Optional deterministic CI regression check for tool-using agents? #1109

Closed
opened 2026-02-20 17:43:06 -05:00 by yindo · 1 comment
Owner

Originally created by @ZackMitchell910 on GitHub (Jan 5, 2026).

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?

Originally created by @ZackMitchell910 on GitHub (Jan 5, 2026). 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?
yindo closed this issue 2026-02-20 17:43:06 -05:00
Author
Owner

@eyurtsev commented on GitHub (Jan 6, 2026):

Hi @ZackMitchell910, thanks for asking, we don't want to add this to our CI

@eyurtsev commented on GitHub (Jan 6, 2026): Hi @ZackMitchell910, thanks for asking, we don't want to add this to our CI
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#1109