Add note context visibility in chat and standardize UI design tokens

Improve chat context: build_context() now returns metadata about auto-found
notes, emitted as an SSE event so the frontend can display context pills
showing which notes influenced the response. Users can promote notes for
deeper context (+) or exclude irrelevant ones (x). A note picker lets users
manually attach notes. Multi-word search uses per-term AND matching, and
auto-search iterates keywords individually for broader OR-style coverage.

Standardize styling: introduce CSS design tokens (--radius-sm/md/lg/pill,
--color-success/warning/overlay, --focus-ring) and migrate all components
to use them. Fix header alignment to full-width, add active nav link state,
replace hardcoded colors with CSS variables, and normalize button padding.

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

src/fabledassistant/routes/chat.py

@@ -85,6 +85,7 @@ async def send_message_route(conv_id: int):
     if not content:
         return jsonify({"error": "content is required"}), 400
     context_note_id = data.get("context_note_id")
+    exclude_note_ids = data.get("exclude_note_ids") or []
 
     # Save user message
     await add_message(conv_id, "user", content, context_note_id=context_note_id)
@@ -96,11 +97,17 @@ async def send_message_route(conv_id: int):
             history.append({"role": msg.role, "content": msg.content})
 
     # Build context with note search, URL fetching, etc.
-    messages = await build_context(history, context_note_id, content)
+    messages, context_meta = await build_context(
+        history, context_note_id, content, exclude_note_ids=exclude_note_ids
+    )
 
     model = conv.model or await get_setting("default_model", Config.OLLAMA_MODEL)
 
     async def generate():
+        # Emit context metadata before streaming LLM response
+        context_event = json.dumps({"context": context_meta})
+        yield f"data: {context_event}\n\n"
+
         full_response = []
         try:
             async for chunk in stream_chat(messages, model):

src/fabledassistant/routes/settings.py

@@ -1,10 +1,29 @@
+import httpx
 from quart import Blueprint, jsonify, request
 
+from fabledassistant.config import Config
 from fabledassistant.services.settings import get_all_settings, set_setting
 
 settings_bp = Blueprint("settings", __name__, url_prefix="/api/settings")
 
 
+async def _get_installed_models() -> set[str]:
+    """Return set of installed Ollama model names, with and without :latest."""
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            resp = await client.get(f"{Config.OLLAMA_URL}/api/tags")
+            resp.raise_for_status()
+            data = resp.json()
+            names: set[str] = set()
+            for m in data.get("models", []):
+                name = m["name"]
+                names.add(name)
+                names.add(name.replace(":latest", ""))
+            return names
+    except Exception:
+        return set()
+
+
 @settings_bp.route("", methods=["GET"])
 async def get_settings_route():
     settings = await get_all_settings()
@@ -16,6 +35,13 @@ async def update_settings_route():
     data = await request.get_json()
     if not isinstance(data, dict):
         return jsonify({"error": "Expected a JSON object"}), 400
+
+    if "default_model" in data:
+        model = str(data["default_model"])
+        installed = await _get_installed_models()
+        if installed and model not in installed:
+            return jsonify({"error": f"Model '{model}' is not installed"}), 400
+
     for key, value in data.items():
         await set_setting(key, str(value))
     settings = await get_all_settings()