Post-#674 doc arc: E-NOBODY-WAITS-1 ruling, VISION.md (graded AGI canon), ancestry census, D-MTS-1 design inputs

.claude/board/AGENT_LOG.md

@@ -1,3 +1,23 @@
+## 2026-07-10 — fable-vision-keeper — VISION.md synthesized, filigree-reviewed, ratified (operator: "pull back in anything from the AGI aspiring... you keep the vision alive")
+
+- **The artifact:** `.claude/v3/VISION.md` — the AGI-aspiring canon re-grounded through the 2026-07-10 substrate: the Click's three carrier moves and the loop-invariant lesson; thinking-is-a-struct → thinking-is-a-ROW (full organ table incl. free_energy/Kausal + global_context); projection as a FIVE-axis fact (bytes/readings/time/scale/bits — the fifth measured on proxies, fence riding the thesis sentence); families→runbooks→templates ladder; the Rubicon heart under E-NOBODY-WAITS-1; the anti-dilution laws; the road in dependency order. Every claim graded [G]/[G-on-proxies]/[RULING]/[ASPIRATION].
+- **Orchestration per operator directive:** 2 Sonnet preflights (ancestry census — see entry below; AGI-passage harvest: 8-source anchored inventory) + 2 Opus filigree reviewers (dilution-collapse-sentinel + overclaim-auditor charters) on the draft; main-thread synthesis + consolidation.
+- **Filigree verdicts, all 9 applied:** dilution side — free_energy+global_context restored to the organ table (P1, self-contradiction caught), "not the algebra" softened to carrier-in-niche, time-axis cite precised to #631's four probes, DeepNSM 680GB→16.5MB restored to the spine, homeostasis-floor+MUL named; overclaim side — the §0 thesis and §3 reconstructibility claims now carry the proxy fence ON the sentence (the exact overclaim D-MTS-6's header warns of, caught before shipping), "FREE"→negligible, "exactly Rubicon-conformant"→by-construction, March benchmark numbers dated.
+- **Also this arc:** plan addendum (third wave, operator): AriGraph context V3-TENANT-SHAPED for streamed Markov context; arm-discovery (Aerial+) + DeepNSM ingest legs; CAM-PQ 48-bit path codes (address side) vs 6×palette256² 12-B tenant (value side) — the D-MTS-1 spec's frozen representational comparison. TECH_DEBT TD-STYLE-TABLE-RESIDUE extended with the census finds. README + FUTURE-DESIGN pointers to VISION.md.
+
+## 2026-07-10 — census-worker-ancestry-pipeline — V3 census extended to thinking-engine / p64-bridge / cognitive-shader-driver (doc-only)
+
+- **Census worker (Sonnet, doc-only, edit-only fleet rule honored):** appended `.claude/v3/MODULE-TABLE.md` ADDENDUM covering 51 thinking-engine files + p64-bridge/lib.rs + 22 cognitive-shader-driver src files (bare `crates/p64` does not exist locally — only `crates/p64-bridge`, and both it and thinking-engine sit under `workspace.exclude`, not `members`). Added a `gem-status` column (WIRED-HOT-PATH / UNWIRED-GEM / CALIBRATION-ONLY / LAB-ONLY / RESIDUE) per FUTURE-DESIGN.md's wiring-queue framing. *[Correction 2026-07-10, PR #676 review: the worker's headline counts were 49/23; recount against the tree = 51/22 (the table rows were right, the headings/summary wrong); workspace-scope phrasing fixed — coderabbit findings, all applied.]*
+- **Notable finds:** style-table proliferation is WORSE than FUTURE-DESIGN/D-TSC-1 tracked — `superposition.rs::ThinkingStyle = DetectedStyle` collides in name (not value) with `cognitive_stack.rs::ThinkingStyle = StyleFamily` in the SAME crate; `auto_style.rs` (bare consts) + `engine_bridge.rs::UNIFIED_STYLES` + p64-bridge's `StyleParams` are 3 MORE independent 12-slot tables beyond what D-TSC-1's fleet-run addressed — worth a follow-up grep to confirm `UNIFIED_STYLES`'s definition site (not just callers) was routed. Also: `GestaltState` independently defined in both `awareness_dto.rs` and `world_model.rs`; 3 near-identical lens modules (jina/bge_m3/reranker_lens); `signed_domino.rs`/`branching.rs` extend the M8 near-duplicate-engine count beyond the 3 FUTURE-DESIGN names. `splat_ops.rs` is RESIDUE (self-declared deprecated, scheduled sprint-15+ removal, do not touch per §1 rule 8).
+- **No code changed.** Deliverable: MODULE-TABLE.md ADDENDUM (2). Commit: `13188ad` (landed with the VISION.md draft, same arc; count corrections in the PR #676 review-fix commit). Tests: n/a (doc-only; validation = per-file `pub`-surface grep + row-vs-tree recount). Outcome: census live, feeds FUTURE-DESIGN wiring queue + TD-STYLE-TABLE-RESIDUE extension.
+
+## 2026-07-10 — fable-674-postmerge — #674 MERGED; E-NOBODY-WAITS-1 banked (doc-only, operator: "leave it as is and just document")
+
+- **#674 merged** (`cd5178e`); branch restarted from main; PR_ARC_INVENTORY #674 entry prepended (the deferred post-merge hygiene, now done).
+- **Operator audit resolved:** "kanban step vs ack pump — duplicate route? Rubicon ignored?" → grounded answer: Rubicon intact and owner-side (KanbanColumn IS the 4-phase model; cast records intent AHEAD of ack — crossing at intent formation); the ack-pump is the canonical MESSAGE-FREE route (`ack_and_propose` proposal → `try_advance_phase(&mut)`; `&mut` is the serialization — codex #578's race and #579's overlay both dissolve); rs-graph-llm has zero ack code (storage-side concern only). The redundancy runs the OTHER way: supervisor `KanbanMsg`/`ractor::call!` drivers are a second, message-based model.
+- **Ruling banked:** E-NOBODY-WAITS-1 (no messages, no actors anywhere; ractor = compile-time ownership guarantee only; **prime invariant: nobody waits for anything or any scheduling**). Disposition per operator: LEAVE AS IS — TD-MESSAGE-RESIDUE documents the residue, no retirement queued; drift signal = NEW code reaching for KanbanMsg/call!.
+- Doc-only commit: EPIPHANIES + TECH_DEBT + PR_ARC + this entry. No code touched.
+
 ## 2026-07-10 — fable-dmts6-probe — D-MTS-6 measured GREEN + PR #674 opened + codex P2 ack-dedup fix
 
 - **PR #674 opened** (operator ask): the full 14-commit branch arc; session subscribed to PR activity; hourly self check-in armed.

.claude/board/EPIPHANIES.md

@@ -3,6 +3,16 @@
 
 **The probe** (zero-dep, D-MTS-5 machinery: seed `0x9E3779B97F4A7C15`, M=4096, COMMA_STRIDE=2395, L=12 levels; baseline = the full CausalEdge64's 8+8-bit truth payload): each level stores only k bits of each truth value with the comma phase acting as **deterministic subtractive dither** (generated from the address, never stored); read-time de-dithers and averages the L witnesses. Three awareness proxies vs the baseline over 8192 NARS revision/deduction pairs + a 64-step revision chain: revision-outcome |ΔE|, MetaWord-analog surprise-bit agreement, F-descent trajectory ρ. **Measured (ALL GATES PASS):** the comma lane's knee is **k\*=1** — one stored bit per level (2 explicit truth bits/edge vs the baseline 16) already gives mean|ΔE| 0.0084, surprise agreement 0.9688, descent ρ 0.9792. The aligned control (collapsed pyramid) needs **k\*=4**. Mechanism made visible: the comma walk is a **low-discrepancy per-edge lattice**, so de-dithered averaging behaves like stratified sampling — comma k=1 RMSE 0.0244 vs aligned 0.2503 (10×), matching aligned between k=3 and k=4: the lattice buys **≈3.4 effective bits ≈ log₂(12)=3.58**. Replay bit-identical across passes and level orders. **Honest chronicle:** run #1 FAILED its own G1 — the gate was mis-registered (demanded EXACT surprise agreement at k=8, but the comma lane is a dithered reconstruction, never an identity path); the fix was a diagnosis measurement, not a tune: G1′ additionally requires every disagreeing pair's margin-to-threshold < 0.005, and the measured max margin is **1.7e-5** — every flip is threshold-boundary noise, proven. **Fences:** proxies ≠ the full ShaderDriver loop — any real CausalEdge64 shrink is gated on **D-MTS-6b** (driver-integrated fixture); the economy claim is marginal-cost (the L per-level slots are the pyramid's OWN envelope storage — the probe measures what they jointly RECOVER, not free storage).
 
+## 2026-07-10 — E-NOBODY-WAITS-1 — no messages, no actors, anywhere: ractor is ONLY the compile-time ownership guarantee; the prime invariant is that NOBODY waits for anything or any scheduling
+**Status:** RULING (operator, 2026-07-10, post-#674-merge audit of "kanban step vs ack pump"; disposition: LEAVE AS IS AND DOCUMENT — no retirement work opened)
+
+The operator's audit question — did the ack-pump duplicate the existing BatchWriter→kanban-step route, or ignore the Rubicon model? — resolved into a foundational clarification: **we don't use messages at all, nor actors; ractor exists solely as the compile-time ownership guarantee** (the delegation declaration — `KanbanActor`-over-real-`MailboxSoA` names WHO owns, never a message path). Consequences, all verified in code:
+
+1. **The Rubicon model is intact and owner-side.** `contract::kanban::KanbanColumn` IS the 4-phase Rubicon (Planning→CognitiveWork = the −550ms Σ-commit crossing; Planning→Prune = the pre-Rubicon Libet veto; Evaluation 3-way; Plan→Planning re-deliberation). The crossing is the owner's, at intent formation — the cast records intent AHEAD of the ack, Rubicon-conformant.
+2. **The message-free loop is the canonical route:** `BatchWriter::ack_and_propose` (first-transition-dedup'd, #674) → `Option<KanbanMove>` proposal → `MailboxSoaOwner::try_advance_phase(&mut self, to)` — plain method calls end to end. **`&mut` IS the serialization**: the stale-phase race codex #578 guarded against, and the atomicity ceremony built for it, only exist in a message world; under exclusive ownership the race is a compile error — the ractor ruling doing its job. The #579 exec-overlay concern also dissolves in the direct path (the proposal itself is applied; `exec` travels with it). The ack is storage-side postactional evidence of cycle N seeding cycle N+1's deliberation — it proposes, the owner disposes, and rs-graph-llm contains no ack code at all (consumer transitions are envelope KanbanMoves on the same Rubicon DAG).
+3. **Any message path in the tree is redundancy.** Named residue: `lance-graph-supervisor`'s `KanbanMsg::{Tick,Advance}`, `ractor::call!` RPC, `drive_version_tick`, `drive_scheduled_tick` (consumers: supervisor tests + onebrc-probe lane E — which, fittingly, measured the actor-model tax). **Operator disposition: left as is, documented** (TECH_DEBT TD-MESSAGE-RESIDUE); the drift signal is NEW code reaching for `KanbanMsg`/`call!` instead of the `&mut` owner surface.
+4. **THE PRIME INVARIANT (the operator's closing emphasis): nobody is waiting for anything or any scheduling.** Writes are fire-and-forget ("melden macht frei"); acks propose; updates reprioritize, never gate; absorbing views rest the loop, never deadlock it; the thinker never blocks on I/O, on a scheduler, or on another mailbox. Every future design choice on this surface is judged against this sentence first.
+
 ## 2026-07-10 — E-FIVE-STYLE-TABLES-1 — the M9 dedup found FIVE mutually divergent hand-rolled style tables; duplication had already produced live semantic drift, and the weakest gate would have greenlit silent corruption
 **Status:** FINDING (measured during D-TSC-1 implementation, the first 5+3 council run; all five replaced by `StyleFamily::default_runbook()`/`ThinkingStyle::family()`, shipped with 1549 tests green)
 

.claude/board/PR_ARC_INVENTORY.md

@@ -35,6 +35,22 @@
 
 ---
 
+## #674 lance-graph: V3 W2–W6 continuation + comma quorum/awareness measured + 5+3 council + StyleFamily dedup (D-TSC-1)
+
+**Status:** MERGED 2026-07-10 (merge commit `cd5178e`), branch `claude/review-claude-board-files-nhqgx1`, 16 commits. Companion: rs-graph-llm `8ef18b9` (same branch name there, not yet PR'd) — `run_cycle` explicit `on_behalf` (owner ≠ classid).
+
+**Added:** `contract::step_mask::StepMask` (W3a); `planner::elevation::cycle::CycleBudget` (W2d/M12); `MailboxSoA::cast_on_behalf` (W4a) + standalone `with-planner` E0432 fix; `contract examples/adoption_scan` (W6a); `BatchWriter::ack_and_propose` (D-ORG-1, first-transition-dedup'd per codex P2); `contract::style_family::StyleFamily` + `default_runbook()`/`ThinkingStyle::family()` (D-TSC-1/M9); `PlannerStyleExt`/`EngineStyleExt`; `superposition::DetectedStyle` rename; thinking-engine gains the lance-graph-contract dep; probes `perturbation-sim/examples/{comma_quorum,comma_awareness}.rs` (D-MTS-5/6); `.claude/agents/5plus3-council.md` + `/5plus3` skill; `.claude/v3/FUTURE-DESIGN.md`.
+
+**Locked:** the seven 2026-07-10 rulings (E-ACK-IS-THE-KANBAN-TRIGGER-1, E-ORCHESTRATION-ORGANS-1, E-THINKING-STYLES-ARE-CLASSES-1, E-MARKOV-TEMPORAL-STREAM-1, E-COMMA-QUORUM-1/E-COMMA-REPLAY-1, E-STYLE-FAMILY-VS-RUNBOOK-1, E-THINKING-TENANTS-V3-1); measured findings E-COMMA-QUORUM-MEASURED-1 (N_eff 11.00/12; boundary condition N_eff = min(L, spectral participation)), E-COMMA-AWARENESS-MEASURED-1 (k*=1 vs aligned k*=4; ≈log2(12) effective bits), E-FIVE-STYLE-TABLES-1 (five divergent style tables — the M9 payoff made concrete); M9 RESOLVED with G1 = 1 enum + 3 deprecated aliases; the 5+3 anti-mush sequencing (spec-first, consolidate-before-review); style behavior changes documented + G7 literal-pinned (planner arms 9/10/11, driver 8/9/10, parse 8/9/10, engine 36→12 ranges).
+
+**Deferred:** D-MTS-6b (driver-integrated awareness fixture — gates ANY real CausalEdge64 shrink); D-MTS-1..3 (gate ALL VSA-path removal); D-TTV-1 (thinking tenants → V3); D-TSC-2/3 (batched OGAR mint, never solo); D-TSC-4 (W6c/0x1000 coexistence — ESCALATED, operator ruling needed); W2a BoardAggregates (batched-mint gate); TD-STYLE-TABLE-RESIDUE (ndarray pair / wip imports / p64-bridge ordinal probe).
+
+**Docs:** spec `dtsc1-thinkingstyle-dedup-spec-v1.md` (v1→v2→v3, full council fix ledgers); plan `temporal-markov-and-style-classes-v1.md`; FUTURE-DESIGN landing zone; TYPE_DUPLICATION_MAP/COMPONENT-MAP/MODULE-TABLE addenda; .grok thinking_styles superseded banner.
+
+**Post-merge ruling (2026-07-10, same day):** E-NOBODY-WAITS-1 — no messages/no actors anywhere (ractor = compile-time ownership guarantee only); the ack-pump is the canonical message-free route; supervisor KanbanMsg drivers regraded documented redundancy (TD-MESSAGE-RESIDUE, leave-as-is); prime invariant: nobody waits for anything or any scheduling.
+
+**Confidence (2026-07-10):** HIGH — all 6 CI checks green at merge; 1549 lib tests across the four touched crates; both probes ALL GATES PASS with honest run chronicles.
+
 ## #632 lance-graph: Cross-session intake — RouteBucketTyped (C6) merged, emission_scan minted, OCR codebook mirror, GraphRAG-rs inventory + operator rulings
 
 **Status:** MERGED 2026-07-02 (merge commit `df367471`), branch `claude/v3-substrate-migration-review-o0yoxv`. Companion: OGAR #148 (merge `75d955b`) — the cross-repo fuses + serialized allocation batch; merged FIRST per the lockstep note; this post-merge commit carries the ogar-vocab lock bumps that cleared COUNT_FUSE (fired 65 vs 68 in the in-between state — first live demonstration of the fuse mechanism, then green 68 == 68, lance-graph-ogar 81 tests).

.claude/board/TECH_DEBT.md

@@ -1,5 +1,22 @@
 # Technical Debt Log — Open + Paid (double-entry, append-only)
 
+## TD-MESSAGE-RESIDUE (2026-07-10, operator-ruled LEAVE-AS-IS)
+
+Per E-NOBODY-WAITS-1: no messages, no actors anywhere — ractor is only
+the compile-time ownership guarantee. The message-based arm in
+`lance-graph-supervisor` (`KanbanMsg::{Tick,Advance}`, `ractor::call!`,
+`drive_version_tick`, `drive_scheduled_tick`; consumers: supervisor
+tests + onebrc-probe lane E) is REDUNDANCY relative to the canonical
+message-free loop (`BatchWriter::ack_and_propose` proposal →
+`MailboxSoaOwner::try_advance_phase(&mut)` — `&mut` is the
+serialization). **Disposition: left as is, documented — NO retirement
+work queued** (operator, 2026-07-10). Not a bug: the code is correct in
+its own model; it is a second model. Drift signal: NEW code reaching
+for `KanbanMsg`/`ractor::call!` instead of the `&mut` owner surface —
+that, not the existing residue, is what a reviewer blocks. The prime
+invariant every change on this surface is judged against: **nobody
+waits for anything or any scheduling.**
+
 ## TD-STYLE-TABLE-RESIDUE (2026-07-10, D-TSC-1 follow-ups)
 
 Three residues from the M9 ThinkingStyle dedup (all OUT of D-TSC-1 scope,
@@ -16,6 +33,18 @@ each with its own closing condition):
    with no `mod cognitive` — dormant behind `#[cfg(feature = "wip")]`.
    Close: point them at contract StyleFamily/ThinkingStyle when the wip
    modules wake, or delete.
+3a. **Census extension (2026-07-10, ancestry census):** three MORE
+   independent 12-slot style tables beyond the D-TSC-1 sweep —
+   `cognitive-shader-driver/src/auto_style.rs` bare u8 consts,
+   `engine_bridge.rs::UNIFIED_STYLES` params (parity-tested but its
+   PARAMS are a hand table), `p64-bridge StyleParams[12]` (historical
+   order). Also: `GestaltState` defined independently in thinking-engine
+   `awareness_dto.rs` AND `world_model.rs`; the jina/bge_m3/reranker
+   lens triplet is near-identical; `wire.rs` (1852 lines) is the
+   largest driver file while LAB-ONLY. All documented in the
+   MODULE-TABLE ancestry addendum; close via M8/M9-style follow-ups
+   when Track B lands.
+
 3. **p64-bridge ordinal-order probe (spec I15):** `crates/p64-bridge/src/
    lib.rs STYLES[ord % 12]` uses the HISTORICAL order (Analytical=0), NOT
    StyleFamily order (Deliberate=0). Doc comment now warns (convert by

.claude/plans/temporal-markov-and-style-classes-v1.md

@@ -59,6 +59,31 @@ never stored); per-level content = palette-quantized magnitude envelope only.
 > E-COMMA-AWARENESS-MEASURED-1.
 > Execution spec for D-TSC-1: `.claude/plans/dtsc1-thinkingstyle-dedup-spec-v1.md`.
 
+> **Addendum (operator, 2026-07-10, third wave — D-MTS-1 context-building
+> design input):** the **AriGraph context, V3-TENANT-SHAPED, is most
+> probably essential for Markov-chain context building while streaming
+> text.** The ingest legs feeding it: **`lance-graph-arm-discovery`**
+> (the Aerial+ transcode — float-free association-rule discovery via the
+> palette256 integer distance oracle, ρ=0.9973, → `{s,p,o,f,c}` ndjson →
+> SPO loader) and **DeepNSM** (text→SPO via the 6-state PoS FSM; the
+> **64×64 = 4096 COCA vocabulary IS the CAM index codebook**, 4096² u8
+> LUT). The representational comparison the D-MTS-1 spec MUST weigh for
+> the streamed context items:
+>
+> - **CAM-PQ `6×8 = 48-bit` codes** — 6 subspaces × 1 byte = 6 bytes =
+>   exactly the OGAR GUID path (HEEL+HIP+TWIG): the ADDRESS-side coding.
+> - **`6× palette256:palette256` = 12 bytes = ONE V3 tenant** — 6
+>   subspaces × an X:Y byte PAIR each (the 256×256 centroid-tile
+>   reading, le-contract L4 carve): the VALUE-tenant-side coding —
+>   exactly one content-blind facet payload.
+>
+> The likely resolution (to be probed, not assumed): key addresses,
+> tenant carries — the 48-bit path codes route/dedupe the streamed SPO
+> items, while the palette² tenant is the projection surface the
+> perturbation shader attends per cycle. This joins D-TTV-1 (the
+> AriGraph-context lane is a thinking tenant) and instantiates the L4
+> carrier named in E-MARKOV-TEMPORAL-STREAM-1.
+
 ## Track B — Thinking styles as classes (domain:appid:classview)
 
 Ruling: styles move entirely under the classid umbrella. A style class

.claude/v3/FUTURE-DESIGN.md

@@ -4,6 +4,7 @@
 > landing zone the operator asked for (2026-07-10): future substrate design
 > lands HERE first, referencing the V3 inventory (`COMPONENT-MAP.md`,
 > `MODULE-TABLE.md`, `soa_layout/*`) so design converges on what exists.
+> **The WHY lives in `VISION.md`** (same folder — the graded canon synthesis).
 > Canonical ruling text lives on the board (`.claude/board/EPIPHANIES.md`);
 > this file is the design-side index + the wiring queue. Read AFTER the V3
 > README; cite EPIPHANIES entries in PRs, not this mirror.