Skip to content

Commit 7ef6c2b

Browse files
authored
Merge pull request #411 from AdaWorldAPI/claude/splat3d-cpu-simd-renderer-MAOO0
Cognitive substrate: locked 33-TSV atom layer + 34-tactic recipes + escalation loop
2 parents 38c966a + 5a0abe4 commit 7ef6c2b

55 files changed

Lines changed: 5890 additions & 0 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

.claude/board/AGENT_LOG.md

Lines changed: 168 additions & 0 deletions
Large diffs are not rendered by default.

.claude/board/EPIPHANIES.md

Lines changed: 419 additions & 0 deletions
Large diffs are not rendered by default.

.claude/board/INTEGRATION_PLANS.md

Lines changed: 112 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,115 @@
1+
## 2026-05-27 — atom-mailbox-substrate-v1 (ladder-serves-mailbox: atoms→styles→personas, quorum projection, counterfactual mantissa, AriGraph hot/cold/tombstone)
2+
3+
**Status:** PROPOSAL (implements `EPIPHANIES.md` E-LADDER-SERVES-MAILBOX; extends `rung-persona-orchestration-v1` D-PERSONA-1 downward into the atom layer and outward into the mailbox lifecycle).
4+
**Confidence:** HIGH on the mechanism→shipped-type mapping; **CONJECTURE on the atom basis (D-ATOM-0, the load-bearing unsolved decision)** and the I4-32D SIMD layout until probed.
5+
**Plan file:** `.claude/plans/atom-mailbox-substrate-v1.md`
6+
**Predecessors:** `rung-persona-orchestration-v1`, `rung-mul-grounding-v1`, `cognitive-substrate-convergence-v1`.
7+
**Anchored iron rules:** `I-VSA-IDENTITIES`, `E-BATON-1`, `I-LEGACY-API-FEATURE-GATED`, The Click.
8+
9+
### Scope
10+
Three-layer cognitive basis under the mailbox-served ladder: **atoms (bipolar I4-32D, 32 dims / 64 poles) → thinking styles (compositions) → persona recipes (compositions + thresholds + β)**. Each atom *measured by a quorum* (`(position, confidence)` = NARS truth per axis; splits = Contradiction never averaged); split-poles *preserved as a `CausalEdge64` −6 counterfactual mantissa* (ghost-tier test → `awareness.revise`); memory *ephemeral-hot in mailbox → calcified-cold SPO + Lance tombstone-witness* (GoBD audit by construction). wisdom↔Staunen = sampling temperature (self-regulated by free energy; the `WisdomMarker` 0.1 floor = min temperature).
11+
12+
### Decision gates (block scaffolding)
13+
D-ATOM-0 atom-basis route (ICA/PCA over 36 / theory-driven from 6 clusters / hybrid) · D-ATOM-0b NARS as categorical register (Test 0, recommended) vs bipolar atoms.
14+
15+
### Deliverables
16+
D-ATOM-1 atom catalogue + `I4x32` type + pack/SIMD (`contract::atoms`, blocked on D-ATOM-0) · D-ATOM-2 style/persona Cranelift recipe templates (`contract::jit`/`thinking`) · D-ATOM-3 quorum-projection per axis (`contract::escalation`/`a2a_blackboard`) · D-ATOM-4 counterfactual mantissa v2 deposit / v3 mailbox+revision (basis-independent) · D-ATOM-5 AriGraph hot/calcify/tombstone (basis-independent).
17+
18+
### Execution
19+
Sonnet `///`-scaffold wave (disjoint file scopes, BLOCKED-not-guess) → P2 review (`/code-review` high, ultra for D-ATOM-1/2; no literal codex binary) → implement+remove stubs → per-deliverable PR into the working branch → subscribe+autofix CI → merge → repeat. Parallel-now: D-ATOM-4 v2, D-ATOM-5 (basis-independent); D-ATOM-1/2 spawn after D-ATOM-0.
20+
21+
### Invariants
22+
persona=Layer-2 (no container) · NARS type in register (Test 0) · markers ≤32 (I-VSA-IDENTITIES) · splits=Contradiction never averaged · counterfactual in separate lane · one graph · no persisted singleton (E-BATON-1) · ractor async only at swarm boundary · bounded respawn · `latency_budget` arbiter, no hot-Pod wall-clock · SIMD gated on `ndarray-vertical-simd-alien-magic.md`.
23+
24+
---
25+
26+
## 2026-05-26 — rung-persona-orchestration-v1 (time-bound persona orchestration: boring checklist → meta-recipe → hot/cold/feedback anneal)
27+
28+
**Status:** PROPOSAL (sibling to `rung-mul-grounding-v1`; the time-bound + composition layer)
29+
**Confidence:** HIGH on structure (hot/cold/feedback = the original ladybug architecture + OpenAI macro-evals + ADK Memory Bank, converged); MED on ractor adoption + macro-eval harness (net-new).
30+
**Plan file:** `.claude/plans/rung-persona-orchestration-v1.md`
31+
**Predecessors:** `rung-mul-grounding-v1` (b4efb55), `rung-ladder-grounding-v1` (b0ef6fa), `cognitive-substrate-convergence-v1`.
32+
**Design refs (read-only general-web; ladybug-rs is outside GitHub-MCP scope):** ladybug-rs `INTEGRATION_PLAN.md` @177a321 §"BF16 Superposition (Hot/Cold/Feedback)" L542+ + 4-phase `[DONE]/[TODO]` gate + 3 composition modes + BindSpace-blackboard; `src/spectroscopy/detector.rs` @177a321; Claude chief-of-staff; OpenAI macro-evals; Google ADK Memory Bank.
33+
34+
### Scope
35+
36+
Ground (restore-on-SoA, NOT port) ladybug's hot/cold/feedback loop + phase-gate checklist + blackboard composition onto our contract/SoA floor, as the time-bound layer over the `rung-mul` experience curve.
37+
38+
- **Two orthogonal orderings × time budget:** epistemic experience-curve (Axis A) × social etiquette arc (Axis B), arbitrated by `latency_budget` (`elevation/mod.rs:131`). 2D menu phase×DK-position; etiquette = soft prior + anytime graceful-degradation, not rigid FSM.
39+
- **Boring checklist (verify, temp≈0):** hard gates (contracts/SoA/store/NARS/thresholds/FreeEnergy) vs soft (capabilities/wisdom-store/eval — degrade). Continuous health invariant: red-at-runtime → let-it-crash → supervisor restart = rung-shift + NaN→Lab.
40+
- **Meta-recipe (compose, cold):** declarative child-spec manifest (data not code, macro-evaluable); blackboard composition on `a2a_blackboard`/SoA (per ladybug BindSpace), ractor supervises + carries Batons.
41+
- **Hot/cold/feedback (L542 grounding):** hot = annealed cognitive cycle; cold = macro-eval = **wisdom-marker factory** (ladybug `CrystalCodebook` "lived history" → our *distilled calibrated* marker); feedback = hydrate-before-the-fact (ADK Preload).
42+
- **Temperature anneal:** explore hot → exploit cold, **evidence-gated** (Boole-bound caps cooling — no premature Mount Stupid). Grounded: detector `noise_tolerance=base·(1+(1−conf)·0.5)`, `fanout=base·(1+bridgeness·0.5)` (bridgeness=macro-eval suspect-bridge=our work-metric, triple convergence).
43+
- **Substrate:** ractor YES (outer swarm under `OrchestrationBridge`, async only at boundary, SoA inner sync); surrealdb NO for cognitive (redundant w/ lance-graph/AriGraph, not boring; prefer SQLite/Lance operational); AriGraph = the one graph.
44+
45+
### Deliverables
46+
47+
D-PERSONA-1 hard/soft checklist verifier (~180) · D-PERSONA-2 meta-recipe manifest (recipe-as-data, ~150) · D-PERSONA-3 hot/cold/feedback wiring + CrystalCodebook→wisdom-marker + Preload hydrate (~240) · D-PERSONA-4 macro-eval harness (scenario→trace→discover→diagnose, suspect-bridge=blasgraph betweenness, ~280, HIGH) · D-PERSONA-5 ractor outer-swarm runtime (~200).
48+
49+
### Honest gaps vs original
50+
51+
ladybug `detector.rs` has NO null/dead-end/escalation ("all inputs produce valid output") → our NaN→cautious-exploration→Lab + dead-end-as-work is net-new. `CrystalCodebook` dumps lived history → we distill it into a calibrated marker (Boole-bound, ≤32 identities). ractor + etiquette arc not in original.
52+
53+
### Invariants
54+
55+
restore-on-SoA not port · hard/soft graceful-degradation · recipe-as-data (macro-evaluable) · evidence-gated anneal (Boole-bound cooling cap) · blackboard composition not direct calls · ractor async only at swarm boundary · no second graph · I-VSA-IDENTITIES (markers ≤32) · `latency_budget` time arbiter.
56+
57+
---
58+
59+
## 2026-05-26 — rung-mul-grounding-v1 (the MUL fine-tuned into the ladder as an experience curve over the SPO 2³ NARS decomposition)
60+
61+
**Status:** PROPOSAL (follow-on to `rung-ladder-grounding-v1`)
62+
**Confidence:** HIGH on structure (it is the Dunning-Kruger curve mechanized); MED on the per-projection `SpoHead` refactor; CONJECTURE on the wisdom-marker calibration readout until D-RUNG-MUL-4 tests it.
63+
**Plan file:** `.claude/plans/rung-mul-grounding-v1.md`
64+
**Predecessors:** `rung-ladder-grounding-v1` (b0ef6fa), `cognitive-substrate-convergence-v1` (CausalEdge64 v2 §6 — causal mask = Pearl 2³ IS the rung axis), `E-AGICHAT-DIMENSION-CONTRACT` (afabefd), `E-I4-META-1`.
65+
66+
### Scope
67+
68+
Grade the coarse integer rung ladder with the MUL, organized as an **experience curve**: every strategy ordered by the evidence level at which it becomes *necessary* — which collapses into the Dunning-Kruger curve with a mechanical trigger at each point.
69+
70+
- **SPO 2³ corrected:** it is the **powerset of {S,P,O}** (8 evidential projections `___,S__,_P_,__O,SP_,S_O,_PO,SPO`) for causality testing through NARS **decomposition** — NOT a distance-cube/popcount. `nars_engine.rs` today computes `all_projections() -> [u32;8]` as *distances* and `SpoHead` carries *one* truth; de-grounding that to per-projection truth is D-RUNG-MUL-1.
71+
- **Causation = screening-off:** `S_O` strong but screened off by P (`SP_``_PO`) ⇒ spurious/mediated; all projections compared to `___` for lift over base rate.
72+
- **Work (exploit):** decomposition + screening-off coverage, **confidence/expectation-gated (never frequency)**, AIKR-gated by `budget.quality`. Two curves over one axis: work climbs monotone, confidence is DK-shaped; **wisdom = calibration gap `|conf−competence|→0`**.
73+
- **Two sparse-data routes:** NaN sentinel ("no field") → cautious-exploration (Exploratory, high exploration_rate) + `ElevationLevel`↑ + **Lab request**; sparse field → gaussian splat → `FreeEnergy::compose` as the *sole* confidence source (F caps confidence ⇒ **no data ⇏ overconfidence**). Explore drive = `wonder` × `free_will_modifier` × trust.
74+
- **Wisdom markers:** long-term VSA-**identity** bundle (≤32 per I-VSA-IDENTITIES; truths in content store) hydrated *before the fact* as the KL prior — the curve becomes a spiral.
75+
76+
### Deliverables
77+
78+
D-RUNG-MUL-1 per-projection NARS truth (`SpoHead` 8 `(f,c)`, planner ~220) · D-RUNG-MUL-2 NaN→cautious-exploration+Lab gate, distinct from `c=0` (~160) · D-RUNG-MUL-3 wisdom marker (identity bundle + hydrate-as-KL-prior, contract+planner ~180) · D-RUNG-MUL-4 screening-off work + Boole/Fréchet bound + calibration-gap readout (~150) · D-RUNG-MUL-5 splat→`FreeEnergy::compose` as sole sparse-data confidence (~120).
79+
80+
### Invariants
81+
82+
Confidence-gated never frequency-gated (frequency alone = Mount Stupid) · Boole/Fréchet bound on conjunction confidence · no data ⇏ overconfidence (only FreeEnergy or floored-NaN may signal) · I-VSA-IDENTITIES (markers ≤32 identities, content in store) · AIKR `budget.quality` fanout cap · AGI-as-SoA (markers = column ops, not a new service) · decomposition not distance-cube. Folds into `elevation/homeostasis.rs` (MUL-L6) beside `evaluate_rung_shift`; does not fork.
83+
84+
---
85+
86+
## 2026-05-26 — rung-ladder-grounding-v1 (the most-obvious first grounding of the agichat gestell)
87+
88+
**Status:** PROPOSAL
89+
**Confidence:** HIGH — deterministic integer/threshold logic, zero VSA in the decision path; cleanest possible first restore.
90+
**Plan file:** `.claude/plans/rung-ladder-grounding-v1.md`
91+
**Predecessors:** `E-AGICHAT-DIMENSION-CONTRACT` (afabefd), `E-I4-META-1`, `E-BATON-1`; shipped floor ndarray `SoaColumns` (42cb7123) + i4-32 unpack (8de1dcf8).
92+
**Follow-on (planned, user-flagged):** `rung-mul-grounding-v1` — the **MUL fine-tuned into the ladder**: ladybug's 10-layer MUL (`MulSnapshot`) becomes the *trigger source* refining the ladder's coarse binary triggers into graded escalation (DK MountStupid → escalate; homeostasis Anxiety + allostatic-load → escalate; false-flow → escalate; gate-block reason → escalate). `elevation/homeostasis.rs` is already MUL-L6 — ladder + MUL co-finetune there.
93+
94+
### Scope
95+
96+
Ground agichat's **RungShift ladder** + **CollapseGate SD** as LE-contract types/logic on the SoA floor. The ladder was never inflated (ladybug-rs `rung.rs` is a faithful port) — the work is to express it as a bit-exact Pod and wire its triggers to grounded signals.
97+
98+
- **CollapseGate:** SD over candidate scores → `FLOW(<0.15)/HOLD/BLOCK(>0.35)`; SD = dispersion, not confidence.
99+
- **RungShift:** rung 0-9, bands 0-2/3-5/6-9; triggers sustained-block(≥3) / predictive-failure(avg P<0.3 / window 5) / structural-mismatch → +1 (cap 9); tick-based cooldown.
100+
- **Grounding:** `RungState` = 16-byte `#[repr(C)]` Pod (no `Vec` — fixed `[u8;5]` P-ring; tick cooldown; u8/i4-quantized scores) in a `SoaColumns` column; `evaluate_rung_shift` PURE (no `&mut` during compute) folded into `lance-graph-planner/src/elevation/` beside `homeostasis.rs`; SD via ndarray SIMD; `GateState` into `collapse_gate.rs`.
101+
- **Hook:** RungLevel = the **R1-R9 dim-group** of the 33-TSV (`ThinkingStyleI4_32D`).
102+
103+
### Deliverables
104+
105+
D-RUNG-1 contract types (lance-graph-contract, ~150) · D-RUNG-2 pure ladder logic in `elevation/` (planner, ~200) · D-RUNG-3 `RungState` SoA column + tick update (~100) · D-RUNG-4 SD→GateState in `collapse_gate.rs` + rung→TSV-R1-R9 map (~120). Parity tests vs verbatim agichat semantics.
106+
107+
### Invariants
108+
109+
No `Vec`/alloc in hot Pod · no `&mut` during compute (pure evaluate, builder apply) · tick-based not wall-clock · integer rung (no float-resonance carrier — the de-grounding ladybug-rs did) · SD = dispersion not confidence · RungShift separate from SD.
110+
111+
---
112+
1113
## 2026-05-15 — cognitive-substrate-convergence-v1 (CSV — i4 mantissa + gapless baton + active inference)
2114

3115
**Status:** Active (PROPOSAL — awaits OQ-CSV-1..6 ratification before sprint-11 D-CSV-* spawn)

.claude/board/LATEST_STATE.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -57,6 +57,8 @@ Types that EXIST — do NOT re-propose them:
5757

5858
Full reference: `.claude/knowledge/causal-edge-64-spo-variant.md` + `.claude/knowledge/causal-edge-64-thinking-engine-variant.md` + `.claude/knowledge/causal-edge-64-synergies-and-pr-trajectory.md`. Reunification path (Option R-3): transcode 8-channel → SPO at thinking-engine L3 commit boundary; see `.claude/knowledge/cognitive-shader-driver-thinking-engine-reunification.md`.
5959

60+
**`escalation`** (D-PERSONA-1, 2026-05-26, branch `claude/splat3d-cpu-simd-renderer-MAOO0`): the escalation+epiphany loop = the boot checklist (a *restore* of ladybug's qualia loop on our SoA — NOT a bespoke verifier). `CollapseHint` {Flow, Fanout, RungElevate} + `fanout_width` / `noise_tolerance` / `rung_delta` (ladybug `detector.rs` formulas); `Archetype` {Guardian, Catalyst, Balanced} + `InnerCouncil::{deliberate, from_signals}` + `is_split(0.7,0.5)` ×1.2 split-amplify → `CouncilVerdict`; `EpiphanyDetector::observe` (sim > baseline×1.5 ∧ window ≥ 4) → `Epiphany`; `GhostEcho` (8 named: Affinity/Epiphany/Somatic/Staunen/Wisdom/Thought/Grief/Boundary — canonical zero-dep home, mirrors `thinking_engine::ghosts::GhostType`, see TD-GHOST-ECHO-DUP-1) + `WisdomMarker` (asymptotic decay → 0.1 floor, never zero); `GateKind` {Hard, Soft} + `ChecklistItem` + `Checklist::{step, mark_red, boot_ready, all_flow, degraded}` (green-flip = Flow + epiphany; let-it-crash = `mark_red` re-escalate). Planner wiring at `lance_graph_planner::mul::escalation::{boot_checklist, verdict_from}` (§2: 6 HARD / 3 SOFT items + a `MulAssessment` → `CouncilVerdict` adapter). 13 tests (10 contract + 3 planner).
61+
6062
## cognitive-shader-driver Wire Surface (lab-only, post D0.1)
6163

6264
Types live in `crates/cognitive-shader-driver/src/wire.rs` behind `--features serve`:

.claude/board/STATUS_BOARD.md

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -495,6 +495,25 @@ Consolidates sprint-10 architectural decisions before context dilution.
495495

496496
---
497497

498+
## rung-persona-orchestration-v1 — time-bound persona orchestration (checklist → meta-recipe → hot/cold/feedback anneal)
499+
500+
Active proposal. Authored 2026-05-26. Plan path:
501+
`.claude/plans/rung-persona-orchestration-v1.md`. Sibling/time-bound
502+
composition layer over `rung-mul-grounding-v1`. Grounds ladybug's
503+
hot/cold/feedback loop onto our contract types + SoA floor
504+
(restore-on-SoA, not port). Epiphany: `E-RIGID-RULES-OPEN-DOORS`.
505+
506+
| D-id | Title | Crate(s) | ~LOC | Risk | Status | PR / Evidence |
507+
|---|---|---|---|---|---|---|
508+
| D-PERSONA-1 | escalation+epiphany loop = the checklist (`felt_parse` collapse-hint + `InnerCouncil`/`HdrResonance` split + `EpiphanyDetector`; green-flip = Epiphany/Wisdom ghost) — NOT a bespoke verifier | contract + planner | 160 | LOW | **In progress** | branch `claude/splat3d-cpu-simd-renderer-MAOO0` |
509+
| D-PERSONA-2 | meta-recipe manifest (declarative child-spec, recipe-as-data, macro-evaluable) | contract | 150 | MED | **Queued** ||
510+
| D-PERSONA-3 | hot/cold/feedback wiring — anneal + `CrystalCodebook`→wisdom-marker cold path + Preload hydrate | planner + Lance | 240 | MED | **Queued** ||
511+
| D-PERSONA-4 | macro-eval harness (scenario→trace→discover→diagnose; suspect-bridge = blasgraph betweenness; 5 rubrics from D-RUNG-MUL) | planner + Lance | 280 | HIGH | **Queued** ||
512+
| D-PERSONA-5 | ractor outer-swarm runtime under `OrchestrationBridge` (batons as messages, async only at boundary) | planner | 200 | MED | **Queued** ||
513+
| D-PERSONA-6 | `odoo_scanner` + `OdooBridge` — harvest Odoo `l10n_de` → Finance-ns `MappingProposal`s; bind existing `TaxEngine`; GoBD by construction | ontology + contract + planner | 280 | MED | **Queued** ||
514+
515+
---
516+
498517
## Update protocol
499518

500519
When a deliverable ships:

.claude/board/TECH_DEBT.md

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -13,6 +13,18 @@
1313
---
1414

1515

16+
### TD-GHOST-ECHO-DUP-1 (D-PERSONA-1)
17+
18+
- **Severity:** P3 (cosmetic type-dup; no runtime correctness risk — the two enums are not exchanged across a crate boundary today)
19+
- **Surfaced in:** D-PERSONA-1 (`rung-persona-orchestration-v1` §2), 2026-05-26, branch `claude/splat3d-cpu-simd-renderer-MAOO0`
20+
- **Status:** Open
21+
- **Description:** `lance_graph_contract::escalation::GhostEcho` (8 variants: Affinity / Epiphany / Somatic / Staunen / Wisdom / Thought / Grief / Boundary) is a second declaration of the same 8 named ghost echoes already in `thinking_engine::ghosts::GhostType` (`crates/thinking-engine/src/ghosts.rs`). The duplication is *intentional and currently unavoidable*: `lance-graph-contract` is ZERO-DEP and cannot import the excluded `thinking-engine` crate, and the contract is the canonical "single source of truth for types" home for the wisdom-marker substrate (≤32 named identities per I-VSA-IDENTITIES). The two are NOT interchanged across a boundary today, so there is no silent-corruption risk (cf. I-LEGACY-API-FEATURE-GATED), only a naming/maintenance dup.
22+
- **Resolution (when thinking-engine joins the workspace):** make `thinking_engine::ghosts::GhostType` a re-export of (or `From`/`Into` with) `contract::escalation::GhostEcho`, retiring the thinking-engine copy. Until then, keep the variant sets identical (same 8, same order) so a future `transmute`/`From` bridge is trivial.
23+
- **Cross-ref:** `crates/lance-graph-contract/src/escalation.rs` (`GhostEcho`, `WisdomMarker`); `crates/thinking-engine/src/ghosts.rs` (`GhostType`, `GhostField`); `docs/TYPE_DUPLICATION_MAP.md`; `.claude/plans/rung-persona-orchestration-v1.md` §2 + §8.
24+
25+
---
26+
27+
1628
### TD-NDARRAY-SIMD-UNPACK-I4-16D (W1a-#1)
1729

1830
- **Severity:** P1 (blocks mul.rs follow-up + future i4-packed codec consumers)

0 commit comments

Comments
 (0)