feat: Sprint 2 - 概率语义 + 轻量快照 + 数据库约束

P0-05: confidence → subjective_confidence 改名(15 文件)
       LLM 主观置信度与概率分离
P0-02: predictions 增加 cutoff_at + input_hash(轻量快照)
       MatchContext 暴露 match_dt
       单/多 Agent 路径均记录快照元数据
P2-05: 数据库 CHECK 约束
       - pred_home_goals >= 0
       - pred_away_goals >= 0
       - subjective_confidence 0~1
       - pred_1x2 IN (1,X,2)
       - mode IN (single,multi)
P2-06: limit 分页约束(ge=1, le=200)
P2-01: 新增 /health/ready 就绪检查

src/llm/agents/base.py

@@ -48,7 +48,7 @@ class AgentReport:
     data_sufficiency: str = "medium"              # high | medium | low | none
     analysis: str = ""
     home_edge: float | None = None                # -1.0 ~ 1.0, 正=利主队
-    confidence: float | None = None               # 0.0 ~ 1.0
+    subjective_confidence: float | None = None               # 0.0 ~ 1.0
     key_evidence: list[str] = field(default_factory=list)
     # xg agent 专属
     exp_home_goals: float | None = None
@@ -67,7 +67,7 @@ class AgentReport:
             "data_sufficiency": self.data_sufficiency,
             "analysis": self.analysis,
             "home_edge": self.home_edge,
-            "confidence": self.confidence,
+            "subjective_confidence": self.subjective_confidence,
             "key_evidence": self.key_evidence,
             "exp_home_goals": self.exp_home_goals,
             "exp_away_goals": self.exp_away_goals,
@@ -122,7 +122,7 @@ def _parse_report(agent: str, parsed: dict, resp: LLMResponse, model: str) -> Ag
         data_sufficiency=validated.data_sufficiency,
         analysis=validated.analysis,
         home_edge=validated.home_edge,
-        confidence=validated.confidence,
+        subjective_confidence=validated.subjective_confidence,
         key_evidence=validated.key_evidence,
         exp_home_goals=validated.exp_home_goals,
         exp_away_goals=validated.exp_away_goals,

src/llm/agents/orchestrator.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 
 import asyncio
+import hashlib
 import json
 import logging
 import time
@@ -68,7 +69,7 @@ class MultiPredictResult:
     pred_home_goals: float | None
     pred_away_goals: float | None
     pred_1x2: str | None
-    confidence: float | None
+    subjective_confidence: float | None
     reasoning: str | None
     agent_outputs: list[dict]
     agent_weights: dict | None
@@ -164,6 +165,7 @@ async def predict_match_multi(
 
     # 1. 比赛头(各 agent 共享;不存在则 404)
     header = await load_match_header(match_id)
+    cutoff_at = header.match_dt
 
     # 2. 并行专家
     specialist_provider = _get_specialist_provider()
@@ -177,6 +179,11 @@ async def predict_match_multi(
 
     latency_ms = int((time.perf_counter() - start) * 1000)
 
+    # 3.5 计算输入 hash(基于终裁报告)
+    input_hash = hashlib.sha256(
+        _reports_to_json(reports).encode("utf-8")
+    ).hexdigest()
+
     # 4. 存库
     async with AsyncSessionLocal() as db:
         m = await db.get(Match, match_id)
@@ -203,10 +210,12 @@ async def predict_match_multi(
             pred_home_goals=validated.pred_home_goals,
             pred_away_goals=validated.pred_away_goals,
             pred_1x2=validated.pred_1x2,
-            confidence=validated.confidence,
+            subjective_confidence=validated.subjective_confidence,
             reasoning=validated.reasoning,
             raw_response=final,
             agent_outputs=[r.to_dict() for r in reports],
+            cutoff_at=cutoff_at,
+            input_hash=input_hash,
         )
         db.add(pred)
         await db.commit()
@@ -221,7 +230,7 @@ async def predict_match_multi(
             pred_home_goals=pred.pred_home_goals,
             pred_away_goals=pred.pred_away_goals,
             pred_1x2=pred.pred_1x2,
-            confidence=pred.confidence,
+            subjective_confidence=pred.subjective_confidence,
             reasoning=pred.reasoning,
             agent_outputs=pred.agent_outputs,
             agent_weights=agent_weights,