feat(v3): Web 应用化基线（异步任务/SSE/llama-server 管理/Vue SPA 四页 + 设置页整页滚动修复）

2026-09-01 08:31:47 +08:00
parent 8d36eeec59
commit 3bbdcb7cc7
60 changed files with 7236 additions and 1160 deletions
@@ -1,68 +1,76 @@
-"""核心数据模型（纯标准库，无外部依赖）"""
-from __future__ import annotations
-
-import time
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class Classification:
-    """分类器输出：领域 + 置信度 + 难度"""
-    domain: str
-    confidence: float
-    difficulty: str                      # easy | medium | hard
-    difficulty_score: float = 0.5
-    raw_scores: Dict[str, float] = field(default_factory=dict)
-    matched_rules: List[str] = field(default_factory=list)
-
-
-@dataclass
-class ExpertResponse:
-    """专家模型输出"""
-    text: str
-    model_used: str
-    latency_ms: float = 0.0
-    tokens: int = 0
-    cost_est: float = 0.0                # 相对成本估计（美元，近似）
-
-
-@dataclass
-class RouterResult:
-    """一次路由的完整结果"""
-    query: str
-    response: str
-    domain: str
-    difficulty: str
-    confidence: float
-    upgraded: bool                       # 是否升级到大模型
-    quality_score: float
-    model_used: str
-    route: List[str] = field(default_factory=list)   # 路由决策轨迹
-    latency_ms: float = 0.0
-    cache_hit: bool = False
-    cache_level: Optional[str] = None    # exact | semantic
-    cost_est: float = 0.0
-    error: Optional[str] = None
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "query": self.query,
-            "response": self.response,
-            "domain": self.domain,
-            "difficulty": self.difficulty,
-            "confidence": round(self.confidence, 4),
-            "upgraded": self.upgraded,
-            "quality_score": round(self.quality_score, 4),
-            "model_used": self.model_used,
-            "route": self.route,
-            "latency_ms": round(self.latency_ms, 2),
-            "cache_hit": self.cache_hit,
-            "cache_level": self.cache_level,
-            "cost_est": round(self.cost_est, 6),
-            "error": self.error,
-        }
-
-
-def now_ms() -> float:
-    return time.perf_counter() * 1000.0␍
+"""核心数据模型（纯标准库，无外部依赖）"""
+from __future__ import annotations
+
+import time
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+
+
+@dataclass
+class Classification:
+    """分类器输出：领域 + 置信度 + 难度"""
+    domain: str
+    confidence: float
+    difficulty: str                      # easy | medium | hard
+    difficulty_score: float = 0.5
+    raw_scores: Dict[str, float] = field(default_factory=dict)
+    matched_rules: List[str] = field(default_factory=list)
+
+
+@dataclass
+class ExpertResponse:
+    """专家模型输出"""
+    text: str
+    model_used: str
+    latency_ms: float = 0.0
+    tokens: int = 0
+    cost_est: float = 0.0                # 相对成本估计（美元，近似）
+
+
+@dataclass
+class RouterResult:
+    """一次路由的完整结果"""
+    query: str
+    response: str
+    domain: str
+    difficulty: str
+    confidence: float
+    upgraded: bool                       # 是否升级到大模型
+    quality_score: float
+    model_used: str
+    route: List[str] = field(default_factory=list)   # 路由决策轨迹
+    latency_ms: float = 0.0
+    cache_hit: bool = False
+    cache_level: Optional[str] = None    # exact | semantic
+    cost_est: float = 0.0
+    error: Optional[str] = None
+    subdomain: Optional[str] = None      # 二级子领域（如 investing/labor）
+    subdomain2: Optional[str] = None     # 三级子领域（如 fund/overtime）
+    domain_group: Optional[str] = None   # 大领域组（两级路由第一级：tech/professional/...）
+    request_id: Optional[str] = None     # 请求 ID（配合 /traces/{id} 查询完整推理链）
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "query": self.query,
+            "response": self.response,
+            "domain": self.domain,
+            "difficulty": self.difficulty,
+            "confidence": round(self.confidence, 4),
+            "upgraded": self.upgraded,
+            "quality_score": round(self.quality_score, 4),
+            "model_used": self.model_used,
+            "route": self.route,
+            "latency_ms": round(self.latency_ms, 2),
+            "cache_hit": self.cache_hit,
+            "cache_level": self.cache_level,
+            "cost_est": round(self.cost_est, 6),
+            "error": self.error,
+            "subdomain": self.subdomain,
+            "subdomain2": self.subdomain2,
+            "domain_group": self.domain_group,
+            "request_id": self.request_id,
+        }
+
+
+def now_ms() -> float:
+    return time.perf_counter() * 1000.0