Accept dict run_config in openai_agents Temporal runner - #1739
Merged
Conversation
DABH
commented
Aug 11, 2026
DABH
enabled auto-merge (squash)
August 11, 2026 06:10
brianstrauch
approved these changes
Aug 11, 2026
| if run_config is None: | ||
| run_config = RunConfig() | ||
| run_config = ( | ||
| RunConfig() if run_config is None else _coerce_run_config(run_config) |
Member
There was a problem hiding this comment.
Could move the None check into the function and call it _normalize_run_config() so this is more compact.
tconley1428
approved these changes
Aug 11, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
openai-agents>= 0.19.0 (just out of cooldown quarantine) accepts aRunConfigor - now - a plain dict. So CI (pyright) was failing. We update things to ensure valid functionality whether a plain dict orRunConfigis used by a user, and normalize either to aRunConfig. Note we need it to be aRunConfignot a dict so that the plugin correctly wraps the model (by intercepting/overwriting the model config); see below.Why
See
test-latest-depsfailure:https://github.com/temporalio/sdk-python/actions/runs/31451259813
This was also a runtime bug, not just a typing one: on openai-agents >= 0.19,
Runner.run(..., run_config={...})inside a workflow crashed in our_prepare_workflow_runwithAttributeError: 'dict' object has no attribute 'model'before reaching the agents runner's own coercion.How tested
CI