Repository navigation
fix: preserve JSON responses to streaming requests - #12
Merged
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A successful JSON response to a streaming request was discarded, followed by another generation. This could lose assistant progress notes and tool calls and duplicate token usage. Consume the original response with the existing format parser and body cap, then keep the learned buffered mode for future requests. Malformed or unreadable responses return their error without silently replacing the generation.
Validation: full SDK race suite and golangci-lint pass. OpenAI Chat Completions and Responses regressions verify one request per generation, preserved notes/reasoning/tool calls/usage/signatures, subsequent buffered requests, malformed JSON, read failures and the 50 MiB body bound. The new fallback branches have complete statement coverage.
This patch will be tagged v0.6.1 after CI and squash merge; odek v2.29.7 consumes it for the partial-turn rendering fix.