experientiallabs/experiential

test-build

Run the live Experiential build-to-serve path as an unattended automation. Fits the pinned terminal-tasks trace export through the CLI, calibrates the judge non-interactively, fits a router, verifies exact replay, and serves the frozen policy on loopback. Use…

原文语言：英语

improve-judge

Improve a canonical common-owned judge from reviewed rollout evidence, human labels, and leakage-safe calibration without bypassing the frozen router workflow.

原文语言：英语

ready-for-merge

Mandatory pre-merge gate for every PR. Runs /code-review --fix at an effort level scaled to the PR's breadth, resolves every review comment (Cursor, Greptile, humans), and verifies the diff complies with AGENTS.md. Use whenever the user says a PR is ready to…

原文语言：英语

test-gateway

End-to-end happy-path test of the Experiential local gateway, covering interactive first-run setup via the exp run TUI, the served OpenAI-compatible routes, usage accounting, restart persistence, and integration with an external OpenAI-compatible client such…

原文语言：英语