mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-10-25 01:45:23 +08:00
Merge pull request #2665 from langbot-app/test/regression-boundary-cleanup-20261017
test: remove self-confirming tests and strengthen regression boundaries
This commit is contained in:
huanghuoguoguo
@@ -235,17 +235,6 @@ class TestInvokeLLMAuthorization:
|
||||
session = await registry.get('run_nonexistent')
|
||||
assert session is None
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_invoke_llm_no_run_id_unrestricted(self):
|
||||
"""INVOKE_LLM: no run_id should be unrestricted (backward compat)."""
|
||||
# When no run_id is provided, the authorization check is skipped
|
||||
# This is the unscoped path for regular plugin calls
|
||||
|
||||
# Simulate: if not run_id, skip authorization
|
||||
run_id = None
|
||||
# Authorization check should NOT be triggered
|
||||
assert run_id is None # No authorization check
|
||||
|
||||
|
||||
class TestInvokeLLMStreamAuthorization:
|
||||
"""Tests for INVOKE_LLM_STREAM authorization."""
|
||||
@@ -290,13 +279,6 @@ class TestInvokeLLMStreamAuthorization:
|
||||
|
||||
await registry.unregister('run_stream_unauthorized')
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_invoke_llm_stream_no_run_id_unrestricted(self):
|
||||
"""INVOKE_LLM_STREAM: no run_id should be unrestricted."""
|
||||
run_id = None
|
||||
# No authorization check
|
||||
assert run_id is None
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_tool_manager_get_tool_detail_returns_uniform_schema():
|
||||
@@ -376,13 +358,6 @@ class TestCallToolAuthorization:
|
||||
|
||||
await registry.unregister('run_tool_unauthorized')
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_tool_no_run_id_unrestricted(self):
|
||||
"""CALL_TOOL: no run_id should be unrestricted."""
|
||||
run_id = None
|
||||
# No authorization check
|
||||
assert run_id is None
|
||||
|
||||
|
||||
class TestRetrieveKnowledgeBaseAuthorization:
|
||||
"""Tests for RETRIEVE_KNOWLEDGE_BASE authorization."""
|
||||
@@ -495,49 +470,6 @@ class TestAuthorizationPathDifferentiation:
|
||||
|
||||
await registry.unregister(run_id)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_regular_plugin_path_no_run_id(self):
|
||||
"""Regular plugin calls have no run_id and skip session check."""
|
||||
# Regular plugin call has no run_id
|
||||
run_id = None
|
||||
|
||||
# Authorization check should be skipped when run_id is None.
|
||||
# This is handled in handler.py with: if run_id: ...
|
||||
assert run_id is None
|
||||
|
||||
# For regular plugins:
|
||||
# - INVOKE_LLM: unrestricted access to any model
|
||||
# - CALL_TOOL: unrestricted access to any tool
|
||||
# - RETRIEVE_KNOWLEDGE_BASE: checks pipeline config instead
|
||||
|
||||
|
||||
class TestHandlerAuthorizationErrorMessages:
|
||||
"""Tests for error message content in authorization failures."""
|
||||
|
||||
def test_model_not_authorized_error_message(self):
|
||||
"""Error message should mention model not authorized."""
|
||||
expected_msg = 'Model model_999 is not authorized for this agent run'
|
||||
assert 'not authorized' in expected_msg
|
||||
assert 'model_999' in expected_msg
|
||||
|
||||
def test_tool_not_authorized_error_message(self):
|
||||
"""Error message should mention tool not authorized."""
|
||||
expected_msg = 'Tool image_gen is not authorized for this agent run'
|
||||
assert 'not authorized' in expected_msg
|
||||
assert 'image_gen' in expected_msg
|
||||
|
||||
def test_kb_not_authorized_error_message(self):
|
||||
"""Error message should mention kb not authorized."""
|
||||
expected_msg = 'Knowledge base kb_999 is not authorized for this agent run'
|
||||
assert 'not authorized' in expected_msg
|
||||
assert 'kb_999' in expected_msg
|
||||
|
||||
def test_session_not_found_error_message(self):
|
||||
"""Error message should mention session not found."""
|
||||
expected_msg = 'Run session run_xyz not found or expired'
|
||||
assert 'not found' in expected_msg
|
||||
assert 'run_xyz' in expected_msg
|
||||
|
||||
|
||||
class TestRETRIEVEKNOWLEDGEBASEBugFix:
|
||||
"""Tests for the RETRIEVE_KNOWLEDGE_BASE bug fix in handler.py.
|
||||
@@ -696,16 +628,6 @@ class TestHandlerActionAuthorization:
|
||||
expected_error = f'Run session {run_id} not found or expired'
|
||||
assert 'not found' in expected_error
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_invoke_llm_handler_no_run_id_unrestricted(self):
|
||||
"""INVOKE_LLM handler: no run_id skips authorization (backward compat)."""
|
||||
# Simulate handler logic: if not run_id, skip authorization
|
||||
run_id = None
|
||||
|
||||
# In handler.py, authorization check is inside: if run_id: ...
|
||||
# So when run_id is None, authorization is skipped.
|
||||
assert run_id is None
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_tool_handler_authorized_path(self):
|
||||
"""CALL_TOOL handler: authorized when tool in resources."""
|
||||
@@ -764,14 +686,6 @@ class TestHandlerActionAuthorization:
|
||||
|
||||
await registry.unregister(run_id)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_tool_handler_no_run_id_unrestricted(self):
|
||||
"""CALL_TOOL handler: no run_id skips authorization."""
|
||||
run_id = None
|
||||
|
||||
# Authorization check is inside: if run_id: ...
|
||||
assert run_id is None
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_retrieve_knowledge_base_handler_authorized_path(self):
|
||||
"""RETRIEVE_KNOWLEDGE_BASE handler: authorized when kb in resources."""
|
||||
@@ -837,53 +751,6 @@ class TestSDKRunnerAPIProxyFieldConsistency:
|
||||
These tests verify that SDK sends field names that match what Host handler reads.
|
||||
"""
|
||||
|
||||
def test_call_tool_field_names_match(self):
|
||||
"""CALL_TOOL: SDK 'parameters' matches Host 'parameters'."""
|
||||
# SDK agent_run_api.py line 146: "parameters": parameters
|
||||
# Host handler.py line 457: parameters = data['parameters']
|
||||
sdk_field = 'parameters'
|
||||
host_field = 'parameters'
|
||||
assert sdk_field == host_field
|
||||
|
||||
def test_call_tool_run_id_field_present(self):
|
||||
"""CALL_TOOL: SDK includes 'run_id' field."""
|
||||
# SDK agent_run_api.py line 144: "run_id": self.run_id
|
||||
# Host handler.py line 458: run_id = data.get('run_id')
|
||||
sdk_fields = ['run_id', 'tool_name', 'parameters']
|
||||
host_expected_fields = ['tool_name', 'parameters', 'run_id']
|
||||
|
||||
for field in host_expected_fields:
|
||||
assert field in sdk_fields
|
||||
|
||||
def test_invoke_llm_field_names_match(self):
|
||||
"""INVOKE_LLM: SDK fields match Host handler."""
|
||||
# SDK agent_run_api.py lines 77-82
|
||||
sdk_fields = ['run_id', 'llm_model_uuid', 'messages', 'funcs', 'extra_args', 'timeout']
|
||||
# Host handler.py lines 333-337
|
||||
host_fields = ['llm_model_uuid', 'messages', 'funcs', 'extra_args', 'run_id']
|
||||
|
||||
for field in host_fields:
|
||||
assert field in sdk_fields
|
||||
|
||||
def test_invoke_llm_stream_field_names_match(self):
|
||||
"""INVOKE_LLM_STREAM: SDK fields match Host handler."""
|
||||
# SDK agent_run_api.py lines 111-116
|
||||
sdk_fields = ['run_id', 'llm_model_uuid', 'messages', 'funcs', 'extra_args']
|
||||
# Host handler.py lines 397-401
|
||||
host_fields = ['llm_model_uuid', 'messages', 'funcs', 'extra_args', 'run_id']
|
||||
|
||||
for field in host_fields:
|
||||
assert field in sdk_fields
|
||||
|
||||
def test_retrieve_knowledge_base_field_names_match(self):
|
||||
"""RETRIEVE_KNOWLEDGE_BASE: SDK fields match Host handler."""
|
||||
# SDK agent_run_api.py lines 178-183
|
||||
sdk_fields = ['run_id', 'kb_id', 'query_text', 'top_k', 'filters']
|
||||
|
||||
# Note: query_id is from query context, not SDK proxy
|
||||
for field in ['run_id', 'kb_id', 'query_text', 'top_k', 'filters']:
|
||||
assert field in sdk_fields
|
||||
|
||||
def test_retrieve_knowledge_base_action_enum_correct(self):
|
||||
"""RETRIEVE_KNOWLEDGE_BASE: SDK uses correct action enum."""
|
||||
from langbot_plugin.entities.io.actions.enums import PluginToRuntimeAction
|
||||
@@ -906,31 +773,6 @@ class TestNoRunIdBackwardCompatPath:
|
||||
have unrestricted access to certain APIs.
|
||||
"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_invoke_llm_no_run_id_unrestricted_access(self):
|
||||
"""INVOKE_LLM: no run_id means unrestricted model access."""
|
||||
# Handler.py line 340: if run_id: ...
|
||||
# When run_id is None, the authorization block is skipped
|
||||
run_id = None
|
||||
llm_model_uuid = 'any_model'
|
||||
|
||||
# Simulate handler logic: no run_id skips authorization.
|
||||
assert run_id is None
|
||||
|
||||
# Model can be any UUID (unrestricted)
|
||||
assert llm_model_uuid == 'any_model'
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_tool_no_run_id_unrestricted_access(self):
|
||||
"""CALL_TOOL: no run_id means unrestricted tool access."""
|
||||
run_id = None
|
||||
tool_name = 'any_tool'
|
||||
|
||||
# Handler.py line 463: if run_id: ...
|
||||
assert run_id is None
|
||||
|
||||
assert tool_name == 'any_tool'
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_retrieve_knowledge_base_no_run_id_pipeline_check(self):
|
||||
"""RETRIEVE_KNOWLEDGE_BASE: no run_id uses pipeline config check."""
|
||||
@@ -963,70 +805,6 @@ class TestNoRunIdBackwardCompatPath:
|
||||
class TestSessionExpiryAndCleanup:
|
||||
"""Tests for session expiry and cleanup scenarios."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_session_expiry_detection(self):
|
||||
"""Session expiry: old session should be considered expired."""
|
||||
import time
|
||||
|
||||
registry = AgentRunSessionRegistry()
|
||||
resources = make_resources(models=[{'model_id': 'model_001'}])
|
||||
|
||||
# Register session
|
||||
await registry.register(
|
||||
run_id='run_expiry_test',
|
||||
runner_id='plugin:test/runner/default',
|
||||
query_id=1,
|
||||
plugin_identity='test/runner',
|
||||
resources=resources,
|
||||
)
|
||||
|
||||
session = await registry.get('run_expiry_test')
|
||||
assert session is not None
|
||||
|
||||
# Check session status
|
||||
started_at = session['status']['started_at']
|
||||
last_activity = session['status']['last_activity_at']
|
||||
assert last_activity >= started_at
|
||||
|
||||
# Session should be valid initially
|
||||
current_time = int(time.time())
|
||||
assert current_time - started_at < 10 # Less than 10 seconds old
|
||||
|
||||
await registry.unregister('run_expiry_test')
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cleanup_stale_sessions(self):
|
||||
"""Cleanup: stale sessions should be removed."""
|
||||
registry = AgentRunSessionRegistry()
|
||||
resources = make_resources(models=[{'model_id': 'model_001'}])
|
||||
|
||||
# Register session
|
||||
await registry.register(
|
||||
run_id='run_cleanup_test',
|
||||
runner_id='plugin:test/runner/default',
|
||||
query_id=1,
|
||||
plugin_identity='test/runner',
|
||||
resources=resources,
|
||||
)
|
||||
|
||||
# Session exists
|
||||
session = await registry.get('run_cleanup_test')
|
||||
assert session is not None
|
||||
|
||||
# Cleanup with max_age=0 (immediate cleanup)
|
||||
# Note: This won't actually cleanup because session is just created
|
||||
# We need to manually test cleanup logic
|
||||
cleaned = await registry.cleanup_stale_sessions(max_age_seconds=0)
|
||||
assert isinstance(cleaned, int)
|
||||
|
||||
# Session should still exist (it was just created)
|
||||
# With max_age=0, sessions with last_activity > 0 seconds ago would be cleaned
|
||||
# But since it's just created, last_activity_at is current time
|
||||
session_after = await registry.get('run_cleanup_test')
|
||||
assert session_after is not None
|
||||
|
||||
await registry.unregister('run_cleanup_test')
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_unregister_removes_session(self):
|
||||
"""Unregister: session should be removed from registry."""
|
||||
@@ -2002,32 +1780,3 @@ class TestCallerPluginIdentityValidation:
|
||||
assert 'no plugin_identity' in error.message
|
||||
|
||||
await registry.unregister('run_missing_pull_identity')
|
||||
|
||||
|
||||
class TestBackwardCompatStorageNoRunId:
|
||||
"""Tests for unscoped storage actions without run_id.
|
||||
|
||||
Regular plugins (non-Runner) don't have run_id and should
|
||||
have unrestricted access to storage APIs.
|
||||
"""
|
||||
|
||||
def test_storage_no_run_id_skips_validation(self):
|
||||
"""Storage actions without run_id skip Host-side validation."""
|
||||
# Handler.py: if run_id: ...validation...
|
||||
# When run_id is None, validation is skipped
|
||||
run_id = None
|
||||
|
||||
# Simulate handler logic: no run_id skips validation.
|
||||
assert run_id is None
|
||||
|
||||
# Storage access unrestricted for regular plugins
|
||||
assert run_id is None
|
||||
|
||||
def test_file_no_run_id_skips_validation(self):
|
||||
"""GET_CONFIG_FILE without run_id skips Host-side validation."""
|
||||
run_id = None
|
||||
|
||||
assert run_id is None
|
||||
|
||||
# File access unrestricted for regular plugins
|
||||
assert run_id is None
|
||||
|
||||
Reference in New Issue
Block a user