fix(openai): emit output_text for assistant content in responses input#11169
Merged
Conversation
🦋 Changeset detectedLatest commit: 8242ece The changes in this PR will be included in the next version bump. This PR includes changesets to release 8 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
![open-swe[bot]](https://avatars.githubusercontent.com/in/1395372?s=60&v=4){kind=small}
Christian Bromann (christian-bromann)
approved these changes
Jul 9, 2026
Christian Bromann (christian-bromann)
left a comment
Christian Bromann (christian-bromann)
left a comment
Member
There was a problem hiding this comment.
LGTM 👍
Colin Francis (colifran)
pushed a commit
that referenced
this pull request
Jul 9, 2026
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/classic@1.0.39 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 ## @langchain/deepseek@1.1.4 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 ## @langchain/fireworks@0.2.4 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 ## @langchain/neo4j@0.1.11 ### Patch Changes - Updated dependencies []: - @langchain/classic@1.0.39 ## @langchain/openai@1.5.4 ### Patch Changes - [#11169](#11169) [`988ca7d`](988ca7d) Thanks [@colifran](https://github.com/colifran)! - fix(openai): emit output_text for assistant content in responses input ## @langchain/openrouter@0.4.4 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 ## @langchain/together-ai@0.2.4 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 ## @langchain/xai@1.4.4 ### Patch Changes - Updated dependencies [[`988ca7d`](988ca7d)]: - @langchain/openai@1.5.4 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
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
The openai responses converter typed all text content as
input_textregardless of role. For example, an assistant message became{ role: "assistant", content: [{ type: "input_text", … }] }and the API rejected it:This bug only affects the native openai responses api and only on multi-turn runs since the bad
input_textis on a prior assistant turn replayed as input meaning a single first turn never triggers it.This PR makes the text part role-aware, i.e.,
output_textfor assistant,input_textotherwise, this matches Python's_construct_responses_api_input.Tests
Added
convertStandardContentMessageToResponsesInputregression tests verifying that an assistant message converts tooutput_textand a user message staysinput_text.