feat(router): Phase 1 - Actual Circuit Breaker for GPU hosts

- Added is_circuit_tripped(), trip_circuit(), half_open_probe() functions
- Filters out models with tripped circuits in route() function
- Trips circuit on 502/504 errors and timeouts in chat() function
- Prevents hung GPU cascades (Node #480 scenario)

Approved by Abiba via relay #635

Signed-off-by: Mumuni <mumuni@sysloggh.com>

router/router.py

@@ -242,7 +242,8 @@ def route(rd, tier, agent=""):
     turns = len([m for m in msgs if m.get("role") in ("user","assistant")])
     hints = rd.get("routing_hints",{})
     allowed = TIER_MODELS.get(tier, ["gemma-4-12b"])
-    avail = [m for m in available_models() if m in allowed]
+    # Phase 1: Filter out models with tripped circuit breakers
+    avail = [m for m in available_models() if m in allowed and not is_circuit_tripped(m)]
     if not avail: return {"model": allowed[0], "reason": "all_saturated", "saturated": True}
     if all(is_gpu_busy(m) for m in avail):
         return {"model": avail[0], "reason": "all_saturated", "saturated": True}
@@ -463,7 +464,10 @@ def chat():
         lat = int((time.time()-start)*1000)
         gpu_decr(model)
         
-        if resp.status_code != 200: return jsonify({"error":"GPU error "+str(resp.status_code)}), 502
+        if resp.status_code != 200:
+            if resp.status_code in (502, 504):
+                trip_circuit(model, 30)
+            return jsonify({"error":"GPU error "+str(resp.status_code)}), 502
         if is_stream:
             # Buffer SSE chunks, handle split lines for large responses
             chunks = []
@@ -537,7 +541,8 @@ def chat():
         return resp
     except requests.Timeout:
         gpu_decr(model)
-        log.error("TIMEOUT: %s -> %s", agent, model)
+        trip_circuit(model, 30)
+        log.error("TIMEOUT: %s -> %s (Circuit tripped)", agent, model)
         return jsonify({"error":"timeout"}), 504
     except Exception as e:
         gpu_decr(model)