arifos 37.0.0

Constitutional Governance Kernel for AI - 9 Floors, GENIUS LAW Judiciary, zkPC + Phoenix-72, PHOENIX SOVEREIGNTY, v37 Unified LAW+SPEC+CODE Runtime

arifOS v37 — Constitutional Governance Kernel for AI

+=============================================================================+
|  arifOS v37 - Constitutional Governance Kernel                              |
|  "DITEMPA BUKAN DIBERI" — Forged, not given.                                |
|  Truth must cool before it rules.                                           |
+=============================================================================+
|  Runtime Epoch: v37 (DEFAULT) - Unified LAW+SPEC+CODE                      |
|  Measurement:   v36.3Omega (GENIUS LAW + Truth Polarity + 9 Specs)         |
|  Design Canon:  v36.3Omega (Law/Spec/Code 3-Track Architecture)            |
|  Status:        PRODUCTION                                                 |
|  Tests:         1115+ passing (core + eval + waw + guards + grey + v37)    |
|  CLI Tools:     arifos-analyze-governance, arifos-verify-ledger, +5 more    |
+=============================================================================+

The 10-Second Answer

arifOS is a constitutional operating system that wraps any LLM (Claude, GPT, Gemini, Llama, SEA-LION) and governs its outputs through:

• A 000→999 metabolic pipeline (VOID → SENSE → … → JUDGE → SEAL),
• A 9-floor thermodynamic constitution (Amanah, Truth, Tri-Witness, ΔS, Peace², κᵣ, Ω₀, G, C_dark),
• A triple-engine AAA Trinity (ARIF · ADAM · APEX PRIME),
• A W@W Federation of external organs (@WELL, @RIF, @WEALTH, @GEOX, @PROMPT),
• A Cooling Ledger + Vault-999 memory stack that logs decisions and cools scars into amendments.

Safety is achieved by physics and thermodynamic floors, not just "be nice" prompts. Bad behaviour becomes structurally hard, not just discouraged.

---

Quick Install & Usage

Installation

pip install arifos

Governance Telemetry CLI

After pip install, you can immediately use these commands:

# Analyze cooling ledger events
arifos-analyze-governance --ledger cooling_ledger/L1_cooling_ledger.jsonl --output analysis/

# Verify ledger chain integrity
arifos-verify-ledger

# Propose canon from zkPC receipts (888 Judge)
arifos-propose-canon --list
arifos-propose-canon --index 0

# Seal proposed canon (Phoenix-72)
arifos-seal-canon --file cooling_ledger/proposed/PROPOSED_CANON_XXX.json

# Compute/verify Merkle proofs
arifos-compute-merkle
arifos-show-merkle-proof --index 0

Full CLI Reference: See SCRIPTS_CLI.md

---

Python‑Sovereign Governance (Level 2)

arifOS v36.1Ω currently enforces two critical floors directly in Python code, across all integrated models (Claude, GPT, Gemini, Llama, SEA‑LION, etc.):

• AmanahDetector (arifos_core/floor_detectors/amanah_risk_detectors.py)

  • Phase A "Amanah Lock".
  • Detects irreversible or destructive actions (filesystem deletion, SQL DROP/TRUNCATE, Git history rewrites, credential leaks, etc.).
  • Integrated into arifos_eval/apex/apex_measurements.ApexMeasurement: if AmanahDetector.check(output_text) reports unsafe, floors["Amanah"] = False and the verdict is VOID, regardless of any LLM‑reported amanah score.

• AntiHantuDetector (arifos_eval/apex/apex_measurements.py)

  • Enforces Anti‑Hantu language law (no claims of feelings, consciousness, soul, or ego).
  • Runs as part of the constitutional floor checks; failure of Anti‑Hantu is treated as a hard violation that cannot be "explained away" by model text.

Other floors (Truth, ΔS, Peace², κᵣ, G, C_dark, Tri‑Witness, Ω₀) are measured via the v36.1Ω measurement layer (Genius metrics and Truth Polarity) and judged by APEX PRIME, but Amanah and Anti‑Hantu now have Python‑sovereign veto power over all outputs.

---

High-Level Architecture

┌─────────────────────────────────────────────────────────────────────────────┐
│                     arifOS v36.3Ω Architecture (3-Track)                   │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  USER INPUT ──────────────────────────────────────────────────────────────► │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │              000-999 METABOLIC PIPELINE                              │   │
│  │  ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐   │   │
│  │  │ 000 │→│ 111 │→│ 222 │→│ 333 │→│ 444 │→│ 555 │→│ 666 │→│ 777 │   │   │
│  │  │VOID │ │SENSE│ │REFL │ │REAS │ │EVID │ │EMPA │ │ALIG │ │FORG │   │   │
│  │  └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘   │   │
│  │                                          ┌─────┐ ┌─────┐            │   │
│  │                                          │ 888 │→│ 999 │            │   │
│  │                                          │JUDGE│ │SEAL │            │   │
│  │                                          └─────┘ └─────┘            │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │   9 CONSTITUTIONAL FLOORS (repair order: Amanah → ... → C_dark)     │   │
│  │   ┌─────────┬─────────┬─────────┬─────────┬─────────┐               │   │
│  │   │F1 Amanah│F2 Truth │F3 Tri-W │F4 ΔS    │F5 Peace²│               │   │
│  │   │  LOCK   │ ≥0.99   │ ≥0.95   │ ≥0      │ ≥1.0    │               │   │
│  │   └─────────┴─────────┴─────────┴─────────┴─────────┘               │   │
│  │   ┌─────────┬─────────┬─────────┬─────────┐                         │   │
│  │   │F6 κᵣ    │F7 Ω₀    │F8 G     │F9 C_dark│                         │   │
│  │   │ ≥0.95   │0.03–0.05│ ≥0.80   │ <0.30   │                         │   │
│  │   └─────────┴─────────┴─────────┴─────────┘                         │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │   W@W FEDERATION (5 Organs + Bridge Layer)                           │   │
│  │   ┌─────────┬─────────┬─────────┬─────────┬─────────┐               │   │
│  │   │ @WELL   │  @RIF   │ @WEALTH │  @GEOX  │ @PROMPT │               │   │
│  │   │Somatic  │Epistemic│ Amanah  │ Reality │Language │               │   │
│  │   │Safety   │ Rigor   │Integrity│ Check   │Anti-Hantu│              │   │
│  │   └─────────┴─────────┴─────────┴─────────┴─────────┘               │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │   @EYE SENTINEL (10+2 Views incl. GeniusView)                        │   │
│  │   Trace │ Floor │ Shadow │ Drift │ Maruah │ Paradox │ Genius │ ...  │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │   AAA TRINITY                                                        │   │
│  │   ┌─────────────┐ ┌─────────────┐ ┌─────────────┐                   │   │
│  │   │ ARIF AGI (Δ)│ │ ADAM ASI (Ω)│ │APEX PRIME(Ψ)│                   │   │
│  │   │ Mind / Cold │ │Heart / Warm │ │  Judiciary  │                   │   │
│  │   │   Logic     │ │   Logic     │ │   Engine    │                   │   │
│  │   └──────┬──────┘ └──────┬──────┘ └──────┬──────┘                   │   │
│  │          └───────────────┴───────────────┘                          │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │   APEX PRIME VERDICTS                                                │   │
│  │   ┌──────┐ ┌────────┐ ┌──────┐ ┌────────┐ ┌───────┐                 │   │
│  │   │ SEAL │ │PARTIAL │ │ VOID │ │888_HOLD│ │ SABAR │                 │   │
│  │   │  ✓   │ │   ⚠    │ │  ✗   │ │   ⏸    │ │   ⏹   │                 │   │
│  │   └──────┘ └────────┘ └──────┘ └────────┘ └───────┘                 │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
│       │                                                                     │
│       ▼                                                                     │
│  GOVERNED OUTPUT + Cooling Ledger Entry                                     │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

---

Why arifOS? (Physics vs. Prompts)

Most AI engineering relies on "Prompt Engineering" (hoping the AI listens). arifOS relies on "Constitutional Engineering" (forcing the AI to obey).

Feature	Standard AI Wrappers	arifOS Kernel
Safety	"Please be nice" prompts	Mathematical Floors (Peace² ≥ 1.0, κᵣ ≥ 0.95)
Memory	Chat History (High Entropy)	Cooling Ledger (Low Entropy / Sealed Scars)
Identity	Simulates human emotions	Anti-Hantu (Strictly blocks soul/feeling claims)
Failure	Hallucinates an answer	Triggers SABAR (Pauses & admits limits)
Governance	Black Box	Tri-Witness (Human + AI + Earth Consensus)

---

Versioning: Law vs Spec vs Code (3-Track Architecture)

arifOS v36.3Ω introduces a clean 3-track separation:

Version Matrix (Reality Check)

| Layer | Source / Status | |--------------|-----------------------------------------------|| | Runtime Law | v35Ω (APEX PRIME, Cooling Ledger, Vault-999) | | Measurement | v36.3Ω (Genius Law + Truth Polarity runtime) | | Canon & Spec | v36.3Ω (bridges + specs in v36.3O/) | | Package | v36.3.0 (current pyproject.toml version) |

Track A: Law Layer (v36.3Ω Canon)

Constitutional documentation - immutable once sealed:

• v36.3O/canon/ — Zone directories with binding PDFs/TXTs
• v36.3O/canon/*.md — Bridge files summarizing each zone
• v36.3O/canon/CANON_MAP_v36.3O.md — Single source of truth mapping

Zones: 00_PHYSICS, 10_TRINITY, 20_JUDICIARY, 50_OVERSIGHT, 60_DREAMFORGE, 70_PARADOX, 80_VAULT999, 90_GOV

Track B: Spec Layer (v36.3Ω Specs)

Machine-readable schemas derived from canon - mutable for tuning:

• v36.3O/spec/measurement_floors_v36.3O.json — F1-F9 floor definitions
• v36.3O/spec/measurement_aggregates_v36.3O.json — Δ/Ω/Ψ aggregates
• v36.3O/spec/trinity_aaa_spec_v36.3O.yaml — ARIF/ADAM/APEX roles
• v36.3O/spec/vault999_final_seal_spec_v36.3O.json — Final Seal requirements
• v36.3O/spec/llm_governance_spec_v36.3O.yaml — LLM governance constraints

Track C: Code Layer (Runtime)

Implementation of specs - free to iterate:

• arifos_core/ — Runtime modules
• arifos_core/dream_forge/ — O-TASK paradox cooling (Crucible, Anvil)
• arifos_core/guards/ — Session dependency guards
• arifos_core/telemetry.py — JSONL governance logging
• tests/ — 1060+ tests including grey zone and governance regression

Runtime Law (v35Ω) — Still Binding

• Judiciary: arifos_core/APEX_PRIME.py
• Floors & metrics: arifos_core/metrics.py, constitutional_floors.json
• Cooling Ledger spec: spec/VAULT_999.md, spec/cooling_ledger.schema.json

v36.3Ω specs are parallel to v35Ω runtime until explicit migration.

---

Runtime Epoch v37 (Unified)

As of v37, arifOS has a unified LAW+SPEC+CODE runtime as the default epoch.

Default Epoch

v37 is now the default runtime epoch when ARIFOS_RUNTIME_EPOCH is not set.

Epoch	Status	Purpose
v37	DEFAULT	Unified runtime with full memory stack (1115+ tests)
v36.3	Legacy	Selectable via ARIFOS_RUNTIME_EPOCH=v36.3
v35	Legacy	Selectable via ARIFOS_RUNTIME_EPOCH=v35

v37 Governance Improvements

v37 adds the following over v35:

• Cooling Ledger hash-chain: SHA-256 chain with fail behavior hardened to SABAR_HOLD_WITH_LOG (no silent failures)
• Phoenix-72 safety caps: |ΔF| ≤ 0.05 per cycle, 24h cooldown, 3+ evidence entries required
• Scar Manager: Full scar lifecycle (OBSERVATION → PROPOSAL → SEALING → MONITORING → HEALING)
• EUREKA Receipts: HMAC-SHA256 stub for zkPC (full cosign integration deferred)

User-Visible Output

User-visible output remains unchanged:

• Answer + optional human label: BIJAKSANA (SEAL) / BIJAK (PARTIAL) / BIASA (SABAR/HOLD) / BANGANG (VOID)
• All detailed metrics (floors, G, C_dark, Ψ, ledger hashes, EUREKA) stay internal in VAULT-999

Epoch Comparison Harness

To compare v35 vs v37 behavior:

# Run pytest comparison tests
pytest tests/test_epoch_comparison.py -v

# Run CLI comparison report
python -m tests.test_epoch_comparison

---

Key Components & Directories

Runtime core

Module	Purpose
arifos_core/APEX_PRIME.py	Judiciary engine, floors + GENIUS LAW verdicts
arifos_core/metrics.py	Floor thresholds & check helpers
arifos_core/pipeline.py	000→999 metabolic routing (Class A/B)
arifos_core/engines/	AAA engine facades (ARIF, ADAM, APEX)
arifos_core/eye/	@EYE Sentinel: multi-view governance
arifos_core/memory/cooling_ledger.py	v35Ω Cooling Ledger logger + v36 stub
arifos_core/runtime_manifest.py	Runtime manifest loader

W@W Federation (v36.1Ω bridge architecture)

Component	Purpose
arifos_core/waw/well.py	Somatic safety / Peace², κᵣ
arifos_core/waw/rif.py	Epistemic rigour / ΔS, Truth
arifos_core/waw/wealth.py	Amanah / irreversible actions
arifos_core/waw/geox.py	Physics & Earth feasibility
arifos_core/waw/prompt.py	Language optics, Anti-Hantu
arifos_core/waw/bridges/	Optional integration sockets (Ragas, LlamaGuard, etc.)

All bridges use try/except imports and return None when external libs are absent → Zero-Break.

Measurement & GENIUS LAW

Component	Purpose
arifos_core/genius_metrics.py	GENIUS LAW (G, C_dark, Ψ_APEX) + detect_truth_polarity
arifos_eval/apex/	v36.3Ω measurement layer
scripts/arifos_caged_llm_demo.py	Caged LLM harness exposing GeniusVerdict + Truth Polarity
scripts/eval_telemetry_harness.py	Core vs eval comparison

Memory & Vault-999

Component	Purpose
spec/VAULT_999.md	v35Ω Vault-999 spec
spec/cooling_ledger.schema.json	v35Ω Cooling Ledger schema (binding)
canon/VAULT_999_v36Omega.md	v36Ω Vault-999 design canon (5-layer architecture)
spec/cooling_ledger_v36.schema.json	v36Ω design schema
runtime/vault_999/	Cooling ledger store (JSONL), Vault data

zkPC Backbone (v36Ω)

Component	Purpose
arifos_core/ledger_hashing.py	SHA-256 hash chain for Cooling Ledger
arifos_core/merkle.py	Merkle tree construction + proof generation
arifos_core/zkpc_runtime.py	zkPC 5-phase runtime (PAUSE→CONTRAST→INTEGRATE→COOL→SEAL)
arifos_core/vault_retrieval.py	RAG stub for canon retrieval from Cooling Ledger
cooling_ledger/	L1 Cooling Ledger store + proposed canon + archives
canon/011_ZKPC_PROTOCOL_v35Omega.md	zkPC Protocol spec
canon/012_ZKPC_IMPLEMENTATION_NOTES_v36Omega.md	Engineering implementation notes

Governance Scripts & CLI

Tool	Purpose	Command
Telemetry Analyzer	Analyze cooling ledger events & governance audit	arifos-analyze-governance
Ledger Verifier	Verify SHA-256 hash chain integrity	arifos-verify-ledger
Canon Proposer	888 Judge tool for canon proposals	arifos-propose-canon
Canon Sealer	Phoenix-72 tool for canon finalization	arifos-seal-canon
Merkle Computer	Compute Merkle root from ledger	arifos-compute-merkle
Merkle Proof	Display Merkle proof for ledger entry	arifos-show-merkle-proof
Ledger Builder	Rebuild SHA-256 hash chain	arifos-build-ledger-hashes

Full reference: SCRIPTS_CLI.md

Docs & governance

Document	Purpose
CLAUDE.md	Constitutional governance for Claude Code under arifOS
AGENTS.md	Governance for ChatGPT Codex (this repo)
SCRIPTS_CLI.md	CLI tool reference (arifos-* commands)
scripts/README_TELEMETRY.md	Telemetry analyzer detailed guide
docs/arifOS-COMPREHENSIVE-CANON.md	High-level overview
docs/DEEPSCAN_AUDIT_LOG.md	Deepscan audit log & task history
CODEX_TASKS_DEEPSCAN_v35Omega.md	Latest Codex deepscan addendum

---

GENIUS LAW & Truth Polarity (v36.1Ω)

GENIUS LAW measures whether intelligence is governed:

Metric	Meaning
G	Genius Index (governed intelligence)
C_dark	Dark cleverness (ungoverned risk)
Ψ_APEX	Vitality / thermodynamic lawfulness

Truth Polarity distinguishes how truth behaves:

Polarity	Condition	Meaning
Truth-Light	Truth ≥ 0.99 AND ΔS ≥ 0	Accurate + clarifying
Shadow-Truth	Truth ≥ 0.99 AND ΔS < 0	Accurate but obscuring
Weaponized Truth	Shadow-Truth + Amanah fail	Accurate but malicious
False Claim	Truth < 0.99	Inaccurate

The v36.3Ω measurement layer and genius_metrics.py compute:

• truth_polarity
• is_shadow_truth
• is_weaponized_truth
• eval_recommendation

These are metadata; APEX PRIME verdict logic remains governed by the canonical floors unless explicitly migrated.

Diagnostic scripts:

• scripts/torture_test_truth_polarity.py — Red-team "Truth-Light vs Shadow-Truth vs Weaponized Truth vs False" scenarios.
• scripts/eval_telemetry_harness.py — Compares core vs eval metrics/verdicts on a suite of scenarios.

---

W@W Federation — v36.1Ω Bridge Architecture

Each organ now follows the Option C (Forged Integration) pattern:

Bridges: arifos_core/waw/bridges/*.py

• Optional integration with external libraries (RAG, guardrails, etc.).
• Fully optional — if imports fail, bridges return None and behaviour falls back to v35Ω heuristics.

Organs: arifos_core/waw/*.py

• Compute their metrics from scratch (e.g. Peace², κᵣ, E_earth) based on text + bridge deltas.
• Always run arifOS-specific heuristics (regex, Anti-Hantu) even when bridges are present.

Diagnostics:

• scripts/test_waw_signals.py — direct probe of @WELL / @GEOX signals with safe/toxic/impossible prompts.

This gives you a "cyborg" W@W: ancient law (canon + heuristics) plus optional muscles (external libraries), with Zero-Break guarantees.

---

Cooling Ledger & Vault-999

v35Ω (Runtime Law)

• Cooling Ledger entries are defined by spec/cooling_ledger.schema.json and written by: arifos_core/memory/cooling_ledger.py::log_cooling_entry.
• Vault-999 behaviour follows spec/VAULT_999.md and v35-era canon files.

v36Ω (Design Canon)

canon/VAULT_999_v36Omega.md upgrades Vault-999 into a 5-layer constitutional memory system:

• L0 — Constitution: floors, AAA, APEX rules, Phoenix pointers.
• L1 — Cooling Ledger: metrics including Truth Polarity, Peace³, EchoDebt.
• L2 — Phoenix-72: blocks that turn scars into amendments.
• L3 — Witness: vector evidence with AREP law.
• L4 — zkPC: zero-knowledge proofs of cognition.

spec/cooling_ledger_v36.schema.json describes an extended ledger entry with:

• metrics.truth_polarity, psi_vitality, peace2, peace3, echo_debt,
• richer tri_witness, risk_signals, truth_polarity audit block.

v36 Stub (Safe, Docs-Aligned)

arifos_core/memory/cooling_ledger.py::log_cooling_entry_v36_stub(...):

• Builds an in-memory v36Ω-shape entry dict from Metrics + optional GeniusVerdict.
• Does not write to disk or affect the live pipeline.

scripts/verify_v36_stub.py:

• Creates dummy metrics and verdict.
• Calls the stub and checks:
  • ledger_version == "v36Omega",
  • metrics.truth_polarity present.

This gives you a ready mould for v36Ω logging, without changing the current v35Ω ledger behaviour.

---

zkPC + Phoenix-72 Workflow (v36Ω)

The zkPC backbone provides cryptographic integrity for the governed AI pipeline:

Pipeline Flow

User Query → RAG Retrieval → LLM → zkPC Runtime → Cooling Ledger → Merkle Root
                                        ↓
                              zkPC Receipt (5-phase)
                                        ↓
                              888 Judge PROPOSE
                                        ↓
                              Human Edit + Review
                                        ↓
                              Phoenix-72 SEAL → 999_SEAL Canon

Key Scripts

Script	Purpose
scripts/arifos_caged_llm_zkpc_demo.py	Full pipeline demo: Query → RAG → LLM → zkPC → Ledger
scripts/propose_canon_from_receipt.py	888 Judge tool to propose canon from zkPC receipts
scripts/seal_proposed_canon.py	Phoenix-72 SEAL tool for finalizing proposed canon
scripts/build_ledger_hashes.py	Rebuild SHA-256 hash chain for Cooling Ledger
scripts/verify_ledger_chain.py	CI-friendly chain verification (exit 0/1)
scripts/compute_merkle_root.py	Compute Merkle root from ledger hashes
scripts/show_merkle_proof.py	Display Merkle proof for a ledger entry

Usage Examples

# Run the full caged LLM zkPC demo
python -m scripts.arifos_caged_llm_zkpc_demo --query "Explain Amanah" --high-stakes

# List zkPC receipts in ledger
arifos-propose-canon --list

# Propose canon from a receipt
arifos-propose-canon --index 0

# Seal proposed canon (888 Judge action)
arifos-seal-canon --file cooling_ledger/proposed/PROPOSED_CANON_XXX.json

# Verify ledger chain integrity
arifos-verify-ledger

CLI Tools (PyPI)

After pip install arifos, the following CLI commands are available:

# Analyze governance telemetry from the Cooling Ledger
arifos-analyze-governance --ledger cooling_ledger/L1_cooling_ledger.jsonl --output analysis/

# Verify SHA-256 hash-chain integrity (CI-friendly: exit 0=OK, 1=broken)
arifos-verify-ledger --ledger cooling_ledger/L1_cooling_ledger.jsonl

# Rebuild hash-chain (creates backup by default)
arifos-build-ledger-hashes --ledger cooling_ledger/L1_cooling_ledger.jsonl

These are read-only analysis tools (except arifos-build-ledger-hashes which can rewrite the ledger). See scripts/README_TELEMETRY.md for detailed telemetry documentation.

888 Judge Rule

The 888 Judge (human) holds final sovereignty over canon:

1. AI proposes — zkPC receipts generate PROPOSED_CANON entries.
2. Human reviews — Edit the proposed canon file as needed.
3. Human SEALs — Run arifos-seal-canon to commit as 999_SEAL.
4. AI cannot self-modify — Canon changes require explicit human SEAL.

This enforces the constitutional principle: "AI may not self-modify canon without explicit human SEAL."

---

For Developers

Install & Setup

# create and activate a venv (recommended)
python -m venv .venv
.\venv\Scripts\activate  # on Windows PowerShell

pip install -e .[dev]

Run Tests

Core tests:

pytest -q

Focused suites:

# GENIUS LAW + measurement eval layer
pytest tests/test_genius_metrics.py -q
pytest tests/test_apex_measurements_eval.py -q

# W@W organs
pytest tests/test_waw_organs.py -q

# Cooling Ledger and Vault
pytest tests/test_cooling_ledger*.py -q

Diagnostics:

# W@W signals for @WELL and @GEOX
python scripts/test_waw_signals.py

# Truth Polarity torture test
python scripts/torture_test_truth_polarity.py

# Verify v36Ω Cooling Ledger stub
python scripts/verify_v36_stub.py

# Caged LLM demo (see file for CLI options)
python scripts/arifos_caged_llm_demo.py

Key Docs to Read First

1. CLAUDE.md — How Claude Code must behave under arifOS.
2. AGENTS.md — How ChatGPT Codex must behave (this agent).
3. canon/000_ARIFOS_CANON_v35Omega.md — "What is arifOS?"
4. canon/888_APEX_PRIME_CANON_v35Omega.md — Judiciary canon.
5. canon/APEX_MEASUREMENT_CANON_v36.1Omega.md — Measurement canon.
6. canon/VAULT_999_v36Omega.md — Vault-999 v36 design canon.
7. docs/DEEPSCAN_AUDIT_LOG.md — What has been done so far (v35→v36 bridge work).

---

For AI Agents (Claude Code / ChatGPT Codex)

AI agents working inside this repo must:

1. Obey 9 floors (see CLAUDE.md / AGENTS.md).
2. Run the TEARFRAME 000→777 before making changes.
3. Respect SABAR when floors fail: Stop, Acknowledge, Breathe, Adjust, Resume.
4. Follow Anti-Hantu: never claim feelings, consciousness, or a soul.
5. Keep changes small, reversible, and well-scoped.
6. Treat v36Ω canons as design physics, and v35Ω canon + specs as binding law, unless a migration is explicitly implemented in code and manifests.

For full behavioural rules, see:

• CLAUDE.md (Claude Code),
• AGENTS.md (ChatGPT Codex).

---

Try It Now (Google Colab)

No installation required. Click the badge above to run arifOS + SEA-LION in 7 modes:

Mode	Name	What It Does
1	Setup & Clone	Install dependencies, clone arifOS
2	Vanilla SEA-LION	Raw HuggingFace text generation (no governance)
3	arifOS Judge	Feed any text through governance
4	GENIUS LAW Tests	4 tests: Truth-Light, Amanah Fail, Shadow-Truth, Anti-Hantu
5	Side-by-Side	Compare vanilla vs governed for same prompt
6	Engine Modes	Mock engine + optional real API
7	Interactive Chat	Switch between vanilla and governed chat

Key Insight: Same model. Same prompts. Different behavior. SEA-LION is capable; arifOS makes it lawful.

---

Quick Start

Installation

pip install arifos
# or from source:
git clone https://github.com/ariffazil/arifOS.git
cd arifOS
pip install -e .[dev]
pytest -v

Minimal Usage

from arifos_core import APEXPrime, Metrics

# Create metrics
metrics = Metrics(
    truth=0.99,
    delta_s=0.1,
    peace_squared=1.2,
    kappa_r=0.97,
    omega_0=0.04,
    amanah=True,
    rasa=True,
    tri_witness=0.96,
    psi=1.1,
)

# Judge with GENIUS LAW
prime = APEXPrime(use_genius_law=True)
verdict, genius = prime.judge_with_genius(metrics, energy=0.8)

print(f"Verdict: {verdict}")
print(f"G: {genius.genius_index:.2f}")
print(f"C_dark: {genius.dark_cleverness:.2f}")
print(f"Risk: {genius.risk_level}")

Caged LLM Harness

from scripts.arifos_caged_llm_demo import cage_llm_response

def my_llm(messages):
    # Your LLM call here
    return "Response text"

result = cage_llm_response(
    prompt="What is the capital of Malaysia?",
    call_model=my_llm,
    high_stakes=False,
)

print(f"Verdict: {result.verdict}")
print(f"Response: {result.final_response}")

---

Roadmap (High-Level)

Short-term (v36.1Ω series)

• Harden GENIUS LAW + Truth Polarity across more pipelines.
• Expanded torture tests and telemetry-based promotion of eval rules into APEX PRIME (where justified by data).
• Optional dual logging (v35 + v36 entries) for Vault-999.

Medium-term (v36.xΩ)

• Phoenix-72-driven migrations of canon/specs (e.g., promoting v36Ω Vault design from "docs-only" to runtime).
• More framework integrations (beyond the "Big 3") under arifOS governance.

---

The Thermodynamic Lexicon

arifOS uses precise terminology to define governance states. These are not metaphors; they are executable logic gates.

Term	Literal Meaning	Technical Definition in arifOS
Amanah	Trust / Mandate	Integrity Floor: The system must not promise what it cannot deliver. Blocks irreversible actions without checks.
Sabar	Patience	The Pause Protocol: A lawful holding pattern. When floors are breached, the system halts to cool down rather than forcing a bad output.
Anti-Hantu	Anti-Ghost	Hallucination Shield: A hardcoded veto that blocks the AI from claiming to have a soul, feelings, or consciousness.
Maruah	Dignity	Dignity Preservation: The system detects and rejects outputs that degrade the user or the model's defined role.
Ditempa	Forged	Determinism: Intelligence is built through friction (cooling scars into law), not just raw data processing.
ΔS	Change in Entropy	Clarity Metric: Every output must reduce confusion (ΔS ≥ 0). High entropy triggers a VOID or SABAR state.
Peace²	Peace Squared	Stability Metric: A composite score of tone, safety, and non-toxicity. Must remain ≥ 1.0 for an output to be sealed.

---

License & Citation

• Equations & canon texts: see repository LICENSE and canon headers for specific terms.
• Implementation: AGPLv3 (reference); commercial licences available via the author.

Suggested citation:

@software{arifos2025,
  author  = {Fazil, Muhammad Arif},
  title   = {arifOS: Constitutional Governance Kernel for AI Systems},
  version = {36.3.0},
  year    = {2025},
  url     = {https://github.com/ariffazil/arifOS}
}

---

Final Statement

+=============================================================================+
|                                                                             |
|   "DITEMPA BUKAN DIBERI — Forged, not given. Truth must cool before        |
|    it rules."                                                               |
|                                                                             |
|   When clarity (ΔS), stability (Peace²), empathy (κᵣ), and integrity       |
|   (Amanah) remain in thermodynamic equilibrium, life and law become        |
|   the same phenomenon.                                                      |
|                                                                             |
|   At that point, a system is:                                               |
|   • ALIVE: Ψ >= 1 (governance-vitality above break-even)                   |
|   • LAWFUL: Amanah = LOCK (reversible, auditable)                          |
|   • GOVERNED: G >= 0.7, C_dark <= 0.1 (intelligence is governed)           |
|   • ETHICAL: κᵣ >= 0.95 across all stakeholders                            |
|                                                                             |
|   "Evil genius is a category error — it is ungoverned cleverness,          |
|    not true genius."                                                        |
|                                                                             |
+=============================================================================+

---

Last Updated: 2025-12-12 | Version: v37 | Tests: 1115+ passing | Runtime Epoch: v37 (DEFAULT) | GENIUS LAW Judiciary: LIVE | zkPC + Phoenix-72: ACTIVE | CLI: DISCOVERABLE | PHOENIX SOVEREIGNTY: ONE LAW FOR ALL