agentvibes 2.4.3 → 2.5.0

package/linkedin/vibe-coding-and-pulseaudio.md

@@ -0,0 +1,121 @@
+# Vibe Coding: How PulseAudio Can Give Your Remote SSH Session a Voice!
+
+My mornings and late evenings are when I'm at my creative peak. I like to use this time for things that are fun—or at least that I think are fun. Since I recently created AgentVibes (a way to make my computer speak back to me), I wanted to solve a limitation I was experiencing while working on a remote server. That curiosity led me down the PulseAudio rabbit hole, and what I discovered fundamentally changed how I code with AI.
+
+## What is "Vibe Coding"?
+
+According to Gene Kim, a researcher and author featured in the DORA report, **"vibe coding"** is defined as any form of coding where you don't type out code by hand. Instead of manual typing, the code emerges from an **iterative conversation with an AI**.
+
+This is the future of software development. Not replacing developers, but amplifying our capabilities through natural dialogue.
+
+## If We're Going to Have a Conversation, Let's Use Voice
+
+When I discovered whisper typing several months ago, it fundamentally changed the way I use my computer. Rather than typing everything to my AI assistant, I now **talk** using whisper typing. The speed, the naturalness, the flow—it was transformative.
+
+But then a thought struck me: **If I can talk to my computer, why can't it talk back?**
+
+That question led me to create [**AgentVibes**](https://github.com/paulpreibisch/AgentVibes)—a plugin for Claude Code that brings professional text-to-speech narration to your AI coding sessions. Your AI assistant can now acknowledge your requests, confirm task completion, and provide feedback through voice.
+
+Imagine this workflow:
+- You speak your coding request using whisper typing
+- Your AI assistant acknowledges with voice: "I'll refactor that authentication module for you"
+- You continue working while hearing real-time progress updates
+- The AI confirms: "Refactoring complete, all tests passing"
+
+This is vibe coding at its finest—a natural, conversational flow between human and AI.
+
+## The Remote Server Problem
+
+But I discovered a limitation. Since text-to-speech typically executes on the computer you're programming on, **what happens when you're programming on a remote machine via SSH?**
+
+This is the reality for many developers:
+- Cloud development environments
+- Powerful remote servers
+- Team shared infrastructure
+- Corporate VDI setups
+
+The audio plays on the remote server—where you can't hear it. The conversational flow breaks down. The vibe is lost.
+
+## Enter PulseAudio: The Hidden Hero
+
+I went to task trying to figure out if there was a way to somehow play audio from a remote machine onto my local machine. That's when I was introduced to the true capabilities of **PulseAudio**.
+
+Now, I've been a Linux user for many years and have used PulseAudio forever. But little did I know that **PulseAudio can actually stream audio over a network**, allowing a client to play audio from a remote server.
+
+This completely blew my mind. 🤯
+
+Here's what makes this powerful:
+
+### The Architecture
+```
+Remote Linux Server (PulseAudio)
+    ↓ SSH Reverse Tunnel
+Windows Client (WSL/RDP Audio)
+    ↓
+Local Speakers 🔊
+```
+
+### What This Enables
+- Run AgentVibes on your remote server
+- Hear TTS announcements on your local speakers
+- Maintain the conversational flow of vibe coding
+- Work from anywhere with full audio feedback
+
+I'll tell you, I was **floored** that this was even possible.
+
+## The Game-Changing Impact
+
+The ability to have your AI assistant **acknowledge what you've typed and provide vocal confirmation** really does change the game when vibe coding.
+
+Here's why it matters:
+
+**1. Cognitive Offloading**
+You don't need to constantly check the terminal to see if your AI understood. Voice acknowledgment lets you focus on problem-solving.
+
+**2. Natural Flow State**
+Conversations have rhythm. When both parties speak and listen, you stay in flow. Text-only breaks that rhythm.
+
+**3. Active Guidance with Voice Feedback**
+Vibe coding doesn't mean you stop paying attention—quite the opposite. You're actively guiding the AI through the implementation, reviewing its decisions, and course-correcting in real-time. Voice acknowledgment keeps you in the loop while your hands stay free to sketch architecture, review documentation, or reference other code. The conversation is continuous, and if you're an experienced developer, the depth and precision of that conversation becomes truly transformative.
+
+**4. Reduced Context Switching**
+No need to constantly alt-tab between terminal and code. Your ears keep you updated.
+
+## Try It Yourself
+
+Want to experience vibe coding with remote audio? I've documented the entire setup process.
+
+**Check out AgentVibes:**
+📦 GitHub: [github.com/paulpreibisch/AgentVibes](https://github.com/paulpreibisch/AgentVibes)
+
+**Remote Audio Setup Guide:**
+📚 Complete documentation: [Remote Audio Setup](https://github.com/paulpreibisch/AgentVibes/blob/master/docs/remote-audio-setup.md)
+
+The setup includes:
+- Automated scripts for Linux and Windows
+- PulseAudio network configuration
+- SSH tunnel setup
+- Troubleshooting guides
+- VS Code Remote-SSH integration
+
+It took me a morning to figure out, but now you can set it up in 10 minutes.
+
+## The Bigger Picture
+
+This journey taught me something important: **The best developer tools emerge from solving real problems in your own workflow.**
+
+I didn't set out to become a PulseAudio expert. I just wanted my AI assistant to talk back when I'm working on remote servers. The solution required diving deep into audio streaming, SSH tunneling, and network protocols—but the result is worth it.
+
+Vibe coding isn't just about AI generating code. It's about creating an **environment where human and AI collaborate naturally**—through conversation, through voice, through continuous feedback loops.
+
+And sometimes, that requires discovering that the tools you've been using for years have hidden superpowers you never knew existed.
+
+---
+
+**What's your experience with AI-assisted development? Have you tried vibe coding? Let's discuss in the comments!**
+
+#VibeCoding #AI #DeveloperTools #SoftwareEngineering #PulseAudio #RemoteDevelopment #DevOps #AIAssisted #ClaudeCode #OpenSource
+
+---
+
+*P.S. - If you found this interesting, check out the AgentVibes project on GitHub. It's open source, supports multiple TTS providers (including free Piper TTS), and has 30+ professional AI voices. Star the repo if you find it useful!* ⭐

package/mcp-server/server.py

@@ -440,6 +440,40 @@ class AgentVibesServer:
             return result
         return f"❌ Failed to download extra voices: {result}"
 
+    async def get_verbosity(self) -> str:
+        """
+        Get current verbosity level.
+
+        Returns:
+            Current verbosity level with description
+        """
+        result = await self._run_script("verbosity-manager.sh", ["get"])
+        if result:
+            level = result.strip()
+            descriptions = {
+                "low": "LOW - Acknowledgments + Completions only (minimal)",
+                "medium": "MEDIUM - + Major decisions and findings (balanced)",
+                "high": "HIGH - All reasoning (maximum transparency)"
+            }
+            desc = descriptions.get(level, level)
+            return f"🎙️ Current Verbosity: {desc}\n\n💡 Change with: set_verbosity(level=\"low|medium|high\")"
+        return "❌ Failed to get verbosity level"
+
+    async def set_verbosity(self, level: str) -> str:
+        """
+        Set verbosity level to control how much Claude speaks.
+
+        Args:
+            level: Verbosity level (low, medium, or high)
+
+        Returns:
+            Success or error message
+        """
+        result = await self._run_script("verbosity-manager.sh", ["set", level])
+        if result and "✅" in result:
+            return f"{result}\n\n⚠️  Restart Claude Code for changes to take effect"
+        return f"❌ Failed to set verbosity: {result}"
+
     # Helper methods
     async def _run_script(self, script_name: str, args: list[str]) -> str:
         """Run a bash script and return output"""
@@ -717,6 +751,38 @@ Examples:
                 },
             },
         ),
+        Tool(
+            name="get_verbosity",
+            description="Get current AgentVibes verbosity level (low/medium/high). Verbosity controls how much Claude speaks while working - from minimal (acknowledgments only) to maximum transparency (all reasoning spoken).",
+            inputSchema={"type": "object", "properties": {}},
+        ),
+        Tool(
+            name="set_verbosity",
+            description="""Set AgentVibes verbosity level to control how much Claude speaks while working.
+
+Verbosity Levels:
+- LOW: Only acknowledgments (start) and completions (end). Minimal interruption.
+- MEDIUM: + Major decisions and key findings. Balanced transparency.
+- HIGH: All reasoning, decisions, and findings. Maximum transparency.
+
+Perfect for:
+- LOW: Quiet work sessions, minimal distraction
+- MEDIUM: Understanding major decisions without full narration
+- HIGH: Full transparency, learning mode, debugging complex tasks
+
+Note: Changes take effect on next Claude Code session restart.""",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "level": {
+                        "type": "string",
+                        "description": "Verbosity level to set",
+                        "enum": ["low", "medium", "high"]
+                    }
+                },
+                "required": ["level"],
+            },
+        ),
     ]
 
 
@@ -758,6 +824,10 @@ async def call_tool(name: str, arguments: dict) -> list[TextContent]:
         elif name == "download_extra_voices":
             auto_yes = arguments.get("auto_yes", False)
             result = await agent_vibes.download_extra_voices(auto_yes)
+        elif name == "get_verbosity":
+            result = await agent_vibes.get_verbosity()
+        elif name == "set_verbosity":
+            result = await agent_vibes.set_verbosity(arguments["level"])
         else:
             result = f"Unknown tool: {name}"
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "agentvibes",
-  "version": "2.4.3",
+  "version": "2.5.0",
   "description": "Now your AI Agents can finally talk back! Professional TTS voice for Claude Code and Claude Desktop (via MCP) with multi-provider support.",
   "homepage": "https://agentvibes.org",
   "keywords": [

package/scripts/audio-tunnel.config

@@ -0,0 +1,17 @@
+# AgentVibes Audio Tunnel Configuration
+# Personal configuration - DO NOT COMMIT
+
+# Remote server hostname (from your ~/.ssh/config)
+REMOTE_HOST="ubuntu-rdp"
+
+# Tunnel port (default: 14713)
+TUNNEL_PORT="14713"
+
+# PulseAudio socket path (WSL default)
+PULSE_SOCKET="/mnt/wslg/PulseServer"
+
+# Log file for automatic fixes
+AUTO_FIX_LOG="/tmp/audio-tunnel-autofix.log"
+
+# Healthcheck interval in minutes (for cron setup)
+CHECK_INTERVAL="5"

package/src/installer.js

@@ -113,26 +113,31 @@ function showReleaseInfo() {
   console.log(
     boxen(
       chalk.white.bold('═══════════════════════════════════════════════════════════════\n') +
-      chalk.cyan.bold('  📦 AgentVibes v2.4.1 - macOS Audio Playback Fix\n') +
+      chalk.cyan.bold('  📦 AgentVibes v2.5.0 - Verbosity Control System\n') +
       chalk.white.bold('═══════════════════════════════════════════════════════════════\n\n') +
-      chalk.green.bold('🔊 CRITICAL FIX:\n\n') +
-      chalk.cyan('Fixed macOS Audio Playback\n') +
-      chalk.gray('   • Audio now plays correctly on macOS using native afplay\n') +
-      chalk.gray('   • Resolved silent audio playback issue from v2.4.0\n') +
-      chalk.gray('   • Platform detection for Linux/WSL vs macOS audio players\n') +
-      chalk.gray('   • Thanks to BMadCode for reporting! 🙏\n\n') +
-      chalk.cyan('🍎 macOS Support Complete (v2.4.0 + v2.4.1)\n') +
-      chalk.gray('   • Install via precompiled binaries (no Python/pipx!)\n') +
-      chalk.gray('   • Architecture auto-detection (Apple Silicon & Intel)\n') +
-      chalk.gray('   • Audio playback now working perfectly\n') +
-      chalk.gray('   • Completely free offline TTS for Mac users\n\n') +
+      chalk.green.bold('🎙️ NEW FEATURE:\n\n') +
+      chalk.cyan('Intelligent Verbosity Control\n') +
+      chalk.gray('   • Control how much Claude speaks while working\n') +
+      chalk.gray('   • LOW: Acknowledgments + completions only (minimal)\n') +
+      chalk.gray('   • MEDIUM: + Major decisions and findings (balanced)\n') +
+      chalk.gray('   • HIGH: Full reasoning process (maximum transparency)\n') +
+      chalk.gray('   • Uses emoji markers (💭 🤔 ✓) for automatic TTS\n') +
+      chalk.gray('   • No manual Bash calls needed!\n\n') +
+      chalk.cyan('How to Use:\n') +
+      chalk.gray('   /agent-vibes:verbosity high    # Maximum transparency\n') +
+      chalk.gray('   /agent-vibes:verbosity medium  # Balanced\n') +
+      chalk.gray('   /agent-vibes:verbosity low     # Minimal (default)\n\n') +
+      chalk.cyan('Perfect For:\n') +
+      chalk.gray('   • LOW: Quiet, focused work sessions\n') +
+      chalk.gray('   • MEDIUM: Understanding major decisions\n') +
+      chalk.gray('   • HIGH: Learning mode, debugging complex tasks\n\n') +
       chalk.white.bold('═══════════════════════════════════════════════════════════════\n\n') +
       chalk.green.bold('🚀 TRY LANGUAGE LEARNING MODE:\n\n') +
       chalk.cyan('  /agent-vibes:language english\n') +
       chalk.cyan('  /agent-vibes:target spanish\n') +
       chalk.cyan('  /agent-vibes:learn\n\n') +
-      chalk.white('  Now while coding, you can also learn a second language\n') +
-      chalk.white('  such as Spanish, Italian, French, Mandarin, you name it! 🌍\n\n') +
+      chalk.white('  Learn a second language while coding!\n') +
+      chalk.white('  Spanish, Italian, French, Mandarin, and more! 🌍\n\n') +
       chalk.white.bold('═══════════════════════════════════════════════════════════════\n\n') +
       chalk.gray('📖 Full Release Notes: RELEASE_NOTES.md\n') +
       chalk.gray('🌐 Website: https://agentvibes.org\n') +