fix(runtime): complete reconnect recovery paths

tests/unit_tests/box/test_box_connector.py

@@ -126,6 +126,29 @@ async def test_box_runtime_connector_cleans_partial_transport_on_connect_failure
     connector._close_managed_subprocess.assert_awaited_once()
 
 
+@pytest.mark.asyncio
+async def test_box_runtime_connector_starts_heartbeat_after_reconnect(
+    monkeypatch: pytest.MonkeyPatch,
+):
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    connector = BoxRuntimeConnector(make_app(Mock()))
+    connector._start_local_stdio = AsyncMock(side_effect=[RuntimeError('bind failed'), None])
+    connector._stop_transport = AsyncMock()
+    connector._close_managed_subprocess = AsyncMock()
+
+    with pytest.raises(RuntimeError, match='bind failed'):
+        await connector.initialize()
+
+    assert connector._heartbeat_task is None
+
+    await connector.reconnect()
+
+    assert connector._heartbeat_task is not None
+    assert not connector._heartbeat_task.done()
+    await connector.aclose()
+
+
 @pytest.mark.asyncio
 async def test_box_stdio_connection_does_not_capture_unconsumed_stderr(
     monkeypatch: pytest.MonkeyPatch,

tests/unit_tests/box/test_box_service.py

@@ -347,6 +347,28 @@ async def test_box_service_shutdown_reaps_connector_when_runtime_rpc_is_offline(
     connector.aclose.assert_awaited_once()
 
 
+@pytest.mark.asyncio
+async def test_box_service_reconnect_restores_workspace_and_runs_cleanup(
+    monkeypatch: pytest.MonkeyPatch,
+):
+    app = make_app(Mock())
+    app.skill_mgr = SimpleNamespace(reload_skills=AsyncMock())
+    service = BoxService(app, client=Mock(spec=BoxRuntimeClient))
+    connector = Mock()
+    connector.reconnect = AsyncMock()
+    service._ensure_default_workspace = Mock()
+    service._purge_attachment_dirs = AsyncMock()
+    monkeypatch.setattr('langbot.pkg.box.service.asyncio.sleep', AsyncMock())
+
+    await service._reconnect_loop(connector)
+
+    connector.reconnect.assert_awaited_once()
+    service._ensure_default_workspace.assert_called_once()
+    service._purge_attachment_dirs.assert_awaited_once()
+    app.skill_mgr.reload_skills.assert_awaited_once()
+    assert service.available is True
+
+
 @pytest.mark.asyncio
 async def test_box_runtime_reuses_request_session():
     logger = Mock()

tests/unit_tests/provider/test_mcp_box_integration.py

@@ -725,14 +725,10 @@ class TestGetRuntimeInfoDict:
         )
         assert writable._build_box_session_id() != default._build_box_session_id()
 
-    def test_stdio_session_refuses_when_box_unavailable(self, mcp_module):
-        """Policy: when Box is configured but unavailable (disabled in config
-        OR connection failed), stdio MCP servers are NOT treated as box-stdio.
-        ``_init_stdio_python_server`` will raise a clear refusal at start
-        time; until then, the runtime info simply omits box_session_id so the
-        UI can render the disabled state cleanly."""
+    def test_stdio_session_waits_for_enabled_box_when_temporarily_unavailable(self, mcp_module):
         ap = _make_ap()
         ap.box_service.available = False
+        ap.box_service.enabled = True
         s = _make_session(
             mcp_module,
             {
@@ -745,9 +741,58 @@ class TestGetRuntimeInfoDict:
             ap=ap,
         )
         info = s.get_runtime_info_dict()
+        assert info['box_session_id'] == 'mcp-shared'
+        assert info['box_enabled'] is True
+
+    def test_stdio_session_refuses_when_box_is_disabled(self, mcp_module):
+        ap = _make_ap()
+        ap.box_service.available = False
+        ap.box_service.enabled = False
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'stdio',
+                'command': 'python',
+                'args': [],
+            },
+            ap=ap,
+        )
+
+        info = s.get_runtime_info_dict()
+
         assert 'box_session_id' not in info
         assert 'box_enabled' not in info
 
+    @pytest.mark.asyncio
+    async def test_stdio_session_waits_until_box_reconnects(self, mcp_module, monkeypatch):
+        mcp_stdio_module = sys.modules['langbot.pkg.provider.tools.loaders.mcp_stdio']
+        ap = _make_ap()
+        ap.box_service.available = False
+        ap.box_service.enabled = True
+        session = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'stdio',
+                'command': 'python',
+                'args': [],
+                'box': {'startup_timeout_sec': 1},
+            },
+            ap=ap,
+        )
+
+        async def reconnect_box(_delay):
+            ap.box_service.available = True
+
+        monkeypatch.setattr(mcp_stdio_module.asyncio, 'sleep', reconnect_box)
+
+        await session._box_stdio_runtime._wait_for_box_runtime()
+
+        assert ap.box_service.available is True
+
     def test_stdio_session_without_box_service_uses_local_stdio(self, mcp_module):
         ap = _make_ap()
         del ap.box_service

tests/unit_tests/provider/test_mcp_resources.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import asyncio
 import base64
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, Mock
@@ -321,3 +322,42 @@ async def test_build_resource_context_for_query_uses_only_bound_attached_text_re
     assert query.variables[MCP_RESOURCE_CONTEXT_QUERY_KEY]['resource_count'] == 1
     docs.session.read_resource.assert_awaited_once()
     other.session.read_resource.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_mcp_loader_shutdown_cancels_startup_tasks_and_closes_sessions_concurrently():
+    loader = MCPLoader(_app())
+    hosted_cancelled = asyncio.Event()
+
+    async def pending_host():
+        try:
+            await asyncio.Event().wait()
+        finally:
+            hosted_cancelled.set()
+
+    hosted_task = asyncio.create_task(pending_host())
+    await asyncio.sleep(0)
+    loader._hosted_mcp_tasks = [hosted_task]
+
+    started: set[str] = set()
+    all_started = asyncio.Event()
+
+    class Session:
+        def __init__(self, name: str):
+            self.name = name
+
+        async def shutdown(self):
+            started.add(self.name)
+            if len(started) == 2:
+                all_started.set()
+            await all_started.wait()
+
+    loader.sessions = {'one': Session('one'), 'two': Session('two')}
+
+    await asyncio.wait_for(loader.shutdown(), timeout=1)
+
+    assert hosted_cancelled.is_set()
+    assert hosted_task.cancelled()
+    assert started == {'one', 'two'}
+    assert loader._hosted_mcp_tasks == []
+    assert loader.sessions == {}

tests/unit_tests/provider/test_skill_tools.py

@@ -458,6 +458,25 @@ class TestSkillToolLoader:
         assert await loader.has_tool('activate') is True
         assert await loader.has_tool('register_skill') is True
 
+    @pytest.mark.asyncio
+    async def test_tools_reappear_after_box_backend_recovers(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import SkillToolLoader
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(skills={'demo': _make_skill_data(name='demo')})
+        ap.box_service = SimpleNamespace(
+            available=False,
+            get_status=AsyncMock(return_value={'backend': {'available': True}}),
+        )
+
+        loader = SkillToolLoader(ap)
+        await loader.initialize()
+        assert await loader.get_tools() == []
+
+        ap.box_service.available = True
+
+        assert sorted(tool.name for tool in await loader.get_tools()) == ['activate', 'register_skill']
+
 
 class TestNativeToolLoaderSkillPaths:
     @pytest.mark.asyncio

tests/unit_tests/provider/test_tool_manager_native.py

@@ -151,6 +151,21 @@ async def test_native_tool_loader_exposes_all_tools_when_box_available():
         assert await loader.has_tool(tool_name) is True
 
 
+@pytest.mark.asyncio
+async def test_native_tool_loader_refreshes_after_box_recovers():
+    box_service = SimpleNamespace(
+        available=False,
+        get_status=AsyncMock(return_value={'backend': {'available': True}}),
+    )
+    loader = NativeToolLoader(SimpleNamespace(box_service=box_service, logger=Mock()))
+    await loader.initialize()
+    assert await loader.get_tools() == []
+
+    box_service.available = True
+
+    assert [tool.name for tool in await loader.get_tools()] == ['exec', 'read', 'write', 'edit', 'glob', 'grep']
+
+
 # ── read/write/edit file tool tests ─────────────────────────────