runtime error

Exit code: 3. Reason: Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:httpx:HTTP Request: GET http://127.0.0.1:8093/health "HTTP/1.1 503 Service Unavailable" INFO:model_service:Stopping llama-server background process... INFO:model_service:Terminating process PID 10... INFO:model_service:llama-server stopped. ERROR: Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 638, in lifespan async with self.lifespan_context(app) as maybe_state: File "/usr/local/lib/python3.10/contextlib.py", line 199, in __aenter__ return await anext(self.gen) File "/workspace/app/main.py", line 65, in lifespan raise e File "/workspace/app/main.py", line 60, in lifespan await model_service.wait_until_ready(timeout_seconds=45) File "/workspace/app/services/model_service.py", line 131, in wait_until_ready raise TimeoutError("llama-server failed to load model within the timeout limit.") TimeoutError: llama-server failed to load model within the timeout limit. ERROR: Application startup failed. Exiting. ======================================================= Starting IDE Code Completion Engine... Model: zai-org_GLM-4.5-Air-IQ1_M.gguf FastAPI Host: http://127.0.0.1:7860 Swagger UI Docs: http://127.0.0.1:7860/docs llama-server Backend Port: 8093 ======================================================= [AGENT] Warning: Agent init failed: cannot import name 'get_execution_graph' from 'app.enhanced.execution_graph' (/workspace/app/enhanced/execution_graph.py) Error starting model backend: llama-server failed to load model within the timeout limit.

Container logs: