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/features/evaluation/eval_trace_format.py

@@ -2,14 +2,15 @@
 
 from __future__ import annotations
 
-from app.core.config import settings
 from app.features.conversation.models import Segment
+from app.features.evaluation.constants import eval_cfg
 from app.features.evaluation.eval_trace_schemas import (
     ChapterEvidenceBundle,
     EvidenceFormatMeta,
     FormattedMemoirEvidence,
     StoryEvidenceBundle,
 )
+from app.features.memoir.constants import memoir
 from app.features.memory.models import (
     MemoryChunk,
     MemoryFact,
@@ -20,7 +21,7 @@ from app.features.memory.models import (
 
 def _memoir_evidence_char_cap() -> int:
     """与 ``Settings.eval_judge_memoir_evidence_max_chars`` 对齐。"""
-    return max(1000, int(settings.eval_judge_memoir_evidence_max_chars))
+    return max(1000, int(eval_cfg.judge_memoir_evidence_max_chars))
 
 
 def _approx_tokens(chars: int) -> int: