hailin
d097c64c81
Implements a two-level abort controller design to support real-time
interruption when the user speaks while the agent is still responding:
sessionAbortController (session-scoped)
- Created once when startSession() is called
- Fired only by terminateSession() (user hangs up)
- Propagated into each turn via addEventListener
turnAbort (per-turn, stored as handle.currentTurnAbort)
- Created fresh at the start of each executeTurn() call
- Stored on the VoiceSessionHandle so injectMessage() can abort it
- When a new inject arrives while a turn is running, injectMessage()
calls turnAbort.abort() BEFORE enqueuing the new message
Interruption flow:
1. User speaks mid-response → LiveKit stops TTS playback (client-side)
2. STT utterance → POST voice/inject → injectMessage() fires
3. handle.currentTurnAbort.abort() called → sets aborted flag
4. for-await loop checks turnAbort.signal.aborted on next SDK event → break
5. catch block NOT reached (break ≠ exception) → no error event emitted
6. finally block saves partial text with "[中断]" suffix to history
7. New message dequeued → fresh executeTurn() starts immediately
Why no "Agent error" message plays to the user:
- break exits the for-await loop silently, not via exception
- The catch block's error-event emission is guarded by err?.name !== 'AbortError'
AND requires an actual exception; a plain break never enters catch
- Empty or partial responses are filtered by `if response:` in agent.py
Also update module-level JSDoc with full architecture explanation covering
the long-lived run loop design, two-level abort hierarchy, tenant context
injection pattern, and SDK session resume across turns.
Update agent.py module docstring to document voice session lifecycle and
interruption flow for future maintainers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
||
|---|---|---|
| deploy | ||
| docs | ||
| it0-web-admin | ||
| it0_app | ||
| packages | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| Dockerfile.service | ||
| README.md | ||
| entrypoint.sh | ||
| logo.svg | ||
| package.json | ||
| pnpm-lock.yaml | ||
| pnpm-workspace.yaml | ||
| tsconfig.base.json | ||
| turbo.json | ||
README.md
IT0 — AI-Powered Server Cluster Operations Platform
Intelligent operations platform that combines AI agents with human oversight for managing server clusters.
Architecture
- Backend: NestJS microservices (TypeScript) with DDD + Clean Architecture
- Mobile: Flutter app with Riverpod state management
- Web Admin: Next.js dashboard with Zustand + React Query
- Voice: Python service for voice-based interaction (STT/TTS/VAD)
Services
| Service | Description |
|---|---|
| auth-service | Authentication, RBAC, API key management |
| agent-service | AI agent orchestration (Claude CLI + API) |
| inventory-service | Server, cluster, credential management |
| monitor-service | Metrics collection, alerting, health checks |
| ops-service | Task execution, approvals, standing orders |
| comm-service | Multi-channel notifications, escalation |
| audit-service | Audit logging, compliance trail |
| voice-service | Voice pipeline (Python) |
Quick Start
# Backend
pnpm install
pnpm dev
# Flutter
cd it0_app && flutter pub get && flutter run
# Web Admin
cd it0-web-admin && pnpm install && pnpm dev
Tech Stack
- Runtime: Node.js 20+, Dart 3.x, Python 3.11+
- Database: PostgreSQL (schema-per-tenant)
- Cache/Events: Redis Streams
- AI: Anthropic Claude (CLI + API)
- Build: pnpm workspaces + Turborepo