fix(backend): 落实 PR #11 第二轮评审意见

- Benchmark 容量淘汰只删终态 run，满容量且全活动时返回 BENCHMARK_CAPACITY_EXCEEDED
- 创建 run 前校验索引兼容性（BENCHMARK_INDEX_INCOMPATIBLE）
- 取消 run 补发 RunCancelled 终止事件；失败分支脱敏（BENCHMARK_RUN_FAILED）
- 失败样本计入汇总分母，报告输出 total/successful/failed/failure_rate
- load_dataset 按文件名隔离无关损坏文件，顶层非对象拒绝
- FTS score_threshold 先于计数/分页，total 与 items 一致
- Benchmark SSE 支持 Last-Event-ID 游标
- 移除 Agent Benchmark 501 占位接口
- 同步第二阶段接口契约与开发说明文档

Co-Authored-By: Claude Code <noreply@anthropic.com>

backend/app/retrieval/vectorstore.py

@@ -35,6 +35,7 @@ class VectorStore(Protocol):
     async def upsert(self, records: list[VectorRecord]) -> None: ...
     async def delete(self, ids: list[str]) -> None: ...
     async def search(self, vector: list[float], *, top_k: int) -> list[VectorHit]: ...
+    async def count(self) -> int: ...
 
 
 class SqliteVecStore:
@@ -92,3 +93,10 @@ class SqliteVecStore:
                 conn.execute("DELETE FROM vec_blocks")
         finally:
             conn.close()
+
+    async def count(self) -> int:
+        conn = connect()
+        try:
+            return conn.execute("SELECT COUNT(*) FROM vec_blocks").fetchone()[0]
+        finally:
+            conn.close()