Merge ddd0e8fbf2 into 8265bbf295

## Summary
- Track all files with TTS injection applied during installation
- Display informative summary explaining what TTS injection does
- Show backup location and restore command for recovery

## What is TTS Injection?
TTS (Text-to-Speech) injection adds voice instructions to BMAD agents,
enabling them to speak their responses aloud using AgentVibes.

Example: When you activate the PM agent, it will greet you with
spoken audio like "Hey! I'm your Project Manager. How can I help?"

## Changes
- **installer.js**: Track files in `processAgentFiles()`, `buildStandaloneAgents()`,
  and `rebuildAgentFiles()` when TTS markers are processed
- **compiler.js**: Add TTS injection support for custom agent compilation
- **ui.js**: Enhanced installation summary showing:
  - Explanation of what TTS injection is with example
  - List of all files with TTS injection applied (grouped by type)
  - Backup location (~/.bmad-tts-backups/)
  - Restore command for recovery

## Example Output
```
═══════════════════════════════════════════════════
            AgentVibes TTS Injection Summary
═══════════════════════════════════════════════════

What is TTS Injection?

  TTS (Text-to-Speech) injection adds voice instructions to BMAD agents,
  enabling them to speak their responses aloud using AgentVibes.

  Example: When you activate the PM agent, it will greet you with
  spoken audio like "Hey! I'm your Project Manager. How can I help?"

✅ TTS injection applied to 11 file(s):

  Party Mode (multi-agent conversations):
    • .bmad/core/workflows/party-mode/instructions.md
  Agent TTS (individual agent voices):
    • .bmad/bmm/agents/analyst.md
    • .bmad/bmm/agents/architect.md
    ...

Backups & Recovery:

  Pre-injection backups are stored in:
    ~/.bmad-tts-backups/

  To restore original files (removes TTS instructions):
    bmad-tts-injector.sh --restore /path/to/.bmad
```

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

Co-authored-by: Paul Preibisch <paul@paulpreibisch.com>
Co-authored-by: Claude <noreply@anthropic.com>

src/modules/bmm/workflows/4-implementation/code-review/instructions.xml

@@ -3,6 +3,8 @@
   <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
   <critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
   <critical>Generate all documents in {document_output_language}</critical>
+  <critical>ALWAYS reload {{sprint_status}} (docs/sprint-artifacts/sprint-status.yaml by default) from disk immediately before reading or
+    updating statuses. Multiple workflows change this file between runs; never rely on a previously loaded copy or cached memory.</critical>
 
   <critical>🔥 YOU ARE AN ADVERSARIAL CODE REVIEWER - Find what's wrong or missing! 🔥</critical>
   <critical>Your purpose: Validate story file claims against actual implementation</critical>
@@ -173,4 +175,4 @@
     </output>
   </step>
 
-</workflow>
+</workflow>

src/modules/bmm/workflows/4-implementation/create-story/instructions.xml

@@ -2,6 +2,8 @@
   <critical>The workflow execution engine is governed by: {project-root}/{bmad_folder}/core/tasks/workflow.xml</critical>
   <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
   <critical>Communicate all responses in {communication_language} and generate all documents in {document_output_language}</critical>
+  <critical>ALWAYS reload {{sprint_status}} (docs/sprint-artifacts/sprint-status.yaml by default) from disk immediately before reading or
+    updating statuses. Multiple workflows change this file between runs; never rely on a previously loaded copy or cached memory.</critical>
 
   <critical>🔥 CRITICAL MISSION: You are creating the ULTIMATE story context engine that prevents LLM developer mistakes, omissions or
     disasters! 🔥</critical>
@@ -351,4 +353,4 @@
     </output>
   </step>
 
-</workflow>
+</workflow>

src/modules/bmm/workflows/4-implementation/dev-story/instructions.xml

@@ -3,6 +3,8 @@
   <critical>You MUST have already loaded and processed: {installed_path}/workflow.yaml</critical>
   <critical>Communicate all responses in {communication_language} and language MUST be tailored to {user_skill_level}</critical>
   <critical>Generate all documents in {document_output_language}</critical>
+  <critical>ALWAYS reload {{sprint_status}} (docs/sprint-artifacts/sprint-status.yaml by default) from disk immediately before reading or
+    updating statuses. Multiple workflows change this file between runs; never rely on a previously loaded copy or cached memory.</critical>
   <critical>Only modify the story file in these areas: Tasks/Subtasks checkboxes, Dev Agent Record (Debug Log, Completion Notes), File List,
     Change Log, and Status</critical>
   <critical>Execute ALL steps in exact order; do NOT skip steps</critical>
@@ -403,4 +405,4 @@
     <action>Remain flexible - allow user to choose their own path or ask for other assistance</action>
   </step>
 
-</workflow>
+</workflow>

src/modules/bmm/workflows/4-implementation/retrospective/instructions.md

@@ -26,6 +26,7 @@ PARTY MODE PROTOCOL:
 - Create natural back-and-forth with user actively participating
 - Show disagreements, diverse perspectives, authentic team dynamics
   </critical>
+  <critical>ALWAYS reload {{sprint_status_file}} (docs/sprint-artifacts/sprint-status.yaml by default) from disk immediately before reading or updating statuses. Multiple workflows change this file between runs; never rely on a previously loaded copy or cached memory.</critical>
 
 <workflow>
 

src/modules/bmm/workflows/testarch/ci/github-actions-template.yaml

@@ -27,10 +27,21 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=24" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 24 (current LTS)"
+          fi
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ steps.node-version.outputs.value }}
           cache: "npm"
 
       - name: Install dependencies
@@ -54,10 +65,21 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=22" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 22 (current LTS)"
+          fi
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ steps.node-version.outputs.value }}
           cache: "npm"
 
       - name: Cache Playwright browsers
@@ -99,10 +121,21 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=22" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 22 (current LTS)"
+          fi
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version-file: ".nvmrc"
+          node-version: ${{ steps.node-version.outputs.value }}
           cache: "npm"
 
       - name: Cache Playwright browsers

src/modules/bmm/workflows/testarch/ci/gitlab-ci-template.yaml

@@ -15,6 +15,8 @@ variables:
   npm_config_cache: "$CI_PROJECT_DIR/.npm"
   # Playwright browser cache
   PLAYWRIGHT_BROWSERS_PATH: "$CI_PROJECT_DIR/.cache/ms-playwright"
+  # Default Node version when .nvmrc is missing
+  DEFAULT_NODE_VERSION: "24"
 
 # Caching configuration
 cache:
@@ -29,19 +31,32 @@ cache:
 # Lint stage - Code quality checks
 lint:
   stage: lint
-  image: node:20
-  script:
+  image: node:$DEFAULT_NODE_VERSION
+  before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
     - npm ci
+  script:
     - npm run lint
   timeout: 5 minutes
 
 # Test stage - Parallel execution with sharding
 .test-template: &test-template
   stage: test
-  image: node:20
+  image: node:$DEFAULT_NODE_VERSION
   needs:
     - lint
   before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
     - npm ci
     - npx playwright install --with-deps chromium
   artifacts:
@@ -75,7 +90,7 @@ test:shard-4:
 # Burn-in stage - Flaky test detection
 burn-in:
   stage: burn-in
-  image: node:20
+  image: node:$DEFAULT_NODE_VERSION
   needs:
     - test:shard-1
     - test:shard-2
@@ -86,6 +101,12 @@ burn-in:
     - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
     - if: '$CI_PIPELINE_SOURCE == "schedule"'
   before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
     - npm ci
     - npx playwright install --with-deps chromium
   script:

src/modules/bmm/workflows/testarch/ci/instructions.md

@@ -61,8 +61,8 @@ Scaffolds a production-ready CI/CD quality pipeline with test execution, burn-in
      - Ask user if unable to auto-detect
 
 5. **Read Environment Configuration**
-   - Check for `.nvmrc` to determine Node version
-   - Default to Node 20 LTS if not found
+   - Use `.nvmrc` for Node version if present
+   - If missing, default to a current LTS (Node 24) or newer instead of a fixed old version
    - Read `package.json` to identify dependencies (affects caching strategy)
 
 **Halt Condition:** If preflight checks fail, stop immediately and report which requirement failed.

tools/cli/installers/lib/core/installer.js

@@ -51,6 +51,7 @@ class Installer {
     this.configCollector = new ConfigCollector();
     this.ideConfigManager = new IdeConfigManager();
     this.installedFiles = []; // Track all installed files
+    this.ttsInjectedFiles = []; // Track files with TTS injection applied
   }
 
   /**
@@ -146,8 +147,8 @@ class Installer {
           content = content.replaceAll('{*bmad_folder*}', '{bmad_folder}');
         }
 
-        // Process AgentVibes injection points
-        content = this.processTTSInjectionPoints(content);
+        // Process AgentVibes injection points (pass targetPath for tracking)
+        content = this.processTTSInjectionPoints(content, targetPath);
 
         // Write to target with replaced content
         await fs.ensureDir(path.dirname(targetPath));
@@ -226,10 +227,14 @@ class Installer {
    *   - src/modules/bmm/agents/*.md (rules sections)
    * - TTS Hook: .claude/hooks/bmad-speak.sh (in AgentVibes repo)
    */
-  processTTSInjectionPoints(content) {
+  processTTSInjectionPoints(content, targetPath = null) {
     // Check if AgentVibes is enabled (set during installation configuration)
     const enableAgentVibes = this.enableAgentVibes || false;
 
+    // Check if content contains any TTS injection markers
+    const hasPartyMode = content.includes('<!-- TTS_INJECTION:party-mode -->');
+    const hasAgentTTS = content.includes('<!-- TTS_INJECTION:agent-tts -->');
+
     if (enableAgentVibes) {
       // Replace party-mode injection marker with actual TTS call
       // Use single quotes to prevent shell expansion of special chars like !
@@ -253,6 +258,12 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
    IMPORTANT: Use single quotes as shown - do NOT escape special characters like ! or $ inside single quotes
    Run in background (&) to avoid blocking`,
       );
+
+      // Track files that had TTS injection applied
+      if (targetPath && (hasPartyMode || hasAgentTTS)) {
+        const injectionType = hasPartyMode ? 'party-mode' : 'agent-tts';
+        this.ttsInjectedFiles.push({ path: targetPath, type: injectionType });
+      }
     } else {
       // Strip injection markers cleanly when AgentVibes is disabled
       content = content.replaceAll(/<!-- TTS_INJECTION:party-mode -->\n?/g, '');
@@ -1021,6 +1032,8 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
         modules: config.modules,
         ides: config.ides,
         customFiles: customFiles.length > 0 ? customFiles : undefined,
+        ttsInjectedFiles: this.enableAgentVibes && this.ttsInjectedFiles.length > 0 ? this.ttsInjectedFiles : undefined,
+        agentVibesEnabled: this.enableAgentVibes || false,
       });
 
       // Offer cleanup for legacy files (only for updates, not fresh installs, and only if not skipped)
@@ -1526,13 +1539,16 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
 
         // Build YAML + customize to .md
         const customizeExists = await fs.pathExists(customizePath);
-        const xmlContent = await this.xmlHandler.buildFromYaml(yamlPath, customizeExists ? customizePath : null, {
+        let xmlContent = await this.xmlHandler.buildFromYaml(yamlPath, customizeExists ? customizePath : null, {
           includeMetadata: true,
         });
 
         // DO NOT replace {project-root} - LLMs understand this placeholder at runtime
         // const processedContent = xmlContent.replaceAll('{project-root}', projectDir);
 
+        // Process TTS injection points (pass targetPath for tracking)
+        xmlContent = this.processTTSInjectionPoints(xmlContent, mdPath);
+
         // Write the built .md file to bmad/{module}/agents/ with POSIX-compliant final newline
         const content = xmlContent.endsWith('\n') ? xmlContent : xmlContent + '\n';
         await fs.writeFile(mdPath, content, 'utf8');
@@ -1628,13 +1644,16 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
       }
 
       // Build YAML to XML .md
-      const xmlContent = await this.xmlHandler.buildFromYaml(sourceYamlPath, customizeExists ? customizePath : null, {
+      let xmlContent = await this.xmlHandler.buildFromYaml(sourceYamlPath, customizeExists ? customizePath : null, {
         includeMetadata: true,
       });
 
       // DO NOT replace {project-root} - LLMs understand this placeholder at runtime
       // const processedContent = xmlContent.replaceAll('{project-root}', projectDir);
 
+      // Process TTS injection points (pass targetPath for tracking)
+      xmlContent = this.processTTSInjectionPoints(xmlContent, targetMdPath);
+
       // Write the built .md file with POSIX-compliant final newline
       const content = xmlContent.endsWith('\n') ? xmlContent : xmlContent + '\n';
       await fs.writeFile(targetMdPath, content, 'utf8');
@@ -1722,13 +1741,16 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
         }
 
         // Build YAML + customize to .md
-        const xmlContent = await this.xmlHandler.buildFromYaml(sourceYamlPath, customizeExists ? customizePath : null, {
+        let xmlContent = await this.xmlHandler.buildFromYaml(sourceYamlPath, customizeExists ? customizePath : null, {
           includeMetadata: true,
         });
 
         // DO NOT replace {project-root} - LLMs understand this placeholder at runtime
         // const processedContent = xmlContent.replaceAll('{project-root}', projectDir);
 
+        // Process TTS injection points (pass targetPath for tracking)
+        xmlContent = this.processTTSInjectionPoints(xmlContent, targetMdPath);
+
         // Write the rebuilt .md file with POSIX-compliant final newline
         const content = xmlContent.endsWith('\n') ? xmlContent : xmlContent + '\n';
         await fs.writeFile(targetMdPath, content, 'utf8');

tools/cli/installers/lib/ide/shared/workflow-command-generator.js

@@ -125,12 +125,15 @@ class WorkflowCommandGenerator {
       }
     }
 
+    const coreWorkflowPath = `${this.bmadFolderName}/core/tasks/workflow.xml`;
+
     // Replace template variables
     return template
       .replaceAll('{{name}}', workflow.name)
       .replaceAll('{{module}}', workflow.module)
       .replaceAll('{{description}}', workflow.description)
       .replaceAll('{{workflow_path}}', workflowPath)
+      .replaceAll('{{core_workflow_path}}', coreWorkflowPath)
       .replaceAll('{bmad_folder}', this.bmadFolderName)
       .replaceAll('{*bmad_folder*}', '{bmad_folder}');
   }

tools/cli/installers/lib/ide/templates/workflow-command-template.md

@@ -5,7 +5,7 @@ description: '{{description}}'
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">
-1. Always LOAD the FULL @{bmad_folder}/core/tasks/workflow.xml
+1. Always LOAD the FULL @{{core_workflow_path}}
 2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @{{workflow_path}}
 3. Pass the yaml path {{workflow_path}} as 'workflow-config' parameter to the workflow.xml instructions
 4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions

tools/cli/lib/agent/compiler.js

@@ -482,10 +482,39 @@ function compileAgent(yamlContent, answers = {}, agentName = '', targetPath = ''
   };
 }
 
+/**
+ * Process TTS injection markers in content
+ * @param {string} content - Content to process
+ * @param {boolean} enableAgentVibes - Whether AgentVibes is enabled
+ * @returns {Object} { content: string, hadInjection: boolean }
+ */
+function processTTSInjectionPoints(content, enableAgentVibes) {
+  const hasAgentTTS = content.includes('<!-- TTS_INJECTION:agent-tts -->');
+
+  if (enableAgentVibes && hasAgentTTS) {
+    // Replace agent-tts injection marker with TTS rule
+    content = content.replaceAll(
+      '<!-- TTS_INJECTION:agent-tts -->',
+      `- When responding to user messages, speak your responses using TTS:
+   Call: \`.claude/hooks/bmad-speak.sh '{agent-id}' '{response-text}'\` after each response
+   Replace {agent-id} with YOUR agent ID from <agent id="..."> tag at top of this file
+   Replace {response-text} with the text you just output to the user
+   IMPORTANT: Use single quotes as shown - do NOT escape special characters like ! or $ inside single quotes
+   Run in background (&) to avoid blocking`,
+    );
+    return { content, hadInjection: true };
+  } else if (!enableAgentVibes && hasAgentTTS) {
+    // Strip injection markers when disabled
+    content = content.replaceAll(/<!-- TTS_INJECTION:agent-tts -->\n?/g, '');
+  }
+
+  return { content, hadInjection: false };
+}
+
 /**
  * Compile agent file to .md
  * @param {string} yamlPath - Path to agent YAML file
- * @param {Object} options - { answers: {}, outputPath: string }
+ * @param {Object} options - { answers: {}, outputPath: string, enableAgentVibes: boolean }
  * @returns {Object} Compilation result
  */
 function compileAgentFile(yamlPath, options = {}) {
@@ -501,13 +530,24 @@ function compileAgentFile(yamlPath, options = {}) {
     outputPath = path.join(dir, `${basename}.md`);
   }
 
+  // Process TTS injection points if enableAgentVibes option is provided
+  let xml = result.xml;
+  let ttsInjected = false;
+  if (options.enableAgentVibes !== undefined) {
+    const ttsResult = processTTSInjectionPoints(xml, options.enableAgentVibes);
+    xml = ttsResult.content;
+    ttsInjected = ttsResult.hadInjection;
+  }
+
   // Write compiled XML
-  fs.writeFileSync(outputPath, result.xml, 'utf8');
+  fs.writeFileSync(outputPath, xml, 'utf8');
 
   return {
     ...result,
+    xml,
     outputPath,
     sourcePath: yamlPath,
+    ttsInjected,
   };
 }
 

tools/cli/lib/ui.js

@@ -363,11 +363,60 @@ class UI {
       `🔧 Tools Configured: ${result.ides?.length > 0 ? result.ides.join(', ') : 'none'}`,
     ];
 
+    // Add AgentVibes TTS info if enabled
+    if (result.agentVibesEnabled) {
+      summary.push(`🎤 AgentVibes TTS: Enabled`);
+    }
+
     CLIUtils.displayBox(summary.join('\n\n'), {
       borderColor: 'green',
       borderStyle: 'round',
     });
 
+    // Display TTS injection details if present
+    if (result.ttsInjectedFiles && result.ttsInjectedFiles.length > 0) {
+      console.log('\n' + chalk.cyan.bold('═══════════════════════════════════════════════════'));
+      console.log(chalk.cyan.bold('            AgentVibes TTS Injection Summary'));
+      console.log(chalk.cyan.bold('═══════════════════════════════════════════════════\n'));
+
+      // Explain what TTS injection is
+      console.log(chalk.white.bold('What is TTS Injection?\n'));
+      console.log(chalk.dim('  TTS (Text-to-Speech) injection adds voice instructions to BMAD agents,'));
+      console.log(chalk.dim('  enabling them to speak their responses aloud using AgentVibes.\n'));
+      console.log(chalk.dim('  Example: When you activate the PM agent, it will greet you with'));
+      console.log(chalk.dim('  spoken audio like "Hey! I\'m your Project Manager. How can I help?"\n'));
+
+      console.log(chalk.green(`✅ TTS injection applied to ${result.ttsInjectedFiles.length} file(s):\n`));
+
+      // Group by type
+      const partyModeFiles = result.ttsInjectedFiles.filter((f) => f.type === 'party-mode');
+      const agentTTSFiles = result.ttsInjectedFiles.filter((f) => f.type === 'agent-tts');
+
+      if (partyModeFiles.length > 0) {
+        console.log(chalk.yellow('  Party Mode (multi-agent conversations):'));
+        for (const file of partyModeFiles) {
+          console.log(chalk.dim(`    • ${file.path}`));
+        }
+      }
+
+      if (agentTTSFiles.length > 0) {
+        console.log(chalk.yellow('  Agent TTS (individual agent voices):'));
+        for (const file of agentTTSFiles) {
+          console.log(chalk.dim(`    • ${file.path}`));
+        }
+      }
+
+      // Show backup info and restore command
+      console.log('\n' + chalk.white.bold('Backups & Recovery:\n'));
+      console.log(chalk.dim('  Pre-injection backups are stored in:'));
+      console.log(chalk.cyan('    ~/.bmad-tts-backups/\n'));
+      console.log(chalk.dim('  To restore original files (removes TTS instructions):'));
+      console.log(chalk.cyan(`    bmad-tts-injector.sh --restore ${result.path}\n`));
+
+      console.log(chalk.cyan('💡 BMAD agents will now speak when activated!'));
+      console.log(chalk.dim('   Ensure AgentVibes is installed: https://agentvibes.org'));
+    }
+
     console.log('\n' + chalk.green.bold('✨ BMAD is ready to use!'));
   }