fix: add instruction back to provider options for codex oauth models to prevent BAD REQUEST error on Agent Create#20887
Open
OpeOginni wants to merge 5 commits intoanomalyco:devfrom
Open
Conversation
OpeOginni
changed the title
Contributor
Author
|
Added back the conditional system message, since its already added to the Instruction |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Closes #20820
Type of change
What does this PR do?
It adds back the
instructionsoption for oauth openai provider connections, to the Agent Creation function as when removed returns a 400 BAD REQUEST and a responseBody withInstructions are required.This PR follows the way instructions are passed in the llm.ts file, adding the instruction as providerOptions only for openai oauth connection models in the
streamObjectfunction.How did you verify your code works?
Tested with
bun run agent create --log-level=DEBUG --print-logs --pure --model openai/gpt-5.4, and the agent is created without the BAD REQUEST error. Also tested with thegpt-5.3-codexmodel.Screenshots / recordings
Checklist