feat(api): DeepSeek V4 Flash 默认、HTTP 错讯与多供应商分层

- 主链路默认 deepseek-v4-flash，DEEPSEEK_THINKING_ENABLED 对齐旧非思考 chat
- 评测台评审装配迁入 adapters/llm（deepseek_eval_judge、zhipu_eval_judge）与 eval_judge_spec
- 拆分 llm_http_openai_chat_errors 与 llm_errors（DeepSeek/智谱品牌与文档链），llm_call 支持 http_error_vendor
- EvalJudgeService 按 spec.provider 传入 allm_json_call；评测台前端文案改为 V4 Flash
- 更新 .env 示例与 staging/production 的 DEEPSEEK_MODEL；补充 openai/供应商错讯测试

Made-with: Cursor

api/tests/test_eval_judge_llm_spec.py

@@ -51,7 +51,8 @@ def test_build_eval_judge_deepseek_context_budget(
     spec = build_eval_judge_llm_spec("deepseek", None)
     assert spec is not None
     assert spec.provider == "deepseek"
-    assert spec.resolved_model == "deepseek-reasoner"
+    # 旧名 deepseek-reasoner 规范为 v4-flash 思考模式
+    assert spec.resolved_model == "deepseek-v4-flash"
     assert spec.context_window_tokens == 64_000
     n = eval_judge_conversation_transcript_max_chars_for_context(64_000)
     glm_n = eval_judge_conversation_transcript_max_chars_for_context(200_000)