root
d4956c23f0
feat: OpenAI 兼容端点完整实现 + reasoning_content 输出通道
- StageContext 新增 ReasoningContent + TokenUsage 字段
- emitResponse 将 reasoning_content / usage 传入 Payload
- /v1/chat/completions:
- 非流式返回 reasoning_content + token_usage
- 流式 (stream=true) SSE 分块返回 reasoning/content/finish chunk
- token_usage 来自精确 LLM 回报而非估算
2026-07-03 20:49:43 +08:00
..
2026-07-03 20:49:43 +08:00
2026-07-03 20:46:04 +08:00
2026-07-02 12:04:36 +08:00
2026-07-02 12:04:36 +08:00
2026-07-03 20:46:04 +08:00
2026-07-02 15:47:16 +08:00
2026-07-03 20:46:04 +08:00
2026-07-03 20:46:04 +08:00
2026-07-02 12:04:36 +08:00
2026-07-02 15:47:16 +08:00
2026-07-03 16:53:34 +08:00
2026-07-03 20:49:43 +08:00
2026-07-03 20:49:43 +08:00
2026-07-02 12:04:36 +08:00
2026-07-02 12:04:36 +08:00
2026-07-02 15:47:16 +08:00
2026-07-02 12:04:36 +08:00
2026-07-02 15:47:16 +08:00