chore(claude): enable provided playwright test agents

[carlosthe19916]

Addresses: #909

Enabling Playwright provided Test Agents as documented in the official webpage https://playwright.dev/docs/test-agents

This PR is the result of executing npx playwright init-agents --loop=claude with no customization to the default agent definition.

Notice that this PR also includes a new MCP server

"playwright-test": {
      "command": "npx",
      "args": [
        "playwright",
        "run-test-mcp-server"
      ]
    }

which is different from

"playwright": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@playwright/mcp@latest"
      ],
      "env": {}
    },

Summary by Sourcery

Integrate Playwright-provided test agents for planning, generating, and healing browser tests, and wire them up via a dedicated Playwright test MCP server.

New Features:

• Add a Playwright test generator agent for creating Playwright test files from high-level test plans.
• Add a Playwright test planner agent for exploring web apps and producing structured test plans.
• Add a Playwright test healer agent for diagnosing and fixing failing Playwright tests using Playwright MCP tools.

Enhancements:

• Register a new playwright-test MCP server configuration to back the Playwright testing agents.

[sourcery-ai]

Reviewer's Guide

Adds Playwright-provided Claude test agents (planner, generator, healer) and wires them to a new playwright-test MCP server configuration, enabling automated planning, generation, and healing of Playwright tests via Claude.

File-Level Changes

Change	Details	Files
Configure new Playwright Test MCP server for Claude separate from existing generic Playwright MCP server.	Add playwright-test MCP server entry that runs npx playwright run-test-mcp-server. Keep existing playwright MCP entry that runs @playwright/mcp@latest, clarifying there are now two distinct Playwright-related MCP endpoints.	.mcp.json
Introduce a Claude agent for generating Playwright tests from existing test plans and seed files using the new Playwright Test MCP tools.	Create playwright-test-generator agent definition with detailed role instructions for turning markdown test plans into single-file Playwright tests. Wire generator-focused MCP tools (generator_setup_page, generator_read_log, generator_write_test, and browser_* tools) into the agent. Document example input/output workflow for converting a sample test plan into a generated test file with best-practice structure.	.claude/agents/playwright-test-generator.md
Introduce a Claude agent for planning comprehensive Playwright test suites by exploring a web app via Playwright browser tools.	Create playwright-test-planner agent definition with responsibilities for exploring the UI, mapping user flows, and drafting test scenarios. Attach planner-specific tools (planner_setup_page, planner_save_plan, and browser_* tools) and describe constraints around screenshots and exploration depth. Define required structure and quality standards for saved markdown test plans including scenario breakdown, steps, and negative tests.	.claude/agents/playwright-test-planner.md
Introduce a Claude agent for debugging and healing failing Playwright tests using Playwright Test MCP debugging tools.	Create playwright-test-healer agent definition focused on running, debugging, and fixing failing tests via test_run, test_debug, test_list, and browser inspection tools. Lay out a step-by-step healing workflow: run tests, debug failures, inspect context, identify root cause, edit tests, and re-run until green. Codify best practices such as robust selectors, avoiding discouraged APIs, documenting fixes, and using test.fixme() when the app is broken rather than the test.	.claude/agents/playwright-test-healer.md

Possibly linked issues

• #claude: The PR implements the issue’s decision by enabling Playwright-provided test agents and configuring the new MCP server.

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've left some high level feedback:

• The description field in playwright-test-generator frontmatter is extremely long and contains example markup inline; consider moving the example into the body text so the description stays concise and the YAML remains more readable and maintainable.
• The hard‑coded tools lists for the three new agents are quite verbose and tightly coupled to the MCP server API; consider adding a brief comment or central reference near .mcp.json to keep these in sync if Playwright’s MCP tool names change (e.g., when regenerating via init-agents).

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `description` field in `playwright-test-generator` frontmatter is extremely long and contains example markup inline; consider moving the example into the body text so the description stays concise and the YAML remains more readable and maintainable.
- The hard‑coded `tools` lists for the three new agents are quite verbose and tightly coupled to the MCP server API; consider adding a brief comment or central reference near `.mcp.json` to keep these in sync if Playwright’s MCP tool names change (e.g., when regenerating via `init-agents`).

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 63.91%. Comparing base (9e82125) to head (ab2a6c6).

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #911      +/-   ##
==========================================
- Coverage   64.40%   63.91%   -0.49%     
==========================================
  Files         187      187              
  Lines        3295     3295              
  Branches      746      746              
==========================================
- Hits         2122     2106      -16     
- Misses        875      891      +16     
  Partials      298      298              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.