From 212352997e192769442feeee9427c4bea7391e91 Mon Sep 17 00:00:00 2001
From: Dev Agent <dev@openclaw.ai>
Date: Tue, 2 Jun 2026 20:12:29 +0300
Subject: [PATCH] fix(main): proper orphan recovery with per-run warning +
 notify (M-1)

---
 src/main.py | 37 +++++++++++++++++++++++++++++++------
 1 file changed, 31 insertions(+), 6 deletions(-)

diff --git a/src/main.py b/src/main.py
index 7d84883..f1952e8 100644
--- a/src/main.py
+++ b/src/main.py
@@ -15,17 +15,42 @@ logging.basicConfig(
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     init_db()
-    # Recover orphaned runs
+    # M-1: proper orphan-recovery.
+    # An orphan = an agent_run with no finished_at that is older than the recovery
+    # window. After a uvicorn restart the monitor thread is gone, so its child claude
+    # process (if any) was reparented to init; we cannot kill it by pid (pid is not
+    # persisted). Instead of silently writing exit=-1, we: enumerate each orphan,
+    # mark it exit=-1, log a warning per run, and notify so a human can check/restart.
+    log = logging.getLogger('orchestrator')
     from .db import get_db
     conn = get_db()
-    orphans = conn.execute(
-        "UPDATE agent_runs SET finished_at=datetime('now'), exit_code=-1 "
+    orphan_rows = conn.execute(
+        "SELECT id, task_id, agent FROM agent_runs "
         "WHERE finished_at IS NULL AND started_at < datetime('now', '-35 minutes')"
-    ).rowcount
+    ).fetchall()
+    for row in orphan_rows:
+        run_id, task_id, agent = row[0], row[1], row[2]
+        conn.execute(
+            "UPDATE agent_runs SET finished_at=datetime('now'), exit_code=-1 WHERE id=?",
+            (run_id,),
+        )
+        log.warning(
+            f"Orphan run {run_id} (task {task_id}, agent {agent}) recovered — "
+            f"manual check needed (process may have been killed on restart)"
+        )
     conn.commit()
     conn.close()
-    if orphans:
-        logging.getLogger('orchestrator').warning(f'Recovered {orphans} orphaned agent runs')
+    if orphan_rows:
+        try:
+            from .notifications import send_telegram
+            ids = ", ".join(str(r[0]) for r in orphan_rows)
+            send_telegram(
+                f"\u26a0\ufe0f Orchestrator restart: {len(orphan_rows)} orphaned agent run(s) "
+                f"(run_id: {ids}) marked exit=-1. Нужна ручная проверка/перезапуск."
+            )
+        except Exception:
+            pass
+        log.warning(f"Recovered {len(orphan_rows)} orphaned agent runs")
     yield