mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-11 03:40:03 +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
78 lines
3.2 KiB
Python
78 lines
3.2 KiB
Python
"""ReMe memory management application entry point."""
|
|
|
|
import asyncio
|
|
import sys
|
|
|
|
from .application import Application
|
|
from .components import R
|
|
from .components.service.cli_service import prepare_start_config, should_precheck_start
|
|
from .config import parse_args, resolve_app_config
|
|
from .enumeration import ComponentEnum
|
|
from .utils import cli_find_reme, load_env, precheck_start, running_service_config
|
|
|
|
_CLIENT_KWARGS = {"host", "port", "timeout", "transport", "command", "args", "show_metadata"}
|
|
|
|
|
|
class ReMe(Application):
|
|
"""ReMe memory management application."""
|
|
|
|
|
|
async def call_server(action: str, **kwargs):
|
|
"""Call the running server with a client matching its *actual* service config.
|
|
|
|
The client backend and its transport/host/port are taken from the running
|
|
``reme start`` process — its start args replayed through the same
|
|
``resolve_app_config`` the server used — so a bare ``reme <action>`` reaches
|
|
the server however it was actually started (``http`` REST or ``mcp``
|
|
streamable-http / sse / stdio), including ``service.*`` overrides that never
|
|
touched the on-disk config file. Falls back to local config resolution when
|
|
no server is detected. Explicit ``backend=`` / ``transport=`` / ``host=`` /
|
|
``port=`` kwargs still win and never leak into the tool payload.
|
|
"""
|
|
# config-selecting keys steer client construction; they are not tool args.
|
|
resolve_kwargs = {}
|
|
if isinstance(kwargs.get("config"), str):
|
|
resolve_kwargs["config"] = kwargs.pop("config")
|
|
if isinstance(kwargs.get("service"), dict):
|
|
resolve_kwargs["service"] = kwargs.pop("service")
|
|
|
|
# Prefer the running server's real config; fall back to the local config file.
|
|
service = running_service_config()
|
|
if service is None:
|
|
service = resolve_app_config(**resolve_kwargs).get("service")
|
|
service = service if isinstance(service, dict) else {}
|
|
|
|
backend: str = kwargs.pop("backend", None) or service.get("backend", "http")
|
|
# Seed client kwargs from the service config only when we are actually using
|
|
# that service's backend — transport/host/port are backend-specific, so an
|
|
# explicit backend override must not inherit the other backend's settings.
|
|
seed = service if backend == service.get("backend") else {}
|
|
client_kwargs = {k: seed[k] for k in _CLIENT_KWARGS if k in seed}
|
|
client_kwargs.update({key: kwargs.pop(key) for key in list(kwargs) if key in _CLIENT_KWARGS})
|
|
|
|
client_cls = R.get(ComponentEnum.CLIENT, backend)
|
|
if client_cls is None:
|
|
raise ValueError(f"Unknown client backend: {backend!r}")
|
|
async with client_cls(**client_kwargs) as client:
|
|
async for chunk in client(action=action, **kwargs):
|
|
print(chunk, end="", flush=True)
|
|
print()
|
|
|
|
|
|
def main():
|
|
"""Parse CLI arguments and launch the appropriate mode."""
|
|
action, kwargs = parse_args(*sys.argv[1:])
|
|
if action == "start":
|
|
load_env()
|
|
kwargs = prepare_start_config(kwargs)
|
|
if should_precheck_start(kwargs) and not precheck_start(kwargs.get("service")):
|
|
return
|
|
ReMe(**kwargs).run_app()
|
|
elif action == "find_reme":
|
|
cli_find_reme()
|
|
else:
|
|
asyncio.run(call_server(action, **kwargs))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|