"File already exists: {save_path}")
+                        logger.debug("File already exists: %s", save_path)
                         continue
-                    
-                    # Save the file
+
                     with open(save_path, 'wb') as f:
                         f.write(content)
-                    
+                    any_successful_download = True
+
                 elif ExampleImagesProcessor._is_not_found_error(content):
                     error_msg = f"Failed to download file: {image_url}, status code: 404 - Model metadata might be stale"
                     logger.warning(error_msg)
-                    model_success = False  # Mark the model as failed due to 404 error
-                    failed_images.append(image_url)  # Track failed URL
-                    # Return early to trigger metadata refresh attempt
-                    return False, True, failed_images  # (success, is_metadata_stale, failed_images)
+                    model_success = False
+                    failed_images.append(image_url)
+                    return False, True, failed_images, rate_limited_images
+
+                elif "Rate limited (429)" in str(content):
+                    max_attempts = 3
+                    for attempt in range(1, max_attempts + 1):
+                        wait = ExampleImagesProcessor._extract_retry_after(str(content)) * (2 ** (attempt - 1))
+                        logger.warning(
+                            "Rate limited (429) for %s, retry %d/%d after %ds",
+                            image_url, attempt, max_attempts, wait,
+                        )
+                        await asyncio.sleep(wait)
+
+                        success, content, headers = await _attempt_download()
+                        if success:
+                            media_ext = ExampleImagesProcessor._get_file_extension_from_content_or_headers(
+                                content, headers, original_url, image.get("type")
+                            )
+                            is_image = media_ext in SUPPORTED_MEDIA_EXTENSIONS['images']
+                            is_video = media_ext in SUPPORTED_MEDIA_EXTENSIONS['videos']
+
+                            if not (is_image or is_video):
+                                logger.debug("Skipping unsupported file type: %s", media_ext)
+                                break
+
+                            save_filename = f"image_{i}{media_ext}"
+                            save_path = os.path.join(model_dir, save_filename)
+                            if os.path.exists(save_path):
+                                logger.debug("File already exists: %s", save_path)
+                                break
+
+                            with open(save_path, 'wb') as f:
+                                f.write(content)
+                            any_successful_download = True
+                            break
+                        elif "Rate limited (429)" in str(content):
+                            continue
+                        elif ExampleImagesProcessor._is_not_found_error(content):
+                            logger.warning("Failed to download file: %s, status code: 404", image_url)
+                            model_success = False
+                            failed_images.append(image_url)
+                            break
+                        else:
+                            logger.warning("Failed to download file: %s, error: %s", image_url, content)
+                            model_success = False
+                            failed_images.append(image_url)
+                            break
+                    else:
+                        logger.warning(
+                            "Giving up on %s after %d retries due to rate limiting",
+                            image_url, max_attempts,
+                        )
+                        rate_limited_images.append(image_url)
+                        model_success = False
                 else:
                     error_msg = f"Failed to download file: {image_url}, error: {content}"
                     logger.warning(error_msg)
-                    model_success = False  # Mark the model as failed
-                    failed_images.append(image_url)  # Track failed URL
+                    model_success = False
+                    failed_images.append(image_url)
             except Exception as e:
                 error_msg = f"Error downloading file {image_url}: {str(e)}"
                 logger.error(error_msg)
-                model_success = False  # Mark the model as failed
-                failed_images.append(image_url)  # Track failed URL
-        
-        return model_success, False, failed_images  # (success, is_metadata_stale, failed_images)
+                model_success = False
+                failed_images.append(image_url)
+
+        return any_successful_download or model_success, False, failed_images, rate_limited_images
     
     @staticmethod
     async def process_local_examples(model_file_path, model_file_name, model_name, model_dir, optimize):

py/utils/settings_paths.py

@@ -12,6 +12,7 @@ from platformdirs import user_config_dir
 
 
 APP_NAME = "ComfyUI-LoRA-Manager"
+_LM_PORTABLE_ENV = "LORA_MANAGER_PORTABLE"
 _LOGGER = logging.getLogger(__name__)
 
 
@@ -100,7 +101,11 @@ def ensure_settings_file(logger: Optional[logging.Logger] = None) -> str:
 
 
 def _should_use_portable_settings(path: str, logger: logging.Logger) -> bool:
-    """Return ``True`` when the repository settings file enables portable mode."""
+    """Return ``True`` when the env var forces it or the settings file enables it."""
+
+    if os.environ.get(_LM_PORTABLE_ENV, "0") == "1":
+        logger.debug("Portable mode enabled via %s", _LM_PORTABLE_ENV)
+        return True
 
     if not os.path.exists(path):
         return False

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui-lora-manager"
 description = "Revolutionize your workflow with the ultimate LoRA companion for ComfyUI!"
-version = "1.1.6"
+version = "1.1.8"
 license = {file = "LICENSE"}
 dependencies = [
     "aiohttp",

standalone.py

@@ -1,6 +1,10 @@
 import os
 import sys
 import json
+# Ensure the script's directory is on sys.path so that py.* imports resolve
+# regardless of the current working directory (e.g. when launched via
+# ComfyUI's python_embeded from the ComfyUI root directory).
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from py.middleware.cache_middleware import cache_control
 from py.middleware.error_middleware import api_json_error
 from py.utils.settings_paths import ensure_settings_file

static/css/components/menu.css

@@ -40,6 +40,12 @@
     margin: 3px 0;
 }
 
+.context-menu-item.disabled {
+    opacity: 0.4;
+    cursor: not-allowed;
+    pointer-events: none;
+}
+
 .context-menu-item.delete-item {
     color: var(--danger-color);
 }

static/css/components/modal/download-modal.css

@@ -577,13 +577,14 @@
     border: 1px solid var(--border-color);
     border-radius: var(--border-radius-sm);
     cursor: pointer;
-    transition: var(--transition-base);
+    transition: var(--transition-base), box-shadow var(--transition-fast), transform var(--transition-fast);
     background: var(--bg-color);
 }
 
 .file-option:hover {
     border-color: var(--lora-accent);
-    box-shadow: var(--shadow-sm);
+    box-shadow: var(--shadow-md);
+    transform: translateY(-1px);
 }
 
 .file-option.selected {
@@ -698,10 +699,25 @@
     color: var(--lora-accent);
 }
 
-/* Batch Preview List */
+/* BUG 1 FIX: Single scrollbar — modal-content becomes a flex column so the
+   batch preview step can flex; the list scrolls instead of the modal-content. */
+#downloadModal .modal-content {
+    display: flex;
+    flex-direction: column;
+}
+
+#batchPreviewStep {
+    display: flex;
+    flex-direction: column;
+    min-height: 0;
+    flex: 1;
+}
+
+/* Batch Preview List — no max-height; flexes inside #batchPreviewStep */
 .batch-preview-list {
-    max-height: 400px;
+    flex: 1;
     overflow-y: auto;
+    min-height: 0;
     margin: var(--space-2) 0;
     display: flex;
     flex-direction: column;
@@ -859,6 +875,8 @@
     position: sticky;
     top: 0;
     z-index: 1;
+    backdrop-filter: blur(8px);
+    -webkit-backdrop-filter: blur(8px);
 }
 
 .batch-preview-select-all input[type="checkbox"] {
@@ -884,3 +902,100 @@
 [data-theme="dark"] .batch-preview-select-all {
     background: var(--lora-surface);
 }
+
+/* FEATURE 2: HF repo grouping — collapsible groups by repo */
+.batch-preview-group {
+    display: flex;
+    flex-direction: column;
+    background: var(--surface-base);
+}
+
+.batch-preview-group-header {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    padding: 10px 12px;
+    background: var(--color-accent-subtle);
+    border-bottom: 1px solid var(--color-accent-border);
+    cursor: pointer;
+    user-select: none;
+    transition: background var(--transition-fast);
+}
+
+.batch-preview-group-header:hover {
+    background: oklch(var(--color-accent-l) var(--color-accent-c) var(--color-accent-h) / 0.18);
+}
+
+.batch-preview-group-toggle {
+    width: 14px;
+    font-size: 0.75em;
+    color: var(--text-color);
+    opacity: 0.7;
+    transition: transform var(--transition-fast);
+    flex-shrink: 0;
+}
+
+.batch-preview-group-toggle.expanded {
+    transform: rotate(90deg);
+}
+
+.batch-preview-group-name {
+    flex: 1;
+    min-width: 0;
+    font-weight: 600;
+    color: var(--text-color);
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    font-size: 0.95em;
+}
+
+.batch-preview-group-count {
+    font-size: 0.8em;
+    color: var(--text-color);
+    opacity: 0.7;
+    flex-shrink: 0;
+}
+
+.batch-preview-group-select-all {
+    width: 18px;
+    height: 18px;
+    cursor: pointer;
+    accent-color: var(--lora-accent);
+    flex-shrink: 0;
+    padding: 0;
+    margin: 0;
+}
+
+.batch-preview-group-body {
+    display: flex;
+    flex-direction: column;
+    gap: 1px;
+    background: var(--border-color);
+    overflow: hidden;
+    max-height: 0;
+    opacity: 0;
+    transition: max-height 0.35s ease, opacity 0.2s ease;
+}
+
+.batch-preview-group-body.expanded {
+    opacity: 1;
+    max-height: 9999px; /* rest state: content visible; JS inline style overrides during transitions */
+}
+
+/* Dark theme overrides for group styles */
+[data-theme="dark"] .batch-preview-group {
+    background: var(--surface-base);
+}
+
+[data-theme="dark"] .batch-preview-group-header {
+    background: var(--color-accent-subtle);
+}
+
+[data-theme="dark"] .batch-preview-group-header:hover {
+    background: oklch(var(--color-accent-l) var(--color-accent-c) var(--color-accent-h) / 0.22);
+}
+
+[data-theme="dark"] .batch-preview-group-body {
+    background: var(--border-color);
+}

static/css/components/modal/relink-civitai-modal.css

@@ -21,18 +21,22 @@
   margin-bottom: 4px;
 }
 
-.input-group {
+#relinkCivitaiModal .input-group,
+#linkHfModal .input-group {
   display: flex;
   flex-direction: column;
   margin-bottom: var(--space-2);
 }
 
-.input-group label {
+#relinkCivitaiModal .input-group label,
+#linkHfModal .input-group label {
   margin-bottom: var(--space-1);
   font-weight: 500;
 }
 
-.input-group input {
+#relinkCivitaiModal .input-group input,
+#linkHfModal .input-group input {
+  width: auto;
   padding: 8px 12px;
   border-radius: var(--border-radius-xs);
   border: 1px solid var(--border-color);

static/css/components/modal/settings-modal.css

@@ -1562,6 +1562,29 @@ input:checked + .toggle-slider:before {
     box-shadow: 0 0 0 2px rgba(var(--lora-accent-rgb, 79, 70, 229), 0.1);
 }
 
+.extra-folder-path-row .path-controls .extra-folder-path-input.has-error {
+    border-color: var(--lora-error);
+    background-color: rgba(220, 53, 69, 0.08);
+    background-color: rgba(from var(--lora-error) r g b / 0.08);
+}
+
+.extra-folder-path-row .path-controls .extra-folder-path-input.has-error:focus {
+    box-shadow: 0 0 0 2px rgba(220, 53, 69, 0.15);
+    box-shadow: 0 0 0 2px rgba(from var(--lora-error) r g b / 0.15);
+}
+
+.extra-folder-path-error {
+    color: var(--lora-error);
+    font-size: 0.8em;
+    margin-top: 4px;
+    line-height: 1.4;
+    display: none;
+}
+
+.extra-folder-path-error.visible {
+    display: block;
+}
+
 .extra-folder-path-row .path-controls .remove-path-btn {
     width: 32px;
     height: 32px;
@@ -1592,3 +1615,45 @@ input:checked + .toggle-slider:before {
     animation: settings-highlight-pulse 1.5s ease-in-out 3;
     border-radius: var(--border-radius-xs);
 }
+
+/* ---- Combobox panel for AI Provider settings ---- */
+/* The panel is appended to <body> by Combobox.js and positioned relative to
+   the enhanced <input>. Styles reuse settings-modal CSS variables. */
+
+.lm-combobox-panel {
+    position: absolute;
+    z-index: 10002;
+    max-height: 240px;
+    overflow-y: auto;
+    background: var(--lora-surface, #2a2a2a);
+    border: 1px solid var(--border-color, rgba(255, 255, 255, 0.12));
+    border-radius: var(--border-radius-xs, 6px);
+    box-shadow: var(--shadow-elevated, 0 6px 18px rgba(0, 0, 0, 0.45));
+    font-size: 0.95em;
+    color: var(--text-color, rgba(226, 232, 240, 0.9));
+    padding: 4px 0;
+    box-sizing: border-box;
+}
+
+.lm-combobox-option {
+    padding: 6px 12px;
+    cursor: pointer;
+    user-select: none;
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+}
+
+.lm-combobox-option:hover,
+.lm-combobox-option.is-active {
+    background: rgba(from var(--lora-accent) r g b / 0.2);
+    color: var(--lora-accent);
+}
+
+.lm-combobox-empty {
+    padding: 8px 12px;
+    color: var(--text-color);
+    opacity: 0.45;
+    font-style: italic;
+    user-select: none;
+}

static/css/components/search-filter.css

@@ -274,6 +274,11 @@
     font-style: italic;
 }
 
+/* Inline extra tags (selected but not in top-20/appended after API results) */
+.filter-tag.extra-tag {
+    border-style: dashed;
+}
+
 /* Ensure solid border and full opacity when active or excluded */
 .filter-tag.special-tag.active,
 .filter-tag.special-tag.exclude {

static/js/api/apiConfig.js

@@ -93,6 +93,7 @@ export function getApiEndpoints(modelType) {
         // Query operations
         scan: `/api/lm/${modelType}/scan`,
         topTags: `/api/lm/${modelType}/top-tags`,
+        searchTags: `/api/lm/${modelType}/search-tags`,
         baseModels: `/api/lm/${modelType}/base-models`,
         roots: `/api/lm/${modelType}/roots`,
         folders: `/api/lm/${modelType}/folders`,

static/js/api/baseModelApi.js

@@ -112,6 +112,18 @@ export class BaseModelApiClient {
         }
     }
 
+    async cancelDownload(downloadId) {
+        try {
+            const response = await fetch(
+                `${DOWNLOAD_ENDPOINTS.cancelGet}?download_id=${encodeURIComponent(downloadId)}`
+            );
+            return await response.json();
+        } catch (error) {
+            console.error('Error cancelling download:', error);
+            return { success: false, error: error.message };
+        }
+    }
+
     async loadMoreWithVirtualScroll(resetPage = false, updateFolders = false) {
         const pageState = this.getPageState();
 

static/js/components/Combobox.js

@@ -0,0 +1,394 @@
+// Combobox.js — Reusable dropdown-suggestion + free-text input component.
+//
+// Enhances an existing <input> element with a dropdown panel that merges static
+// `presets` with asynchronously fetched options (`fetchOptions`). The input
+// remains a free-text field — selecting a dropdown option is optional, the
+// user can always type an arbitrary value.
+//
+// Zero dependencies: pure DOM manipulation. Exported on `window.Combobox`
+// so non-module callers can instantiate it, and as a named ES module export
+// for callers that import it directly.
+//
+// Usage:
+//   const box = new Combobox(inputEl, {
+//     presets: ['masterpiece', 'best quality'],
+//     fetchOptions: async (q) => await fetchSuggestions(q),
+//     placeholder: 'Type a value…',
+//     onSelect: (value) => console.log('chose', value),
+//   });
+//   box.updatePresets(['new', 'presets']);
+//   box.setValue('masterpiece');
+
+const DEBOUNCE_MS = 300;
+
+export class Combobox {
+    /**
+     * @param {HTMLInputElement} inputElement Existing <input> to enhance.
+     * @param {Object} options
+     * @param {string[]} [options.presets=[]] Static preset values shown in dropdown.
+     * @param {(inputValue: string) => Promise<string[]>} [options.fetchOptions]
+     *        Async function returning dynamic suggestions for the current input.
+     * @param {string} [options.placeholder] Placeholder text for the empty state.
+     * @param {(value: string) => void} [options.onSelect] Callback when an option is chosen.
+     */
+    constructor(inputElement, options = {}) {
+        if (!inputElement || inputElement.tagName !== 'INPUT') {
+            console.error('Combobox: expected an <input> element');
+            return;
+        }
+
+        this.input = inputElement;
+        this.presets = Array.isArray(options.presets) ? [...options.presets] : [];
+        this.fetchOptions = typeof options.fetchOptions === 'function' ? options.fetchOptions : null;
+        this.placeholder = options.placeholder || '';
+        this.onSelect = typeof options.onSelect === 'function' ? options.onSelect : null;
+
+        // Internal state
+        this._isOpen = false;
+        this._activeIndex = -1;
+        this._renderedOptions = []; // current visible option strings (de-duplicated, merged)
+        this._fetchToken = 0; // guards against out-of-order async fetch results
+        this._fetchTimer = null;
+        this._suppressInputOpen = false; // guards setValue() from reopening the dropdown
+
+        this._buildDropdown();
+        this._bindEvents();
+    }
+
+    // ---- public API ----
+
+    /**
+     * Replace the preset list. Re-renders the dropdown if it is open.
+     * @param {string[]} presets
+     * @returns {void}
+     */
+    updatePresets(presets) {
+        this.presets = Array.isArray(presets) ? [...presets] : [];
+        if (this._isOpen) {
+            this._refresh();
+        }
+    }
+
+    /**
+     * Set the input value programmatically without triggering the dropdown
+     * or firing synthetic events.
+     * @param {string} value
+     * @returns {void}
+     */
+    setValue(value) {
+        const prev = this._suppressInputOpen;
+        this._suppressInputOpen = true;
+        this.input.value = value ?? '';
+        this._suppressInputOpen = prev;
+        if (this._isOpen) {
+            this._refresh();
+        }
+    }
+
+    // ---- build ----
+
+    _buildDropdown() {
+        const panel = document.createElement('div');
+        panel.className = 'lm-combobox-panel';
+        panel.setAttribute('role', 'listbox');
+        panel.style.display = 'none';
+        // Append to <body> so the panel is never clipped by an overflow:hidden
+        // ancestor; positioning is recomputed on each open.
+        document.body.appendChild(panel);
+        this.panel = panel;
+
+        if (this.placeholder) {
+            this.input.setAttribute('placeholder', this.placeholder);
+        }
+        this.input.setAttribute('autocomplete', 'off');
+        this.input.setAttribute('role', 'combobox');
+        this.input.setAttribute('aria-autocomplete', 'list');
+        this.input.setAttribute('aria-expanded', 'false');
+    }
+
+    // ---- event wiring ----
+
+    _bindEvents() {
+        this.input.addEventListener('focus', () => {
+            if (this._suppressInputOpen) return;
+            this._open();
+        });
+
+        this.input.addEventListener('input', () => {
+            if (this._suppressInputOpen) return;
+            this._open();          // no-op if already open
+            this._refresh();       // re-filter by current input value
+            this._scheduleFetch();
+        });
+
+        this.input.addEventListener('keydown', (event) => this._onKeyDown(event));
+
+        // Click an option (delegated)
+        this.panel.addEventListener('click', (event) => {
+            const item = event.target.closest('.lm-combobox-option');
+            if (!item) return;
+            const value = item.dataset.value;
+            if (value !== undefined) {
+                this._choose(value);
+            }
+        });
+
+        // Hover updates the active highlight so keyboard + mouse stay in sync.
+        this.panel.addEventListener('mouseover', (event) => {
+            const item = event.target.closest('.lm-combobox-option');
+            if (!item) return;
+            const idx = Number(item.dataset.index);
+            if (!Number.isNaN(idx)) {
+                this._setActiveIndex(idx);
+            }
+        });
+
+        // Click outside closes the dropdown.
+        this._outsideClickHandler = (event) => {
+            if (this._isOpen && !this.input.contains(event.target) && !this.panel.contains(event.target)) {
+                this._close();
+            }
+        };
+        document.addEventListener('mousedown', this._outsideClickHandler);
+
+        // Reposition on viewport changes while open.
+        this._resizeHandler = () => {
+            if (this._isOpen) this._position();
+        };
+        window.addEventListener('resize', this._resizeHandler);
+        window.addEventListener('scroll', this._resizeHandler, true);
+    }
+
+    // ---- keyboard ----
+
+    _onKeyDown(event) {
+        if (!this._isOpen) {
+            if (event.key === 'ArrowDown') {
+                event.preventDefault();
+                this._open();
+                this._setActiveIndex(0);
+            }
+            return;
+        }
+
+        switch (event.key) {
+            case 'ArrowDown':
+                event.preventDefault();
+                this._setActiveIndex(this._activeIndex + 1);
+                break;
+
+            case 'ArrowUp':
+                event.preventDefault();
+                this._setActiveIndex(this._activeIndex - 1);
+                break;
+
+            case 'Enter':
+                // Only intercept Enter to pick an option when one is actively
+                // highlighted; otherwise let the input's default behavior
+                // (form submit / free-text commit) proceed.
+                if (this._activeIndex >= 0 && this._activeIndex < this._renderedOptions.length) {
+                    event.preventDefault();
+                    this._choose(this._renderedOptions[this._activeIndex]);
+                }
+                break;
+
+            case 'Escape':
+                event.preventDefault();
+                this._close();
+                this.input.focus();
+                break;
+
+            case 'Tab':
+                // Allow normal tab navigation; just close the panel.
+                this._close();
+                break;
+        }
+    }
+
+    // ---- open / close ----
+
+    _open() {
+        if (this._isOpen) return;
+        this._isOpen = true;
+        this.panel.style.display = 'block';
+        this.input.setAttribute('aria-expanded', 'true');
+        // On open, render ALL presets — do not filter by the current input
+        // value.  Filtering on the input event is handled separately.
+        this._render(this.presets);
+        this._position();
+    }
+
+    _close() {
+        if (!this._isOpen) return;
+        this._isOpen = false;
+        this.panel.style.display = 'none';
+        this.input.setAttribute('aria-expanded', 'false');
+        this._activeIndex = -1;
+        this._cancelFetch();
+    }
+
+    _position() {
+        const rect = this.input.getBoundingClientRect();
+        const panelHeight = this.panel.offsetHeight;
+        const viewportHeight = window.innerHeight;
+        const spaceBelow = viewportHeight - rect.bottom;
+        const spaceAbove = rect.top;
+
+        // Flip above the input when there is more room there.
+        const placeAbove = spaceBelow < panelHeight && spaceAbove > spaceBelow;
+        const top = placeAbove
+            ? rect.top + window.scrollY - panelHeight
+            : rect.bottom + window.scrollY;
+
+        this.panel.style.top = `${Math.max(0, top)}px`;
+        this.panel.style.left = `${rect.left + window.scrollX}px`;
+        this.panel.style.minWidth = `${rect.width}px`;
+    }
+
+    // ---- rendering ----
+
+    /** Render a list of strings into the panel. */
+    _render(items) {
+        this._renderedOptions = items;
+        this.panel.innerHTML = '';
+        if (items.length === 0) {
+            const empty = document.createElement('div');
+            empty.className = 'lm-combobox-empty';
+            empty.textContent = this.placeholder ? this.placeholder : 'No options';
+            this.panel.appendChild(empty);
+            this._activeIndex = -1;
+            return;
+        }
+
+        const fragment = document.createDocumentFragment();
+        items.forEach((opt, idx) => {
+            const item = document.createElement('div');
+            item.className = 'lm-combobox-option';
+            item.setAttribute('role', 'option');
+            item.dataset.value = opt;
+            item.dataset.index = String(idx);
+            item.textContent = opt;
+            if (idx === this._activeIndex) {
+                item.classList.add('is-active');
+            }
+            fragment.appendChild(item);
+        });
+        this.panel.appendChild(fragment);
+
+        if (this._activeIndex >= items.length) {
+            this._setActiveIndex(items.length - 1);
+        }
+    }
+
+    /** Filter presets by current input value and re-render. */
+    _refresh() {
+        const value = this.input.value;
+        const filtered = this._filterPresets(value);
+        const merged = this._mergeUnique(filtered, this._fetchedOptions || []);
+        this._render(merged);
+    }
+
+    _filterPresets(value) {
+        const v = (value || '').toLowerCase();
+        if (!v) return [...this.presets];
+        return this.presets.filter((p) => String(p).toLowerCase().startsWith(v));
+    }
+
+    _mergeUnique(...lists) {
+        const seen = new Set();
+        const out = [];
+        for (const list of lists) {
+            for (const item of list) {
+                const key = String(item);
+                if (!seen.has(key)) {
+                    seen.add(key);
+                    out.push(key);
+                }
+            }
+        }
+        return out;
+    }
+
+    _setActiveIndex(idx) {
+        const max = this._renderedOptions.length - 1;
+        const clamped = Math.max(-1, Math.min(max, idx));
+        this._activeIndex = clamped;
+        // Update DOM classes without full re-render.
+        const items = this.panel.querySelectorAll('.lm-combobox-option');
+        items.forEach((el, i) => {
+            el.classList.toggle('is-active', i === clamped);
+        });
+        // Scroll the active item into view inside the panel.
+        if (clamped >= 0 && items[clamped]) {
+            items[clamped].scrollIntoView({ block: 'nearest' });
+        }
+    }
+
+    /**
+     * Remove the panel from the DOM and detach event listeners.
+     * Call this before discarding the Combobox instance.
+     */
+    destroy() {
+        this._close();
+        if (this.panel && this.panel.parentNode) {
+            this.panel.parentNode.removeChild(this.panel);
+        }
+        document.removeEventListener('mousedown', this._outsideClickHandler);
+        window.removeEventListener('resize', this._resizeHandler);
+        window.removeEventListener('scroll', this._resizeHandler, true);
+    }
+
+    _choose(value) {
+        this.input.value = value;
+        this._close();
+        if (typeof this.onSelect === 'function') {
+            this.onSelect(value);
+        }
+        // Re-focus without reopening the dropdown.
+        this._suppressInputOpen = true;
+        this.input.focus();
+        this._suppressInputOpen = false;
+    }
+
+    // ---- async fetch (debounced) ----
+
+    _scheduleFetch() {
+        if (!this.fetchOptions) return;
+        this._cancelFetch();
+        this._fetchTimer = setTimeout(() => {
+            this._fetchTimer = null;
+            this._runFetch();
+        }, DEBOUNCE_MS);
+    }
+
+    _cancelFetch() {
+        if (this._fetchTimer) {
+            clearTimeout(this._fetchTimer);
+            this._fetchTimer = null;
+        }
+        this._fetchToken++; // invalidate any in-flight result
+    }
+
+    async _runFetch() {
+        if (!this.fetchOptions) return;
+        const token = this._fetchToken;
+        const value = this.input.value;
+        let results;
+        try {
+            results = await this.fetchOptions(value);
+        } catch (err) {
+            console.error('Combobox fetchOptions error:', err);
+            results = [];
+        }
+        // Stale guard: a newer fetch or close superseded this one.
+        if (token !== this._fetchToken || !this._isOpen) return;
+        this._fetchedOptions = Array.isArray(results) ? results : [];
+        this._refresh();
+    }
+}
+
+// Expose for non-module callers (templates load via <script type="module">,
+// but some widget code reads globals off `window`).
+if (typeof window !== 'undefined') {
+    window.Combobox = Combobox;
+}

static/js/components/ContextMenu/BaseContextMenu.js

@@ -27,8 +27,9 @@ export class BaseContextMenu {
             const menuItem = e.target.closest('.context-menu-item');
             if (!menuItem || !this.currentCard) return;
 
-            // Ignore clicks on submenu trigger (has-submenu parent)
+            // Ignore clicks on submenu trigger (has-submenu parent) or disabled items
             if (menuItem.classList.contains('has-submenu')) return;
+            if (menuItem.classList.contains('disabled')) return;
 
             const action = menuItem.dataset.action;
             if (!action) return;

static/js/components/ContextMenu/BulkContextMenu.js

@@ -274,7 +274,7 @@ export class BulkContextMenu extends BaseContextMenu {
             case 'resume-metadata-refresh':
                 bulkManager.setSkipMetadataRefresh(false);
                 break;
-            case 'enrich-hf-agent-bulk':
+            case 'enrich-hf-llm-bulk':
                 this.enrichBulkWithAgent();
                 break;
             case 'delete-all':
@@ -377,7 +377,6 @@ export class BulkContextMenu extends BaseContextMenu {
 
         const { agentManager } = await import('../../managers/AgentManager.js');
 
-        // Check if LLM is configured
         const configured = await agentManager.isLlmConfigured();
         if (!configured) {
             showToast('toast.agent.llmNotConfigured', {}, 'warning');
@@ -386,41 +385,66 @@ export class BulkContextMenu extends BaseContextMenu {
 
         const modelPaths = [...state.selectedModels];
 
-        // Connect WebSocket for progress
         agentManager.connect();
 
-        // Set up one-time completion handler
+        const progressUI = state.loadingManager.showEnhancedProgress(
+            `Enriching metadata for ${modelPaths.length} models...`
+        );
+
+        function cleanupCallbacks() {
+            const pIdx = agentManager.progressCallbacks.indexOf(onProgress);
+            if (pIdx >= 0) agentManager.progressCallbacks.splice(pIdx, 1);
+            const cIdx = agentManager.completeCallbacks.indexOf(onComplete);
+            if (cIdx >= 0) agentManager.completeCallbacks.splice(cIdx, 1);
+            const eIdx = agentManager.errorCallbacks.indexOf(onError);
+            if (eIdx >= 0) agentManager.errorCallbacks.splice(eIdx, 1);
+        }
+
+        const onProgress = (data) => {
+            if (data.status === 'processing' && data.current_path && data.updated_data && Object.keys(data.updated_data).length > 0) {
+                if (state.virtualScroller?.updateSingleItem) {
+                    state.virtualScroller.updateSingleItem(data.current_path, data.updated_data);
+                }
+                const pct = data.total > 0 ? Math.floor((data.processed / data.total) * 100) : 0;
+                const name = data.current_path.split('/').pop();
+                progressUI.updateProgress(pct, name, `Processing ${data.processed}/${data.total}: ${name}`);
+            }
+        };
+        agentManager.onProgress(onProgress);
+
         const onComplete = (data) => {
-            const idx = agentManager.completeCallbacks.indexOf(onComplete);
-            if (idx >= 0) agentManager.completeCallbacks.splice(idx, 1);
+            cleanupCallbacks();
 
             if (data.status === 'completed') {
+                if (state.bulkMode) bulkManager.toggleBulkMode();
+                progressUI.complete(data.summary || 'Enrich complete');
                 showToast(
                     'toast.agent.enrichComplete',
                     { summary: data.summary || 'Done' },
                     'success'
                 );
-                // Soft reload to reflect updated metadata
-                window.location.reload();
-            } else if (data.status === 'error') {
-                showToast(
-                    'toast.agent.enrichFailed',
-                    { error: data.error || 'Unknown error' },
-                    'error'
-                );
             }
         };
         agentManager.onComplete(onComplete);
 
-        showToast(
-            'toast.agent.enrichStarted',
-            { count: modelPaths.length },
-            'info'
-        );
+        const onError = (data) => {
+            cleanupCallbacks();
+            if (state.bulkMode) bulkManager.toggleBulkMode();
+            state.loadingManager.hide();
+            showToast(
+                'toast.agent.enrichFailed',
+                { error: data.error || 'Unknown error' },
+                'error'
+            );
+        };
+        agentManager.onError(onError);
 
         try {
             await agentManager.executeSkill('enrich_hf_metadata', modelPaths);
         } catch (error) {
+            cleanupCallbacks();
+            if (state.bulkMode) bulkManager.toggleBulkMode();
+            state.loadingManager.hide();
             showToast(
                 'toast.agent.enrichFailed',
                 { error: error.message },

static/js/components/ContextMenu/LoraContextMenu.js

@@ -1,5 +1,6 @@
 import { BaseContextMenu } from './BaseContextMenu.js';
 import { ModelContextMenuMixin } from './ModelContextMenuMixin.js';
+import { state } from '../../state/index.js';
 import { getModelApiClient, resetAndReload } from '../../api/modelApiFactory.js';
 import { copyLoraSyntax, sendLoraToWorkflow, buildLoraSyntax, showToast } from '../../utils/uiHelpers.js';
 import { showExcludeModal, showDeleteModal } from '../../utils/modalUtils.js';
@@ -23,6 +24,17 @@ export class LoraContextMenu extends BaseContextMenu {
     showMenu(x, y, card) {
         super.showMenu(x, y, card);
         this.updateExcludeMenuItem();
+        this.updateEnrichMenuItem(card);
+    }
+
+    updateEnrichMenuItem(card) {
+        const enrichItem = this.menu?.querySelector('[data-action="enrich-hf-llm"]');
+        if (!enrichItem) return;
+        const hasHfUrl = !!card.dataset.hf_url;
+        enrichItem.classList.toggle('disabled', !hasHfUrl);
+        enrichItem.title = hasHfUrl
+            ? ''
+            : 'Link this model to a HuggingFace repo first (Link Model \u2192 Link to HuggingFace)';
     }
 
     handleMenuAction(action, menuItem) {
@@ -63,7 +75,7 @@ export class LoraContextMenu extends BaseContextMenu {
             case 'refresh-metadata':
                 getModelApiClient().refreshSingleModelMetadata(this.currentCard.dataset.filepath);
                 break;
-            case 'enrich-hf-agent':
+            case 'enrich-hf-llm':
                 this.enrichWithAgent(this.currentCard.dataset.filepath);
                 break;
             case 'exclude':
@@ -78,39 +90,61 @@ export class LoraContextMenu extends BaseContextMenu {
     async enrichWithAgent(filePath) {
         const { agentManager } = await import('../../managers/AgentManager.js');
 
-        // Check if LLM is configured
         const configured = await agentManager.isLlmConfigured();
         if (!configured) {
             showToast('toast.agent.llmNotConfigured', {}, 'warning');
             return;
         }
 
-        // Connect WebSocket for progress
         agentManager.connect();
 
-        // Set up one-time completion handler
+        const progressUI = state.loadingManager.showEnhancedProgress(
+            'Enriching metadata with AI...'
+        );
+
+        function cleanupCallbacks() {
+            const pIdx = agentManager.progressCallbacks.indexOf(onProgress);
+            if (pIdx >= 0) agentManager.progressCallbacks.splice(pIdx, 1);
+            const cIdx = agentManager.completeCallbacks.indexOf(onComplete);
+            if (cIdx >= 0) agentManager.completeCallbacks.splice(cIdx, 1);
+            const eIdx = agentManager.errorCallbacks.indexOf(onError);
+            if (eIdx >= 0) agentManager.errorCallbacks.splice(eIdx, 1);
+        }
+
+        const onProgress = (data) => {
+            if (data.status === 'processing' && data.current_path && data.updated_data && Object.keys(data.updated_data).length > 0) {
+                if (state.virtualScroller?.updateSingleItem) {
+                    state.virtualScroller.updateSingleItem(data.current_path, data.updated_data);
+                }
+                const pct = data.total > 0 ? Math.floor((data.processed / data.total) * 100) : 0;
+                const name = data.current_path.split('/').pop();
+                progressUI.updateProgress(pct, name, `Processing ${name}`);
+            }
+        };
+        agentManager.onProgress(onProgress);
+
         const onComplete = (data) => {
-            const idx = agentManager.completeCallbacks.indexOf(onComplete);
-            if (idx >= 0) agentManager.completeCallbacks.splice(idx, 1);
+            cleanupCallbacks();
 
             if (data.status === 'completed') {
+                progressUI.complete(data.summary || 'Enrich complete');
                 showToast('toast.agent.enrichComplete', { summary: data.summary || 'Done' }, 'success');
-                // Soft reload to reflect updated metadata
-                if (typeof resetAndReload === 'function') {
-                    resetAndReload();
-                }
-            } else if (data.status === 'error') {
-                showToast('toast.agent.enrichFailed', { error: data.error || 'Unknown error' }, 'error');
             }
         };
         agentManager.onComplete(onComplete);
 
-        // Show progress toast
-        showToast('toast.agent.enrichStarted', {}, 'info');
+        const onError = (data) => {
+            cleanupCallbacks();
+            state.loadingManager.hide();
+            showToast('toast.agent.enrichFailed', { error: data.error || 'Unknown error' }, 'error');
+        };
+        agentManager.onError(onError);
 
         try {
             await agentManager.executeSkill('enrich_hf_metadata', [filePath]);
         } catch (error) {
+            cleanupCallbacks();
+            state.loadingManager.hide();
             showToast('toast.agent.enrichFailed', { error: error.message }, 'error');
         }
     }
@@ -118,7 +152,9 @@ export class LoraContextMenu extends BaseContextMenu {
     sendLoraToWorkflow(replaceMode) {
         const card = this.currentCard;
         const usageTips = JSON.parse(card.dataset.usage_tips || '{}');
-        const loraSyntax = buildLoraSyntax(card.dataset.file_name, usageTips);
+        const folder = card.dataset.folder || '';
+        const loraName = folder ? `${folder}/${card.dataset.file_name}` : card.dataset.file_name;
+        const loraSyntax = buildLoraSyntax(loraName, usageTips);
 
         sendLoraToWorkflow(loraSyntax, replaceMode, 'lora');
     }

static/js/components/ContextMenu/ModelContextMenuMixin.js

@@ -187,6 +187,74 @@ export const ModelContextMenuMixin = {
         setTimeout(() => urlInput.focus(), 50);
     },
 
+    // HuggingFace linking methods
+    showLinkHfModal() {
+        const filePath = this.currentCard.dataset.filepath;
+        if (!filePath) return;
+
+        const confirmBtn = document.getElementById('confirmLinkHfBtn');
+        const urlInput = document.getElementById('hfModelUrl');
+        const errorDiv = document.getElementById('hfModelUrlError');
+
+        if (this._boundLinkHfHandler) {
+            confirmBtn.removeEventListener('click', this._boundLinkHfHandler);
+        }
+
+        this._boundLinkHfHandler = async () => {
+            const hfUrl = urlInput.value.trim();
+            if (!hfUrl) {
+                errorDiv.textContent = 'Please enter a HuggingFace repository URL.';
+                return;
+            }
+
+            const hfPattern = /^https?:\/\/huggingface\.co\/([^/]+\/[^/]+)\/?$/;
+            if (!hfPattern.test(hfUrl)) {
+                errorDiv.textContent = 'Invalid URL format. Expected: https://huggingface.co/user/repo';
+                return;
+            }
+
+            errorDiv.textContent = '';
+            modalManager.closeModal('linkHfModal');
+
+            try {
+                state.loadingManager.showSimpleLoading('Linking to HuggingFace...');
+
+                const response = await fetch('/api/lm/set-hf-url', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({ file_path: filePath, hf_url: hfUrl }),
+                });
+
+                if (!response.ok) {
+                    const errData = await response.json().catch(() => ({}));
+                    throw new Error(errData.error || `Request failed: ${response.statusText}`);
+                }
+
+                const data = await response.json();
+                if (data.success) {
+                    showToast('toast.contextMenu.linkHfSuccess', {}, 'success');
+                    await this.resetAndReload();
+                } else {
+                    throw new Error(data.error || 'Failed to link model');
+                }
+            } catch (error) {
+                console.error('Error linking model to HuggingFace:', error);
+                showToast('toast.contextMenu.linkHfFailed', { message: error.message }, 'error');
+            } finally {
+                state.loadingManager.hide();
+            }
+        };
+
+        confirmBtn.addEventListener('click', this._boundLinkHfHandler);
+
+        urlInput.value = '';
+        errorDiv.textContent = '';
+
+        modalManager.showModal('linkHfModal');
+
+        setTimeout(() => urlInput.focus(), 50);
+    },
+
     extractModelVersionId(url) {
         return extractCivitaiModelUrlParts(url);
     },
@@ -295,6 +363,9 @@ export const ModelContextMenuMixin = {
             case 'relink-civitai':
                 this.showRelinkCivitaiModal();
                 return true;
+            case 'link-hf':
+                this.showLinkHfModal();
+                return true;
             case 'set-nsfw':
                 this.showNSFWLevelSelector(null, null, this.currentCard);
                 return true;

static/js/components/RecipeCard.js

@@ -358,7 +358,7 @@ class RecipeCard {
                         <div class="delete-preview">
                             ${isVideo ?
                     `<video src="${previewUrl}" controls muted loop playsinline style="max-width: 100%;"></video>` :
-                    `<img src="${previewUrl}" alt="${this.recipe.title}">`
+                `<img src="${previewUrl}" alt="${this.recipe.title}" onerror="this.onerror=null; this.src='/loras_static/images/no-preview.png'">`
                 }
                         </div>
                         <div class="delete-info">

static/js/components/RecipeModal.js

@@ -757,7 +757,7 @@ class RecipeModal {
                     `<video class="thumbnail-video" autoplay loop muted playsinline>
                         <source src="${lora.preview_url}" type="video/mp4">
                      </video>` :
-                    `<img src="${lora.preview_url || '/loras_static/images/no-preview.png'}" alt="LoRA preview">`;
+                    `<img src="${lora.preview_url || '/loras_static/images/no-preview.png'}" alt="LoRA preview" onerror="this.onerror=null; this.src='/loras_static/images/no-preview.png'">`;
 
                 let loraItemClass = 'recipe-lora-item';
                 if (existsLocally) {
@@ -1606,7 +1606,7 @@ class RecipeModal {
             <video class="thumbnail-video" autoplay loop muted playsinline>
                 <source src="${previewUrl}" type="video/mp4">
             </video>
-        ` : `<img src="${previewUrl}" alt="Checkpoint preview">`;
+        ` : `<img src="${previewUrl}" alt="Checkpoint preview" onerror="this.onerror=null; this.src='/loras_static/images/no-preview.png'">`;
 
         const badge = existsLocally ? `
             <div class="local-badge">

static/js/components/shared/ModelCard.js

@@ -643,7 +643,7 @@ export function createModelCard(model, modelType) {
         <div class="card-preview ${shouldBlur ? 'blurred' : ''}">
             ${isVideo ?
             `<video ${videoAttrs.join(' ')} style="pointer-events: none;"></video>` :
-            `<img src="${versionedPreviewUrl}" alt="${model.model_name}">`
+            `<img src="${versionedPreviewUrl}" alt="${model.model_name}" onerror="this.onerror=null; this.src='/loras_static/images/no-preview.png'">`
         }
             <div class="card-header">
                 ${shouldBlur ?

static/js/components/shared/ModelVersionsTab.js

@@ -432,7 +432,7 @@ function renderMediaMarkup(version) {
 
     return `
         <div class="version-media">
-            <img src="${escapeHtml(version.previewUrl)}" alt="${escapeHtml(version.name || 'preview')}">
+            <img src="${escapeHtml(version.previewUrl)}" alt="${escapeHtml(version.name || 'preview')}" onerror="this.onerror=null; this.src='/loras_static/images/no-preview.png'">
         </div>
     `;
 }

static/js/components/shared/showcase/MediaUtils.js

@@ -586,6 +586,7 @@ export function initMediaControlHandlers(container) {
             const imageMetaRaw = this.dataset.imageMeta;
             const imageUrl = this.dataset.imageUrl;
             const imageNsfw = this.dataset.imageNsfw;
+            const imgId = this.dataset.imgId || '';
             const localPath = this.dataset.localPath || '';
             const showcaseSection = this.closest('.showcase-section');
             const modelHash = showcaseSection ? showcaseSection.dataset.modelHash : '';
@@ -613,6 +614,7 @@ export function initMediaControlHandlers(container) {
                             meta: imageMeta,
                             url: imageUrl,
                             nsfwLevel: imageNsfw ? parseInt(imageNsfw, 10) : undefined,
+                            id: imgId || undefined,
                         },
                         model_hash: modelHash,
                         model_name: modelName || modelHash,

static/js/components/shared/showcase/ShowcaseView.js

@@ -174,7 +174,10 @@ function renderMediaItem(img, index, exampleFiles) {
     const localUrl = localFile ? localFile.path : '';
     
     // Calculate appropriate aspect ratio
-    const aspectRatio = (img.height / img.width) * 100;
+    // Defensive fallback: 0 width/height → 4:3 default (prevents NaN layout)
+    const safeW = img.width || 4;
+    const safeH = img.height || 3;
+    const aspectRatio = (safeH / safeW) * 100;
     const containerWidth = 800; // modal content maximum width
     const minHeightPercent = 40; 
     const maxHeightPercent = (window.innerHeight * 0.6 / containerWidth) * 100;
@@ -210,8 +213,8 @@ function renderMediaItem(img, index, exampleFiles) {
     const model = meta.Model || '';
     const steps = meta.steps || '';
     const sampler = meta.sampler || '';
-    const cfgScale = meta.cfgScale || '';
-    const clipSkip = meta.clipSkip || '';
+    const cfgScale = meta.cfg_scale || meta.cfgScale || '';
+    const clipSkip = meta.clip_skip || meta.clipSkip || '';
     
     // Check if we have any meaningful generation parameters
     const hasParams = seed || model || steps || sampler || cfgScale || clipSkip;
@@ -242,6 +245,7 @@ function renderMediaItem(img, index, exampleFiles) {
                     data-image-url="${img.url || ''}"
                     data-image-nsfw="${img.nsfwLevel ?? ''}"
                     data-image-id="${cdnImageId}"
+                    data-img-id="${img.id || ''}"
                     data-local-path="${localFile ? localFile.path : ''}">
                 <i class="fas fa-book-open"></i>
             </button>

static/js/core.js

@@ -15,6 +15,7 @@ import { initTheme, initBackToTop } from './utils/uiHelpers.js';
 import { initializeInfiniteScroll } from './utils/infiniteScroll.js';
 import { i18n } from './i18n/index.js';
 import { onboardingManager } from './managers/OnboardingManager.js';
+import './components/Combobox.js';
 import { BulkContextMenu } from './components/ContextMenu/BulkContextMenu.js';
 import { createPageContextMenu, createGlobalContextMenu } from './components/ContextMenu/index.js';
 import { initializeEventManagement } from './utils/eventManagementInit.js';

static/js/managers/AgentManager.js

@@ -165,6 +165,18 @@ class AgentManager {
      *
      * @returns {Promise<boolean>}
      */
+    _readProviderRequiresKey(providerId) {
+        const script = document.getElementById('llmProviderPresets');
+        if (!script) return true; // safe default
+        try {
+            const presets = JSON.parse(script.textContent);
+            const preset = presets[providerId];
+            return preset ? preset.requires_key !== false : true;
+        } catch {
+            return true;
+        }
+    }
+
     async isLlmConfigured() {
         try {
             const response = await fetch('/api/lm/settings');
@@ -172,8 +184,9 @@ class AgentManager {
             const data = await response.json();
             const provider = data.settings?.llm_provider;
             const hasModel = !!data.settings?.llm_model;
-            const hasKey = !!data.settings?.llm_api_key;
-            return hasModel && (hasKey || provider === 'ollama');
+            const hasKey = !!(data.settings?.llm_api_key_set || data.settings?.llm_api_key);
+            const needsKey = this._readProviderRequiresKey(provider);
+            return hasModel && (hasKey || !needsKey);
         } catch {
             return false;
         }

static/js/managers/BatchImportManager.js

@@ -1,5 +1,5 @@
 import { modalManager } from './ModalManager.js';
-import { showToast } from '../utils/uiHelpers.js';
+import { showToast, setupAutoNewlineOnPaste } from '../utils/uiHelpers.js';
 import { translate } from '../utils/i18nHelpers.js';
 import { WS_ENDPOINTS } from '../api/apiConfig.js';
 import { getStorageItem, setStorageItem } from '../utils/storageHelpers.js';
@@ -43,6 +43,9 @@ export class BatchImportManager {
                 setStorageItem('batch_import_skip_no_metadata', e.target.checked);
             });
         }
+
+        // Auto-append newline after pasting a URL in the batch URL input
+        setupAutoNewlineOnPaste('batchUrlInput');
     }
 
     /**

static/js/managers/BulkManager.js

@@ -397,6 +397,7 @@ export class BulkManager {
         const updated = {
             ...existing,
             fileName: card.dataset.file_name ?? existing.fileName,
+            folder: card.dataset.folder ?? existing.folder,
             usageTips: card.dataset.usage_tips ?? existing.usageTips,
             modelName: card.dataset.name ?? existing.modelName,
         };
@@ -494,7 +495,8 @@ export class BulkManager {
 
             if (metadata) {
                 const usageTips = JSON.parse(metadata.usageTips || '{}');
-                loraSyntaxes.push(buildLoraSyntax(metadata.fileName, usageTips));
+                const loraName = metadata.folder ? `${metadata.folder}/${metadata.fileName}` : metadata.fileName;
+                loraSyntaxes.push(buildLoraSyntax(loraName, usageTips));
             } else {
                 missingLoras.push(filepath);
             }
@@ -537,7 +539,8 @@ export class BulkManager {
 
             if (metadata) {
                 const usageTips = JSON.parse(metadata.usageTips || '{}');
-                loraSyntaxes.push(buildLoraSyntax(metadata.fileName, usageTips));
+                const loraName = metadata.folder ? `${metadata.folder}/${metadata.fileName}` : metadata.fileName;
+                loraSyntaxes.push(buildLoraSyntax(loraName, usageTips));
             } else {
                 missingLoras.push(filepath);
             }
@@ -553,7 +556,8 @@ export class BulkManager {
             return;
         }
 
-        await sendLoraToWorkflow(loraSyntaxes.join(', '), replaceMode, 'lora');
+        const exitBulkMode = () => { if (state.bulkMode) this.toggleBulkMode(); };
+        await sendLoraToWorkflow(loraSyntaxes.join(', '), replaceMode, 'lora', exitBulkMode);
     }
 
     async _sendAllEmbeddingsToWorkflow() {
@@ -575,7 +579,8 @@ export class BulkManager {
         }
 
         const joinedCode = embeddingCodes.join(', ');
-        await sendEmbeddingToWorkflow(joinedCode);
+        const exitBulkMode = () => { if (state.bulkMode) this.toggleBulkMode(); };
+        await sendEmbeddingToWorkflow(joinedCode, exitBulkMode);
     }
 
     showBulkDeleteModal() {
@@ -633,7 +638,7 @@ export class BulkManager {
                 filePaths.forEach(path => {
                     state.virtualScroller.removeItemByFilePath(path);
                 });
-                this.clearSelection();
+                if (state.bulkMode) this.toggleBulkMode();
 
                 if (window.modelDuplicatesManager) {
                     window.modelDuplicatesManager.updateDuplicatesBadgeAfterRefresh();
@@ -674,6 +679,7 @@ export class BulkManager {
                     const modelId = this.parseModelId(item?.civitai?.modelId);
                     metadataCache.set(item.file_path, {
                         fileName: item.file_name,
+                        folder: item.folder || '',
                         usageTips: item.usage_tips || '{}',
                         modelName: item.name || item.file_name,
                         ...(modelId !== null ? { modelId } : {})
@@ -763,8 +769,9 @@ export class BulkManager {
                     `Re-import complete: ${completed} re-imported, ${failed} failed`
                 );
                 const { resetAndReload: recipeResetAndReload } = await import('../api/recipeApi.js');
-                recipeResetAndReload(false, { preserveScroll: false });
                 this.clearSelection();
+                if (state.bulkMode) this.toggleBulkMode();
+                recipeResetAndReload(false, { preserveScroll: false });
             } else {
                 state.loadingManager.hide();
                 showToast('toast.recipes.reimportBulkFailed', {}, 'error');
@@ -829,7 +836,7 @@ export class BulkManager {
                     );
                 }
 
-                this.clearSelection();
+                if (state.bulkMode) this.toggleBulkMode();
             } else {
                 throw new Error(result.error || 'Bulk repair failed');
             }
@@ -874,6 +881,8 @@ export class BulkManager {
                 if (this.isStripVisible) {
                     this.updateThumbnailStrip();
                 }
+
+                if (state.bulkMode) this.toggleBulkMode();
             }
 
         } catch (error) {
@@ -927,6 +936,7 @@ export class BulkManager {
                 showToast('toast.models.bulkUpdatesNone', { type: typeLabel }, 'info');
             }
 
+            if (state.bulkMode) this.toggleBulkMode();
             await resetAndReload(false);
         } catch (error) {
             console.error('Error checking updates for selected models:', error);
@@ -1273,6 +1283,8 @@ export class BulkManager {
                 showToast(toastKey, { count: failCount }, 'warning');
             }
 
+            if (state.bulkMode) this.toggleBulkMode();
+
         } catch (error) {
             console.error('Error during bulk tag operation:', error);
             const toastKey = mode === 'replace' ? 'toast.models.bulkTagsReplaceFailed' : 'toast.models.bulkTagsAddFailed';
@@ -1398,6 +1410,8 @@ export class BulkManager {
         } else {
             showToast('toast.models.bulkFavoriteFailed', {}, 'error');
         }
+
+        if (state.bulkMode) this.toggleBulkMode();
     }
 
     /**
@@ -1526,6 +1540,8 @@ export class BulkManager {
             showToast('toast.models.bulkContentRatingFailed', {}, 'error');
         }
 
+        if (state.bulkMode) this.toggleBulkMode();
+
         return successCount > 0;
     }
 
@@ -1580,6 +1596,8 @@ export class BulkManager {
         } else {
             showToast('toast.models.skipMetadataRefreshFailed', {}, 'error');
         }
+
+        if (state.bulkMode) this.toggleBulkMode();
     }
 
     /**
@@ -1647,13 +1665,19 @@ export class BulkManager {
                 cancelled = true;
             });
 
+            const isRecipesPage = state.currentPageType === 'recipes';
+
             for (const filepath of state.selectedModels) {
                 if (cancelled) {
                     showToast('toast.api.operationCancelled', {}, 'info');
                     break;
                 }
                 try {
-                    await getModelApiClient().saveModelMetadata(filepath, { base_model: newBaseModel });
+                    if (isRecipesPage) {
+                        await updateRecipeMetadata(filepath, { base_model: newBaseModel });
+                    } else {
+                        await getModelApiClient().saveModelMetadata(filepath, { base_model: newBaseModel });
+                    }
                     successCount++;
                 } catch (error) {
                     errorCount++;
@@ -1674,6 +1698,8 @@ export class BulkManager {
                 showToast('toast.models.bulkBaseModelUpdateFailed', {}, 'error');
             }
 
+            if (state.bulkMode) this.toggleBulkMode();
+
         } catch (error) {
             console.error('Error during bulk base model operation:', error);
             showToast('toast.models.bulkBaseModelUpdateFailed', {}, 'error');
@@ -1711,6 +1737,7 @@ export class BulkManager {
             // Call the auto-organize method with selected file paths
             await apiClient.autoOrganizeModels(filePaths);
 
+            if (state.bulkMode) this.toggleBulkMode();
             resetAndReload(true);
         } catch (error) {
             console.error('Error during bulk auto-organize:', error);

static/js/managers/BulkMissingLoraDownloadManager.js

@@ -196,6 +196,17 @@ export class BulkMissingLoraDownloadManager {
         let completedDownloads = 0;
         let failedDownloads = 0;
         let currentLoraProgress = 0;
+        let cancelled = false;
+
+        loadingManager.showCancelButton(async () => {
+            if (cancelled) return;
+            cancelled = true;
+            try {
+                await this.loraApiClient.cancelDownload(batchDownloadId);
+            } catch (e) {
+                console.error('Cancel request failed:', e);
+            }
+        });
 
         // Set up WebSocket message handler
         ws.onmessage = (event) => {
@@ -207,6 +218,11 @@ export class BulkMissingLoraDownloadManager {
                 return;
             }
 
+            if (data.status === 'cancelled') {
+                cancelled = true;
+                return;
+            }
+
             // Process progress updates
             if (data.status === 'progress' && data.download_id && data.download_id.startsWith(batchDownloadId)) {
                 currentLoraProgress = data.progress;
@@ -249,6 +265,8 @@ export class BulkMissingLoraDownloadManager {
 
         // Download each LoRA sequentially
         for (let i = 0; i < lorasToDownload.length; i++) {
+            if (cancelled) break;
+
             const lora = lorasToDownload[i];
             
             currentLoraProgress = 0;
@@ -275,11 +293,13 @@ export class BulkMissingLoraDownloadManager {
                     modelId,
                     versionId,
                     loraRoot,
-                    '', // Empty relative path, use default paths
+                    '',
                     useDefaultPaths,
                     batchDownloadId
                 );
 
+                if (cancelled) break;
+
                 if (!response.success) {
                     console.error(`Failed to download LoRA ${lora.name || lora.file_name}: ${response.error}`);
                     failedDownloads++;
@@ -288,8 +308,10 @@ export class BulkMissingLoraDownloadManager {
                     updateProgress(100, completedDownloads, '');
                 }
             } catch (error) {
-                console.error(`Error downloading LoRA ${lora.name || lora.file_name}:`, error);
-                failedDownloads++;
+                if (!cancelled) {
+                    console.error(`Error downloading LoRA ${lora.name || lora.file_name}:`, error);
+                    failedDownloads++;
+                }
             }
         }
 
@@ -300,7 +322,10 @@ export class BulkMissingLoraDownloadManager {
         loadingManager.hide();
 
         // Show completion message
-        if (failedDownloads === 0) {
+        if (cancelled) {
+            showToast('toast.downloads.downloadStopped', {}, 'info',
+                `Download cancelled. ${completedDownloads} item(s) completed.`);
+        } else if (failedDownloads === 0) {
             showToast('toast.loras.allDownloadSuccessful', { count: completedDownloads }, 'success');
         } else {
             showToast('toast.loras.downloadPartialSuccess', {

static/js/managers/DownloadManager.js

@@ -1,5 +1,5 @@
 import { modalManager } from './ModalManager.js';
-import { showToast } from '../utils/uiHelpers.js';
+import { showToast, setupAutoNewlineOnPaste } from '../utils/uiHelpers.js';
 import { state } from '../state/index.js';
 import { LoadingManager } from './LoadingManager.js';
 import { getModelApiClient, resetAndReload } from '../api/modelApiFactory.js';
@@ -31,6 +31,7 @@ export class DownloadManager {
         // HF download state
         this.hfRepoId = null;
         this.hfSelectedFiles = [];
+        this.hfRepoCollapsed = {};
 
         this.loadingManager = new LoadingManager();
         this.folderTreeManager = new FolderTreeManager();
@@ -107,7 +108,8 @@ export class DownloadManager {
         // Default path toggle handler
         document.getElementById('useDefaultPath').addEventListener('change', this.handleToggleDefaultPath);
 
-
+        // Auto-append newline after pasting a URL so users can paste multiple URLs in succession
+        setupAutoNewlineOnPaste('modelUrl');
     }
 
     updateModalLabels() {
@@ -173,6 +175,7 @@ export class DownloadManager {
         // Reset HF state
         this.hfRepoId = null;
         this.hfSelectedFiles = [];
+        this.hfRepoCollapsed = {};
     }
 
     async retrieveVersionsForModel(modelId, source = null) {
@@ -463,8 +466,8 @@ export class DownloadManager {
         const trimmed = url.trim();
         if (!trimmed) return null;
 
-        // CivitAI
-        if (/civitai\.com\/models\//i.test(trimmed) || /civitaiarchive|civarchive/i.test(trimmed)) {
+        // CivitAI — matches civitai.com, civitai.red, civitai.green, etc.
+        if (/civitai\.(?:com|red|green)\/models\//i.test(trimmed) || /civitaiarchive|civarchive/i.test(trimmed)) {
             // Will be parsed by existing CivitAI logic
             return { type: 'civitai' };
         }
@@ -725,14 +728,23 @@ export class DownloadManager {
 
     confirmFileSelection() {
         const selectedRadio = document.querySelector('#fileSelectionList input[type="radio"]:checked');
-        if (!selectedRadio) return;
+        if (!selectedRadio) {
+            console.warn('[download] confirmFileSelection: no radio button checked');
+            return;
+        }
 
         const version = this.currentVersion;
-        if (!version) return;
+        if (!version) {
+            console.warn('[download] confirmFileSelection: no currentVersion set');
+            return;
+        }
 
         const modelFiles = (version.files || []).filter(f => f.type === 'Model' || f.type === 'UNet' || f.type === 'Diffusion Model');
         this.selectedFile = modelFiles.find(f => f.id.toString() === selectedRadio.value);
 
+        console.log('[download] confirmFileSelection: selected file id=%s, name="%s", type="%s", metadata=%o',
+            this.selectedFile?.id, this.selectedFile?.name, this.selectedFile?.type, this.selectedFile?.metadata);
+
         document.getElementById('fileSelectionStep').style.display = 'none';
         document.getElementById('locationStep').style.display = 'block';
         this.proceedToLocationContent();
@@ -869,16 +881,26 @@ export class DownloadManager {
         const displayName = versionName || `#${versionId}`;
         let ws = null;
         let updateProgress = () => { };
+        let cancelled = false;
+        const downloadId = Date.now().toString();
 
         try {
             this.loadingManager.restoreProgressBar();
             updateProgress = this.loadingManager.showDownloadProgress(1);
             updateProgress(0, 0, displayName);
-
-            const downloadId = Date.now().toString();
             const wsProtocol = window.location.protocol === 'https:' ? 'wss://' : 'ws://';
             ws = new WebSocket(`${wsProtocol}${window.location.host}/ws/download-progress?id=${downloadId}`);
 
+            this.loadingManager.showCancelButton(async () => {
+                if (cancelled) return;
+                cancelled = true;
+                try {
+                    await this.apiClient.cancelDownload(downloadId);
+                } catch (e) {
+                    console.error('Cancel request failed:', e);
+                }
+            });
+
             ws.onmessage = event => {
                 const data = JSON.parse(event.data);
 
@@ -887,6 +909,12 @@ export class DownloadManager {
                     return;
                 }
 
+                if (data.status === 'cancelled') {
+                    cancelled = true;
+                    this.loadingManager.setStatus(translate('modals.download.status.cancelled', {}, 'Download cancelled'));
+                    return;
+                }
+
                 if (data.status === 'progress' && data.download_id === downloadId) {
                     const metrics = {
                         bytesDownloaded: data.bytes_downloaded,
@@ -925,6 +953,10 @@ export class DownloadManager {
                 fileParams
             );
 
+            if (cancelled) {
+                return false;
+            }
+
             if (response?.skipped) {
                 this.loadingManager.setStatus(translate('modals.download.status.finalizing'));
                 updateProgress(100, 0, displayName);
@@ -965,8 +997,12 @@ export class DownloadManager {
 
             return true;
         } catch (error) {
-            console.error('Failed to download model version:', error);
-            showToast('toast.downloads.downloadError', { message: error?.message }, 'error');
+            if (cancelled) {
+                console.log('Download cancelled by user:', downloadId);
+            } else {
+                console.error('Failed to download model version:', error);
+                showToast('toast.downloads.downloadError', { message: error?.message }, 'error');
+            }
             return false;
         } finally {
             try {
@@ -986,16 +1022,33 @@ export class DownloadManager {
         const totalFiles = this.hfSelectedFiles.length;
         const updateProgress = this.loadingManager.showDownloadProgress(totalFiles);
 
+        let cancelled = false;
+        let currentDownloadId = null;
+
+        this.loadingManager.showCancelButton(async () => {
+            if (cancelled) return;
+            cancelled = true;
+            if (currentDownloadId) {
+                try {
+                    await this.apiClient.cancelDownload(currentDownloadId);
+                } catch (e) {
+                    console.error('Cancel request failed:', e);
+                }
+            }
+        });
+
         try {
             let completedDownloads = 0;
             for (let i = 0; i < totalFiles; i++) {
+                if (cancelled) break;
+
                 const filename = this.hfSelectedFiles[i];
                 updateProgress(0, completedDownloads, filename);
                 this.loadingManager.setStatus(`Downloading ${filename}...`);
 
-                const downloadId = Date.now().toString() + '_' + i;
+                currentDownloadId = Date.now().toString() + '_' + i;
                 const wsProtocol = window.location.protocol === 'https:' ? 'wss://' : 'ws://';
-                const ws = new WebSocket(`${wsProtocol}${window.location.host}/ws/download-progress?id=${downloadId}`);
+                const ws = new WebSocket(`${wsProtocol}${window.location.host}/ws/download-progress?id=${currentDownloadId}`);
 
                 try {
                     await new Promise((resolve, reject) => {
@@ -1003,12 +1056,13 @@ export class DownloadManager {
                         ws.onerror = reject;
                     });
 
-                    // Capture completed count at WS creation time so progress
-                    // updates arriving after completedDownloads increments still
-                    // show the correct "N / total" position.
                     const snapshotCompleted = completedDownloads;
                     ws.onmessage = (event) => {
                         const data = JSON.parse(event.data);
+                        if (data.status === 'cancelled') {
+                            cancelled = true;
+                            return;
+                        }
                         if (data.status === 'progress') {
                             const metrics = {
                                 bytesDownloaded: data.bytes_downloaded,
@@ -1026,9 +1080,11 @@ export class DownloadManager {
                         modelRoot,
                         relativePath: targetFolder,
                         useDefaultPaths,
-                        download_id: downloadId,
+                        download_id: currentDownloadId,
                     });
 
+                    if (cancelled) break;
+
                     if (response?.success) {
                         completedDownloads++;
                         updateProgress(100, completedDownloads, filename);
@@ -1038,13 +1094,19 @@ export class DownloadManager {
                 }
             }
 
-            showToast('toast.loras.downloadCompleted', {}, 'success');
-            // Reload page data — model is already in scanner cache via backend
+            if (cancelled) {
+                showToast('toast.downloads.downloadStopped', {}, 'info',
+                    `Download cancelled. ${completedDownloads} item(s) completed.`);
+            } else {
+                showToast('toast.loras.downloadCompleted', {}, 'success');
+            }
             await resetAndReload(true);
             return true;
         } catch (error) {
-            console.error('Failed to download HF model:', error);
-            showToast('toast.downloads.downloadError', { message: error?.message }, 'error');
+            if (!cancelled) {
+                console.error('Failed to download HF model:', error);
+                showToast('toast.downloads.downloadError', { message: error?.message }, 'error');
+            }
             return false;
         } finally {
             this.loadingManager.hide();
@@ -1077,7 +1139,7 @@ export class DownloadManager {
 
     showBatchPreviewStep() {
         document.querySelectorAll('.download-step').forEach(step => step.style.display = 'none');
-        document.getElementById('batchPreviewStep').style.display = 'block';
+        document.getElementById('batchPreviewStep').style.display = 'flex';
 
         const validCount = this.batchModels.filter(m => {
             if (m.error) return false;
@@ -1091,56 +1153,36 @@ export class DownloadManager {
         const list = document.getElementById('batchPreviewList');
         const hasHfItems = this.batchModels.some(m => m.source === 'huggingface' && !m.error);
 
-        let itemsHtml = this.batchModels.map((item, index) => {
-            if (item.error) {
-                return `
-                    <div class="batch-preview-item batch-preview-error" data-index="${index}">
-                        <div class="batch-preview-icon">
-                            <i class="fas fa-exclamation-triangle"></i>
-                        </div>
-                        <div class="batch-preview-info">
-                            <div class="batch-preview-name">${item.url}</div>
-                            <div class="batch-preview-meta batch-preview-error-text">${item.error}</div>
-                        </div>
-                        <button class="batch-preview-remove" data-index="${index}" title="${translate('common.actions.remove', {}, 'Remove')}">
-                            <i class="fas fa-times"></i>
-                        </button>
+        // Error items render flat, outside any group
+        const errorItemsHtml = this.batchModels.map((item, index) => {
+            if (!item.error) return null;
+            return `
+                <div class="batch-preview-item batch-preview-error" data-index="${index}">
+                    <div class="batch-preview-icon">
+                        <i class="fas fa-exclamation-triangle"></i>
                     </div>
-                `;
-            }
+                    <div class="batch-preview-info">
+                        <div class="batch-preview-name">${item.url}</div>
+                        <div class="batch-preview-meta batch-preview-error-text">${item.error}</div>
+                    </div>
+                    <button class="batch-preview-remove" data-index="${index}" title="${translate('common.actions.remove', {}, 'Remove')}">
+                        <i class="fas fa-times"></i>
+                    </button>
+                </div>
+            `;
+        }).filter(Boolean).join('');
 
+        // CivitAI items render flat, outside any group (unchanged)
+        const civitaiItemsHtml = this.batchModels.map((item, index) => {
+            if (item.error) return null;
+            if (item.source === 'huggingface') return null;
             const ver = item.selectedVersion;
-
-            // HF batch item rendering with checkbox
-            if (item.source === 'huggingface') {
-                const hfSize = item.fileSizeBytes
-                    ? formatFileSize(item.fileSizeBytes)
-                    : '?';
-                return `
-                    <div class="batch-preview-item" data-index="${index}">
-                        <input type="checkbox" class="batch-preview-checkbox"
-                               data-index="${index}" ${item.checked !== false ? 'checked' : ''} />
-                        <div class="batch-preview-info">
-                            <div class="batch-preview-name">${item.displayName || item.filename || `HF #${index}`} <span class="hf-badge">HF</span></div>
-                            <div class="batch-preview-meta">
-                                <span>${hfSize}</span>
-                                <span>${item.repo || ''}</span>
-                            </div>
-                        </div>
-                        <button class="batch-preview-remove" data-index="${index}" title="${translate('common.actions.remove', {}, 'Remove')}">
-                            <i class="fas fa-times"></i>
-                        </button>
-                    </div>
-                `;
-            }
-
             const firstImage = ver?.images?.find(img => !img.url.endsWith('.mp4'));
             const thumbnailUrl = firstImage ? firstImage.url : '/loras_static/images/no-preview.png';
             const fileSize = ver?.modelSizeKB
                 ? (ver.modelSizeKB / 1024).toFixed(1)
                 : (ver?.files?.[0]?.sizeKB ? (ver.files[0].sizeKB / 1024).toFixed(1) : '?');
             const existsLocally = ver?.existsLocally;
-
             return `
                 <div class="batch-preview-item ${existsLocally ? 'batch-preview-local' : ''}" data-index="${index}">
                     <div class="batch-preview-thumbnail">
@@ -1161,8 +1203,59 @@ export class DownloadManager {
                     ` : ''}
                 </div>
             `;
+        }).filter(Boolean).join('');
+
+        // Group HF items by repo (data model stays flat — only rendering groups)
+        const hfGroups = {};
+        this.batchModels.forEach((item, index) => {
+            if (item.error || item.source !== 'huggingface') return;
+            const repo = item.repo || 'unknown';
+            if (!hfGroups[repo]) hfGroups[repo] = [];
+            hfGroups[repo].push({ item, index });
+        });
+
+        const renderHfItem = ({ item, index }) => {
+            const hfSize = item.fileSizeBytes ? formatFileSize(item.fileSizeBytes) : '?';
+            return `
+                <div class="batch-preview-item" data-index="${index}">
+                    <input type="checkbox" class="batch-preview-checkbox"
+                           data-index="${index}" ${item.checked !== false ? 'checked' : ''} />
+                    <div class="batch-preview-info">
+                        <div class="batch-preview-name">${item.displayName || item.filename || `HF #${index}`} <span class="hf-badge">HF</span></div>
+                        <div class="batch-preview-meta">
+                            <span>${hfSize}</span>
+                            <span>${item.repo || ''}</span>
+                        </div>
+                    </div>
+                    <button class="batch-preview-remove" data-index="${index}" title="${translate('common.actions.remove', {}, 'Remove')}">
+                        <i class="fas fa-times"></i>
+                    </button>
+                </div>
+            `;
+        };
+
+        const hfGroupsHtml = Object.keys(hfGroups).map(repo => {
+            const items = hfGroups[repo];
+            const isCollapsed = this.hfRepoCollapsed[repo] === true;
+            const allChecked = items.every(({ item }) => item.checked !== false);
+            const fileCount = items.length;
+            return `
+                <div class="batch-preview-group" data-repo="${repo}">
+                    <div class="batch-preview-group-header">
+                        <i class="fas fa-chevron-right batch-preview-group-toggle ${isCollapsed ? '' : 'expanded'}"></i>
+                        <span class="batch-preview-group-name">${repo}</span>
+                        <span class="batch-preview-group-count">${fileCount} ${translate('modals.download.fileSelection.files', {}, 'files')}</span>
+                        <input type="checkbox" class="batch-preview-group-select-all" data-repo="${repo}" ${allChecked ? 'checked' : ''} />
+                    </div>
+                    <div class="batch-preview-group-body ${isCollapsed ? '' : 'expanded'}">
+                        ${items.map(renderHfItem).join('')}
+                    </div>
+                </div>
+            `;
         }).join('');
 
+        let itemsHtml = errorItemsHtml + civitaiItemsHtml + hfGroupsHtml;
+
         // Prepend select-all toolbar if there are HF items with checkboxes
         if (hasHfItems) {
             const allChecked = this.batchModels
@@ -1178,7 +1271,90 @@ export class DownloadManager {
 
         list.innerHTML = itemsHtml;
 
+        const updateCountAndSelectAll = () => {
+            const checkedCount = this.batchModels.filter(
+                m => !m.error && m.checked !== false
+            ).length;
+            document.getElementById('downloadModalTitle').textContent =
+                translate('modals.download.titleWithType', { type: this.apiClient.apiConfig.config.displayName }) +
+                ` (${checkedCount})`;
+            const nextBtn = document.getElementById('nextFromBatchBtn');
+            nextBtn.disabled = checkedCount === 0;
+            nextBtn.classList.toggle('disabled', checkedCount === 0);
+            // Global select-all
+            const selectAll = document.getElementById('batchSelectAll');
+            if (selectAll) {
+                const hfItems = this.batchModels.filter(m => m.source === 'huggingface' && !m.error);
+                selectAll.checked = hfItems.length > 0 && hfItems.every(m => m.checked !== false);
+            }
+            // Per-group select-all
+            list.querySelectorAll('.batch-preview-group-select-all').forEach(gsa => {
+                const repo = gsa.dataset.repo;
+                const repoItems = this.batchModels.filter(m => m.source === 'huggingface' && !m.error && m.repo === repo);
+                gsa.checked = repoItems.length > 0 && repoItems.every(m => m.checked !== false);
+            });
+        };
+
         list.onclick = (e) => {
+            // Per-group select-all checkbox
+            const groupSelectAll = e.target.closest('.batch-preview-group-select-all');
+            if (groupSelectAll) {
+                const repo = groupSelectAll.dataset.repo;
+                const checked = groupSelectAll.checked;
+                this.batchModels.forEach((m, idx) => {
+                    if (m.source === 'huggingface' && !m.error && m.repo === repo) {
+                        m.checked = checked;
+                        const cb = list.querySelector(`.batch-preview-checkbox[data-index="${idx}"]`);
+                        if (cb) cb.checked = checked;
+                    }
+                });
+                updateCountAndSelectAll();
+                return;
+            }
+
+            const header = e.target.closest('.batch-preview-group-header');
+            if (header) {
+                const group = header.closest('.batch-preview-group');
+                const repo = group.dataset.repo;
+                const body = group.querySelector('.batch-preview-group-body');
+                const toggle = group.querySelector('.batch-preview-group-toggle');
+                const isCollapsed = this.hfRepoCollapsed[repo];
+                if (isCollapsed) {
+                    this.hfRepoCollapsed[repo] = false;
+                    body.style.transition = ''; // restore in case collapse was interrupted
+                    body.classList.add('expanded');
+                    toggle.classList.add('expanded');
+                    // force reflow so expanded class is registered before setting height
+                    void body.offsetHeight;
+                    body.style.maxHeight = body.scrollHeight + 'px';
+                    const onEnd = (e) => {
+                        if (e.propertyName !== 'max-height') return;
+                        if (this.hfRepoCollapsed[repo] !== false) return;
+                        body.style.maxHeight = ''; // fall back to .expanded's 9999px
+                        body.removeEventListener('transitionend', onEnd);
+                    };
+                    body.addEventListener('transitionend', onEnd);
+                } else {
+                    this.hfRepoCollapsed[repo] = true;
+                    body.style.maxHeight = body.scrollHeight + 'px';
+                    requestAnimationFrame(() => {
+                        // animate only max-height; keep expanded so opacity stays 1
+                        body.style.transition = 'max-height 0.35s ease';
+                        body.style.maxHeight = '0';
+                        toggle.classList.remove('expanded');
+                        const onEnd = (e) => {
+                            if (e.propertyName !== 'max-height') return;
+                            if (this.hfRepoCollapsed[repo] !== true) return; // state changed since
+                            body.classList.remove('expanded');
+                            body.style.transition = '';
+                            body.removeEventListener('transitionend', onEnd);
+                        };
+                        body.addEventListener('transitionend', onEnd);
+                    });
+                }
+                return;
+            }
+
             const removeBtn = e.target.closest('.batch-preview-remove');
             if (removeBtn) {
                 const idx = parseInt(removeBtn.dataset.index);
@@ -1193,7 +1369,7 @@ export class DownloadManager {
             }
         };
 
-        // Checkbox handler for HF batch items
+        // Individual HF checkbox handler
         const checkboxes = list.querySelectorAll('.batch-preview-checkbox');
         checkboxes.forEach(cb => {
             cb.addEventListener('change', (e) => {
@@ -1201,26 +1377,11 @@ export class DownloadManager {
                 if (this.batchModels[idx]) {
                     this.batchModels[idx].checked = e.target.checked;
                 }
-                // Update valid count in title and Next button
-                const checkedCount = this.batchModels.filter(
-                    m => !m.error && m.checked !== false
-                ).length;
-                document.getElementById('downloadModalTitle').textContent =
-                    translate('modals.download.titleWithType', { type: this.apiClient.apiConfig.config.displayName }) +
-                    ` (${checkedCount})`;
-                const nextBtn = document.getElementById('nextFromBatchBtn');
-                nextBtn.disabled = checkedCount === 0;
-                nextBtn.classList.toggle('disabled', checkedCount === 0);
-                // Update select-all checkbox state
-                const selectAll = document.getElementById('batchSelectAll');
-                if (selectAll) {
-                    const hfItems = this.batchModels.filter(m => m.source === 'huggingface' && !m.error);
-                    selectAll.checked = hfItems.length > 0 && hfItems.every(m => m.checked !== false);
-                }
+                updateCountAndSelectAll();
             });
         });
 
-        // Select-all handler
+        // Global select-all handler
         const selectAll = document.getElementById('batchSelectAll');
         if (selectAll) {
             selectAll.addEventListener('change', (e) => {
@@ -1233,16 +1394,7 @@ export class DownloadManager {
                         this.batchModels[idx].checked = checked;
                     }
                 });
-                // Update valid count in title and Next button
-                const checkedCount = this.batchModels.filter(
-                    m => !m.error && m.checked !== false
-                ).length;
-                document.getElementById('downloadModalTitle').textContent =
-                    translate('modals.download.titleWithType', { type: this.apiClient.apiConfig.config.displayName }) +
-                    ` (${checkedCount})`;
-                const nextBtn = document.getElementById('nextFromBatchBtn');
-                nextBtn.disabled = checkedCount === 0;
-                nextBtn.classList.toggle('disabled', checkedCount === 0);
+                updateCountAndSelectAll();
             });
         }
 
@@ -1333,12 +1485,23 @@ export class DownloadManager {
             }
 
             const fileParams = this.selectedFile ? {
+                id: this.selectedFile.id,
                 type: this.selectedFile.type || 'Model',
-                format: this.selectedFile.metadata?.format || 'SafeTensor',
-                size: this.selectedFile.metadata?.size || 'full',
-                fp: this.selectedFile.metadata?.fp,
+                format: this.selectedFile.metadata?.format || null,
+                size: this.selectedFile.metadata?.size || null,
+                fp: this.selectedFile.metadata?.fp || null,
             } : null;
 
+            if (fileParams) {
+                console.log('[download] startDownload (single): fileParams built from selectedFile — id=%s, type=%s, format=%s, size=%s, fp=%s',
+                    fileParams.id, fileParams.type, fileParams.format, fileParams.size, fileParams.fp);
+            } else {
+                console.log('[download] startDownload (single): this.selectedFile is null — no file selection, will download primary/default file. version=%s has %d files',
+                    this.currentVersion?.id, (this.currentVersion?.files || []).length);
+            }
+
+            modalManager.closeModal('downloadModal');
+
             return this.executeDownloadWithProgress({
                 modelId: this.modelId,
                 versionId: this.currentVersion.id,
@@ -1377,11 +1540,27 @@ export class DownloadManager {
 
         let completedDownloads = 0;
         let failedDownloads = 0;
+        let cancelled = false;
+
+        loadingManager.showCancelButton(async () => {
+            if (cancelled) return;
+            cancelled = true;
+            try {
+                await this.apiClient.cancelDownload(batchDownloadId);
+            } catch (e) {
+                console.error('Cancel request failed:', e);
+            }
+        });
 
         ws.onmessage = (event) => {
             const data = JSON.parse(event.data);
             if (data.type === 'download_id') return;
 
+            if (data.status === 'cancelled') {
+                cancelled = true;
+                return;
+            }
+
             if (data.status === 'progress' && data.download_id?.startsWith(batchDownloadId)) {
                 const current = downloadItems[completedDownloads + failedDownloads];
                 const name = current?.selectedVersion?.name || current?.displayName || current?.filename || `#${completedDownloads + failedDownloads + 1}`;
@@ -1400,6 +1579,8 @@ export class DownloadManager {
         });
 
         for (let i = 0; i < downloadItems.length; i++) {
+            if (cancelled) break;
+
             const item = downloadItems[i];
             const name = item.displayName || item.filename || (item.selectedVersion?.name || `Model #${item.modelId}`);
             const isHf = item.source === 'huggingface';
@@ -1410,7 +1591,6 @@ export class DownloadManager {
             try {
                 let response;
                 if (isHf) {
-                    // Per-file WebSocket for real-time progress
                     const downloadId = Date.now().toString() + '_hf_' + i;
                     const wsHf = new WebSocket(`${wsProtocol}${window.location.host}/ws/download-progress?id=${downloadId}`);
                     try {
@@ -1444,6 +1624,8 @@ export class DownloadManager {
                         wsHf.close();
                     }
                 } else {
+                    console.log('[download] batch download: fileParams NOT passed for modelId=%s, versionId=%s — backend will use primary file',
+                        item.modelId, item.selectedVersion?.id);
                     response = await this.apiClient.downloadModel(
                         item.modelId,
                         item.selectedVersion.id,
@@ -1455,6 +1637,8 @@ export class DownloadManager {
                     );
                 }
 
+                if (cancelled) break;
+
                 if (!response.success) {
                     failedDownloads++;
                 } else {
@@ -1462,15 +1646,20 @@ export class DownloadManager {
                     updateProgress(100, completedDownloads, '');
                 }
             } catch (err) {
-                console.error(`Failed to download ${name}:`, err);
-                failedDownloads++;
+                if (!cancelled) {
+                    console.error(`Failed to download ${name}:`, err);
+                    failedDownloads++;
+                }
             }
         }
 
         ws.close();
         loadingManager.hide();
 
-        if (failedDownloads === 0) {
+        if (cancelled) {
+            showToast('toast.downloads.downloadStopped', {}, 'info',
+                `Download cancelled. ${completedDownloads} item(s) completed.`);
+        } else if (failedDownloads === 0) {
             showToast('toast.loras.allDownloadSuccessful', { count: completedDownloads }, 'success');
         } else {
             showToast('toast.loras.downloadPartialSuccess', {
@@ -1488,6 +1677,10 @@ export class DownloadManager {
         modelRoot = '',
         targetFolder = ''
     } = {}) {
+        console.warn('[download] downloadVersionWithDefaults: NO fileParams will be sent — backend will always use primary file. '
+            + 'modelType=%s, modelId=%s, versionId=%s, versionName="%s"',
+            modelType, modelId, versionId, versionName);
+
         try {
             this.apiClient = getModelApiClient(modelType);
         } catch (error) {

static/js/managers/FilterManager.js

@@ -1,6 +1,7 @@
 import { getCurrentPageState } from '../state/index.js';
 import { showToast, updatePanelPositions } from '../utils/uiHelpers.js';
 import { getModelApiClient } from '../api/modelApiFactory.js';
+import { getApiEndpoints } from '../api/apiConfig.js';
 import { removeStorageItem, setStorageItem, getStorageItem } from '../utils/storageHelpers.js';
 import { MODEL_TYPE_DISPLAY_NAMES } from '../utils/constants.js';
 import { translate } from '../utils/i18nHelpers.js';
@@ -24,6 +25,12 @@ export class FilterManager {
         this.baseModelOptions = [];
         this.tagsLoaded = false;
 
+        // Tag search state
+        this.modelTagsSearchInput = document.getElementById('modelTagsSearchInput');
+        this.tagSearchDebounceTimer = null;
+        this.tagSearchAbortController = null;
+        this.tagSearchQuery = '';
+
         // Initialize preset manager
         this.presetManager = new FilterPresetManager({
             page: this.currentPage,
@@ -123,6 +130,60 @@ export class FilterManager {
                 this.renderBaseModelTags();
             });
         }
+
+        if (this.modelTagsSearchInput) {
+            this.modelTagsSearchInput.addEventListener('input', () => {
+                clearTimeout(this.tagSearchDebounceTimer);
+                this.tagSearchDebounceTimer = setTimeout(() => {
+                    this.handleTagSearchInput();
+                }, 150);
+            });
+        }
+    }
+
+    handleTagSearchInput() {
+        const query = (this.modelTagsSearchInput?.value || '').trim();
+        const trimmedQuery = query.toLowerCase();
+        if (trimmedQuery === this.tagSearchQuery) return;
+        this.tagSearchQuery = trimmedQuery;
+
+        if (!trimmedQuery) {
+            // Empty query: reload top tags (default/common view)
+            this.loadTopTags();
+            return;
+        }
+        this.searchTags(trimmedQuery);
+    }
+
+    async searchTags(query) {
+        // Abort any in-flight search request
+        if (this.tagSearchAbortController) {
+            this.tagSearchAbortController.abort();
+        }
+        this.tagSearchAbortController = new AbortController();
+        const controller = this.tagSearchAbortController;
+
+        try {
+            const tagsEndpoint = `${getApiEndpoints(this.currentPage).searchTags}?q=${encodeURIComponent(query)}&limit=20`;
+            const response = await fetch(tagsEndpoint, { signal: controller.signal });
+            if (!response.ok) throw new Error('Failed to search tags');
+            const data = await response.json();
+            if (controller.signal.aborted) return; // stale response
+            if (data.success && data.tags) {
+                this.createTagFilterElements(data.tags);
+            } else {
+                throw new Error('Invalid response format');
+            }
+        } catch (error) {
+            if (error.name === 'AbortError') return; // expected, ignore
+            console.error('Error searching tags:', error);
+            const tagsContainer = document.getElementById('modelTagsFilter');
+            if (tagsContainer) {
+                tagsContainer.innerHTML = '<div class="tags-error">Failed to search tags</div>';
+            }
+            const emptyState = document.getElementById('modelTagsEmptyState');
+            if (emptyState) emptyState.hidden = true;
+        }
     }
 
     getNormalizedSearchQuery(input) {
@@ -146,15 +207,24 @@ export class FilterManager {
     }
 
     async loadTopTags() {
+        // Abort any in-flight tag search request
+        if (this.tagSearchAbortController) {
+            this.tagSearchAbortController.abort();
+            this.tagSearchAbortController = null;
+        }
+        this.tagSearchQuery = '';
+
         try {
             // Show loading state
             const tagsContainer = document.getElementById('modelTagsFilter');
+            const emptyState = document.getElementById('modelTagsEmptyState');
             if (!tagsContainer) return;
+            if (emptyState) emptyState.hidden = true;
 
             tagsContainer.innerHTML = '<div class="tags-loading">Loading tags...</div>';
 
             // Determine the API endpoint based on the page type
-            const tagsEndpoint = `/api/lm/${this.currentPage}/top-tags?limit=20`;
+            const tagsEndpoint = `${getApiEndpoints(this.currentPage).topTags}?limit=20`;
 
             const response = await fetch(tagsEndpoint);
             if (!response.ok) throw new Error('Failed to fetch tags');
@@ -179,29 +249,38 @@ export class FilterManager {
 
     createTagFilterElements(tags) {
         const tagsContainer = document.getElementById('modelTagsFilter');
+        const emptyState = document.getElementById('modelTagsEmptyState');
         if (!tagsContainer) return;
 
         tagsContainer.innerHTML = '';
+        if (emptyState) emptyState.hidden = true;
 
         // Collect existing tag names from the API response
         const existingTagNames = new Set(tags.map(t => t.tag));
 
-        // Add any active filter tags that aren't in the top 20
+        // Collect active filter tags that aren't in the response (excluding __no_tags__)
+        const missingSelectedTags = [];
         if (this.filters.tags) {
             Object.keys(this.filters.tags).forEach(tagName => {
-                // Skip special tags like __no_tags__
                 if (tagName.startsWith('__')) return;
-
                 if (!existingTagNames.has(tagName)) {
-                    // Add this tag to the list with count 0 (unknown)
-                    tags.push({ tag: tagName, count: 0 });
+                    missingSelectedTags.push({ tag: tagName, count: 0 });
                     existingTagNames.add(tagName);
                 }
             });
         }
 
+        // Append missing selected tags after the API results so they appear inline
+        for (const t of missingSelectedTags) {
+            tags.push(t);
+        }
+
         if (!tags.length) {
-            tagsContainer.innerHTML = `<div class="no-tags">No ${this.currentPage === 'recipes' ? 'recipe ' : ''}tags available</div>`;
+            if (this.tagSearchQuery) {
+                if (emptyState) emptyState.hidden = false;
+            } else {
+                tagsContainer.innerHTML = `<div class="no-tags">No ${this.currentPage === 'recipes' ? 'recipe ' : ''}tags available</div>`;
+            }
             return;
         }
 
@@ -209,6 +288,10 @@ export class FilterManager {
             const tagEl = document.createElement('div');
             tagEl.className = 'filter-tag tag-filter';
             const tagName = tag.tag;
+
+            if (missingSelectedTags.some(t => t.tag === tagName)) {
+                tagEl.classList.add('extra-tag');
+            }
             tagEl.dataset.tag = tagName;
 
             // Show count only if it's > 0 (known count)
@@ -234,26 +317,28 @@ export class FilterManager {
             tagsContainer.appendChild(tagEl);
         });
 
-        // Add "No tags" as a special filter at the end
-        const noTagsEl = document.createElement('div');
-        noTagsEl.className = 'filter-tag tag-filter special-tag';
-        const noTagsLabel = translate('header.filter.noTags', {}, 'No tags');
-        const noTagsKey = '__no_tags__';
-        noTagsEl.dataset.tag = noTagsKey;
-        noTagsEl.innerHTML = noTagsLabel;
+        // Add "No tags" as a special filter at the end (skip during search)
+        if (!this.tagSearchQuery) {
+            const noTagsEl = document.createElement('div');
+            noTagsEl.className = 'filter-tag tag-filter special-tag';
+            const noTagsLabel = translate('header.filter.noTags', {}, 'No tags');
+            const noTagsKey = '__no_tags__';
+            noTagsEl.dataset.tag = noTagsKey;
+            noTagsEl.innerHTML = noTagsLabel;
 
-        noTagsEl.addEventListener('click', async () => {
-            const currentState = (this.filters.tags && this.filters.tags[noTagsKey]) || 'none';
-            const newState = this.getNextTriStateState(currentState);
-            this.setTagFilterState(noTagsKey, newState);
-            this.applyTagElementState(noTagsEl, newState);
+            noTagsEl.addEventListener('click', async () => {
+                const currentState = (this.filters.tags && this.filters.tags[noTagsKey]) || 'none';
+                const newState = this.getNextTriStateState(currentState);
+                this.setTagFilterState(noTagsKey, newState);
+                this.applyTagElementState(noTagsEl, newState);
 
-            this.updateActiveFiltersCount();
+                this.updateActiveFiltersCount();
 
-            await this.applyFilters(false);
-        });
+                await this.applyFilters(false);
+            });
 
-        tagsContainer.appendChild(noTagsEl);
+            tagsContainer.appendChild(noTagsEl);
+        }
         this.updateTagSelections();
     }
 
@@ -341,7 +426,7 @@ export class FilterManager {
         if (!baseModelTagsContainer) return;
 
         // Set the API endpoint based on current page
-        const apiEndpoint = `/api/lm/${this.currentPage}/base-models?limit=0`;
+        const apiEndpoint = `${getApiEndpoints(this.currentPage).baseModels}?limit=0`;
 
         // Fetch base models
         fetch(apiEndpoint)
@@ -721,6 +806,16 @@ export class FilterManager {
             tagLogic: 'any'
         });
 
+        // Clear tag search input and reset search state
+        if (this.modelTagsSearchInput) {
+            this.modelTagsSearchInput.value = '';
+        }
+        this.tagSearchQuery = '';
+        if (this.tagSearchAbortController) {
+            this.tagSearchAbortController.abort();
+            this.tagSearchAbortController = null;
+        }
+
         // Update tag logic toggle UI
         this.updateTagLogicToggleUI();
 
@@ -731,6 +826,10 @@ export class FilterManager {
         // Update UI
         this.updateTagSelections();
         this.updateActiveFiltersCount();
+        // Reload tag area to drop any non-top-20 tags from the deactivated preset
+        if (this.tagsLoaded) {
+            await this.loadTopTags();
+        }
         this.presetManager.renderPresets(); // Re-render to remove active state
 
         // Remove from local Storage

static/js/managers/FilterPresetManager.js

@@ -478,11 +478,9 @@ export class FilterPresetManager {
             const pageState = getCurrentPageState();
             pageState.filters = this.filterManager.cloneFilters();
 
-            // If tags haven't been loaded yet, load them first
-            if (!this.filterManager.tagsLoaded) {
-                await this.filterManager.loadTopTags();
-                this.filterManager.tagsLoaded = true;
-            }
+            // Refresh tag display so preset's non-top-20 tags appear inline
+            await this.filterManager.loadTopTags();
+            this.filterManager.tagsLoaded = true;
 
             // Check again after async operation
             if (requestId !== this.applyPresetRequestId) return;
@@ -745,8 +743,16 @@ export class FilterPresetManager {
                 presetEl.classList.add('active');
             }
 
-            presetEl.addEventListener('click', (e) => {
-                e.stopPropagation();
+            // Apply preset on click (toggle if already active)
+            // Bind to the whole .filter-preset div so clicking anywhere inside triggers apply
+            presetEl.addEventListener('click', async () => {
+                this.cancelPendingDelete();
+
+                if (this.activePreset === preset.name) {
+                    await this.filterManager.clearFilters();
+                } else {
+                    await this.applyPreset(preset.name);
+                }
             });
 
             const presetName = document.createElement('span');
@@ -759,18 +765,6 @@ export class FilterPresetManager {
             deleteBtn.innerHTML = '<i class="fas fa-times"></i>';
             deleteBtn.title = translate('header.filter.presetDeleteTooltip', {}, 'Delete preset');
 
-            // Apply preset on name click (toggle if already active)
-            presetName.addEventListener('click', async (e) => {
-                e.stopPropagation();
-                this.cancelPendingDelete();
-
-                if (this.activePreset === preset.name) {
-                    await this.filterManager.clearFilters();
-                } else {
-                    await this.applyPreset(preset.name);
-                }
-            });
-
             // Two-step delete on delete button click
             deleteBtn.addEventListener('click', (e) => {
                 e.stopPropagation();

static/js/managers/LoadingManager.js

@@ -281,6 +281,10 @@ export class LoadingManager {
         // Initialize transfer stats with empty data
         updateTransferStats();
 
+        if (this.cancelButton) {
+            this.loadingContent.appendChild(this.cancelButton);
+        }
+
         // Return update function
         return (currentProgress, currentIndex = 0, currentName = '', metrics = {}) => {
             // Update current item progress

static/js/managers/ModalManager.js

@@ -264,6 +264,19 @@ export class ModalManager {
             });
         }
 
+        // Add linkHfModal registration
+        const linkHfModal = document.getElementById('linkHfModal');
+        if (linkHfModal) {
+            this.registerModal('linkHfModal', {
+                element: linkHfModal,
+                onClose: () => {
+                    this.getModal('linkHfModal').element.style.display = 'none';
+                    document.body.classList.remove('modal-open');
+                },
+                closeOnOutsideClick: true
+            });
+        }
+
         // Add exampleAccessModal registration
         const exampleAccessModal = document.getElementById('exampleAccessModal');
         if (exampleAccessModal) {

static/js/managers/MoveManager.js

@@ -330,8 +330,9 @@ class MoveManager {
                     .filter(r => r.success)
                     .map(r => ({ original_file_path: r.original_file_path, new_file_path: r.new_file_path }));
 
-                // Deselect moving items
+                // Deselect moving items and exit bulk mode
                 this.bulkFilePaths.forEach(path => bulkManager.deselectItem(path));
+                if (state.bulkMode) bulkManager.toggleBulkMode();
             } else {
                 // Single move mode
                 const result = await apiClient.moveSingleModel(this.currentFilePath, targetPath, this.useDefaultPath);

static/js/managers/SettingsManager.js

@@ -789,6 +789,27 @@ export class SettingsManager {
         }
     }
 
+    async _fetchProviderModelsAsync() {
+        try {
+            const resp = await fetch('/api/lm/llm/provider-models');
+            if (!resp.ok) return;
+            const data = await resp.json();
+            if (data.success && data.models) {
+                this._providerModels = data.models;
+                // Refresh model combobox if the settings modal is still open.
+                // Skip when provider is Ollama — it fetches its own live list
+                // from the local Ollama API and we must not overwrite it.
+                const llmProviderSelect = document.getElementById('llmProvider');
+                const provider = llmProviderSelect ? llmProviderSelect.value : 'openai';
+                if (this._llmModelCombobox && provider !== 'ollama') {
+                    this._llmModelCombobox.updatePresets(this._providerModels[provider] || []);
+                }
+            }
+        } catch (_) {
+            // Silently ignore — models stay empty until next modal open
+        }
+    }
+
     async loadSettingsToUI() {
         // Set frontend settings from state
         const blurMatureContentCheckbox = document.getElementById('blurMatureContent');
@@ -829,20 +850,112 @@ export class SettingsManager {
         this.updateApiKeyStatus();
         this.updateLlmApiKeyStatus();
 
-        // AI Provider settings
+        // ── AI Provider settings ──────────────────────────────────────
+        // Load provider presets from the JSON script tag embedded in the template
+        this._providerPresets = {};
+        this._providerModels = {};
+        const presetsScript = document.getElementById('llmProviderPresets');
+        if (presetsScript) {
+            try {
+                this._providerPresets = JSON.parse(presetsScript.textContent);
+            } catch (_) {
+                this._providerPresets = {};
+            }
+        }
+        const modelsScript = document.getElementById('llmProviderModels');
+        if (modelsScript) {
+            try {
+                this._providerModels = JSON.parse(modelsScript.textContent);
+            } catch (_) {
+                this._providerModels = {};
+            }
+        }
+
+        // If the embedded provider models is empty (server did not block on
+        // the remote catalog during page render), fetch asynchronously.
+        if (!this._providerModels || Object.keys(this._providerModels).length === 0) {
+            this._fetchProviderModelsAsync();
+        }
+
         const llmProviderSelect = document.getElementById('llmProvider');
         if (llmProviderSelect) {
             llmProviderSelect.value = state.global.settings.llm_provider || 'openai';
         }
 
+        // Destroy previous combobox instances before creating new ones,
+        // since loadSettingsToUI() runs on every modal open.
+        if (this._llmApiBaseCombobox) { this._llmApiBaseCombobox.destroy(); }
+        if (this._llmModelCombobox) { this._llmModelCombobox.destroy(); }
+
         const llmApiBaseInput = document.getElementById('llmApiBase');
         if (llmApiBaseInput) {
             llmApiBaseInput.value = state.global.settings.llm_api_base || '';
+            const presetUrls = Object.values(this._providerPresets)
+                .map(p => p.api_base)
+                .filter(Boolean);
+            if (typeof Combobox !== 'undefined') {
+                this._llmApiBaseCombobox = new Combobox(llmApiBaseInput, {
+                    presets: presetUrls,
+                    placeholder: 'https://api.openai.com/v1',
+                });
+            }
         }
 
+        // Helper to update model Combobox presets from catalog / Ollama API
         const llmModelInput = document.getElementById('llmModel');
-        if (llmModelInput) {
-            llmModelInput.value = state.global.settings.llm_model || '';
+        this._llmModelCombobox = null;
+        if (llmModelInput && typeof Combobox !== 'undefined') {
+            const currentProvider = llmProviderSelect ? llmProviderSelect.value : 'openai';
+            const fallbackModels = currentProvider === 'ollama' ? [] : (this._providerModels[currentProvider] || []);
+            this._llmModelCombobox = new Combobox(llmModelInput, {
+                presets: fallbackModels,
+                placeholder: translate('settings.aiProvider.modelPlaceholder', {}, 'Select a model...'),
+                onSelect: (value) => {
+                    state.global.settings.llm_model = value;
+                    this.saveSetting('llm_model', value)
+                        .then(() => showToast('toast.settings.settingsUpdated', { setting: 'model' }, 'success'))
+                        .catch(() => {});
+                },
+            });
+        }
+
+        const _loadModelPresets = async (provider) => {
+            if (!this._llmModelCombobox) return;
+            if (provider === 'ollama') {
+                try {
+                    const apiBase = document.getElementById('llmApiBase')?.value?.trim() || 'http://localhost:11434/v1';
+                    const resp = await fetch(`/api/lm/llm/models?provider=ollama&api_base=${encodeURIComponent(apiBase)}`);
+                    if (resp.ok) {
+                        const data = await resp.json();
+                        if (data.success && Array.isArray(data.models)) {
+                            this._llmModelCombobox.updatePresets(data.models);
+                            return;
+                        }
+                    }
+                } catch (_) {}
+                this._llmModelCombobox.updatePresets([]);
+            } else {
+                this._llmModelCombobox.updatePresets(this._providerModels[provider] || []);
+            }
+        };
+        _loadModelPresets(llmProviderSelect ? llmProviderSelect.value : 'openai');
+
+        // Provider change → auto-fill API Base URL + update model presets
+        if (llmProviderSelect) {
+            llmProviderSelect.addEventListener('change', () => {
+                const provider = llmProviderSelect.value;
+                const preset = this._providerPresets[provider];
+                if (preset) {
+                    if (llmApiBaseInput && preset.api_base) {
+                        llmApiBaseInput.value = preset.api_base;
+                        if (this._llmApiBaseCombobox) {
+                            this._llmApiBaseCombobox.setValue(preset.api_base);
+                        }
+                        llmApiBaseInput.dispatchEvent(new Event('blur'));
+                    }
+                }
+                _loadModelPresets(provider);
+            });
         }
 
         const civitaiHostSelect = document.getElementById('civitaiHost');
@@ -1580,13 +1693,15 @@ export class SettingsManager {
                 <input type="text" class="extra-folder-path-input"
                        placeholder="${translate('settings.extraFolderPaths.pathPlaceholder', {}, '/path/to/models')}" value="${path}"
                        onblur="settingsManager.updateExtraFolderPaths('${modelType}')"
+                       onfocus="settingsManager.clearExtraFolderPathError(this)"
                        onkeydown="if(event.key === 'Enter') { this.blur(); }" />
                 <button type="button" class="remove-path-btn"
-                        onclick="this.parentElement.parentElement.remove(); settingsManager.updateExtraFolderPaths('${modelType}')"
+                        onclick="settingsManager.removeExtraFolderPathRow(this, '${modelType}')"
                         title="${translate('common.actions.delete', {}, 'Delete')}">
                     <i class="fas fa-times"></i>
                 </button>
             </div>
+            <div class="extra-folder-path-error"></div>
         `;
 
         container.appendChild(row);
@@ -1600,7 +1715,63 @@ export class SettingsManager {
         }
     }
 
+    clearExtraFolderPathError(input) {
+        input.classList.remove('has-error');
+        const row = input.closest('.extra-folder-path-row');
+        if (row) {
+            const errEl = row.querySelector('.extra-folder-path-error');
+            if (errEl) {
+                errEl.classList.remove('visible');
+                errEl.textContent = '';
+            }
+        }
+    }
+
+    _clearAllExtraFolderPathErrors() {
+        document.querySelectorAll('.extra-folder-path-input.has-error').forEach((input) => {
+            input.classList.remove('has-error');
+        });
+        document.querySelectorAll('.extra-folder-path-error.visible').forEach((el) => {
+            el.classList.remove('visible');
+            el.textContent = '';
+        });
+    }
+
+    _markExtraFolderPathsError(modelType, overlappingPaths, showMessage = false) {
+        const container = document.getElementById(`extraFolderPaths-${modelType}`);
+        if (!container) return;
+
+        const inputs = container.querySelectorAll('.extra-folder-path-input');
+        inputs.forEach((input) => {
+            const val = input.value.trim();
+            if (val && overlappingPaths.includes(val)) {
+                input.classList.add('has-error');
+                if (showMessage) {
+                    const row = input.closest('.extra-folder-path-row');
+                    if (row) {
+                        const errEl = row.querySelector('.extra-folder-path-error');
+                        if (errEl) {
+                            errEl.textContent = translate('settings.extraFolderPaths.validation.checkpointUnetOverlapInline', {}, 'This path is also used for a different model type. Use separate folders for checkpoints and diffusion models.');
+                            errEl.classList.add('visible');
+                        }
+                    }
+                }
+            }
+        });
+    }
+
+    removeExtraFolderPathRow(btn, modelType) {
+        const row = btn.closest('.extra-folder-path-row');
+        if (row) {
+            row.remove();
+            this.updateExtraFolderPaths(modelType);
+        }
+    }
+
     async updateExtraFolderPaths(changedModelType) {
+        // Clear previous errors
+        this._clearAllExtraFolderPathErrors();
+
         const extraFolderPaths = {};
 
         // Collect paths for all model types
@@ -1621,6 +1792,32 @@ export class SettingsManager {
             extraFolderPaths[modelType] = paths;
         });
 
+        // Client-side pre-check: checkpoints and unet must not share the same path.
+        // Normalise paths to reduce false negatives vs the backend's realpath + normcase.
+        const normalise = (p) => p.replace(/[/\\]+$/, '').toLowerCase();
+        const ckptSet = new Set((extraFolderPaths.checkpoints || []).map(normalise));
+        const unetSet = new Set((extraFolderPaths.unet || []).map(normalise));
+        const ckptOverlap = (extraFolderPaths.checkpoints || []).filter(p => p && unetSet.has(normalise(p)));
+        const unetOverlap = (extraFolderPaths.unet || []).filter(p => p && ckptSet.has(normalise(p)));
+        const hasOverlap = ckptOverlap.length > 0 || unetOverlap.length > 0;
+
+        if (hasOverlap) {
+            // Error message only on the side the user just edited.
+            // The other side gets red border only (passive conflict indicator).
+            if (changedModelType === 'checkpoints') {
+                this._markExtraFolderPathsError('checkpoints', ckptOverlap, true);
+                this._markExtraFolderPathsError('unet', unetOverlap, false);
+            } else if (changedModelType === 'unet') {
+                this._markExtraFolderPathsError('unet', unetOverlap, true);
+                this._markExtraFolderPathsError('checkpoints', ckptOverlap, false);
+            } else {
+                // Pre-existing conflict from direct config edit — mark both without messages
+                this._markExtraFolderPathsError('checkpoints', ckptOverlap, false);
+                this._markExtraFolderPathsError('unet', unetOverlap, false);
+            }
+            return;
+        }
+
         // Check if paths have actually changed
         const currentPaths = state.global.settings.extra_folder_paths || {};
         const pathsChanged = JSON.stringify(currentPaths) !== JSON.stringify(extraFolderPaths);
@@ -2149,6 +2346,16 @@ export class SettingsManager {
                 enableMetadataArchiveCheckbox.checked = state.global.settings.enable_metadata_archive_db || false;
             }
 
+            const enableCivarchiveApiCheckbox = document.getElementById('enableCivarchiveApi');
+            if (enableCivarchiveApiCheckbox) {
+                enableCivarchiveApiCheckbox.checked = state.global.settings.enable_civarchive_api ?? true;
+            }
+
+            const metadataProviderOrderSelect = document.getElementById('metadataProviderOrder');
+            if (metadataProviderOrderSelect) {
+                metadataProviderOrderSelect.value = state.global.settings.metadata_provider_order || 'civitai_archive_sqlite';
+            }
+
             // Load status
             await this.updateMetadataArchiveStatus();
         } catch (error) {
@@ -2949,7 +3156,7 @@ export class SettingsManager {
     }
 
     updateLlmApiKeyStatus() {
-        const hasKey = !!state.global.settings.llm_api_key;
+        const hasKey = !!(state.global.settings.llm_api_key_set || state.global.settings.llm_api_key);
         const statusText = document.getElementById('llmApiKeyStatusText');
         const actionBtn = document.getElementById('llmApiKeyActionBtn');
         if (!statusText || !actionBtn) return;

static/js/managers/import/DownloadManager.js

@@ -168,6 +168,18 @@ export class DownloadManager {
         let failedDownloads = 0;
         let accessFailures = 0;
         let currentLoraProgress = 0;
+        let cancelled = false;
+
+        this.importManager.loadingManager.showCancelButton(async () => {
+            if (cancelled) return;
+            cancelled = true;
+            try {
+                const loraClient = getModelApiClient(MODEL_TYPES.LORA);
+                await loraClient.cancelDownload(batchDownloadId);
+            } catch (e) {
+                console.error('Cancel request failed:', e);
+            }
+        });
 
         // Set up progress tracking for current download
         ws.onmessage = (event) => {
@@ -179,6 +191,11 @@ export class DownloadManager {
                 return;
             }
 
+            if (data.status === 'cancelled') {
+                cancelled = true;
+                return;
+            }
+
             // Process progress updates for our current active download
             if (data.status === 'progress' && data.download_id && data.download_id.startsWith(batchDownloadId)) {
                 // Update current LoRA progress
@@ -221,6 +238,8 @@ export class DownloadManager {
         const useDefaultPaths = getStorageItem('use_default_path_loras', false);
 
         for (let i = 0; i < this.importManager.downloadableLoRAs.length; i++) {
+            if (cancelled) break;
+
             const lora = this.importManager.downloadableLoRAs[i];
 
             // Reset current LoRA progress for new download
@@ -241,15 +260,13 @@ export class DownloadManager {
                     batchDownloadId
                 );
 
+                if (cancelled) break;
+
                 if (!response.success) {
                     console.error(`Failed to download LoRA ${lora.name}: ${response.error}`);
-
                     failedDownloads++;
-                    // Continue with next download
                 } else {
                     completedDownloads++;
-
-                    // Update progress to show completion of current LoRA
                     updateProgress(100, completedDownloads, '');
 
                     if (completedDownloads + failedDownloads < this.importManager.downloadableLoRAs.length) {
@@ -259,9 +276,10 @@ export class DownloadManager {
                     }
                 }
             } catch (downloadError) {
-                console.error(`Error downloading LoRA ${lora.name}:`, downloadError);
-                failedDownloads++;
-                // Continue with next download
+                if (!cancelled) {
+                    console.error(`Error downloading LoRA ${lora.name}:`, downloadError);
+                    failedDownloads++;
+                }
             }
         }
 
@@ -269,7 +287,10 @@ export class DownloadManager {
         ws.close();
 
         // Show appropriate completion message based on results
-        if (failedDownloads === 0) {
+        if (cancelled) {
+            showToast('toast.downloads.downloadStopped', {}, 'info',
+                `Download cancelled. ${completedDownloads} item(s) completed.`);
+        } else if (failedDownloads === 0) {
             showToast('toast.loras.allDownloadSuccessful', { count: completedDownloads }, 'success');
         } else {
             if (accessFailures > 0) {

static/js/state/index.js

@@ -13,6 +13,8 @@ const DEFAULT_SETTINGS_BASE = Object.freeze({
     language: 'en',
     show_only_sfw: false,
     enable_metadata_archive_db: false,
+    enable_civarchive_api: true,
+    metadata_provider_order: 'civitai_archive_sqlite',
     proxy_enabled: false,
     proxy_type: 'http',
     proxy_host: '',