[codex] Handle Codex tool search transcript shapes#24
Merged
Conversation
steipete
approved these changes
Jun 11, 2026
steipete
left a comment
steipete
left a comment
Contributor
There was a problem hiding this comment.
Approved after maintainer fixup.
Proof: local ruff, runtime contract smoke, full pytest, built wheel install, live ClawBench/OpenClaw protocol v4 run, Docker build, and Docker parser smoke all passed. CI is green at exact head 0f9b95b.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
codexDynamicToolsLoadingexplicitlyWhy
OpenClaw latest main can run GPT-5.5 through the Codex runtime with dynamic tool loading. Without parser hardening, bridge/control output shapes can fail to correlate tool results back to calls, which makes trajectory/verifier signals look like zeros even when tools ran. The lane config also needs to pass the Codex plugin setting from ClawBench until OpenClaw exposes a fully stable external contract.
Validation
bash -n scripts/container_lane_eval.sh/Users/zhentongfan/Desktop/openclaw/clawbench/.venv/bin/python -m pytest -q tests/test_client.py-> 19 passed/Users/zhentongfan/Desktop/openclaw/clawbench/.venv/bin/python -m pytest -q-> 299 passed, 5 skipped