hailin
ce13c8b770
fix(agents): remove official website referral from fallback labels, use neutral disclaimer
...
Replace "请以入境处官方信息为准" / "建议向香港入境处官网核实" with
"基于AI训练数据，可能不是最新信息" across all fallback messages.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 22:10:45 -08:00
hailin
04dbc61131
feat(agents): add capability boundary guardrails — input gate, cascading fallback, output gate rules
...
Four guardrail improvements to enforce agent capability boundaries:
1. Cascading Fallback (Fix 1+4):
- Rewrite searchKnowledge() in immigration-tools.service.ts with 3-tier fallback:
KB (similarity >= 0.55) → Web Search → Built-in Knowledge (clearly labeled)
- Rewrite executeTool() in policy-expert.service.ts to use retrieveKnowledge()
with confidence threshold; returns [KB_EMPTY]/[KB_LOW_CONFIDENCE]/[KB_ERROR]
markers so the model knows to label source reliability
2. Input Gate (Fix 2):
- New InputGateService using Haiku for lightweight pre-classification
- Classifications: ON_TOPIC / OFF_TOPIC (threshold >= 0.7) / HARMFUL (>= 0.6)
- Short messages (< 5 chars) fast-path to ON_TOPIC
- Gate failure is non-fatal (allows message through)
- Integrated in CoordinatorAgentService.sendMessage() before agent loop entry
- OFF_TOPIC/HARMFUL messages get fixed responses without entering agent loop
3. Output Gate Enhancement (Fix 3):
- Add TOPIC_BOUNDARY and NO_FABRICATION to EvaluationRuleType
- TOPIC_BOUNDARY: regex detection for code blocks, programming keywords,
AI identity exposure, off-topic indicators in agent responses
- NO_FABRICATION: detects policy claims without policy_expert invocation
or source markers; ensures factual claims are knowledge-backed
- Both rule types are admin-configurable (zero rules = zero checks)
- No DB migration needed (ruleType is varchar(50))
Files changed:
- NEW: agents/coordinator/input-gate.service.ts
- MOD: agents/coordinator/coordinator-agent.service.ts (inject InputGate + gate check)
- MOD: agents/agents.module.ts (register InputGateService)
- MOD: agents/coordinator/evaluation-gate.service.ts (2 new evaluators)
- MOD: domain/entities/evaluation-rule.entity.ts (2 new rule types)
- MOD: agents/specialists/policy-expert.service.ts (RAG confidence threshold)
- MOD: claude/tools/immigration-tools.service.ts (cascading fallback)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 21:59:10 -08:00
hailin
4c125f3276
feat(agent): add 4 real-time tools for enhanced agent capabilities
...
Add the following real-time tools to ImmigrationToolsService:
- get_current_datetime: Get current date/time with timezone support
- web_search: Search internet for latest immigration news/policies (Google CSE)
- get_exchange_rate: Query real-time currency exchange rates (for investment immigration)
- fetch_immigration_news: Fetch latest immigration announcements
All tools include graceful degradation with fallback responses when external APIs are unavailable.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 00:46:55 -08:00
hailin
911132ab3e
feat(agent): upgrade to Level 3 with real RAG, Memory and Evolution integration
...
## Summary
Upgrade iConsulting from Level 2 (48 points) to Level 3 (68 points) by
implementing real service-to-service integration between conversation-service
and knowledge-service.
## New Files
- knowledge-client.service.ts: HTTP client for knowledge-service APIs
- knowledge.module.ts: NestJS module for KnowledgeClientService
- AGENT_EVALUATION_REPORT.md: Agent capability evaluation report
- LEVEL3_UPGRADE_PLAN.md: Upgrade plan and completion report
## Changes
### RAG Integration
- search_knowledge tool now calls /api/v1/knowledge/retrieve
- check_off_topic tool calls /api/v1/knowledge/check-off-topic
- Results include real vector similarity search from knowledge base
### Memory Integration
- save_user_memory writes to PostgreSQL + Neo4j via knowledge-service
- collect_assessment_info saves user data to long-term memory
- generate_payment records payment intent to user memory
- New get_user_context tool retrieves user's historical memories
### Evolution Integration
- getAccumulatedExperience() fetches approved system experiences
- sendMessage() dynamically injects experiences into system prompt
- System learns from approved experiences across all conversations
## Expected Score Improvement
| Dimension | Before | After | Delta |
|------------|--------|-------|-------|
| Tool Use | 14/20 | 18/20 | +4 |
| Memory | 12/20 | 16/20 | +4 |
| RAG | 10/20 | 16/20 | +6 |
| Evolution | 8/20 | 14/20 | +6 |
| Total | 48 | 68 | +20 |
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-22 23:45:58 -08:00
hailin
a7add8ff90
Initial commit: iConsulting 香港移民咨询智能客服系统
...
项目架构:
- Monorepo (pnpm + Turborepo)
- 后端: NestJS 微服务 + Claude Agent SDK
- 前端: React + Vite + Ant Design
包含服务:
- conversation-service: 对话服务 (Claude AI)
- user-service: 用户认证服务
- payment-service: 支付服务 (支付宝/微信/Stripe)
- knowledge-service: 知识库服务 (RAG + Neo4j)
- evolution-service: 自我进化服务
- web-client: 用户前端
- admin-client: 管理后台
基础设施:
- PostgreSQL + Redis + Neo4j
- Kong API Gateway
- Nginx 反向代理
- Docker Compose 部署配置
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-09 00:01:12 -08:00
hailin