feat(0.41.0): GenerationRecord per-candidate dimensional + per-scenario scores#102
Merged
Merged
Conversation
…r-scenario scores
A reflective ImprovementDriver (e.g. an LLM that proposes improved prompts
conditioned on the parent's weakest dimensions + best/worst scenarios) needs
more than one composite per candidate. Extend GenerationRecord.candidates
with:
- dimensions: Record<string, number> (mean per judge dimension)
- scenarios: Array<{scenarioId, composite}> (per-scenario composite)
Populated in run-optimization from each candidate's campaign cells; exported
as GenerationCandidate. Unblocks faithful reflection-mutator ports onto the
substrate (creative-agent system-prompt-head surface) without per-consumer
side channels.
Version-lock bump: npm + pyproject + python client __version__.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Why
Unblocks the faithful reflection-mutator port onto the substrate (creative-agent `system-prompt-head` surface) — replacing run-prompt-evolution's bespoke GA — without a per-consumer side channel.
Test plan
Version-lock bump 0.40.5 → 0.41.0 (npm + pyproject + python client).