Skip to content

Optional deterministic CI regression check for tool-using agents? #4174

@ZackMitchell910

Description

@ZackMitchell910

Hi! I’m working on RunLedger, a small deterministic CI check for agent/tool calls. You record tool outputs once locally, then CI reuses them (no network, no secrets). It adds a tiny eval suite + workflow and is optional/removable.

If you’re open to it, what’s the best existing agent/example entrypoint to wire to for a minimal demo?

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions