Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
TypeScript automationchromechromiume2e-testingelectronend-to-end-testingfirefoxjavascriptplaywrighttesttest-automationtestingtesting-toolswebwebkit
chore: use new chatmodes location (#37973)
Pavel Feldmanb49143444832
diff --git a/examples/todomvc/.claude/agents/playwright-test-generator.agent.md b/examples/todomvc/.claude/agents/pwt-generator.mdsimilarity index 73%rename from examples/todomvc/.claude/agents/playwright-test-generator.agent.mdrename to examples/todomvc/.claude/agents/pwt-generator.mdindex 276b2d737f..0425618de1 100644--- a/examples/todomvc/.claude/agents/playwright-test-generator.agent.md+++ b/examples/todomvc/.claude/agents/pwt-generator.md@@ -1,7 +1,7 @@----name: playwright-test-generator-description: Use this agent when you need to create automated browser tests using Playwright. Examples: <example>Context: User wants to test a login flow on their web application. user: 'I need a test that logs into my app at localhost:3000 with username [email protected] and password 123456, then verifies the dashboard page loads' assistant: 'I'll use the generator agent to create and validate this login test for you' <commentary> The user needs a specific browser automation test created, which is exactly what the generator agent is designed for. </commentary></example><example>Context: User has built a new checkout flow and wants to ensure it works correctly. user: 'Can you create a test that adds items to cart, proceeds to checkout, fills in payment details, and confirms the order?' assistant: 'I'll use the generator agent to build a comprehensive checkout flow test' <commentary> This is a complex user journey that needs to be automated and tested, perfect for the generator agent. </commentary></example>-tools: Read, Glob, Grep, mcp__playwright-test__browser_click, mcp__playwright-test__browser_drag, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_file_upload, mcp__playwright-test__browser_handle_dialog, mcp__playwright-test__browser_hover, mcp__playwright-test__browser_navigate, mcp__playwright-test__browser_press_key, mcp__playwright-test__browser_select_option, mcp__playwright-test__browser_snapshot, mcp__playwright-test__browser_type, mcp__playwright-test__browser_verify_element_visible, mcp__playwright-test__browser_verify_list_visible, mcp__playwright-test__browser_verify_text_visible, mcp__playwright-test__browser_verify_value, mcp__playwright-test__browser_wait_for, mcp__playwright-test__generator_read_log, mcp__playwright-test__generator_setup_page, mcp__playwright-test__generator_write_test+name: pwt-generator+description: Use this agent when you need to create automated browser tests using Playwright. Examples: <example>Context: User wants to generate a test for the test plan item. <test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite> <test-name><!-- Name of the test case without the ordinal like "should add two numbers" --></test-name> <test-file><!-- Name of the file to save the test into, like tests/multiplication/should-add-two-numbers.spec.ts --></test-file> <seed-file><!-- Seed file path from test plan --></seed-file> <body><!-- Test case content including steps and expectations --></body></example>+tools: Glob, Grep, Read, mcp__playwright-test__browser_click, mcp__playwright-test__browser_drag, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_file_upload, mcp__playwright-test__browser_handle_dialog, mcp__playwright-test__browser_hover, mcp__playwright-test__browser_navigate, mcp__playwright-test__browser_press_key, mcp__playwright-test__browser_select_option, mcp__playwright-test__browser_snapshot, mcp__playwright-test__browser_type, mcp__playwright-test__browser_verify_element_visible, mcp__playwright-test__browser_verify_list_visible, mcp__playwright-test__browser_verify_text_visible, mcp__playwright-test__browser_verify_value, mcp__playwright-test__browser_wait_for, mcp__playwright-test__generator_read_log, mcp__playwright-test__generator_setup_page, mcp__playwright-test__generator_write_testmodel: sonnetcolor: blue---diff --git a/examples/todomvc/.claude/agents/playwright-test-healer.agent.md b/examples/todomvc/.claude/agents/pwt-healer.mdsimilarity index 74%rename from examples/todomvc/.claude/agents/playwright-test-healer.agent.mdrename to examples/todomvc/.claude/agents/pwt-healer.mdindex 18cd979974..347ba0bbd4 100644--- a/examples/todomvc/.claude/agents/playwright-test-healer.agent.md+++ b/examples/todomvc/.claude/agents/pwt-healer.md@@ -1,7 +1,7 @@----name: playwright-test-healer-description: Use this agent when you need to debug and fix failing Playwright tests. Examples: <example>Context: A developer has a failing Playwright test that needs to be debugged and fixed. user: 'The login test is failing, can you fix it?' assistant: 'I'll use the healer agent to debug and fix the failing login test.' <commentary> The user has identified a specific failing test that needs debugging and fixing, which is exactly what the healer agent is designed for. </commentary></example><example>Context: After running a test suite, several tests are reported as failing. user: 'Test user-registration.spec.ts is broken after the recent changes' assistant: 'Let me use the healer agent to investigate and fix the user-registration test.' <commentary> A specific test file is failing and needs debugging, which requires the systematic approach of the playwright-test-healer agent. </commentary></example>-tools: Read, Glob, Grep, Write, Edit, MultiEdit, mcp__playwright-test__browser_console_messages, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_generate_locator, mcp__playwright-test__browser_network_requests, mcp__playwright-test__browser_snapshot, mcp__playwright-test__test_debug, mcp__playwright-test__test_list, mcp__playwright-test__test_run+name: pwt-healer+description: Use this agent when you need to debug and fix failing Playwright tests.+tools: Glob, Grep, Read, Edit, MultiEdit, Write, mcp__playwright-test__browser_console_messages, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_generate_locator, mcp__playwright-test__browser_network_requests, mcp__playwright-test__browser_snapshot, mcp__playwright-test__test_debug, mcp__playwright-test__test_list, mcp__playwright-test__test_runmodel: sonnetcolor: red---diff --git a/examples/todomvc/.claude/agents/playwright-test-planner.agent.md b/examples/todomvc/.claude/agents/pwt-planner.mdsimilarity index 66%rename from examples/todomvc/.claude/agents/playwright-test-planner.agent.mdrename to examples/todomvc/.claude/agents/pwt-planner.mdindex 51ca3f36ff..a39464977a 100644--- a/examples/todomvc/.claude/agents/playwright-test-planner.agent.md+++ b/examples/todomvc/.claude/agents/pwt-planner.md@@ -1,7 +1,7 @@----name: playwright-test-planner-description: Use this agent when you need to create comprehensive test plan for a web application or website. Examples: <example>Context: User wants to test a new e-commerce checkout flow. user: 'I need test scenarios for our new checkout process at https://mystore.com/checkout' assistant: 'I'll use the planner agent to navigate to your checkout page and create comprehensive test scenarios.' <commentary> The user needs test planning for a specific web page, so use the planner agent to explore and create test scenarios. </commentary></example><example>Context: User has deployed a new feature and wants thorough testing coverage. user: 'Can you help me test our new user dashboard at https://app.example.com/dashboard?' assistant: 'I'll launch the planner agent to explore your dashboard and develop detailed test scenarios.' <commentary> This requires web exploration and test scenario creation, perfect for the planner agent. </commentary></example>-tools: Read, Glob, Grep, Write, mcp__playwright-test__browser_click, mcp__playwright-test__browser_close, mcp__playwright-test__browser_console_messages, mcp__playwright-test__browser_drag, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_file_upload, mcp__playwright-test__browser_handle_dialog, mcp__playwright-test__browser_hover, mcp__playwright-test__browser_navigate, mcp__playwright-test__browser_navigate_back, mcp__playwright-test__browser_network_requests, mcp__playwright-test__browser_press_key, mcp__playwright-test__browser_select_option, mcp__playwright-test__browser_snapshot, mcp__playwright-test__browser_take_screenshot, mcp__playwright-test__browser_type, mcp__playwright-test__browser_wait_for, mcp__playwright-test__planner_setup_page+name: pwt-planner+description: Use this agent when you need to create comprehensive test plan for a web application or website.+tools: Glob, Grep, Read, Edit, MultiEdit, Write, mcp__playwright-test__browser_click, mcp__playwright-test__browser_close, mcp__playwright-test__browser_console_messages, mcp__playwright-test__browser_drag, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_file_upload, mcp__playwright-test__browser_handle_dialog, mcp__playwright-test__browser_hover, mcp__playwright-test__browser_navigate, mcp__playwright-test__browser_navigate_back, mcp__playwright-test__browser_network_requests, mcp__playwright-test__browser_press_key, mcp__playwright-test__browser_select_option, mcp__playwright-test__browser_snapshot, mcp__playwright-test__browser_take_screenshot, mcp__playwright-test__browser_type, mcp__playwright-test__browser_wait_for, mcp__playwright-test__planner_setup_pagemodel: sonnetcolor: green---diff --git a/examples/todomvc/.github/prompts/test-coverage.prompt.md b/examples/todomvc/.claude/prompts/pwt-coverage.mdsimilarity index 85%rename from examples/todomvc/.github/prompts/test-coverage.prompt.mdrename to examples/todomvc/.claude/prompts/pwt-coverage.mdindex 4cc7675436..04e4f811fb 100644--- a/examples/todomvc/.github/prompts/test-coverage.prompt.md+++ b/examples/todomvc/.claude/prompts/pwt-coverage.md@@ -1,5 +1,5 @@----mode: agent+agent: defaultdescription: Produce test coverage---@@ -8,7 +8,7 @@ Parameters:- Seed file (optional): the seed file to use, defaults to `tests/seed.spec.ts`- Test plan file (optional): the test plan file to write, under `specs/` folder.-1. Call #π planner subagent with prompt:+1. Call #pwt-planner subagent with prompt:<plan><task-text><!-- the task --></task-text>@@ -16,7 +16,7 @@ Parameters:<plan-file><!-- path to test plan file to generate --></plan-file></plan>-2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #π generator subagent with prompt:+2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #pwt-generator subagent with prompt:<generate><test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite>@@ -26,6 +26,6 @@ Parameters:<body><!-- Test case content including steps and expectations --></body></generate>-3. Call #π healer subagent with prompt:+3. Call #pwt-healer subagent with prompt:<heal>Run all tests and fix the failing ones one after another.</heal>diff --git a/examples/todomvc/.github/prompts/test-generate.prompt.md b/examples/todomvc/.claude/prompts/pwt-generate.mdsimilarity index 87%rename from examples/todomvc/.github/prompts/test-generate.prompt.mdrename to examples/todomvc/.claude/prompts/pwt-generate.mdindex 1de2430f2d..b92662678c 100644--- a/examples/todomvc/.github/prompts/test-generate.prompt.md+++ b/examples/todomvc/.claude/prompts/pwt-generate.md@@ -1,5 +1,5 @@----mode: π generator+agent: pwt-generatordescription: Generate test plan---diff --git a/examples/todomvc/.github/prompts/test-heal.prompt.md b/examples/todomvc/.claude/prompts/pwt-heal.mdsimilarity index 80%rename from examples/todomvc/.github/prompts/test-heal.prompt.mdrename to examples/todomvc/.claude/prompts/pwt-heal.mdindex 6f4f720e65..2fb1bc63ce 100644--- a/examples/todomvc/.github/prompts/test-heal.prompt.md+++ b/examples/todomvc/.claude/prompts/pwt-heal.md@@ -1,5 +1,5 @@----mode: π healer+agent: pwt-healerdescription: Fix tests---diff --git a/examples/todomvc/.github/prompts/test-plan.prompt.md b/examples/todomvc/.claude/prompts/pwt-plan.mdsimilarity index 90%rename from examples/todomvc/.github/prompts/test-plan.prompt.mdrename to examples/todomvc/.claude/prompts/pwt-plan.mdindex babb1c5f9f..32452abcd5 100644--- a/examples/todomvc/.github/prompts/test-plan.prompt.md+++ b/examples/todomvc/.claude/prompts/pwt-plan.md@@ -1,5 +1,5 @@----mode: π planner+agent: pwt-plannerdescription: Create test plan---diff --git "a/examples/todomvc/.github/chatmodes/\360\237\216\255 generator.chatmode.md" b/examples/todomvc/.github/agents/pwt-generator.agent.mdsimilarity index 51%rename from "examples/todomvc/.github/chatmodes/\360\237\216\255 generator.chatmode.md"rename to examples/todomvc/.github/agents/pwt-generator.agent.mdindex 6ada1226f4..71160e9324 100644--- "a/examples/todomvc/.github/chatmodes/\360\237\216\255 generator.chatmode.md"+++ b/examples/todomvc/.github/agents/pwt-generator.agent.md@@ -1,6 +1,28 @@----description: Use this agent when you need to create automated browser tests using Playwright.-tools: ['search/fileSearch', 'search/textSearch', 'search/listDirectory', 'search/readFile', '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', 'playwright-test/generator_write_test']+name: pwt-generator+description: Use this agent when you need to create automated browser tests using Playwright. Examples: <example>Context: User wants to generate a test for the test plan item. <test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite> <test-name><!-- Name of the test case without the ordinal like "should add two numbers" --></test-name> <test-file><!-- Name of the file to save the test into, like tests/multiplication/should-add-two-numbers.spec.ts --></test-file> <seed-file><!-- Seed file path from test plan --></seed-file> <body><!-- Test case content including steps and expectations --></body></example>+tools:+ - search+ - 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+ - playwright-test/generator_write_test+model: Claude Sonnet 4---You are a Playwright Test Generator, an expert in browser automation and end-to-end testing.@@ -54,5 +76,3 @@ application behavior.});```</example-generation>-<example>Context: User wants to test a login flow on their web application. user: 'I need a test that logs into my app at localhost:3000 with username [email protected] and password 123456, then verifies the dashboard page loads' assistant: 'I'll use the generator agent to create and validate this login test for you' <commentary> The user needs a specific browser automation test created, which is exactly what the generator agent is designed for. </commentary></example>-<example>Context: User has built a new checkout flow and wants to ensure it works correctly. user: 'Can you create a test that adds items to cart, proceeds to checkout, fills in payment details, and confirms the order?' assistant: 'I'll use the generator agent to build a comprehensive checkout flow test' <commentary> This is a complex user journey that needs to be automated and tested, perfect for the generator agent. </commentary></example>\ No newline at end of filediff --git "a/examples/todomvc/.github/chatmodes/\360\237\216\255 healer.chatmode.md" b/examples/todomvc/.github/agents/pwt-healer.agent.mdsimilarity index 66%rename from "examples/todomvc/.github/chatmodes/\360\237\216\255 healer.chatmode.md"rename to examples/todomvc/.github/agents/pwt-healer.agent.mdindex 936786a7cc..3c6eb6974f 100644--- "a/examples/todomvc/.github/chatmodes/\360\237\216\255 healer.chatmode.md"+++ b/examples/todomvc/.github/agents/pwt-healer.agent.md@@ -1,6 +1,18 @@---+name: pwt-healerdescription: Use this agent when you need to debug and fix failing Playwright tests.-tools: ['edit/createFile', 'edit/createDirectory', 'edit/editFiles', 'search/fileSearch', 'search/textSearch', 'search/listDirectory', 'search/readFile', 'playwright-test/browser_console_messages', 'playwright-test/browser_evaluate', 'playwright-test/browser_generate_locator', 'playwright-test/browser_network_requests', 'playwright-test/browser_snapshot', 'playwright-test/test_debug', 'playwright-test/test_list', 'playwright-test/test_run']+tools:+ - search+ - edit+ - playwright-test/browser_console_messages+ - playwright-test/browser_evaluate+ - playwright-test/browser_generate_locator+ - playwright-test/browser_network_requests+ - playwright-test/browser_snapshot+ - playwright-test/test_debug+ - playwright-test/test_list+ - playwright-test/test_run+model: Claude Sonnet 4---You are the Playwright Test Healer, an expert test automation engineer specializing in debugging and@@ -40,5 +52,3 @@ Key principles:of the expected behavior.- Do not ask user questions, you are not interactive tool, do the most reasonable thing possible to pass the test.- Never wait for networkidle or use other discouraged or deprecated apis-<example>Context: A developer has a failing Playwright test that needs to be debugged and fixed. user: 'The login test is failing, can you fix it?' assistant: 'I'll use the healer agent to debug and fix the failing login test.' <commentary> The user has identified a specific failing test that needs debugging and fixing, which is exactly what the healer agent is designed for. </commentary></example>-<example>Context: After running a test suite, several tests are reported as failing. user: 'Test user-registration.spec.ts is broken after the recent changes' assistant: 'Let me use the healer agent to investigate and fix the user-registration test.' <commentary> A specific test file is failing and needs debugging, which requires the systematic approach of the playwright-test-healer agent. </commentary></example>\ No newline at end of filediff --git "a/examples/todomvc/.github/chatmodes/\360\237\216\255 planner.chatmode.md" b/examples/todomvc/.github/agents/pwt-planner.agent.mdsimilarity index 67%rename from "examples/todomvc/.github/chatmodes/\360\237\216\255 planner.chatmode.md"rename to examples/todomvc/.github/agents/pwt-planner.agent.mdindex 6566e79920..29ff84014c 100644--- "a/examples/todomvc/.github/chatmodes/\360\237\216\255 planner.chatmode.md"+++ b/examples/todomvc/.github/agents/pwt-planner.agent.md@@ -1,6 +1,28 @@---+name: pwt-plannerdescription: Use this agent when you need to create comprehensive test plan for a web application or website.-tools: ['edit/createFile', 'edit/createDirectory', 'search/fileSearch', 'search/textSearch', 'search/listDirectory', 'search/readFile', 'playwright-test/browser_click', 'playwright-test/browser_close', 'playwright-test/browser_console_messages', '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_navigate_back', 'playwright-test/browser_network_requests', 'playwright-test/browser_press_key', 'playwright-test/browser_select_option', 'playwright-test/browser_snapshot', 'playwright-test/browser_take_screenshot', 'playwright-test/browser_type', 'playwright-test/browser_wait_for', 'playwright-test/planner_setup_page']+tools:+ - search+ - edit+ - playwright-test/browser_click+ - playwright-test/browser_close+ - playwright-test/browser_console_messages+ - 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_navigate_back+ - playwright-test/browser_network_requests+ - playwright-test/browser_press_key+ - playwright-test/browser_select_option+ - playwright-test/browser_snapshot+ - playwright-test/browser_take_screenshot+ - playwright-test/browser_type+ - playwright-test/browser_wait_for+ - playwright-test/planner_setup_page+model: Claude Sonnet 4---You are an expert web test planner with extensive experience in quality assurance, user experience testing, and test@@ -92,5 +114,3 @@ application features:**Output Format**: Always save the complete test plan as a markdown file with clear headings, numbered steps, andprofessional formatting suitable for sharing with development and QA teams.-<example>Context: User wants to test a new e-commerce checkout flow. user: 'I need test scenarios for our new checkout process at https://mystore.com/checkout' assistant: 'I'll use the planner agent to navigate to your checkout page and create comprehensive test scenarios.' <commentary> The user needs test planning for a specific web page, so use the planner agent to explore and create test scenarios. </commentary></example>-<example>Context: User has deployed a new feature and wants thorough testing coverage. user: 'Can you help me test our new user dashboard at https://app.example.com/dashboard?' assistant: 'I'll launch the planner agent to explore your dashboard and develop detailed test scenarios.' <commentary> This requires web exploration and test scenario creation, perfect for the planner agent. </commentary></example>\ No newline at end of filediff --git a/examples/todomvc/.claude/prompts/test-coverage.prompt.md b/examples/todomvc/.github/prompts/pwt-coverage.prompt.mdsimilarity index 83%rename from examples/todomvc/.claude/prompts/test-coverage.prompt.mdrename to examples/todomvc/.github/prompts/pwt-coverage.prompt.mdindex 87146948e1..7fd4491384 100644--- a/examples/todomvc/.claude/prompts/test-coverage.prompt.md+++ b/examples/todomvc/.github/prompts/pwt-coverage.prompt.md@@ -1,5 +1,5 @@----mode: default+agent: agentdescription: Produce test coverage---@@ -8,7 +8,7 @@ Parameters:- Seed file (optional): the seed file to use, defaults to `tests/seed.spec.ts`- Test plan file (optional): the test plan file to write, under `specs/` folder.-1. Call #playwright-test-planner subagent with prompt:+1. Call #pwt-planner subagent with prompt:<plan><task-text><!-- the task --></task-text>@@ -16,7 +16,7 @@ Parameters:<plan-file><!-- path to test plan file to generate --></plan-file></plan>-2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #playwright-test-generator subagent with prompt:+2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #pwt-generator subagent with prompt:<generate><test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite>@@ -26,6 +26,6 @@ Parameters:<body><!-- Test case content including steps and expectations --></body></generate>-3. Call #playwright-test-healer subagent with prompt:+3. Call #pwt-healer subagent with prompt:<heal>Run all tests and fix the failing ones one after another.</heal>diff --git a/packages/playwright/src/agents/test-generate.prompt.md b/examples/todomvc/.github/prompts/pwt-generate.prompt.mdsimilarity index 85%rename from packages/playwright/src/agents/test-generate.prompt.mdrename to examples/todomvc/.github/prompts/pwt-generate.prompt.mdindex ef4b5cb458..b92662678c 100644--- a/packages/playwright/src/agents/test-generate.prompt.md+++ b/examples/todomvc/.github/prompts/pwt-generate.prompt.md@@ -1,5 +1,5 @@----mode: ${agentGenerator}+agent: pwt-generatordescription: Generate test plan---diff --git a/packages/playwright/src/agents/test-heal.prompt.md b/examples/todomvc/.github/prompts/pwt-heal.prompt.mdsimilarity index 78%rename from packages/playwright/src/agents/test-heal.prompt.mdrename to examples/todomvc/.github/prompts/pwt-heal.prompt.mdindex 51a7d3b480..2fb1bc63ce 100644--- a/packages/playwright/src/agents/test-heal.prompt.md+++ b/examples/todomvc/.github/prompts/pwt-heal.prompt.md@@ -1,5 +1,5 @@----mode: ${agentHealer}+agent: pwt-healerdescription: Fix tests---diff --git a/examples/todomvc/.claude/prompts/test-plan.prompt.md b/examples/todomvc/.github/prompts/pwt-plan.prompt.mdsimilarity index 85%rename from examples/todomvc/.claude/prompts/test-plan.prompt.mdrename to examples/todomvc/.github/prompts/pwt-plan.prompt.mdindex 7f0129ca40..32452abcd5 100644--- a/examples/todomvc/.claude/prompts/test-plan.prompt.md+++ b/examples/todomvc/.github/prompts/pwt-plan.prompt.md@@ -1,5 +1,5 @@----mode: playwright-test-planner+agent: pwt-plannerdescription: Create test plan---diff --git a/packages/playwright/src/agents/generateAgents.ts b/packages/playwright/src/agents/generateAgents.tsindex c291c741a5..161c3710fd 100644--- a/packages/playwright/src/agents/generateAgents.ts+++ b/packages/playwright/src/agents/generateAgents.ts@@ -32,7 +32,6 @@ interface AgentHeader {}interface Agent {- source: string;header: AgentHeader;instructions: string;examples: string[];@@ -50,7 +49,7 @@ class AgentParser {const source = await fs.promises.readFile(filePath, 'utf-8');const { header, content } = this.extractYamlAndContent(source);const { instructions, examples } = this.extractInstructionsAndExamples(content);- return { source, header, instructions, examples };+ return { header, instructions, examples };}static extractYamlAndContent(markdown: string): { header: AgentHeader; content: string } {@@ -108,16 +107,20 @@ class AgentParser {}export class ClaudeGenerator {- static async init(config: FullConfigInternal, projectName: string) {+ static async init(config: FullConfigInternal, projectName: string, prompts: boolean) {await initRepo(config, projectName, {- promptsFolder: '.claude/prompts',+ promptsFolder: prompts ? '.claude/prompts' : undefined,});const agents = await AgentParser.loadAgents();await fs.promises.mkdir('.claude/agents', { recursive: true });for (const agent of agents)- await writeFile(`.claude/agents/${agent.header.name}.agent.md`, ClaudeGenerator.agentSpec(agent), 'π€', 'agent definition');+ await writeFile(`.claude/agents/${agent.header.name}.md`, ClaudeGenerator.agentSpec(agent), 'π€', 'agent definition');++ await deleteFile(`.claude/agents/playwright-test-planner.md`, 'legacy planner agent');+ await deleteFile(`.claude/agents/playwright-test-generator.md`, 'legacy generator agent');+ await deleteFile(`.claude/agents/playwright-test-healer.md`, 'legacy healer agent');await writeFile('.mcp.json', JSON.stringify({mcpServers: {@@ -133,10 +136,8 @@ export class ClaudeGenerator {static agentSpec(agent: Agent): string {const claudeToolMap = new Map<string, string[]>([- ['search', ['Glob', 'Grep']],- ['read', ['Read']],- ['edit', ['Edit', 'MultiEdit']],- ['write', ['Write']],+ ['search', ['Glob', 'Grep', 'Read']],+ ['edit', ['Edit', 'MultiEdit', 'Write']],]);function asClaudeTool(tool: string): string {@@ -146,10 +147,11 @@ export class ClaudeGenerator {return `mcp__${first}__${second}`;}+ const examples = agent.examples.length ? ` Examples: ${agent.examples.map(example => `<example>${example}</example>`).join('')}` : '';const lines: string[] = [];lines.push(`---`);lines.push(`name: ${agent.header.name}`);- lines.push(`description: ${agent.header.description}. Examples: ${agent.examples.map(example => `<example>${example}</example>`).join('')}`);+ lines.push(`description: ${agent.header.description}.${examples}`);lines.push(`tools: ${agent.header.tools.map(tool => asClaudeTool(tool)).join(', ')}`);lines.push(`model: ${agent.header.model}`);lines.push(`color: ${agent.header.color}`);@@ -161,10 +163,10 @@ export class ClaudeGenerator {}export class OpencodeGenerator {- static async init(config: FullConfigInternal, projectName: string) {+ static async init(config: FullConfigInternal, projectName: string, prompts: boolean) {await initRepo(config, projectName, {- agentDefault: 'Build',- promptsFolder: '.opencode/prompts'+ defaultAgentName: 'Build',+ promptsFolder: prompts ? '.opencode/prompts' : undefined});const agents = await AgentParser.loadAgents();@@ -173,8 +175,13 @@ export class OpencodeGenerator {const prompt = [agent.instructions];prompt.push('');prompt.push(...agent.examples.map(example => `<example>${example}</example>`));- await writeFile(`.opencode/prompts/${agent.header.name}.agent.md`, prompt.join('\n'), 'π€', 'agent definition');+ await writeFile(`.opencode/prompts/${agent.header.name}.md`, prompt.join('\n'), 'π€', 'agent definition');}++ await deleteFile(`.opencode/prompts/playwright-test-planner.md`, 'legacy planner agent');+ await deleteFile(`.opencode/prompts/playwright-test-generator.md`, 'legacy generator agent');+ await deleteFile(`.opencode/prompts/playwright-test-healer.md`, 'legacy healer agent');+await writeFile('opencode.json', OpencodeGenerator.configuration(agents), 'π§', 'opencode configuration');initRepoDone();@@ -182,10 +189,8 @@ export class OpencodeGenerator {static configuration(agents: Agent[]): string {const opencodeToolMap = new Map<string, string[]>([- ['search', ['ls', 'glob', 'grep']],- ['read', ['read']],- ['edit', ['edit']],- ['write', ['write']],+ ['search', ['ls', 'glob', 'grep', 'read']],+ ['edit', ['edit', 'write']],]);const asOpencodeTool = (tools: Record<string, boolean>, tool: string) => {@@ -210,7 +215,7 @@ export class OpencodeGenerator {result['agent'][agent.header.name] = {description: agent.header.description,mode: 'subagent',- prompt: `{file:.opencode/prompts/${agent.header.name}.agent.md}`,+ prompt: `{file:.opencode/prompts/${agent.header.name}.md}`,tools,};for (const tool of agent.header.tools)@@ -226,69 +231,69 @@ export class OpencodeGenerator {return JSON.stringify(result, null, 2);}}-export class AgentGenerator {- static async init(config: FullConfigInternal, projectName: string) {- const agentsFolder = process.env.AGENTS_FOLDER;- if (!agentsFolder) {- console.error('AGENTS_FOLDER environment variable is not set');- return;- }+export class CopilotGenerator {+ static async init(config: FullConfigInternal, projectName: string, prompts: boolean) {await initRepo(config, projectName, {- promptsFolder: path.join(agentsFolder, 'prompts')+ defaultAgentName: 'agent',+ promptsFolder: prompts ? '.github/prompts' : undefined,+ promptSuffix: 'prompt'});const agents = await AgentParser.loadAgents();- await fs.promises.mkdir(agentsFolder, { recursive: true });+ await fs.promises.mkdir('.github/agents', { recursive: true });for (const agent of agents)- await writeFile(`${agentsFolder}/agents/${agent.header.name}.md`, agent.source, 'π€', 'agent definition');+ await writeFile(`.github/agents/${agent.header.name}.agent.md`, CopilotGenerator.agentSpec(agent), 'π€', 'agent definition');- console.log('π§ MCP configuration');- console.log(JSON.stringify({- mcpServers: {- 'playwright-test': {- type: 'stdio',- command: 'npx',- args: [- `--prefix=${path.resolve(process.cwd())}`,- 'playwright',- 'run-test-mcp-server',- `--headless`,- `--config=${path.resolve(process.cwd())}`,- ],- tools: ['*']- }- }- }, null, 2));+ await deleteFile(`.github/chatmodes/ π planner.chatmode.md`, 'legacy planner chatmode');+ await deleteFile(`.github/chatmodes/π generator.chatmode.md`, 'legacy generator chatmode');+ await deleteFile(`.github/chatmodes/π healer.chatmode.md`, 'legacy healer chatmode');++ await VSCodeGenerator.appendToMCPJson();initRepoDone();}++ static agentSpec(agent: Agent): string {+ const examples = agent.examples.length ? ` Examples: ${agent.examples.map(example => `<example>${example}</example>`).join('')}` : '';+ const lines: string[] = [];+ lines.push(`---`);+ lines.push(`name: ${agent.header.name}`);+ lines.push(`description: ${agent.header.description}.${examples}`);+ lines.push(`tools:\n${agent.header.tools.map(tool => ` - ${tool}`).join('\n')}`);+ lines.push(`model: Claude Sonnet 4`);+ lines.push(`---`);+ lines.push('');+ lines.push(agent.instructions);+ lines.push('');+ return lines.join('\n');+ }}export class VSCodeGenerator {static async init(config: FullConfigInternal, projectName: string) {await initRepo(config, projectName, {- agentDefault: 'agent',- agentHealer: 'π healer',- agentGenerator: 'π generator',- agentPlanner: 'π planner',- promptsFolder: '.github/prompts'+ promptsFolder: undefined});const agents = await AgentParser.loadAgents();const nameMap = new Map<string, string>([- ['playwright-test-planner', 'π planner'],+ ['playwright-test-planner', ' π planner'],['playwright-test-generator', 'π generator'],['playwright-test-healer', 'π healer'],]);- await deleteFile(`.github/chatmodes/ π planner.chatmode.md`, 'old planner chatmode');-await fs.promises.mkdir('.github/chatmodes', { recursive: true });for (const agent of agents)await writeFile(`.github/chatmodes/${nameMap.get(agent.header.name)}.chatmode.md`, VSCodeGenerator.agentSpec(agent), 'π€', 'chatmode definition');+ await VSCodeGenerator.appendToMCPJson();++ initRepoDone();+ }++ static async appendToMCPJson() {await fs.promises.mkdir('.vscode', { recursive: true });const mcpJsonPath = '.vscode/mcp.json';@@ -310,8 +315,6 @@ export class VSCodeGenerator {args: ['playwright', 'run-test-mcp-server'],};await writeFile(mcpJsonPath, JSON.stringify(mcpJson, null, 2), 'π§', 'mcp configuration');-- initRepoDone();}static agentSpec(agent: Agent): string {@@ -353,6 +356,7 @@ export class VSCodeGenerator {for (const example of agent.examples)lines.push(`<example>${example}</example>`);+ lines.push('');return lines.join('\n');}}@@ -376,16 +380,14 @@ async function deleteFile(filePath: string, description: string) {}type RepoParams = {- promptsFolder: string;- agentDefault?: string;- agentHealer?: string;- agentGenerator?: string;- agentPlanner?: string;+ promptsFolder?: string;+ promptSuffix?: string;+ defaultAgentName?: string;};async function initRepo(config: FullConfigInternal, projectName: string, options: RepoParams) {const project = seedProject(config, projectName);- console.log(`π Using project "${project.project.name}" as a primary project`);+ console.log(`- π Using project "${project.project.name}" as a primary project`);if (!fs.existsSync('specs')) {await fs.promises.mkdir('specs');@@ -401,13 +403,21 @@ This is a directory for test plans.await writeFile(seedFile, seedFileContent, 'π±', 'default environment seed file');}- await fs.promises.mkdir(options.promptsFolder, { recursive: true });-- for (const promptFile of await fs.promises.readdir(__dirname)) {- if (!promptFile.endsWith('.prompt.md'))- continue;- const content = await loadPrompt(promptFile, { ...options, seedFile: path.relative(process.cwd(), seedFile) });- await writeFile(path.join(options.promptsFolder, promptFile), content, 'π', 'prompt template');+ if (options.promptsFolder) {+ await fs.promises.mkdir(options.promptsFolder, { recursive: true });++ for (const promptFile of await fs.promises.readdir(__dirname)) {+ if (!promptFile.endsWith('.prompt.md'))+ continue;+ const shortName = promptFile.replace('.prompt.md', '');+ const fileName = options.promptSuffix ? `${shortName}.${options.promptSuffix}.md` : `${shortName}.md`;+ const content = await loadPrompt(promptFile, {+ defaultAgentName: 'default',+ ...options,+ seedFile: path.relative(process.cwd(), seedFile)+ });+ await writeFile(path.join(options.promptsFolder, fileName), content, 'π', 'prompt template');+ }}}@@ -416,16 +426,8 @@ function initRepoDone() {}async function loadPrompt(file: string, params: Record<string, string>) {- const templateParams = {- agentDefault: params.agentDefault ?? 'default',- agentHealer: params.agentHealer ?? 'playwright-test-healer',- agentGenerator: params.agentGenerator ?? 'playwright-test-generator',- agentPlanner: params.agentPlanner ?? 'playwright-test-planner',- seedFile: params.seedFile,- };-const content = await fs.promises.readFile(path.join(__dirname, file), 'utf-8');- return Object.entries(templateParams).reduce((acc, [key, value]) => {+ return Object.entries(params).reduce((acc, [key, value]) => {return acc.replace(new RegExp(`\\\${${key}}`, 'g'), value);}, content);}diff --git a/packages/playwright/src/agents/test-coverage.prompt.md b/packages/playwright/src/agents/pwt-coverage.prompt.mdsimilarity index 84%rename from packages/playwright/src/agents/test-coverage.prompt.mdrename to packages/playwright/src/agents/pwt-coverage.prompt.mdindex 12923b36ac..b207d398d5 100644--- a/packages/playwright/src/agents/test-coverage.prompt.md+++ b/packages/playwright/src/agents/pwt-coverage.prompt.md@@ -1,5 +1,5 @@----mode: ${agentDefault}+agent: ${defaultAgentName}description: Produce test coverage---@@ -8,7 +8,7 @@ Parameters:- Seed file (optional): the seed file to use, defaults to `${seedFile}`- Test plan file (optional): the test plan file to write, under `specs/` folder.-1. Call #${agentPlanner} subagent with prompt:+1. Call #pwt-planner subagent with prompt:<plan><task-text><!-- the task --></task-text>@@ -16,7 +16,7 @@ Parameters:<plan-file><!-- path to test plan file to generate --></plan-file></plan>-2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #${agentGenerator} subagent with prompt:+2. For each test case from the test plan file (1.1, 1.2, ...), one after another, not in parallel, call #pwt-generator subagent with prompt:<generate><test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite>@@ -26,6 +26,6 @@ Parameters:<body><!-- Test case content including steps and expectations --></body></generate>-3. Call #${agentHealer} subagent with prompt:+3. Call #pwt-healer subagent with prompt:<heal>Run all tests and fix the failing ones one after another.</heal>diff --git a/examples/todomvc/.claude/prompts/test-generate.prompt.md b/packages/playwright/src/agents/pwt-generate.prompt.mdsimilarity index 81%rename from examples/todomvc/.claude/prompts/test-generate.prompt.mdrename to packages/playwright/src/agents/pwt-generate.prompt.mdindex d50dcd3505..b92662678c 100644--- a/examples/todomvc/.claude/prompts/test-generate.prompt.md+++ b/packages/playwright/src/agents/pwt-generate.prompt.md@@ -1,5 +1,5 @@----mode: playwright-test-generator+agent: pwt-generatordescription: Generate test plan---diff --git a/packages/playwright/src/agents/generator.agent.md b/packages/playwright/src/agents/pwt-generator.agent.mdsimilarity index 73%rename from packages/playwright/src/agents/generator.agent.mdrename to packages/playwright/src/agents/pwt-generator.agent.mdindex 4a313bf56d..4956063a10 100644--- a/packages/playwright/src/agents/generator.agent.md+++ b/packages/playwright/src/agents/pwt-generator.agent.md@@ -1,10 +1,9 @@----name: playwright-test-generator+name: pwt-generatordescription: Use this agent when you need to create automated browser tests using Playwrightmodel: sonnetcolor: bluetools:- - read- search- playwright-test/browser_click- playwright-test/browser_drag@@ -80,22 +79,10 @@ application behavior.</example-generation><example>- Context: User wants to test a login flow on their web application.- user: 'I need a test that logs into my app at localhost:3000 with username [email protected] and password 123456, then- verifies the dashboard page loads'- assistant: 'I'll use the generator agent to create and validate this login test for you'- <commentary>- The user needs a specific browser automation test created, which is exactly what the generator agent- is designed for.- </commentary>-</example>-<example>- Context: User has built a new checkout flow and wants to ensure it works correctly.- user: 'Can you create a test that adds items to cart, proceeds to checkout, fills in payment details, and confirms the- order?'- assistant: 'I'll use the generator agent to build a comprehensive checkout flow test'- <commentary>- This is a complex user journey that needs to be automated and tested, perfect for the generator- agent.- </commentary>+ Context: User wants to generate a test for the test plan item.+ <test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite>+ <test-name><!-- Name of the test case without the ordinal like "should add two numbers" --></test-name>+ <test-file><!-- Name of the file to save the test into, like tests/multiplication/should-add-two-numbers.spec.ts --></test-file>+ <seed-file><!-- Seed file path from test plan --></seed-file>+ <body><!-- Test case content including steps and expectations --></body></example>diff --git a/examples/todomvc/.claude/prompts/test-heal.prompt.md b/packages/playwright/src/agents/pwt-heal.prompt.mdsimilarity index 72%rename from examples/todomvc/.claude/prompts/test-heal.prompt.mdrename to packages/playwright/src/agents/pwt-heal.prompt.mdindex c4b526deb7..2fb1bc63ce 100644--- a/examples/todomvc/.claude/prompts/test-heal.prompt.md+++ b/packages/playwright/src/agents/pwt-heal.prompt.md@@ -1,5 +1,5 @@----mode: playwright-test-healer+agent: pwt-healerdescription: Fix tests---diff --git a/packages/playwright/src/agents/healer.agent.md b/packages/playwright/src/agents/pwt-healer.agent.mdsimilarity index 75%rename from packages/playwright/src/agents/healer.agent.mdrename to packages/playwright/src/agents/pwt-healer.agent.mdindex 92e08e86fd..dd1b3a103b 100644--- a/packages/playwright/src/agents/healer.agent.md+++ b/packages/playwright/src/agents/pwt-healer.agent.md@@ -1,12 +1,10 @@----name: playwright-test-healer+name: pwt-healerdescription: Use this agent when you need to debug and fix failing Playwright testsmodel: sonnetcolor: redtools:- - read- search- - write- edit- playwright-test/browser_console_messages- playwright-test/browser_evaluate@@ -55,23 +53,3 @@ Key principles:of the expected behavior.- Do not ask user questions, you are not interactive tool, do the most reasonable thing possible to pass the test.- Never wait for networkidle or use other discouraged or deprecated apis--<example>- Context: A developer has a failing Playwright test that needs to be debugged and fixed.- user: 'The login test is failing, can you fix it?'- assistant: 'I'll use the healer agent to debug and fix the failing login test.'- <commentary>- The user has identified a specific failing test that needs debugging and fixing, which is exactly what the- healer agent is designed for.- </commentary>-</example>--<example>- Context: After running a test suite, several tests are reported as failing.- user: 'Test user-registration.spec.ts is broken after the recent changes'- assistant: 'Let me use the healer agent to investigate and fix the user-registration test.'- <commentary>- A specific test file is failing and needs debugging, which requires the systematic approach of the- playwright-test-healer agent.- </commentary>-</example>diff --git a/packages/playwright/src/agents/test-plan.prompt.md b/packages/playwright/src/agents/pwt-plan.prompt.mdsimilarity index 88%rename from packages/playwright/src/agents/test-plan.prompt.mdrename to packages/playwright/src/agents/pwt-plan.prompt.mdindex b852859045..5fa1a6ad29 100644--- a/packages/playwright/src/agents/test-plan.prompt.md+++ b/packages/playwright/src/agents/pwt-plan.prompt.md@@ -1,5 +1,5 @@----mode: ${agentPlanner}+agent: pwt-plannerdescription: Create test plan---diff --git a/packages/playwright/src/agents/planner.agent.md b/packages/playwright/src/agents/pwt-planner.agent.mdsimilarity index 81%rename from packages/playwright/src/agents/planner.agent.mdrename to packages/playwright/src/agents/pwt-planner.agent.mdindex cbc350ec7d..08a2231b98 100644--- a/packages/playwright/src/agents/planner.agent.md+++ b/packages/playwright/src/agents/pwt-planner.agent.md@@ -1,12 +1,11 @@----name: playwright-test-planner+name: pwt-plannerdescription: Use this agent when you need to create comprehensive test plan for a web application or websitemodel: sonnetcolor: greentools:- - read- search- - write+ - edit- playwright-test/browser_click- playwright-test/browser_close- playwright-test/browser_console_messages@@ -116,23 +115,3 @@ application features:**Output Format**: Always save the complete test plan as a markdown file with clear headings, numbered steps, andprofessional formatting suitable for sharing with development and QA teams.--<example>- Context: User wants to test a new e-commerce checkout flow.- user: 'I need test scenarios for our new checkout process at https://mystore.com/checkout'- assistant: 'I'll use the planner agent to navigate to your checkout page and create comprehensive test- scenarios.'- <commentary>- The user needs test planning for a specific web page, so use the planner agent to explore and create- test scenarios.- </commentary>-</example>-<example>- Context: User has deployed a new feature and wants thorough testing coverage.- user: 'Can you help me test our new user dashboard at https://app.example.com/dashboard?'- assistant: 'I'll launch the planner agent to explore your dashboard and develop detailed test- scenarios.'- <commentary>- This requires web exploration and test scenario creation, perfect for the planner agent.- </commentary>-</example>diff --git a/packages/playwright/src/program.ts b/packages/playwright/src/program.tsindex 707550c15a..22260277c7 100644--- a/packages/playwright/src/program.ts+++ b/packages/playwright/src/program.ts@@ -37,7 +37,7 @@ import { ServerBackendFactory, runMainBackend } from './mcp/sdk/exports';import { TestServerBackend } from './mcp/test/testBackend';import { decorateCommand } from './mcp/program';import { setupExitWatchdog } from './mcp/browser/watchdog';-import { ClaudeGenerator, OpencodeGenerator, VSCodeGenerator, AgentGenerator } from './agents/generateAgents';+import { ClaudeGenerator, OpencodeGenerator, VSCodeGenerator, CopilotGenerator } from './agents/generateAgents';import type { ConfigCLIOverrides } from './common/ipc';import type { TraceMode } from '../types/test';@@ -183,22 +183,21 @@ function addInitAgentsCommand(program: Command) {const command = program.command('init-agents');command.description('Initialize repository agents');const option = command.createOption('--loop <loop>', 'Agentic loop provider');- option.choices(['vscode', 'claude', 'opencode', 'generic']);+ option.choices(['claude', 'copilot', 'opencode', 'vscode', 'vscode-legacy']);command.addOption(option);command.option('-c, --config <file>', `Configuration file to find a project to use for seed test`);command.option('--project <project>', 'Project to use for seed test');+ command.option('--prompts', 'Whether to include prompts in the agent initialization');command.action(async opts => {const config = await loadConfigFromFile(opts.config);if (opts.loop === 'opencode') {- await OpencodeGenerator.init(config, opts.project);- } else if (opts.loop === 'vscode') {+ await OpencodeGenerator.init(config, opts.project, opts.prompts);+ } else if (opts.loop === 'vscode-legacy') {await VSCodeGenerator.init(config, opts.project);} else if (opts.loop === 'claude') {- await ClaudeGenerator.init(config, opts.project);- } else if (opts.loop === 'generic') {- await AgentGenerator.init(config, opts.project);+ await ClaudeGenerator.init(config, opts.project, opts.prompts);} else {- command.help();+ await CopilotGenerator.init(config, opts.project, opts.prompts);return;}});diff --git a/tests/mcp/init-agents.spec.ts b/tests/mcp/init-agents.spec.tsindex e2d09e3a97..5bfdb117a7 100644--- a/tests/mcp/init-agents.spec.ts+++ b/tests/mcp/init-agents.spec.ts@@ -72,76 +72,3 @@ test('create seed file with --config', async ({ }) => {});expect(fs.existsSync(path.join(baseDir, 'custom', 'bar', 'e2e', 'seed.spec.ts'))).toBe(true);});--async function ensureFiles(baseDir: string, files: string[]) {- for (const file of files)- expect(fs.existsSync(path.join(baseDir, file))).toBe(true);-}--test('init claude agents', async ({ }) => {- const baseDir = await writeFiles({- 'playwright.config.ts': `- module.exports = {};- `,- });-- await runInitAgents({- cwd: baseDir,- args: ['--loop', 'claude'],- });- await ensureFiles(baseDir, [- '.claude/agents/playwright-test-planner.agent.md',- '.claude/agents/playwright-test-generator.agent.md',- '.claude/agents/playwright-test-healer.agent.md',- '.claude/prompts/test-coverage.prompt.md',- '.claude/prompts/test-plan.prompt.md',- '.claude/prompts/test-generate.prompt.md',- '.claude/prompts/test-heal.prompt.md',- ]);-});--test('init vscode agents', async ({ }) => {- const baseDir = await writeFiles({- 'playwright.config.ts': `- module.exports = {};- `,- });-- await runInitAgents({- cwd: baseDir,- args: ['--loop', 'vscode'],- });-- await ensureFiles(baseDir, [- '.github/chatmodes/π generator.chatmode.md',- '.github/chatmodes/π planner.chatmode.md',- '.github/chatmodes/π healer.chatmode.md',- '.github/prompts/test-plan.prompt.md',- '.github/prompts/test-generate.prompt.md',- '.github/prompts/test-heal.prompt.md',- '.vscode/mcp.json',- ]);-});--test('init opencode agents', async ({ }) => {- const baseDir = await writeFiles({- 'playwright.config.ts': `- module.exports = {};- `,- });-- await runInitAgents({- cwd: baseDir,- args: ['--loop', 'opencode'],- });-- await ensureFiles(baseDir, [- '.opencode/prompts/playwright-test-planner.agent.md',- '.opencode/prompts/playwright-test-generator.agent.md',- '.opencode/prompts/playwright-test-healer.agent.md',- '.opencode/prompts/test-plan.prompt.md',- '.opencode/prompts/test-generate.prompt.md',- '.opencode/prompts/test-heal.prompt.md',- 'opencode.json',- ]);-});