fix(gateway): persist watcher metadata in checkpoint for crash recovery (#1706)

Salvaged from PR #1573 by @eren-karakus0. Cherry-picked with authorship preserved.

Fixes #1143 — background process notifications resume after gateway restart.

Co-authored-by: Muhammet Eren Karakuş <erenkar950@gmail.com>

tests/gateway/test_background_process_notifications.py

@@ -50,13 +50,16 @@ def _build_runner(monkeypatch, tmp_path, mode: str) -> GatewayRunner:
     return runner
 
 
-def _watcher_dict(session_id="proc_test"):
-    return {
+def _watcher_dict(session_id="proc_test", thread_id=""):
+    d = {
         "session_id": session_id,
         "check_interval": 0,
         "platform": "telegram",
         "chat_id": "123",
     }
+    if thread_id:
+        d["thread_id"] = thread_id
+    return d
 
 
 # ---------------------------------------------------------------------------
@@ -196,3 +199,47 @@ async def test_run_process_watcher_respects_notification_mode(
     if expected_fragment is not None:
         sent_message = adapter.send.await_args.args[1]
         assert expected_fragment in sent_message
+
+
+@pytest.mark.asyncio
+async def test_thread_id_passed_to_send(monkeypatch, tmp_path):
+    """thread_id from watcher dict is forwarded as metadata to adapter.send()."""
+    import tools.process_registry as pr_module
+
+    sessions = [SimpleNamespace(output_buffer="done\n", exited=True, exit_code=0)]
+    monkeypatch.setattr(pr_module, "process_registry", _FakeRegistry(sessions))
+
+    async def _instant_sleep(*_a, **_kw):
+        pass
+    monkeypatch.setattr(asyncio, "sleep", _instant_sleep)
+
+    runner = _build_runner(monkeypatch, tmp_path, "all")
+    adapter = runner.adapters[Platform.TELEGRAM]
+
+    await runner._run_process_watcher(_watcher_dict(thread_id="42"))
+
+    assert adapter.send.await_count == 1
+    _, kwargs = adapter.send.call_args
+    assert kwargs["metadata"] == {"thread_id": "42"}
+
+
+@pytest.mark.asyncio
+async def test_no_thread_id_sends_no_metadata(monkeypatch, tmp_path):
+    """When thread_id is empty, metadata should be None (general topic)."""
+    import tools.process_registry as pr_module
+
+    sessions = [SimpleNamespace(output_buffer="done\n", exited=True, exit_code=0)]
+    monkeypatch.setattr(pr_module, "process_registry", _FakeRegistry(sessions))
+
+    async def _instant_sleep(*_a, **_kw):
+        pass
+    monkeypatch.setattr(asyncio, "sleep", _instant_sleep)
+
+    runner = _build_runner(monkeypatch, tmp_path, "all")
+    adapter = runner.adapters[Platform.TELEGRAM]
+
+    await runner._run_process_watcher(_watcher_dict())
+
+    assert adapter.send.await_count == 1
+    _, kwargs = adapter.send.call_args
+    assert kwargs["metadata"] is None

tests/tools/test_process_registry.py

@@ -294,6 +294,61 @@ class TestCheckpoint:
             recovered = registry.recover_from_checkpoint()
             assert recovered == 0
 
+    def test_write_checkpoint_includes_watcher_metadata(self, registry, tmp_path):
+        with patch("tools.process_registry.CHECKPOINT_PATH", tmp_path / "procs.json"):
+            s = _make_session()
+            s.watcher_platform = "telegram"
+            s.watcher_chat_id = "999"
+            s.watcher_thread_id = "42"
+            s.watcher_interval = 60
+            registry._running[s.id] = s
+            registry._write_checkpoint()
+
+            data = json.loads((tmp_path / "procs.json").read_text())
+            assert len(data) == 1
+            assert data[0]["watcher_platform"] == "telegram"
+            assert data[0]["watcher_chat_id"] == "999"
+            assert data[0]["watcher_thread_id"] == "42"
+            assert data[0]["watcher_interval"] == 60
+
+    def test_recover_enqueues_watchers(self, registry, tmp_path):
+        checkpoint = tmp_path / "procs.json"
+        checkpoint.write_text(json.dumps([{
+            "session_id": "proc_live",
+            "command": "sleep 999",
+            "pid": os.getpid(),  # current process — guaranteed alive
+            "task_id": "t1",
+            "session_key": "sk1",
+            "watcher_platform": "telegram",
+            "watcher_chat_id": "123",
+            "watcher_thread_id": "42",
+            "watcher_interval": 60,
+        }]))
+        with patch("tools.process_registry.CHECKPOINT_PATH", checkpoint):
+            recovered = registry.recover_from_checkpoint()
+            assert recovered == 1
+            assert len(registry.pending_watchers) == 1
+            w = registry.pending_watchers[0]
+            assert w["session_id"] == "proc_live"
+            assert w["platform"] == "telegram"
+            assert w["chat_id"] == "123"
+            assert w["thread_id"] == "42"
+            assert w["check_interval"] == 60
+
+    def test_recover_skips_watcher_when_no_interval(self, registry, tmp_path):
+        checkpoint = tmp_path / "procs.json"
+        checkpoint.write_text(json.dumps([{
+            "session_id": "proc_live",
+            "command": "sleep 999",
+            "pid": os.getpid(),
+            "task_id": "t1",
+            "watcher_interval": 0,
+        }]))
+        with patch("tools.process_registry.CHECKPOINT_PATH", checkpoint):
+            recovered = registry.recover_from_checkpoint()
+            assert recovered == 1
+            assert len(registry.pending_watchers) == 0
+
 
 # =========================================================================
 # Kill process