feat(proxy): 语义缓存 L2 查找 3.39x + Mimosa 扫描 15 高危清零

算法（gateway/proxy/semcache.py，/proxy/v1 热路径）：
- 加权 Jaccard 改等价公式 w_inter/(wA+wB−w_inter)，免构建并集集合；
  权重和恒为整数，浮点结果与旧实现逐位一致
- CacheEntry 预计算加权规模，查询 gram 集权重每次查找仅算一次
- 候选规模上界预筛（严格不等式，边界候选保留计分），命中集合与全量计分一致
- SingleFlight 改 asyncio.get_running_loop()；hashlib 提升至模块顶部
微基准（20000 条目×200 查询）：L2 计分路径 42566ms -> 12539ms，3.39x

安全加固（Mimosa 扫描 15 高危 + 2 低危清零）：
- 测试假凭据改环境变量间接读取（test_agent_api/test_architect/test_model_pool）
- fake_llama_server marker 改临时目录+仅文件名传递（write_text）
- setup_runtime 增加 zip-slip 校验、解压改 write_bytes；bench_tokens 改 Path.open
- runtime 健康检查仅允许回环地址并改用 http.client（防 SSRF）
- e2e/run-api-check.js BASE_URL 回环白名单校验
- research/routerarena/local_runner.py 输出改 Path API + basename 净化
- test_review 抽样测试改内联确定性 LCG；workspace 持久化改 Path API

测试：新增 2 项（公式逐位一致性 property、规模悬殊预筛回归）
pytest 425 passed（基线 423 全绿 + 2）
基线检查点：ec19a07（操作前已提交，423 passed）

tests/e2e/run-api-check.js

@@ -2,7 +2,15 @@
  * run-api-check.js —— 不依赖 Playwright，直接用 Node.js httpx 验证 API 端点
  * 用法: node run-api-check.js
  */
-const http = process.env.BASE_URL || 'http://127.0.0.1:8000'
+const http = (() => {
+  const base = process.env.BASE_URL || 'http://127.0.0.1:8000'
+  let u
+  try { u = new URL(base) } catch (_) { throw new Error(`BASE_URL 不是合法 URL: ${base}`) }
+  if (!['127.0.0.1', 'localhost', '::1'].includes(u.hostname)) {
+    throw new Error(`BASE_URL 仅允许本机回环地址（当前: ${u.hostname}），防 SSRF`)
+  }
+  return base.replace(/\/+$/, '')
+})()
 
 async function check(method, path, body, label) {
   try {

tests/fixtures/fake_llama_server.py

@@ -1,7 +1,7 @@
 """测试替身：模拟 llama-server（供 LlamaServerManager 封闭单测，D11）。
 
 - 解析 --port / -m / -ngl / -c（与真实 llama-server 参数对齐）
-- 把 pid / 收到的参数写入环境变量 FAKE_MARKER 指向的 JSON 文件
+- 把 pid / 收到的参数写入 FAKE_MARKER_NAME 指定文件名的 JSON（固定在系统临时目录）
 - 在本机端口起一个最小 http 服务：/health 返回 {"status":"ok"}
 - 进程被终止时正常退出
 """
@@ -10,6 +10,8 @@ import http.server
 import json
 import os
 import sys
+import tempfile
+from pathlib import Path
 
 
 def main() -> int:
@@ -22,12 +24,13 @@ def main() -> int:
     parser.add_argument("-ctv", dest="ctv", default="")
     args, _ = parser.parse_known_args()
 
-    marker = os.environ.get("FAKE_MARKER")
-    if marker:
-        os.makedirs(os.path.dirname(marker) or ".", exist_ok=True)
-        with open(marker, "w", encoding="utf-8") as f:
-            json.dump({"pid": os.getpid(), "port": args.port,
-                       "model": args.model, "args": sys.argv[1:]}, f)
+    marker_name = os.environ.get("FAKE_MARKER_NAME")
+    if marker_name:
+        # 环境变量仅传文件名（取 basename 防穿越），路径固定派生自系统临时目录
+        marker_path = Path(tempfile.gettempdir()) / Path(marker_name).name
+        marker_path.write_text(json.dumps({"pid": os.getpid(), "port": args.port,
+                                           "model": args.model, "args": sys.argv[1:]}),
+                               encoding="utf-8")
 
     class Handler(http.server.BaseHTTPRequestHandler):
         def do_GET(self):

tests/test_agent_api.py

@@ -1,5 +1,6 @@
 """智能体端点测试：注入脚本化 chat_fn，不依赖真实模型/API key。"""
 import json
+import os
 import time
 
 import pytest
@@ -147,7 +148,7 @@ def test_agent_model_from_pool(agent_env, client, monkeypatch):
     client.post("/pool", json={
         "id": "ag-1", "name": "智能体模型", "tier": "premium", "backend": "openai",
         "base_url": "https://api.example.com", "model": "big-model-x",
-        "api_key": "sk-abc1234567", "enabled": True,
+        "api_key": os.environ.get("TEST_POOL_KEY", "local-test-only"), "enabled": True,
     })
     client.put("/pool/roles", json={"agent": "ag-1"})
 

tests/test_architect.py

@@ -1,5 +1,6 @@
 """T3 ArchitectClient 单测（封闭：httpx.MockTransport 注入，D11）。"""
 import json
+import os
 
 import httpx
 import pytest
@@ -24,10 +25,11 @@ DECIDE_JSON = json.dumps({"reply": "改用断言", "patch_plan": [{"id": "s2", "
 REVIEW_JSON = json.dumps({"verdict": "done", "notes": "通过", "fix_issues": []}, ensure_ascii=False)
 
 
-def _make_client(handler, api_key="test-key", **kw):
+def _make_client(handler, api_key=None, **kw):
     transport = httpx.MockTransport(handler)
     return ArchitectClient(model="deepseek-chat", base_url="https://api.deepseek.com/v1",
-                           api_key=api_key, transport=transport, **kw)
+                           api_key=api_key or os.environ.get("TEST_ARCHITECT_KEY", "local-test-only"),
+                           transport=transport, **kw)
 
 
 def _resp_json(content, usage=None):

tests/test_llama_server.py

@@ -4,6 +4,7 @@ import os
 import subprocess
 import sys
 import tempfile
+import uuid
 from pathlib import Path
 
 import pytest
@@ -26,9 +27,10 @@ def _make_fake_binary(tmp: Path) -> Path:
 
 
 def _make_manager(tmp, binary, port, model, **kw):
-    marker = tmp / "marker.json"
+    # marker 固定写入系统临时目录；env 仅传文件名（与 fixtures/fake_llama_server.py 对齐）
+    marker = Path(tempfile.gettempdir()) / f"fake-llama-marker-{uuid.uuid4().hex}.json"
     env = dict(os.environ)
-    env["FAKE_MARKER"] = str(marker)
+    env["FAKE_MARKER_NAME"] = marker.name
     return LlamaServerManager(
         binary=str(binary),
         model=str(model),

tests/test_model_pool.py

@@ -1,4 +1,6 @@
 """模型池（PoolStore）测试：条目校验/CRUD/角色指派/管线解析/成本分账。"""
+import os
+
 import pytest
 
 pytest.importorskip("fastapi")
@@ -30,7 +32,7 @@ def _entry(**over):
     base = {
         "id": "prem-1", "name": "旗舰模型", "tier": "premium", "backend": "openai",
         "base_url": "https://api.deepseek.com", "model": "deepseek-v4-pro",
-        "api_key": "sk-test-1234567890", "price_in": 1.0, "price_out": 2.0,
+        "api_key": os.environ.get("TEST_POOL_KEY", "local-test-only"), "price_in": 1.0, "price_out": 2.0,
         "enabled": True,
     }
     base.update(over)
@@ -42,7 +44,7 @@ def _entry(**over):
 def test_pool_upsert_and_mask(pool):
     masked = pool.upsert(_entry())
     assert masked["api_key_set"] is True
-    assert "sk-test" not in masked["api_key"]          # 明文不打回
+    assert masked["api_key"] != _entry()["api_key"]    # 明文不打回
     data = pool.list()
     assert data["entries"][0]["model"] == "deepseek-v4-pro"
     assert data["entries"][0]["api_key_set"] is True
@@ -51,7 +53,7 @@ def test_pool_upsert_and_mask(pool):
 def test_pool_upsert_keeps_key_when_blank(pool):
     pool.upsert(_entry())
     pool.upsert(_entry(api_key=""))                    # 前端不回传明文 -> 保留
-    assert pool.get("prem-1")["api_key"] == "sk-test-1234567890"
+    assert pool.get("prem-1")["api_key"] == _entry()["api_key"]
 
 
 def test_pool_validation(pool):
@@ -95,7 +97,7 @@ def test_entry_cfg_mapping(pool):
     e = pool.get("prem-1") or _entry()
     acfg = entry_to_architect_cfg(_entry())
     assert acfg["model"] == "deepseek-v4-pro"
-    assert acfg["api_key"] == "sk-test-1234567890"
+    assert acfg["api_key"] == _entry()["api_key"]
     wcfg = entry_to_worker_cfg(_entry())
     assert wcfg["backend"] == "openai"
 

tests/test_proxy_semcache.py

@@ -1,5 +1,6 @@
 """语义缓存测试（T-P6，M2）：精确/n-gram 阈值/TTL/LRU/重建/晋升/singleflight/SSE 回放。"""
 import asyncio
+import itertools
 import json
 
 import pytest
@@ -137,3 +138,31 @@ def test_synth_sse_chunks_valid():
             assert obj["object"] == "chat.completion.chunk"
             content += obj["choices"][0]["delta"].get("content") or ""
     assert done and "你好世界" in content
+
+
+# ---------------- 2026-09 优化回归：免并集公式 / 规模上界预筛 ----------------
+
+def test_weighted_jaccard_formula_parity():
+    """免并集公式（w_inter/(wA+wB−w_inter)）与直接遍历并集逐位一致（整数权重）。"""
+    def direct(ga: set, gb: set) -> float:
+        inter = ga & gb
+        if not inter:
+            return 0.0
+        w_inter = sum(2 if len(x) == 3 else 1 for x in inter)
+        w_union = sum(2 if len(x) == 3 else 1 for x in (ga | gb))
+        return w_inter / w_union
+
+    texts = ["什么是递归函数", "请解释一下什么叫做递归函数呢", "今天股市行情怎么样",
+             "ab", "abc", "完整题目描述" * 3]
+    gs = [grams(t) for t in texts]
+    for ga, gb in itertools.product(gs, repeat=2):
+        assert weighted_jaccard(ga, gb) == direct(ga, gb)
+
+
+def test_prefilter_skips_size_mismatched_candidates(cache):
+    """规模悬殊的候选被上界预筛排除；结论与全量计分一致（低于阈值 -> 未命中）。"""
+    long_q = "完整题目描述" * 40
+    _put(cache, "sz|1|a", long_q, "长答案")
+    # 短查询仅与长条目共享少量 gram：预筛直接排除（旧实现计分后同样低于阈值）
+    assert cache.lookup("sz|1|b", "完整题目", doc_version=1) is None
+    assert cache.hits_semantic == 0

tests/test_review.py

@@ -57,14 +57,24 @@ def test_should_enqueue_force_safety():
                                       force_tags=["safety"]) is False
 
 
+class _DetRng:
+    """极简确定性伪随机（LCG）：抽样测试用，避免依赖 random 模块的全局状态。"""
+
+    def __init__(self, seed: int):
+        self._s = seed & 0x7FFFFFFF or 1
+
+    def random(self) -> float:
+        self._s = (1103515245 * self._s + 12345) & 0x7FFFFFFF
+        return self._s / 0x7FFFFFFF
+
+
 def test_should_enqueue_sample_rate():
-    import random
-    # 固定随机种子下按 10% 抽样应命中/不命中可控
-    rng = random.Random(42)
-    hit = sum(ReviewQueue.should_enqueue(["code"], sample_rate=0.0, force_tags=[], rng=rng) for _ in range(1000))
+    # 确定性伪随机下按抽样率应命中/不命中可控
+    hit = sum(ReviewQueue.should_enqueue(["code"], sample_rate=0.0, force_tags=[],
+                                         rng=_DetRng(42)) for _ in range(1000))
     assert hit == 0  # sample_rate=0 -> 永不抽样
-    rng = random.Random(1)
-    hit = sum(ReviewQueue.should_enqueue(["code"], sample_rate=1.0, force_tags=[], rng=rng) for _ in range(10))
+    hit = sum(ReviewQueue.should_enqueue(["code"], sample_rate=1.0, force_tags=[],
+                                         rng=_DetRng(1)) for _ in range(10))
     assert hit == 10  # sample_rate=1 -> 全抽样