LLM-10: Implement LLM prompt/evaluation fixture harness #22

Open
opened 2026-05-06 21:14:42 -07:00 by jwilger · 0 comments
Owner

Roadmap key: LLM-10

Depends on: LLM-4, LLM-5

Acceptance criteria

  • Checked-in non-secret fixtures exercise model patch, repair, code generation, component selection, and learning extraction prompts against the fake provider and validate structured outputs deterministically.

Source

Created from .kilo/plans/1778116681638-nimble-star.md.

Roadmap key: `LLM-10` Depends on: [LLM-4](https://git.johnwilger.com/jwilger/anything_app/issues/16), [LLM-5](https://git.johnwilger.com/jwilger/anything_app/issues/17) ## Acceptance criteria - Checked-in non-secret fixtures exercise model patch, repair, code generation, component selection, and learning extraction prompts against the fake provider and validate structured outputs deterministically. ## Source Created from `.kilo/plans/1778116681638-nimble-star.md`.
Sign in to join this conversation.
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Reference
Slipstream/anything_app#22
No description provided.