Debug why an Autonoma preview deployment broke - read live deploy status, build and app logs, and a diagnosis, then fix a missing secret or preview config from inside your repo.
This config will be passed to Cursor on install. Inspect `command`, `args`, and `env` before continuing.
Autonoma runs your end-to-end tests against a per-PR preview deployment of your app. When a preview fails to build or deploy, or a test fails because the app is broken, this connects your agent to the live evidence and lets it fix the cause in your repo.
Tools: list_apps, get_deploy_status, get_endpoints, get_build_logs, get_app_logs, diagnose_deploy, get_secret_status, set_secret, edit_previewkit_config, wait_for_deploy.
Flow: check get_deploy_status or diagnose_deploy first, read the relevant logs, then fix with set_secret (a missing value) or edit_previewkit_config (build/wiring), and confirm with wait_for_deploy.
Requires an Autonoma account with the repo connected; sign-in happens via OAuth in the browser.