fix: fix OpenAI reasoning + web_search replay failure - #23402
Closed
ibetitsmike wants to merge 4 commits into
Closed
fix: fix OpenAI reasoning + web_search replay failure#23402ibetitsmike wants to merge 4 commits into
ibetitsmike wants to merge 4 commits into
Conversation
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Breezy! ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes the follow-up turn failure when an OpenAI reasoning model produces both reasoning output and a provider-executed
web_search_callin the same response.Root cause: The
fantasyadapter skipped reasoning items entirely during replay. Whenstore=true, web_search items were replayed viaitem_referencebut the reasoning item that preceded them was dropped. OpenAI rejects this with: "reasoning was provided without its required following item."Fix: Updated the pinned
fantasyfork to emititem_referencefor reasoning items whenstore=true, keeping them paired with subsequent provider-executed tool calls. Upstream PR: coder/fantasy#7Changes
coderd/chatd/chattest/openai.go: Extended fake OpenAI server to stream reasoning + web_search + text eventscoderd/chatd/integration_test.go: AddedTestOpenAIReasoningWithWebSearchRoundTripandTestOpenAIReasoningWithWebSearchRoundTripStoreFalsego.mod/go.sum: Updated fantasy pin to include the replay fix