DI-4253: support OPENAI_CODEX_REASONING_EFFORT env var#149
Merged
Conversation
Lets the ai-codegen-api ade-bench harness match the studio dev agent's configured reasoning effort (low) when running the codex baseline, so the comparison isn't confounded by effort defaults. When the env var is unset, behavior is unchanged — codex picks its own default.
joellabes
approved these changes
May 27, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
When comparing the codex baseline against another agent, it's useful to be able to dial codex's reasoning effort to match the other agent's configuration, so the comparison isn't confounded by effort defaults. There's no way to do that today from outside the agent.
What
OpenAICodexAgentreads an optionalOPENAI_CODEX_REASONING_EFFORTenv var and, if set, passes it through as-c model_reasoning_effort=<value>on the codex command line. When unset, the command is unchanged.Going through an env var rather than a constructor kwarg avoids touching the
Harness/AgentFactoryplumbing, since callers (run_harness.py, downstream wrappers) don't currently thread arbitrary agent kwargs through.Drafted by Opus 4.7 under the direction of @wiggzz.