inferences should retry in durable-tools if the output is empty #5956
+247
−9
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
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0b7d21f48b
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
GabrielBianconi
previously approved these changes
Jan 29, 2026
Member
Author
|
/merge-queue |
Contributor
|
🚀 Merge queue workflow triggered! View the run: https://github.com/tensorzero/tensorzero/actions/runs/21461414995 |
6feca03 to
3883e62
Compare
Member
|
/merge-queue |
Contributor
|
🚀 Merge queue workflow triggered! View the run: https://github.com/tensorzero/tensorzero/actions/runs/21462672703 |
Aaron1011
approved these changes
Jan 29, 2026
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Outdated suggestions cannot be applied.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.
Note
Medium Risk
Behavior of
ToolContext::inferencechanges to treat empty model outputs as step failures, which can increase retries or mark tasks failed where they previously succeeded with empty data. Risk is moderate because it affects durable task execution semantics but not security-sensitive logic.Overview
Prevents durable inference steps from silently succeeding with empty model output by making
ToolContext::inferencereturn an error when chat responses have no content blocks or JSON responses haveoutput.raw == None, enabling the durable step to be retried.Adds integration coverage that mocks empty chat/JSON inference responses and asserts the spawned
TaskToolrun is marked failed with an empty output failure reason.Written by Cursor Bugbot for commit 3883e62. This will update automatically on new commits. Configure here.