feat: v2.0 — maintenance module, AI analysis, station power fix

- Add full 检修维护中心 (6.4): 3-type work orders (消缺/巡检/抄表),
  asset management, warehouse, work plans, billing settlement
- Add AI智能分析 tab with LLM-powered diagnostics (StepFun + ZhipuAI)
- Add AI模型配置 settings page (provider, temperature, prompts)
- Fix station power accuracy: use API station total (station_power)
  instead of inverter-level computation — eliminates timing gaps
- Add 7 new DB models, 4 new API routers, 5 new frontend pages
- Migrations: 009 (maintenance expansion) + 010 (AI analysis)
- Version bump: 1.6.1 → 2.0.0

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

core/backend/app/models/ai_ops.py

@@ -86,3 +86,21 @@ class OpsInsight(Base):
     generated_at = Column(DateTime(timezone=True), server_default=func.now())
     valid_until = Column(DateTime(timezone=True))
     created_at = Column(DateTime(timezone=True), server_default=func.now())
+
+
+class AIAnalysisResult(Base):
+    """AI智能分析结果"""
+    __tablename__ = "ai_analysis_results"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    scope = Column(String(20), default="station")  # device, station, all
+    device_id = Column(Integer, ForeignKey("devices.id"), nullable=True)
+    analysis_type = Column(String(20), default="diagnostic")  # diagnostic, insight, custom
+    prompt_used = Column(Text)
+    result_text = Column(Text)
+    model_used = Column(String(100))
+    provider_used = Column(String(20))  # stepfun, zhipu
+    tokens_used = Column(Integer)
+    duration_ms = Column(Integer)
+    created_by = Column(Integer, ForeignKey("users.id"))
+    created_at = Column(DateTime(timezone=True), server_default=func.now())