Add Text-to-Speech Integration via TTS_INJECTION System (#934)

* feat: Add provider-agnostic TTS integration via injection point system

Implements comprehensive Text-to-Speech integration for BMAD agents using a generic
TTS_INJECTION marker system. When AgentVibes (or any compatible TTS provider) is
installed, all BMAD agents can speak their responses with unique AI voices.

## Key Features

**Provider-Agnostic Architecture**
- Uses generic `TTS_INJECTION` markers instead of vendor-specific naming
- Future-proof for multiple TTS providers beyond AgentVibes
- Clean separation - BMAD stays TTS-agnostic, providers handle injection

**Installation Flow**
- BMAD → AgentVibes: TTS instructions injected when AgentVibes detects existing BMAD installation
- AgentVibes → BMAD: TTS instructions injected during BMAD installation when AgentVibes detected
- User must manually create voice assignment file when AgentVibes installs first (documented limitation)

**Party Mode Voice Support**
- Each agent speaks with unique assigned voice in multi-agent discussions
- PM, Architect, Developer, Analyst, UX Designer, etc. - all with distinct voices

**Zero Breaking Changes**
- Fully backward compatible - works without any TTS provider
- `TTS_INJECTION` markers are benign HTML comments if not processed
- No changes to existing agent behavior or non-TTS workflows

## Implementation Details

**Files Modified:**
- `tools/cli/installers/lib/core/installer.js` - TTS injection processing logic
- `tools/cli/lib/ui.js` - AgentVibes detection and installation prompts
- `tools/cli/commands/install.js` - Post-install guidance for AgentVibes setup
- `src/utility/models/fragments/activation-rules.xml` - TTS_INJECTION marker for agents
- `src/core/workflows/party-mode/instructions.md` - TTS_INJECTION marker for party mode

**Injection Point System:**
```xml
<rules>
  - ALWAYS communicate in {communication_language}
  <!-- TTS_INJECTION:agent-tts -->
  - Stay in character until exit selected
</rules>
```

When AgentVibes is detected, the installer replaces this marker with:
```
- When responding to user messages, speak your responses using TTS:
  Call: `.claude/hooks/bmad-speak.sh '{agent-id}' '{response-text}'` after each response
  IMPORTANT: Use single quotes - do NOT escape special characters like ! or $
```

**Special Character Handling:**
- Explicit guidance to use single quotes without escaping
- Prevents "backslash exclamation" artifacts in speech

**User Experience:**
```
User: "How should we architect this feature?"
Architect: [Text response] + 🔊 [Professional voice explains architecture]
```

Party Mode:
```
PM (John): "I'll focus on user value..." 🔊 [Male professional voice]
UX Designer (Sara): "From a user perspective..." 🔊 [Female voice]
Architect (Marcus): "The technical approach..." 🔊 [Male technical voice]
```

## Testing

**Unit Tests:**  62/62 passing
- 49/49 schema validation tests
- 13/13 installation component tests

**Integration Testing:**
-  BMAD → AgentVibes (automatic injection)
-  AgentVibes → BMAD (automatic injection)
-  No TTS provider (markers remain as comments)

## Documentation

Comprehensive testing guide created with:
- Both installation scenario walkthroughs
- Verification commands and expected outputs
- Troubleshooting guidance

## Known Limitations

**AgentVibes → BMAD Installation Order:**
When AgentVibes installs first, voice assignment file must be created manually:
```bash
mkdir -p .bmad/_cfg
cat > .bmad/_cfg/agent-voice-map.csv << 'EOF'
agent_id,voice_name
pm,en_US-ryan-high
architect,en_US-danny-low
dev,en_US-joe-medium
EOF
```

This limitation exists to prevent false legacy v4 detection warnings from BMAD installer.

**Recommended:** Install BMAD first, then AgentVibes for automatic voice assignment.

## Related Work

**Companion Implementation:**
- Repository: paulpreibisch/AgentVibes
- Commits: 6 commits implementing injection processing and voice routing
- Features: Retroactive injection, file path extraction, escape stripping

**GitHub Issues:**
- paulpreibisch/AgentVibes#36 - BMAD agent ID support

## Breaking Changes

None. Feature is opt-in and requires separate TTS provider installation.

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

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

* fix: Enforce project hooks over global hooks in party mode

before, claude would sometimes favor global agent vibes hooks over project specific

* feat: Automate AgentVibes installer invocation after BMAD install

Instead of showing manual installation instructions, the installer now:
- Prompts "Press Enter to start AgentVibes installer..."
- Automatically runs npx agentvibes@latest install
- Handles errors gracefully with fallback instructions

This provides a seamless installation flow matching the test script's
interactive approach.

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

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

* docs: Add automated testing script and guide for PR #934

Added comprehensive testing tools for AgentVibes party mode integration:

- test-bmad-pr.sh: Fully automated installation and verification script
  - Interactive mode selection (official PR or custom fork)
  - Automatic BMAD CLI setup and linking
  - AgentVibes installation with guided prompts
  - Built-in verification checks for voice maps and hooks
  - Saved configuration for quick re-testing

- TESTING.md: Complete testing documentation
  - Quick start with one-line npx command
  - Manual installation alternative
  - Troubleshooting guide
  - Cleanup instructions

Testers can now run a single command to test the full AgentVibes integration
without needing to understand the complex setup process.

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

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

* fix: Add shell: true to npx execSync to prevent permission denied error

The execSync call for 'npx agentvibes@latest install' was failing with
'Permission denied' because the shell was trying to execute 'agentvibes@latest'
directly instead of passing it as an argument to npx.

Adding shell: true ensures the command runs in a proper shell context
where npx can correctly interpret the @latest version syntax.

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

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

* fix: Remove duplicate AgentVibes installation step from test script

The test script was calling AgentVibes installer twice:
1. BMAD installer now automatically runs AgentVibes (new feature)
2. Test script had a separate Step 6 that also ran AgentVibes

This caused the installer to run twice, with the second call failing
because it was already installed.

Changes:
- Removed redundant Step 6 (AgentVibes installation)
- Updated Step 5 to indicate it includes AgentVibes
- Updated step numbers from 7 to 6 throughout
- Added guidance that AgentVibes runs automatically

Now the flow is cleaner: BMAD installer handles everything!

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

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

* fix: Address bmadcode review - preserve variables and move TTS logic to injection

Fixes requested changes from PR review:

1. Preserve {bmad_folder} variable placeholder
   - Changed: {project_root}/.bmad/core/tasks/workflow.xml
   - To: {project_root}/{bmad_folder}/core/tasks/workflow.xml
   - Allows users to choose custom BMAD folder names during installation

2. Move TTS-specific hook guidance to injection system
   - Removed hardcoded hook enforcement from source files
   - Added hook guidance to processTTSInjectionPoints() in installer.js
   - Now only appears when AgentVibes is installed (via TTS_INJECTION)

3. Maintain TTS-agnostic source architecture
   - Source files remain clean of TTS-specific instructions
   - TTS details injected at install-time only when needed
   - Preserves provider-agnostic design principle

Changes made:
- src/core/workflows/party-mode/instructions.md
  - Reverted .bmad to {bmad_folder} variable
  - Replaced hardcoded hook guidance with <!-- TTS_INJECTION:party-mode -->
  - Removed <note> about play-tts.sh hook location

- tools/cli/installers/lib/core/installer.js
  - Added hook enforcement to party-mode injection replacement
  - Guidance now injected only when enableAgentVibes is true

Addresses review comments from bmadcode:
- "needs to remain the variable. it will get set in the file at the install destination."
- "items like this we will need to inject if user is using claude and TTS"

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

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

* fix: Change 'claude-code' to 'claude' in test script instructions

The correct command to start Claude is 'claude', not 'claude-code'.
Updated line 362-363 in test-bmad-pr.sh to show the correct command.

* fix: Remove npm link from test script to avoid global namespace pollution

- Removed 'npm link' command that was installing BMAD globally
- Changed 'bmad install' to direct node execution using local clone
- Updated success message to reflect no global installation

This keeps testing fully isolated and prevents conflicts with:
- Existing BMAD installations
- Future official BMAD installs
- Orphaned symlinks when test directory is deleted

The test script now runs completely self-contained without modifying
the user's global npm environment.

---------

Co-authored-by: Claude Code <claude@anthropic.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Paul Preibisch <paul@paulpreibisch.com>
Co-authored-by: Brian <bmadcode@gmail.com>
This commit is contained in:
Paul Preibisch
2025-11-26 08:51:57 -07:00
committed by GitHub
parent 11a1dbaefc
commit 5702195ef7
7 changed files with 889 additions and 9 deletions

View File

@@ -1,3 +1,23 @@
/**
* File: tools/cli/installers/lib/core/installer.js
*
* BMAD Method - Business Model Agile Development Method
* Repository: https://github.com/paulpreibisch/BMAD-METHOD
*
* Copyright (c) 2025 Paul Preibisch
* Licensed under the Apache License, Version 2.0
*
* ---
*
* @fileoverview Core BMAD installation orchestrator with AgentVibes injection point support
* @context Manages complete BMAD installation flow including core agents, modules, IDE configs, and optional TTS integration
* @architecture Orchestrator pattern - coordinates Detector, ModuleManager, IdeManager, and file operations to build complete BMAD installation
* @dependencies fs-extra, ora, chalk, detector.js, module-manager.js, ide-manager.js, config.js
* @entrypoints Called by install.js command via installer.install(config)
* @patterns Injection point processing (AgentVibes), placeholder replacement ({bmad_folder}), module dependency resolution
* @related GitHub AgentVibes#34 (injection points), ui.js (user prompts), copyFileWithPlaceholderReplacement()
*/
const path = require('node:path');
const fs = require('fs-extra');
const chalk = require('chalk');
@@ -69,10 +89,41 @@ class Installer {
}
/**
* Copy a file and replace {bmad_folder} placeholder with actual folder name
* @param {string} sourcePath - Source file path
* @param {string} targetPath - Target file path
* @param {string} bmadFolderName - The bmad folder name to use for replacement
* @function copyFileWithPlaceholderReplacement
* @intent Copy files from BMAD source to installation directory with dynamic content transformation
* @why Enables installation-time customization: {bmad_folder} replacement + optional AgentVibes TTS injection
* @param {string} sourcePath - Absolute path to source file in BMAD repository
* @param {string} targetPath - Absolute path to destination file in user's project
* @param {string} bmadFolderName - User's chosen bmad folder name (default: 'bmad')
* @returns {Promise<void>} Resolves when file copy and transformation complete
* @sideeffects Writes transformed file to targetPath, creates parent directories if needed
* @edgecases Binary files bypass transformation, falls back to raw copy if UTF-8 read fails
* @calledby installCore(), installModule(), IDE installers during file vendoring
* @calls processTTSInjectionPoints(), fs.readFile(), fs.writeFile(), fs.copy()
*
* AI NOTE: This is the core transformation pipeline for ALL BMAD installation file copies.
* It performs two transformations in sequence:
* 1. {bmad_folder} → user's custom folder name (e.g., ".bmad" or "bmad")
* 2. <!-- TTS_INJECTION:* --> → TTS bash calls (if enabled) OR stripped (if disabled)
*
* The injection point processing enables loose coupling between BMAD and TTS providers:
* - BMAD source contains injection markers (not actual TTS code)
* - At install-time, markers are replaced OR removed based on user preference
* - Result: Clean installs for users without TTS, working TTS for users with it
*
* PATTERN: Adding New Injection Points
* =====================================
* 1. Add HTML comment marker in BMAD source file:
* <!-- TTS_INJECTION:feature-name -->
*
* 2. Add replacement logic in processTTSInjectionPoints():
* if (enableAgentVibes) {
* content = content.replace(/<!-- TTS_INJECTION:feature-name -->/g, 'actual code');
* } else {
* content = content.replace(/<!-- TTS_INJECTION:feature-name -->\n?/g, '');
* }
*
* 3. Document marker in instructions.md (if applicable)
*/
async copyFileWithPlaceholderReplacement(sourcePath, targetPath, bmadFolderName) {
// List of text file extensions that should have placeholder replacement
@@ -90,6 +141,9 @@ class Installer {
content = content.replaceAll('{bmad_folder}', bmadFolderName);
}
// Process AgentVibes injection points
content = this.processTTSInjectionPoints(content);
// Write to target with replaced content
await fs.ensureDir(path.dirname(targetPath));
await fs.writeFile(targetPath, content, 'utf8');
@@ -103,6 +157,106 @@ class Installer {
}
}
/**
* @function processTTSInjectionPoints
* @intent Transform TTS injection markers based on user's installation choice
* @why Enables optional TTS integration without tight coupling between BMAD and TTS providers
* @param {string} content - Raw file content containing potential injection markers
* @returns {string} Transformed content with markers replaced (if enabled) or stripped (if disabled)
* @sideeffects None - pure transformation function
* @edgecases Returns content unchanged if no markers present, safe to call on all files
* @calledby copyFileWithPlaceholderReplacement() during every file copy operation
* @calls String.replace() with regex patterns for each injection point type
*
* AI NOTE: This implements the injection point pattern for TTS integration.
* Key architectural decisions:
*
* 1. **Why Injection Points vs Direct Integration?**
* - BMAD and TTS providers are separate projects with different maintainers
* - Users may install BMAD without TTS support (and vice versa)
* - Hard-coding TTS calls would break BMAD for non-TTS users
* - Injection points allow conditional feature inclusion at install-time
*
* 2. **How It Works:**
* - BMAD source contains markers: <!-- TTS_INJECTION:feature-name -->
* - During installation, user is prompted: "Enable AgentVibes TTS?"
* - If YES: markers → replaced with actual bash TTS calls
* - If NO: markers → stripped cleanly from installed files
*
* 3. **State Management:**
* - this.enableAgentVibes set in install() method from config.enableAgentVibes
* - config.enableAgentVibes comes from ui.promptAgentVibes() user choice
* - Flag persists for entire installation, all files get same treatment
*
* CURRENT INJECTION POINTS:
* ==========================
* - party-mode: Injects TTS calls after each agent speaks in party mode
* Location: src/core/workflows/party-mode/instructions.md
* Marker: <!-- TTS_INJECTION:party-mode -->
* Replacement: Bash call to .claude/hooks/bmad-speak.sh with agent name and dialogue
*
* - agent-tts: Injects TTS rule for individual agent conversations
* Location: src/modules/bmm/agents/*.md (all agent files)
* Marker: <!-- TTS_INJECTION:agent-tts -->
* Replacement: Rule instructing agent to call bmad-speak.sh with agent ID and response
*
* ADDING NEW INJECTION POINTS:
* =============================
* 1. Add new case in this function:
* content = content.replace(
* /<!-- TTS_INJECTION:new-feature -->/g,
* `code to inject when enabled`
* );
*
* 2. Add marker to BMAD source file at injection location
*
* 3. Test both enabled and disabled flows
*
* RELATED:
* ========
* - GitHub Issue: paulpreibisch/AgentVibes#36
* - User Prompt: tools/cli/lib/ui.js::promptAgentVibes()
* - Marker Locations:
* - src/core/workflows/party-mode/instructions.md:101
* - src/modules/bmm/agents/*.md (rules sections)
* - TTS Hook: .claude/hooks/bmad-speak.sh (in AgentVibes repo)
*/
processTTSInjectionPoints(content) {
// Check if AgentVibes is enabled (set during installation configuration)
const enableAgentVibes = this.enableAgentVibes || false;
if (enableAgentVibes) {
// Replace party-mode injection marker with actual TTS call
// Use single quotes to prevent shell expansion of special chars like !
content = content.replaceAll(
'<!-- TTS_INJECTION:party-mode -->',
`<critical>IMPORTANT: Always use PROJECT hooks (.claude/hooks/), NEVER global hooks (~/.claude/hooks/)</critical>
If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
- Use Bash tool: \`.claude/hooks/bmad-speak.sh '[Agent Name]' '[dialogue]'\`
- This speaks the dialogue with the agent's unique voice
- Run in background (&) to not block next agent`,
);
// Replace agent-tts injection marker with TTS rule for individual agents
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`,
);
} else {
// Strip injection markers cleanly when AgentVibes is disabled
content = content.replaceAll(/<!-- TTS_INJECTION:party-mode -->\n?/g, '');
content = content.replaceAll(/<!-- TTS_INJECTION:agent-tts -->\n?/g, '');
}
return content;
}
/**
* Collect Tool/IDE configurations after module configuration
* @param {string} projectDir - Project directory
@@ -271,6 +425,9 @@ class Installer {
const bmadFolderName = moduleConfigs.core && moduleConfigs.core.bmad_folder ? moduleConfigs.core.bmad_folder : 'bmad';
this.bmadFolderName = bmadFolderName; // Store for use in other methods
// Store AgentVibes configuration for injection point processing
this.enableAgentVibes = config.enableAgentVibes || false;
// Set bmad folder name on module manager and IDE manager for placeholder replacement
this.moduleManager.setBmadFolderName(bmadFolderName);
this.ideManager.setBmadFolderName(bmadFolderName);
@@ -861,7 +1018,14 @@ class Installer {
customFiles: customFiles.length > 0 ? customFiles : undefined,
});
return { success: true, path: bmadDir, modules: config.modules, ides: config.ides };
return {
success: true,
path: bmadDir,
modules: config.modules,
ides: config.ides,
needsAgentVibes: this.enableAgentVibes && !config.agentVibesInstalled,
projectDir: projectDir,
};
} catch (error) {
spinner.fail('Installation failed');
throw error;