ai: keep slow-CPU chat streams alive

On the FX-8320 the first token took over a minute, and Sanic's default
60-second RESPONSE_TIMEOUT killed the stream before anything was sent.
Raise the timeout above the chat loop's own 600s hard ceiling, and emit
a status event before every model call so the stream is never silent —
for proxies and for the user staring at a slow machine.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

modules/ai/chat.py

@@ -152,6 +152,9 @@ async def post_chat(request: Request, body: ChatRequest):
                 return
 
             service.record_llm_activity()
+            # Always send something before the model call: on slow CPUs the first token can be
+            # minutes away, and a silent stream looks dead to the UI and to proxies.
+            await _send_event(response, 'status', dict(message='Thinking…'))
             tool_calls = []
             final_answer = []
             async for event in llama_chat_stream(messages, tools):

modules/ai/test/test_chat_api.py

@@ -92,7 +92,8 @@ async def test_chat_tool_call_then_answer(async_client, ai_enabled, video_factor
     assert response.status_code == HTTPStatus.OK
 
     events = _parse_sse(response.text)
-    names = [e for e, _ in events]
+    # A status event precedes every model call so slow CPUs never leave the stream silent.
+    names = [e for e, _ in events if e != 'status']
     assert names == ['tool_call', 'tool_result', 'token', 'token', 'done']
     tool_call = dict(events)['tool_call']
     assert tool_call == dict(tool='search_videos', args=dict(search_str='canning'))
@@ -116,7 +117,7 @@ async def test_chat_plain_answer(async_client, ai_enabled):
     body = dict(mode='help', messages=[dict(role='user', content='hi')])
     with patch:
         request, response = await async_client.post('/api/chat/', content=json.dumps(body))
-    events = _parse_sse(response.text)
+    events = [e for e in _parse_sse(response.text) if e[0] != 'status']
     assert events == [('token', dict(content='Hello!')), ('done', dict(content='Hello!'))]
 
 

wrolpi/root_api.py

@@ -51,6 +51,9 @@ api_app.config.FALLBACK_ERROR_FORMAT = 'json'
 # Caddy is the single proxy in front of the API; trust its X-Forwarded-For so request.remote_addr
 # is the browser's address (used by the speed test).
 api_app.config.PROXIES_COUNT = 1
+# The AI chat streams for as long as CHAT_TIMEOUT_SECONDS (its own hard ceiling); Sanic's 60s
+# default killed the stream before a slow CPU produced its first token.
+api_app.config.RESPONSE_TIMEOUT = 660
 
 api_bp = Blueprint('RootAPI', url_prefix='/api')