Merge pull request #1013 from willmiao/agent

Hugging Face model metadata AI enrichment

py/routes/handlers/agent_handlers.py

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

py/routes/handlers/hf_handlers.py

@@ -49,6 +49,14 @@ async def _get_hf_api_session() -> aiohttp.ClientSession:
     return _hf_api_session
 
 
+async def close_hf_api_session() -> None:
+    """Close the shared HF API session, if it was ever created."""
+    global _hf_api_session
+    if _hf_api_session is not None and not _hf_api_session.closed:
+        await _hf_api_session.close()
+        _hf_api_session = None
+
+
 def _infer_model_type(model_root: str) -> tuple[Any, str]:
     """Determine model class and scanner by matching ``model_root`` against the
     configured root paths for each model type (from ``Config``).

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 (
@@ -49,6 +55,7 @@ from ...utils.constants import (
     VALID_LORA_TYPES,
 )
 from .hf_handlers import HfHandler
+from .agent_handlers import AgentHandler
 from ...utils.civitai_utils import rewrite_preview_url
 from ...utils.example_images_paths import (
     find_non_compliant_items_in_example_images_root,
@@ -1399,8 +1406,9 @@ 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",
         }
     )
 
@@ -1458,6 +1466,8 @@ 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
@@ -1562,6 +1572,42 @@ class SettingsHandler:
             logger.error("Error updating settings: %s", exc, exc_info=True)
             return web.Response(status=500, text=str(exc))
 
+    async def get_llm_models(self, request: web.Request) -> web.Response:
+        """Return the model list for a provider.
+
+        For ``ollama`` the list is fetched live from the local Ollama API
+        (only models actually pulled locally are shown).  For all other
+        providers the opencode model catalog is used.
+
+        Query parameters:
+            provider (required): Internal provider id (``openai``, ``ollama``, etc.).
+
+        Returns:
+            ``{"success": true, "models": ["gpt-4o", ...]}``.
+        """
+        provider_id = request.query.get("provider", "").strip()
+        if not provider_id:
+            return web.json_response(
+                {"success": False, "error": "provider query parameter is required", "models": []},
+                status=400,
+            )
+
+        try:
+            if provider_id == "ollama":
+                api_base = request.query.get("api_base", "").strip() or self._settings.get("llm_api_base", "")
+                if not api_base:
+                    api_base = "http://localhost:11434/v1"
+                models = await fetch_ollama_models(api_base)
+            else:
+                models = await get_provider_model_ids(provider_id)
+            return web.json_response({"success": True, "models": models})
+        except Exception as exc:
+            logger.warning("get_llm_models failed for %s: %s", provider_id, exc)
+            return web.json_response(
+                {"success": False, "error": str(exc), "models": []},
+                status=500,
+            )
+
     def _validate_example_images_path(self, folder_path: str) -> str | None:
         if not os.path.exists(folder_path):
             return f"Path does not exist: {folder_path}"
@@ -1584,6 +1630,20 @@ 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:
@@ -3317,6 +3377,7 @@ class MiscHandlerSet:
         example_workflows: ExampleWorkflowsHandler,
         base_model: BaseModelHandlerSet,
         hf_handler: HfHandler | None = None,
+        agent_handler: AgentHandler | None = None,
     ) -> None:
         self.health = health
         self.settings = settings
@@ -3336,6 +3397,7 @@ class MiscHandlerSet:
         self.example_workflows = example_workflows
         self.base_model = base_model
         self.hf_handler = hf_handler
+        self.agent_handler = agent_handler
 
     def to_route_mapping(
         self,
@@ -3351,6 +3413,8 @@ 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,
@@ -3384,6 +3448,10 @@ 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,
+            # Agent skill handlers
+            "get_agent_skills": self.agent_handler.get_agent_skills,
+            "execute_agent_skill": self.agent_handler.execute_agent_skill,
+            "cancel_agent_skill": self.agent_handler.cancel_agent_skill,
             # Base model handlers
             "get_base_models": self.base_model.get_base_models,
             "refresh_base_models": self.base_model.refresh_base_models,

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:

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"),
@@ -101,6 +103,16 @@ MISC_ROUTE_DEFINITIONS: tuple[RouteDefinition, ...] = (
     RouteDefinition(
         "POST", "/api/lm/download-hf-model", "download_hf_model"
     ),
+    # Agent skill endpoints
+    RouteDefinition(
+        "GET", "/api/lm/agent/skills", "get_agent_skills"
+    ),
+    RouteDefinition(
+        "POST", "/api/lm/agent/execute/{skill_name}", "execute_agent_skill"
+    ),
+    RouteDefinition(
+        "POST", "/api/lm/agent/cancel", "cancel_agent_skill"
+    ),
 )
 
 

py/routes/misc_routes.py

@@ -40,6 +40,7 @@ from .handlers.misc_handlers import (
 )
 from .handlers.base_model_handlers import BaseModelHandlerSet
 from .handlers.hf_handlers import HfHandler
+from .handlers.agent_handlers import AgentHandler
 from .misc_route_registrar import MiscRouteRegistrar
 
 logger = logging.getLogger(__name__)
@@ -138,6 +139,7 @@ class MiscRoutes:
         example_workflows = ExampleWorkflowsHandler()
         base_model = BaseModelHandlerSet()
         hf_handler = HfHandler()
+        agent_handler = AgentHandler()
 
         return self._handler_set_factory(
             health=health,
@@ -158,6 +160,7 @@ class MiscRoutes:
             example_workflows=example_workflows,
             base_model=base_model,
             hf_handler=hf_handler,
+            agent_handler=agent_handler,
         )