fix: default remaining to high quota for unknown models on startup and update AGENTS.md

volc_limit_sync.py

@@ -1025,14 +1025,36 @@ def active_monitor_loop():
             beijing_time_ts = now + (8 * 3600)
             today_str = time.strftime("%Y-%m-%d", time.gmtime(beijing_time_ts))
 
-            # Idle Check
-            usage_key_global = f"daily_usage:{today_str}:global_total"
-            current_usage_global = int(redis_client.get(usage_key_global) or 0)
-            last_usage_global = sum(last_usage_map.values()) if last_usage_map else 0
-            delta = current_usage_global - last_usage_global
+            # Idle Check - Only exit idle if a "low quota" model has usage
+            LOW_QUOTA_THRESHOLD = 800000  # 判定为“低额度”的阈值
+            model_usages = {}
+            any_low_quota_usage = False
+            
+            for m in MONITORED_MODELS:
+                m_usage = 0
+                target_hashes = [p[1] for p in MONITORED_MODEL_PAIRS if p[0] == m]
+                for h in target_hashes:
+                    val = redis_client.get(f"daily_usage:{today_str}:{m}:{h}")
+                    if val: m_usage += float(val)
+                val_no_hash = redis_client.get(f"daily_usage:{today_str}:{m}")
+                if val_no_hash: m_usage += float(val_no_hash)
+                model_usages[m] = m_usage
+
+                # Calculate delta for this specific model
+                m_delta = m_usage - last_usage_map.get(m, 0.0)
+                
+                # Check if this model is considered "low quota"
+                rem_key = f"limit:dynamic:volcengine:remaining:{m}"
+                rem_val = redis_client.get(rem_key)
+                # 未知额度视为充足，避免首次启动时所有模型被误判为"低额度"
+                remaining = float(rem_val) if rem_val is not None else float(LOW_QUOTA_THRESHOLD)
+
+                if m_delta > 0 and remaining < LOW_QUOTA_THRESHOLD:
+                    any_low_quota_usage = True
+
             time_diff = now - last_sync_time
 
-            if delta <= 0:
+            if not any_low_quota_usage:
                 if idle_start_time == 0:
                     idle_start_time = now
             else:
@@ -1085,10 +1107,8 @@ def active_monitor_loop():
             burst_reason = ""
 
             for model in MONITORED_MODELS:
-                # 1. Get Current Usage
-                curr_usage_key = f"limit:dynamic:volcengine:usage:{model}"
-                curr_usage_val = redis_client.get(curr_usage_key)
-                curr_usage = float(curr_usage_val) if curr_usage_val else 0.0
+                # 1. Get Current Usage (calculated above)
+                curr_usage = model_usages.get(model, 0.0)
 
                 # 2. Get Last Synced Usage (Snapshot)
                 last_usage = last_usage_map.get(model, 0.0)
@@ -1325,15 +1345,8 @@ def active_monitor_loop():
                     global_min_remaining = temp_min_remaining
 
                 # Update snapshots for next iteration delta calculation
-                current_usage_global_snapshot = 0
-                for m in MONITORED_MODELS:
-                    uk = f"limit:dynamic:volcengine:usage:{m}"
-                    uv = redis_client.get(uk)
-                    u_val = float(uv) if uv else 0.0
+                for m, u_val in model_usages.items():
                     last_usage_map[m] = u_val
-                    current_usage_global_snapshot += u_val
-
-                last_usage_map["global"] = current_usage_global_snapshot
                 last_sync_time = now
 
                 if global_min_remaining > 800000: