L'électron rare
20aed903ba
- Voice pipeline: ESP32 WebSocket client → voice bridge → LLM → Piper TTS (Tower :8001) - Hints engine: 3 puzzles (LA_440, LEFOU_PIANO, QR_FINALE), anti-cheat, 3 hint levels - MCP hardware server: 6 tools (puzzle, audio, LED, camera, scenario, status), stdio transport - Analytics: ESP32 module + 6 web endpoints + Dashboard UI with chat interface - Security: auth middleware (Bearer NVS), rate limiting, input validation on 30 endpoints - Frontend: code-split (1.1MB → 210KB initial), ErrorBoundary, API timeout, WS reconnect - Tests: 24 Python + 38 TypeScript + 18 MCP = 80 project tests (+ 19 mascarade) - Specs: AI_INTEGRATION_SPEC, MCP_HARDWARE_SERVER_SPEC, QA_TEST_MATRIX_SPEC - Docs: SECURITY, DEPLOYMENT_RUNBOOK, voice pipeline guide, AI architecture map - 6 AI agent definitions (.github/agents/ai_*.md) - TUI orchestration script (tools/dev/zacus_tui.py) - Docker compose TTS for Tower + KXKM-AI - CHANGELOG, README, mkdocs.yml updated - Cycle detection (DFS) in runtime3 validator - Sprint plan: plans/SPRINT_AI_INTEGRATION.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1.3 KiB
1.3 KiB
Sprint Plan: AI Integration — Zacus
Sprint 1 (Week 1-2): Security + Voice Foundation
- Deploy auth middleware to main.cpp (integrate security/ module)
- Order INMP441 microphone module
- Deploy Piper TTS Docker on VM (docker-compose.tts.yml)
- Test Piper TTS French voice quality
- Contact Espressif for "Professeur Zacus" wake word training
- Set up ESP-IDF dev environment alongside Arduino
Sprint 2 (Week 2-3): Voice Pipeline Alpha
- Integrate ESP-SR WakeNet with placeholder wake word
- Implement WebSocket audio streaming (ESP32 → mascarade)
- Create mascarade voice bridge endpoint
- Test mic → server → TTS → speaker round-trip
- Measure end-to-end latency (target: <2s)
Sprint 3 (Week 3-4): Vision + Hints
- Deploy ESP-DL v3.2 on ESP32-S3
- Train custom object detection model (3 puzzle props)
- Implement LLM hint endpoint on mascarade
- Create prompt library for Professor Zacus NPC
- Integrate analytics event tracking
Sprint 4 (Week 4): Integration + Polish
- Deploy XTTS-v2 on KXKM-AI for voice cloning
- Record Professor Zacus 10s voice sample
- Full voice pipeline with cloned voice
- AudioCraft ambient generation test
- End-to-end game playtest with AI features