ci: implement multi-model evaluation support #169

Open

omkargaikwad23 wants to merge 8 commits intomainfrom

claude-ci-evals

Commits on May 7, 2026

ci: implement multi-model evaluation support by replacing static run configs with dynamic discovery and adding Claude/Gemini-specific configurations.
omkargaikwad23
committed
ci: simplify PR label checks and update Claude model version in evals config
omkargaikwad23
committed
ci: update model, region, and environment configuration for Cloud SQL evaluation
omkargaikwad23
committed
ci: update evaluation model to claude-opus-4-1 and set CLOUD_ML_REGION env var
omkargaikwad23
committed
ci: update claude-opus model version to 4-6 in eval configuration
omkargaikwad23
committed
ci: update evaluation configuration with skill tagging, model upgrade to 4-7, and restructured run settings
omkargaikwad23
committed
ci: upgrade claude-code version to 2.1.119
omkargaikwad23
committed
ci: split shared dataset into model-specific configurations and update references
omkargaikwad23
committed