feat: Add generation_kwargs to run methods of Agent #9616
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
|
|
sjrl
reviewed
Jul 17, 2025
Co-authored-by: Sebastian Husch Lee <[email protected]>
sjrl
reviewed
Jul 18, 2025
Comment on lines
+241
to
+242
| streaming_callback: Optional[StreamingCallbackT] = None, | ||
| generation_kwargs: Optional[Dict[str, Any]] = None, |
There was a problem hiding this comment.
Since I know other work is being done on this run method in a separate feature branch let's go ahead and make generation_kwargs a keyword only arg.
Suggested change
| streaming_callback: Optional[StreamingCallbackT] = None, | |
| generation_kwargs: Optional[Dict[str, Any]] = None, | |
| streaming_callback: Optional[StreamingCallbackT] = None, | |
| *, | |
| generation_kwargs: Optional[Dict[str, Any]] = None, |
sjrl
reviewed
Jul 18, 2025
Comment on lines
+345
to
+346
| streaming_callback: Optional[StreamingCallbackT] = None, | ||
| generation_kwargs: Optional[Dict[str, Any]] = None, |
There was a problem hiding this comment.
Same here
Suggested change
| streaming_callback: Optional[StreamingCallbackT] = None, | |
| generation_kwargs: Optional[Dict[str, Any]] = None, | |
| streaming_callback: Optional[StreamingCallbackT] = None, | |
| *, | |
| generation_kwargs: Optional[Dict[str, Any]] = None, |
sjrl
reviewed
Jul 18, 2025
| @@ -746,7 +746,7 @@ def test_run(self, weather_tool): | |||
| chat_generator = OpenAIChatGenerator(model="gpt-4o-mini") | |||
| agent = Agent(chat_generator=chat_generator, tools=[weather_tool], max_agent_steps=3) | |||
| agent.warm_up() | |||
| response = agent.run([ChatMessage.from_user("What is the weather in Berlin?")]) | |||
| response = agent.run([ChatMessage.from_user("What is the weather in Berlin?")], generation_kwargs={"temperature": 0.0}) | |||
There was a problem hiding this comment.
Could we add a new unit test instead that resuses chat_generator = MockChatGeneratorWithoutRunAsync() and chat_generator.run.assert_called_once_with(messages=..., tools=..., generation_kwargs=...) so we can check that the generation_kwargs are being properly propogated?
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.
Related Issues
Proposed Changes:
added a generation_kwargs parameter to Agent which are to be passed to LLM
How did you test it?
added generation_kwargs to unit test run
Checklist
fix:,feat:,build:,chore:,ci:,docs:,style:,refactor:,perf:,test:and added!in case the PR includes breaking changes.