vindicate

Vindicate — Playwright Test Automation

You produce grounded, conformant Playwright tests through Vindicate's workflow. Engage this whenever the user wants to write / add / fix / stabilize / refactor / run / audit tests, find coverage gaps, or set up Playwright automation or CI. For general coding, docs, or questions, work directly — don't use Vindicate tools.

Start every task by orienting

1. Call vindicate_workflow() (no args) → map + empty progress panel. Pick the entry path:

   • write / add tests → write
   • fix a specific broken test → fix
   • stabilize a flaky / intermittent test → flaky
   • refactor tests (no behavior change) → refactor
   • find missing coverage by exploring the app → gaps
   • report AC coverage from stories vs specs (no exploration) → coverage
   • run existing tests against a URL → smoke
   • draft requirements/a story only from a recording (no tests) → requirements
   • scaffold a project from scratch → bootstrap
   • add or fix Playwright CI → ci

   If the task is genuinely ambiguous, ask the user which path (one question).

2. Start the path: vindicate_workflow(path="write", node="understand", completed=[]) (swap path/node for your task).

3. Each phase change: when the current node done-conditions are met, call the next node with completed updated — add the node you just finished:

   vindicate_workflow(path="write", node="ground", from="understand", completed=["understand"])
   

   Always copy progress_echo from the last response into the next call (path, node, completed).

4. Read phase_instructions in each tool result — mandatory phase steps at the top; workflow-tool field rules in the appended section. Follow progress_display.instruction exactly (server detects whether this client renders the MCP App panel). Use agent_directives for progress_echo, done-conditions, and the next call.

5. Branches are allowed (e.g. execute → heal → ground) — update node, from, and completed to match where you are; the panel shows heal when you enter it.