feat(health): /health 深检——磁盘水位 + 下游依赖 TCP 探测，异常返回 503 degraded

背景: 9·19 磁盘满事故中业务已瘫但 /health 仍 200（只看模型就绪标志），
网关持续把流量打到本机。深检让 worker 在磁盘不足(min_free_gb, 默认5G)或
ComfyUI/change_hair TCP 不通时主动报 503，网关探测两次失败即摘除。

- 配置: worker_config.json "health" 段，env HEALTH_MIN_FREE_GB/
  HEALTH_CHECK_DEPS/HEALTH_DEP_COMFYUI/HEALTH_DEPS_CACHE_SECONDS 可覆盖
- 依赖探测 0.8s 超时并发执行，结果缓存 5s；深检自身异常按就绪返回
- 测试: 深检各分支用例 + 旧用例改为 mock 深检（不依赖本机服务）

tests/test_api.py

@@ -36,12 +36,76 @@ def test_auth_missing_token_401(client):
     assert r.status_code == 401
 
 
-def test_health_no_token_200(client):
+def _patch_health_ok(monkeypatch):
+    """让 /health 深检确定性通过：不依赖本机磁盘水位与 8188/8801 服务存活。"""
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 0.0, "check_deps": True})
+
+    async def _deps_ok():
+        return True, {"comfyui": True, "change_hair": True}
+    monkeypatch.setattr(app_module, "_check_deps", _deps_ok)
+
+
+def test_health_no_token_200(client, monkeypatch):
+    _patch_health_ok(monkeypatch)
     r = client.get("/health")
     assert r.status_code == 200
     assert r.json()["status"] == "ok"
 
 
+def test_health_disk_low_503(client, monkeypatch):
+    # 阈值调到不可能的 99999G → 必然触发磁盘水位 503
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 99999.0, "check_deps": False})
+    r = client.get("/health")
+    assert r.status_code == 503
+    body = r.json()
+    assert body["status"] == "degraded"
+    assert body["reason"].startswith("disk_free_below")
+
+
+def test_health_dep_down_503(client, monkeypatch):
+    monkeypatch.setattr(app_module, "_HEALTH_CFG", {
+        **app_module._HEALTH_CFG, "min_free_gb": 0.0, "check_deps": True})
+
+    async def _deps_down():
+        return False, {"comfyui": False, "change_hair": True}
+    monkeypatch.setattr(app_module, "_check_deps", _deps_down)
+    r = client.get("/health")
+    assert r.status_code == 503
+    body = r.json()
+    assert body["status"] == "degraded"
+    assert "comfyui" in body["reason"]
+
+
+def test_health_ok_carries_detail(client, monkeypatch):
+    _patch_health_ok(monkeypatch)
+    r = client.get("/health")
+    assert r.status_code == 200
+    body = r.json()
+    assert "disk_free_gb" in body
+    assert body["deps"] == {"comfyui": True, "change_hair": True}
+
+
+def test_tcp_probe_real_socket():
+    # 用进程内真实 socket 验证探测本身（曾因 open_connection 返回元组误判全部不可达）
+    import asyncio
+
+    async def scenario():
+        server = await asyncio.start_server(lambda r, w: None, host="127.0.0.1", port=0)
+        port = server.sockets[0].getsockname()[1]
+        up = await app_module._tcp_probe("127.0.0.1", port)
+        server.close()
+        await server.wait_closed()
+        # 端口 1 无监听，本机 connect 立即被拒
+        down = await app_module._tcp_probe("127.0.0.1", 1)
+        return up, down
+
+    up, down = asyncio.run(scenario())
+    assert up is True
+    assert down is False
+
+
 def test_param_none_provided_1007(client):
     r = client.post(URL, headers=H)
     assert r.json()["code"] == 1007