refactor(api): TOML 配置 SSOT、统一错误契约、Auth/事务加固与可观测性 (#33)

配置 SSOT（TOML + .env）
统一错误契约
Auth 与事务边界
Redis / Celery 可靠性:业务 Redis（DB/0）与 Celery broker/backend（DB/1）显式拆分；连接池、sync client
可观测性（OpenTelemetry + LGTM）

api/app/adapters/llm/zhipu_eval_judge.py

@@ -7,27 +7,28 @@ from langchain_openai import ChatOpenAI
 from app.adapters.llm.openai_base_url import normalize_openai_compatible_base_url
 from app.core.config import settings
 from app.core.eval_judge_spec import EvalJudgeLlmSpec
+from app.features.evaluation.constants import eval_cfg
 
 
 def build_zhipu_eval_judge_spec(
     judge_model: str | None,
 ) -> EvalJudgeLlmSpec | None:
     """密钥缺失时返回 None。"""
-    api_key = (settings.eval_judge_api_key or settings.zhipu_api_key or "").strip()
+    api_key = (settings.zhipu_api_key or "").strip()
     if not api_key:
         return None
     want = (judge_model or "").strip()
     base = normalize_openai_compatible_base_url(
-        settings.eval_judge_base_url,
+        eval_cfg.judge_base_url,
         fallback="https://open.bigmodel.cn/api/paas/v4",
     )
-    model = want or (settings.eval_judge_model or "glm-5")
-    ctx = int(settings.eval_judge_context_window_tokens)
+    model = want or (eval_cfg.judge_model or "glm-5")
+    ctx = int(eval_cfg.judge_context_window_tokens)
     llm_kw: dict = {
         "api_key": api_key,
         "base_url": base,
         "model": model,
-        "temperature": settings.eval_judge_temperature,
+        "temperature": eval_cfg.judge_temperature,
     }
     return EvalJudgeLlmSpec(
         llm=ChatOpenAI(**llm_kw),