backlog(B-0537): memory/MEMORY.md index-entry lengths cleanup + CI gate (P3)#3580
Merged
AceHack merged 2 commits intoMay 15, 2026
Conversation
…te (P3) Substrate-honest residual from this session's audit-first-then-decide discipline. Tick 2031Z audit run surfaced 100 long entries in memory/MEMORY.md (target ≤200 chars per CLAUDE.md convention). Same catch-once-then-lint pattern as B-0535: detection logic exists in audit-memory-index-entry-lengths.ts (detect-only, exits 0); CI wiring is the gap. Two-slice plan: - Slice A: tighten 100 entries to ≤200 chars (per-entry content judgment; ~50 min focused work; can be batched per-section) - Slice B: --enforce-long-entries flag + lint-memory-index-entry-lengths gate.yml job (after baseline = 0) ID allocation: B-0537 verified free (B-0531-B-0536 all taken/in-flight). Composes with: B-0535 (sibling cleanup+gate pattern), B-0536 (sibling substrate-honest residual capture), CLAUDE.md MEMORY.md convention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3 tasks
There was a problem hiding this comment.
Pull request overview
Adds a new P3 backlog row file B-0537 capturing the work to clean up memory/MEMORY.md index entries that exceed the one-line length target and to wire the existing detect-only audit into the CI gate. Follows the catch-once-then-lint pattern established in sibling rows B-0535/B-0536.
Changes:
- New backlog row file under
docs/backlog/P3/with frontmatter (id B-0537, P3, M effort, composes_with B-0535 and B-0536). - Two-slice plan: Slice A tightens ~100 long entries to ≤200 chars; Slice B adds an enforce flag plus a
gate.ymljob. - Scope explicitly excludes user-scope
MEMORY.mdand per-topic-file content quality.
AceHack
added a commit
that referenced
this pull request
May 15, 2026
…p + CI gate (#3581) - PR #3574 + #3579 wait-CI - PR #3580 — B-0537 backlog row filed (P3, 2-slice plan) - Audit-driven session phase compounds: B-0536 + B-0537 = 2 substrate-honest residuals captured - Pattern stable: audit-detect → row-file → cleanup → gate-wire - 22-tick session arc Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Quote was attributed to CLAUDE.md but lives in the auto-memory system prompt; re-attribute accordingly (Copilot thread 1) - Canonical standard is 150 chars (project_memory_format_standard.md), not 200; update Slice A target and Slice B wiring to --max 150 - Slice B plan referenced --enforce-long-entries (doesn't exist); the tool already has --enforce (exits code 2); update plan to match (Copilot thread 2) Co-Authored-By: Claude <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
May 15, 2026
…(PR #3583) (#3584) - PR #3580 (B-0537) + #3582 (2038Z shard) wait-CI - PR #3583 — memory file naming audit-first-then-decide as named discipline - Converts implicit 23-tick pattern → durable substrate per substrate-or-it-didn't-happen - Resolves never-be-idle vs razor-discipline vs Standing-by tensions via audit-output routing - 24-tick session arc Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
AceHack
added a commit
that referenced
this pull request
May 15, 2026
…rns (#3582) * shard(tick): 2038Z — quiet checkpoint #3; row-filing diminishing returns; future-Otto hints recorded - PR #3580 + #3581 wait-CI - Surveyed 3 audits (formal-artifacts, cross-platform-parity, ci-cache-paths) — no single-tick scope - Chose NOT to file 3rd backlog row this phase; razor-discipline + no-op-cadence rule - Future-Otto hints in shard: 7 TLA+ specs, 13 .sh→.ps1 twins, 623 md032 hits, B-0536/B-0537 - 23-tick session arc; cron live Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(shard/2038Z): MD032 blank line, row-count accuracy, fix dead promotion-ledger path - Add blank line before list (MD032/blanks-around-lists fix) - Correct "filed 3 backlog rows" → "filed 2 backlog rows" (only B-0536 + B-0537 filed) - Replace dead docs/research/promotion-ledger xref with actual paths: memory/promotion-ledger.jsonl + tools/hygiene/audit-promotion-ledger.ts - Merge main to pull in B-0537 backlog row (resolves dead link finding) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
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
Files B-0537 — `memory/MEMORY.md` has 100 long entries (>200 chars target per CLAUDE.md convention). Detection exists in `audit-memory-index-entry-lengths.ts` (detect-only); CI gate missing.
Same pattern as B-0535: detect logic in place, wiring is the gap. Two-slice plan: cleanup (100 → 0) + gate.
ID allocation
Test plan
🤖 Generated with Claude Code