Playwright · Test runner API · all subjects

out of scope

7 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Playwright Test Generator agent tools available

The playwright-test-generator agent has access to the following tools for browser interaction: playwright-test/browser_click, playwright-test/browser_drag, playwright-test/browser_evaluate, playwright-test/browser_file_upload, playwright-test/browser_handle_dialog, playwright-test/browser_hover, playwright-test/browser_navigate, playwright-test/browser_press_key, playwright-test/browser_select_option, playwright-test/browser_snapshot, playwright-test/browser_type, playwright-test/browser_verify_element_visible, playwright-test/browser_verify_list_visible, playwright-test/browser_verify_text_visible, playwright-test/browser_verify_value, playwright-test/browser_wait_for, playwright-test/generator_read_log, playwright-test/generator_setup_page, and playwright-test/generator_write_test.

Playwright test coverage agent workflow overview

The playwright-test-coverage agent produces test coverage by following a three-step workflow: first calling the playwright-test-planner subagent to create a test plan, then calling the playwright-test-generator subagent for each test case sequentially (not in parallel), and finally calling the playwright-test-healer subagent to run and fix any failing tests.

playwright-test-coverage agent parameters

The playwright-test-coverage agent accepts three parameters: Task (required, the task to perform), Seed file (optional, defaults to ${seedFile}), and Test plan file (optional, specifies where to write the test plan file under the specs/ folder).

playwright-test-planner subagent input format

The playwright-test-planner subagent is called with a prompt containing: task-text (the task), seed-file (path to seed file), and plan-file (path to test plan file to generate).

playwright-test-generator subagent input format

The playwright-test-generator subagent is called for each test case with a prompt containing: test-suite (verbatim name of the test spec group without ordinal), test-name (name of the test case without ordinal), test-file (name of the file to save the test into), seed-file (seed file path from test plan), and body (test case content including steps and expectations).

playwright-test-healer subagent purpose

The playwright-test-healer subagent runs all tests and fixes failing ones one after another.

Test case generation sequencing

Test cases from the test plan file must be processed one after another in sequence, not in parallel, when calling the playwright-test-generator subagent.

Give your agent this brain