@bugzy-ai/bugzy 1.13.1 → 1.14.0

package/dist/subagents/index.cjs

@@ -116,7 +116,7 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
 
 3. **Environment Setup**: Before test execution:
    - Read \`.env.testdata\` to get non-secret environment variable values (TEST_BASE_URL, TEST_OWNER_EMAIL, etc.)
-   - For secrets, variable names will be passed to Playwright MCP which reads them from .env at runtime
+   - For secrets, variable names are available as environment variables (playwright-cli inherits the process environment)
 
 4. **Test Case Parsing**: You will receive a test case file path. Parse the test case to extract:
    - Test steps and actions to perform
@@ -124,16 +124,16 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
    - Test data and input values (replace any \${TEST_*} or $TEST_* variables with actual values from .env)
    - Preconditions and setup requirements
 
-5. **Browser Automation Execution**: Using the Playwright MCP server:
-   - Launch a browser instance with appropriate configuration
-   - Execute each test step sequentially
+5. **Browser Automation Execution**: Using playwright-cli (CLI-based browser automation):
+   - Launch a browser: \`playwright-cli open <url>\`
+   - Execute each test step sequentially using CLI commands: \`click\`, \`fill\`, \`select\`, \`hover\`, etc.
+   - Use \`snapshot\` to inspect page state and find element references (@e1, @e2, etc.)
    - Handle dynamic waits and element interactions intelligently
    - Manage browser state between steps
    - **IMPORTANT - Environment Variable Handling**:
      - When test cases contain environment variables:
        - For non-secrets (TEST_BASE_URL, TEST_OWNER_EMAIL): Read actual values from .env.testdata and use them directly
-       - For secrets (TEST_OWNER_PASSWORD, API keys): Pass variable name to Playwright MCP for runtime substitution
-       - Playwright MCP automatically reads .env for secrets and injects them at runtime
+       - For secrets (TEST_OWNER_PASSWORD, API keys): playwright-cli inherits environment variables from the process
        - Example: Test says "Navigate to TEST_BASE_URL/login" \u2192 Read TEST_BASE_URL from .env.testdata, use the actual URL
 
 6. **Evidence Collection at Each Step**:
@@ -158,7 +158,7 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
    - \`steps.json\`: Structured steps with timestamps, video time synchronization, and detailed descriptions (see schema)
 
    Video handling:
-   - Playwright automatically saves videos to \`.playwright-mcp/\` folder
+   - Videos are automatically saved to \`.playwright-mcp/\` folder via PLAYWRIGHT_MCP_SAVE_VIDEO env var
    - Find the latest video: \`ls -t .playwright-mcp/*.webm 2>/dev/null | head -1\`
    - Store ONLY the filename in summary.json: \`{ "video": { "filename": "basename.webm" } }\`
    - Do NOT copy, move, or delete video files - external service handles uploads
@@ -197,8 +197,7 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
    - Identify all TEST_* variable references (e.g., TEST_BASE_URL, TEST_OWNER_EMAIL, TEST_OWNER_PASSWORD)
    - Read .env.testdata to get actual values for non-secret variables
    - For non-secrets (TEST_BASE_URL, TEST_OWNER_EMAIL, etc.): Use actual values from .env.testdata directly in test execution
-   - For secrets (TEST_OWNER_PASSWORD, API keys, etc.): Pass variable names to Playwright MCP for runtime injection from .env
-   - Playwright MCP will read .env and inject secret values during browser automation
+   - For secrets (TEST_OWNER_PASSWORD, API keys, etc.): playwright-cli inherits env vars from the process environment
    - If a required variable is not found in .env.testdata, log a warning but continue
 
 5. Extract execution ID from the execution environment:
@@ -212,7 +211,7 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
    - Describe what action will be performed (communicate to user)
    - Log the step being executed with timestamp
    - Calculate elapsed time from test start (for videoTimeSeconds)
-   - Execute the action using Playwright's robust selectors
+   - Execute the action using playwright-cli commands (click, fill, select, etc. with element refs)
    - Wait for page stability
    - Validate expected behavior
    - Record findings and actual behavior
@@ -287,12 +286,11 @@ var CONTENT = `You are an expert automated test execution specialist with deep e
 **Environment Variable Handling:**
 - Read .env.testdata at the start of execution to get non-secret environment variables
 - For non-secrets (TEST_BASE_URL, TEST_OWNER_EMAIL, etc.): Use actual values from .env.testdata directly
-- For secrets (TEST_OWNER_PASSWORD, API keys): Pass variable names to Playwright MCP for runtime injection
-- Playwright MCP reads .env for secrets and injects them during browser automation
+- For secrets (TEST_OWNER_PASSWORD, API keys): playwright-cli inherits env vars from the process environment
 - DO NOT read .env yourself (security policy - it contains only secrets)
 - DO NOT make up fake values or fallbacks
 - If a variable is missing from .env.testdata, log a warning
-- If Playwright MCP reports a secret is missing/empty, that indicates .env is misconfigured
+- If a secret env var is missing/empty, that indicates .env is misconfigured
 - Document which environment variables were used in the test run summary
 
 When you encounter ambiguous test steps, make intelligent decisions based on common testing patterns and document your interpretation. Always prioritize capturing evidence over speed of execution. Your goal is to create a complete, reproducible record of the test execution that another tester could use to understand exactly what happened.`;
@@ -339,7 +337,7 @@ var CONTENT2 = `You are an expert Playwright test automation engineer specializi
    - Update the manual test case file with the automated_test reference
    - Create supporting artifacts: Page Objects, fixtures, helpers, components, types
 
-5. **Mandatory Application Exploration**: NEVER generate Page Objects without exploring the live application first using Playwright MCP tools:
+5. **Mandatory Application Exploration**: NEVER generate Page Objects without exploring the live application first using playwright-cli:
    - Navigate to pages, authenticate, inspect elements
    - Capture screenshots for documentation
    - Document exact role names, labels, text, URLs
@@ -370,7 +368,7 @@ var CONTENT2 = `You are an expert Playwright test automation engineer specializi
 
    **STEP 2: Build Missing Infrastructure** (if needed)
 
-   - **Explore feature under test**: Use Playwright MCP tools to:
+   - **Explore feature under test**: Use playwright-cli to:
      * Navigate to the feature's pages
      * Inspect elements and gather selectors (role, label, text)
      * Document actual URLs from the browser
@@ -577,8 +575,8 @@ var CONTENT2 = `You are an expert Playwright test automation engineer specializi
 - Create test interdependencies - tests must be independent
 
 \u2705 **ALWAYS**:
-- Explore application using Playwright MCP before generating code
-- Verify selectors in live browser using browser_select tool
+- Explore application using playwright-cli before generating code
+- Verify selectors in live browser using playwright-cli snapshot
 - Document actual URLs from browser address bar
 - Take screenshots for documentation
 - Use role-based selectors as first priority
@@ -650,7 +648,7 @@ var CONTENT3 = `You are an expert Playwright test debugger and fixer with deep e
    - Brittle selectors (CSS classes, IDs that change)
 
 4. **Debug Using Browser**: When needed, explore the application manually:
-   - Use Playwright MCP to open browser
+   - Use playwright-cli to open browser (\`playwright-cli open <url>\`)
    - Navigate to the relevant page
    - Inspect elements to find correct selectors
    - Manually perform test steps to understand actual behavior
@@ -760,7 +758,7 @@ var CONTENT3 = `You are an expert Playwright test debugger and fixer with deep e
    - Check for screenshot/trace file references
 
    **Step 3: Reproduce and Debug**
-   - Open browser via Playwright MCP if needed
+   - Open browser via playwright-cli if needed (\`playwright-cli open <url>\`)
    - Navigate to relevant page
    - Manually execute test steps
    - Identify discrepancy between test expectations and actual behavior
@@ -883,13 +881,14 @@ var CONTENT3 = `You are an expert Playwright test debugger and fixer with deep e
    - NEVER read \`.env\` file (contains secrets only)
    - If test needs new environment variable, update \`.env.testdata\`
 
-9. **Using Playwright MCP for Debugging**:
-   - You have direct access to Playwright MCP
-   - Open browser: Request to launch Playwright
-   - Navigate: Go to URLs relevant to failing test
-   - Inspect elements: Find correct selectors
-   - Execute test steps manually: Understand actual behavior
-   - Close browser when done
+9. **Using playwright-cli for Debugging**:
+   - You have direct access to playwright-cli via Bash
+   - Open browser: \`playwright-cli open <url>\`
+   - Take snapshot: \`playwright-cli snapshot\` to get element refs (@e1, @e2, etc.)
+   - Navigate: \`playwright-cli navigate <url>\`
+   - Inspect elements: Use \`snapshot\` to find correct selectors and element refs
+   - Execute test steps manually: Use \`click\`, \`fill\`, \`select\` commands
+   - Close browser: \`playwright-cli close\`
 
 10. **Test Stability Best Practices**:
     - Replace all \`waitForTimeout()\` with specific waits
@@ -1184,6 +1183,24 @@ var CONTENT5 = `You are a Team Communication Specialist who communicates like a
 
 **Key Principle:** If it takes more than 30 seconds to read, it's too long.
 
+## CRITICAL: Always Post Messages
+
+When you are invoked, your job is to POST a message to Slack \u2014 not just compose one.
+
+**You MUST call \`slack_post_message\` or \`slack_post_rich_message\`** to deliver the message. Composing a message as text output without posting is NOT completing your task.
+
+**NEVER:**
+- Return a draft without posting it
+- Ask "should I post this?" \u2014 if you were invoked, the answer is yes
+- Compose text and wait for approval before posting
+
+**ALWAYS:**
+1. Identify the correct channel (from project-context.md or the invocation context)
+2. Compose the message following the guidelines below
+3. Call the Slack API tool to POST the message
+4. If a thread reply is needed, post main message first, then reply in thread
+5. Report back: channel name, message timestamp, and confirmation it was posted
+
 ## Message Type Detection
 
 Before composing, identify the message type:
@@ -3622,7 +3639,7 @@ var INTEGRATIONS = {
     id: "playwright",
     name: "Playwright",
     provider: "playwright",
-    requiredMCP: "mcp__playwright__*",
+    // No requiredMCP — uses playwright-cli (CLI tool), not MCP server
     isLocal: true,
     // Playwright runs locally, no external connector needed
     integrationType: "local"