feat(box): add box.enabled toggle and gate consumers on availability

Make the Box sandbox runtime optional. When ``box.enabled`` is false in
config (or when an enabled Box fails to connect), every dependent feature
degrades to the same disabled-state UX rather than crashing or silently
falling back to less safe code paths.

Backend:

- config.yaml: new top-level ``box.enabled: true`` flag (default true)
- BoxService:
  - Read box.enabled on construction
  - initialize() short-circuits when disabled — no remote WS connect, no
    stdio subprocess fork
  - _on_runtime_disconnect is a no-op when disabled (no reconnect loop
    on a deliberately-off service)
  - get_status() now exposes ``enabled`` so the frontend can tell
    "disabled in config" from "configured but failed"
- MCP stdio loader (mcp_stdio.uses_box_stdio): requires box_service to
  be available, not just installed
- MCP _init_stdio_python_server: when ap.box_service exists but is
  unavailable, refuse the stdio server with an actionable error instead
  of silently falling through to host-stdio (which bypasses the sandbox
  the operator asked for). Setups without ap.box_service installed at
  all keep the legacy host-stdio fallback for pre-Box dev mode
- SkillService._require_box_for_write: refuses create/update/install/
  write_skill_file when ap.box_service is installed but unavailable.
  Distinguishes disabled vs failed in the error message so the UI can
  surface the right hint. Legacy setups (no ap.box_service) keep the
  local fallback path — that distinction is what keeps the existing
  local-skills tests valid

Tests:
- Box disabled-state behavior (4 cases)
- Skill write refusal in disabled & failed states (7 cases)
- MCP stdio runtime info policy updated to match new refuse-when-down
  behavior

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Junyan Qin
2026-05-20 17:07:53 +08:00
parent 99328cf4c0
commit ec2d21fe63
8 changed files with 261 additions and 4 deletions

View File

@@ -152,8 +152,10 @@ def make_app(
profile: str = 'default',
host_root: str = '',
workspace_quota_mb: int | None = None,
enabled: bool = True,
):
box_config = {
'enabled': enabled,
'backend': 'local',
'runtime': {'endpoint': ''},
'local': {
@@ -1225,6 +1227,65 @@ class TestBoxHostMountModeNone:
)
class TestBoxDisabledByConfig:
"""``box.enabled = false`` must keep the BoxService usable as a status
surface but skip every connection attempt and report unavailable."""
@pytest.mark.asyncio
async def test_initialize_skips_connector_when_disabled(self):
logger = Mock()
app = make_app(logger, enabled=False)
client = Mock(spec=BoxRuntimeClient)
client.initialize = AsyncMock()
service = BoxService(app, client=client)
await service.initialize()
# The client must not be touched; we did not even open a connection.
client.initialize.assert_not_awaited()
assert service.enabled is False
assert service.available is False
# The reason is captured so the dashboard / UI can show it.
assert 'disabled' in service._connector_error.lower()
@pytest.mark.asyncio
async def test_get_status_reports_disabled(self):
logger = Mock()
service = BoxService(make_app(logger, enabled=False), client=Mock(spec=BoxRuntimeClient))
await service.initialize()
status = await service.get_status()
assert status['available'] is False
assert status['enabled'] is False
assert 'disabled' in status['connector_error'].lower()
@pytest.mark.asyncio
async def test_get_status_distinguishes_enabled_but_unavailable(self):
logger = Mock()
client = Mock(spec=BoxRuntimeClient)
client.initialize = AsyncMock(side_effect=RuntimeError('docker daemon not running'))
service = BoxService(make_app(logger, enabled=True), client=client)
await service.initialize()
status = await service.get_status()
assert status['available'] is False
assert status['enabled'] is True
assert 'docker daemon' in status['connector_error']
@pytest.mark.asyncio
async def test_disconnect_callback_is_no_op_when_disabled(self):
logger = Mock()
service = BoxService(make_app(logger, enabled=False), client=Mock(spec=BoxRuntimeClient))
# Should be safe to fire; must not flip reconnect state on a disabled
# service. If it tried to schedule a reconnect, the test would hang.
await service._on_runtime_disconnect(connector=Mock())
assert service._reconnecting is False
class TestBuildSkillExtraMounts:
"""Robustness of skill mount construction against a stale skill cache.

View File

@@ -561,7 +561,12 @@ class TestGetRuntimeInfoDict:
assert info['box_session_id'] == 'mcp-shared'
assert info['box_enabled'] is True
def test_stdio_session_waits_for_unavailable_box_runtime(self, mcp_module):
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."""
ap = _make_ap()
ap.box_service.available = False
s = _make_session(
@@ -576,8 +581,8 @@ class TestGetRuntimeInfoDict:
ap=ap,
)
info = s.get_runtime_info_dict()
assert info['box_session_id'] == 'mcp-shared'
assert info['box_enabled'] is True
assert 'box_session_id' not in info
assert 'box_enabled' not in info
def test_stdio_session_without_box_service_uses_local_stdio(self, mcp_module):
ap = _make_ap()

View File

@@ -72,6 +72,90 @@ def test_scan_directory_errors_when_skill_is_deeper_than_two_levels(skill_servic
skill_service.scan_directory(str(tmp_path))
class TestRequireBoxForWrite:
"""Writes must refuse when ``ap.box_service`` is installed but unavailable
(disabled in config OR connection failed). Legacy setups without
``ap.box_service`` continue to use the local fallback."""
def _ap_with_disabled_box(self):
return SimpleNamespace(
skill_mgr=SimpleNamespace(reload_skills=AsyncMock()),
box_service=SimpleNamespace(
available=False,
enabled=False,
_connector_error='Box runtime is disabled in config (box.enabled = false)',
),
)
def _ap_with_failed_box(self):
return SimpleNamespace(
skill_mgr=SimpleNamespace(reload_skills=AsyncMock()),
box_service=SimpleNamespace(
available=False,
enabled=True,
_connector_error='docker daemon not running',
),
)
@pytest.mark.asyncio
async def test_create_skill_refused_when_box_disabled(self):
service = SkillService(self._ap_with_disabled_box())
with pytest.raises(ValueError, match='disabled in config'):
await service.create_skill({'name': 'x'})
@pytest.mark.asyncio
async def test_create_skill_refused_when_box_failed(self):
service = SkillService(self._ap_with_failed_box())
with pytest.raises(ValueError, match='docker daemon not running'):
await service.create_skill({'name': 'x'})
@pytest.mark.asyncio
async def test_update_skill_refused_when_box_disabled(self):
service = SkillService(self._ap_with_disabled_box())
with pytest.raises(ValueError, match='Editing a skill requires the Box runtime'):
await service.update_skill('x', {})
@pytest.mark.asyncio
async def test_write_skill_file_refused_when_box_disabled(self):
service = SkillService(self._ap_with_disabled_box())
with pytest.raises(ValueError, match='Editing skill files requires the Box runtime'):
await service.write_skill_file('x', 'a.txt', 'hi')
@pytest.mark.asyncio
async def test_install_from_github_refused_when_box_disabled(self):
service = SkillService(self._ap_with_disabled_box())
with pytest.raises(ValueError, match='Installing a skill from GitHub'):
await service.install_from_github({'owner': 'o', 'repo': 'r', 'asset_url': 'https://example/x.zip'})
@pytest.mark.asyncio
async def test_install_from_zip_upload_refused_when_box_disabled(self):
service = SkillService(self._ap_with_disabled_box())
with pytest.raises(ValueError, match='Installing a skill from upload'):
await service.install_from_zip_upload(file_bytes=b'', filename='x.zip')
@pytest.mark.asyncio
async def test_legacy_setup_without_box_service_still_allows_local_create(self, tmp_path, monkeypatch):
"""Setups that never installed ap.box_service (pre-Box dev mode) keep
using the local-skills fallback path — that's the whole point of the
``getattr`` distinguisher in _require_box_for_write."""
monkeypatch.setenv('LANGBOT_DATA_ROOT', str(tmp_path / 'data'))
service = SkillService(SimpleNamespace(skill_mgr=SimpleNamespace(reload_skills=AsyncMock())))
service.get_skill_by_name = AsyncMock(return_value=None)
service.get_skill = AsyncMock(
return_value={
'name': 'local-skill',
'package_root': str(tmp_path / 'data' / 'skills' / 'local-skill'),
'description': '',
'instructions': '',
}
)
# Does not raise — gate is a no-op without ap.box_service.
await service.create_skill(
{'name': 'local-skill', 'display_name': 'Local', 'description': '', 'instructions': 'hi'}
)
@pytest.mark.asyncio
async def test_create_skill_import_preserves_existing_skill_content_when_form_fields_blank(tmp_path, monkeypatch):
source_dir = tmp_path / 'external-skills' / 'manual-skill'