Restore parallel tool calls for Codex OAuth - #578
Merged
ericdallo merged 1 commit intoAug 24, 2026
Merged
Conversation
Route explicitly parallel-capable Lite models through the ordinary Responses function-tool shape, since the Lite endpoint requires serial tool calls. Preserve the Lite path for fallback and partial model metadata. 🤖 Generated with [ECA](https://eca.dev) (openai/gpt-5.6-sol - xhigh) Co-Authored-By: eca-agent <git@eca.dev>
ericdallo
approved these changes
Aug 24, 2026
ericdallo
left a comment
ericdallo
left a comment
Member
There was a problem hiding this comment.
Looks good, LMK if any issues with that, thank you
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Getting parallel tool calls work with Codex with OAuth proved much simpler than I feared. Oddly the API requires the "Responses Lite" API with codex-5.6 models, but then it advertises parallel support allowing to use the full Responses API when returning parallel tool calls. I bet it wasn't designed by humans.
Summary
all_turnsreasoning context and function-tool visibility without enabling hosted web or image toolsTesting
clojure -M:test --focus eca.llm-providers.openai-testclojure -M:test --focus eca.llm-api-testclojure -M:test --focus eca.features.chat-test/concurrent-tool-calls-testLC_ALL=C LANG=C bb testclj-kondo --lint src/eca/llm_providers/openai.clj test/eca/llm_providers/openai_test.cljCloses #572
🤖 Generated with ECA (openai/gpt-5.6-sol - xhigh)