Set 'temperature = 0' for extract_entities e2e test variants #3189
+90
−80
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
We had a model inference cache regen failure due to OpenAI and Anthropic generating different NER output (which caused the judge requests to be different, leading to a cache miss) instead of exactly the same output. Setting temperature=0 should make the test more consistent
There was a problem hiding this comment.
Pull Request Overview
This PR adds temperature = 0 configuration to all extract_entities function variants across two configuration files to improve test consistency. The change addresses a model inference cache regeneration failure where OpenAI and Anthropic models were generating different Named Entity Recognition (NER) outputs, causing cache misses due to different judge requests.
- Sets temperature to 0 for all extract_entities variants in both main and e2e configuration files
- Ensures deterministic model outputs to prevent cache misses during testing
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| ui/fixtures/config/tensorzero.toml | Added temperature=0 to 5 extract_entities variants for consistent model outputs |
| ui/fixtures/config/tensorzero.e2e.toml | Added temperature=0 to 5 extract_entities variants in e2e test configuration |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
|
/regen-fixtures |
virajmehta
approved these changes
Aug 20, 2025
virajmehta
previously approved these changes
Aug 20, 2025
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Outdated suggestions cannot be applied.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.
We had a model inference cache regen failure due to OpenAI and Anthropic generating different NER output (which caused the judge requests to be different, leading to a cache miss) instead of exactly the same output.
Setting temperature=0 should make the test more consistent
Important
Set
temperature = 0forextract_entitiesvariants to ensure consistent NER output and partially re-enable cache validation in workflow.temperature = 0forextract_entitiesvariants intensorzero.e2e.tomlandtensorzero.tomlto ensure consistent NER output..github/workflows/ui-tests-e2e-model-inference-cache.yml, but keep the exit condition commented out.This description was created by
for 1babbae. You can customize this summary. It will automatically update as commits are pushed.