fix(provider): scope gpt-5 reasoningEffort to native providers only#31465
Open
liloi wants to merge 2 commits into
Open
fix(provider): scope gpt-5 reasoningEffort to native providers only#31465liloi wants to merge 2 commits into
liloi wants to merge 2 commits into
Conversation
The `reasoningEffort = "medium"` assignment was unconditionally applied to all providers when the model ID matched gpt-5. This caused requests to fail on third-party gateways (e.g. Sophon) accessed via @ai-sdk/openai-compatible, which may not support the reasoningEffort parameter. Move the assignment inside the existing native provider allowlist guard so only @ai-sdk/openai, @ai-sdk/azure, @ai-sdk/github-copilot, and @ai-sdk/amazon-bedrock/mantle receive it.
github-actions
Bot
added
needs:compliance
Contributor
|
Thanks for your contribution! This PR doesn't have a linked issue. All PRs must reference an existing issue. Please:
See CONTRIBUTING.md for details. |
Contributor
|
The following comment was made by an LLM, it may be inaccurate: Potential Duplicate Found:
Why it may be related: |
github-actions
Bot
removed
needs:issue
needs:compliance
Contributor
|
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 #31466
Type of change
What does this PR do?
reasoningEffort = "medium"is set unconditionally at L1145 for all gpt-5 models, regardless of provider type. When using@ai-sdk/openai-compatibleto connect to third-party gateways (e.g. Sophon), the gateway may not support this parameter and rejects the request.The fix moves the
reasoningEffortassignment inside the existing provider allowlist condition (which already guardsreasoningSummary), so it only applies to native providers that actually support it:@ai-sdk/openai,@ai-sdk/azure,@ai-sdk/github-copilot, and@ai-sdk/amazon-bedrock/mantle.How did you verify your code works?
Confirmed that after the change, requests via
@ai-sdk/openai-compatibleto a Sophon gateway no longer includereasoningEffortand succeed. Native OpenAI provider behavior is unchanged.Screenshots / recordings
N/A (backend-only change)
Checklist