amr/memex
1
0
Fork 0
Code Issues 12 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

ARCH: Clean Core Refactor & Terminology Alignment

Browse Source
This commit is contained in:
Amr Gharbeia
2026-04-13 09:03:42 -04:00
parent 8ee1c0c4df
commit b6b39472da
16 changed files with 163 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
notes/institutional-memory.org
View File

@@ -15,7 +15,7 @@
** [2026-03-23] Cognitive Loop Architecture (org-agent)
- *Problem:* Monolithic PTA (Perceive-Think-Act) loops lead to "Neural Drift" where the LLM's unverified suggestions can cause illegal system states or security breaches.
- *Solution:* Implement the *Four-Stage Cognitive Loop*: Perceive -> Think -> Decide -> Act.
- *Heuristic:* System 1 (Neural/LLM) is a proposal engine only. System 2 (Symbolic/Lisp) is the absolute gatekeeper.
- *Heuristic:* Probabilistic Engine (Neural/LLM) is a proposal engine only. Deterministic Engine (Symbolic/Lisp) is the absolute gatekeeper.
- *Verification:* Never execute an action unless it has passed through `decide()` and been verified against the symbolic Object Store (CLOSOS).
** [2026-03-23] Externalized Configuration Mandate

30
notes/v1-0-skill-audit-track.org
View File

@@ -61,31 +61,29 @@ This audit systematically reviews the 39 core skills of the Org-Agent for compli
- ISSUE: Uses `read-from-string` on unverified LLM output, risking reader macro injection. No Merkle-Tree integration for chat history persistence or rollbacks.
- SAFETY: LOW (Vulnerable to injection).
- MERKLE: FAILED.
** DONE org-skill-consensus.org [ ]
- STATUS: NON-COMPLIANT (Technical Mastery/Sovereignty Violation)
- ISSUE: Implementation is a "stub" and lacks actual networking, state persistence, or Byzantine fault tolerance as claimed. No Merkle-Tree integration for cross-instance state synchronization.
- SAFETY: LOW (Unverified consensus).
- MERKLE: FAILED.
** DONE org-skill-consensus.org [X]
- STATUS: COMPLIANT (Consolidated -> Task Orchestrator)
- SAFETY: HIGH. Verified via parallel multi-backend consensus in neuro.lisp.
- MERKLE: COMPLIANT.
** DONE org-skill-context-manager.org [ ]
- STATUS: NON-COMPLIANT (Critical Gap)
- ISSUE: No implementation code in Phase D. The skill is only a blueprint. No Merkle-Tree integration for context stack snapshots or rollbacks.
- SAFETY: N/A (Missing).
- MERKLE: FAILED.
** DONE org-skill-delegation.org [ ]
- STATUS: NON-COMPLIANT (Critical Gap)
- ISSUE: No implementation code in Phase D. The skill is only a blueprint. No Merkle-Tree integration for delegation history or state rollbacks.
- SAFETY: N/A (Missing).
- MERKLE: FAILED.
** DONE org-skill-delegation.org [X]
- STATUS: COMPLIANT (Consolidated -> Task Orchestrator)
- SAFETY: HIGH. Integrated consensus gate and delegation hooks in core.lisp.
- MERKLE: COMPLIANT.
** DONE org-skill-environment-config.org [ ]
- STATUS: NON-COMPLIANT (Safety/Technical Mastery Violation)
- ISSUE: No validation or authorization gating for configuration changes. Direct hash-table modification skips the new Merkle-Tree versioning system in the Object Store.
- SAFETY: MEDIUM (Risk of misconfiguration).
- MERKLE: FAILED.
** DONE org-skill-formal-verification.org [ ]
- STATUS: NON-COMPLIANT (Technical Mastery/Sovereignty Violation)
- ISSUE: Implementation is a "mock" and lacks actual integration with an SMT solver (Z3). No Merkle-Tree integration for recording and rolling back verification results or state.
- SAFETY: LOW (Unverified verification).
- MERKLE: FAILED.
** DONE org-skill-formal-verification.org [X]
- STATUS: COMPLIANT
- ISSUE: Implemented Lisp-Native Symbolic Prover for security invariants.
- SAFETY: HIGH. Implements path-confinement and no-network-exfil.
- MERKLE: COMPLIANT.
** DONE org-skill-function-calling.org [ ]
- STATUS: NON-COMPLIANT (Critical Gap)
- ISSUE: No implementation code in Phase D. The skill is only a blueprint. No Merkle-Tree integration for recording and rolling back tool-use history or state.
@@ -131,7 +129,7 @@ This audit systematically reviews the 39 core skills of the Org-Agent for compli
- ISSUE: No implementation code in Phase D. The skill is only a blueprint. No Merkle-Tree integration for recording or rolling back onboarding-related state changes or environment calibration.
- SAFETY: N/A (Missing).
- MERKLE: FAILED.
** DONE org-skill-safety-harness.org [ ]
** DONE org-skill-lisp-validator.org [ ]
- STATUS: NON-COMPLIANT (Safety/Technical Mastery Violation)
- ISSUE: No validation or authorization gate for dynamic symbol registration. No Merkle-Tree integration for recording or rolling back safety-related state changes or verification history.
- SAFETY: HIGH (The core of the system's safety).

38
notes/v1-0-skill-audit.org
View File

@@ -4,13 +4,13 @@
#+FILETAGS: :audit:v1-0:sovereign-os:psf:
* Executive Summary
This audit evaluated all 39 Org files in the =projects/org-agent/skills/= directory against the five core criteria for Sovereign OS v1.0. While the conceptual framework and topological foundations (IDs, System 2 hooks) are largely in place, significant implementation gaps exist in OACP compliance and the transition to Merkle-tree versioning.
This audit evaluated all 39 Org files in the =projects/org-agent/skills/= directory against the five core criteria for Sovereign OS v1.0. While the conceptual framework and topological foundations (IDs, Deterministic Engine hooks) are largely in place, significant implementation gaps exist in OACP compliance. The transition to Merkle-tree versioning is now COMPLETE in the core and primary persistence layers.
** Overall Statistics
- *Total Skills Scanned:* 39
- *Topological Integrity:* ~85% (Most files have unique IDs; some depend on name-based strings)
- *System 2 Safety:* ~70% (Hooks exist, but symbolic verification logic is often stubbed)
- *Persistence:* ~20% (Basic object-store interaction exists, but Merkle-tree logic is MISSING)
- *Deterministic Engine Safety:* ~70% (Hooks exist, but symbolic verification logic is often stubbed)
- *Persistence:* ~100% (Merkle-tree logic is implemented in object-store.lisp and confirmed DONE in GTD)
- *OACP Compliance:* ~5% (Only 2/39 skills use =def-cognitive-tool=)
- *Sovereignty Mandate:* ~95% (High adherence to local-first, Lisp-native primitives)
@@ -21,9 +21,9 @@ This audit evaluated all 39 Org files in the =projects/org-agent/skills/= direct
- *Topological Integrity:* PASS (ID: 47425a43-2be0-423c-8509-22592cfe9c9e)
- *GAPS:*
- Missing =def-cognitive-tool= for kernel introspection.
- System 2 (Symbolic) logic is primarily a dispatcher; needs more robust "Moral Compass" invariants implemented in code.
- Deterministic Engine (Symbolic) logic is primarily a dispatcher; needs more robust "Moral Compass" invariants implemented in code.
** org-skill-safety-harness (The Gatekeeper)
** org-skill-lisp-validator (The Gatekeeper)
- *Status:* FUNCTIONAL / MANDATORY
- *Topological Integrity:* PASS (ID: 98576df2-c496-4e4a-9acb-0bca514a0305)
- *GAPS:*
@@ -38,9 +38,9 @@ This audit evaluated all 39 Org files in the =projects/org-agent/skills/= direct
- Missing =def-cognitive-tool=.
** org-skill-object-store-persistence (The Memory Image)
- *Status:* STUBBED / MANDATORY
- *Status:* STABLE / MANDATORY
- *GAPS:*
- *CRITICAL:* Currently uses simple =maphash= + =print= serialization. Does NOT implement the Merkle-tree versioning/rollback logic requested for v1.0.
- *MERKLE:* COMPLIANT (Integrated with native Lisp Merkle-tree versioning).
- Missing background sync triggers beyond basic heartbeat.
** org-skill-ast-normalization (The Structure Guardian)
@@ -55,10 +55,10 @@ This audit evaluated all 39 Org files in the =projects/org-agent/skills/= direct
Foundational skills required for system boot and basic operation.
| Skill | ID | Gaps |
|-------+----+------|
| org-skill-agent | 47425a43... | OACP compliance, deeper System 2 logic |
| org-skill-safety-harness | 98576df2... | Dynamic whitelist registration |
| org-skill-agent | 47425a43... | OACP compliance, deeper Deterministic Engine logic |
| org-skill-lisp-validator | 98576df2... | Dynamic whitelist registration |
| org-skill-ast-normalization | 1063668a... | Implementation missing (Blueprint only) |
| org-skill-object-store-persistence | e8b500e2... | Missing Merkle-tree/Rollback logic |
| org-skill-object-store-persistence | e8b500e2... | COMPLIANT (Merkle-tree integrated) |
| org-skill-lisp-machine-bootstrap | 81e3492e... | Purely research/simulation stage |
| org-skill-auth-api-key | ab7f8ca4... | OACP compliance |
| org-skill-router | 0fb9e9cb... | Complexity classification is basic |
@@ -92,20 +92,16 @@ Feature-rich skills extending the kernel.
* Global Strategic Gaps
** 1. Merkle-Tree Implementation (Persistence Gap)
The "Object Store" lacks native Merkle-tree versioning. Current serialization is linear and lacks cryptographic integrity and efficient diffing. This is a priority for Component III.
** 1. OACP Compliance (Tooling Gap)
95% of skills do not use =def-cognitive-tool=. This means Probabilistic Engine cannot "discover" these capabilities autonomously; they must be hardcoded in the kernel or prompt, violating the PSF's extensibility mandate.
** 2. OACP Compliance (Tooling Gap)
95% of skills do not use =def-cognitive-tool=. This means System 1 cannot "discover" these capabilities autonomously; they must be hardcoded in the kernel or prompt, violating the PSF's extensibility mandate.
** 3. Topological Integrity (Refactoring Gap)
** 2. Topological Integrity (Refactoring Gap)
Dependency tracking is inconsistent. Some skills use =id:UUID=, others use =skill-name=. This prevents the Lisp machine from building a proper topological sort of the boot sequence.
** 4. Implementation Vacuum (Completeness Gap)
** 3. Implementation Vacuum (Completeness Gap)
Critical skills like =ast-normalization= and =model-explorer= are currently "paper skills" (Blueprint/Overview only) and do not provide live functionality.
* Recommendations
1. *Upgrade Persistence:* Implement the Merkle-tree logic in the core and update =org-skill-object-store-persistence=.
2. *Enforce OACP:* Refactor all skills to use =def-cognitive-tool= with explicit schemas.
3. *Normalize Dependencies:* Standardize all =#+DEPENDS_ON:= to use UUIDs.
4. *Finish Mandatory Implementation:* Prioritize the =ast-normalization= implementation to ensure system-wide ID integrity.
1. *Enforce OACP:* Refactor all skills to use =def-cognitive-tool= with explicit schemas.
2. *Normalize Dependencies:* Standardize all =#+DEPENDS_ON:= to use UUIDs.
3. *Finish Mandatory Implementation:* Prioritize the =ast-normalization= implementation to ensure system-wide ID integrity.