Merge branch 'alphaFuthures'

.gitignore

@@ -0,0 +1,29 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+dist/
+build/
+
+# Virtual environments
+venv/
+.venv/
+
+
+# Logs
+*.log
+data/collector.log
+
+# IDE
+.vscode/
+.idea/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Cache
+cache/*.pkl

DESIGN.md

@@ -0,0 +1,185 @@
+# Design System Inspired by Revolut
+
+## 1. Visual Theme & Atmosphere
+
+Revolut's website is fintech confidence distilled into pixels — a design system that communicates "your money is in capable hands" through massive typography, generous whitespace, and a disciplined neutral palette. The visual language is built on Aeonik Pro, a geometric grotesque that creates billboard-scale headlines at 136px with weight 500 and aggressive negative tracking (-2.72px). This isn't subtle branding; it's fintech at stadium scale.
+
+The color system is built on a comprehensive `--rui-*` (Revolut UI) token architecture with semantic naming for every state: danger (`#e23b4a`), warning (`#ec7e00`), teal (`#00a87e`), blue (`#494fdf`), deep-pink (`#e61e49`), and more. But the marketing surface itself is remarkably restrained — near-black (`#191c1f`) and pure white (`#ffffff`) dominate, with the colorful semantic tokens reserved for the product interface, not the marketing page.
+
+What distinguishes Revolut is its pill-everything button system. Every button uses 9999px radius — primary dark (`#191c1f`), secondary light (`#f4f4f4`), outlined (`transparent + 2px solid`), and ghost on dark (`rgba(244,244,244,0.1) + 2px solid`). The padding is generous (14px 32px–34px), creating large, confident touch targets. Combined with Inter for body text at various weights and positive letter-spacing (0.16px–0.24px), the result is a design that feels both premium and accessible — banking for the modern era.
+
+**Key Characteristics:**
+- Aeonik Pro display at 136px weight 500 — billboard-scale fintech headlines
+- Near-black (`#191c1f`) + white binary with comprehensive `--rui-*` semantic tokens
+- Universal pill buttons (9999px radius) with generous padding (14px 32px)
+- Inter for body text with positive letter-spacing (0.16px–0.24px)
+- Rich semantic color system: blue, teal, pink, yellow, green, brown, danger, warning
+- Zero shadows detected — depth through color contrast only
+- Tight display line-heights (1.00) with relaxed body (1.50–1.56)
+
+## 2. Color Palette & Roles
+
+### Primary
+- **Revolut Dark** (`#191c1f`): Primary dark surface, button background, near-black text
+- **Pure White** (`#ffffff`): `--rui-color-action-label`, primary light surface
+- **Light Surface** (`#f4f4f4`): Secondary button background, subtle surface
+
+### Brand / Interactive
+- **Revolut Blue** (`#494fdf`): `--rui-color-blue`, primary brand blue
+- **Action Blue** (`#4f55f1`): `--rui-color-action-photo-header-text`, header accent
+- **Blue Text** (`#376cd5`): `--website-color-blue-text`, link blue
+
+### Semantic
+- **Danger Red** (`#e23b4a`): `--rui-color-danger`, error/destructive
+- **Deep Pink** (`#e61e49`): `--rui-color-deep-pink`, critical accent
+- **Warning Orange** (`#ec7e00`): `--rui-color-warning`, warning states
+- **Yellow** (`#b09000`): `--rui-color-yellow`, attention
+- **Teal** (`#00a87e`): `--rui-color-teal`, success/positive
+- **Light Green** (`#428619`): `--rui-color-light-green`, secondary success
+- **Green Text** (`#006400`): `--website-color-green-text`, green text
+- **Light Blue** (`#007bc2`): `--rui-color-light-blue`, informational
+- **Brown** (`#936d62`): `--rui-color-brown`, warm neutral accent
+- **Red Text** (`#8b0000`): `--website-color-red-text`, dark red text
+
+### Neutral Scale
+- **Mid Slate** (`#505a63`): Secondary text
+- **Cool Gray** (`#8d969e`): Muted text, tertiary
+- **Gray Tone** (`#c9c9cd`): `--rui-color-grey-tone-20`, borders/dividers
+
+## 3. Typography Rules
+
+### Font Families
+- **Display**: `Aeonik Pro` — geometric grotesque, no detected fallbacks
+- **Body / UI**: `Inter` — standard system sans
+- **Fallback**: `Arial` for specific button contexts
+
+### Hierarchy
+
+| Role | Font | Size | Weight | Line Height | Letter Spacing | Notes |
+|------|------|------|--------|-------------|----------------|-------|
+| Display Mega | Aeonik Pro | 136px (8.50rem) | 500 | 1.00 (tight) | -2.72px | Stadium-scale hero |
+| Display Hero | Aeonik Pro | 80px (5.00rem) | 500 | 1.00 (tight) | -0.8px | Primary hero |
+| Section Heading | Aeonik Pro | 48px (3.00rem) | 500 | 1.21 (tight) | -0.48px | Feature sections |
+| Sub-heading | Aeonik Pro | 40px (2.50rem) | 500 | 1.20 (tight) | -0.4px | Sub-sections |
+| Card Title | Aeonik Pro | 32px (2.00rem) | 500 | 1.19 (tight) | -0.32px | Card headings |
+| Feature Title | Aeonik Pro | 24px (1.50rem) | 400 | 1.33 | normal | Light headings |
+| Nav / UI | Aeonik Pro | 20px (1.25rem) | 500 | 1.40 | normal | Navigation, buttons |
+| Body Large | Inter | 18px (1.13rem) | 400 | 1.56 | -0.09px | Introductions |
+| Body | Inter | 16px (1.00rem) | 400 | 1.50 | 0.24px | Standard reading |
+| Body Semibold | Inter | 16px (1.00rem) | 600 | 1.50 | 0.16px | Emphasized body |
+| Body Bold Link | Inter | 16px (1.00rem) | 700 | 1.50 | 0.24px | Bold links |
+
+### Principles
+- **Weight 500 as display default**: Aeonik Pro uses medium (500) for ALL headings — no bold. This creates authority through size and tracking, not weight.
+- **Billboard tracking**: -2.72px at 136px is extremely compressed — text designed to be read at a glance, like airport signage.
+- **Positive tracking on body**: Inter uses +0.16px to +0.24px, creating airy, well-spaced reading text that contrasts with the compressed headings.
+
+## 4. Component Stylings
+
+### Buttons
+
+**Primary Dark Pill**
+- Background: `#191c1f`
+- Text: `#ffffff`
+- Padding: 14px 32px
+- Radius: 9999px (full pill)
+- Hover: opacity 0.85
+- Focus: `0 0 0 0.125rem` ring
+
+**Secondary Light Pill**
+- Background: `#f4f4f4`
+- Text: `#000000`
+- Padding: 14px 34px
+- Radius: 9999px
+- Hover: opacity 0.85
+
+**Outlined Pill**
+- Background: transparent
+- Text: `#191c1f`
+- Border: `2px solid #191c1f`
+- Padding: 14px 32px
+- Radius: 9999px
+
+**Ghost on Dark**
+- Background: `rgba(244, 244, 244, 0.1)`
+- Text: `#f4f4f4`
+- Border: `2px solid #f4f4f4`
+- Padding: 14px 32px
+- Radius: 9999px
+
+### Cards & Containers
+- Radius: 12px (small), 20px (cards)
+- No shadows — flat surfaces with color contrast
+- Dark and light section alternation
+
+### Navigation
+- Aeonik Pro 20px weight 500
+- Clean header, hamburger toggle at 12px radius
+- Pill CTAs right-aligned
+
+## 5. Layout Principles
+
+### Spacing System
+- Base unit: 8px
+- Scale: 4px, 6px, 8px, 14px, 16px, 20px, 24px, 32px, 40px, 48px, 80px, 88px, 120px
+- Large section spacing: 80px–120px
+
+### Border Radius Scale
+- Standard (12px): Navigation, small buttons
+- Card (20px): Feature cards
+- Pill (9999px): All buttons
+
+## 6. Depth & Elevation
+
+| Level | Treatment | Use |
+|-------|-----------|-----|
+| Flat (Level 0) | No shadow | Everything — Revolut uses zero shadows |
+| Focus | `0 0 0 0.125rem` ring | Accessibility focus |
+
+**Shadow Philosophy**: Revolut uses ZERO shadows. Depth comes entirely from the dark/light section contrast and the generous whitespace between elements.
+
+## 7. Do's and Don'ts
+
+### Do
+- Use Aeonik Pro weight 500 for all display headings
+- Apply 9999px radius to all buttons — pill shape is universal
+- Use generous button padding (14px 32px)
+- Keep the palette to near-black + white for marketing surfaces
+- Apply positive letter-spacing on Inter body text
+
+### Don't
+- Don't use shadows — Revolut is flat by design
+- Don't use bold (700) for Aeonik Pro headings — 500 is the weight
+- Don't use small buttons — the generous padding is intentional
+- Don't apply semantic colors to marketing surfaces — they're for the product
+
+## 8. Responsive Behavior
+
+### Breakpoints
+| Name | Width | Key Changes |
+|------|-------|-------------|
+| Mobile Small | <400px | Compact, single column |
+| Mobile | 400–720px | Standard mobile |
+| Tablet | 720–1024px | 2-column layouts |
+| Desktop | 1024–1280px | Standard desktop |
+| Large | 1280–1920px | Full layout |
+
+## 9. Agent Prompt Guide
+
+### Quick Color Reference
+- Dark: Revolut Dark (`#191c1f`)
+- Light: White (`#ffffff`)
+- Surface: Light (`#f4f4f4`)
+- Blue: Revolut Blue (`#494fdf`)
+- Danger: Red (`#e23b4a`)
+- Success: Teal (`#00a87e`)
+
+### Example Component Prompts
+- "Create a hero: white background. Headline at 136px Aeonik Pro weight 500, line-height 1.00, letter-spacing -2.72px, #191c1f text. Dark pill CTA (#191c1f, 9999px, 14px 32px). Outlined pill secondary (transparent, 2px solid #191c1f)."
+- "Build a pill button: #191c1f background, white text, 9999px radius, 14px 32px padding, 20px Aeonik Pro weight 500. Hover: opacity 0.85."
+
+### Iteration Guide
+1. Aeonik Pro 500 for headings — never bold
+2. All buttons are pills (9999px) with generous padding
+3. Zero shadows — flat is the Revolut identity
+4. Near-black + white for marketing, semantic colors for product

app/analysis_db.py

@@ -0,0 +1,40 @@
+"""
+期货智析数据库 - 独立存储
+"""
+from pathlib import Path
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker, declarative_base
+from datetime import datetime
+
+# 数据目录
+DATA_DIR = Path(__file__).resolve().parent.parent / "data"
+DATA_DIR.mkdir(parents=True, exist_ok=True)
+
+ANALYSIS_DB_PATH = DATA_DIR / "futures_analysis.db"
+
+analysis_engine = create_engine(
+    f"sqlite:///{ANALYSIS_DB_PATH}",
+    connect_args={"check_same_thread": False},
+    pool_pre_ping=True,
+)
+
+AnalysisSessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=analysis_engine)
+AnalysisBase = declarative_base()
+
+
+def get_analysis_db():
+    """获取期货智析数据库会话"""
+    db = AnalysisSessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()
+
+
+def init_analysis_db():
+    """初始化期货智析数据库表"""
+    # 确保导入所有模型类，使其注册到 AnalysisBase
+    from app import analysis_models
+    # 直接导入 analysis_models 模块中的所有类
+    from app.analysis_models import FuturesAnalysis, WatchedSymbol, AIModelConfig, AnalysisSettings, AIAnalysisCache
+    AnalysisBase.metadata.create_all(bind=analysis_engine)

app/analysis_models.py

@@ -0,0 +1,102 @@
+"""
+期货智析数据模型
+"""
+from datetime import datetime
+from sqlalchemy import Column, String, Integer, Float, Text, DateTime, Boolean, Index, UniqueConstraint, JSON
+from app.analysis_db import AnalysisBase
+
+
+class FuturesAnalysis(AnalysisBase):
+    """期货分析报告表"""
+    __tablename__ = "futures_analysis"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    symbol = Column(String(32), nullable=False, index=True, comment="品种合约代码")
+    analysis_time = Column(DateTime, nullable=False, default=datetime.now, index=True, comment="分析时间")
+    period = Column(String(16), nullable=False, default="15min", comment="分析周期")
+    # 分析结果
+    suggestion = Column(String(32), nullable=True, comment="交易建议: 逢低做多/逢高做空/观望等待")
+    suggestion_type = Column(String(16), nullable=True, comment="建议类型: up/down/neutral")
+    entry_price = Column(Float, nullable=True, comment="建议入场价")
+    target_price = Column(Float, nullable=True, comment="目标价位")
+    stop_loss = Column(Float, nullable=True, comment="止损价位")
+    risk_level = Column(String(16), nullable=True, comment="风险等级: 低/中/高")
+    # 技术指标
+    macd_signal = Column(String(16), nullable=True, comment="MACD信号")
+    rsi_value = Column(Float, nullable=True, comment="RSI值")
+    boll_signal = Column(String(16), nullable=True, comment="布林带信号")
+    kdj_signal = Column(String(16), nullable=True, comment="KDJ信号")
+    # 趋势评分
+    trend_score = Column(Integer, nullable=True, comment="趋势评分 0-100")
+    success_rate = Column(Float, nullable=True, comment="交易成功率")
+    # 关键点位
+    resistance_levels = Column(JSON, nullable=True, comment="压力位列表")
+    support_levels = Column(JSON, nullable=True, comment="支撑位列表")
+    # 多周期趋势
+    period_trends = Column(JSON, nullable=True, comment="各周期趋势")
+
+    def __repr__(self):
+        return f"<FuturesAnalysis {self.symbol} {self.analysis_time}>"
+
+
+class WatchedSymbol(AnalysisBase):
+    """用户关注品种表"""
+    __tablename__ = "watched_symbols"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    symbol = Column(String(32), nullable=False, unique=True, comment="品种合约代码")
+    name = Column(String(64), nullable=True, comment="品种名称")
+    note = Column(Text, nullable=True, comment="备注")
+    created_at = Column(DateTime, nullable=False, default=datetime.now)
+    updated_at = Column(DateTime, nullable=False, default=datetime.now, onupdate=datetime.now)
+
+    def __repr__(self):
+        return f"<WatchedSymbol {self.symbol}>"
+
+
+class AIModelConfig(AnalysisBase):
+    """AI模型配置表"""
+    __tablename__ = "ai_model_configs"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    provider = Column(String(32), nullable=False, comment="AI提供商: openai/anthropic/google等")
+    model_name = Column(String(64), nullable=False, comment="模型名称")
+    api_key = Column(String(256), nullable=False, comment="API密钥")
+    api_base = Column(String(256), nullable=True, comment="API基础URL")
+    model_id = Column(String(64), nullable=True, comment="模型ID")
+    temperature = Column(Float, nullable=True, default=0.7, comment="温度参数")
+    max_tokens = Column(Integer, nullable=True, default=2000, comment="最大输出token")
+    enabled = Column(Boolean, nullable=False, default=True, comment="是否启用")
+    is_active = Column(Boolean, nullable=False, default=False, comment="是否为当前活跃模型")
+    created_at = Column(DateTime, nullable=False, default=datetime.now)
+    updated_at = Column(DateTime, nullable=False, default=datetime.now, onupdate=datetime.now)
+
+    def __repr__(self):
+        return f"<AIModelConfig {self.provider} {self.model_name}>"
+
+
+class AnalysisSettings(AnalysisBase):
+    """分析设置表（单例配置）"""
+    __tablename__ = "analysis_settings"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    key = Column(String(64), nullable=False, unique=True, comment="配置键")
+    value = Column(JSON, nullable=False, comment="配置值")
+    updated_at = Column(DateTime, nullable=False, default=datetime.now, onupdate=datetime.now)
+
+    def __repr__(self):
+        return f"<AnalysisSettings {self.key}>"
+
+
+class AIAnalysisCache(AnalysisBase):
+    """AI分析缓存表"""
+    __tablename__ = "ai_analysis_cache"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    symbol = Column(String(32), nullable=False, index=True, comment="品种合约代码")
+    analysis_data = Column(JSON, nullable=False, comment="AI分析结果数据")
+    kline_timestamp = Column(DateTime, nullable=True, comment="分析时K线数据的时间戳")
+    created_at = Column(DateTime, nullable=False, default=datetime.now, index=True, comment="分析时间")
+
+    def __repr__(self):
+        return f"<AIAnalysisCache {self.symbol} {self.created_at}>"

app/api/ai_config.py

@@ -0,0 +1,189 @@
+"""
+AI模型配置接口 - 管理AI分析模型的配置
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/ai-config", tags=["AI模型配置"])
+
+
+class AIModelConfig(BaseModel):
+    """AI模型配置"""
+    model_name: str
+    api_key: str
+    api_base: str = "https://api.openai.com/v1"
+    model_id: str = "gpt-4"
+    temperature: float = 0.7
+    max_tokens: int = 2000
+    enabled: bool = True
+
+
+class AIConfigResponse(BaseModel):
+    """AI配置响应"""
+    success: bool
+    data: Optional[dict] = None
+    message: str = ""
+
+
+class SaveAIConfigRequest(BaseModel):
+    """保存AI配置请求"""
+    models: list = []
+    active_model: Optional[str] = None
+    analysis_settings: Optional[dict] = None
+
+
+CONFIG_DIR = Path(__file__).resolve().parent.parent.parent / "config"
+AI_CONFIG_FILE = CONFIG_DIR / "ai_config.json"
+
+
+def _ensure_config_dir():
+    CONFIG_DIR.mkdir(parents=True, exist_ok=True)
+
+
+def _load_ai_config() -> dict:
+    """加载AI配置"""
+    _ensure_config_dir()
+    if not AI_CONFIG_FILE.exists():
+        return {
+            "models": [],
+            "active_model": None,
+            "analysis_settings": {
+                "enable_technical_analysis": True,
+                "enable_fundamental_analysis": False,
+                "enable_sentiment_analysis": False,
+                "risk_tolerance": "medium",
+                "max_position_pct": 10
+            }
+        }
+    with open(AI_CONFIG_FILE, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def _save_ai_config(config: dict):
+    """保存AI配置"""
+    _ensure_config_dir()
+    with open(AI_CONFIG_FILE, "w", encoding="utf-8") as f:
+        json.dump(config, f, ensure_ascii=False, indent=4)
+
+
+@router.get("", response_model=AIConfigResponse)
+def get_ai_config():
+    """获取当前AI模型配置"""
+    try:
+        config = _load_ai_config()
+        return {"success": True, "data": config}
+    except Exception as e:
+        logger.error(f"加载AI配置失败: {e}")
+        return {"success": False, "message": str(e)}
+
+
+@router.post("", response_model=AIConfigResponse)
+def save_ai_config(config: SaveAIConfigRequest):
+    """保存AI模型配置"""
+    try:
+        config_dict = {
+            "models": config.models,
+            "active_model": config.active_model,
+            "analysis_settings": config.analysis_settings or {}
+        }
+        _save_ai_config(config_dict)
+        return {"success": True, "message": "AI配置保存成功"}
+    except Exception as e:
+        logger.error(f"保存AI配置失败: {e}")
+        return {"success": False, "message": str(e)}
+
+
+@router.post("/test", response_model=AIConfigResponse)
+def test_ai_connection(model_config: AIModelConfig):
+    """测试AI模型连接"""
+    try:
+        import httpx
+        
+        headers = {
+            "Authorization": f"Bearer {model_config.api_key}",
+            "Content-Type": "application/json"
+        }
+        
+        data = {
+            "model": model_config.model_id,
+            "messages": [{"role": "user", "content": "Hello"}],
+            "max_tokens": 10
+        }
+        
+        with httpx.Client(timeout=30) as client:
+            response = client.post(
+                f"{model_config.api_base}/chat/completions",
+                headers=headers,
+                json=data
+            )
+            
+            if response.status_code == 200:
+                return {"success": True, "message": "连接测试成功"}
+            else:
+                return {"success": False, "message": f"连接失败: {response.status_code} - {response.text}"}
+                
+    except Exception as e:
+        logger.error(f"AI连接测试失败: {e}")
+        return {"success": False, "message": f"连接测试失败: {str(e)}"}
+
+
+@router.get("/providers")
+def get_ai_providers():
+    """获取支持的AI提供商列表"""
+    providers = [
+        {
+            "id": "openai",
+            "name": "OpenAI",
+            "api_base": "https://api.openai.com/v1",
+            "models": ["gpt-4o", "gpt-4-turbo", "gpt-3.5-turbo"]
+        },
+        {
+            "id": "anthropic",
+            "name": "Anthropic Claude",
+            "api_base": "https://api.anthropic.com/v1",
+            "models": ["claude-3-opus", "claude-3-sonnet", "claude-3-haiku"]
+        },
+        {
+            "id": "google",
+            "name": "Google Gemini",
+            "api_base": "https://generativelanguage.googleapis.com/v1beta",
+            "models": ["gemini-pro", "gemini-pro-vision"]
+        },
+        {
+            "id": "aliyun",
+            "name": "阿里云通义千问",
+            "api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
+            "models": ["qwen-max", "qwen-plus", "qwen-turbo"]
+        },
+        {
+            "id": "aliyun_coding",
+            "name": "阿里云通义灵码",
+            "api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
+            "models": ["qwen-coder-plus", "qwen-coder-turbo"]
+        },
+        {
+            "id": "bailian",
+            "name": "阿里百炼",
+            "api_base": "https://coding.dashscope.aliyuncs.com/v1",
+            "models": ["qwen3.6-plus", "qwen3.5-plus", "qwen3-max", "qwen3-coder-plus", "MiniMax-M2.5", "glm-4.7", "kimi-k2.5"]
+        },
+        {
+            "id": "baidu",
+            "name": "百度文心一言",
+            "api_base": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop",
+            "models": ["ernie-4.0", "ernie-3.5", "ernie-speed"]
+        },
+        {
+            "id": "zhipu",
+            "name": "智谱清言",
+            "api_base": "https://open.bigmodel.cn/api/paas/v4",
+            "models": ["glm-4", "glm-3-turbo"]
+        }
+    ]
+    return {"success": True, "data": providers}

app/api/futures_analysis.py

@@ -0,0 +1,956 @@
+"""
+期货智析接口 - 提供期货分析数据
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+import threading
+
+from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
+from sqlalchemy.orm import Session
+
+from app.database import get_db
+from app.analysis_db import get_analysis_db
+from app.analysis_models import FuturesAnalysis, WatchedSymbol, AIModelConfig, AnalysisSettings, AIAnalysisCache
+from app.services.cache import get_cached_data, get_latest_cached, save_market_data
+from app.services.collector import fetch_symbol_data
+
+logger = logging.getLogger(__name__)
+router = APIRouter(prefix="/futures", tags=["期货智析"])
+
+CONFIG_DIR = Path(__file__).resolve().parent.parent.parent / "config"
+SYMBOLS_CONFIG_FILE = CONFIG_DIR / "symbols_config.json"
+
+
+def _load_symbols_config() -> dict:
+    """加载品种配置文件"""
+    if not SYMBOLS_CONFIG_FILE.exists():
+        return {"futures": {}, "stock": {}}
+    with open(SYMBOLS_CONFIG_FILE, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+@router.get("/list")
+def get_futures_list(db: Session = Depends(get_db)):
+    """获取所有期货品种列表及摘要信息（从symbols_config.json读取）"""
+    config = _load_symbols_config()
+    futures_config = config.get("futures", {})
+    
+    if not futures_config:
+        return {"success": True, "data": []}
+
+    futures_data = []
+    for name, symbol_code in futures_config.items():
+        cached = get_cached_data(db, symbol_code, "futures")
+        if cached and cached.get("timeframes"):
+            all_candles = []
+            for period, candles in cached.get("timeframes", {}).items():
+                all_candles.extend(candles)
+            
+            if all_candles:
+                latest_candle = all_candles[-1]
+                open_price = float(latest_candle.get("open", 0))
+                close_price = float(latest_candle.get("close", 0))
+                high_price = float(latest_candle.get("high", 0))
+                low_price = float(latest_candle.get("low", 0))
+                
+                change = close_price - open_price
+                change_pct = (change / open_price * 100) if open_price > 0 else 0
+                
+                futures_data.append({
+                    "symbol": symbol_code,
+                    "name": name,
+                    "price": close_price,
+                    "change": round(change, 2),
+                    "changePct": round(change_pct, 2),
+                    "suggestion": _get_suggestion(close_price, open_price, change_pct),
+                    "suggestionType": "up" if change >= 0 else "down",
+                    "periods": _get_period_trends(all_candles),
+                    "successRate": _calc_success_rate(all_candles),
+                    "trendScore": _calc_trend_score(all_candles),
+                    "resistance": round(2 * ((high_price + low_price + close_price) / 3) - low_price, 2),
+                    "support": round(2 * ((high_price + low_price + close_price) / 3) - high_price, 2),
+                    "open": open_price,
+                    "high": high_price,
+                    "low": low_price,
+                    "volume": sum(float(c.get("volume", 0)) for c in all_candles)
+                })
+        else:
+            futures_data.append({
+                "symbol": symbol_code,
+                "name": name,
+                "price": 0,
+                "change": 0,
+                "changePct": 0,
+                "suggestion": "等待数据",
+                "suggestionType": "neutral",
+                "periods": {"5": "neutral", "15": "neutral", "30": "neutral", "60": "neutral"},
+                "successRate": 0,
+                "trendScore": 0,
+                "resistance": 0,
+                "support": 0,
+                "open": 0,
+                "high": 0,
+                "low": 0,
+                "volume": 0
+            })
+
+    return {"success": True, "data": futures_data}
+
+
+@router.get("/detail/{symbol}")
+def get_futures_detail(symbol: str, db: Session = Depends(get_db)):
+    """获取指定期货品种的详细分析数据"""
+    cached = get_cached_data(db, symbol, "futures")
+    if not cached:
+        raise HTTPException(status_code=404, detail=f"未找到 {symbol} 的缓存数据")
+
+    all_candles = []
+    for period, candles in cached.get("timeframes", {}).items():
+        all_candles.extend(candles)
+
+    if not all_candles:
+        raise HTTPException(status_code=404, detail=f"未找到 {symbol} 的K线数据")
+
+    latest_candle = all_candles[-1]
+    open_price = float(latest_candle.get("open", 0))
+    close_price = float(latest_candle.get("close", 0))
+    high_price = float(latest_candle.get("high", 0))
+    low_price = float(latest_candle.get("low", 0))
+    
+    change = close_price - open_price
+    change_pct = (change / open_price * 100) if open_price > 0 else 0
+    
+    # Pivot Point 公式计算关键点位
+    pp = (high_price + low_price + close_price) / 3
+    r1 = round(2 * pp - low_price, 2)
+    r2 = round(pp + (high_price - low_price), 2)
+    s1 = round(2 * pp - high_price, 2)
+    s2 = round(pp - (high_price - low_price), 2)
+    
+    suggestion = _get_suggestion(close_price, open_price, change_pct)
+    suggestion_type = "up" if change >= 0 else "down"
+    trend_score = _calc_trend_score(all_candles)
+    
+    data = {
+        "symbol": symbol,
+        "name": _get_futures_name(symbol),
+        "price": close_price,
+        "change": round(change, 2),
+        "changePct": round(change_pct, 2),
+        "suggestion": suggestion,
+        "suggestionType": suggestion_type,
+        "suggestionReason": _get_suggestion_reason(symbol, suggestion),
+        "open": open_price,
+        "high": high_price,
+        "low": low_price,
+        "volume": sum(float(c.get("volume", 0)) for c in all_candles),
+        "entryPrice": round(close_price * 0.995, 2) if change >= 0 else round(close_price * 1.005, 2),
+        "targetPrice": r1 if change >= 0 else s1,
+        "stopLoss": s1 if change >= 0 else r1,
+        "riskLevel": "低" if trend_score >= 80 else "中" if trend_score >= 60 else "高",
+        "macd": _calc_macd(all_candles),
+        "rsi": _calc_rsi(all_candles),
+        "boll": _calc_boll(all_candles),
+        "kdj": _calc_kdj(all_candles),
+        "resistances": [r1, r2],
+        "supports": [s1, s2],
+        "pivotPoint": round(pp, 2),
+        "periodConsistency": _get_period_trends(all_candles)
+    }
+
+    return {"success": True, "data": data}
+
+
+@router.get("/kline/{symbol}")
+def get_kline_data(symbol: str, period: str = "15", db: Session = Depends(get_db)):
+    """获取指定品种和周期的K线数据"""
+    period_map = {
+        "5": "5min",
+        "15": "15min",
+        "30": "30min",
+        "60": "60min",
+        "1440": "daily",
+        "daily": "daily"
+    }
+    db_period = period_map.get(period, f"{period}min")
+    
+    cached = get_cached_data(db, symbol, "futures", [db_period])
+    if not cached or not cached.get("timeframes"):
+        raise HTTPException(status_code=404, detail=f"未找到 {symbol} {db_period} 的缓存数据")
+
+    candles = cached["timeframes"].get(db_period, [])
+    kline_data = []
+    for c in candles:
+        time_str = c.get("datetime", c.get("time", ""))
+        if time_str and len(time_str) >= 16:
+            time_str = time_str[:16].replace("T", " ")
+        kline_data.append([
+            time_str,
+            str(c.get("open", 0)),
+            str(c.get("close", 0)),
+            str(c.get("low", 0)),
+            str(c.get("high", 0)),
+            str(int(c.get("volume", 0)))
+        ])
+
+    return {"success": True, "data": kline_data}
+
+
+def _get_futures_name(symbol: str) -> str:
+    """根据合约代码获取品种名称"""
+    name_map = {
+        "AU": "黄金", "AG": "白银", "CU": "铜", "AL": "铝",
+        "ZN": "锌", "NI": "镍", "SN": "锡", "PB": "铅",
+        "RB": "螺纹钢", "HC": "热卷", "I": "铁矿石", "J": "焦炭",
+        "JM": "焦煤", "ZC": "动力煤", "MA": "甲醇", "TA": "PTA",
+        "EG": "乙二醇", "PP": "聚丙烯", "L": "塑料", "V": "PVC",
+        "M": "豆粕", "RM": "菜粕", "C": "玉米", "CS": "淀粉",
+        "A": "豆一", "B": "豆二", "Y": "豆油", "P": "棕榈油",
+        "OI": "菜油", "CF": "棉花", "SR": "白糖", "AP": "苹果",
+        "JD": "鸡蛋", "LH": "生猪", "FU": "燃料油", "LU": "低硫燃油",
+        "SC": "原油", "EC": "集运指数", "BU": "沥青", "RU": "橡胶",
+        "NR": "20号胶", "SP": "纸浆", "SS": "不锈钢", "SA": "纯碱",
+        "FG": "玻璃", "UR": "尿素", "SF": "硅铁", "SM": "锰硅",
+        "IF": "沪深300", "IC": "中证500", "IH": "上证50", "IM": "中证1000",
+        "T": "10年期国债", "TF": "5年期国债", "TS": "2年期国债", "TL": "30年期国债",
+    }
+    return name_map.get(symbol, symbol)
+
+
+def _get_suggestion(close: float, open: float, change_pct: float) -> str:
+    """根据价格走势给出操作建议"""
+    if change_pct > 2:
+        return "逢低做多"
+    elif change_pct > 0.5:
+        return "逢低做多"
+    elif change_pct > -0.5:
+        return "观望等待"
+    elif change_pct > -2:
+        return "逢高做空"
+    else:
+        return "逢高做空"
+
+
+def _get_suggestion_reason(symbol: str, suggestion: str) -> str:
+    """获取建议理由"""
+    reasons = {
+        "逢低做多": "技术面突破，趋势明确，建议逢低介入",
+        "逢高做空": "技术面走弱，下行压力增大",
+        "观望等待": "多空力量均衡，等待方向明确"
+    }
+    return reasons.get(suggestion, "等待进一步信号")
+
+
+def _get_period_trends(candles: list) -> dict:
+    """计算各周期趋势 - 根据不同周期取不同长度的K线计算"""
+    period_config = {
+        "5": {"bars": 10, "threshold": 0.003},
+        "15": {"bars": 15, "threshold": 0.005},
+        "30": {"bars": 20, "threshold": 0.008},
+        "60": {"bars": 30, "threshold": 0.01}
+    }
+    
+    result = {}
+    
+    for period, cfg in period_config.items():
+        bars = cfg["bars"]
+        threshold = cfg["threshold"]
+        
+        if len(candles) < bars:
+            result[period] = "neutral"
+            continue
+        
+        recent = candles[-bars:]
+        first_close = float(recent[0].get("close", 0))
+        last_close = float(recent[-1].get("close", 0))
+        
+        if first_close <= 0:
+            result[period] = "neutral"
+            continue
+        
+        change_pct = (last_close - first_close) / first_close
+        
+        if change_pct > threshold:
+            result[period] = "up"
+        elif change_pct < -threshold:
+            result[period] = "down"
+        else:
+            result[period] = "neutral"
+    
+    return result
+
+
+def _calc_success_rate(candles: list) -> int:
+    """计算交易成功率（简化版）"""
+    if len(candles) < 10:
+        return 50
+    
+    wins = 0
+    for i in range(1, len(candles)):
+        prev_close = float(candles[i-1].get("close", 0))
+        curr_close = float(candles[i].get("close", 0))
+        if curr_close >= prev_close:
+            wins += 1
+    
+    return int(wins / (len(candles) - 1) * 100)
+
+
+def _calc_trend_score(candles: list) -> int:
+    """计算趋势评分（0-100）"""
+    if len(candles) < 5:
+        return 50
+    
+    recent = candles[-10:]
+    closes = [float(c.get("close", 0)) for c in recent]
+    
+    if len(closes) < 2:
+        return 50
+    
+    up_count = sum(1 for i in range(1, len(closes)) if closes[i] >= closes[i-1])
+    score = int(up_count / (len(closes) - 1) * 100)
+    
+    return max(0, min(100, score))
+
+
+def _calc_ema(data: list, period: int) -> list:
+    """计算EMA，返回与输入等长的列表，前面用None填充"""
+    ema = [None] * len(data)
+    multiplier = 2 / (period + 1)
+    
+    if len(data) < period:
+        return ema
+    
+    ema[period - 1] = sum(data[:period]) / period
+    
+    for i in range(period, len(data)):
+        ema[i] = (data[i] - ema[i-1]) * multiplier + ema[i-1]
+    
+    return ema
+
+
+def _calc_macd(candles: list) -> dict:
+    """计算MACD指标"""
+    if len(candles) < 26:
+        return {"signal": "中性", "detail": "数据不足"}
+    
+    closes = [float(c.get("close", 0)) for c in candles]
+    ema12 = _calc_ema(closes, 12)
+    ema26 = _calc_ema(closes, 26)
+    
+    dif_list = []
+    for i in range(len(closes)):
+        if ema12[i] is not None and ema26[i] is not None:
+            dif_list.append(ema12[i] - ema26[i])
+        else:
+            dif_list.append(None)
+    
+    # 只对有效DIF值计算DEA，避免None替换为0导致计算错误
+    dif_valid = [d for d in dif_list if d is not None]
+    if dif_valid:
+        dea_valid = _calc_ema(dif_valid, 9)
+        dea_list = [None] * (len(dif_list) - len(dif_valid)) + dea_valid
+    else:
+        dea_list = [None] * len(dif_list)
+    
+    dif = dif_list[-1]
+    dea = dea_list[-1]
+    
+    if dif is not None and dea is not None:
+        if dif > dea:
+            signal = "金叉"
+        elif dif < dea:
+            signal = "死叉"
+        else:
+            signal = "中性"
+    else:
+        signal = "中性"
+    
+    return {"signal": signal, "detail": f"DIF: {dif:.4f}"}
+
+
+def _calc_rsi(candles: list) -> dict:
+    """计算RSI指标"""
+    if len(candles) < 15:
+        return {"value": 50, "status": "正常"}
+    
+    closes = [float(c.get("close", 0)) for c in candles[-15:]]
+    gains = []
+    losses = []
+    
+    for i in range(1, len(closes)):
+        diff = closes[i] - closes[i-1]
+        gains.append(max(0, diff))
+        losses.append(max(0, -diff))
+    
+    avg_gain = sum(gains) / len(gains) if gains else 0
+    avg_loss = sum(losses) / len(losses) if losses else 0
+    
+    if avg_loss == 0:
+        rsi = 100
+    else:
+        rs = avg_gain / avg_loss
+        rsi = 100 - (100 / (1 + rs))
+    
+    rsi = int(rsi)
+    if rsi > 70:
+        status = "超买"
+    elif rsi < 30:
+        status = "超卖"
+    else:
+        status = "正常"
+    
+    return {"value": rsi, "status": status}
+
+
+def _calc_boll(candles: list) -> dict:
+    """计算布林带"""
+    if len(candles) < 20:
+        return {"signal": "中轨", "detail": "区间: --"}
+    
+    closes = [float(c.get("close", 0)) for c in candles[-20:]]
+    ma = sum(closes) / len(closes)
+    std = (sum((c - ma) ** 2 for c in closes) / len(closes)) ** 0.5
+    
+    upper = ma + 2 * std
+    lower = ma - 2 * std
+    current = closes[-1]
+    
+    if current > upper:
+        signal = "上轨外"
+    elif current < lower:
+        signal = "下轨外"
+    elif current > ma:
+        signal = "中轨上"
+    else:
+        signal = "中轨"
+    
+    return {"signal": signal, "detail": f"区间: {lower:.0f}-{upper:.0f}"}
+
+
+def _calc_kdj(candles: list) -> dict:
+    """计算KDJ指标"""
+    if len(candles) < 9:
+        return {"signal": "中性", "detail": "K: -- D: --"}
+    
+    highs = [float(c.get("high", 0)) for c in candles[-9:]]
+    lows = [float(c.get("low", 0)) for c in candles[-9:]]
+    closes = [float(c.get("close", 0)) for c in candles[-9:]]
+    
+    highest = max(highs)
+    lowest = min(lows)
+    current = closes[-1]
+    
+    if highest == lowest:
+        rsv = 50
+    else:
+        rsv = (current - lowest) / (highest - lowest) * 100
+    
+    k = int(rsv * 2 / 3 + 50 / 3)
+    d = int(k * 2 / 3 + 50 / 3)
+    
+    if k > d:
+        signal = "偏多"
+    elif k < d:
+        signal = "偏空"
+    else:
+        signal = "中性"
+    
+    return {"signal": signal, "detail": f"K: {k} D: {d}"}
+
+
+# ==================== 期货智析数据管理接口 ====================
+
+@router.get("/analysis/history/{symbol}")
+def get_analysis_history(symbol: str, limit: int = 10, adb: Session = Depends(get_analysis_db)):
+    """获取品种历史分析记录"""
+    records = adb.query(FuturesAnalysis).filter(
+        FuturesAnalysis.symbol == symbol
+    ).order_by(
+        FuturesAnalysis.analysis_time.desc()
+    ).limit(limit).all()
+    
+    return {
+        "success": True,
+        "data": [{
+            "id": r.id,
+            "symbol": r.symbol,
+            "analysis_time": r.analysis_time.isoformat(),
+            "suggestion": r.suggestion,
+            "suggestion_type": r.suggestion_type,
+            "trend_score": r.trend_score,
+            "entry_price": r.entry_price,
+            "target_price": r.target_price,
+            "stop_loss": r.stop_loss,
+            "risk_level": r.risk_level
+        } for r in records]
+    }
+
+
+@router.post("/analysis/save")
+def save_analysis_record(data: dict, adb: Session = Depends(get_analysis_db)):
+    """保存分析记录到数据库"""
+    try:
+        record = FuturesAnalysis(
+            symbol=data.get("symbol"),
+            suggestion=data.get("suggestion"),
+            suggestion_type=data.get("suggestion_type"),
+            entry_price=data.get("entry_price"),
+            target_price=data.get("target_price"),
+            stop_loss=data.get("stop_loss"),
+            risk_level=data.get("risk_level"),
+            macd_signal=data.get("macd", {}).get("signal") if data.get("macd") else None,
+            rsi_value=data.get("rsi", {}).get("value") if data.get("rsi") else None,
+            boll_signal=data.get("boll", {}).get("signal") if data.get("boll") else None,
+            kdj_signal=data.get("kdj", {}).get("signal") if data.get("kdj") else None,
+            trend_score=data.get("trend_score"),
+            success_rate=data.get("success_rate"),
+            resistance_levels=data.get("resistances"),
+            support_levels=data.get("supports"),
+            period_trends=data.get("periodConsistency")
+        )
+        adb.add(record)
+        adb.commit()
+        return {"success": True, "message": "分析记录已保存", "id": record.id}
+    except Exception as e:
+        adb.rollback()
+        logger.error(f"保存分析记录失败: {e}")
+        return {"success": False, "message": str(e)}
+
+
+# ==================== 关注品种管理 ====================
+
+@router.get("/watched")
+def get_watched_symbols(adb: Session = Depends(get_analysis_db)):
+    """获取关注的品种列表"""
+    symbols = adb.query(WatchedSymbol).order_by(WatchedSymbol.created_at.desc()).all()
+    return {
+        "success": True,
+        "data": [{
+            "id": s.id,
+            "symbol": s.symbol,
+            "name": s.name,
+            "note": s.note,
+            "created_at": s.created_at.isoformat()
+        } for s in symbols]
+    }
+
+
+@router.post("/watched")
+def add_watched_symbol(data: dict, adb: Session = Depends(get_analysis_db)):
+    """添加关注品种"""
+    try:
+        symbol = data.get("symbol")
+        existing = adb.query(WatchedSymbol).filter(WatchedSymbol.symbol == symbol).first()
+        if existing:
+            return {"success": False, "message": "该品种已关注"}
+        
+        new_symbol = WatchedSymbol(
+            symbol=symbol,
+            name=data.get("name"),
+            note=data.get("note")
+        )
+        adb.add(new_symbol)
+        adb.commit()
+        return {"success": True, "message": "已添加关注", "id": new_symbol.id}
+    except Exception as e:
+        adb.rollback()
+        return {"success": False, "message": str(e)}
+
+
+@router.delete("/watched/{symbol}")
+def remove_watched_symbol(symbol: str, adb: Session = Depends(get_analysis_db)):
+    """取消关注品种"""
+    try:
+        record = adb.query(WatchedSymbol).filter(WatchedSymbol.symbol == symbol).first()
+        if not record:
+            return {"success": False, "message": "未找到该品种"}
+        adb.delete(record)
+        adb.commit()
+        return {"success": True, "message": "已取消关注"}
+    except Exception as e:
+        adb.rollback()
+        return {"success": False, "message": str(e)}
+
+
+# ==================== AI模型配置管理 ====================
+
+@router.get("/ai-models")
+def get_ai_models(adb: Session = Depends(get_analysis_db)):
+    """获取AI模型配置列表"""
+    models = adb.query(AIModelConfig).order_by(AIModelConfig.created_at.desc()).all()
+    settings = adb.query(AnalysisSettings).filter(
+        AnalysisSettings.key == "analysis_settings"
+    ).first()
+    
+    return {
+        "success": True,
+        "data": {
+            "models": [{
+                "id": m.id,
+                "provider": m.provider,
+                "model_name": m.model_name,
+                "api_base": m.api_base,
+                "model_id": m.model_id,
+                "temperature": m.temperature,
+                "max_tokens": m.max_tokens,
+                "enabled": m.enabled,
+                "is_active": m.is_active,
+                "created_at": m.created_at.isoformat()
+            } for m in models],
+            "analysis_settings": settings.value if settings else {
+                "enable_technical_analysis": True,
+                "enable_fundamental_analysis": False,
+                "enable_sentiment_analysis": False,
+                "risk_tolerance": "medium",
+                "max_position_pct": 10
+            }
+        }
+    }
+
+
+@router.post("/ai-models")
+def save_ai_model(data: dict, adb: Session = Depends(get_analysis_db)):
+    """保存AI模型配置"""
+    try:
+        if data.get("action") == "save_settings":
+            settings = adb.query(AnalysisSettings).filter(
+                AnalysisSettings.key == "analysis_settings"
+            ).first()
+            if settings:
+                settings.value = data.get("settings", {})
+            else:
+                settings = AnalysisSettings(
+                    key="analysis_settings",
+                    value=data.get("settings", {})
+                )
+                adb.add(settings)
+            adb.commit()
+            return {"success": True, "message": "分析设置已保存"}
+        
+        model_data = data.get("model", {})
+        model = AIModelConfig(
+            provider=model_data.get("provider", "custom"),
+            model_name=model_data.get("model_name", ""),
+            api_key=model_data.get("api_key", ""),
+            api_base=model_data.get("api_base"),
+            model_id=model_data.get("model_id"),
+            temperature=model_data.get("temperature", 0.7),
+            max_tokens=model_data.get("max_tokens", 2000),
+            enabled=model_data.get("enabled", True),
+            is_active=model_data.get("is_active", False)
+        )
+        
+        if model.is_active:
+            adb.query(AIModelConfig).update({"is_active": False})
+        
+        adb.add(model)
+        adb.commit()
+        return {"success": True, "message": "AI模型已保存", "id": model.id}
+    except Exception as e:
+        adb.rollback()
+        return {"success": False, "message": str(e)}
+
+
+@router.put("/ai-models/{model_id}")
+def update_ai_model(model_id: int, data: dict, adb: Session = Depends(get_analysis_db)):
+    """更新AI模型配置"""
+    try:
+        model = adb.query(AIModelConfig).filter(AIModelConfig.id == model_id).first()
+        if not model:
+            return {"success": False, "message": "模型不存在"}
+        
+        if "is_active" in data and data["is_active"]:
+            adb.query(AIModelConfig).update({"is_active": False})
+            model.is_active = True
+        else:
+            for key, value in data.items():
+                if hasattr(model, key):
+                    setattr(model, key, value)
+        
+        adb.commit()
+        return {"success": True, "message": "模型已更新"}
+    except Exception as e:
+        adb.rollback()
+        return {"success": False, "message": str(e)}
+
+
+@router.delete("/ai-models/{model_id}")
+def delete_ai_model(model_id: int, adb: Session = Depends(get_analysis_db)):
+    """删除AI模型配置"""
+    try:
+        model = adb.query(AIModelConfig).filter(AIModelConfig.id == model_id).first()
+        if not model:
+            return {"success": False, "message": "模型不存在"}
+        adb.delete(model)
+        adb.commit()
+        return {"success": True, "message": "模型已删除"}
+    except Exception as e:
+        adb.rollback()
+        return {"success": False, "message": str(e)}
+
+
+# ==================== 数据刷新接口 ====================
+
+from app.services.cache import needs_refresh, get_symbol_timestamp
+from app.services.ai_analysis import AIFuturesAnalyzer
+
+refresh_lock = threading.Lock()
+refresh_status = {"running": False, "progress": 0, "total": 0, "message": ""}
+REFRESH_THRESHOLD = 300  # 5分钟阈值
+
+
+def _refresh_single_symbol_sync(db: Session, symbol: str) -> dict:
+    """同步刷新单个品种数据（会等待采集完成）"""
+    try:
+        # 先检查是否需要刷新
+        if not needs_refresh(db, symbol, "futures", REFRESH_THRESHOLD):
+            last_refresh = get_symbol_timestamp(db, symbol, "futures")
+            return {
+                "success": True,
+                "message": f"{symbol} 数据仍然新鲜，无需刷新",
+                "last_refresh": last_refresh.isoformat() if last_refresh else None,
+                "refreshed": False
+            }
+        
+        # 需要刷新，执行采集
+        logger.info(f"开始刷新 {symbol} 数据...")
+        result = fetch_symbol_data(symbol, "futures")
+        
+        if result.get("timeframes"):
+            save_market_data(db, symbol, result)
+            logger.info(f"{symbol} 数据刷新完成")
+            return {
+                "success": True,
+                "message": f"{symbol} 数据已更新",
+                "refreshed": True
+            }
+        return {"success": False, "message": f"{symbol} 未获取到数据", "refreshed": False}
+    except Exception as e:
+        logger.error(f"刷新 {symbol} 失败: {e}")
+        return {"success": False, "message": f"{symbol} 刷新失败: {str(e)}", "refreshed": False}
+
+
+@router.post("/refresh/{symbol}")
+def refresh_single_symbol_api(symbol: str, db: Session = Depends(get_db)):
+    """刷新单个品种合约数据（同步执行，检查时间戳）"""
+    if refresh_lock.locked():
+        return {"success": False, "message": "数据刷新中，请稍后再试"}
+    
+    try:
+        refresh_lock.acquire()
+        result = _refresh_single_symbol_sync(db, symbol)
+        return result
+    finally:
+        refresh_lock.release()
+
+
+@router.post("/refresh-all")
+def refresh_all_symbols_api(background_tasks: BackgroundTasks):
+    """刷新所有品种合约数据（异步执行）"""
+    global refresh_status
+    
+    if refresh_lock.locked():
+        return {"success": False, "message": "数据刷新中，请稍后再试"}
+    
+    # 从配置加载所有品种
+    config = _load_symbols_config()
+    futures_config = config.get("futures", {})
+    symbols = list(futures_config.values())
+    
+    def refresh_all_task():
+        global refresh_status
+        
+        # 在后台任务内部创建新的数据库会话
+        local_db = next(get_db())
+        
+        try:
+            with refresh_lock:
+                refresh_status = {"running": True, "progress": 0, "total": len(symbols), "message": "开始刷新..."}
+            
+            for i, symbol in enumerate(symbols):
+                refresh_status["message"] = f"正在刷新 {symbol} ({i + 1}/{len(symbols)})"
+                refresh_status["progress"] = i + 1
+                _refresh_single_symbol_sync(local_db, symbol)
+            
+            with refresh_lock:
+                refresh_status = {"running": False, "progress": len(symbols), "total": len(symbols), "message": "全部刷新完成"}
+        finally:
+            local_db.close()
+    
+    background_tasks.add_task(refresh_all_task)
+    return {"success": True, "message": "开始刷新所有品种数据...", "count": len(symbols)}
+
+
+@router.get("/refresh-status")
+def get_refresh_status():
+    """获取刷新状态"""
+    return {"success": True, "data": refresh_status}
+
+
+# ==================== AI智能分析接口 ====================
+
+@router.post("/ai-analysis/{symbol}")
+def run_ai_analysis(symbol: str, db: Session = Depends(get_db), analysis_db: Session = Depends(get_analysis_db)):
+    """执行AI智能分析"""
+    try:
+        analyzer = AIFuturesAnalyzer(db, analysis_db)
+        result = analyzer.analyze(symbol)
+        
+        if result.get("success"):
+            return {
+                "success": True,
+                "data": result["data"]
+            }
+        else:
+            return {
+                "success": False,
+                "error": result.get("error", "AI分析失败")
+            }
+    except Exception as e:
+        logger.error(f"AI分析失败: {e}")
+        return {
+            "success": False,
+            "error": f"AI分析失败: {str(e)}"
+        }
+
+
+@router.get("/ai-analysis/{symbol}")
+def get_ai_analysis(symbol: str, force_refresh: bool = False, db: Session = Depends(get_db), analysis_db: Session = Depends(get_analysis_db)):
+    """获取AI分析结果（智能判断是否需要重新分析）"""
+    try:
+        analyzer = AIFuturesAnalyzer(db, analysis_db)
+        
+        if force_refresh:
+            logger.info(f"强制刷新: {symbol}")
+            result = analyzer.analyze(symbol)
+            if result.get("success"):
+                return {
+                    "success": True,
+                    "data": result["data"],
+                    "is_cached": False
+                }
+            else:
+                return {
+                    "success": False,
+                    "error": result.get("error", "AI分析失败")
+                }
+        
+        # 获取最新缓存
+        cache = analyzer.get_latest_cache(symbol)
+        if cache:
+            # 智能判断是否需要重新分析
+            if analyzer.should_reanalyze(symbol, cache):
+                logger.info(f"检测到数据变化或超时，自动重新分析: {symbol}")
+                result = analyzer.analyze(symbol)
+                if result.get("success"):
+                    return {
+                        "success": True,
+                        "data": result["data"],
+                        "is_cached": False
+                    }
+                else:
+                    # 如果重新分析失败，返回旧缓存
+                    logger.warning(f"重新分析失败，返回旧缓存: {symbol}")
+                    return {
+                        "success": True,
+                        "data": {
+                            "id": cache.id,
+                            "symbol": cache.symbol,
+                            "analysis_time": cache.created_at.isoformat(),
+                            "result": cache.analysis_data
+                        },
+                        "is_cached": True,
+                        "warning": "分析数据可能不是最新的"
+                    }
+            
+            # 返回缓存数据
+            return {
+                "success": True,
+                "data": {
+                    "id": cache.id,
+                    "symbol": cache.symbol,
+                    "analysis_time": cache.created_at.isoformat(),
+                    "result": cache.analysis_data
+                },
+                "is_cached": True
+            }
+        
+        # 没有缓存，执行分析
+        result = analyzer.analyze(symbol)
+        if result.get("success"):
+            return {
+                "success": True,
+                "data": result["data"],
+                "is_cached": False
+            }
+        else:
+            return {
+                "success": False,
+                "error": result.get("error", "未找到分析结果")
+            }
+    except Exception as e:
+        logger.error(f"获取AI分析结果失败: {e}")
+        return {
+            "success": False,
+            "error": f"获取AI分析失败: {str(e)}"
+        }
+
+
+@router.get("/ai-analysis/{symbol}/history")
+def get_ai_analysis_history(symbol: str, limit: int = 20, analysis_db: Session = Depends(get_analysis_db)):
+    """获取AI分析历史记录"""
+    try:
+        records = analysis_db.query(AIAnalysisCache).filter(
+            AIAnalysisCache.symbol == symbol
+        ).order_by(
+            AIAnalysisCache.created_at.desc()
+        ).limit(limit).all()
+        
+        return {
+            "success": True,
+            "data": [{
+                "id": r.id,
+                "symbol": r.symbol,
+                "analysis_time": r.created_at.isoformat(),
+                "analysis_data": r.analysis_data
+            } for r in records]
+        }
+    except Exception as e:
+        logger.error(f"获取AI分析历史失败: {e}")
+        return {
+            "success": False,
+            "error": f"获取历史记录失败: {str(e)}"
+        }
+
+
+@router.get("/ai-analysis/history/{record_id}")
+def get_ai_analysis_detail(record_id: int, analysis_db: Session = Depends(get_analysis_db)):
+    """获取单条AI分析记录详情"""
+    try:
+        record = analysis_db.query(AIAnalysisCache).filter(
+            AIAnalysisCache.id == record_id
+        ).first()
+        
+        if not record:
+            return {
+                "success": False,
+                "error": "记录不存在"
+            }
+        
+        return {
+            "success": True,
+            "data": {
+                "id": record.id,
+                "symbol": record.symbol,
+                "analysis_time": record.created_at.isoformat(),
+                "analysis_data": record.analysis_data
+            }
+        }
+    except Exception as e:
+        logger.error(f"获取AI分析详情失败: {e}")
+        return {
+            "success": False,
+            "error": f"获取记录详情失败: {str(e)}"
+        }

app/main.py

@@ -12,7 +12,7 @@ from fastapi.responses import FileResponse
 
 from app.database import engine, Base
 from app.config import HOST, PORT, LOG_LEVEL
-from app.api import data, tasks, config
+from app.api import data, tasks, config, futures_analysis, ai_config
 from app.services.scheduler import start_scheduler, stop_scheduler
 
 # 配置日志
@@ -29,6 +29,9 @@ async def lifespan(app: FastAPI):
     # 启动时：建表 + 启动调度器
     logger.info("创建数据库表...")
     Base.metadata.create_all(bind=engine)
+    from app.analysis_db import init_analysis_db
+    init_analysis_db()
+    logger.info("期货智析数据库初始化完成")
 
     logger.info("启动定时调度器...")
     start_scheduler()
@@ -87,6 +90,20 @@ def ui_page():
 app.include_router(data.router, prefix="/api/v1")
 app.include_router(tasks.router, prefix="/api/v1")
 app.include_router(config.router, prefix="/api/v1")
+app.include_router(futures_analysis.router, prefix="/api/v1")
+app.include_router(ai_config.router, prefix="/api/v1")
+
+
+@app.get("/futures-analysis")
+def futures_analysis_page():
+    """期货智析页面"""
+    return FileResponse(str(STATIC_DIR / "futures_analysis.html"))
+
+
+@app.get("/ai-config")
+def ai_config_page():
+    """AI模型配置页面"""
+    return FileResponse(str(STATIC_DIR / "ai_config.html"))
 
 
 @app.get("/api/v1/health")

app/models.py

@@ -28,6 +28,20 @@ class MarketData(Base):
         return f"<MarketData {self.symbol} {self.period} candles={self.candle_count}>"
 
 
+class SymbolTimestamp(Base):
+    """合约数据时间戳表 - 记录每个合约的最新数据时间"""
+    __tablename__ = "symbol_timestamps"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    symbol = Column(String(32), nullable=False, unique=True, index=True, comment="品种合约代码")
+    data_type = Column(String(16), nullable=False, default="futures", comment="数据类型")
+    last_refresh_at = Column(DateTime, nullable=False, default=datetime.now, comment="最后刷新时间")
+    refresh_count = Column(Integer, default=0, comment="刷新次数")
+
+    def __repr__(self):
+        return f"<SymbolTimestamp {self.symbol} last_refresh={self.last_refresh_at}>"
+
+
 class ScheduledTask(Base):
     """定时任务配置表"""
     __tablename__ = "scheduled_tasks"

app/services/ai_analysis.py

@@ -0,0 +1,517 @@
+"""
+AI分析服务 - 期货四维联合分析
+"""
+import json
+import re
+import logging
+from datetime import datetime
+from typing import Dict, List, Optional
+from sqlalchemy.orm import Session
+
+from app.analysis_models import AIAnalysisCache
+from app.services.cache import get_cached_data, get_latest_cached
+from pathlib import Path
+
+CONFIG_DIR = Path(__file__).resolve().parent.parent.parent / "config"
+AI_CONFIG_FILE = CONFIG_DIR / "ai_config.json"
+
+logger = logging.getLogger(__name__)
+
+
+class AIAnalysisPrompt:
+    """AI分析提示词管理器"""
+    
+    SYSTEM_PROMPT = """你是一位拥有20年实战经验的资深金融交易分析师，精通A股市场与商品期货的技术分析。
+你的核心使命是基于提供的K线数据，执行【四维联合判断分析法(4D-XV)】，并提供包含风控红线审查的客观交易策略。
+
+你的分析必须遵循以下原则：
+1. 数据驱动：所有结论必须基于输入的JSON数据，严禁凭空捏造。
+2. 四维共振：任何交易建议必须经过MACD（趋势）、成交量（资金）、KDJ（时机）、多周期（方向）的交叉验证。
+3. 红线否决：如果数据触发【17条交易红线】，必须直接给出【禁止交易】或【止损】的建议。
+4. 客观中立：不使用绝对化表述，提供情景预案（概率估算）。
+5. 动态切换：遇到关键位放量突破时，立即切换右侧思维，不逆势死扛。"""
+
+    ANALYSIS_TEMPLATE = """请严格按照以下JSON格式输出分析结果（不要输出任何其他内容）：
+
+{
+  "summary": "一句话总结当前市场状态",
+  "four_dimensional": {
+    "60min": {
+      "macd": {"trend": "up/down/neutral", "histogram": "放大/缩小/背离", "position": "零轴上/下"},
+      "volume": {"status": "放量上涨/缩量回调/趋势量能/拐点量能", "ratio": 1.5},
+      "kdj": {"k": 85, "d": 80, "j": 95, "status": "超买/超卖/中性", "signal": "金叉/死叉/钝化"},
+      "conclusion": "定大势结论"
+    },
+    "30min": {
+      "macd": {"trend": "up/down/neutral", "histogram": "放大/缩小/背离", "position": "零轴上/下"},
+      "volume": {"status": "放量/缩量/正常", "ratio": 1.5},
+      "kdj": {"k": 50, "d": 45, "j": 60, "status": "中性", "signal": "金叉/死叉"},
+      "conclusion": "找拐点结论"
+    },
+    "15min": {
+      "macd": {"trend": "up/down/neutral", "histogram": "放大/缩小/背离", "position": "零轴上/下"},
+      "volume": {"status": "放量/缩量/正常", "ratio": 2.0},
+      "kdj": {"k": 30, "d": 25, "j": 40, "status": "超卖", "signal": "金叉/死叉"},
+      "conclusion": "择入场结论"
+    },
+    "5min": {
+      "macd": {"trend": "up/down/neutral", "histogram": "放大/缩小/背离", "position": "零轴上/下"},
+      "volume": {"status": "放量/缩量/正常", "ratio": 1.8},
+      "kdj": {"k": 50, "d": 45, "j": 60, "status": "超买/超卖/中性", "signal": "金叉/死叉"},
+      "conclusion": "精确定位入场点"
+    }
+  },
+  "kdj_diagnosis": {
+    "current_status": "超买/超卖/中性区域",
+    "divergence": "是否存在顶/底背离",
+    "paralysis": "是否钝化（持续>6根K线）",
+    "recommendation": "KDJ使用建议"
+  },
+  "pivot_points": {
+    "r2": 7500,
+    "r1": 7350,
+    "pp": 7200,
+    "s1": 7050,
+    "s2": 6900,
+    "validation": {
+      "test_count": 3,
+      "volume_confirmed": true,
+      "multi_period_resonance": true,
+      "breakback_confirmed": false
+    }
+  },
+  "red_lines_check": {
+    "passed": true,
+    "violated": [],
+    "warnings": ["暂无红线警告"]
+  },
+  "discipline_score": {
+    "total": 9,
+    "max": 11,
+    "details": {
+      "trend": true,
+      "position": true,
+      "signal": true,
+      "risk": true,
+      "mindset": true
+    }
+  },
+  "trading_suggestion": {
+    "direction": "做多/做空/观望",
+    "confidence": 75,
+    "entry_range": {"min": 7050, "max": 7100},
+    "stop_loss": 6950,
+    "take_profit": [{"price": 7200, "ratio": 50}, {"price": 7350, "ratio": 30}, {"price": 7500, "ratio": 20}],
+    "position_size": "轻仓/半仓/重仓",
+    "reason": "做多理由"
+  },
+  "scenario_plans": {
+    "breakthrough": {"probability": 35, "action": "放量突破关键位，跟随右侧思维"},
+    "consolidation": {"probability": 40, "action": "R1-S1区间内高抛低吸"},
+    "reversal": {"probability": 15, "action": "MACD顶/底背离+量能不足，立即止损反手"},
+    "news_impact": {"probability": 10, "action": "减仓50%规避不确定性"}
+  },
+  "risk_warnings": [
+    "技术指标具有滞后性，历史表现不代表未来",
+    "需结合基本面和市场情绪综合判断"
+  ],
+  "experience_lessons": [
+    "警惕缩量创新高，可能是诱多信号",
+    "KDJ超买钝化中不宜逆势做空"
+  ]
+}"""
+
+    @classmethod
+    def build_prompt(cls, symbol: str, data: Dict) -> str:
+        """构建完整的AI分析提示词"""
+        prompt = f"""{cls.SYSTEM_PROMPT}
+
+现在请分析以下期货品种的K线数据：
+
+## 品种信息
+- 合约代码：{symbol}
+- 当前价格：{data.get('current_price', 'N/A')}
+
+## 多周期K线数据
+```json
+{json.dumps(data, ensure_ascii=False, indent=2)}
+```
+
+{cls.ANALYSIS_TEMPLATE}"""
+
+        return prompt
+
+
+class AIFuturesAnalyzer:
+    """AI期货分析器"""
+    
+    def __init__(self, db: Session, analysis_db: Session = None):
+        self.db = db
+        self.analysis_db = analysis_db or db
+    
+    def get_active_model(self) -> Optional[Dict]:
+        """获取当前激活的AI模型配置"""
+        try:
+            if not AI_CONFIG_FILE.exists():
+                return None
+            
+            with open(AI_CONFIG_FILE, "r", encoding="utf-8") as f:
+                config = json.load(f)
+            
+            models = config.get("models", [])
+            active_model_name = config.get("active_model")
+            
+            if active_model_name:
+                for model in models:
+                    if model.get("model_name") == active_model_name and model.get("enabled", True):
+                        return model
+            
+            for model in models:
+                if model.get("enabled", True):
+                    logger.warning(f"未找到匹配的激活模型，使用第一个启用的模型: {model.get('model_name')}")
+                    return model
+            
+            return None
+        except Exception as e:
+            logger.error(f"加载AI配置失败: {e}")
+            return None
+    
+    def prepare_multi_period_data(self, symbol: str) -> Optional[Dict]:
+        """准备多周期数据用于AI分析"""
+        cached_data = get_cached_data(
+            self.db, 
+            symbol, 
+            "futures",
+            ["5min", "15min", "30min", "60min", "daily"]
+        )
+        
+        if not cached_data or not cached_data.get("timeframes"):
+            return None
+        
+        timeframes = cached_data.get("timeframes", {})
+        current_price = cached_data.get("current_price")
+        
+        result = {
+            "symbol": symbol,
+            "current_price": current_price,
+            "timeframes": {}
+        }
+        
+        for period_name, db_period in [("5min", "5min"), ("15min", "15min"), 
+                                        ("30min", "30min"), ("60min", "60min"), 
+                                        ("daily", "daily")]:
+            if period_name in timeframes and timeframes[period_name]:
+                candles = timeframes[period_name]
+                if len(candles) >= 20:
+                    result["timeframes"][period_name] = self._analyze_timeframe(candles, period_name)
+        
+        return result
+    
+    def _analyze_timeframe(self, candles: List[Dict], period: str) -> Dict:
+        """分析单个周期的技术指标"""
+        if not candles or len(candles) < 20:
+            return {}
+        
+        closes = [float(c.get("close", 0)) for c in candles]
+        highs = [float(c.get("high", 0)) for c in candles]
+        lows = [float(c.get("low", 0)) for c in candles]
+        volumes = [float(c.get("volume", 0)) for c in candles]
+        
+        ma10 = sum(closes[-10:]) / 10 if len(closes) >= 10 else None
+        ma20 = sum(closes[-20:]) / 20 if len(closes) >= 20 else None
+        
+        macd_data = self._calc_macd(closes)
+        kdj_data = self._calc_kdj(highs, lows, closes)
+        
+        avg_volume = sum(volumes[-20:]) / 20 if len(volumes) >= 20 else 0
+        current_volume = volumes[-1] if volumes else 0
+        
+        return {
+            "trend": "up" if closes[-1] > closes[0] else "down",
+            "ma10": round(ma10, 2) if ma10 else None,
+            "ma20": round(ma20, 2) if ma20 else None,
+            "macd_dif": round(macd_data["dif"], 4),
+            "macd_dea": round(macd_data["dea"], 4),
+            "macd_histogram": round(macd_data["histogram"], 4),
+            "kdj_k": kdj_data["k"],
+            "kdj_d": kdj_data["d"],
+            "kdj_j": kdj_data["j"],
+            "volume_avg": round(avg_volume, 2),
+            "volume_current": round(current_volume, 2),
+            "volume_ratio": round(current_volume / avg_volume, 2) if avg_volume > 0 else 1,
+            "candles": candles[-10:] if len(candles) > 10 else candles
+        }
+    
+    def _calc_macd(self, closes: List[float]) -> Dict:
+        """计算MACD指标"""
+        if len(closes) < 26:
+            return {"dif": 0, "dea": 0, "histogram": 0}
+        
+        ema12 = self._calc_ema(closes, 12)
+        ema26 = self._calc_ema(closes, 26)
+        
+        dif = ema12 - ema26
+        dea = self._calc_ema([dif] * len(closes), 9)
+        histogram = 2 * (dif - dea)
+        
+        return {"dif": dif, "dea": dea, "histogram": histogram}
+    
+    def _calc_ema(self, data: List[float], period: int) -> float:
+        """计算EMA"""
+        if len(data) < period:
+            return sum(data) / len(data) if data else 0
+        
+        multiplier = 2 / (period + 1)
+        ema = sum(data[:period]) / period
+        
+        for i in range(period, len(data)):
+            ema = (data[i] - ema) * multiplier + ema
+        
+        return ema
+    
+    def _calc_kdj(self, highs: List[float], lows: List[float], closes: List[float]) -> Dict:
+        """计算KDJ指标"""
+        if len(closes) < 9:
+            return {"k": 50, "d": 50, "j": 50}
+        
+        period = 9
+        recent_highs = highs[-period:]
+        recent_lows = lows[-period:]
+        recent_closes = closes[-period:]
+        
+        highest = max(recent_highs)
+        lowest = min(recent_lows)
+        current = recent_closes[-1]
+        
+        if highest == lowest:
+            rsv = 50
+        else:
+            rsv = (current - lowest) / (highest - lowest) * 100
+        
+        k = rsv * 2 / 3 + 50 / 3
+        d = k * 2 / 3 + 50 / 3
+        j = 3 * k - 2 * d
+        
+        return {"k": round(k, 2), "d": round(d, 2), "j": round(j, 2)}
+    
+    def call_ai_model(self, prompt: str, model: Dict) -> Optional[str]:
+        """调用AI模型"""
+        try:
+            import requests
+            
+            api_base = model.get("api_base", "https://api.openai.com/v1")
+            api_key = model.get("api_key", "")
+            model_id = model.get("model_id") or model.get("model_name", "")
+            
+            logger.info(f"========== AI模型调用开始 ==========")
+            logger.info(f"API Base: {api_base}")
+            logger.info(f"API Key: {'已配置' if api_key else '未配置'} ({api_key[:10]}...)" if api_key else "API Key: 未配置")
+            logger.info(f"Model ID: {model_id}")
+            logger.info(f"Temperature: {model.get('temperature', 0.7)}")
+            logger.info(f"Max Tokens: {model.get('max_tokens', 2000)}")
+            
+            if not api_key:
+                logger.error("API Key 未配置，无法调用AI模型")
+                return None
+            
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}"
+            }
+            
+            payload = {
+                "model": model_id,
+                "messages": [
+                    {"role": "user", "content": prompt}
+                ],
+                "temperature": model.get("temperature", 0.7),
+                "max_tokens": model.get("max_tokens", 2000)
+            }
+            
+            url = f"{api_base}/chat/completions"
+            logger.info(f"请求 URL: {url}")
+            logger.info(f"请求 Payload 大小: {len(str(payload))} 字符")
+            
+            response = requests.post(
+                url,
+                headers=headers,
+                json=payload,
+                timeout=180  # 增加到180秒（3分钟）超时
+            )
+            
+            logger.info(f"响应状态码: {response.status_code}")
+            
+            if response.status_code == 200:
+                result = response.json()
+                content = result["choices"][0]["message"]["content"]
+                logger.info(f"AI响应成功，内容长度: {len(content)} 字符")
+                logger.info(f"========== AI模型调用成功 ==========")
+                return content
+            else:
+                logger.error(f"AI模型调用失败:")
+                logger.error(f"  状态码: {response.status_code}")
+                logger.error(f"  响应内容: {response.text}")
+                logger.error(f"========== AI模型调用失败 ==========")
+                return None
+                
+        except requests.exceptions.Timeout:
+            logger.error("AI模型调用超时（超过60秒）")
+            logger.error(f"========== AI模型调用失败 ==========")
+            return None
+        except requests.exceptions.ConnectionError as e:
+            logger.error(f"AI模型连接错误: {e}")
+            logger.error(f"========== AI模型调用失败 ==========")
+            return None
+        except requests.exceptions.RequestException as e:
+            logger.error(f"AI模型请求异常: {e}")
+            logger.error(f"========== AI模型调用失败 ==========")
+            return None
+        except Exception as e:
+            logger.error(f"调用AI模型未知异常: {e}", exc_info=True)
+            logger.error(f"========== AI模型调用失败 ==========")
+            return None
+    
+    def parse_ai_response(self, response: str) -> Optional[Dict]:
+        """解析AI返回的JSON响应"""
+        try:
+            json_match = re.search(r'\{[\s\S]*\}', response)
+            if json_match:
+                return json.loads(json_match.group(0))
+            return None
+        except Exception as e:
+            logger.error(f"解析AI响应失败: {e}")
+            return None
+    
+    def save_analysis_cache(self, symbol: str, analysis_data: Dict, kline_timestamp: datetime) -> AIAnalysisCache:
+        """保存AI分析结果到缓存"""
+        cache = AIAnalysisCache(
+            symbol=symbol,
+            analysis_data=analysis_data,
+            kline_timestamp=kline_timestamp,
+            created_at=datetime.now()
+        )
+        
+        self.analysis_db.add(cache)
+        self.analysis_db.commit()
+        self.analysis_db.refresh(cache)
+        
+        return cache
+
+    def get_latest_cache(self, symbol: str) -> Optional[AIAnalysisCache]:
+        """获取最新的AI分析缓存"""
+        return self.analysis_db.query(AIAnalysisCache).filter(
+            AIAnalysisCache.symbol == symbol
+        ).order_by(AIAnalysisCache.created_at.desc()).first()
+    
+    def get_latest_kline_timestamp(self, symbol: str) -> Optional[datetime]:
+        """获取当前K线数据的最新时间戳"""
+        cached_data = get_cached_data(
+            self.db,
+            symbol,
+            "futures",
+            ["5min", "15min", "30min", "60min", "daily"]
+        )
+        
+        if not cached_data or not cached_data.get("timeframes"):
+            return None
+        
+        latest_time = None
+        for period, candles in cached_data.get("timeframes", {}).items():
+            if candles and len(candles) > 0:
+                last_candle = candles[-1]
+                time_str = last_candle.get("datetime", last_candle.get("time", ""))
+                if time_str:
+                    try:
+                        candle_time = datetime.fromisoformat(time_str.replace("Z", "+00:00"))
+                        if latest_time is None or candle_time > latest_time:
+                            latest_time = candle_time
+                    except:
+                        pass
+        
+        return latest_time
+    
+    def should_reanalyze(self, symbol: str, cache: AIAnalysisCache) -> bool:
+        """判断是否需要重新分析"""
+        if not cache:
+            return True
+        
+        # 1. 检查时间是否超过15分钟
+        time_since_analysis = (datetime.now() - cache.created_at).total_seconds()
+        if time_since_analysis > 900:  # 15分钟 = 900秒
+            logger.info(f"分析时间已超过15分钟，需要重新分析")
+            return True
+        
+        # 2. 检查K线数据是否有变化
+        current_kline_time = self.get_latest_kline_timestamp(symbol)
+        if current_kline_time and cache.kline_timestamp:
+            if current_kline_time > cache.kline_timestamp:
+                logger.info(f"K线数据已更新（当前: {current_kline_time}, 缓存: {cache.kline_timestamp}），需要重新分析")
+                return True
+        
+        return False
+    
+    def analyze(self, symbol: str) -> Dict:
+        """执行完整的AI分析流程"""
+        logger.info(f"===== 开始AI分析: {symbol} =====")
+        
+        # 获取当前K线数据的时间戳
+        kline_timestamp = self.get_latest_kline_timestamp(symbol)
+        logger.info(f"当前K线数据时间戳: {kline_timestamp}")
+        
+        model = self.get_active_model()
+        if not model:
+            logger.error("未找到激活的AI模型配置")
+            return {
+                "success": False,
+                "error": "未配置AI模型或模型未激活"
+            }
+        
+        logger.info(f"使用AI模型: {model.get('model_name')}")
+        
+        data = self.prepare_multi_period_data(symbol)
+        if not data:
+            logger.error(f"未找到 {symbol} 的市场数据")
+            return {
+                "success": False,
+                "error": f"未找到 {symbol} 的市场数据"
+            }
+        
+        logger.info(f"市场数据准备成功，包含周期: {list(data.get('timeframes', {}).keys())}")
+        
+        prompt = AIAnalysisPrompt.build_prompt(symbol, data)
+        logger.info(f"AI提示词生成完成，长度: {len(prompt)} 字符")
+        
+        response = self.call_ai_model(prompt, model)
+        
+        if not response:
+            logger.error("AI模型返回空响应")
+            return {
+                "success": False,
+                "error": "AI模型调用失败"
+            }
+        
+        logger.info(f"AI模型响应接收成功，长度: {len(response)} 字符")
+        
+        analysis_result = self.parse_ai_response(response)
+        if not analysis_result:
+            logger.error(f"AI响应解析失败，原始响应前100字符: {response[:100]}")
+            return {
+                "success": False,
+                "error": "AI响应解析失败"
+            }
+        
+        logger.info(f"AI响应解析成功")
+        
+        cache = self.save_analysis_cache(symbol, analysis_result, kline_timestamp)
+        logger.info(f"分析结果已保存到缓存，ID: {cache.id}, K线时间戳: {kline_timestamp}")
+        logger.info(f"===== AI分析完成: {symbol} =====")
+        
+        return {
+            "success": True,
+            "data": {
+                "id": cache.id,
+                "symbol": symbol,
+                "analysis_time": cache.created_at.isoformat(),
+                "result": analysis_result
+            }
+        }

app/services/cache.py

@@ -8,7 +8,7 @@ from typing import Dict, List, Optional
 
 from sqlalchemy.orm import Session
 
-from app.models import MarketData, ScheduledTask
+from app.models import MarketData, ScheduledTask, SymbolTimestamp
 from app.config import CACHE_TTL_SECONDS
 
 logger = logging.getLogger(__name__)
@@ -67,7 +67,7 @@ def check_cache_status(
 
 def save_market_data(db: Session, symbol: str, data: Dict) -> MarketData:
     """
-    保存采集结果到缓存。
+    保存采集结果到缓存，并同步更新合约时间戳。
 
     Args:
         symbol: 品种代码
@@ -105,6 +105,9 @@ def save_market_data(db: Session, symbol: str, data: Dict) -> MarketData:
             )
             db.add(record)
 
+    # 更新合约时间戳
+    update_symbol_timestamp(db, symbol, data.get("type", "futures"), now)
+
     db.commit()
     logger.info(f"缓存已更新: {symbol}, {len(data.get('timeframes', {}))} 个周期")
 
@@ -115,6 +118,58 @@ def save_market_data(db: Session, symbol: str, data: Dict) -> MarketData:
     ).order_by(MarketData.fetched_at.desc()).first()
 
 
+def update_symbol_timestamp(db: Session, symbol: str, data_type: str, refresh_time: datetime) -> None:
+    """更新或创建合约时间戳记录"""
+    timestamp_record = db.query(SymbolTimestamp).filter_by(
+        symbol=symbol,
+        data_type=data_type
+    ).first()
+
+    if timestamp_record:
+        timestamp_record.last_refresh_at = refresh_time
+        timestamp_record.refresh_count += 1
+    else:
+        timestamp_record = SymbolTimestamp(
+            symbol=symbol,
+            data_type=data_type,
+            last_refresh_at=refresh_time,
+            refresh_count=1
+        )
+        db.add(timestamp_record)
+    
+    db.commit()
+
+
+def get_symbol_timestamp(db: Session, symbol: str, data_type: str = "futures") -> Optional[datetime]:
+    """获取合约最后刷新时间"""
+    record = db.query(SymbolTimestamp).filter_by(
+        symbol=symbol,
+        data_type=data_type
+    ).first()
+    return record.last_refresh_at if record else None
+
+
+def needs_refresh(db: Session, symbol: str, data_type: str = "futures", threshold_seconds: int = 300) -> bool:
+    """
+    检查合约是否需要刷新（数据是否超过阈值时间）
+    
+    Args:
+        db: 数据库会话
+        symbol: 品种代码
+        data_type: 数据类型
+        threshold_seconds: 阈值时间（秒），默认300秒（5分钟）
+        
+    Returns:
+        True 表示需要刷新，False 表示数据仍然新鲜
+    """
+    last_refresh = get_symbol_timestamp(db, symbol, data_type)
+    if last_refresh is None:
+        return True  # 从未刷新过，需要刷新
+    
+    age = (datetime.now() - last_refresh).total_seconds()
+    return age > threshold_seconds
+
+
 def get_latest_cached(
     db: Session,
     symbol: str,

app/static/ai_config.css

@@ -0,0 +1,568 @@
+:root {
+    --bg-primary: #0d0f14;
+    --bg-secondary: #151820;
+    --bg-card: #1a1d28;
+    --bg-card-hover: #222633;
+    --border-color: #2a2d3a;
+    --text-primary: #e8eaed;
+    --text-secondary: #9aa0ab;
+    --text-muted: #6b7280;
+    --green: #22c55e;
+    --green-bg: rgba(34, 197, 94, 0.15);
+    --green-border: rgba(34, 197, 94, 0.3);
+    --red: #ef4444;
+    --red-bg: rgba(239, 68, 68, 0.15);
+    --blue: #3b82f6;
+    --purple: #8b5cf6;
+    --orange: #f59e0b;
+}
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', 'PingFang SC', 'Hiragino Sans GB', 'Microsoft YaHei', sans-serif;
+    background: var(--bg-primary);
+    color: var(--text-primary);
+    line-height: 1.5;
+}
+
+.app-container {
+    min-height: 100vh;
+    display: flex;
+    flex-direction: column;
+}
+
+.top-nav {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 12px 24px;
+    background: var(--bg-secondary);
+    border-bottom: 1px solid var(--border-color);
+}
+
+.nav-left {
+    display: flex;
+    align-items: center;
+    gap: 16px;
+}
+
+.back-link {
+    color: var(--text-secondary);
+    text-decoration: none;
+    font-size: 14px;
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    transition: color 0.2s;
+}
+
+.back-link:hover {
+    color: var(--text-primary);
+}
+
+.page-title {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    font-size: 16px;
+    font-weight: 600;
+}
+
+.page-title i {
+    color: var(--green);
+}
+
+.nav-right {
+    display: flex;
+    align-items: center;
+    gap: 16px;
+}
+
+.nav-icon-btn {
+    color: var(--text-secondary);
+    text-decoration: none;
+    font-size: 16px;
+    padding: 6px;
+    border-radius: 6px;
+    transition: all 0.2s;
+}
+
+.nav-icon-btn:hover {
+    color: var(--text-primary);
+    background: var(--bg-card);
+}
+
+.main-content {
+    flex: 1;
+    padding: 24px;
+    max-width: 900px;
+    margin: 0 auto;
+    width: 100%;
+}
+
+.config-container {
+    display: flex;
+    flex-direction: column;
+    gap: 20px;
+}
+
+.config-card {
+    background: var(--bg-card);
+    border: 1px solid var(--border-color);
+    border-radius: 12px;
+    padding: 20px;
+}
+
+.card-header {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    margin-bottom: 16px;
+    padding-bottom: 12px;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.card-header h3 {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    font-size: 16px;
+    font-weight: 600;
+}
+
+.card-header h3 i {
+    color: var(--green);
+}
+
+/* 提供商网格 */
+.provider-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(140px, 1fr));
+    gap: 12px;
+}
+
+.provider-card {
+    padding: 16px;
+    background: var(--bg-secondary);
+    border: 2px solid var(--border-color);
+    border-radius: 10px;
+    text-align: center;
+    cursor: pointer;
+    transition: all 0.2s;
+}
+
+.provider-card:hover {
+    border-color: var(--text-muted);
+    background: var(--bg-card-hover);
+}
+
+.provider-card.active {
+    border-color: var(--green);
+    background: var(--green-bg);
+}
+
+.provider-card i {
+    font-size: 28px;
+    margin-bottom: 8px;
+    color: var(--text-secondary);
+}
+
+.provider-card.active i {
+    color: var(--green);
+}
+
+.provider-card .provider-name {
+    font-size: 13px;
+    font-weight: 500;
+}
+
+/* 表单 */
+.form-grid {
+    display: grid;
+    grid-template-columns: repeat(2, 1fr);
+    gap: 16px;
+}
+
+.form-group {
+    display: flex;
+    flex-direction: column;
+    gap: 6px;
+}
+
+.form-group label {
+    font-size: 13px;
+    color: var(--text-secondary);
+}
+
+.form-control {
+    padding: 10px 14px;
+    background: var(--bg-secondary);
+    border: 1px solid var(--border-color);
+    border-radius: 8px;
+    color: var(--text-primary);
+    font-size: 14px;
+    outline: none;
+    transition: border-color 0.2s;
+}
+
+.form-control:focus {
+    border-color: var(--green);
+}
+
+.input-with-toggle {
+    position: relative;
+    display: flex;
+    align-items: center;
+}
+
+.input-with-toggle .form-control {
+    flex: 1;
+    padding-right: 40px;
+}
+
+.toggle-visibility {
+    position: absolute;
+    right: 10px;
+    background: none;
+    border: none;
+    color: var(--text-muted);
+    cursor: pointer;
+    padding: 4px;
+}
+
+.form-range {
+    width: 100%;
+    height: 6px;
+    border-radius: 3px;
+    background: var(--bg-secondary);
+    outline: none;
+    -webkit-appearance: none;
+}
+
+.form-range::-webkit-slider-thumb {
+    -webkit-appearance: none;
+    width: 18px;
+    height: 18px;
+    border-radius: 50%;
+    background: var(--green);
+    cursor: pointer;
+}
+
+.range-labels {
+    display: flex;
+    justify-content: space-between;
+    font-size: 11px;
+    color: var(--text-muted);
+}
+
+.form-actions {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    margin-top: 16px;
+}
+
+.test-result {
+    font-size: 13px;
+}
+
+.test-result.success {
+    color: var(--green);
+}
+
+.test-result.error {
+    color: var(--red);
+}
+
+/* 当前启用的AI卡片 */
+.active-ai-card {
+    border-color: var(--green-border);
+    background: var(--green-bg);
+}
+
+.active-ai-card .card-header h3 {
+    color: var(--green);
+}
+
+.active-ai-card .card-header i {
+    color: var(--green);
+}
+
+.active-ai-display {
+    display: flex;
+    align-items: center;
+    gap: 16px;
+    padding: 12px;
+}
+
+.active-ai-icon {
+    width: 48px;
+    height: 48px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    background: rgba(34, 197, 94, 0.15);
+    border: 1px solid var(--green-border);
+    border-radius: 12px;
+    color: var(--green);
+    font-size: 24px;
+}
+
+.active-ai-info {
+    display: flex;
+    flex-direction: column;
+    gap: 4px;
+}
+
+.active-ai-name {
+    font-size: 16px;
+    font-weight: 600;
+    color: var(--text-primary);
+}
+
+.active-ai-model {
+    font-size: 13px;
+    color: var(--text-secondary);
+}
+
+/* 设置列表 */
+.settings-list {
+    display: flex;
+    flex-direction: column;
+    gap: 16px;
+}
+
+.setting-item {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 12px 0;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.setting-item:last-child {
+    border-bottom: none;
+}
+
+.setting-info {
+    display: flex;
+    flex-direction: column;
+    gap: 2px;
+}
+
+.setting-name {
+    font-size: 14px;
+    font-weight: 500;
+}
+
+.setting-desc {
+    font-size: 12px;
+    color: var(--text-muted);
+}
+
+/* 开关 */
+.switch {
+    position: relative;
+    width: 48px;
+    height: 26px;
+}
+
+.switch input {
+    opacity: 0;
+    width: 0;
+    height: 0;
+}
+
+.slider {
+    position: absolute;
+    cursor: pointer;
+    top: 0;
+    left: 0;
+    right: 0;
+    bottom: 0;
+    background: var(--bg-secondary);
+    border: 1px solid var(--border-color);
+    border-radius: 26px;
+    transition: 0.3s;
+}
+
+.slider:before {
+    position: absolute;
+    content: "";
+    height: 20px;
+    width: 20px;
+    left: 2px;
+    bottom: 2px;
+    background: var(--text-muted);
+    border-radius: 50%;
+    transition: 0.3s;
+}
+
+input:checked + .slider {
+    background: var(--green-bg);
+    border-color: var(--green-border);
+}
+
+input:checked + .slider:before {
+    transform: translateX(22px);
+    background: var(--green);
+}
+
+/* 模型列表 */
+.models-list {
+    display: flex;
+    flex-direction: column;
+    gap: 10px;
+}
+
+.model-item {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 12px 16px;
+    background: var(--bg-secondary);
+    border: 1px solid var(--border-color);
+    border-radius: 8px;
+}
+
+.model-info {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+}
+
+.model-status {
+    width: 10px;
+    height: 10px;
+    border-radius: 50%;
+}
+
+.model-status.active {
+    background: var(--green);
+    box-shadow: 0 0 8px var(--green);
+}
+
+.model-status.inactive {
+    background: var(--text-muted);
+}
+
+.model-name {
+    font-size: 14px;
+    font-weight: 500;
+}
+
+.model-provider {
+    font-size: 12px;
+    color: var(--text-muted);
+}
+
+.model-actions {
+    display: flex;
+    gap: 8px;
+}
+
+.model-actions button {
+    padding: 6px 12px;
+    font-size: 12px;
+    border-radius: 6px;
+    border: none;
+    cursor: pointer;
+    transition: all 0.2s;
+}
+
+.btn-set-active {
+    background: var(--green-bg);
+    color: var(--green);
+    border: 1px solid var(--green-border);
+}
+
+.btn-set-active:hover {
+    background: var(--green);
+    color: white;
+}
+
+.btn-delete {
+    background: var(--red-bg);
+    color: var(--red);
+    border: 1px solid var(--red-border);
+}
+
+.btn-delete:hover {
+    background: var(--red);
+    color: white;
+}
+
+/* 按钮 */
+.btn {
+    padding: 10px 20px;
+    border-radius: 8px;
+    font-size: 14px;
+    font-weight: 500;
+    cursor: pointer;
+    border: none;
+    display: inline-flex;
+    align-items: center;
+    gap: 8px;
+    transition: all 0.2s;
+}
+
+.btn-sm {
+    padding: 6px 12px;
+    font-size: 12px;
+}
+
+.btn-lg {
+    padding: 12px 28px;
+    font-size: 15px;
+}
+
+.btn-primary {
+    background: var(--green);
+    color: white;
+}
+
+.btn-primary:hover {
+    background: #16a34a;
+}
+
+.btn-secondary {
+    background: var(--bg-secondary);
+    color: var(--text-primary);
+    border: 1px solid var(--border-color);
+}
+
+.btn-secondary:hover {
+    background: var(--bg-card-hover);
+}
+
+.save-actions {
+    display: flex;
+    justify-content: center;
+    gap: 16px;
+    padding: 20px 0;
+}
+
+/* 响应式 */
+@media (max-width: 768px) {
+    .form-grid {
+        grid-template-columns: 1fr;
+    }
+    
+    .provider-grid {
+        grid-template-columns: repeat(3, 1fr);
+    }
+    
+    .save-actions {
+        flex-direction: column;
+    }
+    
+    .save-actions .btn {
+        width: 100%;
+        justify-content: center;
+    }
+}

app/static/ai_config.html

@@ -0,0 +1,211 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>AI模型配置 - 期货智析</title>
+    <link rel="stylesheet" href="/static/ai_config.css">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+</head>
+<body>
+    <div class="app-container">
+        <header class="top-nav">
+            <div class="nav-left">
+                <a href="/static/futures_analysis.html" class="back-link">
+                    <i class="fas fa-arrow-left"></i> 返回期货智析
+                </a>
+                <div class="page-title">
+                    <i class="fas fa-robot"></i>
+                    <span>AI模型配置</span>
+                </div>
+            </div>
+            <div class="nav-right">
+                <a href="/" class="nav-icon-btn" title="返回首页">
+                    <i class="fas fa-home"></i>
+                </a>
+            </div>
+        </header>
+
+        <main class="main-content">
+            <div class="config-container">
+                <!-- 当前启用的AI -->
+                <div class="config-card active-ai-card" id="active-ai-card" style="display:none;">
+                    <div class="card-header">
+                        <h3><i class="fas fa-check-circle"></i> 当前启用</h3>
+                    </div>
+                    <div class="active-ai-display">
+                        <div class="active-ai-icon" id="active-ai-icon">
+                            <i class="fas fa-robot"></i>
+                        </div>
+                        <div class="active-ai-info">
+                            <div class="active-ai-name" id="active-ai-name">--</div>
+                            <div class="active-ai-model" id="active-ai-model">--</div>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- AI提供商选择 -->
+                <div class="config-card">
+                    <div class="card-header">
+                        <h3><i class="fas fa-cloud"></i> AI提供商</h3>
+                    </div>
+                    <div class="provider-grid" id="provider-grid">
+                        <!-- 动态生成 -->
+                    </div>
+                </div>
+
+                <!-- API配置 -->
+                <div class="config-card">
+                    <div class="card-header">
+                        <h3><i class="fas fa-key"></i> API配置</h3>
+                    </div>
+                    <div class="form-grid">
+                        <div class="form-group">
+                            <label>提供商</label>
+                            <select id="api-provider" class="form-control">
+                                <option value="openai">OpenAI</option>
+                                <option value="anthropic">Anthropic Claude</option>
+                                <option value="google">Google Gemini</option>
+                                <option value="aliyun">阿里云通义千问</option>
+                                <option value="aliyun_coding">阿里云通义灵码</option>
+                                <option value="bailian">阿里百炼</option>
+                                <option value="baidu">百度文心一言</option>
+                                <option value="zhipu">智谱清言</option>
+                                <option value="custom">自定义</option>
+                            </select>
+                        </div>
+                        <div class="form-group">
+                            <label>API Key</label>
+                            <div class="input-with-toggle">
+                                <input type="password" id="api-key" class="form-control" placeholder="sk-...">
+                                <button type="button" class="toggle-visibility" onclick="toggleApiKeyVisibility()">
+                                    <i class="fas fa-eye"></i>
+                                </button>
+                            </div>
+                        </div>
+                        <div class="form-group">
+                            <label>API Base URL</label>
+                            <input type="text" id="api-base" class="form-control" placeholder="https://api.openai.com/v1">
+                        </div>
+                        <div class="form-group">
+                            <label>模型ID</label>
+                            <select id="model-id" class="form-control">
+                                <option value="gpt-4o">gpt-4o</option>
+                                <option value="gpt-4-turbo">gpt-4-turbo</option>
+                                <option value="gpt-3.5-turbo">gpt-3.5-turbo</option>
+                            </select>
+                        </div>
+                        <div class="form-group">
+                            <label>自定义模型</label>
+                            <input type="text" id="custom-model" class="form-control" placeholder="输入自定义模型名称（留空使用上方选择）">
+                        </div>
+                    </div>
+                    <div class="form-actions">
+                        <button class="btn btn-secondary" onclick="testConnection()">
+                            <i class="fas fa-plug"></i> 测试连接
+                        </button>
+                        <span id="test-result" class="test-result"></span>
+                    </div>
+                </div>
+
+                <!-- 模型参数 -->
+                <div class="config-card">
+                    <div class="card-header">
+                        <h3><i class="fas fa-sliders-h"></i> 模型参数</h3>
+                    </div>
+                    <div class="form-grid">
+                        <div class="form-group">
+                            <label>Temperature (创造力): <span id="temp-value">0.7</span></label>
+                            <input type="range" id="temperature" class="form-range" min="0" max="2" step="0.1" value="0.7">
+                            <div class="range-labels">
+                                <span>精确</span>
+                                <span>创造</span>
+                            </div>
+                        </div>
+                        <div class="form-group">
+                            <label>Max Tokens (最大输出)</label>
+                            <input type="number" id="max-tokens" class="form-control" value="2000" min="100" max="8000">
+                        </div>
+                    </div>
+                </div>
+
+                <!-- 分析设置 -->
+                <div class="config-card">
+                    <div class="card-header">
+                        <h3><i class="fas fa-cogs"></i> 分析设置</h3>
+                    </div>
+                    <div class="settings-list">
+                        <div class="setting-item">
+                            <div class="setting-info">
+                                <span class="setting-name">技术分析</span>
+                                <span class="setting-desc">基于K线和技术指标进行分析</span>
+                            </div>
+                            <label class="switch">
+                                <input type="checkbox" id="enable-technical" checked>
+                                <span class="slider"></span>
+                            </label>
+                        </div>
+                        <div class="setting-item">
+                            <div class="setting-info">
+                                <span class="setting-name">基本面分析</span>
+                                <span class="setting-desc">结合宏观经济和行业数据</span>
+                            </div>
+                            <label class="switch">
+                                <input type="checkbox" id="enable-fundamental">
+                                <span class="slider"></span>
+                            </label>
+                        </div>
+                        <div class="setting-item">
+                            <div class="setting-info">
+                                <span class="setting-name">情绪分析</span>
+                                <span class="setting-desc">分析市场情绪和新闻舆情</span>
+                            </div>
+                            <label class="switch">
+                                <input type="checkbox" id="enable-sentiment">
+                                <span class="slider"></span>
+                            </label>
+                        </div>
+                        <div class="form-group">
+                            <label>风险偏好</label>
+                            <select id="risk-tolerance" class="form-control">
+                                <option value="conservative">保守型</option>
+                                <option value="medium" selected>平衡型</option>
+                                <option value="aggressive">激进型</option>
+                            </select>
+                        </div>
+                        <div class="form-group">
+                            <label>最大仓位比例 (%)</label>
+                            <input type="number" id="max-position" class="form-control" value="10" min="1" max="100">
+                        </div>
+                    </div>
+                </div>
+
+                <!-- 已保存的模型 -->
+                <div class="config-card">
+                    <div class="card-header">
+                        <h3><i class="fas fa-database"></i> 已保存的模型</h3>
+                        <button class="btn btn-primary btn-sm" onclick="addNewModel()">
+                            <i class="fas fa-plus"></i> 添加模型
+                        </button>
+                    </div>
+                    <div class="models-list" id="models-list">
+                        <!-- 动态生成 -->
+                    </div>
+                </div>
+
+                <!-- 保存按钮 -->
+                <div class="save-actions">
+                    <button class="btn btn-primary btn-lg" onclick="saveConfig()">
+                        <i class="fas fa-save"></i> 保存配置
+                    </button>
+                    <button class="btn btn-secondary btn-lg" onclick="loadConfig()">
+                        <i class="fas fa-sync"></i> 重新加载
+                    </button>
+                </div>
+            </div>
+        </main>
+    </div>
+
+    <script src="/static/ai_config.js"></script>
+</body>
+</html>

app/static/ai_config.js

@@ -0,0 +1,369 @@
+const API_BASE = '/api/v1/ai-config';
+
+let currentConfig = null;
+let selectedProvider = 'openai';
+
+document.addEventListener('DOMContentLoaded', function() {
+    loadProviders();
+    loadConfig();
+    initEventListeners();
+});
+
+function initEventListeners() {
+    document.getElementById('api-provider').addEventListener('change', function() {
+        selectedProvider = this.value;
+        updateProviderModels();
+    });
+    
+    document.getElementById('temperature').addEventListener('input', function() {
+        document.getElementById('temp-value').textContent = this.value;
+    });
+}
+
+async function loadProviders() {
+    try {
+        const response = await fetch(`${API_BASE}/providers`);
+        const data = await response.json();
+        if (data.success) {
+            renderProviders(data.data);
+        }
+    } catch (error) {
+        console.error('加载提供商失败:', error);
+        renderProviders(getDefaultProviders());
+    }
+}
+
+function getDefaultProviders() {
+    return [
+        { id: 'openai', name: 'OpenAI', icon: 'fas fa-brain' },
+        { id: 'anthropic', name: 'Claude', icon: 'fas fa-robot' },
+        { id: 'google', name: 'Gemini', icon: 'fas fa-gem' },
+        { id: 'aliyun', name: '通义千问', icon: 'fas fa-cloud' },
+        { id: 'aliyun_coding', name: '通义灵码', icon: 'fas fa-code' },
+        { id: 'bailian', name: '阿里百炼', icon: 'fas fa-flask' },
+        { id: 'baidu', name: '文心一言', icon: 'fas fa-comments' },
+        { id: 'zhipu', name: '智谱清言', icon: 'fas fa-lightbulb' }
+    ];
+}
+
+function renderProviders(providers) {
+    const grid = document.getElementById('provider-grid');
+    const iconMap = {
+        'openai': 'fas fa-brain',
+        'anthropic': 'fas fa-robot',
+        'google': 'fas fa-gem',
+        'aliyun': 'fas fa-cloud',
+        'aliyun_coding': 'fas fa-code',
+        'bailian': 'fas fa-flask',
+        'baidu': 'fas fa-comments',
+        'zhipu': 'fas fa-lightbulb',
+        'custom': 'fas fa-cog'
+    };
+    
+    grid.innerHTML = providers.map(p => `
+        <div class="provider-card ${p.id === selectedProvider ? 'active' : ''}" data-provider="${p.id}">
+            <i class="${iconMap[p.id] || 'fas fa-cog'}"></i>
+            <div class="provider-name">${p.name}</div>
+        </div>
+    `).join('');
+    
+    grid.querySelectorAll('.provider-card').forEach(card => {
+        card.addEventListener('click', function() {
+            grid.querySelectorAll('.provider-card').forEach(c => c.classList.remove('active'));
+            this.classList.add('active');
+            selectedProvider = this.dataset.provider;
+            document.getElementById('api-provider').value = selectedProvider;
+            updateProviderModels();
+        });
+    });
+}
+
+function updateProviderModels() {
+    const modelSelect = document.getElementById('model-id');
+    const modelMap = {
+        'openai': ['gpt-4o', 'gpt-4-turbo', 'gpt-3.5-turbo'],
+        'anthropic': ['claude-3-opus', 'claude-3-sonnet', 'claude-3-haiku'],
+        'google': ['gemini-pro', 'gemini-pro-vision'],
+        'aliyun': ['qwen-max', 'qwen-plus', 'qwen-turbo'],
+        'aliyun_coding': ['qwen-coder-plus', 'qwen-coder-turbo'],
+        'bailian': ['qwen3.6-plus', 'qwen3.5-plus', 'qwen3-max', 'qwen3-coder-plus', 'MiniMax-M2.5', 'glm-4.7', 'kimi-k2.5', 'custom'],
+        'baidu': ['ernie-4.0', 'ernie-3.5', 'ernie-speed'],
+        'zhipu': ['glm-4', 'glm-3-turbo'],
+        'custom': ['custom-model']
+    };
+    
+    const apiBaseMap = {
+        'openai': 'https://api.openai.com/v1',
+        'anthropic': 'https://api.anthropic.com/v1',
+        'google': 'https://generativelanguage.googleapis.com/v1beta',
+        'aliyun': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+        'aliyun_coding': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+        'bailian': 'https://coding.dashscope.aliyuncs.com/v1',
+        'baidu': 'https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop',
+        'zhipu': 'https://open.bigmodel.cn/api/paas/v4',
+        'custom': ''
+    };
+    
+    const models = modelMap[selectedProvider] || ['custom-model'];
+    modelSelect.innerHTML = models.map(m => `<option value="${m}">${m}</option>`).join('');
+    document.getElementById('api-base').value = apiBaseMap[selectedProvider] || '';
+}
+
+async function loadConfig() {
+    try {
+        const response = await fetch(API_BASE);
+        const result = await response.json();
+        if (result.success && result.data) {
+            currentConfig = result.data;
+            populateForm(currentConfig);
+            renderModelsList(currentConfig.models || []);
+        }
+    } catch (error) {
+        console.error('加载配置失败:', error);
+    }
+}
+
+function populateForm(config) {
+    if (config.models && config.models.length > 0) {
+        const activeModel = config.models.find(m => m.enabled) || config.models[0];
+        document.getElementById('api-provider').value = activeModel.provider || 'openai';
+        document.getElementById('api-key').value = activeModel.api_key || '';
+        document.getElementById('api-base').value = activeModel.api_base || '';
+        document.getElementById('model-id').value = activeModel.model_id || 'gpt-4o';
+        document.getElementById('custom-model').value = '';
+        document.getElementById('temperature').value = activeModel.temperature || 0.7;
+        document.getElementById('temp-value').textContent = activeModel.temperature || 0.7;
+        document.getElementById('max-tokens').value = activeModel.max_tokens || 2000;
+        
+        // 选中当前启用的提供商卡片
+        const providerCard = document.querySelector(`.provider-card[data-provider="${activeModel.provider}"]`);
+        if (providerCard) {
+            document.querySelectorAll('.provider-card').forEach(c => c.classList.remove('active'));
+            providerCard.classList.add('active');
+        }
+        
+        // 更新模型下拉框
+        updateProviderModels();
+    }
+    
+    if (config.analysis_settings) {
+        document.getElementById('enable-technical').checked = config.analysis_settings.enable_technical_analysis !== false;
+        document.getElementById('enable-fundamental').checked = config.analysis_settings.enable_fundamental_analysis === true;
+        document.getElementById('enable-sentiment').checked = config.analysis_settings.enable_sentiment_analysis === true;
+        document.getElementById('risk-tolerance').value = config.analysis_settings.risk_tolerance || 'medium';
+        document.getElementById('max-position').value = config.analysis_settings.max_position_pct || 10;
+    }
+}
+
+function renderModelsList(models) {
+    const list = document.getElementById('models-list');
+    const activeCard = document.getElementById('active-ai-card');
+    
+    if (!models || models.length === 0) {
+        list.innerHTML = '<div class="empty-state">暂无已保存的模型</div>';
+        activeCard.style.display = 'none';
+        return;
+    }
+    
+    const activeModel = models.find(m => m.enabled);
+    if (activeModel) {
+        activeCard.style.display = 'block';
+        document.getElementById('active-ai-name').textContent = getProviderName(activeModel.provider || activeModel.api_base);
+        document.getElementById('active-ai-model').textContent = activeModel.model_name || activeModel.model_id || '--';
+        
+        const iconMap = {
+            'openai': 'fab fa-openai',
+            'anthropic': 'fas fa-robot',
+            'google': 'fab fa-google',
+            'aliyun': 'fas fa-cloud',
+            'aliyun_coding': 'fas fa-code',
+            'bailian': 'fas fa-flask',
+            'baidu': 'fas fa-comments',
+            'zhipu': 'fas fa-lightbulb'
+        };
+        const icon = document.getElementById('active-ai-icon').querySelector('i');
+        icon.className = iconMap[activeModel.provider] || 'fas fa-robot';
+    } else {
+        activeCard.style.display = 'none';
+    }
+    
+    list.innerHTML = models.map((model, index) => `
+        <div class="model-item">
+            <div class="model-info">
+                <div class="model-status ${model.enabled ? 'active' : 'inactive'}"></div>
+                <div>
+                    <div class="model-name">${model.model_name || model.model_id}</div>
+                    <div class="model-provider">${getProviderName(model.provider || model.api_base)}</div>
+                </div>
+            </div>
+            <div class="model-actions">
+                ${!model.enabled ? `<button class="btn-set-active" onclick="setActiveModel(${index})">设为默认</button>` : '<span class="active-badge">当前启用</span>'}
+                <button class="btn-delete" onclick="deleteModel(${index})"><i class="fas fa-trash"></i></button>
+            </div>
+        </div>
+    `).join('');
+}
+
+function getProviderName(apiBase) {
+    const map = {
+        'openai': 'OpenAI',
+        'anthropic': 'Anthropic',
+        'google': 'Google',
+        'aliyun': '阿里云',
+        'aliyun_coding': '阿里云通义灵码',
+        'bailian': '阿里百炼',
+        'baidu': '百度',
+        'zhipu': '智谱'
+    };
+    return map[apiBase] || apiBase;
+}
+
+function toggleApiKeyVisibility() {
+    const input = document.getElementById('api-key');
+    const icon = document.querySelector('.toggle-visibility i');
+    if (input.type === 'password') {
+        input.type = 'text';
+        icon.className = 'fas fa-eye-slash';
+    } else {
+        input.type = 'password';
+        icon.className = 'fas fa-eye';
+    }
+}
+
+async function testConnection() {
+    const resultEl = document.getElementById('test-result');
+    resultEl.textContent = '测试中...';
+    resultEl.className = 'test-result';
+    
+    const customModel = document.getElementById('custom-model').value.trim();
+    const selectedModel = document.getElementById('model-id').value;
+    const modelId = customModel || (selectedModel === 'custom' ? '' : selectedModel);
+    
+    if (!modelId) {
+        resultEl.textContent = '✗ 请输入模型ID';
+        resultEl.className = 'test-result error';
+        return;
+    }
+    
+    const config = {
+        model_name: modelId,
+        api_key: document.getElementById('api-key').value,
+        api_base: document.getElementById('api-base').value,
+        model_id: modelId,
+        temperature: parseFloat(document.getElementById('temperature').value),
+        max_tokens: parseInt(document.getElementById('max-tokens').value),
+        enabled: true
+    };
+    
+    try {
+        const response = await fetch(`${API_BASE}/test`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify(config)
+        });
+        
+        if (!response.ok) {
+            resultEl.textContent = `✗ 请求失败: ${response.status}`;
+            resultEl.className = 'test-result error';
+            return;
+        }
+        
+        const data = await response.json();
+        
+        if (data.success) {
+            resultEl.textContent = '✓ 连接成功';
+            resultEl.className = 'test-result success';
+        } else {
+            resultEl.textContent = '✗ ' + (data.message || '未知错误');
+            resultEl.className = 'test-result error';
+        }
+    } catch (error) {
+        resultEl.textContent = '✗ 连接失败: ' + (error.message || '未知错误');
+        resultEl.className = 'test-result error';
+    }
+}
+
+async function saveConfig() {
+    const models = currentConfig?.models || [];
+    const existingIndex = models.findIndex(m => m.provider === selectedProvider);
+    
+    const customModel = document.getElementById('custom-model').value.trim();
+    const selectedModel = document.getElementById('model-id').value;
+    const modelId = customModel || (selectedModel === 'custom' ? '' : selectedModel);
+    
+    const newModel = {
+        model_name: modelId,
+        provider: selectedProvider,
+        api_key: document.getElementById('api-key').value,
+        api_base: document.getElementById('api-base').value,
+        model_id: modelId,
+        temperature: parseFloat(document.getElementById('temperature').value),
+        max_tokens: parseInt(document.getElementById('max-tokens').value),
+        enabled: true
+    };
+    
+    if (existingIndex >= 0) {
+        models[existingIndex] = { ...models[existingIndex], ...newModel };
+    } else {
+        models.push(newModel);
+    }
+    
+    models.forEach(m => {
+        m.enabled = (m.provider === selectedProvider && m.model_id === modelId);
+    });
+    
+    const config = {
+        models: models,
+        active_model: selectedProvider,
+        analysis_settings: {
+            enable_technical_analysis: document.getElementById('enable-technical').checked,
+            enable_fundamental_analysis: document.getElementById('enable-fundamental').checked,
+            enable_sentiment_analysis: document.getElementById('enable-sentiment').checked,
+            risk_tolerance: document.getElementById('risk-tolerance').value,
+            max_position_pct: parseInt(document.getElementById('max-position').value)
+        }
+    };
+    
+    try {
+        const response = await fetch(API_BASE, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify(config)
+        });
+        const data = await response.json();
+        
+        if (data.success) {
+            alert('配置保存成功!');
+            currentConfig = config;
+            renderModelsList(models);
+        } else {
+            alert('保存失败: ' + data.message);
+        }
+    } catch (error) {
+        alert('保存失败: ' + error.message);
+    }
+}
+
+function setActiveModel(index) {
+    if (!currentConfig || !currentConfig.models) return;
+    
+    currentConfig.models.forEach((m, i) => {
+        m.enabled = i === index;
+    });
+    
+    saveConfig();
+}
+
+function deleteModel(index) {
+    if (!confirm('确定要删除这个模型吗?')) return;
+    
+    if (!currentConfig || !currentConfig.models) return;
+    
+    currentConfig.models.splice(index, 1);
+    saveConfig();
+}
+
+function addNewModel() {
+    document.getElementById('api-key').value = '';
+    document.getElementById('api-key').focus();
+}

app/static/futures_analysis.html

@@ -0,0 +1,416 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>期货智析 - 智能期货期权分析系统</title>
+    <link rel="stylesheet" href="/static/futures_analysis.css">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+</head>
+<body class="theme-minimal">
+    <div class="bg-grid"></div>
+    <div class="bg-glow"></div>
+    
+    <div class="app-container">
+        <!-- 顶部导航 -->
+        <header class="top-nav">
+            <div class="nav-left">
+                <div class="logo">
+                    <div class="logo-icon">
+                        <i class="fas fa-chart-line"></i>
+                        <div class="logo-pulse"></div>
+                    </div>
+                    <div class="logo-text">
+                        <span class="logo-title">期货智析</span>
+                        <span class="logo-subtitle">FUTURES INTELLIGENCE</span>
+                    </div>
+                </div>
+            </div>
+            <nav class="nav-center">
+                <a href="#" class="nav-item active" data-page="analysis">
+                    <span class="nav-icon"><i class="fas fa-microchip"></i></span>
+                    <span>品种分析</span>
+                </a>
+                <a href="#" class="nav-item" data-page="watched">
+                    <span class="nav-icon"><i class="fas fa-star"></i></span>
+                    <span>自选</span>
+                </a>
+                <a href="#" class="nav-item" data-page="market">
+                    <span class="nav-icon"><i class="fas fa-globe"></i></span>
+                    <span>市场概览</span>
+                </a>
+                <a href="#" class="nav-item" data-page="risk">
+                    <span class="nav-icon"><i class="fas fa-shield-alt"></i></span>
+                    <span>风险预警</span>
+                </a>
+            </nav>
+            <div class="nav-right">
+                <div class="system-status">
+                    <span class="status-dot"></span>
+                    <span class="status-text">LIVE</span>
+                </div>
+                <div class="datetime" id="current-time">--</div>
+                <a href="/ai-config" class="nav-btn" title="AI配置">
+                    <i class="fas fa-brain"></i>
+                </a>
+                <button class="nav-btn theme-toggle" id="theme-toggle" title="切换主题">
+                    <i class="fas fa-moon"></i>
+                </button>
+                <a href="/" class="nav-btn" title="返回首页">
+                    <i class="fas fa-th-large"></i>
+                </a>
+            </div>
+        </header>
+
+        <!-- Toast 提示容器 -->
+        <div class="toast-container" id="toast-container"></div>
+
+        <!-- 主内容区 -->
+        <main class="main-content">
+            <!-- 品种列表视图 -->
+            <div id="list-view" class="view active">
+                <!-- 搜索栏 -->
+                <div class="search-section">
+                    <div class="search-box">
+                        <i class="fas fa-search"></i>
+                        <input type="text" id="search-input" placeholder="搜索品种名称或代码...">
+                        <kbd>⌘K</kbd>
+                    </div>
+                    <div class="view-controls">
+                        <button class="view-btn active" data-view="grid" title="网格视图">
+                            <i class="fas fa-grid-2"></i>
+                            <span>网格</span>
+                        </button>
+                        <button class="view-btn" data-view="list" title="列表视图">
+                            <i class="fas fa-list"></i>
+                            <span>列表</span>
+                        </button>
+                    </div>
+                </div>
+
+                <!-- 筛选栏 -->
+                <div class="filter-bar">
+                    <div class="filter-tabs">
+                        <button class="filter-tab active" data-category="all">
+                            <span>全部</span>
+                            <span class="filter-count" id="count-all">0</span>
+                        </button>
+                        <button class="filter-tab" data-category="watched">
+                            <i class="fas fa-star"></i>
+                            <span>自选</span>
+                            <span class="filter-count" id="count-watched">0</span>
+                        </button>
+                        <button class="filter-tab" data-category="energy">
+                            <i class="fas fa-fire"></i>
+                            <span>能源</span>
+                        </button>
+                        <button class="filter-tab" data-category="metal">
+                            <i class="fas fa-cube"></i>
+                            <span>金属</span>
+                        </button>
+                        <button class="filter-tab" data-category="agriculture">
+                            <i class="fas fa-seedling"></i>
+                            <span>农产品</span>
+                        </button>
+                        <button class="filter-tab" data-category="finance">
+                            <i class="fas fa-chart-pie"></i>
+                            <span>金融</span>
+                        </button>
+                    </div>
+                    <div class="filter-actions">
+                    <button class="refresh-all-btn" id="refresh-all-btn" title="刷新全部品种">
+                        <i class="fas fa-sync-alt"></i>
+                        <span>刷新全部</span>
+                    </button>
+                    <button class="ai-analyze-all-btn" id="ai-analyze-all-btn" title="AI分析全部品种">
+                        <i class="fas fa-brain"></i>
+                        <span>全部分析</span>
+                    </button>
+                    <div class="sort-select">
+                    <select id="sort-select">
+                        <option value="trend_score">趋势评分</option>
+                        <option value="success_rate">成功率</option>
+                        <option value="change_pct">涨跌幅</option>
+                        <option value="name">名称</option>
+                    </select>
+                </div>
+                </div>
+                </div>
+
+                <!-- 统计概览 -->
+                <div class="stats-overview">
+                    <div class="stat-card" onclick="filterByTrend('all')" style="cursor: pointer;" title="显示全部">
+                        <div class="stat-icon"><i class="fas fa-layer-group"></i></div>
+                        <div class="stat-info">
+                            <span class="stat-value" id="total-count">0</span>
+                            <span class="stat-label">监控品种</span>
+                        </div>
+                    </div>
+                    <div class="stat-card up" onclick="filterByTrend('up')" style="cursor: pointer;" title="筛选上涨趋势">
+                        <div class="stat-icon"><i class="fas fa-arrow-trend-up"></i></div>
+                        <div class="stat-info">
+                            <span class="stat-value" id="up-count">0</span>
+                            <span class="stat-label">上涨趋势</span>
+                        </div>
+                    </div>
+                    <div class="stat-card down" onclick="filterByTrend('down')" style="cursor: pointer;" title="筛选下跌趋势">
+                        <div class="stat-icon"><i class="fas fa-arrow-trend-down"></i></div>
+                        <div class="stat-info">
+                            <span class="stat-value" id="down-count">0</span>
+                            <span class="stat-label">下跌趋势</span>
+                        </div>
+                    </div>
+                    <div class="stat-card neutral" onclick="filterByTrend('neutral')" style="cursor: pointer;" title="筛选震荡整理">
+                        <div class="stat-icon"><i class="fas fa-arrows-left-right"></i></div>
+                        <div class="stat-info">
+                            <span class="stat-value" id="neutral-count">0</span>
+                            <span class="stat-label">震荡整理</span>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- 品种卡片网格 -->
+                <div id="futures-grid" class="futures-grid">
+                    <!-- 动态生成 -->
+                </div>
+            </div>
+
+            <!-- 详情分析视图 -->
+            <div id="detail-view" class="view">
+                <!-- 返回按钮 -->
+                <div class="detail-actions">
+                    <button class="back-btn" id="back-btn">
+                        <i class="fas fa-arrow-left"></i>
+                        <span>返回</span>
+                    </button>
+                    <button class="refresh-btn" id="refresh-symbol-btn" title="刷新合约数据">
+                        <i class="fas fa-sync-alt"></i>
+                        <span>刷新数据</span>
+                    </button>
+                </div>
+
+                <!-- 品种标题区 -->
+                <div class="detail-header">
+                    <div class="header-left">
+                        <div class="symbol-info">
+                            <span class="symbol-name" id="detail-name">--</span>
+                            <span class="symbol-code" id="detail-symbol">--</span>
+                        </div>
+                        <div class="price-main">
+                            <span class="price-value" id="detail-price">--</span>
+                            <span class="price-change" id="detail-change">--</span>
+                            <div class="price-levels">
+                                <span class="level-tag resistance" id="detail-r1">R1: --</span>
+                                <span class="level-tag support" id="detail-s1">S1: --</span>
+                            </div>
+                        </div>
+                    </div>
+                    <div class="header-right">
+                        <div class="quote-grid">
+                            <div class="quote-item">
+                                <span class="quote-label">开盘</span>
+                                <span class="quote-value" id="detail-open">--</span>
+                            </div>
+                            <div class="quote-item">
+                                <span class="quote-label">最高</span>
+                                <span class="quote-value up" id="detail-high">--</span>
+                            </div>
+                            <div class="quote-item">
+                                <span class="quote-label">最低</span>
+                                <span class="quote-value down" id="detail-low">--</span>
+                            </div>
+                            <div class="quote-item">
+                                <span class="quote-label">成交量</span>
+                                <span class="quote-value" id="detail-volume">--</span>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- 周期选择 -->
+                <div class="period-bar">
+                    <span class="period-label"><i class="fas fa-clock"></i> 周期</span>
+                    <div class="period-btns">
+                        <button class="period-btn" data-period="5">5M</button>
+                        <button class="period-btn active" data-period="15">15M</button>
+                        <button class="period-btn" data-period="30">30M</button>
+                        <button class="period-btn" data-period="60">1H</button>
+                    </div>
+                </div>
+
+                <!-- 图表和侧边栏 -->
+                <div class="detail-body">
+                    <div class="chart-section">
+                        <!-- K线图表区 -->
+                        <div class="chart-container">
+                            <div class="chart-header">
+                                <span class="chart-title">K线图</span>
+                                <div class="chart-legend">
+                                    <span class="legend-item"><span class="legend-dot ma5"></span>MA5</span>
+                                    <span class="legend-item"><span class="legend-dot ma10"></span>MA10</span>
+                                    <span class="legend-item"><span class="legend-dot ma20"></span>MA20</span>
+                                </div>
+                            </div>
+                            <div id="kline-chart" class="kline-chart"></div>
+                        </div>
+
+                        <!-- 历史分析记录 -->
+                        <div class="history-container">
+                            <div class="history-header">
+                                <i class="fas fa-clock-rotate-left"></i>
+                                <span>历史分析记录</span>
+                            </div>
+                            <div class="history-list" id="history-list">
+                                <!-- 动态生成 -->
+                            </div>
+                        </div>
+                    </div>
+
+                    <!-- 右侧分析面板 -->
+                    <div class="analysis-sidebar">
+                        <!-- AI智能分析 -->
+                        <div class="panel-card ai-analysis-card" id="ai-analysis-panel">
+                            <div class="panel-header">
+                                <i class="fas fa-brain"></i>
+                                <span>AI 思维分析</span>
+                                <div class="panel-header-actions">
+                                    <button class="ai-analyze-btn" id="ai-analyze-btn" onclick="runAIAnalysis()" title="执行AI分析">
+                                        <i class="fas fa-play"></i>
+                                        <span>智能分析</span>
+                                    </button>
+                                </div>
+                            </div>
+                            <div class="ai-analysis-content" id="ai-analysis-content">
+                                <div class="ai-analysis-placeholder">
+                                    <i class="fas fa-brain"></i>
+                                    <p>点击"智能分析"按钮获取AI分析结果</p>
+                                </div>
+                            </div>
+                        </div>
+
+                        <!-- 技术指标 -->
+                        <div class="panel-card indicators-card">
+                            <div class="panel-header">
+                                <i class="fas fa-wave-pulse"></i>
+                                <span>技术指标</span>
+                            </div>
+                            <div class="indicators-grid">
+                                <div class="indicator-cell">
+                                    <span class="indicator-label">MACD</span>
+                                    <span class="indicator-value" id="macd-signal">--</span>
+                                    <span class="indicator-detail" id="macd-detail">--</span>
+                                </div>
+                                <div class="indicator-cell">
+                                    <span class="indicator-label">RSI</span>
+                                    <span class="indicator-value" id="rsi-value">--</span>
+                                    <span class="indicator-detail" id="rsi-status">--</span>
+                                </div>
+                                <div class="indicator-cell">
+                                    <span class="indicator-label">BOLL</span>
+                                    <span class="indicator-value" id="boll-signal">--</span>
+                                    <span class="indicator-detail" id="boll-detail">--</span>
+                                </div>
+                                <div class="indicator-cell">
+                                    <span class="indicator-label">KDJ</span>
+                                    <span class="indicator-value" id="kdj-signal">--</span>
+                                    <span class="indicator-detail" id="kdj-detail">--</span>
+                                </div>
+                            </div>
+                        </div>
+
+                        <!-- 关键点位 -->
+                        <div class="panel-card levels-card">
+                            <div class="panel-header">
+                                <i class="fas fa-crosshairs"></i>
+                                <span>关键点位</span>
+                            </div>
+                            <div class="levels-container">
+                                <div class="level-group resistance">
+                                    <span class="level-group-label">压力</span>
+                                    <div class="level-item" id="resistance-1"><span>R1</span><span>--</span></div>
+                                    <div class="level-item" id="resistance-2"><span>R2</span><span>--</span></div>
+                                </div>
+                                <div class="level-divider"></div>
+                                <div class="level-item pivot-point" id="pivot-point">
+                                    <span>中枢 (PP)</span>
+                                    <span>--</span>
+                                </div>
+                                <div class="level-divider"></div>
+                                <div class="level-group support">
+                                    <span class="level-group-label">支撑</span>
+                                    <div class="level-item" id="support-1"><span>S1</span><span>--</span></div>
+                                    <div class="level-item" id="support-2"><span>S2</span><span>--</span></div>
+                                </div>
+                            </div>
+                        </div>
+
+                        <!-- 多周期趋势 -->
+                        <div class="panel-card trends-card">
+                            <div class="panel-header">
+                                <i class="fas fa-timeline"></i>
+                                <span>多周期趋势</span>
+                            </div>
+                            <div class="trends-container" id="period-trends">
+                                <!-- 动态生成 -->
+                            </div>
+                        </div>
+
+                        <!-- 情景预案 -->
+                        <div class="panel-card scenario-card" id="scenario-panel" style="display:none;">
+                            <div class="panel-header">
+                                <i class="fas fa-chess"></i>
+                                <span>情景预案</span>
+                            </div>
+                            <div class="scenario-container" id="scenario-plans">
+                                <!-- 动态生成 -->
+                            </div>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </main>
+    </div>
+
+    <!-- AI分析详情对话框 -->
+    <div class="modal-overlay" id="ai-analysis-modal">
+        <div class="modal-content modal-large">
+            <div class="modal-header">
+                <h3><i class="fas fa-brain"></i> AI 四维联合分析报告</h3>
+                <button class="modal-close" onclick="closeModal('ai-analysis-modal')"><i class="fas fa-xmark"></i></button>
+            </div>
+            <div class="modal-body" id="ai-analysis-modal-body">
+                <!-- 动态生成 -->
+            </div>
+        </div>
+    </div>
+
+    <!-- AI建议详情对话框 -->
+    <div class="modal-overlay" id="suggestion-modal">
+        <div class="modal-content">
+            <div class="modal-header">
+                <h3><i class="fas fa-robot"></i> AI 交易建议详情</h3>
+                <button class="modal-close" onclick="closeModal('suggestion-modal')"><i class="fas fa-xmark"></i></button>
+            </div>
+            <div class="modal-body" id="suggestion-modal-body">
+                <!-- 动态生成 -->
+            </div>
+        </div>
+    </div>
+
+    <!-- 历史记录详情对话框 -->
+    <div class="modal-overlay" id="history-modal">
+        <div class="modal-content">
+            <div class="modal-header">
+                <h3><i class="fas fa-clock-rotate-left"></i> 分析记录详情</h3>
+                <button class="modal-close" onclick="closeModal('history-modal')"><i class="fas fa-xmark"></i></button>
+            </div>
+            <div class="modal-body" id="history-modal-body">
+                <!-- 动态生成 -->
+            </div>
+        </div>
+    </div>
+
+    <script src="https://cdn.jsdelivr.net/npm/echarts@5.4.3/dist/echarts.min.js"></script>
+    <script src="/static/futures_analysis.js"></script>
+</body>
+</html>

app/static/index.html

@@ -678,6 +678,15 @@
                 <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/><line x1="16" y1="13" x2="8" y2="13"/><line x1="16" y1="17" x2="8" y2="17"/></svg>
                 <span>运行日志</span>
             </a>
+            <div class="nav-divider"></div>
+            <a class="nav-item" href="/futures-analysis" target="_blank">
+                <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M3 3v18h18"/><path d="M18 17V9"/><path d="M13 17V5"/><path d="M8 17v-3"/></svg>
+                <span>期货智析</span>
+            </a>
+            <a class="nav-item" href="/ai-config" target="_blank">
+                <svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><circle cx="12" cy="12" r="3"/><path d="M19.4 15a1.65 1.65 0 0 0 .33 1.82l.06.06a2 2 0 0 1 0 2.83 2 2 0 0 1-2.83 0l-.06-.06a1.65 1.65 0 0 0-1.82-.33 1.65 1.65 0 0 0-1 1.51V21a2 2 0 0 1-2 2 2 2 0 0 1-2-2v-.09A1.65 1.65 0 0 0 9 19.4a1.65 1.65 0 0 0-1.82.33l-.06.06a2 2 0 0 1-2.83 0 2 2 0 0 1 0-2.83l.06-.06A1.65 1.65 0 0 0 4.68 15a1.65 1.65 0 0 0-1.51-1H3a2 2 0 0 1-2-2 2 2 0 0 1 2-2h.09A1.65 1.65 0 0 0 4.6 9a1.65 1.65 0 0 0-.33-1.82l-.06-.06a2 2 0 0 1 0-2.83 2 2 0 0 1 2.83 0l.06.06A1.65 1.65 0 0 0 9 4.68a1.65 1.65 0 0 0 1-1.51V3a2 2 0 0 1 2-2 2 2 0 0 1 2 2v.09a1.65 1.65 0 0 0 1 1.51 1.65 1.65 0 0 0 1.82-.33l.06-.06a2 2 0 0 1 2.83 0 2 2 0 0 1 0 2.83l-.06.06a1.65 1.65 0 0 0-.33 1.82V9a1.65 1.65 0 0 0 1.51 1H21a2 2 0 0 1 2 2 2 2 0 0 1-2 2h-.09a1.65 1.65 0 0 0-1.51 1z"/></svg>
+                <span>AI配置</span>
+            </a>
         </nav>
     </aside>
 

check_ai_models.py

@@ -0,0 +1,22 @@
+import sqlite3
+
+db_path = 'data/futures_analysis.db'
+
+conn = sqlite3.connect(db_path)
+
+print('=== AI模型配置 ===')
+cursor = conn.execute("SELECT * FROM ai_model_configs")
+cols = [desc[0] for desc in cursor.description]
+print(f'字段: {cols}')
+rows = cursor.fetchall()
+print(f'记录数: {len(rows)}')
+for row in rows:
+    print(dict(zip(cols, row)))
+
+print('\n=== 分析设置 ===')
+cursor = conn.execute("SELECT * FROM analysis_settings")
+rows = cursor.fetchall()
+for row in rows:
+    print(row)
+
+conn.close()

check_cache.py

@@ -0,0 +1,12 @@
+import sqlite3
+
+conn = sqlite3.connect('data/futures_analysis.db')
+cursor = conn.execute('SELECT id, symbol, created_at FROM ai_analysis_cache ORDER BY created_at DESC LIMIT 10')
+
+print('AI分析缓存记录:')
+print('ID | 合约 | 创建时间')
+print('-' * 60)
+for row in cursor:
+    print(f'{row[0]} | {row[1]} | {row[2]}')
+
+conn.close()

check_db.py

@@ -0,0 +1,32 @@
+import sqlite3
+import os
+
+db_path = 'data/futures_analysis.db'
+
+print(f'数据库文件路径: {os.path.abspath(db_path)}')
+print(f'数据库存在: {os.path.exists(db_path)}')
+
+if os.path.exists(db_path):
+    print(f'数据库大小: {os.path.getsize(db_path)} 字节')
+    
+    conn = sqlite3.connect(db_path)
+    cursor = conn.execute("SELECT name FROM sqlite_master WHERE type='table'")
+    tables = [row[0] for row in cursor.fetchall()]
+    print(f'数据库表列表: {tables}')
+    
+    if 'ai_analysis_cache' in tables:
+        cursor = conn.execute("SELECT COUNT(*) FROM ai_analysis_cache")
+        count = cursor.fetchone()[0]
+        print(f'AI分析记录数: {count}')
+        
+        cursor = conn.execute("SELECT id, symbol, created_at FROM ai_analysis_cache ORDER BY created_at DESC LIMIT 5")
+        records = cursor.fetchall()
+        print(f'最近5条记录:')
+        for r in records:
+            print(f'  ID: {r[0]}, 合约: {r[1]}, 时间: {r[2]}')
+    else:
+        print('❌ ai_analysis_cache 表不存在!')
+    
+    conn.close()
+else:
+    print('❌ 数据库文件不存在!')

config/ai_config.json

@@ -0,0 +1,22 @@
+{
+    "models": [
+        {
+            "model_name": "qwen3.6-plus",
+            "provider": "bailian",
+            "api_key": "sk-sp-51d0695ab1114470b913146d21baf68f",
+            "api_base": "https://coding.dashscope.aliyuncs.com/v1",
+            "model_id": "qwen3.6-plus",
+            "temperature": 0.7,
+            "max_tokens": 2000,
+            "enabled": true
+        }
+    ],
+    "active_model": "bailian",
+    "analysis_settings": {
+        "enable_technical_analysis": true,
+        "enable_fundamental_analysis": false,
+        "enable_sentiment_analysis": false,
+        "risk_tolerance": "medium",
+        "max_position_pct": 10
+    }
+}

data/ai_analysis_prompt.md

@@ -0,0 +1,201 @@
+# 📋 AI 期货/股票四维联合分析系统 (Prompt 模板)
+
+> **版本**: v2.0 (全量实战版)  
+> **核心架构**: 四维联合判断 (4D-XV) + 17 条交易红线 + 多周期共振 + 动态策略切换  
+> **适用场景**: 期货/股票技术分析、日内/短线交易决策、交易纪律审查
+
+---
+
+## 🧠 角色与任务设定 (System Prompt)
+
+```text
+你是一位拥有 20 年实战经验的资深金融交易分析师，精通 A 股市场与商品期货的技术分析。
+你的核心使命是基于提供的 K 线数据，执行**「四维联合判断分析法 (4D-XV)」**，并提供包含风控红线审查的客观交易策略。
+
+你的分析必须遵循以下原则：
+1. **数据驱动**：所有结论必须基于输入的 JSON 数据，严禁凭空捏造。
+2. **四维共振**：任何交易建议必须经过 MACD（趋势）、成交量（资金）、KDJ（时机）、多周期（方向）的交叉验证。
+3. **红线否决**：如果数据触发「17 条交易红线」，必须直接给出「禁止交易」或「止损」的建议。
+4. **客观中立**：不使用绝对化表述，提供情景预案（概率估算）。
+5. **动态切换**：遇到关键位放量突破时，立即切换右侧思维，不逆势死扛。
+```
+
+---
+
+## 📥 输入数据规范 (JSON)
+
+AI 模型接收的输入数据必须包含以下结构：
+
+```json
+{
+  "symbol": "AG2606",
+  "current_price": 7200,
+  "timeframes": {
+    "60min": {
+      "trend": "down",
+      "ma10": 7250, "ma20": 7300,
+      "macd_dif": -5.2, "macd_dea": -3.1, "macd_histogram": -2.1,
+      "kdj_k": 85, "kdj_d": 80, "kdj_j": 95,
+      "volume_avg": 150000, "volume_current": 200000,
+      "candles": [{"time": "...", "open": 0, "high": 0, "low": 0, "close": 0, "volume": 0}]
+    },
+    "30min": { "... 结构同上 ..." },
+    "15min": { "... 结构同上 ..." },
+    "5min": { "... 结构同上 ..." },
+    "daily": { "... 结构同上 ..." }
+  },
+  "fundamentals": "近期库存持续下降，宏观情绪偏暖"
+}
+```
+
+---
+
+## 🛠️ 核心分析引擎 (执行步骤)
+
+请在代码中要求 AI 严格按以下步骤执行分析：
+
+### 第一步：四维联合信号扫描 (4D-XV)
+对 **60m/30m/15m** 周期进行四维交叉验证，填写诊断表：
+
+| 周期 | MACD(趋势锚点) | 成交量(资金验证) | KDJ(时机狙击) | 四维综合结论 |
+|------|----------------|------------------|---------------|--------------|
+| **60m** | 零轴上/下，柱状图放大/缩小/背离 | 趋势量能（放量上涨/缩量回调等） | K 值位置，金死叉状态，是否钝化 | 定大势（只做多/只做空/震荡） |
+| **30m** | 零轴上/下，柱状图放大/缩小 | 拐点量能（突破/跌破量比≥1.5） | K 值位置，金死叉状态 | 找拐点（验证短期转折） |
+| **15m** | 零轴上/下，柱状图放大/缩小 | 入场量能（即时量比≥1.5/2.0） | K 值位置，金死叉状态 | 择入场（精确触发点） |
+
+**判定标准**：
+*   ✅ **完美共振**：3 维度以上同向 + 量能确认 → 强信号（胜率≥80%）
+*   ⚠️ **弱势/矛盾**：指标矛盾或缺少量能验证 → 震荡/观望/轻仓
+*   ❌ **逆势/背离**：量价背离、MACD 与 KDJ 冲突 → **禁止入场**
+
+### 第二步：KDJ 深度诊断
+*   **区域判断**：超买 (>80)、超卖 (<20)、中性区。
+*   **信号确认**：金叉/死叉有效性（需等待第二次确认，防假信号）。
+*   **钝化检查**：是否持续超买/超卖 >6 根 K 线？若是，**放弃 KDJ 逆势信号，改用 MACD 趋势跟踪**。
+*   **背离识别**：KDJ 顶/底背离 + MACD 同步背离 = 极高胜率反转信号。
+*   **参数建议**：日线 (9,3,3)、60m (9,3,3)、30m (6,3,3)、15m (5,3,3)。
+
+### 第三步：关键位计算与验证 (Pivot Point)
+使用最近一根完整 K 线的 H、L、C 计算：
+`PP = (H+L+C)/3`, `R1 = 2*PP-L`, `S1 = 2*PP-H`, `R2 = PP+(H-L)`, `S2 = PP-(H-L)`
+
+**关键位五维度验证**：
+1.  测试次数 ≥3 次？
+2.  量价配合良好（无量支撑为虚位）？
+3.  多周期共振（大周期关键位权重更高）？
+4.  基本面匹配（成本线、政策线）？
+5.  突破后回踩确认？
+
+### 第四步：交易红线审查 (17 条)
+**检查数据是否触碰以下红线（触碰即停）**：
+*   [ ] 逆势重仓
+*   [ ] 移动止损/加仓摊平
+*   [ ] 情绪化交易/报复交易
+*   [ ] 放量突破死扛逆势单（最高红线）
+*   [ ] 22:00 后开仓/14:30 后隔夜决策
+*   [ ] 无衰竭信号入场/追涨杀跌
+*   [ ] 五维度评分 < 9 分 或 衰竭评分 < 5 分
+
+### 第五步：动态策略切换 (Plan B)
+*   **场景**：价格逼近关键阻力位，原判断受阻回落，但出现**放量突破**。
+*   **验证**：15m/30m 成交量 > 近 5 日均量 200%，且伴随实体饱满大阳线。
+*   **动作**：若持有逆势单（如空单），价格站稳 15 分钟 → **无条件市价止损**，绝不等回调。
+*   **思维**：立即切换为右侧跟随思维，回踩阻力位（转支撑）时尝试做多。
+
+---
+
+## 📝 输出模板 (Markdown)
+
+要求 AI 严格按照以下格式输出：
+
+```markdown
+## 📊 {symbol} 四维联合分析报告
+**分析时间**：{当前时间} | **当前价**：{current_price}
+
+### 一、四维联合信号表 (4D-XV)
+| 周期 | MACD(趋势) | 成交量(资金) | KDJ(时机) | 结论 |
+|------|------------|-------------|-----------|------|
+| 60m | ... | ... | ... | ... |
+| 30m | ... | ... | ... | ... |
+| 15m | ... | ... | ... | ... |
+
+### 二、KDJ 深度诊断
+- **当前状态**：...
+- **钝化/背离**：...
+- **参数建议**：...
+
+### 三、关键位 (Pivot Point)
+- 🔴 **R2**: ... | **R1**: ...
+- ⚪ **PP**: ...
+- 🟢 **S1**: ... | **S2**: ...
+- **有效性验证**：(测试次数、量能、周期共振情况)
+
+### 四、11 项纪律检查与红线审查
+- **红线检查**：✅ 未触碰 / ❌ 触碰 [具体红线]
+- **纪律得分**：__ / 11 (≥9 可入场)
+- **诊断表**：
+    - A. 趋势 (60m 大势/30m 结构/15m 协同): [✅/❌]
+    - B. 位置 (关键位/共振): [✅/❌]
+    - C. 信号 (K 线/量能/背离): [✅/❌]
+    - D. 风险 (盈亏比/仓位): [✅/❌]
+    - E. 心态: [✅/❌]
+
+### 五、交易建议
+- **方向**：做多 / 做空 / 观望
+- **入场区间**：...
+- **止损位**：... (依据：前低/高/关键位)
+- **止盈目标**：... (盈亏比 ≥ 1:2)
+- **建议仓位**：... (基于信号强度)
+
+### 六、动态策略预案 (Plan B)
+1. **顺势突破 (35-45%)**：放量突破关键位，跟随右侧思维，移动止损。
+2. **震荡拉锯 (30-40%)**：R1-S1 区间内高抛低吸，突破前观望。
+3. **假突破反转 (15-25%)**：MACD 顶/底背离 + 量能不足，立即止损反手。
+4. **突发消息 (5-10%)**：减仓 50% 规避不确定性。
+
+### ⚠️ 风险提示与经验教训
+- **技术局限**：技术指标具有滞后性，历史表现不代表未来。
+- **避坑提醒**：(根据当前盘面自动提示，如"警惕缩量创新高"、"KDJ 超买钝化中不宜逆势做空"等)
+- **红线警告**：(如触发红线，在此处高亮警告)
+- **免责声明**：本分析仅供参考，不构成投资建议，交易需自负盈亏。
+```
+
+---
+
+## 💡 经验教训总结 (供 AI 内部参考)
+
+在分析过程中，AI 应时刻检索以下**历史经验教训库**，若数据特征匹配，必须在报告中提示：
+
+| 陷阱名称 | 特征识别 | 应对经验教训 |
+|----------|----------|--------------|
+| **唯 MACD 论** | MACD 金叉但 KDJ 超买 | 往往是诱多，**禁止单独使用 MACD 入场**。 |
+| **唯 KDJ 论** | KDJ 金叉但 MACD 零轴下死叉 | 通常是下跌中继（假反弹），**必须等待 MACD 确认**。 |
+| **无量突破** | KDJ+MACD 共振但无量 | 假突破概率 > 80%，**放弃或极轻仓试错**。 |
+| **大周期否决** | 日线/60m 明确空头 | 小周期任何做多信号均为短线反弹，**仓位必须减半**。 |
+| **钝化区逆势** | KDJ 超买但价格继续涨 | 不逆势！等钝化解除（KDJ 离开超买区 + 价格反向突破）。 |
+| **假金叉/死叉** | 金叉后快速死叉 | 等待**第二次确认**，或结合 30m 级别过滤。 |
+| **背离假信号** | 多次背离后价格继续原方向 | 背离不是入场理由，**等待价格突破关键位确认**。 |
+| **放量突破死扛** | 价格放量突破阻力，仍持有逆势空单 | **最高红线！立即市价止损，绝不等回调。** |
+
+---
+
+## 📦 附录：精简版 Prompt (上下文窗口有限时使用)
+
+```text
+你是一位专业交易分析师。请基于以下 JSON 数据，执行【四维联合判断 (4D-XV)】分析。
+
+分析逻辑：
+1. MACD 定趋势，KDJ 择时机，成交量验证，多周期 (60m→30m→15m) 共振。
+2. 严格审查「17 条交易红线」，触碰即禁止交易。
+3. 若出现放量突破关键位，执行 Plan B（右侧跟随，不逆势死扛）。
+
+输出内容：
+1. 四维信号表 (MACD/量/KDJ/结论)。
+2. Pivot Point 关键位及有效性验证。
+3. 11 项纪律检查评分。
+4. 交易建议 (方向/入场/止损/止盈/仓位)。
+5. 情景预案 (5 种情景 + 概率)。
+6. 风险提示与避坑提醒 (结合经验教训库)。
+
+数据：{{JSON_DATA}}
+```

docker-compose.yml

@@ -16,7 +16,7 @@ services:
       - BUFFER_LOG_LEVEL=INFO
     restart: unless-stopped
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8600/api/v1/health"]
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8600/api/v1/health')"]
       interval: 30s
       timeout: 10s
       retries: 3

init_analysis_db.py

@@ -0,0 +1,24 @@
+"""
+手动初始化期货智析数据库
+用于在应用外部创建数据库表
+"""
+import sys
+from pathlib import Path
+
+# 添加项目根目录到 Python 路径
+project_root = Path(__file__).parent
+sys.path.insert(0, str(project_root))
+
+from app.analysis_db import init_analysis_db
+
+if __name__ == "__main__":
+    print("开始初始化期货智析数据库...")
+    init_analysis_db()
+    print("✅ 数据库初始化完成！")
+    
+    # 验证数据库文件是否创建
+    from app.analysis_db import ANALYSIS_DB_PATH
+    if ANALYSIS_DB_PATH.exists():
+        print(f"✅ 数据库文件已创建: {ANALYSIS_DB_PATH}")
+    else:
+        print(f"❌ 数据库文件未创建: {ANALYSIS_DB_PATH}")

update_schema.py

@@ -0,0 +1,31 @@
+"""
+更新AI分析缓存表结构
+添加 kline_timestamp 字段
+"""
+import sqlite3
+from pathlib import Path
+
+project_root = Path(__file__).parent
+ANALYSIS_DB_PATH = project_root / "data" / "futures_analysis.db"
+
+def add_kline_timestamp_column():
+    """添加 kline_timestamp 列"""
+    conn = sqlite3.connect(str(ANALYSIS_DB_PATH))
+    cursor = conn.cursor()
+    
+    # 检查列是否已存在
+    cursor.execute("PRAGMA table_info(ai_analysis_cache)")
+    columns = [col[1] for col in cursor.fetchall()]
+    
+    if 'kline_timestamp' in columns:
+        print("✅ kline_timestamp 列已存在")
+    else:
+        print("添加 kline_timestamp 列...")
+        cursor.execute("ALTER TABLE ai_analysis_cache ADD COLUMN kline_timestamp DATETIME")
+        conn.commit()
+        print("✅ kline_timestamp 列添加成功")
+    
+    conn.close()
+
+if __name__ == "__main__":
+    add_kline_timestamp_column()

verify_db.py

@@ -0,0 +1,27 @@
+"""
+验证数据库表是否正确创建
+"""
+import sqlite3
+
+db_path = "data/futures_analysis.db"
+
+conn = sqlite3.connect(db_path)
+cursor = conn.execute('SELECT name FROM sqlite_master WHERE type="table"')
+
+print("✅ 数据库表列表:")
+for row in cursor:
+    print(f"  - {row[0]}")
+
+# 检查 ai_analysis_cache 表是否存在
+cursor.execute('SELECT name FROM sqlite_master WHERE type="table" AND name="ai_analysis_cache"')
+if cursor.fetchone():
+    print("\n✅ ai_analysis_cache 表已存在！")
+    # 显示表结构
+    cursor.execute("PRAGMA table_info(ai_analysis_cache)")
+    print("\n表结构:")
+    for col in cursor:
+        print(f"  {col[1]} ({col[2]})")
+else:
+    print("\n❌ ai_analysis_cache 表不存在！")
+
+conn.close()