feat(ui): explicit chat state machine — typing indicator, streaming progress, timeout and error recovery

tests/e2e/mock_llm.py

@@ -18,7 +18,10 @@ from __future__ import annotations
 
 import hashlib
 import math
+import os
 import re
+import signal
+import threading
 import time
 import uuid
 from typing import Any
@@ -79,6 +82,20 @@ def compose_answer(body: dict[str, Any]) -> str:
     )
 
 
+@app.post("/__shutdown__")
+def shutdown() -> dict[str, Any]:
+    """Test hook (loading-feedback story): terminate this mock process to
+    simulate an LLM outage. The E2E fixture restores a fresh instance on
+    the same port afterwards, so the rest of the session keeps working."""
+
+    def _die() -> None:
+        time.sleep(0.1)  # let the HTTP response flush before we exit
+        os.kill(os.getpid(), signal.SIGTERM)
+
+    threading.Thread(target=_die, daemon=True).start()
+    return {"status": "shutting down"}
+
+
 @app.get("/v1/models")
 def models() -> dict[str, Any]:
     return {