Magnus Müller 5905ad949c feat: add thinking parameter to control agent system prompt ...

- Add --no-thinking flag to disable thinking in agent system prompt
- Default is true (thinking enabled) for backward compatibility
- Pass thinking parameter through entire evaluation pipeline
- Update GitHub Actions workflow to handle thinking parameter

2025-06-29 20:11:45 +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

feat: add thinking parameter to control agent system prompt

2025-06-29 20:11:45 +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

only create pre-release versions manually

2025-06-12 10:49:04 -07:00

test.yaml

run only one proc for tests for now

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