swenyai/SWEny E2E — Agentic Browser Tests
Run agentic browser tests against a deployed app. AI drives the browser, no test scripts.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| workflow | Path to the E2E workflow YAML file to execute (relative to working-directory). | yes | — |
| claude-oauth-token | Claude Code OAuth token. Use this OR anthropic-api-key. OAuth tokens do not consume API credit. | no | — |
| anthropic-api-key | Anthropic API key for Claude. Use this OR claude-oauth-token. | no | — |
| base-url | Base URL of the deployed app under test. Exposed to the workflow as BASE_URL. | no | — |
| cli-version | Version of @sweny-ai/core to install (the package that ships the `sweny` CLI). Defaults to latest. | no | latest |
| agent-browser-version | Version of agent-browser to install. Defaults to latest. | no | latest |
| node-version | Node.js version to install. | no | 24 |
| working-directory | Working directory to run the workflow from. Defaults to the repository root. | no | . |
| screenshots-path | Path (relative to working-directory) where the workflow writes screenshots and artifacts. Uploaded after the run. | no | results/ |
| artifact-name | Name of the uploaded screenshots artifact. The job's run id is appended for uniqueness. | no | e2e-screenshots |
| artifact-retention-days | How long to retain the screenshots artifact (days). | no | 14 |
| verbose | When 'true', print each tool call's input and output inline. Truncated for readability; locally, the CLI's --stream flag yields full untruncated NDJSON. Helpful for debugging a workflow that halts or routes unexpectedly. Requires @sweny-ai/core >= 0.1.94. | no | false |
Outputs
no outputs