[loop-cycle-2] feat: hot-reload providers.yaml without restart (#458) (#470)

src/infrastructure/router/api.py

@@ -183,6 +183,22 @@ async def run_health_check(
     }
 
 
+@router.post("/reload")
+async def reload_config(
+    cascade: Annotated[CascadeRouter, Depends(get_cascade_router)],
+) -> dict[str, Any]:
+    """Hot-reload providers.yaml without restart.
+
+    Preserves circuit breaker state and metrics for existing providers.
+    """
+    try:
+        result = cascade.reload_config()
+        return {"status": "ok", **result}
+    except Exception as exc:
+        logger.error("Config reload failed: %s", exc)
+        raise HTTPException(status_code=500, detail=f"Reload failed: {exc}") from exc
+
+
 @router.get("/config")
 async def get_config(
     cascade: Annotated[CascadeRouter, Depends(get_cascade_router)],

src/infrastructure/router/cascade.py

@@ -815,6 +815,64 @@ class CascadeRouter:
         provider.status = ProviderStatus.HEALTHY
         logger.info("Circuit breaker CLOSED for %s", provider.name)
 
+    def reload_config(self) -> dict:
+        """Hot-reload providers.yaml, preserving runtime state.
+
+        Re-reads the config file, rebuilds the provider list, and
+        preserves circuit breaker state and metrics for providers
+        that still exist after reload.
+
+        Returns:
+            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]] = {}
+        for p in self.providers:
+            old_state[p.name] = (
+                p.metrics,
+                p.circuit_state,
+                p.circuit_opened_at,
+                p.half_open_calls,
+                p.status,
+            )
+
+        old_names = set(old_state.keys())
+
+        # Reload from disk
+        self.providers = []
+        self._load_config()
+
+        # Restore preserved state
+        new_names = {p.name for p in self.providers}
+        preserved = 0
+        for p in self.providers:
+            if p.name in old_state:
+                metrics, circuit, opened_at, half_open, status = old_state[p.name]
+                p.metrics = metrics
+                p.circuit_state = circuit
+                p.circuit_opened_at = opened_at
+                p.half_open_calls = half_open
+                p.status = status
+                preserved += 1
+
+        added = new_names - old_names
+        removed = old_names - new_names
+
+        logger.info(
+            "Config reloaded: %d providers (%d preserved, %d added, %d removed)",
+            len(self.providers),
+            preserved,
+            len(added),
+            len(removed),
+        )
+
+        return {
+            "total_providers": len(self.providers),
+            "preserved": preserved,
+            "added": sorted(added),
+            "removed": sorted(removed),
+        }
+
     def get_metrics(self) -> dict:
         """Get metrics for all providers."""
         return {