Merge remote-tracking branch 'origin/master' into dev/4.11.x

# Conflicts:
#	pyproject.toml
#	uv.lock
#	web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx

tests/unit_tests/provider/test_mcp_box_integration.py

@@ -639,10 +639,13 @@ class TestGetRuntimeInfoDict:
         assert info['box_session_id'] == 'mcp-shared'
         assert info['box_enabled'] is True
 
-    def test_transient_test_session_is_isolated_from_shared(self, mcp_module):
-        """A transient test session (config-page "test", no persisted UUID)
-        must NOT share the live "mcp-shared" Box session. Regression: a failing
-        test churned the shared session and tore down healthy live servers."""
+    def test_transient_test_shares_session_but_isolated_by_process(self, mcp_module):
+        """A transient config-page "test" now shares the same 'mcp-shared' Box
+        session as live servers (so a test reuses the running container / live
+        process instead of a cold per-test session bootstrap). Isolation is at
+        the PROCESS level: the test runs under its own process_id and only ever
+        stops that process_id, so it cannot disturb another server's live
+        process or the shared session itself."""
         ap = _make_ap()
         ap.box_service.available = True
         transient = _make_session(
@@ -670,10 +673,12 @@ class TestGetRuntimeInfoDict:
         )
         assert transient.is_transient is True
         assert live.is_transient is False
-        # Isolated session id for the test, shared for the live server.
-        assert transient._build_box_session_id() == 'mcp-test-gen-uuid-123'
+        # Both share ONE Box session ...
+        assert transient._build_box_session_id() == 'mcp-shared'
         assert live._build_box_session_id() == 'mcp-shared'
-        assert transient._build_box_session_id() != live._build_box_session_id()
+        assert transient._build_box_session_id() == live._build_box_session_id()
+        # ... but are isolated by distinct process_ids within that session.
+        assert transient._box_stdio_runtime.process_id != live._box_stdio_runtime.process_id
 
     def test_stdio_session_refuses_when_box_unavailable(self, mcp_module):
         """Policy: when Box is configured but unavailable (disabled in config
@@ -824,3 +829,129 @@ async def test_init_box_stdio_server_stages_host_path_in_shared_workspace(mcp_mo
     assert process_payload['command'] == 'python'
     assert process_payload['args'] == ['/workspace/.mcp/u1/workspace/server.py']
     assert process_payload['cwd'] == '/workspace/.mcp/u1/workspace'
+
+
+@pytest.mark.asyncio
+async def test_stdio_handshake_raises_coldstart_retry_while_process_alive(mcp_module, tmp_path, monkeypatch):
+    """During a slow (npx) cold start the handshake fails while the managed
+    process is still alive. initialize() must raise _ColdStartRetry (so the
+    outer lifecycle loop reuses the live process and retries without stopping it
+    or consuming the fatal budget), NOT a fatal error."""
+    from contextlib import asynccontextmanager
+
+    mcp_stdio_module = sys.modules['langbot.pkg.provider.tools.loaders.mcp_stdio']
+
+    class ColdClientSession:
+        def __init__(self, *_args):
+            pass
+
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb):
+            return False
+
+        async def initialize(self):
+            # Process still cold-starting: handshake fails.
+            raise Exception('Connection closed')
+
+    @asynccontextmanager
+    async def fake_websocket_client(_url: str):
+        yield ('read-stream', 'write-stream')
+
+    monkeypatch.setattr(mcp_stdio_module, 'ClientSession', ColdClientSession)
+    monkeypatch.setattr(mcp_stdio_module, 'websocket_client', fake_websocket_client)
+    monkeypatch.setattr(mcp_stdio_module, '_HANDSHAKE_ATTEMPT_TIMEOUT_SEC', 1.0, raising=False)
+
+    ap = _make_ap()
+    ap.box_service.available = True
+    ap.box_service.create_session = AsyncMock(return_value={})
+    ap.box_service.start_managed_process = AsyncMock(return_value={})
+    ap.box_service.get_managed_process_websocket_url = Mock(return_value='ws://box/p')
+
+    session = _make_session(
+        mcp_module,
+        {
+            'name': 'slow',
+            'uuid': 'slow-uuid',
+            'mode': 'stdio',
+            'command': 'npx',
+            'args': ['-y', 'some-mcp'],
+        },
+        ap=ap,
+    )
+
+    # Process is NOT exited (still cold-starting) and not yet running for reuse.
+    async def _not_exited():
+        return False
+
+    session._box_stdio_runtime._managed_process_has_exited = _not_exited
+
+    async def _not_running():
+        return False
+
+    session._box_stdio_runtime._managed_process_is_running = _not_running
+
+    with pytest.raises(mcp_stdio_module._ColdStartRetry):
+        await session._init_box_stdio_server()
+
+    # Process was started exactly once (the retry will reuse it, not rebuild).
+    assert ap.box_service.start_managed_process.await_count == 1
+    await session.exit_stack.aclose()
+
+
+@pytest.mark.asyncio
+async def test_stdio_handshake_raises_fatal_when_process_exited(mcp_module, tmp_path, monkeypatch):
+    """If the handshake fails AND the process has definitively exited, that is a
+    real failure — initialize() must NOT swallow it as a cold-start retry."""
+    from contextlib import asynccontextmanager
+
+    mcp_stdio_module = sys.modules['langbot.pkg.provider.tools.loaders.mcp_stdio']
+
+    class DeadClientSession:
+        def __init__(self, *_args):
+            pass
+
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb):
+            return False
+
+        async def initialize(self):
+            raise Exception('Connection closed')
+
+    @asynccontextmanager
+    async def fake_websocket_client(_url: str):
+        yield ('read-stream', 'write-stream')
+
+    monkeypatch.setattr(mcp_stdio_module, 'ClientSession', DeadClientSession)
+    monkeypatch.setattr(mcp_stdio_module, 'websocket_client', fake_websocket_client)
+    monkeypatch.setattr(mcp_stdio_module, '_HANDSHAKE_ATTEMPT_TIMEOUT_SEC', 1.0, raising=False)
+
+    ap = _make_ap()
+    ap.box_service.available = True
+    ap.box_service.create_session = AsyncMock(return_value={})
+    ap.box_service.start_managed_process = AsyncMock(return_value={})
+    ap.box_service.get_managed_process_websocket_url = Mock(return_value='ws://box/p')
+
+    session = _make_session(
+        mcp_module,
+        {'name': 'dead', 'uuid': 'dead-uuid', 'mode': 'stdio', 'command': 'npx', 'args': ['-y', 'x']},
+        ap=ap,
+    )
+
+    async def _exited():
+        return True
+
+    session._box_stdio_runtime._managed_process_has_exited = _exited
+
+    async def _not_running():
+        return False
+
+    session._box_stdio_runtime._managed_process_is_running = _not_running
+
+    with pytest.raises(Exception) as ei:
+        await session._init_box_stdio_server()
+    assert not isinstance(ei.value, mcp_stdio_module._ColdStartRetry)
+    await session.exit_stack.aclose()