mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-09-16 14:57:15 +00:00
fix(agent-debug): stream execution traces with platform mocks and coverage
This commit is contained in:
@@ -1445,3 +1445,30 @@ class TestQueryEntryAdapterHostCapabilities:
|
||||
assert user_item['attachment_refs'][0]['content'] is None
|
||||
assert 'aGVsbG8=' not in str(user_item)
|
||||
assert 'Pinned documentation' not in str(user_item)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_synthetic_event_query_exposes_trusted_workspace_to_tools(clean_agent_state):
|
||||
from langbot.pkg.provider.tools.loaders.skill import get_visible_skills
|
||||
from langbot.pkg.pipeline.pool import get_query_execution_context
|
||||
|
||||
plugin = FakePluginConnector(results=[{'type': 'run.completed', 'data': {'finish_reason': 'stop'}}])
|
||||
app = FakeApplication(plugin, clean_agent_state)
|
||||
orchestrator = AgentRunOrchestrator(app, FakeRegistry(make_descriptor()))
|
||||
query = make_query()
|
||||
plan = orchestrator.query_bridge.build_plan(query)
|
||||
context = get_query_execution_context(query)
|
||||
outputs = [
|
||||
item
|
||||
async for item in orchestrator.run(plan.event, plan.binding, adapter_context={'_execution_context': context})
|
||||
]
|
||||
assert outputs == []
|
||||
synthetic = plugin.sessions_during_run[0]['execution_query']
|
||||
assert synthetic.workspace_uuid == context.workspace_uuid
|
||||
assert synthetic.instance_uuid == context.instance_uuid
|
||||
assert synthetic.placement_generation == context.placement_generation
|
||||
assert synthetic.query_uuid == context.query_uuid
|
||||
received = []
|
||||
app.skill_mgr.get_skills = lambda scope: received.append(scope) or {}
|
||||
get_visible_skills(app, synthetic)
|
||||
assert received[0].workspace_uuid == context.workspace_uuid
|
||||
|
||||
@@ -10,16 +10,107 @@ from langbot_plugin.api.entities.builtin.agent_runner import (
|
||||
SubjectContext,
|
||||
)
|
||||
from langbot_plugin.api.entities.builtin.platform import message as platform_message
|
||||
from langbot_plugin.api.entities.builtin.platform import entities as platform_entities
|
||||
from langbot_plugin.api.entities.builtin.platform import events as platform_events
|
||||
|
||||
from langbot.pkg.agent.runner.host_models import AgentEventEnvelope
|
||||
from langbot.pkg.agent.runner.platform_tools import (
|
||||
PLATFORM_TOOL_DEFINITIONS,
|
||||
build_platform_tool_resources,
|
||||
execute_platform_tool,
|
||||
freeze_platform_context,
|
||||
resolve_agent_platform_tool_names,
|
||||
validate_debug_mock_options,
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize('definition', PLATFORM_TOOL_DEFINITIONS, ids=lambda tool: tool.name)
|
||||
@pytest.mark.parametrize('failure', [False, True])
|
||||
async def test_every_platform_tool_mock_preserves_validation_and_never_calls_bot(definition, failure):
|
||||
pattern = definition.event_patterns[0]
|
||||
event_type = 'group.member_joined' if pattern == '*' else pattern.replace('*', 'received')
|
||||
event = _event(event_type)
|
||||
event.delivery.surface = 'webui'
|
||||
event.delivery.platform_capabilities = {
|
||||
'debug_mock': True,
|
||||
'supported_apis': [definition.api],
|
||||
'mock_options': {'errors': {definition.name: 'E2E denied'}} if failure else {},
|
||||
}
|
||||
resources, capabilities = build_platform_tool_resources(event, [definition.name], ['call'])
|
||||
assert capabilities['unavailable_tools'] == []
|
||||
assert len(resources) == 1
|
||||
parameters = {}
|
||||
for name in definition.parameters.get('required', []):
|
||||
schema = definition.parameters['properties'][name]
|
||||
parameters[name] = schema.get(
|
||||
'enum', [False if schema['type'] == 'boolean' else 30 if schema['type'] == 'integer' else 'fixture-' + name]
|
||||
)[0]
|
||||
ap = SimpleNamespace(
|
||||
platform_mgr=SimpleNamespace(get_bot_by_uuid=AsyncMock(side_effect=AssertionError('real adapter accessed')))
|
||||
)
|
||||
session = {'authorization': {'resources': {'tools': resources}, 'platform_context': freeze_platform_context(event)}}
|
||||
result = await execute_platform_tool(ap, object(), session, definition.name, parameters)
|
||||
assert result['mock'] is True
|
||||
assert result['ok'] is not failure
|
||||
assert result['api'] == definition.api
|
||||
if failure:
|
||||
assert result['error'] == 'E2E denied'
|
||||
else:
|
||||
schemas = {
|
||||
'get_user_info': platform_entities.User,
|
||||
'get_group_info': platform_entities.UserGroup,
|
||||
'get_group_member_info': platform_entities.UserGroupMember,
|
||||
'get_message': platform_events.MessageReceivedEvent,
|
||||
'get_friend_list': platform_entities.User,
|
||||
'get_group_list': platform_entities.UserGroup,
|
||||
'get_group_member_list': platform_entities.UserGroupMember,
|
||||
}
|
||||
if definition.api in schemas:
|
||||
items = result['result'] if isinstance(result['result'], list) else [result['result']]
|
||||
for item in items:
|
||||
schemas[definition.api].model_validate(item)
|
||||
ap.platform_mgr.get_bot_by_uuid.assert_not_awaited()
|
||||
with pytest.raises(ValueError):
|
||||
await execute_platform_tool(ap, object(), session, definition.name, {**parameters, 'forged_target': 'other'})
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
'options',
|
||||
[
|
||||
None,
|
||||
[],
|
||||
{'unexpected': True},
|
||||
{'errors': []},
|
||||
{'errors': {'exec': 'oops'}},
|
||||
{'errors': {'event_reply': ''}},
|
||||
{'results': {'missing': {}}},
|
||||
{'errors': {'event_reply': 'oops'}, 'results': {'event_reply': {}}},
|
||||
{'unsupported_apis': 'send_message'},
|
||||
{'unsupported_apis': ['unknown']},
|
||||
],
|
||||
)
|
||||
def test_invalid_mock_options_are_rejected(options):
|
||||
with pytest.raises(ValueError):
|
||||
validate_debug_mock_options(options)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_mock_fixture_does_not_mutate_options():
|
||||
event = _event()
|
||||
fixture = {'name': 'Fixture User', 'nested': {'value': 42}}
|
||||
event.delivery.surface = 'webui'
|
||||
event.delivery.platform_capabilities = {
|
||||
'debug_mock': True,
|
||||
'mock_options': {'results': {'event_get_actor': fixture}},
|
||||
}
|
||||
session = {'authorization': {'platform_context': freeze_platform_context(event)}}
|
||||
result = await execute_platform_tool(SimpleNamespace(), object(), session, 'event_get_actor', {})
|
||||
assert result['result'] == fixture
|
||||
result['result']['nested']['value'] = 100
|
||||
assert fixture['nested']['value'] == 42
|
||||
|
||||
|
||||
def _event(event_type: str = 'friend.request_received') -> AgentEventEnvelope:
|
||||
return AgentEventEnvelope(
|
||||
event_id='event-1',
|
||||
@@ -88,6 +179,40 @@ def test_platform_resources_require_runner_call_permission() -> None:
|
||||
assert capabilities['unavailable_tools'] == [{'name': 'event_reply', 'reason': 'runner_call_permission_missing'}]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
('name', 'params', 'api'),
|
||||
[
|
||||
('event_reply', {'text': 'Hello'}, 'send_message'),
|
||||
('event_get_actor', {}, 'get_user_info'),
|
||||
('event_get_group', {}, 'get_group_info'),
|
||||
('event_respond_friend_request', {'approve': False}, 'approve_friend_request'),
|
||||
(
|
||||
'platform_send_message',
|
||||
{'target_type': 'group', 'target_id': 'explicit-group', 'text': 'Hi'},
|
||||
'send_message',
|
||||
),
|
||||
],
|
||||
)
|
||||
async def test_debug_mock_executes_without_accessing_a_real_adapter(name, params, api):
|
||||
event = _event()
|
||||
event.delivery.surface = 'webui'
|
||||
event.delivery.platform_capabilities['debug_mock'] = True
|
||||
ap = SimpleNamespace(platform_mgr=SimpleNamespace(get_bot_by_uuid=AsyncMock()))
|
||||
session = {'authorization': {'platform_context': freeze_platform_context(event)}}
|
||||
result = await execute_platform_tool(ap, object(), session, name, params)
|
||||
assert result['mock'] is True and result['ok'] is True
|
||||
assert result['delivery'] == 'simulated'
|
||||
assert result['api'] == api
|
||||
if name == 'event_reply':
|
||||
assert result['parameters'] == {'target_type': 'group', 'target_id': 'group-1', 'text': 'Hello'}
|
||||
if name == 'platform_send_message':
|
||||
assert result['parameters']['target_id'] == 'explicit-group'
|
||||
ap.platform_mgr.get_bot_by_uuid.assert_not_awaited()
|
||||
with pytest.raises(ValueError):
|
||||
await execute_platform_tool(ap, object(), session, name, {**params, 'unexpected': True})
|
||||
|
||||
|
||||
def test_agent_platform_tools_are_resolved_for_the_current_event() -> None:
|
||||
selected = resolve_agent_platform_tool_names(
|
||||
{
|
||||
|
||||
@@ -149,7 +149,8 @@ class TestAgentServiceMetadata:
|
||||
|
||||
|
||||
class TestAgentServiceDebug:
|
||||
async def test_debug_agent_runs_configured_runner_with_synthetic_event(self):
|
||||
@pytest.mark.parametrize('streaming', [False, True])
|
||||
async def test_debug_agent_runs_configured_runner_with_synthetic_event(self, streaming):
|
||||
app = _make_app()
|
||||
agent_config = _agent_row().config
|
||||
agent_config['allowed_platform_tools'] = ['platform_get_user_info']
|
||||
@@ -159,7 +160,16 @@ class TestAgentServiceDebug:
|
||||
}
|
||||
agent_config['allowed_tools'] = ['exec', 'weather']
|
||||
|
||||
visible_event = {
|
||||
'type': 'tool.call.started',
|
||||
'data': {'tool_name': 'exec', 'parameters': {'command': 'echo hi'}},
|
||||
}
|
||||
observer = AsyncMock() if streaming else None
|
||||
|
||||
async def run_agent(event, binding, adapter_context):
|
||||
assert binding.delivery_policy.enable_streaming is streaming
|
||||
await adapter_context['_result_observer']({**visible_event, 'private_context': 'must not leak'})
|
||||
await adapter_context['_result_observer']({'type': 'state.updated', 'data': {'private': True}})
|
||||
yield SimpleNamespace(
|
||||
role='assistant',
|
||||
content='debug result',
|
||||
@@ -193,8 +203,14 @@ class TestAgentServiceDebug:
|
||||
'data': {'member_id': 'user-1'},
|
||||
'conversation_id': 'debug-session',
|
||||
},
|
||||
on_result=observer,
|
||||
)
|
||||
|
||||
if streaming:
|
||||
observer.assert_awaited_once_with(visible_event)
|
||||
assert result['execution_events'] == []
|
||||
else:
|
||||
assert result['execution_events'] == [visible_event]
|
||||
assert result['event_type'] == 'group.member.joined'
|
||||
assert result['conversation_id'] == 'debug-session'
|
||||
assert result['final_text'] == 'debug result'
|
||||
@@ -207,6 +223,10 @@ class TestAgentServiceDebug:
|
||||
]
|
||||
event, binding = app.agent_run_orchestrator.run.call_args.args
|
||||
assert event.workspace_id == WORKSPACE_UUID
|
||||
assert event.delivery.platform_capabilities['debug_mock'] is True
|
||||
assert 'send_message' in event.delivery.platform_capabilities['supported_apis']
|
||||
assert event.delivery.reply_target['target_id'] == 'debug-group'
|
||||
assert binding.delivery_policy.enable_reply is False
|
||||
assert event.data == {'member_id': 'user-1'}
|
||||
assert binding.agent_id == 'agent-1'
|
||||
assert binding.runner_id == 'plugin:test/runner/default'
|
||||
@@ -245,6 +265,100 @@ class TestAgentServiceDebug:
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'event_type',
|
||||
[
|
||||
'message.received',
|
||||
'message.edited',
|
||||
'message.deleted',
|
||||
'message.reaction',
|
||||
'group.member_joined',
|
||||
'group.member_left',
|
||||
'group.member_banned',
|
||||
'friend.request_received',
|
||||
'friend.added',
|
||||
'feedback.received',
|
||||
'bot.invited_to_group',
|
||||
'bot.muted',
|
||||
'bot.unmuted',
|
||||
'bot.removed_from_group',
|
||||
'platform.specific',
|
||||
'custom.probe',
|
||||
],
|
||||
)
|
||||
async def test_debug_event_matrix_preserves_scope_targets_and_mock_options(event_type):
|
||||
app = _make_app()
|
||||
captured = []
|
||||
|
||||
async def run(event, binding, adapter_context):
|
||||
captured.append((event, binding))
|
||||
if False:
|
||||
yield
|
||||
|
||||
app.agent_run_orchestrator = SimpleNamespace(run=run)
|
||||
service = AgentService(app)
|
||||
service.get_agent = AsyncMock(
|
||||
return_value={'kind': AGENT_KIND_AGENT, 'supported_event_patterns': ['*'], 'config': _agent_row().config}
|
||||
)
|
||||
context = SimpleNamespace(
|
||||
instance_uuid='instance-test',
|
||||
workspace_uuid=WORKSPACE_UUID,
|
||||
placement_generation=1,
|
||||
principal=SimpleNamespace(account_uuid='account-test'),
|
||||
entitlement_revision=0,
|
||||
)
|
||||
data = {
|
||||
'group_id': '群组-42',
|
||||
'member_id': 'user-42',
|
||||
'member_name': '测试用户🙂',
|
||||
'request_id': 'request-42',
|
||||
'nested': {'value': [1, 2]},
|
||||
}
|
||||
await service.debug_agent(
|
||||
context,
|
||||
'agent-1',
|
||||
{
|
||||
'event_type': event_type,
|
||||
'text': 'probe',
|
||||
'data': data,
|
||||
'mock': {'errors': {'event_reply': 'denied'}, 'unsupported_apis': ['delete_message']},
|
||||
},
|
||||
)
|
||||
event, binding = captured[0]
|
||||
assert event.data == data
|
||||
assert event.actor.actor_name == '测试用户🙂'
|
||||
assert event.delivery.reply_target['target_id'] == '群组-42'
|
||||
assert 'delete_message' not in event.delivery.platform_capabilities['supported_apis']
|
||||
assert event.delivery.platform_capabilities['mock_options']['errors'] == {'event_reply': 'denied'}
|
||||
assert event.bot_id is None
|
||||
assert binding.delivery_policy.enable_reply is False
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'payload',
|
||||
[
|
||||
{'event_type': ''},
|
||||
{'data': []},
|
||||
{'data': None},
|
||||
{'data': False},
|
||||
{'mock': []},
|
||||
{'mock': {'errors': {'event_reply': None}}},
|
||||
{'actor': []},
|
||||
],
|
||||
)
|
||||
async def test_debug_rejects_invalid_envelope_before_execution(payload):
|
||||
app = _make_app()
|
||||
app.agent_run_orchestrator = SimpleNamespace(run=Mock(side_effect=AssertionError('invalid request executed')))
|
||||
service = AgentService(app)
|
||||
service.get_agent = AsyncMock(
|
||||
return_value={'kind': AGENT_KIND_AGENT, 'supported_event_patterns': ['*'], 'config': _agent_row().config}
|
||||
)
|
||||
with pytest.raises(ValueError):
|
||||
await service.debug_agent(SimpleNamespace(workspace_uuid=WORKSPACE_UUID), 'agent-1', payload)
|
||||
|
||||
|
||||
class TestAgentServiceListAndLookup:
|
||||
async def test_get_agents_merges_agents_and_pipelines_without_leaking_config(self):
|
||||
app = _make_app()
|
||||
|
||||
@@ -169,3 +169,44 @@ async def test_debug_agent_returns_actionable_runner_error():
|
||||
'code': 'dify.config_invalid',
|
||||
'msg': 'api-key is required',
|
||||
}
|
||||
|
||||
|
||||
async def test_debug_stream_preserves_events_before_error():
|
||||
import json
|
||||
|
||||
async def debug_agent(context, agent_uuid, payload, *, on_result):
|
||||
await on_result({'type': 'tool.call.started', 'data': {'tool_name': 'exec'}})
|
||||
raise RunnerExecutionError('test/runner', 'partial failure', error_code='runner.timeout')
|
||||
|
||||
client = await _create_test_client(SimpleNamespace(debug_agent=debug_agent))
|
||||
response = await client.post(
|
||||
'/api/v1/agents/agent-1/debug/stream',
|
||||
headers={'Authorization': 'Bearer test-token'},
|
||||
json={'event_type': 'message.received', 'text': 'hello'},
|
||||
)
|
||||
assert response.status_code == 200
|
||||
frames = [json.loads(line) for line in (await response.get_data()).splitlines() if line]
|
||||
assert frames[0]['kind'] == 'result'
|
||||
assert frames[1]['kind'] == 'error'
|
||||
assert frames[1]['code'] == 'runner.timeout'
|
||||
|
||||
|
||||
async def test_debug_stream_cancels_execution_when_closed():
|
||||
import asyncio
|
||||
from langbot.pkg.api.http.controller.groups.agent_debug_stream import debug_stream_response
|
||||
|
||||
cancelled = asyncio.Event()
|
||||
|
||||
async def debug_agent(context, agent_uuid, payload, *, on_result):
|
||||
try:
|
||||
await on_result({'type': 'message.delta', 'data': {}})
|
||||
await asyncio.Event().wait()
|
||||
finally:
|
||||
cancelled.set()
|
||||
|
||||
response = debug_stream_response(SimpleNamespace(debug_agent=debug_agent), None, 'agent-1', {})
|
||||
iterator = response.response.__aiter__()
|
||||
first = await anext(iterator)
|
||||
assert 'message.delta' in first
|
||||
await iterator.aclose()
|
||||
await asyncio.wait_for(cancelled.wait(), timeout=1)
|
||||
|
||||
@@ -540,6 +540,16 @@ class TestNativeToolLoaderSkillPaths:
|
||||
ap.skill_mgr = _make_skill_manager({'demo': _make_skill_data(name='demo', package_root=tmpdir)})
|
||||
loader = NativeToolLoader(ap)
|
||||
|
||||
if not loader._can_interpret_skill_host_paths():
|
||||
# Windows lacks the secure descriptor-relative host file operations.
|
||||
with pytest.raises(ValueError, match='owned by the Box Runtime'):
|
||||
await loader.invoke_tool(
|
||||
'read',
|
||||
{'path': '/workspace/.skills/demo/SKILL.md'},
|
||||
_make_query(query_id='q1', variables={PIPELINE_BOUND_SKILLS_KEY: ['demo']}),
|
||||
)
|
||||
return
|
||||
|
||||
result = await loader.invoke_tool(
|
||||
'read',
|
||||
{'path': '/workspace/.skills/demo/SKILL.md'},
|
||||
|
||||
@@ -246,6 +246,8 @@ async def test_native_tool_loader_rechecks_admission_at_the_final_invoke_boundar
|
||||
|
||||
|
||||
def _make_loader_with_workspace(tmpdir: str) -> tuple[NativeToolLoader, Mock]:
|
||||
if not native_loader._SECURE_HOST_FILE_OPS_AVAILABLE:
|
||||
pytest.skip('Host file operations require POSIX descriptor-relative APIs; remote Box is tested separately')
|
||||
logger = Mock()
|
||||
box_service = SimpleNamespace(
|
||||
available=True,
|
||||
@@ -508,6 +510,7 @@ async def test_path_escape_blocked():
|
||||
],
|
||||
)
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.skipif(not native_loader._SECURE_HOST_FILE_OPS_AVAILABLE, reason='Requires POSIX descriptor-relative host APIs')
|
||||
async def test_host_workspace_operations_do_not_follow_a_swapped_ancestor(
|
||||
monkeypatch,
|
||||
tool_name: str,
|
||||
@@ -794,3 +797,52 @@ async def test_grep_interrupts_catastrophic_regex(monkeypatch):
|
||||
)
|
||||
|
||||
assert result == {'ok': False, 'error': 'Regex search timed out'}
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize(
|
||||
'tool,parameters',
|
||||
[
|
||||
('read', {'path': '/workspace/probe.txt'}),
|
||||
('write', {'path': '/workspace/probe.txt', 'content': 'ok'}),
|
||||
('edit', {'path': '/workspace/probe.txt', 'old_string': 'ok', 'new_string': 'done'}),
|
||||
('glob', {'path': '/workspace', 'pattern': '*.txt'}),
|
||||
('grep', {'path': '/workspace', 'pattern': 'ok'}),
|
||||
],
|
||||
)
|
||||
@pytest.mark.parametrize('secure_host_apis', [False, True])
|
||||
async def test_standalone_box_files_do_not_require_core_host_workspace(monkeypatch, tool, parameters, secure_host_apis):
|
||||
monkeypatch.setattr(native_loader, '_SECURE_HOST_FILE_OPS_AVAILABLE', secure_host_apis)
|
||||
box = SimpleNamespace(
|
||||
available=True,
|
||||
default_workspace=None,
|
||||
shares_filesystem_with_box=False,
|
||||
execute_tool=AsyncMock(),
|
||||
_tenant_workspace=Mock(side_effect=AssertionError('must not resolve Core path')),
|
||||
)
|
||||
loader = NativeToolLoader(SimpleNamespace(box_service=box, logger=Mock()))
|
||||
remote = AsyncMock(return_value={'ok': True, 'sentinel': tool})
|
||||
monkeypatch.setattr(loader, f'_{tool}_workspace_via_box', remote)
|
||||
assert await loader.invoke_tool(tool, parameters, _make_query()) == {'ok': True, 'sentinel': tool}
|
||||
remote.assert_awaited_once()
|
||||
with pytest.raises(ValueError, match='workspace boundary'):
|
||||
await loader.invoke_tool(tool, {**parameters, 'path': '/workspace/../outside'}, _make_query())
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize('include', [None, '*.txt', 'quote"\n*.md'])
|
||||
async def test_box_grep_script_serializes_optional_include_as_python(monkeypatch, include):
|
||||
import ast
|
||||
|
||||
loader = NativeToolLoader(SimpleNamespace(logger=Mock()))
|
||||
captured = AsyncMock(return_value={'ok': True})
|
||||
monkeypatch.setattr(loader, '_run_workspace_file_script', captured)
|
||||
await loader._grep_workspace_via_box('/workspace', 'probe', include, _make_query())
|
||||
script = captured.call_args.args[0]
|
||||
tree = ast.parse(script)
|
||||
values = {}
|
||||
for statement in tree.body:
|
||||
if isinstance(statement, ast.Assign) and isinstance(statement.targets[0], ast.Name):
|
||||
values[statement.targets[0].id] = ast.literal_eval(statement.value)
|
||||
assert values['include'] == include
|
||||
assert values['path'] == '/workspace'
|
||||
|
||||
Reference in New Issue
Block a user