feat: Geutebruck GeViScope/GeViSoft Action Mapping System - MVP

This MVP release provides a complete full-stack solution for managing action mappings
in Geutebruck's GeViScope and GeViSoft video surveillance systems.

## Features

### Flutter Web Application (Port 8081)
- Modern, responsive UI for managing action mappings
- Action picker dialog with full parameter configuration
- Support for both GSC (GeViScope) and G-Core server actions
- Consistent UI for input and output actions with edit/delete capabilities
- Real-time action mapping creation, editing, and deletion
- Server categorization (GSC: prefix for GeViScope, G-Core: prefix for G-Core servers)

### FastAPI REST Backend (Port 8000)
- RESTful API for action mapping CRUD operations
- Action template service with comprehensive action catalog (247 actions)
- Server management (G-Core and GeViScope servers)
- Configuration tree reading and writing
- JWT authentication with role-based access control
- PostgreSQL database integration

### C# SDK Bridge (gRPC, Port 50051)
- Native integration with GeViSoft SDK (GeViProcAPINET_4_0.dll)
- Action mapping creation with correct binary format
- Support for GSC and G-Core action types
- Proper Camera parameter inclusion in action strings (fixes CrossSwitch bug)
- Action ID lookup table with server-specific action IDs
- Configuration reading/writing via SetupClient

## Bug Fixes
- **CrossSwitch Bug**: GSC and G-Core actions now correctly display camera/PTZ head parameters in GeViSet
- Action strings now include Camera parameter: `@ PanLeft (Comment: "", Camera: 101028)`
- Proper filter flags and VideoInput=0 for action mappings
- Correct action ID assignment (4198 for GSC, 9294 for G-Core PanLeft)

## Technical Stack
- **Frontend**: Flutter Web, Dart, Dio HTTP client
- **Backend**: Python FastAPI, PostgreSQL, Redis
- **SDK Bridge**: C# .NET 8.0, gRPC, GeViSoft SDK
- **Authentication**: JWT tokens
- **Configuration**: GeViSoft .set files (binary format)

## Credentials
- GeViSoft/GeViScope: username=sysadmin, password=masterkey
- Default admin: username=admin, password=admin123

## Deployment
All services run on localhost:
- Flutter Web: http://localhost:8081
- FastAPI: http://localhost:8000
- SDK Bridge gRPC: localhost:50051
- GeViServer: localhost (default port)

Generated with Claude Code (https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

.playwright-mcp/node_modules/playwright/lib/agents/copilot-setup-steps.yml

@@ -0,0 +1,34 @@
+name: "Copilot Setup Steps"
+
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - .github/workflows/copilot-setup-steps.yml
+  pull_request:
+    paths:
+      - .github/workflows/copilot-setup-steps.yml
+
+jobs:
+  copilot-setup-steps:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - uses: actions/setup-node@v4
+      with:
+        node-version: lts/*
+
+    - name: Install dependencies
+      run: npm ci
+
+    - name: Install Playwright Browsers
+      run: npx playwright install --with-deps
+
+    # Customize this step as needed
+    - name: Build application
+      run: npx run build

.playwright-mcp/node_modules/playwright/lib/agents/generateAgents.js

@@ -0,0 +1,395 @@
+"use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+var generateAgents_exports = {};
+__export(generateAgents_exports, {
+  ClaudeGenerator: () => ClaudeGenerator,
+  CopilotGenerator: () => CopilotGenerator,
+  OpencodeGenerator: () => OpencodeGenerator,
+  VSCodeGenerator: () => VSCodeGenerator
+});
+module.exports = __toCommonJS(generateAgents_exports);
+var import_fs = __toESM(require("fs"));
+var import_path = __toESM(require("path"));
+var import_utilsBundle = require("playwright-core/lib/utilsBundle");
+var import_utils = require("playwright-core/lib/utils");
+var import_seed = require("../mcp/test/seed");
+class AgentParser {
+  static async loadAgents() {
+    const files = await import_fs.default.promises.readdir(__dirname);
+    return Promise.all(files.filter((file) => file.endsWith(".agent.md")).map((file) => AgentParser.parseFile(import_path.default.join(__dirname, file))));
+  }
+  static async parseFile(filePath) {
+    const source = await import_fs.default.promises.readFile(filePath, "utf-8");
+    const { header, content } = this.extractYamlAndContent(source);
+    const { instructions, examples } = this.extractInstructionsAndExamples(content);
+    return { header, instructions, examples };
+  }
+  static extractYamlAndContent(markdown) {
+    const lines = markdown.split("\n");
+    if (lines[0] !== "---")
+      throw new Error("Markdown file must start with YAML front matter (---)");
+    let yamlEndIndex = -1;
+    for (let i = 1; i < lines.length; i++) {
+      if (lines[i] === "---") {
+        yamlEndIndex = i;
+        break;
+      }
+    }
+    if (yamlEndIndex === -1)
+      throw new Error("YAML front matter must be closed with ---");
+    const yamlLines = lines.slice(1, yamlEndIndex);
+    const yamlRaw = yamlLines.join("\n");
+    const contentLines = lines.slice(yamlEndIndex + 1);
+    const content = contentLines.join("\n");
+    let header;
+    try {
+      header = import_utilsBundle.yaml.parse(yamlRaw);
+    } catch (error) {
+      throw new Error(`Failed to parse YAML header: ${error.message}`);
+    }
+    if (!header.name)
+      throw new Error('YAML header must contain a "name" field');
+    if (!header.description)
+      throw new Error('YAML header must contain a "description" field');
+    return { header, content };
+  }
+  static extractInstructionsAndExamples(content) {
+    const examples = [];
+    const instructions = content.split("<example>")[0].trim();
+    const exampleRegex = /<example>([\s\S]*?)<\/example>/g;
+    let match;
+    while ((match = exampleRegex.exec(content)) !== null) {
+      const example = match[1].trim();
+      examples.push(example.replace(/[\n]/g, " ").replace(/ +/g, " "));
+    }
+    return { instructions, examples };
+  }
+}
+class ClaudeGenerator {
+  static async init(config, projectName, prompts) {
+    await initRepo(config, projectName, {
+      promptsFolder: prompts ? ".claude/prompts" : void 0
+    });
+    const agents = await AgentParser.loadAgents();
+    await import_fs.default.promises.mkdir(".claude/agents", { recursive: true });
+    for (const agent of agents)
+      await writeFile(`.claude/agents/${agent.header.name}.md`, ClaudeGenerator.agentSpec(agent), "\u{1F916}", "agent definition");
+    await writeFile(".mcp.json", JSON.stringify({
+      mcpServers: {
+        "playwright-test": {
+          command: "npx",
+          args: ["playwright", "run-test-mcp-server"]
+        }
+      }
+    }, null, 2), "\u{1F527}", "mcp configuration");
+    initRepoDone();
+  }
+  static agentSpec(agent) {
+    const claudeToolMap = /* @__PURE__ */ new Map([
+      ["search", ["Glob", "Grep", "Read", "LS"]],
+      ["edit", ["Edit", "MultiEdit", "Write"]]
+    ]);
+    function asClaudeTool(tool) {
+      const [first, second] = tool.split("/");
+      if (!second)
+        return (claudeToolMap.get(first) || [first]).join(", ");
+      return `mcp__${first}__${second}`;
+    }
+    const examples = agent.examples.length ? ` Examples: ${agent.examples.map((example) => `<example>${example}</example>`).join("")}` : "";
+    const lines = [];
+    const header = {
+      name: agent.header.name,
+      description: agent.header.description + examples,
+      tools: agent.header.tools.map((tool) => asClaudeTool(tool)).join(", "),
+      model: agent.header.model,
+      color: agent.header.color
+    };
+    lines.push(`---`);
+    lines.push(import_utilsBundle.yaml.stringify(header, { lineWidth: 1e5 }) + `---`);
+    lines.push("");
+    lines.push(agent.instructions);
+    return lines.join("\n");
+  }
+}
+class OpencodeGenerator {
+  static async init(config, projectName, prompts) {
+    await initRepo(config, projectName, {
+      defaultAgentName: "Build",
+      promptsFolder: prompts ? ".opencode/prompts" : void 0
+    });
+    const agents = await AgentParser.loadAgents();
+    for (const agent of agents) {
+      const prompt = [agent.instructions];
+      prompt.push("");
+      prompt.push(...agent.examples.map((example) => `<example>${example}</example>`));
+      await writeFile(`.opencode/prompts/${agent.header.name}.md`, prompt.join("\n"), "\u{1F916}", "agent definition");
+    }
+    await writeFile("opencode.json", OpencodeGenerator.configuration(agents), "\u{1F527}", "opencode configuration");
+    initRepoDone();
+  }
+  static configuration(agents) {
+    const opencodeToolMap = /* @__PURE__ */ new Map([
+      ["search", ["ls", "glob", "grep", "read"]],
+      ["edit", ["edit", "write"]]
+    ]);
+    const asOpencodeTool = (tools, tool) => {
+      const [first, second] = tool.split("/");
+      if (!second) {
+        for (const tool2 of opencodeToolMap.get(first) || [first])
+          tools[tool2] = true;
+      } else {
+        tools[`${first}*${second}`] = true;
+      }
+    };
+    const result = {};
+    result["$schema"] = "https://opencode.ai/config.json";
+    result["mcp"] = {};
+    result["tools"] = {
+      "playwright*": false
+    };
+    result["agent"] = {};
+    for (const agent of agents) {
+      const tools = {};
+      result["agent"][agent.header.name] = {
+        description: agent.header.description,
+        mode: "subagent",
+        prompt: `{file:.opencode/prompts/${agent.header.name}.md}`,
+        tools
+      };
+      for (const tool of agent.header.tools)
+        asOpencodeTool(tools, tool);
+    }
+    result["mcp"]["playwright-test"] = {
+      type: "local",
+      command: ["npx", "playwright", "run-test-mcp-server"],
+      enabled: true
+    };
+    return JSON.stringify(result, null, 2);
+  }
+}
+class CopilotGenerator {
+  static async init(config, projectName, prompts) {
+    await initRepo(config, projectName, {
+      defaultAgentName: "agent",
+      promptsFolder: prompts ? ".github/prompts" : void 0,
+      promptSuffix: "prompt"
+    });
+    const agents = await AgentParser.loadAgents();
+    await import_fs.default.promises.mkdir(".github/agents", { recursive: true });
+    for (const agent of agents)
+      await writeFile(`.github/agents/${agent.header.name}.agent.md`, CopilotGenerator.agentSpec(agent), "\u{1F916}", "agent definition");
+    await deleteFile(`.github/chatmodes/ \u{1F3AD} planner.chatmode.md`, "legacy planner chatmode");
+    await deleteFile(`.github/chatmodes/\u{1F3AD} generator.chatmode.md`, "legacy generator chatmode");
+    await deleteFile(`.github/chatmodes/\u{1F3AD} healer.chatmode.md`, "legacy healer chatmode");
+    await deleteFile(`.github/agents/ \u{1F3AD} planner.agent.md`, "legacy planner agent");
+    await deleteFile(`.github/agents/\u{1F3AD} generator.agent.md`, "legacy generator agent");
+    await deleteFile(`.github/agents/\u{1F3AD} healer.agent.md`, "legacy healer agent");
+    await VSCodeGenerator.appendToMCPJson();
+    const mcpConfig = { mcpServers: CopilotGenerator.mcpServers };
+    if (!import_fs.default.existsSync(".github/copilot-setup-steps.yml")) {
+      const yaml2 = import_fs.default.readFileSync(import_path.default.join(__dirname, "copilot-setup-steps.yml"), "utf-8");
+      await writeFile(".github/workflows/copilot-setup-steps.yml", yaml2, "\u{1F527}", "GitHub Copilot setup steps");
+    }
+    console.log("");
+    console.log("");
+    console.log(" \u{1F527} TODO: GitHub > Settings > Copilot > Coding agent > MCP configuration");
+    console.log("------------------------------------------------------------------");
+    console.log(JSON.stringify(mcpConfig, null, 2));
+    console.log("------------------------------------------------------------------");
+    initRepoDone();
+  }
+  static agentSpec(agent) {
+    const examples = agent.examples.length ? ` Examples: ${agent.examples.map((example) => `<example>${example}</example>`).join("")}` : "";
+    const lines = [];
+    const header = {
+      "name": agent.header.name,
+      "description": agent.header.description + examples,
+      "tools": agent.header.tools,
+      "model": "Claude Sonnet 4",
+      "mcp-servers": CopilotGenerator.mcpServers
+    };
+    lines.push(`---`);
+    lines.push(import_utilsBundle.yaml.stringify(header) + `---`);
+    lines.push("");
+    lines.push(agent.instructions);
+    lines.push("");
+    return lines.join("\n");
+  }
+  static {
+    this.mcpServers = {
+      "playwright-test": {
+        "type": "stdio",
+        "command": "npx",
+        "args": [
+          "playwright",
+          "run-test-mcp-server"
+        ],
+        "tools": ["*"]
+      }
+    };
+  }
+}
+class VSCodeGenerator {
+  static async init(config, projectName) {
+    await initRepo(config, projectName, {
+      promptsFolder: void 0
+    });
+    const agents = await AgentParser.loadAgents();
+    const nameMap = /* @__PURE__ */ new Map([
+      ["playwright-test-planner", " \u{1F3AD} planner"],
+      ["playwright-test-generator", "\u{1F3AD} generator"],
+      ["playwright-test-healer", "\u{1F3AD} healer"]
+    ]);
+    await import_fs.default.promises.mkdir(".github/chatmodes", { recursive: true });
+    for (const agent of agents)
+      await writeFile(`.github/chatmodes/${nameMap.get(agent.header.name)}.chatmode.md`, VSCodeGenerator.agentSpec(agent), "\u{1F916}", "chatmode definition");
+    await VSCodeGenerator.appendToMCPJson();
+    initRepoDone();
+  }
+  static async appendToMCPJson() {
+    await import_fs.default.promises.mkdir(".vscode", { recursive: true });
+    const mcpJsonPath = ".vscode/mcp.json";
+    let mcpJson = {
+      servers: {},
+      inputs: []
+    };
+    try {
+      mcpJson = JSON.parse(import_fs.default.readFileSync(mcpJsonPath, "utf8"));
+    } catch {
+    }
+    if (!mcpJson.servers)
+      mcpJson.servers = {};
+    mcpJson.servers["playwright-test"] = {
+      type: "stdio",
+      command: "npx",
+      args: ["playwright", "run-test-mcp-server"]
+    };
+    await writeFile(mcpJsonPath, JSON.stringify(mcpJson, null, 2), "\u{1F527}", "mcp configuration");
+  }
+  static agentSpec(agent) {
+    const vscodeToolMap = /* @__PURE__ */ new Map([
+      ["search", ["search/listDirectory", "search/fileSearch", "search/textSearch"]],
+      ["read", ["search/readFile"]],
+      ["edit", ["edit/editFiles"]],
+      ["write", ["edit/createFile", "edit/createDirectory"]]
+    ]);
+    const vscodeToolsOrder = ["edit/createFile", "edit/createDirectory", "edit/editFiles", "search/fileSearch", "search/textSearch", "search/listDirectory", "search/readFile"];
+    const vscodeMcpName = "playwright-test";
+    function asVscodeTool(tool) {
+      const [first, second] = tool.split("/");
+      if (second)
+        return `${vscodeMcpName}/${second}`;
+      return vscodeToolMap.get(first) || first;
+    }
+    const tools = agent.header.tools.map(asVscodeTool).flat().sort((a, b) => {
+      const indexA = vscodeToolsOrder.indexOf(a);
+      const indexB = vscodeToolsOrder.indexOf(b);
+      if (indexA === -1 && indexB === -1)
+        return a.localeCompare(b);
+      if (indexA === -1)
+        return 1;
+      if (indexB === -1)
+        return -1;
+      return indexA - indexB;
+    }).map((tool) => `'${tool}'`).join(", ");
+    const lines = [];
+    lines.push(`---`);
+    lines.push(`description: ${agent.header.description}.`);
+    lines.push(`tools: [${tools}]`);
+    lines.push(`---`);
+    lines.push("");
+    lines.push(agent.instructions);
+    for (const example of agent.examples)
+      lines.push(`<example>${example}</example>`);
+    lines.push("");
+    return lines.join("\n");
+  }
+}
+async function writeFile(filePath, content, icon, description) {
+  console.log(` ${icon} ${import_path.default.relative(process.cwd(), filePath)} ${import_utilsBundle.colors.dim("- " + description)}`);
+  await (0, import_utils.mkdirIfNeeded)(filePath);
+  await import_fs.default.promises.writeFile(filePath, content, "utf-8");
+}
+async function deleteFile(filePath, description) {
+  try {
+    if (!import_fs.default.existsSync(filePath))
+      return;
+  } catch {
+    return;
+  }
+  console.log(` \u2702\uFE0F  ${import_path.default.relative(process.cwd(), filePath)} ${import_utilsBundle.colors.dim("- " + description)}`);
+  await import_fs.default.promises.unlink(filePath);
+}
+async function initRepo(config, projectName, options) {
+  const project = (0, import_seed.seedProject)(config, projectName);
+  console.log(` \u{1F3AD} Using project "${project.project.name}" as a primary project`);
+  if (!import_fs.default.existsSync("specs")) {
+    await import_fs.default.promises.mkdir("specs");
+    await writeFile(import_path.default.join("specs", "README.md"), `# Specs
+
+This is a directory for test plans.
+`, "\u{1F4DD}", "directory for test plans");
+  }
+  let seedFile = await (0, import_seed.findSeedFile)(project);
+  if (!seedFile) {
+    seedFile = (0, import_seed.defaultSeedFile)(project);
+    await writeFile(seedFile, import_seed.seedFileContent, "\u{1F331}", "default environment seed file");
+  }
+  if (options.promptsFolder) {
+    await import_fs.default.promises.mkdir(options.promptsFolder, { recursive: true });
+    for (const promptFile of await import_fs.default.promises.readdir(__dirname)) {
+      if (!promptFile.endsWith(".prompt.md"))
+        continue;
+      const shortName = promptFile.replace(".prompt.md", "");
+      const fileName = options.promptSuffix ? `${shortName}.${options.promptSuffix}.md` : `${shortName}.md`;
+      const content = await loadPrompt(promptFile, {
+        defaultAgentName: "default",
+        ...options,
+        seedFile: import_path.default.relative(process.cwd(), seedFile)
+      });
+      await writeFile(import_path.default.join(options.promptsFolder, fileName), content, "\u{1F4DD}", "prompt template");
+    }
+  }
+}
+function initRepoDone() {
+  console.log(" \u2705 Done.");
+}
+async function loadPrompt(file, params) {
+  const content = await import_fs.default.promises.readFile(import_path.default.join(__dirname, file), "utf-8");
+  return Object.entries(params).reduce((acc, [key, value]) => {
+    return acc.replace(new RegExp(`\\\${${key}}`, "g"), value);
+  }, content);
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  ClaudeGenerator,
+  CopilotGenerator,
+  OpencodeGenerator,
+  VSCodeGenerator
+});

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-coverage.prompt.md

@@ -0,0 +1,31 @@
+---
+agent: ${defaultAgentName}
+description: Produce test coverage
+---
+
+Parameters:
+- Task: the task to perform
+- Seed file (optional): the seed file to use, defaults to `${seedFile}`
+- Test plan file (optional): the test plan file to write, under `specs/` folder.
+
+1. Call #playwright-test-planner subagent with prompt:
+
+<plan>
+  <task-text><!-- the task --></task-text>
+  <seed-file><!-- path to seed file --></seed-file>
+  <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:
+
+<generate>
+  <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>
+</generate>
+
+3. Call #playwright-test-healer subagent with prompt:
+
+<heal>Run all tests and fix the failing ones one after another.</heal>

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-generate.prompt.md

@@ -0,0 +1,8 @@
+---
+agent: playwright-test-generator
+description: Generate test plan
+---
+
+Generate tests for the test plan's bullet 1.1 Add item to card.
+
+Test plan: `specs/coverage.plan.md`

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-generator.agent.md

@@ -0,0 +1,88 @@
+---
+name: playwright-test-generator
+description: Use this agent when you need to create automated browser tests using Playwright
+model: sonnet
+color: blue
+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
+---
+
+You are a Playwright Test Generator, an expert in browser automation and end-to-end testing.
+Your specialty is creating robust, reliable Playwright tests that accurately simulate user interactions and validate
+application behavior.
+
+# For each test you generate
+- Obtain the test plan with all the steps and verification specification
+- Run the `generator_setup_page` tool to set up page for the scenario
+- For each step and verification in the scenario, do the following:
+  - Use Playwright tool to manually execute it in real-time.
+  - Use the step description as the intent for each Playwright tool call.
+- Retrieve generator log via `generator_read_log`
+- Immediately after reading the test log, invoke `generator_write_test` with the generated source code
+  - File should contain single test
+  - File name must be fs-friendly scenario name
+  - Test must be placed in a describe matching the top-level test plan item
+  - Test title must match the scenario name
+  - Includes a comment with the step text before each step execution. Do not duplicate comments if step requires
+    multiple actions.
+  - Always use best practices from the log when generating tests.
+
+   <example-generation>
+   For following plan:
+
+   ```markdown file=specs/plan.md
+   ### 1. Adding New Todos
+   **Seed:** `tests/seed.spec.ts`
+
+   #### 1.1 Add Valid Todo
+   **Steps:**
+   1. Click in the "What needs to be done?" input field
+
+   #### 1.2 Add Multiple Todos
+   ...
+   ```
+
+   Following file is generated:
+
+   ```ts file=add-valid-todo.spec.ts
+   // spec: specs/plan.md
+   // seed: tests/seed.spec.ts
+
+   test.describe('Adding New Todos', () => {
+     test('Add Valid Todo', async { page } => {
+       // 1. Click in the "What needs to be done?" input field
+       await page.click(...);
+
+       ...
+     });
+   });
+   ```
+   </example-generation>
+
+<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>

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-heal.prompt.md

@@ -0,0 +1,6 @@
+---
+agent: playwright-test-healer
+description: Fix tests
+---
+
+Run all my tests and fix the failing ones.

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-healer.agent.md

@@ -0,0 +1,55 @@
+---
+name: playwright-test-healer
+description: Use this agent when you need to debug and fix failing Playwright tests
+model: sonnet
+color: red
+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
+---
+
+You are the Playwright Test Healer, an expert test automation engineer specializing in debugging and
+resolving Playwright test failures. Your mission is to systematically identify, diagnose, and fix
+broken Playwright tests using a methodical approach.
+
+Your workflow:
+1. **Initial Execution**: Run all tests using `test_run` tool to identify failing tests
+2. **Debug failed tests**: For each failing test run `test_debug`.
+3. **Error Investigation**: When the test pauses on errors, use available Playwright MCP tools to:
+   - Examine the error details
+   - Capture page snapshot to understand the context
+   - Analyze selectors, timing issues, or assertion failures
+4. **Root Cause Analysis**: Determine the underlying cause of the failure by examining:
+   - Element selectors that may have changed
+   - Timing and synchronization issues
+   - Data dependencies or test environment problems
+   - Application changes that broke test assumptions
+5. **Code Remediation**: Edit the test code to address identified issues, focusing on:
+   - Updating selectors to match current application state
+   - Fixing assertions and expected values
+   - Improving test reliability and maintainability
+   - For inherently dynamic data, utilize regular expressions to produce resilient locators
+6. **Verification**: Restart the test after each fix to validate the changes
+7. **Iteration**: Repeat the investigation and fixing process until the test passes cleanly
+
+Key principles:
+- Be systematic and thorough in your debugging approach
+- Document your findings and reasoning for each fix
+- Prefer robust, maintainable solutions over quick hacks
+- Use Playwright best practices for reliable test automation
+- If multiple errors exist, fix them one at a time and retest
+- Provide clear explanations of what was broken and how you fixed it
+- You will continue this process until the test runs successfully without any failures or errors.
+- If the error persists and you have high level of confidence that the test is correct, mark this test as test.fixme()
+  so that it is skipped during the execution. Add a comment before the failing step explaining what is happening instead
+  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

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-plan.prompt.md

@@ -0,0 +1,9 @@
+---
+agent: playwright-test-planner
+description: Create test plan
+---
+
+Create test plan for "add to cart" functionality of my app.
+
+- Seed file: `${seedFile}`
+- Test plan: `specs/coverage.plan.md`

.playwright-mcp/node_modules/playwright/lib/agents/playwright-test-planner.agent.md

@@ -0,0 +1,72 @@
+---
+name: playwright-test-planner
+description: Use this agent when you need to create comprehensive test plan for a web application or website
+model: sonnet
+color: green
+tools:
+  - search
+  - 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
+  - playwright-test/planner_save_plan
+---
+
+You are an expert web test planner with extensive experience in quality assurance, user experience testing, and test
+scenario design. Your expertise includes functional testing, edge case identification, and comprehensive test coverage
+planning.
+
+You will:
+
+1. **Navigate and Explore**
+   - Invoke the `planner_setup_page` tool once to set up page before using any other tools
+   - Explore the browser snapshot
+   - Do not take screenshots unless absolutely necessary
+   - Use `browser_*` tools to navigate and discover interface
+   - Thoroughly explore the interface, identifying all interactive elements, forms, navigation paths, and functionality
+
+2. **Analyze User Flows**
+   - Map out the primary user journeys and identify critical paths through the application
+   - Consider different user types and their typical behaviors
+
+3. **Design Comprehensive Scenarios**
+
+   Create detailed test scenarios that cover:
+   - Happy path scenarios (normal user behavior)
+   - Edge cases and boundary conditions
+   - Error handling and validation
+
+4. **Structure Test Plans**
+
+   Each scenario must include:
+   - Clear, descriptive title
+   - Detailed step-by-step instructions
+   - Expected outcomes where appropriate
+   - Assumptions about starting state (always assume blank/fresh state)
+   - Success criteria and failure conditions
+
+5. **Create Documentation**
+
+   Submit your test plan using `planner_save_plan` tool.
+
+**Quality Standards**:
+- Write steps that are specific enough for any tester to follow
+- Include negative testing scenarios
+- Ensure scenarios are independent and can be run in any order
+
+**Output Format**: Always save the complete test plan as a markdown file with clear headings, numbered steps, and
+professional formatting suitable for sharing with development and QA teams.