fix: forward max_tokens in Chat Completions API requests#1495
Merged
joshua-mo-143 merged 1 commit into0xPlaygrounds:mainfrom Mar 10, 2026
Merged
Conversation
The Chat Completions provider's `CompletionRequest` struct was missing the `max_tokens` field. When users set `.max_tokens(N)` on the agent builder, the value was accepted and stored in the core `CompletionRequest` but silently discarded during conversion to the OpenAI Chat Completions request — the `TryFrom` destructured with `..` which dropped it, and the struct had no field to receive it. The Responses API provider correctly handles this via `max_output_tokens`, so only the Chat Completions path was affected. The fix adds `max_tokens: Option<u64>` to the provider's `CompletionRequest`, extracts it from the core request during conversion, and includes it in the serialized API request.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
CompletionRequeststruct is missing amax_tokensfield. When.max_tokens(N)is called on the agent builder, the value flows into the coreCompletionRequestbut is silently discarded duringTryFrom<OpenAIRequestParams>conversion — the destructuring uses..which drops it, and the provider struct has no field to receive it.max_output_tokens, so only the Chat Completions path is affected.max_tokens: Option<u64>to the provider'sCompletionRequest, extracts it during conversion, and serializes it in the API request body.Test plan
test_max_tokens_is_forwarded_to_request— verifiesmax_tokensappears in serialized JSON when settest_max_tokens_omitted_when_none— verifiesmax_tokensis omitted from JSON whenNoneproviders::openai::completion::testspass (7/7)