fix: circuit breaker deadlock — always query sidecar for status

The circuit breaker opened after MAX_RECOVERY_ATTEMPTS failures but
was never reset because the sidecar status query (which calls
circuit_reset()) was skipped when the circuit was open.  This caused
a permanent deadlock: all subsequent requests went to the LXC fallback
with no recovery possible.

Fix: always query the sidecar for /models/status, even when the
circuit is open.  If the sidecar responds successfully, reset the
circuit.  The circuit breaker now only prevents the SWITCH operation,
not the status health check.  If a model is already running when the
circuit is open, route to it directly.

main.py

@@ -403,12 +403,7 @@ async def proxy(
     error: Optional[str] = None
     sidecar_status = None
 
-    # Circuit breaker check
-    if not await circuit_breaker_check():
-        error = "circuit_open"
-    else:
-        # Query Sidecar for active model
-        sidecar_status = None
+    # Always query the sidecar first (to detect recovery even when circuit is open)
     async with httpx.AsyncClient(timeout=3.0) as client:
         try:
             resp = await client.get(f"{SIDECAR_URL}/models/status")
@@ -416,13 +411,19 @@ async def proxy(
                 sidecar_status = resp.json()
                 circuit_reset()
         except Exception:
-                error = "sidecar_down"
+            pass  # Handled below
 
     if sidecar_status is None:
         circuit_record_failure()
         error = "sidecar_down"
+    elif not await circuit_breaker_check():
+        # Sidecar is up but circuit is open from prior switch failures
+        # Only block the switch — allow routing to already-active backend
+        error = "circuit_open"
+        if sidecar_status.get("llama_server_running"):
+            target_url = f"{MAIN_PC_BASE}/{path}"
     else:
-            # Extract requested model from request body
+        # Both sidecar reachable and circuit closed — proceed normally
         body = await request.body()
         body_data = json.loads(body) if body else {}
         requested_model = body_data.get("model")