2 commits

Author	SHA1	Message	Date
Ziyang Guo	4032049117	fix(python-execute): rename the timeout parameter to survive CLI client kwargs ... benchmark.yaml's python_execute job advertised a `timeout` parameter, but `timeout` is one of the CLI's client-selection kwargs (reme/reme.py pops it before the payload is sent), so `reme python_execute code=... timeout=300` never delivered the timeout to the job. The value silently became the HTTP client's request timeout while the subprocess kept the 60s default, so benchmark code that needs longer was killed at 60s with no hint why. HTTP and MCP callers were unaffected. Rename the parameter to `python_timeout`, mirroring how the shell job already avoids the same collision with `shell_timeout`. The step prefers the new name and still accepts the legacy `timeout` context key so existing benchmark configs keep working. A new guard test fails if any job in reme/config/*.yaml or a plugin plugin.yaml declares a client-reserved parameter name again.	2026-10-01 02:15:16 +08:00
jinliyl	2612d25959	feat(lme): add cli execution and agentic search tooling (#334) ... * 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	2026-07-08 17:43:09 +09:00