Python: feat(ag-ui, openai): Add TextReasoningContent to thinking events and reasoning_field to OpenAI client #3094
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
| if reasoning_details := getattr(choice.delta, "reasoning_details", None): | ||
| contents.append(TextReasoningContent(None, protected_data=json.dumps(reasoning_details))) | ||
| # Handle custom reasoning field for OpenAI-compatible APIs (e.g., Kimi, DeepSeek) | ||
| if reasoning_field := getattr(self, "reasoning_field", None): |
Member
There was a problem hiding this comment.
How would a user discover what the reasoning field name is for other API's then openai?
Author
There was a problem hiding this comment.
If I understand your question correctly, users would typically refer to the provider's documentation.
For example, DeepSeek documents reasoning_content here: https://api-docs.deepseek.com/guides/thinking_mode
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
Motivation and Context
The
TextReasoningContenttype exists in agent-framework for representing extended thinking/reasoning content from LLMs (e.g., Anthropic's extended thinking, OpenAI's reasoning). However, the AG-UI Event Bridge does not handle this content type, meaning thinking content is silently dropped when streaming to AG-UI clients.Additionally, OpenAI-compatible APIs (like Kimi, DeepSeek) return reasoning content in a custom field (e.g.,
reasoning_content) rather than the standard response format. The currentOpenAIChatClienthas no way to extract this content.Description
This PR adds two related features:
1. AG-UI Event Bridge (
_events.py)TextReasoningContentby emitting AG-UI thinking events:ThinkingStartEvent→ThinkingTextMessageStartEvent→ThinkingTextMessageContentEvent→ThinkingTextMessageEndEvent→ThinkingEndEventprotected_datafield extraction for OpenAI'sreasoning_detailsformatTextMessageEndEvent)2. OpenAI Chat Client (
_chat_client.py)reasoning_fieldparameter toOpenAIChatClientreasoning_field="reasoning_content"), extract content from that field and emitTextReasoningContentContribution Checklist