Merge branch 'main' into kimi/issue-490

Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>

config/providers.yaml

@@ -54,19 +54,6 @@ providers:
         context_window: 2048
         capabilities: [text, vision, streaming]
     
-  # Secondary: Local AirLLM (if installed)
-  - name: airllm-local
-    type: airllm
-    enabled: false  # Enable if pip install airllm
-    priority: 2
-    models:
-      - name: 70b
-        default: true
-        capabilities: [text, tools, json, streaming]
-      - name: 8b
-        capabilities: [text, tools, json, streaming]
-      - name: 405b
-        capabilities: [text, tools, json, streaming]
     
   # Tertiary: OpenAI (if API key available)
   - name: openai-backup

src/config.py

@@ -64,17 +64,10 @@ class Settings(BaseSettings):
     # Seconds to wait for user confirmation before auto-rejecting.
     discord_confirm_timeout: int = 120
 
-    # ── AirLLM / backend selection ───────────────────────────────────────────
+    # ── Backend selection ────────────────────────────────────────────────────
     # "ollama"  — always use Ollama (default, safe everywhere)
-    # "airllm"  — always use AirLLM (requires pip install ".[bigbrain]")
+    # "auto"    — pick best available local backend, fall back to Ollama
-    # "auto"    — use AirLLM on Apple Silicon if airllm is installed,
+    timmy_model_backend: Literal["ollama", "grok", "claude", "auto"] = "ollama"
-    #             fall back to Ollama otherwise
-    timmy_model_backend: Literal["ollama", "airllm", "grok", "claude", "auto"] = "ollama"
-
-    # AirLLM model size when backend is airllm or auto.
-    # Larger = smarter, but needs more RAM / disk.
-    # 8b  ~16 GB  |  70b  ~140 GB  |  405b  ~810 GB
-    airllm_model_size: Literal["8b", "70b", "405b"] = "70b"
 
     # ── Grok (xAI) — opt-in premium cloud backend ────────────────────────
     # Grok is a premium augmentation layer — local-first ethos preserved.
@@ -476,8 +469,19 @@ def validate_startup(*, force: bool = False) -> None:
                 ", ".join(_missing),
             )
             sys.exit(1)
+        if "*" in settings.cors_origins:
+            _startup_logger.error(
+                "PRODUCTION SECURITY ERROR: CORS wildcard '*' is not allowed "
+                "in production. Set CORS_ORIGINS to explicit origins."
+            )
+            sys.exit(1)
         _startup_logger.info("Production mode: security secrets validated ✓")
     else:
+        if "*" in settings.cors_origins:
+            _startup_logger.warning(
+                "SEC: CORS_ORIGINS contains wildcard '*' — "
+                "restrict to explicit origins before deploying to production."
+            )
         if not settings.l402_hmac_secret:
             _startup_logger.warning(
                 "SEC: L402_HMAC_SECRET is not set — "

src/dashboard/middleware/csrf.py

@@ -100,7 +100,7 @@ class CSRFMiddleware(BaseHTTPMiddleware):
             ...
 
     Usage:
-        app.add_middleware(CSRFMiddleware, secret="your-secret-key")
+        app.add_middleware(CSRFMiddleware, secret=settings.csrf_secret)
 
     Attributes:
         secret: Secret key for token signing (optional, for future use).

src/infrastructure/router/cascade.py

@@ -18,6 +18,8 @@ from enum import Enum
 from pathlib import Path
 from typing import Any
 
+from config import settings
+
 try:
     import yaml
 except ImportError:
@@ -100,7 +102,7 @@ class Provider:
     """LLM provider configuration and state."""
 
     name: str
-    type: str  # ollama, openai, anthropic, airllm
+    type: str  # ollama, openai, anthropic
     enabled: bool
     priority: int
     url: str | None = None
@@ -301,22 +303,13 @@ class CascadeRouter:
                 # Can't check without requests, assume available
                 return True
             try:
-                url = provider.url or "http://localhost:11434"
+                url = provider.url or settings.ollama_url
                 response = requests.get(f"{url}/api/tags", timeout=5)
                 return response.status_code == 200
             except Exception as exc:
                 logger.debug("Ollama provider check error: %s", exc)
                 return False
 
-        elif provider.type == "airllm":
-            # Check if airllm is installed
-            try:
-                import importlib.util
-
-                return importlib.util.find_spec("airllm") is not None
-            except (ImportError, ModuleNotFoundError):
-                return False
-
         elif provider.type in ("openai", "anthropic", "grok"):
             # Check if API key is set
             return provider.api_key is not None and provider.api_key != ""
@@ -826,7 +819,9 @@ class CascadeRouter:
             Summary dict with added/removed/preserved counts.
         """
         # Snapshot current runtime state keyed by provider name
-        old_state: dict[str, tuple[ProviderMetrics, CircuitState, float | None, int, ProviderStatus]] = {}
+        old_state: dict[
+            str, tuple[ProviderMetrics, CircuitState, float | None, int, ProviderStatus]
+        ] = {}
         for p in self.providers:
             old_state[p.name] = (
                 p.metrics,

src/timmy/agent.py

@@ -220,7 +220,7 @@ def create_timmy(
     print_response(message, stream).
     """
     resolved = _resolve_backend(backend)
-    size = model_size or settings.airllm_model_size
+    size = model_size or "70b"
 
     if resolved == "claude":
         from timmy.backends import ClaudeBackend

src/timmy_serve/app.py

@@ -75,6 +75,8 @@ def create_timmy_serve_app() -> FastAPI:
     @asynccontextmanager
     async def lifespan(app: FastAPI):
         logger.info("Timmy Serve starting")
+        app.state.timmy = create_timmy()
+        logger.info("Timmy agent cached in app state")
         yield
         logger.info("Timmy Serve shutting down")
 
@@ -101,7 +103,7 @@ def create_timmy_serve_app() -> FastAPI:
     async def serve_chat(request: Request, body: ChatRequest):
         """Process a chat request."""
         try:
-            timmy = create_timmy()
+            timmy = request.app.state.timmy
             result = timmy.run(body.message, stream=False)
             response_text = result.content if hasattr(result, "content") else str(result)
 

tests/infrastructure/test_router_cascade.py

@@ -2,7 +2,7 @@
 
 import time
 from pathlib import Path
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import AsyncMock, patch
 
 import pytest
 import yaml
@@ -489,34 +489,6 @@ class TestProviderAvailabilityCheck:
 
         assert router._check_provider_available(provider) is False
 
-    def test_check_airllm_installed(self):
-        """Test AirLLM when installed."""
-        router = CascadeRouter(config_path=Path("/nonexistent"))
-
-        provider = Provider(
-            name="airllm",
-            type="airllm",
-            enabled=True,
-            priority=1,
-        )
-
-        with patch("importlib.util.find_spec", return_value=MagicMock()):
-            assert router._check_provider_available(provider) is True
-
-    def test_check_airllm_not_installed(self):
-        """Test AirLLM when not installed."""
-        router = CascadeRouter(config_path=Path("/nonexistent"))
-
-        provider = Provider(
-            name="airllm",
-            type="airllm",
-            enabled=True,
-            priority=1,
-        )
-
-        with patch("importlib.util.find_spec", return_value=None):
-            assert router._check_provider_available(provider) is False
-
 
 class TestCascadeRouterReload:
     """Test hot-reload of providers.yaml."""

tests/test_lazy_init.py

@@ -49,6 +49,34 @@ class TestConfigLazyValidation:
             # Should not raise
             validate_startup(force=True)
 
+    def test_validate_startup_exits_on_cors_wildcard_in_production(self):
+        """validate_startup() should exit in production when CORS has wildcard."""
+        from config import settings, validate_startup
+
+        with (
+            patch.object(settings, "timmy_env", "production"),
+            patch.object(settings, "l402_hmac_secret", "test-secret-hex-value-32"),
+            patch.object(settings, "l402_macaroon_secret", "test-macaroon-hex-value-32"),
+            patch.object(settings, "cors_origins", ["*"]),
+            pytest.raises(SystemExit),
+        ):
+            validate_startup(force=True)
+
+    def test_validate_startup_warns_cors_wildcard_in_dev(self):
+        """validate_startup() should warn in dev when CORS has wildcard."""
+        from config import settings, validate_startup
+
+        with (
+            patch.object(settings, "timmy_env", "development"),
+            patch.object(settings, "cors_origins", ["*"]),
+            patch("config._startup_logger") as mock_logger,
+        ):
+            validate_startup(force=True)
+            mock_logger.warning.assert_any_call(
+                "SEC: CORS_ORIGINS contains wildcard '*' — "
+                "restrict to explicit origins before deploying to production."
+            )
+
     def test_validate_startup_skips_in_test_mode(self):
         """validate_startup() should be a no-op in test mode."""
         from config import validate_startup

tests/timmy/test_timmy_serve_app.py

@@ -8,11 +8,14 @@ from fastapi.testclient import TestClient
 
 @pytest.fixture
 def serve_client():
-    """Create a TestClient for the timmy-serve app."""
+    """Create a TestClient for the timmy-serve app with mocked Timmy agent."""
-    from timmy_serve.app import create_timmy_serve_app
+    with patch("timmy_serve.app.create_timmy") as mock_create:
+        mock_create.return_value = MagicMock()
+        from timmy_serve.app import create_timmy_serve_app
 
-    app = create_timmy_serve_app()
+        app = create_timmy_serve_app()
-    return TestClient(app)
+        with TestClient(app) as client:
+            yield client
 
 
 class TestHealthEndpoint:
@@ -34,18 +37,40 @@ class TestServeStatus:
 
 class TestServeChatEndpoint:
     @patch("timmy_serve.app.create_timmy")
-    def test_chat_returns_response(self, mock_create, serve_client):
+    def test_chat_returns_response(self, mock_create):
         mock_agent = MagicMock()
         mock_result = MagicMock()
         mock_result.content = "I am Timmy."
         mock_agent.run.return_value = mock_result
         mock_create.return_value = mock_agent
 
-        resp = serve_client.post(
+        from timmy_serve.app import create_timmy_serve_app
-            "/serve/chat",
+
-            json={"message": "Who are you?"},
+        app = create_timmy_serve_app()
-        )
+        with TestClient(app) as client:
+            resp = client.post(
+                "/serve/chat",
+                json={"message": "Who are you?"},
+            )
         assert resp.status_code == 200
         data = resp.json()
         assert data["response"] == "I am Timmy."
         mock_agent.run.assert_called_once_with("Who are you?", stream=False)
+
+    @patch("timmy_serve.app.create_timmy")
+    def test_agent_cached_at_startup(self, mock_create):
+        """Verify create_timmy is called once at startup, not per request."""
+        mock_agent = MagicMock()
+        mock_result = MagicMock()
+        mock_result.content = "reply"
+        mock_agent.run.return_value = mock_result
+        mock_create.return_value = mock_agent
+
+        from timmy_serve.app import create_timmy_serve_app
+
+        app = create_timmy_serve_app()
+        with TestClient(app) as client:
+            # Two requests — create_timmy should only be called once (at startup)
+            client.post("/serve/chat", json={"message": "hello"})
+            client.post("/serve/chat", json={"message": "world"})
+        mock_create.assert_called_once()