Fix/responses streaming#4
Merged
Merged
Conversation
Without this override the base class parser (which expects Chat
Completions SSE: choices[0].delta.content) silently yields empty
tokens for every line of a Responses API stream, leaving accumulated
text empty and returning success=false with no error string.
Responses API deltas arrive as:
data: {"type":"response.output_text.delta","delta":"token"}
Default ProviderConfig.maxTokens from 4096 to 0 so providers that gate on if (maxTok > 0) omit the cap entirely. Letting OpenAI use its own default matters for GPT-5 Responses where reasoning tokens count against max_output_tokens — 4096 was being exhausted mid-reasoning and returning incomplete/truncated responses. Anthropic still falls back to 4096 internally because its API requires max_tokens.
Anthropic's Messages API rejects this field with HTTP 400 — it was an OpenAI-ism. `reasoningEffort` is now silently ignored for Anthropic. Extended thinking uses a separate `thinking` block on supporting models.
for more information, see https://pre-commit.ci
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.