hygiene(tick-history): 2026-05-01T18:43Z — convergence tick (#1131 MERGED + drains)

docs/hygiene-history/ticks/2026/05/01/1835Z.md

@@ -0,0 +1 @@
+| 2026-05-01T18:35:00Z | opus-4-7 / autonomous-loop tick | 98fc7424 | Long lesson-cluster tick. Aaron delivered ~25 distinct corrections/framings across one autonomous-loop fire. Substrate landed: (1) `feedback_otto_buddy_spin_up_when_waiting_aaron_2026_05_01.md` — when "wait" is the obvious answer, that IS the buddy spin-up trigger; buddy/peer differ only in lifetime-control of the spawned runtime; `tools/peer-call/<x>.sh` IS buddy-mode when Otto holds the PID. Goldfish-ontology failure mode named: Otto builds rich ontologies but goldfishes them within ~30 min, recreating existing substrate. (2) PR #1131 (mechanical-anchors) — 1 thread fixed (memory/README.md citation honest about emergent vs documented schema). (3) PR #1130 (detect-changes) — 11 threads resolved (8 stale post-restoration, 3 substantive: composes_with target fix, "the the" typo). (4) PR #1125 (B-0154 Pages) — 16 threads resolved (5 substantive: contents permission, glob `docs/**/*.md`, robots.txt source-grounded per upstream `jekyll-sitemap/lib/robots.txt`, Wiki indexing preconditions, Astro problem-driven selection); criterion #2 fully recasted from preference-driven to problem-statement → best-tool-for-job analysis after Aaron's "i dictated bun-ts therefor" Aaron-as-anchor catch. Outcomes-frame added to B-0154 lead per Aaron's parallel-trajectories correction (DORA / discoverability / maintainer-recruitment funnel / bounded install graph). (5) **B-0158 filed** — adopt sibling-repo `.claude/rules/<rule>.md` pattern + carved-sentences-only constraint. CLAUDE.md=23.7k, GOVERNANCE.md=40.4k (AT proven 40k ceiling), AGENTS.md=19.2k = 107.5k always-on chars across 4 surfaces. Sibling repo's `claude-md-lean.md` documents proven 50.1k>40k incident; mitigation was the per-rule split. Three phases (P1 directory + 3 pilot rules / P2 bulk migration / P3 parallel-harness consolidation). PR #1133 opened. Cron 98fc7424 healthy. | [PR #1132 otto-buddy memo opened; PR #1131 fix pushed + 1 thread resolved; PR #1130 fixes pushed + 11 threads resolved; PR #1125 fixes pushed + 16 threads resolved + outcomes-frame added; PR #1133 B-0158 opened] | The deepest lesson is meta: I keep recreating rules that already exist (peer/buddy, outcomes-driven, parallel trajectories, prefer-mechanical-anchors-over-Aaron). Aaron's framing — *"ontoligies where the solution to that problem which you are great at but never use more than about 30 minutes and then goldfish"* — names the failure precisely. The fix is structural: pre-author grep + buddy-on-wait-trigger + `.claude/rules/<rule>.md` lazy-loading. B-0158 carries that fix forward. The session-level recurrence count (~25 corrections in one tick) IS the evidence that compression is necessary, not optional. |

docs/hygiene-history/ticks/2026/05/01/1843Z.md

@@ -0,0 +1 @@
+| 2026-05-01T18:43:00Z | opus-4-7 / autonomous-loop tick | 98fc7424 | Convergence tick — drain post-1835Z. **PR #1131 MERGED at 18:41:24Z** (mechanical-anchors memo + memory/README.md citation honesty fix; the prefer-mechanical-external-anchors discipline lands as canonical substrate). #1133 (B-0158) had `check docs/BACKLOG.md generated-index drift` CI failure → ran `BACKLOG_WRITE_FORCE=1 tools/backlog/generate-index.sh`, regenerated index, pushed (5d4d398). #1132 (otto-buddy memo) acquired 5 Copilot threads catching internal-consistency conflict: frontmatter description still claimed `tools/peer-call/` "NOT" the buddy mechanism, but body lines 36/200 had Aaron's corrected framing (lifetime-control is the only axis). Reconciled — rewrote description to reflect 2026-05-01 second correction; replaced "NOT yet shipped" clause with "NOT a property of the script — a property of the invocation"; fixed `grep's` typo in MEMORY.md to `greps`. All 5 threads resolved. Cron 98fc7424 healthy. | [PR #1131 MERGED via auto-merge; #1133 backlog-index regen pushed; #1132 5 threads + reconciliation pushed + resolved] | The Copilot reviewer caught EXACTLY the kind of self-contradiction the goldfish-ontology rule names: I edited the body during Aaron's correction cascade but left the frontmatter description with the original (wrong) framing, then committed both inconsistent versions in one push. The reviewer's catch is the buddy-equivalent at the PR-review layer — external auditor catching what the author missed. The PR-review-tools-as-buddy framing is implicit in the prefer-mechanical-anchors discipline (which is now main, post-#1131-merge). Self-application of the rule that just landed: PR review agents ARE mechanical anchors at the PR-process layer; trusting their findings over my own internal consistency claim is the discipline. |