┌─────────────────────────────────────────────────────────────┐
│  Docker Container                                            │
│                                                             │
│  ┌─────────────────────────────────────────────────────┐    │
│  │  MCP Server (port 8360)                              │    │
│  │                                                     │    │
│  │  Audio Tools:                                       │    │
│  │    tts_to_mic(text)     → Piper TTS → virtual mic   │    │
│  │    transcribe_speakers() → parec → Whisper STT      │    │
│  │    inject_audio(b64)    → raw audio → virtual mic   │    │
│  │    capture_audio(secs)  → raw audio from speakers   │    │
│  │    wait_for_speech()    → detect + transcribe       │    │
│  │                                                     │    │
│  │  Browser Tools:                                     │    │
│  │    browser_navigate, click, type, screenshot, etc.  │    │
│  │    browser_grant_mic_permission(origin)             │    │
│  │                                                     │    │
│  │  Screen Tools:                                      │    │
│  │    screen_screenshot, screen_size, vnc_url          │    │
│  └──────────┬──────────────────────────┬───────────────┘    │
│             │                          │                     │
│  ┌──────────▼──────────┐  ┌───────────▼───────────────┐    │
│  │  PulseAudio         │  │  Playwright + Chromium    │    │
│  │                     │  │                           │    │
│  │  virtual_mic ◀──────│──│── browser reads as mic    │    │
│  │  (pipe-source)      │  │                           │    │
│  │                     │  │  browser plays audio ──▶  │    │
│  │  virtual_speaker ───│──│── captured via .monitor   │    │
│  │  (null-sink)        │  │                           │    │
│  └─────────────────────┘  └───────────────────────────┘    │
│                                                             │
│  ┌─────────────────────┐  ┌───────────────────────────┐    │
│  │  Xvfb :99           │  │  x11vnc + noVNC          │    │
│  │  1920x1080x24       │  │  port 5900 / 6080        │    │
│  └─────────────────────┘  └───────────────────────────┘    │
└─────────────────────────────────────────────────────────────┘

# Build and start
docker compose up -d --build

# Watch the virtual display (open in your browser)
open http://localhost:6080/vnc.html?autoconnect=true

# Test the MCP server
curl http://localhost:8360/mcp -X POST \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"health","arguments":{}}}'

# Run smoke tests
bash test-smoke.sh

# 1. Build and start
docker compose up -d --build

# 2. Open VNC in your browser to see the desktop
open http://localhost:6080/vnc.html?autoconnect=true

# 3. In the VNC window, Chromium is running. Log into:
#    - https://chat.openai.com (ChatGPT)
#    - https://gemini.google.com (Gemini)

# 4. Export cookies to DragonsKeep so they persist
bash scripts/export-browser-cookies.sh

# 5. Done! Future container starts auto-inject the stored sessions.

# Infrastructure tests (no login required)
cd tests && pip install -r requirements.txt
pytest test_audio_roundtrip.py test_browser.py -v

# ChatGPT conversation tests (requires login)
pytest test_conversations.py -v -m chatgpt --timeout=120

# Gemini conversation tests
pytest test_conversations.py -v -m gemini --timeout=120

# Our Mesh UI conversation tests
pytest test_conversations.py -v -m meshui --timeout=120

# All conversation tests
pytest test_conversations.py -v --timeout=120

# From any MCP client (Kiro, our mesh agent, etc.)

# 1. Navigate to ChatGPT
browser_navigate("https://chat.openai.com")

# 2. Grant mic permission
browser_grant_mic_permission("https://chat.openai.com")

# 3. Click the voice mode button
browser_click("[data-testid='voice-mode-button']")

# 4. Speak a question (injected into the virtual mic)
tts_to_mic("What is the capital of France?")

# 5. Wait for ChatGPT to respond and transcribe what it says
response = wait_for_speech(timeout_seconds=15)
# response == "The capital of France is Paris."

# 6. Assert
assert "Paris" in response