Draft
Conversation
- Added update_llm_config_for_completions_logging to imports
- Modified get_config to accept instance parameter
- Updated llm_config to enable completions logging
- Updated process_instance to pass instance to get_config
This change makes aider_bench save llm_completions in the same way as swe_bench,
with completions being saved in {eval_output_dir}/llm_completions/{instance_id}/
…tions-fork feat: Enable llm_completions logging in aider_bench
Added a new benchmark based on Aider's polyglot benchmark that supports: - Multiple programming languages (Python, JS, Rust, Go, C++, Java) - End-to-end evaluation of code editing capabilities - Automated test execution and validation - Parallel evaluation with multiple workers - Detailed metrics and logging Key components: - run_infer.py: Main benchmark implementation - Dockerfile: Multi-language development environment - Scripts for running benchmarks and building Docker image - Helper modules for prompts and utilities
Modified run_infer.sh to support both argument styles: - Old style: <model> <commit> <agent> <max_iters> <num_workers> - New style: --llm-config <config> --agent-cls <agent> [other options] Updated README to document both usage styles with examples. This maintains backward compatibility with existing scripts.
- Changed imports to use relative paths - Added __init__.py to helper directory - This fixes ModuleNotFoundError when running the benchmark
- Added OpenHands root to PYTHONPATH in run_infer.sh - Changed back to absolute imports in run_infer.py - This fixes the 'no known parent package' error
|
This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds the polyglot benchmark implementation based on the Aider-AI/polyglot-benchmark repository. The benchmark evaluates how effectively an agent can translate natural language coding requests into executable code that passes unit tests across multiple programming languages (Python, JavaScript, Rust, Go, C++, Java).