This is a share-once demonstration of prompt-discovered UI tests. Help the user adapt it to their application with small, understandable changes. Read the target repository's own instructions before changing it.
- Inspect startup commands, dependencies, authentication, optional extension builds, and existing validation commands. Do not guess credentials or replace a real application with a fixture.
- Run
agentic-ui init --workspace <project>. Preserve existing configuration, secrets, and unrelated changes. Set the real target URL, credential names, extension path, repair paths, and appropriate prepare/validation argv arrays. - Help the user supply an OpenRouter key in
.env.agentic-uior their shell. The default model isopenrouter/z-ai/glm-5.3-flash. Never print secret values, overwrite the target's ordinary.env, or commit secret files. - Start the real app and dependencies. Use
host.docker.internalfor host services from Docker and a reachable deployed URL remotely. Build the image and rundoctor. Public recipe replay needs no model key. - Discover one requested workflow, replay its saved recipe, and inspect the result and video. Report observed failures truthfully. Have the user review recipes before committing; commit nothing without authorization.
- Explain repair prerequisites: clean Git checkout, reviewed repair paths, and a project validation command. Publishing a draft PR requires an explicit request and GitHub access; creating a report alone does not require either.
- OpenHands owns Chromium and every browser interaction inside the container. OpenCode orchestrates discovery and repair analysis. Never add a host-browser execution path or another browser driver.
- Default local Docker builds and runs to
linux/arm64. Honor an explicitAGENTIC_UI_PLATFORM=linux/amd64override when a user selects an AMD/x86 container. - Saved recipes replay deterministically without a model. Local and remote use the same runtime definition; multi-platform immutable images make each architecture-specific runtime reproducible.
- Exercise real visible UI and real provider responses. Never invent expected data, titles, pages, accounts, or successful outcomes. Report provider failures.
- Prefer stable semantic selectors and explicit visible assertions. Keep
credentials as
${VARIABLE_NAME}references resolved by the browser process. - Preserve result JSON, failed-step details, screenshots, and continuous video. Quick recording is 720p/10 fps; demo is 1080p/60 fps with an 800 ms dwell between steps. Inspect the actual video rather than assuming recorder startup proves the artifact is usable.
- Read the failure artifact, reproduce it, and distinguish product defects from environment/provider/test failures. A passing reproduction does not justify inventing a defect or claiming it was fixed.
- Make the smallest root-cause change inside configured repair paths. Do not weaken a recipe to conceal a product bug. Respect unrelated project changes.
- The controller runs project validation independently. This demo does not automatically start a repaired candidate, so replaying the original URL cannot validate repaired source. State that limitation in the report.
- Repair agents must not commit, push, create branches, or contact GitHub. The
explicit host
publish-prcommand checks recorded state and publishes a draft PR when requested. Never automatically merge. - PR descriptions explain root cause, resulting behavior, actual validation, and uncertainty. Do not claim unexecuted checks passed.
- OpenCode permissions are advisory. Mounted files are writable and shell commands are powerful; this is not isolation for hostile repositories. Profiles and artifacts can contain secrets and private data.
Keep onboarding concrete. Add project details where needed without introducing a universal framework or claiming support for unexercised integrations.