agentvibes 5.1.4 → 5.2.0

package/.agentvibes/config.json

@@ -1,13 +1,23 @@
-{
-  "backgroundMusic": {
-    "track": "agent_vibes_chillwave_v2_loop.mp3",
-    "enabled": true,
-    "volume": 10
-  },
-  "voice": "en_US-libritts-high::Derek-6",
-  "pretext": "AgentVibes here",
-  "provider": "piper",
-  "effects": {
-    "reverbPreset": "light"
-  }
-}
+{
+  "backgroundMusic": {
+    "track": "agent_vibes_chillwave_v2_loop.mp3",
+    "enabled": true,
+    "volume": 10
+  },
+  "voice": "en_US-libritts-high::Derek-6",
+  "pretext": "AgentVibes here",
+  "provider": "piper",
+  "effects": {
+    "reverbPreset": "light"
+  },
+  "setupCompleted": true,
+  "thumbsUp": [
+    "en_US-libritts-high::Adam-10",
+    "en_US-libritts-high::Leo-7"
+  ],
+  "favorites": [
+    "en_US-libritts-high::Adam-10",
+    "en_US-libritts-high::Leo-7"
+  ],
+  "thumbsDown": []
+}

package/.claude/commands/agent-vibes/verbosity.md

@@ -1,89 +1,98 @@
----
-description: Get or set AgentVibes verbosity level (low/medium/high)
-tags: [user]
----
-
-Get or set the AgentVibes verbosity level to control how much Claude speaks while working.
-
-## Usage
-
-- `/agent-vibes:verbosity` - Show current verbosity level
-- `/agent-vibes:verbosity low` - Set to LOW (minimal)
-- `/agent-vibes:verbosity medium` - Set to MEDIUM (balanced)
-- `/agent-vibes:verbosity high` - Set to HIGH (maximum transparency)
-
-## Verbosity Levels
-
-### LOW (Minimal)
-- ✅ Acknowledgments only (start of task)
-- ✅ Completions only (end of task)
-- 🔇 No reasoning spoken during work
-- Perfect for: Quiet work sessions, minimal distraction
-
-### MEDIUM (Balanced)
-- ✅ Acknowledgments
-- 🤔 Major decisions ("I'll use grep to search")
-- ✓ Key findings ("Found 12 instances")
-- ✅ Completions
-- Perfect for: Understanding major decisions without full narration
-
-### HIGH (Maximum Transparency)
-- ✅ Acknowledgments
-- 💭 All reasoning ("Let me search for all instances")
-- 🤔 All decisions ("I'll use grep for this")
-- ✓ All findings ("Found it at line 1323")
-- ✅ Completions
-- Perfect for: Full transparency, learning mode, debugging complex tasks
-
-## How It Works
-
-Claude uses **emoji markers** in its reasoning text:
-- 💭 = Reasoning/thinking
-- 🤔 = Decisions
-- ✓ = Findings/results
-
-Based on your verbosity level, AgentVibes automatically detects these markers and speaks them aloud.
-
-## Examples
-
-### LOW Verbosity
-```
-User: "Find all TODO comments"
-[TTS: "I'll search for those"]
-[Work happens silently...]
-[TTS: "Found 12 TODO comments"]
-```
-
-### MEDIUM Verbosity
-```
-User: "Find all TODO comments"
-[TTS: "I'll search for those"]
-🤔 I'll use grep to search all files
-[Work happens...]
-✓ Found 12 TODO comments across 5 files
-[TTS: "Found 12 TODO comments"]
-```
-
-### HIGH Verbosity
-```
-User: "Find all TODO comments"
-[TTS: "I'll search for those"]
-💭 Let me search through the codebase for TODO comments
-🤔 I'll use the Grep tool with pattern "TODO"
-[Grep runs...]
-✓ Found 12 TODO comments across 5 files
-💭 Let me organize these by file
-[TTS: "Found 12 TODO comments in 5 files"]
-```
-
-## Notes
-
-- Changes take effect on next Claude Code session restart
-- Verbosity is saved per-project (if `.claude/` exists) or globally
-- You can also control verbosity via MCP: `mcp__agentvibes__set_verbosity(level="high")`
-
-## Related Commands
-
-- `/agent-vibes:personality` - Set voice personality style
-- `/agent-vibes:switch` - Change voice
-- `/agent-vibes:provider` - Switch TTS provider
+---
+description: Get or set AgentVibes verbosity level (low/medium/high/caveman)
+tags: [user]
+---
+
+Get or set the AgentVibes verbosity level to control how much Claude speaks while working.
+
+## Usage
+
+- `/agent-vibes:verbosity` - Show current verbosity level
+- `/agent-vibes:verbosity low` - Set to LOW (minimal)
+- `/agent-vibes:verbosity medium` - Set to MEDIUM (balanced)
+- `/agent-vibes:verbosity high` - Set to HIGH (maximum transparency)
+- `/agent-vibes:verbosity caveman` - Set to CAVEMAN (ultra-terse, max token savings)
+
+## Verbosity Levels
+
+### LOW (Minimal)
+- ✅ Acknowledgments only (start of task)
+- ✅ Completions only (end of task)
+- 🔇 No reasoning spoken during work
+- Perfect for: Quiet work sessions, minimal distraction
+
+### MEDIUM (Balanced)
+- ✅ Acknowledgments
+- 🤔 Major decisions ("I'll use grep to search")
+- ✓ Key findings ("Found 12 instances")
+- ✅ Completions
+- Perfect for: Understanding major decisions without full narration
+
+### HIGH (Maximum Transparency)
+- ✅ Acknowledgments
+- 💭 All reasoning ("Let me search for all instances")
+- 🤔 All decisions ("I'll use grep for this")
+- ✓ All findings ("Found it at line 1323")
+- ✅ Completions
+- Perfect for: Full transparency, learning mode, debugging complex tasks
+
+### CAVEMAN (Ultra-Terse)
+- ⚡ Fragments only — no articles, filler, or hedging
+- 🔤 Abbreviations (DB/auth/config/fn/impl)
+- ➡️ Arrows instead of prose (X -> Y)
+- 📉 65-75% fewer output tokens
+- Perfect for: Maximum token savings, cost-conscious sessions
+- Inspired by [caveman](https://github.com/JuliusBrussee/caveman) (MIT)
+
+## How It Works
+
+Claude uses **emoji markers** in its reasoning text:
+- 💭 = Reasoning/thinking
+- 🤔 = Decisions
+- ✓ = Findings/results
+
+Based on your verbosity level, AgentVibes automatically detects these markers and speaks them aloud.
+
+## Examples
+
+### LOW Verbosity
+```
+User: "Find all TODO comments"
+[TTS: "I'll search for those"]
+[Work happens silently...]
+[TTS: "Found 12 TODO comments"]
+```
+
+### MEDIUM Verbosity
+```
+User: "Find all TODO comments"
+[TTS: "I'll search for those"]
+🤔 I'll use grep to search all files
+[Work happens...]
+✓ Found 12 TODO comments across 5 files
+[TTS: "Found 12 TODO comments"]
+```
+
+### HIGH Verbosity
+```
+User: "Find all TODO comments"
+[TTS: "I'll search for those"]
+💭 Let me search through the codebase for TODO comments
+🤔 I'll use the Grep tool with pattern "TODO"
+[Grep runs...]
+✓ Found 12 TODO comments across 5 files
+💭 Let me organize these by file
+[TTS: "Found 12 TODO comments in 5 files"]
+```
+
+## Notes
+
+- Changes take effect on next Claude Code session restart
+- Verbosity is saved per-project (if `.claude/` exists) or globally
+- You can also control verbosity via MCP: `mcp__agentvibes__set_verbosity(level="high")`
+
+## Related Commands
+
+- `/agent-vibes:personality` - Set voice personality style
+- `/agent-vibes:switch` - Change voice
+- `/agent-vibes:provider` - Switch TTS provider

package/.claude/config/audio-effects.cfg

@@ -50,7 +50,10 @@ _party_mode|compand 0.3,1 6:-70,-60,-20|agent_vibes_dark_chill_step_loop.mp3|0.4
 |||
 # Default (no agent specified) - clean with Bachata background|||
 default||agent_vibes_chillwave_v2_loop.mp3|0.15
+|||
+# Claude Code LLM default - pretext + music for remote receivers without per-LLM config|||
+llm:default|reverb 20 50 50|agent_vibes_chillwave_v2_loop.mp3|0.15||AgentVibes here
 analyst|reverb 70 50 100|agentvibes_soft_flamenco_loop.mp3|0.30
-llm:claude-code|light|agent_vibes_chillwave_v2_loop.mp3|0.15|en_US-lessac-high|Claude Code here|piper
+llm:claude-code|light|Midnight Charleston Stomp.mp3|0.15|en_US-libritts-high::Leo-7|AgentVibes here|piper
 llm:copilot|light|agent_vibes_bossa_nova_v2_loop.mp3|0.15|en_US-libritts-high::Anna-11|Copilot here|piper
 llm:codex|light|agent_vibes_chillwave_v2_loop.mp3|0.15|en_US-lessac-high|Codex here|piper

package/.claude/hooks/bmad-speak.sh

@@ -203,11 +203,11 @@ AGENT_VOICE="$PROFILE_VOICE"
 AGENT_INTRO="$PROFILE_PRETEXT"
 
 if [[ -z "$AGENT_VOICE" ]] && [[ -n "$AGENT_ID" ]] && [[ -f "$SCRIPT_DIR/bmad-voice-manager.sh" ]]; then
-  AGENT_VOICE=$(cd "$PROJECT_ROOT" && "$SCRIPT_DIR/bmad-voice-manager.sh" get-voice "$AGENT_ID" 2>/dev/null || true)
+  AGENT_VOICE=$(cd "$PROJECT_ROOT" && bash "$SCRIPT_DIR/bmad-voice-manager.sh" get-voice "$AGENT_ID" 2>/dev/null || true)
 fi
 
 if [[ -z "$AGENT_INTRO" ]] && [[ -n "$AGENT_ID" ]] && [[ -f "$SCRIPT_DIR/bmad-voice-manager.sh" ]]; then
-  AGENT_INTRO=$(cd "$PROJECT_ROOT" && "$SCRIPT_DIR/bmad-voice-manager.sh" get-intro "$AGENT_ID" 2>/dev/null || true)
+  AGENT_INTRO=$(cd "$PROJECT_ROOT" && bash "$SCRIPT_DIR/bmad-voice-manager.sh" get-intro "$AGENT_ID" 2>/dev/null || true)
 fi
 
 # ---------------------------------------------------------------------------