fix: resolve port conflict between sidecar and llama-server

Sidecar and llama-server were both configured on port 8080, causing
llama-server to fail on startup (port already in use).

- sidecar/app.py: LLAMA_SERVER_PORT → 8081 (sidecar stays on 8080)
- docker-compose.yml: MAIN_PC_URL → port 8081 (router sends chat
  requests to llama-server, not the sidecar)

docker-compose.yml

@@ -8,7 +8,7 @@ services:
       - "9001:9000"
     environment:
       - SIDECAR_URL=http://10.0.4.11:8080
-      - MAIN_PC_URL=http://10.0.4.11:8080/v1
+      - MAIN_PC_URL=http://10.0.4.11:8081/v1
       - FALLBACK_SLM_URL=http://10.0.4.200:8080/v1
       - OPENROUTER_API_KEY=${OPENROUTER_API_KEY:-}
     restart: unless-stopped

sidecar/app.py

@@ -18,7 +18,7 @@ from sidecar.manifest import load_manifest
 # Configuration from environment
 MANIFEST_PATH = os.getenv("MANIFEST_PATH", "/home/bigt/AI/llm/manifest.yaml")
 SIDECAR_PORT = int(os.getenv("SIDECAR_PORT", "8080"))
-LLAMA_SERVER_PORT = 8080
+LLAMA_SERVER_PORT = 8081
 
 # Global state
 _llama_server_process: Optional[asyncio.subprocess.Process] = None