From a9d107929433ec53672ac3fcda1b065e43ff4fbe Mon Sep 17 00:00:00 2001 From: MerCry Date: Thu, 26 Feb 2026 19:58:55 +0800 Subject: [PATCH] =?UTF-8?q?fix:=20=E4=BF=AE=E5=A4=8D=E7=BC=96=E6=8E=92?= =?UTF-8?q?=E5=99=A8=E4=BD=BF=E7=94=A8=E9=94=99=E8=AF=AF=E7=9A=84LLM?= =?UTF-8?q?=E9=85=8D=E7=BD=AE=E9=97=AE=E9=A2=98=20[AC-AISVC-50]?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - 移除编排器中硬编码的LLMConfig创建 - 让LLM客户端使用自己的默认配置（从LLMConfigManager获取） - 修复流式生成方法同样的问题 --- ai-service/app/services/orchestrator.py | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/ai-service/app/services/orchestrator.py b/ai-service/app/services/orchestrator.py index 42d16dc..9b3d418 100644 --- a/ai-service/app/services/orchestrator.py +++ b/ai-service/app/services/orchestrator.py @@ -119,13 +119,7 @@ class OrchestratorService: max_evidence_tokens=getattr(settings, "rag_max_evidence_tokens", 2000), enable_rag=True, ) - self._llm_config = LLMConfig( - model=getattr(settings, "llm_model", "gpt-4o-mini"), - max_tokens=getattr(settings, "llm_max_tokens", 2048), - temperature=getattr(settings, "llm_temperature", 0.7), - timeout_seconds=getattr(settings, "llm_timeout_seconds", 30), - max_retries=getattr(settings, "llm_max_retries", 3), - ) + self._llm_config: LLMConfig | None = None async def generate( self, @@ -345,7 +339,6 @@ class OrchestratorService: try: ctx.llm_response = await self._llm_client.generate( messages=messages, - config=self._llm_config, ) ctx.diagnostics["llm_mode"] = "live" ctx.diagnostics["llm_model"] = ctx.llm_response.model @@ -627,7 +620,7 @@ class OrchestratorService: """ messages = self._build_llm_messages(ctx) - async for chunk in self._llm_client.stream_generate(messages, self._llm_config): + async for chunk in self._llm_client.stream_generate(messages): if not state_machine.can_send_message(): break