Added RunErrorDetails object for MaxTurnsExceeded exception #743
+81
−10
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
rm-openai
requested changes
May 23, 2025
src/agents/exceptions.py
Outdated
| @@ -1,7 +1,8 @@ | |||
| from typing import TYPE_CHECKING | |||
| from typing import TYPE_CHECKING, Optional | |||
There was a problem hiding this comment.
instead of Optiona, you can from __future__ import annotations then do error_details: ErrorDetails | None
src/agents/result.py
Outdated
| @@ -244,3 +248,15 @@ def _cleanup_tasks(self): | |||
|
|
|||
| def __str__(self) -> str: | |||
| return pretty_print_run_result_streaming(self) | |||
|
|
|||
| @dataclass | |||
| class RunErrorDetails(RunResultBase): | |||
There was a problem hiding this comment.
I don't think it makes sense to subclass RunResultBase. The error details and result can/should diverge - for example, final_output doesn't make sense in error details, because by definition there is no error.
src/agents/run.py
Outdated
Comment on lines
211
to
220
| run_error_details = RunErrorDetails( | ||
| input=original_input, | ||
| new_items=generated_items, | ||
| raw_responses=model_responses, | ||
| final_output=None, | ||
| input_guardrail_results=input_guardrail_results, | ||
| output_guardrail_results=[], | ||
| context_wrapper=context_wrapper, | ||
| _last_agent=current_agent | ||
| ) |
There was a problem hiding this comment.
it might make more sense to create this in the outermost try-catch. You'll catch all exceptions there, so you can capture and re-raise
|
Hi, thanks for the suggestions. I should have implemented the requested changes, let me know if I understood correctly or I have to correct the code |
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.
Summary
Introduced the
RunErrorDetailsobject to get partial results from a run interrupted byMaxTurnsExceededexception. In this proposal theRunErrorDetailsobject contains all the fields fromRunResultwithfinal_outputset toNoneandoutput_guardrail_resultsset to an empty list. We can decide to return less information.@rm-openai At the moment the exception doesn't return the
RunErrorDetailsobject for the streaming mode. Do you have any suggestions on how to deal with it? In the_check_errorsfunction ofagents/result.pyfile.Test plan
I have not implemented any tests currently, but if needed I can implement a basic test to retrieve partial data.
Issue number
This PR is an attempt to solve issue #719
Checks
make lintandmake format