Magnus Müller 5b6a00032c Enhance evaluation workflow with validation and error handling improvements ...

- Added validation for START_INDEX and TOTAL_TASKS to ensure they are numeric, with default values set to prevent errors.
- Improved logging for task range calculations and runner ID generation, including warnings for non-numeric inputs.
- Enhanced evaluation output handling with comprehensive error capture and logging, ensuring better debugging information is available.
- Implemented checks for the existence of evaluation logs and provided statistics for better visibility into evaluation outcomes.

2025-07-02 19:39:54 +02:00

..

build-base-image.yml.disabled

disable fast docker for now

2025-06-27 06:05:57 -07:00

claude.yml

allow claude github action to use more tools

2025-06-16 15:47:18 -07:00

cloud_evals.yml

Update cloud_evals.yml

2025-05-01 04:48:19 -04:00

docker.yml

only run docker build on main branch pushes

2025-05-16 05:42:58 -04:00

eval.yaml

Enhance evaluation workflow with validation and error handling improvements

2025-07-02 19:39:54 +02:00

lint.yml

imports

2025-06-21 06:29:10 -07:00

package.yaml

tweak env vars for CI

2025-06-10 03:58:37 -07:00

publish.yml

dont re-run entire tests suite before pypi release

2025-06-30 04:35:51 -04:00

test.yaml

run only one proc for tests for now

2025-06-27 03:02:03 -07:00