free-memory: decision graph emerges from archaeologies + flywheel (Aaron 2026-05-03 architectural observation)

docs/hygiene-history/ticks/2026/05/03/0149Z.md

@@ -0,0 +1 @@
+| 2026-05-03T01:49:00Z | opus-4-7 / autonomous-loop continuation | a2e2cc3a | **Decision-archaeology worked example #3 (BP-24 attribution + sacred-tier) authored + landed PR #1264; Aaron's "do we end up with a decision graph?" question answered + captured as substrate (PR #1265).** Cycle worked: PR #1260 merged b8b975bc with 0 actionable threads (gate-tool count discrepancy resolved as not-real-issue); pivoted to advance Aarav's BP-14 with worked example #3 (BP-24 deceased-family-emulation consent-gate, attribution-archaeology + sacred-tier substrate handling). All 11 layers walked respectfully — sacred-tier nodes cited by path only, not reproduced. 3/3 worked examples now landed; skill-creator can author SKILL.md with 3 distinct sub-modes empirically grounded. Aaron mid-tick observation: *"do we end up with some decision graph or something because of the archeologies and flywheel?"* — yes; the substrate already encodes a typed-edge provenance graph (DataVault-2.0-shaped, PROV-O analogue): nodes = backlog rows / ADRs / memos / skills / personas / research / tick shards / commits; edges = depends_on / composes_with / supersedes / cites / verifies-against / attributes-to / closes / composes_in_skill_domain_with. The archaeologies + flywheel + disciplines make the implicit graph queryable: decision-archaeology = traversal; substrate-claim-checker = invariant; flywheel = growth; at-creation/at-pickup = edge-fill; hub-satellite = stratification. No separate graph database needed — every edge already encoded somewhere. Cron a2e2cc3a still armed. | #1260 (substrate-claim-checker v0.4.4) merged b8b975bc; #1263 (worked example #2) wait-ci, auto-merge armed; #1264 (worked example #3) opened, auto-merge armed; #1265 (decision-graph emergent memo) opened, auto-merge armed | This tick teaches the operational pattern of recognize-the-emergent-architecture: Aaron's question named a property that was already implicit in the substrate. The 5 architectural disciplines already in flight (archaeologies + flywheel + creation/pickup discipline + hub-satellite + verify-then-claim mechanization) compose into a graph that compounds value with backlog size — each new node + edge costs O(1) at creation; each new query benefits from cumulative graph. Aligns with largest-mechanizable-backlog-wins thesis. The graph's value emerges WITHOUT additional design effort because the disciplines were ALREADY encoding the edges in substrate. Mechanization path (`tools/decision-graph/`) proposed but not yet built; future v1+ work composes with substrate-claim-checker v1+ for graph-invariant checking. |

docs/hygiene-history/ticks/2026/05/03/0157Z.md

@@ -0,0 +1 @@
+| 2026-05-03T01:57:00Z | opus-4-7 / autonomous-loop continuation | a2e2cc3a | **#1265 (decision-graph emergent memo): 4 threads triaged — 3 stale-on-merge (worked example #3 now exists post-#1264-merge); 1 real path-form drift fixed.** Cycle worked: PR #1265's Copilot review fired BEFORE PR #1264 (worked example #3) merged; 3 of 4 findings claimed worked example #3 doesn't exist. Now that #1264 has merged (c1dca320), the artifact `docs/research/2026-05-03-decision-archaeology-worked-example-3-bp-24-attribution-archaeology.md` is on main; those findings are stale. Resolved with cross-reference. The 1 real finding: path-form drift in node-class table — `memory/feedback_*.md / project_*` (second variant missing `memory/` prefix) → fixed to uniform full-path form. Recurring sub-class within path-form-drift: when a single table cell lists multiple path patterns, all variants should use uniform form. Cron a2e2cc3a still armed. | #1265 (decision-graph emergent memo) — 4 threads resolved (3 stale, 1 fixed); auto-merge armed; #1266 (worked example #2 empirical rewrite) wait-ci, auto-merge armed | This tick teaches the operational pattern of review-timing-creates-stale-findings: when PR-A's review fires before PR-B (which provides PR-A's claimed substrate) merges, PR-A's review will surface stale findings about substrate not yet on main. The triage discipline correctly identifies stale-on-merge vs real findings; not every flagged issue needs a fix. The substrate-claim-checker v1+ would need to be PR-graph-aware to avoid this class — checking against the eventual-merged state, not the current main state. |

memory/MEMORY.md

@@ -4,6 +4,7 @@
 <!-- paired-edit log (NOT the single-slot latest-marker — that lives on line 3 above): PR #986 lands carved-sentence fixed-point stability + Zeta soul-file executor architecture (Infer.NET-style Bayesian inference, NOT LLMs) + carved sentences ≈ formal specs provable in DST + Deepseek CSAP review absorption (Aaron 2026-04-30 → 2026-05-01, eight-message chain across two autonomous-loop ticks per the file body's section header). Architectural disclosure: substrate IS the priors; alignment IS substrate. The single-slot latest-marker on line 3 (forever-home Aaron 2026-05-01) takes precedence as the chronologically-latest paired edit; this PR's work is earlier. -->
 **📌 Fast path: read `CURRENT-aaron.md` and `CURRENT-amara.md` first.** <!-- paired-edit: PR #690 scheduled-workflow-null-result-hygiene-scan tier-1 promotion 2026-04-28 --> These per-maintainer distillations show what's currently in force. Raw memories below are the history; CURRENT files are the projection. (`CURRENT-aaron.md` refreshed 2026-04-28 with sections 26-30 — speculation rule + EVIDENCE-BASED labeling + JVM preference + dependency honesty + threading lineage Albahari/Toub/Fowler + TypeScript/Bun-default discipline.)
 
+- [**Decision graph emerges from archaeologies + flywheel + at-creation/at-pickup discipline + hub-satellite separation (Aaron 2026-05-03 architectural observation)**](feedback_decision_graph_emergent_from_archaeologies_and_flywheel_aaron_2026_05_03.md) — Substrate already encodes a typed-edge provenance graph (DataVault-2.0-shaped, PROV-O analogue): nodes = backlog rows / ADRs / memos / skills / personas / research / tick shards / commits; edges = depends_on / composes_with / supersedes / cites / verifies-against / attributes-to / closes. Archaeologies + flywheel + disciplines make the implicit graph queryable: decision-archaeology = traversal; substrate-claim-checker = invariant; flywheel = growth; at-creation/at-pickup = edge-fill; hub-satellite = stratification. No separate graph database needed — every edge is encoded in frontmatter / markdown links / ADR blockquotes / SUPERSEDE markers. Sacred-tier nodes need walk-discipline (cite paths, don't reproduce). Mechanization: `tools/decision-graph/` TS tool. Graph value compounds with backlog size.
 - [**Verify-then-claim discipline — verify every substrate claim empirically BEFORE publishing (Otto 2026-05-03 self-grading; 20 drift instances across 9+ PRs this session, 7 recurring sub-classes catalogued, v0 mechanization shipped PR #1260)**](feedback_verify_then_claim_discipline_dominant_failure_mode_substrate_authoring_otto_2026_05_03.md) — The dominant failure mode for substrate authoring this session: Otto wrote "X exists" / "command returns Y" / "table has N rows" without verifying. Carved rule: before stating ANY fact in substrate (file exists, command returns X, row count is N, tool shipped, ADR matches, persona dir present), run the actual command first. 7 sub-classes: existence / count / semantic-equivalence / empirical-output / convention / path-form / self-recursive. Generalizes Otto-247 + Otto-364 + verify-before-deferring at the broader any-substrate-claim layer. **Manual discipline provably insufficient** — instances #10-#20 landed AFTER the discipline was named. `tools/substrate-claim-checker/check-counts.ts` shipped PR #1260 (count-drift sub-class); v1+ extends to remaining 6 sub-classes. Composes with bugs-per-PR-as-immune-system-health metric.
 - [**Skill design — hub-satellite separation + no dynamic commands + plugin/hook packaging + OpenSpec catch-up (Aaron 2026-05-03, three same-tick rules + architectural-debt naming)**](feedback_skills_as_carved_sentences_knowledge_in_docs_datavault_2_0_pattern_aaron_2026_05_03.md) — Three cross-cutting skill-design rules: (1) skills = carved-sentence hubs, knowledge = doc satellites, DataVault 2.0 pattern; (2) no dynamic commands in skills, use TS files under tools/ and reference by path; (3) package skill domains as plugins, use harness hooks for pre/post-condition enforcement (contract-based development). PLUS OpenSpec catch-up named as load-bearing prerequisite — *"if we deleted everything other than it"* — currently sparse; catch-up is its own substantial backlog item. Recursive composition across layers (skill body / command / skill domain / cross-skill contracts / spec).
 - [**Git-native backlog management + long-arc thesis as future skill DOMAIN (Aaron 2026-05-02 forward-looking architectural observation)**](feedback_git_native_backlog_management_long_arc_future_skill_domain_aaron_2026_05_02.md) — Domain emerges (6 procedure skills + 4 named-persona experts + 5 tools) once "down pat"; promotion trigger = 3+ worked examples per skill / 1+ judgment-disagreement per expert. Memo body has Aaron's verbatim quote, Aarav BP-20 composition, canonical starting set.