Stream thinking chunks via reasoning_content and fix eaten tokens - #10
Closed
akachiina wants to merge 2 commits into
Closed
Stream thinking chunks via reasoning_content and fix eaten tokens#10akachiina wants to merge 2 commits into
akachiina wants to merge 2 commits into
Conversation
- Added tool_calls, tool_call_id, name fields to ChatMessage schema - Added tools and tool_choice to ChatCompletionRequest schema - messages_to_prompt now formats history with tool_calls and tool responses - Injects tool definitions into system prompt - Added extract_tool_calls_and_clean_text parser for XML/JSON tool calls - Responses now include tool_calls with finish_reason='tool_calls' - Streaming supports tool calls via delta.tool_calls - Added unit tests for validation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes thinking and search stream behavior: 1. Avoids eating the 1st token of thinking/response fragments. 2. Exposes thinking tokens under reasoning_content instead of content for OpenAI compatibility.