Backend efficiency & consistency pass

- Rewrite get_all_tags() with SQL unnest instead of loading all notes
- Consolidate convert_note_to_task/convert_task_to_note to single-session ops
- Add search_notes_for_context() with single OR-keyword query for build_context()
- Drop selectinload from list_conversations(), use correlated subquery for message_count
- Add set_settings_batch() for single-transaction multi-setting upserts
- Extract get_installed_models() shared helper into services/llm.py
- Delete services/tasks.py pass-through wrapper; routes/tasks.py imports from services.notes
- Add B-tree indexes on notes.title and conversations.updated_at (migration 0007)
- Add logging to services/notes.py, services/chat.py, services/settings.py
- Safe Conversation.to_dict() when messages relationship is not loaded

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/fabledassistant/services/llm.py

@@ -6,7 +6,7 @@ from collections.abc import AsyncGenerator
 import httpx
 
 from fabledassistant.config import Config
-from fabledassistant.services.notes import get_note, list_notes
+from fabledassistant.services.notes import get_note, search_notes_for_context
 from fabledassistant.services.settings import get_setting
 
 logger = logging.getLogger(__name__)
@@ -23,18 +23,32 @@ STOP_WORDS = frozenset({
 })
 
 
-async def ensure_model(model: str) -> None:
-    """Check if model exists in Ollama, pull if missing."""
+async def get_installed_models() -> set[str]:
+    """Return set of installed Ollama model names (with and without :latest)."""
     try:
         async with httpx.AsyncClient(timeout=10.0) as client:
             resp = await client.get(f"{Config.OLLAMA_URL}/api/tags")
             resp.raise_for_status()
             data = resp.json()
-            names = {m["name"] for m in data.get("models", [])}
-            # Check both with and without :latest tag
-            if model in names or f"{model}:latest" in names:
-                logger.info("Model '%s' already available", model)
-                return
+            names: set[str] = set()
+            for m in data.get("models", []):
+                name = m["name"]
+                names.add(name)
+                if name.endswith(":latest"):
+                    names.add(name.removesuffix(":latest"))
+            return names
+    except Exception:
+        logger.warning("Failed to fetch installed Ollama models")
+        return set()
+
+
+async def ensure_model(model: str) -> None:
+    """Check if model exists in Ollama, pull if missing."""
+    try:
+        installed = await get_installed_models()
+        if model in installed or f"{model}:latest" in installed:
+            logger.info("Model '%s' already available", model)
+            return
     except Exception:
         logger.warning("Failed to check Ollama models, attempting pull anyway")
 
@@ -172,39 +186,29 @@ async def build_context(
                 f"--- End Note ---"
             )
 
-    # Search notes by keywords from user message — search per keyword
-    # individually and deduplicate to get OR-style matching (any keyword hit
-    # is relevant context).  Collect up to 3 unique notes.
+    # Search notes by keywords from user message — single OR query
     keywords = _extract_keywords(user_message)
     if keywords:
-        seen_ids: set[int] = set()
-        snippets: list[str] = []
-        for kw in keywords[:5]:
-            if len(snippets) >= 3:
-                break
-            try:
-                notes, _ = await list_notes(q=kw, limit=3)
-                for n in notes:
-                    if n.id in seen_ids:
-                        continue
-                    if current_note_id and n.id == current_note_id:
-                        continue
-                    if n.id in exclude_set:
-                        continue
-                    seen_ids.add(n.id)
-                    body_preview = n.body[:2000] if n.body else ""
-                    snippets.append(f"- {n.title}: {body_preview}")
-                    context_meta["auto_notes"].append({"id": n.id, "title": n.title})
-                    if len(snippets) >= 3:
-                        break
-            except Exception:
-                continue
-        if snippets:
-            system_parts.append(
-                "\n\n--- Related Notes ---\n"
-                + "\n".join(snippets)
-                + "\n--- End Related Notes ---"
+        search_exclude = set(exclude_set)
+        if current_note_id:
+            search_exclude.add(current_note_id)
+        try:
+            notes = await search_notes_for_context(
+                keywords, exclude_ids=search_exclude or None, limit=3
             )
+            snippets: list[str] = []
+            for n in notes:
+                body_preview = n.body[:2000] if n.body else ""
+                snippets.append(f"- {n.title}: {body_preview}")
+                context_meta["auto_notes"].append({"id": n.id, "title": n.title})
+            if snippets:
+                system_parts.append(
+                    "\n\n--- Related Notes ---\n"
+                    + "\n".join(snippets)
+                    + "\n--- End Related Notes ---"
+                )
+        except Exception:
+            logger.warning("Failed to search notes for context", exc_info=True)
 
     # Fetch URL content from user message
     urls = _find_urls(user_message)