auto-sync: 2026-05-31 23:35:05

src/daemon/spawner.py

@@ -757,6 +757,11 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
             # 其他:A1(completed), A4(agent_failed), A7(auth_failed),
             #      A8(gateway_unreachable), A11(lock_conflict),
             #      A10(compact_failed), A12(agent_error)
+            # v2.8.1 Fix-3a: crash 类 outcome 设 cooldown，给 agent session 恢复时间
+            if outcome in ("crashed", "compact_failed", "process_crash", "session_stuck",
+                           "compact_hanging", "agent_error") and self.counter:
+                self.counter.set_cooldown(agent_id, seconds=300)  # 5 分钟
+                logger.info("Crash/error cooldown set for %s: 300s (outcome=%s)", agent_id, outcome)
             # 进程退出 → on_complete release counter
             # 任务状态由各 outcome 自行处理(或等 ticker)
             await self._do_on_complete_async(on_complete, agent_id, outcome)
@@ -1088,9 +1093,59 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
             logger.exception("Failed to revive %s", agent_id)
             return False
 
+    @staticmethod
+    def _check_recent_compaction_jsonl(session_file: str, window_seconds: int = 300) -> bool:
+        """v2.8.1 Fix-1: 读 session jsonl 末尾，检查是否有 window_seconds 内的 compaction 记录。
+
+        比 compactionCheckpoints 更可靠：Gateway 每次完成 compact 必然在 jsonl 末尾追加记录，
+        但不保证更新 compactionCheckpoints。
+        """
+        if not session_file or not pathlib.Path(session_file).exists():
+            return False
+        try:
+            from datetime import datetime, timezone
+            now = datetime.now(timezone.utc)
+            with open(session_file, "rb") as sf:
+                sf.seek(0, 2)
+                size = sf.tell()
+                sf.seek(max(0, size - 51200))
+                tail = sf.read().decode("utf-8", errors="replace")
+            for line in reversed(tail.splitlines()):
+                if not line.strip():
+                    continue
+                try:
+                    import json as _json
+                    obj = _json.loads(line)
+                except (_json.JSONDecodeError, ValueError):
+                    continue
+                if obj.get("type") == "compaction":
+                    ts = obj.get("timestamp", "")
+                    if ts:
+                        try:
+                            ct = datetime.fromisoformat(ts.replace("Z", "+00:00"))
+                            if (now - ct).total_seconds() < window_seconds:
+                                return True
+                        except (ValueError, TypeError):
+                            pass
+                ts = obj.get("timestamp", "")
+                if ts:
+                    try:
+                        ct = datetime.fromisoformat(ts.replace("Z", "+00:00"))
+                        if (now - ct).total_seconds() >= window_seconds:
+                            break
+                    except (ValueError, TypeError):
+                        pass
+            return False
+        except Exception:
+            return False
+
     @staticmethod
     def _check_session_state(agent_id: str) -> dict:
-        """检查 sessions.json 和 lock 状态"""
+        """检查 sessions.json 和 lock 状态
+
+        v2.8.1: compact 检测改用 session jsonl 末尾扫描（Fix-1），
+        替代失效的 compactionCheckpoints 检测。
+        """
         result = {"status": "unknown", "lock_pid": None, "lock_pid_alive": False, "recent_compact": False}
         sessions_path = Path.home() / ".openclaw" / "agents" / agent_id / "sessions" / "sessions.json"
         if not sessions_path.exists():
@@ -1125,13 +1180,10 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
                     except Exception:
                         pass
 
-            # 最近 5 分钟的 compact
-            import time
-            now_ms = time.time() * 1000
-            for cp in main_session.get("compactionCheckpoints", []):
-                if (now_ms - cp.get("createdAt", 0)) < 300_000:
-                    result["recent_compact"] = True
-                    break
+            # v2.8.1 Fix-1: compact 检测改用 session jsonl 末尾扫描
+            # 只在 agent 非空闲时才扫描（减少不必要 I/O）
+            if result["status"] not in ("done", "idle", "unknown", None) and sf:
+                result["recent_compact"] = AgentSpawner._check_recent_compaction_jsonl(sf)
         except Exception:
             pass
         return result