feat(box/mcp): instance-based orphan cleanup, error classification, session API, and integration tests

## Changes

  ### Precise orphan container cleanup
  - Runtime generates a unique instance_id on startup
  - Every container gets a `langbot.box.instance_id` label
  - `cleanup_orphaned_containers()` only removes containers from
    previous instances, preserving containers owned by the current one
  - Containers from older versions (no label) are also cleaned up
  - `cleanup_orphaned_containers` added to `BaseSandboxBackend` as
    a no-op default method, removing hasattr duck-typing

  ### Fine-grained MCP error classification
  - New `MCPSessionErrorPhase` enum with 7 phases: session_create,
    dep_install, process_start, relay_connect, mcp_init, runtime,
    tool_call
  - Each phase in `_init_box_stdio_server()` sets the error phase
    before re-raising, enabling precise failure diagnosis
  - `retry_count` tracked across retry attempts
  - `get_runtime_info_dict()` exposes `error_phase` and `retry_count`

  ### GET /v1/sessions/{id} API
  - `BoxRuntime.get_session()` returns session details including
    managed process info when present
  - `handle_get_session` HTTP handler + route in server.py
  - `BoxRuntimeClient.get_session()` abstract method + remote impl

  ### stdio defaults to Box when runtime is available
  - `_uses_box_stdio()` checks `box_service.available` instead of
    requiring explicit `box` key in server_config
  - `BoxService.initialize()` catches runtime errors gracefully,
    sets `available=False` instead of crashing LangBot startup
  - When no container runtime exists, stdio MCP falls back to
    host-direct execution

  ### Code quality (from /simplify review)
  - Extracted `_VENV_DIRS` / `_VENV_BIN_DIRS` module-level constants
  - Removed dead `_box_network_mode()` method and unused `bc` variable
  - Fixed broken import `from ....box.models` → `from ...box.models`
  - Cached `_resolve_host_path()` result — computed once, passed through
  - Config hash now includes `host_path` field
  - Batched orphan cleanup into single `rm -f` command

  ### Session leak fix
  - `_cleanup_box_stdio_session()` now runs in `_lifecycle_loop`'s
    finally block, covering all exit paths (normal shutdown, error,
    retry, final failure)

  ### Integration tests
  - 6 end-to-end tests covering managed process lifecycle, WebSocket
    stdio bidirectional IO, session cleanup verification, single
    session query, process exit detection, and orphan cleanup safety
This commit is contained in:
youhuanghe
2026-03-21 05:19:48 +00:00
committed by WangCham
parent e8aa7b2e6d
commit 791d052687
7 changed files with 442 additions and 29 deletions

View File

@@ -86,6 +86,9 @@ class BoxRuntimeClient(abc.ABC):
@abc.abstractmethod
async def get_managed_process(self, session_id: str) -> BoxManagedProcessInfo: ...
@abc.abstractmethod
async def get_session(self, session_id: str) -> dict: ...
class RemoteBoxRuntimeClient(BoxRuntimeClient):
"""HTTP client that talks to a standalone Box Runtime service."""
@@ -168,6 +171,15 @@ class RemoteBoxRuntimeClient(BoxRuntimeClient):
except aiohttp.ClientError as exc:
raise BoxRuntimeUnavailableError(f'box runtime unavailable: {exc}') from exc
async def get_session(self, session_id: str) -> dict:
session = self._get_session()
try:
async with session.get(f'{self._base_url}/v1/sessions/{session_id}') as resp:
await self._check_response(resp)
return await resp.json()
except aiohttp.ClientError as exc:
raise BoxRuntimeUnavailableError(f'box runtime unavailable: {exc}') from exc
async def get_backend_info(self) -> dict:
session = self._get_session()
try: