5 Commits

Author	SHA1	Message	Date
DrSmoothl	2a33fd1121	refactor(llm): enable hot-reload for model config and client runtime ... make LLM task config resolution dynamic in LLMRequest load model clients on demand from latest config clear client instance cache on config reload remove stale module-level model_config usage in llm_api add hot-reload tests for LLM/config watcher flow	2026-03-04 21:56:50 +08:00
UnCLAS-Prommer	82b5230df1	解决openai_client的lint问题	2025-07-31 00:49:59 +08:00
UnCLAS-Prommer	3c40ceda4c	大修LLMReq	2025-07-30 09:45:13 +08:00
墨梓柒	16931ef7b4	feat: 支持多个API Key，增强错误处理和负载均衡机制	2025-07-27 13:55:18 +08:00
墨梓柒	909e47bcee	初步重构llmrequest	2025-07-25 13:21:48 +08:00