feat(proxy): T-P6 语义缓存（L1/L2 倒排+singleflight+SSE 回放，M2 核心）

- semcache.py：SemanticCache——L1 精确（LRU max_entries=30万）+ L2 字符 2/3-gram
  倒排索引（启动自 sqlite q_norm 重建）+ 加权 Jaccard（3-gram 权 2）+
  共享 gram>=3 候选门限 + 阈值 0.92 + TTL 滑动过期 + L2 命中 5 次晋升 L1
  （别名键写回表）；SingleFlight（dict[hash->Future] 上限 256/60s 超时降级）；
  synth_sse_chunks 命中回放（分块 delta+finish+[DONE] 合法 SSE）
- ledger：semcache_rows/put_semcache/promote_semcache/purge_expired
- 测试 +10：gram/精确/语义上下阈值/TTL 假时钟/LRU/重建/晋升/singleflight/SSE 合法性，
  全量 422 passed
- 待接线：routes 缓存分支（T-P7 顺带接入，M2 完整闭环在压测前完成）

gateway/proxy/ledger.py

@@ -187,6 +187,51 @@ class Ledger(BillingMixin):
                 (used + 1, today, key_id))
             return True
 
+    # ---------- 语义缓存持久化（T-P6，供 semcache.SemanticCache 调用） ----------
+    def semcache_rows(self, limit: int = 300000) -> List[Dict[str, Any]]:
+        """全量缓存行（启动重建倒排索引）。"""
+        with self._lock, self._connect() as conn:
+            rows = conn.execute(
+                "SELECT cache_key, q_norm, answer, model, created_ts, ttl_ts,"
+                " doc_version, hits FROM semcache LIMIT ?", (limit,)).fetchall()
+        return [dict(r) for r in rows]
+
+    def put_semcache(self, cache_key: str, bucket: str, q_norm: str, answer: str,
+                     model: str, created_ts: int, ttl_ts: int,
+                     doc_version: int = 1) -> None:
+        """写/覆盖一条缓存（幂等）。"""
+        with self._lock, self._connect() as conn:
+            conn.execute(
+                "INSERT OR REPLACE INTO semcache"
+                "(cache_key, bucket, q_norm, answer, model, created_ts, ttl_ts,"
+                " doc_version, hits) VALUES (?,?,?,?,?,?,?,?,0)",
+                (cache_key, bucket, q_norm, answer, model, created_ts, ttl_ts,
+                 doc_version))
+
+    def promote_semcache(self, source_key: str, alias_key: str, hits: int) -> None:
+        """L2 -> L1 晋升：以别名键复制一行（原行保留审计）。"""
+        with self._lock, self._connect() as conn:
+            row = conn.execute(
+                "SELECT * FROM semcache WHERE cache_key = ?", (source_key,)).fetchone()
+            if row is None:
+                return
+            conn.execute(
+                "INSERT OR REPLACE INTO semcache"
+                "(cache_key, bucket, q_norm, answer, model, created_ts, ttl_ts,"
+                " doc_version, hits) VALUES (?,?,?,?,?,?,?,?,?)",
+                (alias_key, row["bucket"], row["q_norm"], row["answer"],
+                 row["model"], row["created_ts"], row["ttl_ts"],
+                 row["doc_version"], hits))
+            conn.execute("UPDATE semcache SET hits = ? WHERE cache_key = ?",
+                         (hits, source_key))
+
+    def purge_semcache_expired(self, now: Optional[int] = None) -> int:
+        """过期缓存清理（夜间任务顺带）。"""
+        now = int(now if now is not None else time.time())
+        with self._lock, self._connect() as conn:
+            cur = conn.execute("DELETE FROM semcache WHERE ttl_ts < ?", (now,))
+            return cur.rowcount
+
     # ---------- 自省（测试/验收用） ----------
     def table_names(self) -> List[str]:
         """列出已建表名（测试验收）。"""