Skip to content

[Agentic] Log model thinking #232

@stefanofornari

Description

@stefanofornari

AS A user
I WANT to see how the model reasoned to provide the answer
SO THAT I have some insights on how it built it, if it made any assumptions, etc.

{ "aiMessage": { "text": "The pom.xml file lists one developer:\n- Stefano Fornari", "thinking": "I have read the pom.xml file and found the developers section, extracting the names listed there.", "toolExecutionRequests": [], "attributes": {} }, "metadata": { "id": "1", "modelName": "gpt-4", "tokenUsage": { "inputTokenCount": 328, "outputTokenCount": 38, "totalTokenCount": 366 }, "finishReason": "STOP" } }

Metadata

Metadata

Assignees

No one assigned
    No fields configured for Feature.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions