mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-13 04:01:35 +00:00
* feat(service): add CLI service for local job execution - Introduce CliService to execute single jobs locally without serving ports - Add prepare_start_config and should_precheck_start functions for CLI job setup - Update reme start command to use CLI service when job argument is provided - Change default service backend from http to cli in jinli_lme config - Modify SearchStep to use constants and rename configuration parameters - Add unit tests for CLI service functionality and configuration handling - Update file extension support to include json format in addition to md and jsonl * feat(search): add BM25 and vector search steps with configuration updates - Add Bm25SearchStep and VectorSearchStep classes with tool context deduplication - Register new search step components in index module - Update configuration to use separate vector_search and bm25_search endpoints - Modify LLM models from qwen3.7-plus/glm-5.1 to glm-5.2 variants - Adjust search parameters and remove hybrid search implementation - Configure embedding store as default in storage settings - Remove auto-memory and file catalog configurations - Update watch directories from multiple paths to session_dir only * feat(agent): add tool result offloading and workspace management - Add tool_results_dir configuration option for offloaded tool results storage - Implement ToolResultOffloadMiddleware to persist large tool results to files - Create WorkspaceBackend to standardize file operations across tools - Add configurable builtin tools selection with sequential execution option - Integrate middleware support for agent wrapper with offloading capability - Update application initialization to create tool results directory - Add safety mechanisms for filesystem operations with sanitized filenames - Enhance agent wrapper with configurable working directory handling - Upgrade agentscope dependency to version 2.0.4 for improved features # Conflicts: # reme/application.py * feat(benchmark): add LongMemEval agentic search and result management - Introduce AgenticAnswerStep for agent-based history search - Add LmePrepareJudgeStep and LmeSaveResultStep for evaluation pipeline - Implement AddDraftStep and ReadAllDraftStep for evidence accumulation - Update configuration with new agent wrapper and search parameters - Add comparison script for analyzing agent run differences - Include documentation for LongMemEval failure analysis - Enhance tool result offloading with skip options - Modify search defaults and indexing behavior * feat(agent): implement tool result offloading with system reminders - Added tool_result_offload_message parameter to agent wrapper reply method - Implemented configurable reminder template for offloaded tool results - Created system reminder messages when tool results are offloaded to files - Added Chinese user message template for agentic answer step - Updated tool result offloading middleware to use custom reminder templates - Enhanced agentic answer instructions to handle long tool results via draft storage * feat(scripts): add LongMemEval results summarization tool - Create summarize_lme_results.py script to analyze result JSON files - Implement command line interface with answer id and dataset root options - Add support for specifying index range with start and end parameters - Include option to show failure details and non-successful completions - Calculate completion statistics and accuracy metrics - Display detailed breakdown of yes/no/other judgements - Handle missing and unreadable result files gracefully - Format output with percentages and comprehensive summary statistics * feat(summarize_lme_results): add question type breakdown to result summary - Import defaultdict from collections module - Add by_type dictionary to track statistics by question type - Count completed, yes, no, and other responses for each question type - Display detailed breakdown table showing accuracy by question type - Include question type column when processing judgements - Print comprehensive summary with question type distribution - Calculate and display accuracy percentage for each question type category * feat(lme): switch to qwen3.7-max model and add shuffle functionality - Changed default LLM model from glm-5.1 to qwen3.7-max in jinli_lme.yaml - Added random module import for shuffle functionality - Implemented --shuffle argument with BooleanOptionalAction for dataset shuffling - Added --seed argument to control random seed for reproducible shuffling - Applied random shuffle to dataset indices when shuffle is enabled - Added console output showing shuffle operation and seed information * fix(cli): set default random seed for shuffle functionality - Changed default seed value from None to 42 for consistent shuffling behavior - Ensures reproducible results when using shuffle option without explicit seed - Maintains backward compatibility while providing deterministic defaults * refactor(benchmark): update agentic answer guidelines for grounding - Updated English instruction to emphasize strict grounding in retrieved context - Modified Chinese instruction to stress evidence-based responses without inference - Removed redundant conciseness requirement in both language versions - Enhanced clarity on proper use of draft saving and retrieval mechanisms - Strengthened emphasis against hallucination of unsupported facts * refactor(benchmark): update agentic search instructions and configuration - Replace separate vector_search and bm25_search with unified search tool - Update agent instructions to use single search tool with multiple strategies - Simplify Chinese instructions for search methodology - Add comprehensive search tool configuration with hybrid vector/BM25 capabilities - Increase model retry attempts from 1 to 3 for better reliability - Remove redundant tool references from job_tools list * feat(search): add configurable search limit with environment variable support - Remove hardcoded limit and min_score parameters from config schema - Increase LLM context size from 200000 to 1000000 - Add REME_SEARCH_LIMIT environment variable support for search configuration - Implement command line argument --search-limit to override default search limit - Add input validation to ensure search limit is positive - Modify subprocess execution to pass environment variables - Update search step to use dynamic default limit from environment or fallback to 5 * refactor(benchmark): remove agentic answer step and related configurations - Removed AgenticAnswerStep class and its registration - Deleted agentic_answer.yaml prompt configuration file - Removed agentic answer related job definitions from jinli_lme.yaml - Cleaned up tool result offloading middleware implementation - Removed tool_results_dir configuration field from application config - Deleted comparison and analysis scripts for agent runs - Removed agentic answer step from LME init module exports - Updated agent wrapper to remove tool result offloading functionality - Removed unused imports and dependencies in agent wrapper module * refactor(benchmark): remove unused LME result processing components - Removed LmePrepareJudgeStep and LmeSaveResultStep classes from benchmark module - Cleaned up imports and exports in lme module initialization - Removed unused middleware configuration from agent wrapper - Deleted obsolete result.py file containing deprecated result processing logic - Simplified agent instantiation by removing middleware parameter - Updated import statements to reflect removed dependencies * refactor(index): remove unused search steps and update imports - Remove Bm25SearchStep and VectorSearchStep from index steps module - Remove unused prepare_start_config and should_precheck_start exports - Move import statements to proper location in reme.py - Update test module to use direct import path for CliService - Remove vector_search and bm25_search configurations from jinli_lme.yaml - Add workspace directory environment variable configuration - Add docstring to getcwd method in agent wrapper - Remove empty middleware list from agent wrapper initialization * feat(index): add BM25 and vector search steps with tool context deduplication - Add Bm25SearchStep for plain BM25 keyword search with tool_context deduplication - Add VectorSearchStep for plain vector search with tool_context deduplication - Implement tool context state management with TTL-based deduplication - Add support for chunk deduplication across tool contexts within TTL window - Update index steps module to include new search step classes - Add test coverage for CLI metadata output functionality - Refactor CLI service to remove unused show_status parameter - Update documentation comments to reflect internal service configuration * feat(steps): add Python code execution capability - Introduce PythonExecuteStep to run Python code in subprocess - Add configuration for python_execute step in jinli_lme.yaml - Register python_execute in available tools list - Implement timeout handling with default 60 second limit - Capture stdout/stderr output and return code metadata - Add comprehensive unit tests for execution scenarios - Support workspace directory context for code execution - Handle timeout errors and runtime exceptions gracefully * refactor(python_execute): replace subprocess with asyncio for Python code execution - Replace subprocess.run with asyncio.create_subprocess_exec for non-blocking execution - Add _PythonResult dataclass to encapsulate execution results and timeout status - Implement proper timeout handling with asyncio.wait_for and process.kill() - Update metadata to include returncode and stderr when timeout occurs - Convert synchronous _run_python method to asynchronous implementation - Maintain backward compatibility while improving execution reliability * refactor(python_execute): replace subprocess with asyncio for Python code execution - Replace subprocess.run with asyncio.create_subprocess_exec for non-blocking execution - Add _PythonResult dataclass to encapsulate execution results and timeout status - Implement proper timeout handling with asyncio.wait_for and process.kill() - Update metadata to include returncode and stderr when timeout occurs - Convert synchronous _run_python method to asynchronous implementation - Maintain backward compatibility while improving execution reliability
218 lines
6.6 KiB
Python
218 lines
6.6 KiB
Python
"""Tests for the ReMe CLI entry helpers."""
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from reme.components.service import cli_service
|
|
from reme.components.service.cli_service import CliService
|
|
from reme import reme as reme_module
|
|
|
|
|
|
def test_prepare_start_config_moves_unknown_start_args_to_job_args(monkeypatch):
|
|
"""``reme start job=...`` is translated into a one-shot cli service config."""
|
|
|
|
monkeypatch.setattr(
|
|
cli_service,
|
|
"resolve_app_config",
|
|
lambda **kwargs: {
|
|
**kwargs,
|
|
"service": {"backend": "http", "host": "127.0.0.1"},
|
|
},
|
|
)
|
|
|
|
cfg = cli_service.prepare_start_config(
|
|
{
|
|
"config": "jinli_lme",
|
|
"workspace_dir": "/tmp/reme",
|
|
"job": "search",
|
|
"query": "hello",
|
|
"limit": 3,
|
|
},
|
|
)
|
|
|
|
assert cfg["config"] == "jinli_lme"
|
|
assert cfg["workspace_dir"] == "/tmp/reme"
|
|
assert cfg["enable_logo"] is False
|
|
assert cfg["log_to_console"] is False
|
|
assert cfg["service"] == {
|
|
"backend": "cli",
|
|
"host": "127.0.0.1",
|
|
"job": "search",
|
|
"job_args": {"query": "hello", "limit": 3},
|
|
}
|
|
|
|
|
|
def test_should_precheck_start_skips_cli_service():
|
|
"""CLI service is local execution and should not run port prechecks."""
|
|
assert cli_service.should_precheck_start({"service": {"backend": "cli"}}) is False
|
|
assert cli_service.should_precheck_start({"service": {"backend": "http"}}) is True
|
|
|
|
|
|
def test_cli_service_runs_configured_job_and_closes_app(capsys):
|
|
"""CLI service runs one local job through app lifecycle and prints its answer."""
|
|
events = []
|
|
|
|
class FakeApp:
|
|
"""Minimal app stub for exercising CliService lifecycle."""
|
|
|
|
async def start(self):
|
|
"""Record app startup."""
|
|
events.append("start")
|
|
|
|
async def close(self):
|
|
"""Record app shutdown."""
|
|
events.append("close")
|
|
|
|
async def run_job(self, name, **kwargs):
|
|
"""Record job execution and return a successful response."""
|
|
events.append(("run_job", name, kwargs))
|
|
return SimpleNamespace(answer="found it", success=True, metadata={"hits": 1})
|
|
|
|
service = CliService(job="search", job_args={"query": "hello"})
|
|
|
|
service.start_service(FakeApp())
|
|
|
|
assert events == [
|
|
"start",
|
|
("run_job", "search", {"query": "hello"}),
|
|
"close",
|
|
]
|
|
assert capsys.readouterr().out == "found it\n"
|
|
|
|
|
|
def test_cli_service_can_print_metadata_from_service_config(capsys):
|
|
"""service.show_metadata controls optional CLI metadata output."""
|
|
|
|
class FakeApp:
|
|
"""Minimal app stub for exercising metadata output."""
|
|
|
|
async def start(self):
|
|
"""No-op app startup."""
|
|
|
|
async def close(self):
|
|
"""No-op app shutdown."""
|
|
|
|
async def run_job(self, _name, **_kwargs):
|
|
"""Return a successful response with metadata."""
|
|
return SimpleNamespace(answer="found it", success=True, metadata={"hits": 1})
|
|
|
|
service = CliService(job="search", show_metadata=True)
|
|
|
|
service.start_service(FakeApp())
|
|
|
|
assert capsys.readouterr().out == 'found it\n{"hits": 1}\n'
|
|
|
|
|
|
def test_cli_service_exits_nonzero_on_failed_response(capsys):
|
|
"""Failed local CLI jobs write to stderr and produce a failing process status."""
|
|
events = []
|
|
|
|
class FakeApp:
|
|
"""Minimal app stub for exercising failure handling."""
|
|
|
|
async def start(self):
|
|
"""Record app startup."""
|
|
events.append("start")
|
|
|
|
async def close(self):
|
|
"""Record app shutdown."""
|
|
events.append("close")
|
|
|
|
async def run_job(self, name, **kwargs):
|
|
"""Record job execution and return a failed response."""
|
|
events.append(("run_job", name, kwargs))
|
|
return SimpleNamespace(answer="boom", success=False, metadata={})
|
|
|
|
service = CliService(job="search", job_args={"query": "hello"})
|
|
|
|
with pytest.raises(SystemExit) as exc_info:
|
|
service.start_service(FakeApp())
|
|
|
|
assert exc_info.value.code == 1
|
|
assert events == [
|
|
"start",
|
|
("run_job", "search", {"query": "hello"}),
|
|
"close",
|
|
]
|
|
captured = capsys.readouterr()
|
|
assert captured.out == ""
|
|
assert captured.err == "boom\n"
|
|
|
|
|
|
def test_call_server_passes_client_kwargs_to_client(monkeypatch, capsys):
|
|
"""CLI helper forwards connection options to the selected client."""
|
|
seen = {}
|
|
|
|
class FakeClient:
|
|
"""Async client stub that records call arguments."""
|
|
|
|
def __init__(self, **kwargs):
|
|
seen["client_kwargs"] = kwargs
|
|
|
|
async def __aenter__(self):
|
|
return self
|
|
|
|
async def __aexit__(self, exc_type, exc_val, exc_tb):
|
|
return None
|
|
|
|
async def __call__(self, action: str, **kwargs):
|
|
seen["action"] = action
|
|
seen["payload"] = kwargs
|
|
yield "ok"
|
|
|
|
monkeypatch.setattr(reme_module.R, "get", lambda component_type, backend: FakeClient)
|
|
monkeypatch.setattr(reme_module, "running_service_config", lambda: None)
|
|
|
|
async def run():
|
|
await reme_module.call_server(
|
|
"search",
|
|
backend="http",
|
|
host="127.0.0.2",
|
|
port=2444,
|
|
timeout=1.5,
|
|
query="hello",
|
|
)
|
|
|
|
asyncio.run(run())
|
|
|
|
assert seen["client_kwargs"] == {"host": "127.0.0.2", "port": 2444, "timeout": 1.5}
|
|
assert seen["action"] == "search"
|
|
assert seen["payload"] == {"query": "hello"}
|
|
assert capsys.readouterr().out == "ok\n"
|
|
|
|
|
|
def test_call_server_treats_show_metadata_as_client_kwarg(monkeypatch, capsys):
|
|
"""show_metadata controls client display and is not sent as a tool argument."""
|
|
seen = {}
|
|
|
|
class FakeClient:
|
|
"""Async client stub that records call arguments."""
|
|
|
|
def __init__(self, **kwargs):
|
|
seen["client_kwargs"] = kwargs
|
|
|
|
async def __aenter__(self):
|
|
return self
|
|
|
|
async def __aexit__(self, exc_type, exc_val, exc_tb):
|
|
return None
|
|
|
|
async def __call__(self, action: str, **kwargs):
|
|
seen["action"] = action
|
|
seen["payload"] = kwargs
|
|
yield "ok"
|
|
|
|
monkeypatch.setattr(reme_module.R, "get", lambda component_type, backend: FakeClient)
|
|
monkeypatch.setattr(reme_module, "running_service_config", lambda: None)
|
|
|
|
async def run():
|
|
await reme_module.call_server("version", backend="http", show_metadata=True)
|
|
|
|
asyncio.run(run())
|
|
|
|
assert seen["client_kwargs"] == {"show_metadata": True}
|
|
assert seen["action"] == "version"
|
|
assert seen["payload"] == {}
|
|
assert capsys.readouterr().out == "ok\n"
|