mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-08-28 05:25:04 +00:00
Some checks are pending
Pre-commit / run (ubuntu-latest) (push) Waiting to run
Tests ReMe / Unit Tests - py3.11 (push) Waiting to run
Tests ReMe / Unit Tests - py3.12 (push) Waiting to run
Tests ReMe / Unit Tests - py3.13 (push) Waiting to run
Windows Smoke / CLI smoke - py3.11 (push) Waiting to run
* feat(config): add environment variable configuration for agent subprocesses - Add environment field to ApplicationConfig to store variables for agent subprocesses - Remove dynamic loading of .env files in agent wrappers - Introduce subprocess_environment property in base agent wrapper - Pass application-level environment variables to Claude Code and Codex agents - Load environment variables once at startup and pass to ReMe application - Remove dependency on load_env utility in agent wrapper implementations - Update tests to use configured environment instead of dynamic loading - Remove unused environment loading utilities and related test cases * refactor(mcp): remove channel notification system and related components - Removed channel notification step implementation - Removed claim channel step implementation - Removed ChannelSink class from MCP service - Removed channel-related documentation from AGENTS.md - Removed channel instruction text from MCP service - Removed all channel-related tests - Updated application context metadata comment to remove channel sink reference - Removed channel module initialization and imports * feat(service): add job whitelisting capability to BaseService - Add optional jobs parameter to BaseService.__init__ to configure job whitelist - Store jobs as set in self.jobs attribute for efficient lookup operations - Modify add_jobs method to filter jobs based on whitelist configuration - Update documentation in both English and Chinese to describe new feature - Add comprehensive unit tests for job whitelisting behavior - Implement flowchart update showing new filtering logic - Preserve existing enable_serve flag behavior alongside new whitelisting * refactor(service): enhance service job validation and MCP tool injection - Add strict validation for service jobs whitelist with detailed error messages - Implement injected job arguments support for MCP services with conflict detection - Add tool error handling for unsuccessful responses in MCP services - Remove duplicate job names in Codex agent wrapper using dict.fromkeys - Update MCP server argument format from single JSON array to repeated --job flags - Add comprehensive test coverage for job injection and error handling scenarios - Update documentation to reflect service job validation and MCP features - Ensure application cleanup occurs even when service lifespan encounters errors * feat(agent): update skill handling to preserve existing Claude skills - Change skills parameter processing to use 'all' instead of filtered list - Add logic to select project skills without restricting Claude's existing skills - Update variable naming from 'skills' to 'selected_skills' for clarity - Modify application context metadata documentation to clarify in-memory state usage - Add test case to verify configured skills are added without filtering existing skills - Update internal skill directory handling to use renamed variable consistently * refactor(agent): restructure agent wrapper components and session storage - Move CcFileSessionStore to separate module for better organization - Add SDK package version logging in base agent wrapper - Update Claude Code agent to use new session store structure with project keys - Refactor Claude Code agent wrapper to use proper type hints and SDK integration - Add support for server tool use events in Claude Code message processing - Improve error handling and resource cleanup in streaming operations - Update Codex agent wrapper with proper type annotations and configuration - Remove deprecated system prompt mode handling from Claude Code wrapper - Fix session path construction for Claude Code transcript storage - Update dependency injection and configuration handling patterns * fix(cc_agent_wrapper): resolve Claude Code SDK integration issues - Added dataclass import and created _BlockState for content block metadata tracking - Implemented proper MCP server name constant and tool context ID validation - Fixed tool_context_id injection to prevent duplicate assignment errors - Resolved skills parameter handling in build_options method - Enhanced job tools integration with MCP servers mapping validation - Replaced deprecated block_ids/block_types/tool_call_names with block_states dict - Updated message_delta to emit USAGE chunks instead of REPLY_END - Fixed stream result handling to ensure proper REPLY_END emission - Improved error handling for session mirror failures and rate limits - Added proper cleanup for expected trailing errors in streams - Refactored Codex agent wrapper initialization and configuration management - Removed obsolete system_prompt_mode from default config - Enhanced test coverage for new block state and error handling features - Fixed async generator handling with aclosing context manager - Improved chunk type mapping for Claude Code SDK events * refactor(tests): remove demo config tests from config parser test suite - Removed test_demo_config_registers_llm_jobs function and its assertions - Eliminated verification of LLM demo job configurations - Removed checks for agent wrapper component settings - Deleted assertions for model configurations and parameters - Cleaned up deprecated test cases related to demo config parsing * refactor(evolve): simplify Claude Code session store path structure - Removed redundant project key subdirectory from session link generation - Updated CcFileSessionStore initialization to use direct session directory path - Maintained existing session layout compatibility for backward compatibility - Added unit tests to verify session persistence behavior with existing transcripts - Ensured UUID-based session files remain accessible at expected locations - Preserved existing session directory structure without additional nesting * refactor(agent): defer optional Codex SDK imports until first use - Moved openai-codex imports inside functions to avoid mandatory dependencies - Added TYPE_CHECKING guard for development time type checking only - Implemented lazy loading mechanism with _get_async_codex_class function - Updated AsyncCodex initialization to occur on demand rather than at module level - Maintained backward compatibility while improving import performance - Added test case to verify package import works without optional Codex SDK - Updated agentscope dependency to version 2.0.4.post1 in pyproject.toml * test(embedded): add compatibility tests for in-process ReMe embedding - Add test suite for QwenPaw-style embedded configurations - Verify optional defaults remain preserved in embedded configs - Ensure in-process application API stays compatible - Test model injection and lifecycle management compatibility - Remove obsolete hermes agent plugin tests - Update CLI import test to cover multiple optional SDKs - Block claude_agent_sdk and openai_codex during import testing
192 lines
6.2 KiB
Python
192 lines
6.2 KiB
Python
"""Tests for service job registration behavior."""
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
from unittest.mock import Mock
|
|
|
|
import pytest
|
|
|
|
from reme.components.job import BaseJob, StreamJob
|
|
from reme.components.service import MCPService
|
|
from reme.schema import Response
|
|
|
|
|
|
def _dummy_app():
|
|
"""Minimal object needed by MCPService.build_service."""
|
|
|
|
async def start():
|
|
return None
|
|
|
|
async def close():
|
|
return None
|
|
|
|
return SimpleNamespace(
|
|
config=SimpleNamespace(app_name="test"),
|
|
context=SimpleNamespace(metadata={}),
|
|
start=start,
|
|
close=close,
|
|
)
|
|
|
|
|
|
def _app_with_jobs(**jobs):
|
|
"""Minimal object needed by BaseService.add_jobs."""
|
|
return SimpleNamespace(context=SimpleNamespace(jobs=jobs))
|
|
|
|
|
|
def test_service_registers_all_enabled_jobs_by_default():
|
|
"""Omitting service.jobs preserves registration of every service-enabled job."""
|
|
service = MCPService()
|
|
service.add_job = Mock(return_value=True)
|
|
enabled = BaseJob(name="enabled")
|
|
disabled = BaseJob(name="disabled", enable_serve=False)
|
|
|
|
service.add_jobs(_app_with_jobs(enabled=enabled, disabled=disabled))
|
|
|
|
service.add_job.assert_called_once_with(enabled)
|
|
|
|
|
|
def test_service_jobs_restricts_registration_to_configured_names():
|
|
"""service.jobs acts as a whitelist without overriding enable_serve."""
|
|
service = MCPService(jobs=["selected"])
|
|
service.add_job = Mock(return_value=True)
|
|
selected = BaseJob(name="selected")
|
|
unselected = BaseJob(name="unselected")
|
|
disabled = BaseJob(name="disabled", enable_serve=False)
|
|
|
|
service.add_jobs(
|
|
_app_with_jobs(selected=selected, unselected=unselected, disabled=disabled),
|
|
)
|
|
|
|
service.add_job.assert_called_once_with(selected)
|
|
|
|
|
|
def test_empty_service_jobs_disables_job_registration():
|
|
"""An explicit empty whitelist exposes no jobs."""
|
|
service = MCPService(jobs=[])
|
|
service.add_job = Mock(return_value=True)
|
|
|
|
service.add_jobs(_app_with_jobs(enabled=BaseJob(name="enabled")))
|
|
|
|
service.add_job.assert_not_called()
|
|
|
|
|
|
def test_explicit_service_jobs_reject_missing_disabled_and_unsupported_jobs():
|
|
"""An explicit service.jobs list fails instead of starting an incomplete service."""
|
|
missing_service = MCPService(jobs=["missing"])
|
|
with pytest.raises(KeyError, match="missing"):
|
|
missing_service.add_jobs(_app_with_jobs())
|
|
|
|
disabled_service = MCPService(jobs=["disabled"])
|
|
with pytest.raises(ValueError, match="disabled"):
|
|
disabled_service.add_jobs(_app_with_jobs(disabled=BaseJob(name="disabled", enable_serve=False)))
|
|
|
|
stream_service = MCPService(jobs=["stream"])
|
|
stream_service.add_job = Mock(return_value=False)
|
|
with pytest.raises(TypeError, match="stream"):
|
|
stream_service.add_jobs(_app_with_jobs(stream=StreamJob(name="stream")))
|
|
|
|
|
|
def test_mcp_service_registers_job_with_empty_parameters():
|
|
"""Empty job parameters must remain a dict for FastMCP FunctionTool validation."""
|
|
service = MCPService()
|
|
service.build_service(_dummy_app())
|
|
|
|
job = BaseJob(name="empty_params", parameters={})
|
|
|
|
assert service.add_job(job) is True
|
|
|
|
|
|
def test_mcp_service_reports_stream_job_skipped():
|
|
"""MCPService intentionally does not expose StreamJob tools."""
|
|
service = MCPService()
|
|
service.build_service(_dummy_app())
|
|
|
|
job = StreamJob(name="stream")
|
|
|
|
assert service.add_job(job) is False
|
|
|
|
|
|
class _RecordingJob:
|
|
"""Small callable matching the job contract used by MCPService.add_job."""
|
|
|
|
name = "record"
|
|
description = "Record arguments"
|
|
parameters = {"type": "object", "properties": {"query": {"type": "string"}}}
|
|
|
|
def __init__(self, response: Response | None = None):
|
|
self.response = response or Response(answer="ok")
|
|
self.calls = []
|
|
|
|
async def __call__(self, **kwargs):
|
|
self.calls.append(kwargs)
|
|
return self.response
|
|
|
|
|
|
def test_mcp_service_injects_job_kwargs_and_rejects_conflicts():
|
|
"""Configured job arguments are injected exactly once and remain server-owned."""
|
|
|
|
async def run():
|
|
service = MCPService(injected_job_kwargs={"tool_context_id": "ctx-1"})
|
|
service.build_service(_dummy_app())
|
|
job = _RecordingJob()
|
|
job.parameters = {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {"type": "string"},
|
|
"tool_context_id": {"type": "string"},
|
|
},
|
|
"required": ["query", "tool_context_id"],
|
|
}
|
|
assert service.add_job(job) is True
|
|
tool = await service.service.get_tool(job.name)
|
|
assert tool is not None
|
|
assert "tool_context_id" not in tool.parameters["properties"]
|
|
assert tool.parameters["required"] == ["query"]
|
|
|
|
result = await tool.run({"query": "alpha"})
|
|
assert job.calls == [{"query": "alpha", "tool_context_id": "ctx-1"}]
|
|
assert "ok" in str(result.content)
|
|
|
|
with pytest.raises(Exception, match="tool_context_id injected by the MCP server"):
|
|
await tool.run({"query": "alpha", "tool_context_id": "caller"})
|
|
|
|
asyncio.run(run())
|
|
|
|
|
|
def test_mcp_service_can_raise_tool_error_for_unsuccessful_response():
|
|
"""Configured MCP services translate failed Responses into tool errors."""
|
|
|
|
async def run():
|
|
service = MCPService(tool_error_on_failure=True)
|
|
service.build_service(_dummy_app())
|
|
job = _RecordingJob(Response(answer="failed", success=False))
|
|
assert service.add_job(job) is True
|
|
tool = await service.service.get_tool(job.name)
|
|
assert tool is not None
|
|
|
|
with pytest.raises(Exception, match="failed"):
|
|
await tool.run({})
|
|
|
|
asyncio.run(run())
|
|
|
|
|
|
def test_service_lifespan_closes_app_after_error():
|
|
"""Application resources close even when serving exits with an exception."""
|
|
|
|
async def run():
|
|
events = []
|
|
|
|
async def start():
|
|
events.append("start")
|
|
|
|
async def close():
|
|
events.append("close")
|
|
|
|
app = SimpleNamespace(start=start, close=close)
|
|
lifespan = MCPService()._lifespan(app, "127.0.0.1", 0) # pylint: disable=protected-access
|
|
with pytest.raises(RuntimeError, match="stop"):
|
|
async with lifespan(None):
|
|
raise RuntimeError("stop")
|
|
assert events == ["start", "close"]
|
|
|
|
asyncio.run(run())
|