feat(harness-codex): codex terminal agent + local rapid-mlx preset - #58
Merged
Conversation
…d-mlx preset codex 0.145+ speaks only the OpenAI responses API (wire_api=chat removed). rapid-mlx (:11437) serves /v1/responses, so codex's local provider points there; verified codex exec drives local gpt-oss. Package mirrors the existing four: install.sh (brew cask + copy-if-absent config merge), config/config.local-mlx.toml, README, moon.yml. herdr integration + Brewfile entry added separately. Co-Authored-By: Claude Opus 4.8 <[email protected]> Claude-Session: https://claude.ai/code/session_01Gni5WQNg9NwTZDszfhYSnf
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Add
harness-codex— OpenAI's codex terminal agent (brew caskcodex0.145.0) as the 5th harness, wired to the local MLX stack.Local-endpoint note
codex 0.145+ speaks only the OpenAI
responsesAPI (wire_api="chat"removed upstream). Of our local servers only rapid-mlx (:11437) serves/v1/responses(mlx_lm.server :11436 is chat-only), so codex's local provider points at rapid-mlx. Verified:codex execdrives local gpt-oss correctly.Package (mirrors the existing 4)
install.sh— brew cask install + copy-if-absent merge of the provider block into~/.codex/config.toml(never clobbers auth)config/config.local-mlx.toml—[model_providers.local-mlx]→ :11437,wire_api=responsesREADME.md,moon.yml(shellcheck lint)herdr integration (
herdr integration install codex) and Brewfile entry handled alongside.🤖 Generated with Claude Code
Need help on this PR? Tag
@codesmith-botwith what you need. Autofix is disabled.