Quick fixes#57
Merged
justindobbs merged 8 commits intomainfrom Feb 28, 2026
Merged
Conversation
…ngChain adapter integration - Add agent_bench/integrations/llm_telemetry.py with Pydantic models (LLMCallRequest, LLMCallResponse, LLMCallTelemetry) - Update LangChain adapter generator to record llm_trace (provider/model, prompt, completion, shim flag) for each LLM call - Add runner support for emitting llm_trace in action_trace entries with opt-out via AGENT_BENCH_DISABLE_LLM_TRACE=1 - Add `agent-bench inspect` command to summar
- Add openai_agents extra in pyproject.toml with openai-agents>=0.0.9 dependency - Document openai_agents extra installation in README.md installation table - Reference official OpenAI Agents documentation at https://openai.github.io/openai-agents-python/
- Add _validate_run_id() to reject path separators, hidden files, and invalid characters in run IDs - Add _run_path() helper with regex validation and resolve() check to prevent directory traversal - Update persist_run() and load_run() to use validated _run_path() instead of direct Path concatenation - Add _validate_run_id() calls in WebUI _load_trace() and run_task() endpoints before loading artifacts - Add test_runlog_security.py with
- Add empty __init__.py to agents/ directory to enable proper Python package imports - Allows agents to be imported as modules from the agents package
…st_run - Remove unused LLMCallTelemetry imports from langchain_adapter.py - Remove unused Optional import from llm_telemetry.py - Add _validate_run_id() call in load_run_artifact() before loading run by ID - Add directory check in load_run_artifact() to reject directory paths - Simplify persist_run() validation by separating str() conversion from _validate_run_id() call
- Add existence check for baseline file/directory before comparison in workflow - Add validation for run_id extraction from run.json in workflow - Add FileNotFoundError handling in _cmd_baseline() to catch missing baseline/run files - Print error messages to stderr and exit with code 1 on validation failures - Refactor workflow to extract run_id into variable before agent-bench command
- Refactor _normalize_trace_entry() to skip None values in addition to volatile keys - Replace dict comprehension with explicit loop to filter both volatile keys and None values - Add run.json artifact (likely test fixture or baseline data)
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
1 participant
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.
No description provided.