-
Notifications
You must be signed in to change notification settings - Fork 2.5k
使用subagent读取图片文件,模型返回非预期内容 #4876
Copy link
Copy link
Closed
Labels
category/coreCore engine and logicCore engine and logiccategory/toolsTool integration and executionTool integration and executionpriority/P2Medium - Moderately impactful, noticeable problemMedium - Moderately impactful, noticeable problemroadmap/subagents-toolsRoadmap: Subagents and tool systemRoadmap: Subagents and tool systemstatus/need-informationMore information is needed to resolve this issue.More information is needed to resolve this issue.type/bugSomething isn't working as expectedSomething isn't working as expected
Metadata
Metadata
Assignees
Labels
category/coreCore engine and logicCore engine and logiccategory/toolsTool integration and executionTool integration and executionpriority/P2Medium - Moderately impactful, noticeable problemMedium - Moderately impactful, noticeable problemroadmap/subagents-toolsRoadmap: Subagents and tool systemRoadmap: Subagents and tool systemstatus/need-informationMore information is needed to resolve this issue.More information is needed to resolve this issue.type/bugSomething isn't working as expectedSomething isn't working as expected
Type
Fields
Give feedbackNo fields configured for issues without a type.
What happened?
创建一个subagent(比如图片分析专家),要求识别图片并描述图片内容;
主agent提交图片分析任务,调用图片分析subagent读取图片,subagent返回了和图片完全无关的内容;
已确认主agent使用相同模型读取图片,可以返回正确的图片描述;
What did you expect to happen?
希望subagent使用read_file读取图片,模型能够正确识别;
Client information
Client Information
Run
qwento enter the interactive CLI, then run the/aboutcommand.Login information
模型:doubao-seed-2.0-pro
Anything else we need to know?
openai要求图片内容必须在user context,subagent图片数据放在tool result,是否是这一点导致的的?