Enable thinking mode in full chat view, keep disabled in widget/panel

stream_chat_with_tools now accepts a think parameter. run_generation
forwards it to Ollama. The message POST route reads think from the
request body. ChatView passes think=true so qwen3 uses chain-of-thought
reasoning for full conversations; the dashboard widget and ChatPanel
omit it, staying fast. Dashboard button updated to "Think it through
in Chat →" to signal the deeper capability.

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

src/fabledassistant/routes/chat.py

@@ -106,6 +106,7 @@ async def send_message_route(conv_id: int):
         return jsonify({"error": "content is required"}), 400
     context_note_id = data.get("context_note_id")
     exclude_note_ids = data.get("exclude_note_ids") or []
+    think = bool(data.get("think", False))
 
     # Reject if generation already running for this conversation
     existing = get_buffer(conv_id)
@@ -134,6 +135,7 @@ async def send_message_route(conv_id: int):
         uid, conv_id, conv.title, content,
         context_note_id=context_note_id,
         exclude_note_ids=exclude_note_ids,
+        think=think,
     ))
 
     return jsonify({

src/fabledassistant/services/generation_task.py

@@ -166,6 +166,7 @@ async def run_generation(
     user_content: str,
     context_note_id: int | None = None,
     exclude_note_ids: list[int] | None = None,
+    think: bool = False,
 ) -> None:
     """Stream LLM response into buffer with periodic DB flushes."""
     MAX_TOOL_ROUNDS = 5
@@ -349,7 +350,7 @@ async def run_generation(
 
             buf.append_event("status", {"status": "Generating response..." if _round == 0 else "Composing response..."})
             t_stream = time.monotonic()
-            async for chunk in stream_chat_with_tools(messages, model, tools=tools):
+            async for chunk in stream_chat_with_tools(messages, model, tools=tools, think=think):
                 if buf.cancel_event.is_set():
                     cancelled = True
                     break

src/fabledassistant/services/llm.py

@@ -114,12 +114,17 @@ async def stream_chat_with_tools(
     messages: list[dict],
     model: str,
     tools: list[dict] | None = None,
+    think: bool = False,
 ) -> AsyncGenerator[ChatChunk, None]:
     """Stream chat completion from Ollama with tool support.
 
     Yields ChatChunk objects. If the model returns tool_calls, a
     ChatChunk(type="tool_calls") is yielded. Always ends with
     ChatChunk(type="done").
+
+    Set think=True to enable the model's chain-of-thought reasoning (qwen3+).
+    Thinking tokens are consumed by Ollama and not forwarded to the caller;
+    only the final response content is yielded. Expect higher TTFT when enabled.
     """
     options: dict = {"num_ctx": 32768}
     if tools:
@@ -129,7 +134,7 @@ async def stream_chat_with_tools(
         "messages": messages,
         "stream": True,
         "options": options,
-        "think": False,
+        "think": think,
     }
     if tools:
         payload["tools"] = tools