Skip to content

fix(memory-md): compress 25 entries in 351-400 char tier — B-0006 tier-41#1557

Merged
AceHack merged 1 commit intomainfrom
fix/memory-md-tier-41-aaron-2026-05-04
May 5, 2026
Merged

fix(memory-md): compress 25 entries in 351-400 char tier — B-0006 tier-41#1557
AceHack merged 1 commit intomainfrom
fix/memory-md-tier-41-aaron-2026-05-04

Conversation

@AceHack
Copy link
Copy Markdown
Member

@AceHack AceHack commented May 5, 2026

Summary

  • Tier-41 compression of 25 longest entries in 351-400 char range in memory/MEMORY.md.
  • Each compressed entry preserves retrieval hooks (concept name, mechanism, date, Otto-NN/persona attribution).
  • File size reduced 934 bytes (~0.91 KB).

Counts

  • Before: 124 entries in 351-400 range.
  • After: 102 entries in 351-400 range (some compressions stayed in range due to filename floor; still meaningfully shorter).

Test plan

  • No underlying memory files touched.
  • No ... ellipses introduced in path references.
  • No fabricated citations / dates.
  • All formatting preserved (leading - [, bold, link target, em-dash separator).

🤖 Generated with Claude Code

…r-41

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings May 5, 2026 01:36
@AceHack AceHack enabled auto-merge (squash) May 5, 2026 01:36
@AceHack AceHack merged commit 8b78ed5 into main May 5, 2026
26 checks passed
@AceHack AceHack deleted the fix/memory-md-tier-41-aaron-2026-05-04 branch May 5, 2026 01:37
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR performs Tier-41 “compression” edits on memory/MEMORY.md, shortening a set of the longest index entries while keeping link targets intact. This helps keep the memory index more scannable/searchable without touching the underlying memo files.

Changes:

  • Shortened the prose portions of 25 memory/MEMORY.md entries (mostly “— …” suffixes).
  • Normalized formatting for a handful of entries so they remain top-level list items (consistent with the rest of the file).

AceHack added a commit that referenced this pull request May 5, 2026
…r-42 (#1558)

Tier-42 of B-0006 MEMORY.md compression. After tier-41 (PR #1557),
102 entries remained in 351-400 char range. Compressed top 25
longest entries while preserving retrieval hooks (concept names,
trigger/mechanism, dates, Otto-NN attribution).

Final 351-400 count: 77 (102 - 25).
File size: 146271 → 144999 bytes (~1.24 KB saved).

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
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.

2 participants