Fix AI caller hanging on 'thinking...' indefinitely

- Add 30s timeout to all frontend fetch calls (safeFetch)
- Add 20s asyncio.timeout around lock+LLM in chat, ai-respond, auto-respond
- Reduce OpenRouter timeout from 60s to 25s
- Reduce Inworld TTS timeout from 60s to 25s
- Return graceful fallback responses on timeout instead of hanging

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

backend/services/llm.py

@@ -114,7 +114,7 @@ class LLMService:
         """Call OpenRouter API with retry"""
         for attempt in range(2):  # Try twice
             try:
-                async with httpx.AsyncClient(timeout=60.0) as client:
+                async with httpx.AsyncClient(timeout=25.0) as client:
                     response = await client.post(
                         "https://openrouter.ai/api/v1/chat/completions",
                         headers={

backend/services/tts.py

@@ -600,7 +600,7 @@ async def generate_speech_inworld(text: str, voice_id: str) -> tuple[np.ndarray,
         },
     }
 
-    async with httpx.AsyncClient(timeout=60.0) as client:
+    async with httpx.AsyncClient(timeout=25.0) as client:
         response = await client.post(url, json=payload, headers=headers)
         response.raise_for_status()
         data = response.json()