fix:批量修复了一些问题

src/api/schemas.py

@@ -29,6 +29,8 @@ class MatchOut(BaseModel):
     match_stage: str | None
     home_xg: float | None = None
     away_xg: float | None = None
+    # 该场比赛的最近预测摘要(按时间倒序,最多 5 条;无预测为空)
+    recent_predictions: list[PredictionOut] = []
 
 
 class MatchListOut(BaseModel):
@@ -42,7 +44,13 @@ class PredictRequest(BaseModel):
     provider: str | None = None
     model: str | None = None
     prompt_version: str | None = None
-    mode: str = "multi"  # multi(默认, 5专家+终裁) | single(单次调用)
+    mode: str = Field(
+        "multi",
+        description="multi(默认,5专家+终裁) | single(单次) | baseline(极简统计基线,不调用 LLM)",
+    )
+    use_cache: bool = True
+    backtest: bool = False
+    cutoff_at: str | None = Field(None, description="显式截止时间 ISO8601,用于回测防未来信息")
 
 
 class PredictOut(BaseModel):
@@ -58,6 +66,13 @@ class PredictOut(BaseModel):
     pred_1x2: str | None
     subjective_confidence: float | None
     reasoning: str | None
+    status: str = "success"
+    # 成本信息(可选;单次/多专家均有)
+    latency_ms: int | None = None
+    prompt_tokens: int | None = None
+    completion_tokens: int | None = None
+    # 限流提示:当请求被节流时告知用户剩余配额(可选)
+    rate_limit_remaining: int | None = None
     agent_outputs: list[dict] | None = None
     agent_weights: dict | None = None
     context: str
@@ -78,7 +93,9 @@ class PredictionOut(BaseModel):
     pred_1x2: str | None
     subjective_confidence: float | None
     reasoning: str | None
+    status: str = "success"
     agent_outputs: list[dict] | None = None
+    agent_weights: dict | None = None
     created_at: datetime
     actual_home_goals: int | None
     actual_away_goals: int | None