5 Commits

Author	SHA1	Message	Date
Pedro Rodrigues	3c3d1f55ca	containerize eval environment with Docker and mock CLIs ... Host now only needs Docker + ANTHROPIC_API_KEY to run evals. Adds multi-stage Dockerfile, mock supabase/docker/psql scripts, entrypoint, docker-compose for local use, and switches CI to Docker-based execution. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-23 19:22:47 +00:00
Pedro Rodrigues	e06a567846	workflow evals with one scenario	2026-02-19 17:06:17 +00:00
Pedro Rodrigues	082eac2a01	multi model testing	2026-02-18 13:28:42 +00:00
Pedro Rodrigues	27d7af255d	initial skills evals	2026-02-18 12:02:28 +00:00
Pedro Rodrigues	760460c221	chore: using mise to manage node versions and tasks (#44) ... * add mise for Node.js version management Replace ad-hoc Node version pinning with mise (mise.toml + mise.lock). This ensures all contributors and CI use the same Node LTS version. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * expand mise with env loading, PATH management, and task runner - [env] _.file loads .env files for local API keys (replaces dotenv) - [env] _.path adds node_modules/.bin to PATH for direct tool access - [tasks] mirrors npm scripts with sources/outputs for file-based caching - eval tasks for running LLM evaluations via mise run - update AGENTS.md and CONTRIBUTING.md to use mise run commands Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-17 12:44:44 +00:00