deploy/README.md

@@ -26,7 +26,7 @@ python3 -m venv /home/bigt/AI/llm/venv
 cat > /home/bigt/AI/llm/.env << 'EOF'
 # Sidecar configuration
 MANIFEST_PATH=/home/bigt/AI/llm/manifest.yaml
-SIDECAR_PORT=8080
+SIDECAR_PORT=8081
 EOF
 
 # 5. Enable and start the service
@@ -57,7 +57,7 @@ curl http://10.0.4.100:9001/v1/models
 | Variable | Default | Description |
 |----------|---------|-------------|
 | `MANIFEST_PATH` | `/home/bigt/AI/llm/manifest.yaml` | Path to the YAML manifest file |
-| `SIDECAR_PORT` | `8080` | Port the sidecar listens on |
+| `SIDECAR_PORT` | `8081` | Port the sidecar listens on |
 
 ### Manifest Format
 

deploy/llm-sidecar.service

@@ -10,11 +10,11 @@ WorkingDirectory=/home/bigt/AI/llm
 # Environment
 EnvironmentFile=-/home/bigt/AI/llm/.env
 Environment=MANIFEST_PATH=/home/bigt/AI/llm/manifest.yaml
-Environment=SIDECAR_PORT=8080
+Environment=SIDECAR_PORT=8081
 Environment=PATH=/home/bigt/AI/llm/venv/bin:/usr/local/bin:/usr/bin:/bin
 
 # Use the sidecar's venv — install deps via deploy/README.md
-ExecStart=/home/bigt/AI/llm/venv/bin/uvicorn sidecar.app:app --host 0.0.0.0 --port 8080
+ExecStart=/home/bigt/AI/llm/venv/bin/uvicorn sidecar.app:app --host 0.0.0.0 --port 8081
 Restart=always
 RestartSec=3
 

main.py

@@ -13,7 +13,7 @@ from dotenv import load_dotenv
 load_dotenv()
 
 # ─── Configuration ───────────────────────────────────────────────────────────
-SIDECAR_URL = os.getenv("SIDECAR_URL", "http://10.0.4.11:8080")
+SIDECAR_URL = os.getenv("SIDECAR_URL", "http://10.0.4.11:8081")
 MAIN_PC_BASE = os.getenv("MAIN_PC_URL", "http://10.0.4.11:8080/v1").removesuffix("/v1")
 FALLBACK_SLM_URL = os.getenv("FALLBACK_SLM_URL", "http://10.0.4.200:8080/v1").removesuffix("/v1")
 OPENROUTER_API_KEY=os.getenv("OPENROUTER_API_KEY", "")

sidecar/app.py

@@ -17,7 +17,7 @@ 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"))
+SIDECAR_PORT = int(os.getenv("SIDECAR_PORT", "8081"))
 LLAMA_SERVER_PORT = 8080
 
 # Global state

tests/conftest.py

@@ -6,7 +6,7 @@ from unittest.mock import patch
 @pytest.fixture(autouse=True)
 def patch_router_urls():
     """Patch router URLs for all tests in this package."""
-    with patch("main.SIDECAR_URL", "http://localhost:8080"), \
+    with patch("main.SIDECAR_URL", "http://localhost:8081"), \
          patch("main.MAIN_PC_BASE", "http://localhost:8080"), \
          patch("main.FALLBACK_SLM_URL", "http://localhost:9999"), \
          patch("main.OPENROUTER_API_KEY", "test-key"), \

tests/test_router_circuit_breaker.py

@@ -58,7 +58,7 @@ class TestOpenRouterFallback:
         async def run_test():
             with respx.mock:
                 # Sidecar is down
-                respx.get("http://localhost:8080/models/status").mock(
+                respx.get("http://localhost:8081/models/status").mock(
                     side_effect=Exception("connection refused")
                 )
                 # OpenRouter works
@@ -84,7 +84,7 @@ class TestDeprecatedHeaderRemoved:
         """Router does not route based on x-intelligence-level: High."""
         async def run_test():
             with respx.mock:
-                respx.get("http://localhost:8080/models/status").mock(
+                respx.get("http://localhost:8081/models/status").mock(
                     return_value=Response(200, json={"active_profile": "qwen-3-8b", "llama_server_running": True})
                 )
                 # Should route to Main PC regardless of header

tests/test_router_fallback_lxc.py

@@ -19,7 +19,7 @@ class TestFallbackChain:
         async def run_test():
             with respx.mock:
                 # Sidecar is down — triggers fallback chain
-                respx.get("http://localhost:8080/models/status").mock(
+                respx.get("http://localhost:8081/models/status").mock(
                     return_value=Response(503, json={"status": "error", "message": "not ready"})
                 )
                 # OpenRouter fails with network error
@@ -50,7 +50,7 @@ class TestFallbackChain:
         async def run_test():
             with respx.mock:
                 # Sidecar down
-                respx.get("http://localhost:8080/models/status").mock(
+                respx.get("http://localhost:8081/models/status").mock(
                     side_effect=Exception("connection refused")
                 )
                 # OpenRouter down
@@ -76,7 +76,7 @@ class TestFallbackChain:
         async def run_test():
             with respx.mock:
                 # Sidecar down, OpenRouter down
-                respx.get("http://localhost:8080/models/status").mock(
+                respx.get("http://localhost:8081/models/status").mock(
                     side_effect=Exception("connection refused")
                 )
                 respx.post("https://openrouter.ai/v1/chat/completions").mock(

tests/test_router_model_detection.py

@@ -9,7 +9,7 @@ from httpx import Response, ASGITransport, AsyncClient
 
 from main import app as router_app
 
-SIDECAR_URL = "http://localhost:8080"
+SIDECAR_URL = "http://localhost:8081"
 MAIN_PC_URL = "http://localhost:8080"
 
 

tests/test_router_queue.py

@@ -6,7 +6,7 @@ from httpx import Response, ASGITransport, AsyncClient
 
 from main import app as router_app
 
-SIDECAR_URL = "http://localhost:8080"
+SIDECAR_URL = "http://localhost:8081"
 MAIN_PC_URL = "http://localhost:8080"
 FALLBACK_URL = "http://localhost:9999"
 

tests/test_router_sse_progress.py

@@ -10,7 +10,7 @@ from httpx import Response, ASGITransport, AsyncClient
 
 from main import app as router_app
 
-SIDECAR_URL = "http://localhost:8080"
+SIDECAR_URL = "http://localhost:8081"
 MAIN_PC_URL = "http://localhost:8080"
 FALLBACK_URL = "http://localhost:9999"
 

tests/test_router_v1_models.py

@@ -7,7 +7,7 @@ from httpx import Response, ASGITransport, AsyncClient
 
 from main import app as router_app
 
-SIDECAR_URL = "http://localhost:8080"
+SIDECAR_URL = "http://localhost:8081"
 
 
 def test_v1_models_returns_profiles_from_sidecar():