Skip to content

feat: Introduce OpenAI Decisions API backend and image input support - #1

Merged
Aaryanverma merged 3 commits into
mainfrom
enhancement/decision-api
Oct 9, 2026
Merged

Aaryanverma merged 3 commits into
mainfrom
enhancement/decision-api

Conversation

@Aaryanverma

Copy link
Copy Markdown
Contributor
  • Added OpenAIDecisionsBackend to support native text/image Decisions.
  • Implemented ImageInput model for inline image evidence handling.
  • Enhanced backend capabilities with evidence validation for text and image modalities.
  • Updated evaluator and calibration logic to accommodate new backend and image inputs.
  • Modified CLI to allow selection between Jev and OpenAI Decisions backends.
  • Improved error handling for unsupported modalities and invalid answers.
  • Added provenance tracking for backend configurations in calibration bundles.

- Added OpenAIDecisionsBackend to support native text/image Decisions.
- Implemented ImageInput model for inline image evidence handling.
- Enhanced backend capabilities with evidence validation for text and image modalities.
- Updated evaluator and calibration logic to accommodate new backend and image inputs.
- Modified CLI to allow selection between Jev and OpenAI Decisions backends.
- Improved error handling for unsupported modalities and invalid answers.
- Added provenance tracking for backend configurations in calibration bundles.
@Aaryanverma
Aaryanverma merged commit 96a9467 into main Oct 9, 2026
12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant