80833f7033
- 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
19 lines
526 B
Python
19 lines
526 B
Python
"""评测台评审 LLM 装配契约（与 OpenAI/Chat Completions 兼容的供应商解耦于适配器层）。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any, Literal
|
|
|
|
EvalJudgeProvider = Literal["zhipu", "deepseek"]
|
|
|
|
|
|
@dataclass(slots=True, frozen=True)
|
|
class EvalJudgeLlmSpec:
|
|
"""智谱 / DeepSeek 等：装配结果供 dependencies 与评测服务使用。"""
|
|
|
|
llm: Any | None
|
|
provider: EvalJudgeProvider
|
|
resolved_model: str
|
|
context_window_tokens: int
|