Commit Graph

12 Commits

Author SHA1 Message Date
Junyan Qin
257d9d3a65 fix(mcp): stabilize shared box managed processes 2026-05-19 00:45:35 +08:00
Junyan Qin
a565f3e022 fix(box): harden sandbox session isolation 2026-05-13 00:20:07 +08:00
Junyan Qin
e4c674a9f0 fix(box): restore sandbox config and shared mcp runtime 2026-05-12 23:25:43 +08:00
huanghuoguoguo
fd68c16056 feat(sandbox): add MCP box integration on top of sandbox base (#2083) 2026-05-04 21:23:23 +08:00
youhuanghe
0f00269a08 chore(sandbox): move MCP loader changes to follow-up branch 2026-05-04 21:23:23 +08:00
youhuanghe
93104a947a feat(box): unify native agent tools around exec/read/write/edit 2026-05-04 21:23:23 +08:00
youhuanghe
2911220054 fix(box): tighten sandbox exposure and restore box integration coverage 2026-05-04 21:23:23 +08:00
youhuanghe
9e0fa375e9 fix: ruff 2026-05-04 21:23:23 +08:00
youhuanghe
14057d1722 refactor: use rpc 2026-05-04 21:23:23 +08:00
youhuanghe
791d052687 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
2026-05-04 21:23:23 +08:00
youhuanghe
c802dc8029 fix: fix box intergration test 2026-05-04 21:23:23 +08:00
youhuanghe
55fc0caf2b feat: add test 2026-05-04 21:23:23 +08:00