Conversation
When a client asks for stream: true, the proxy and `none` paths re-emit the finished completion through generate_streaming_response(extract_contents(...)), which keeps only message.content. A tool call has empty content, so streaming agents (OptiQ Code, the OptiQ Lab, most coding agents) received a bare [DONE] and saw an empty reply; models that answer in `reasoning` lost that too. generate_streaming_completion streams the whole message instead: content, reasoning / reasoning_content, and tool_calls with the per-call index the OpenAI streaming format requires, plus usage in a final chunk. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a client sends
stream: true, the proxy andnonepaths re-emit the finished completion withgenerate_streaming_response(extract_contents(...)), which keeps onlymessage.content.data: [DONE]and see an empty reply.reasoninglose that text as well.This adds
generate_streaming_completion, which streams the whole message: content,reasoning/reasoning_content, andtool_callswith the per-callindexthat the OpenAI streaming format requires, plususagein a final chunk.Found by pointing OptiQ Code at an optillm proxy (
--approach proxy): every turn came back empty. With the patch the same streamed request returns the tool call.Tests:
tests/test_streaming_completion.py(tool calls, text + reasoning, a list of completions).🤖 Generated with Claude Code