Skip to content

XY-953 Add proactive brief benchmark scoring#201

Merged
yvette-carlisle merged 1 commit into
mainfrom
y/elf-xy-953
Jun 16, 2026
Merged

XY-953 Add proactive brief benchmark scoring#201
yvette-carlisle merged 1 commit into
mainfrom
y/elf-xy-953

Conversation

@yvette-carlisle

Copy link
Copy Markdown
Member

Summary

  • Add proactive brief benchmark fixtures and scoring for daily project brief, resume-work brief, stale decision audit, stale plan/preference warning, and private-corpus refresh blocker.
  • Extend the real-world job benchmark with evidence refs, freshness/currentness markers, action rationale, reject/defer reasons, and unsupported/tombstone violation guards.
  • Update the XY-951 stage ledger and benchmarking docs with the proactive brief stage result: improved, 4 pass / 1 blocked, 0 wrong-result/unsupported/tombstone violations.

Validation

  • cargo make real-world-memory-proactive-brief
  • cargo test -p elf-eval --test real_world_job_benchmark proactive_brief -- --test-threads=1
  • cargo test -p elf-eval --test real_world_job_benchmark -- --test-threads=1
  • cargo make real-world-memory
  • cargo make fmt
  • cargo make lint-fix
  • cargo make checks

Notes

  • The private-corpus refresh case remains a typed blocker pending live private-corpus inputs (tracked separately by XY-930).

@yvette-carlisle yvette-carlisle merged commit 7f08eb5 into main Jun 16, 2026
13 checks passed
@yvette-carlisle yvette-carlisle deleted the y/elf-xy-953 branch June 16, 2026 15:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant