feat(Agent): add run_streaming() for structured SSE-compatible stream…#88
Open
rainj2013 wants to merge 1 commit intoMiniMax-AI:mainfrom
Open
feat(Agent): add run_streaming() for structured SSE-compatible stream…#88rainj2013 wants to merge 1 commit intoMiniMax-AI:mainfrom
rainj2013 wants to merge 1 commit intoMiniMax-AI:mainfrom
Conversation
…ing events
Add Agent.run_streaming() as the streaming counterpart to Agent.run().
All core logic (LLM calls, tool execution, token tracking, summarization,
cancellation) is identical; only the output format differs - instead of
printing to stdout, it yields structured AgentEvent objects via
AsyncGenerator.
New schema types:
- AgentEvent: discriminated union event with type, content, thinking,
tool_call, tool_result, step, final_text, total_tokens
- ToolCallEvent: emitted before tool execution (id, name, arguments)
- ToolResultEvent: emitted after tool execution (id, name, success,
content, error)
Event types: thinking | content | tool_call | tool_result |
step_complete | final
Consumers (e.g. SSE handlers) can map these events to their preferred
output format without reimplementing the agent loop.
Added tests: test_streaming.py with 7 test cases covering content
events, final events, tool call flow, cancellation, and max steps.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…ing events
Add Agent.run_streaming() as the streaming counterpart to Agent.run(). All core logic (LLM calls, tool execution, token tracking, summarization, cancellation) is identical; only the output format differs - instead of printing to stdout, it yields structured AgentEvent objects via AsyncGenerator.
New schema types:
Event types: thinking | content | tool_call | tool_result |
step_complete | final
Consumers (e.g. SSE handlers) can map these events to their preferred output format without reimplementing the agent loop.
Added tests: test_streaming.py with 7 test cases covering content events, final events, tool call flow, cancellation, and max steps.