mindforge-cc 5.6.0 → 6.0.0-alpha

package/docs/architecture/V5-ENTERPRISE.md

@@ -13,59 +13,72 @@ The FIM transitions MindForge from local knowledge silos to a shared organizatio
 - **Enterprise Resilience & Governance (v5.1.0)**: A high-availability central hub for sharing high-confidence agentic findings across the entire enterprise.
 - **ZTAI-Signed Provenance**: Every piece of knowledge in the mesh is cryptographically tied to the DID of the agent that generated it.
 
-### Pillar II: Agentic Policy Orchestrator (APO)
+### Pillar II: Agentic Policy Orchestrator (APO) — CADIA Engine (v6.0.0 Alpha)
 
-# MindForge Governance Guide (v5.1.0)
-MindForge v5.1.0 introduces a non-bypassable, intent-level governance layer that evaluates every autonomous wave against organizational security policies.
+# MindForge Governance Guide (v6.0.0)
+MindForge v6.0.0 introduces **Context-Aware Dynamic Impact Analysis (CADIA)**, a non-bypassable, architectural governance layer that evaluates every autonomous wave against organizational security and risk policies.
 
-- **Policy-as-Code (PaC)**: Security rules are defined in declarative JSON/YAML schemas, enabling version-controlled governance.
-- **Real-Time Intent Interception**: The `AutoRunner` intercepts swarm intents (Action, Resource, DID, Tier) before execution.
-- **Dynamic RBAC Mapping**: v5.1.0 automatically maps ZTAI Trust Tiers to project roles based on an agent's **Zero-Trust Agentic Identity (ZTAI)** trust tier.
-- **Fail-Safe Governance**: "Default Deny" posture for sensitive operations (API key access, infra modification, etc.).
+- **Policy-as-Code (PaC)**: Security rules are defined in declarative JSON schemas, enabling version-controlled governance.
+- **Dynamic Blast Radius Analysis**: Calculates real-time architectural risk based on file influence, session entropy (multi-file modification speed), and goal alignment.
+- **Session Entropy Guardrails**: Risk increases logarithmically as an agent touches more files, preventing "Rogue Wave" mass corruption.
+- **ZTAI-Trust Weighting**: Senior agents (Tier 3) gain "Architectural Credit," while Tier 1-2 agents are kept under strict risk caps.
+- **Reasoning Proof Bypass**: Tier 3 agents can override high-risk blocks by providing a cryptographically signed "Reasoning Proof."
+- **Enterprise Audit Log**: All evaluations are logged to `.planning/RISK-AUDIT.jsonl` for compliance reporting.
 
-### Pillar III: Predictive Agentic Reliability (PAR)
+### Pillar III: Predictive Agentic Reliability (PAR) (v5.5.0)
 
-The PAR layer addresses reasoning decay and execution drifting in long-running autonomous sessions.
+The PAR layer addresses reasoning decay and execution drifting in long-running autonomous sessions by monitoring the "logic-space" of the agent.
 
-- **Loop Detection (S03/S04)**: Advanced `StuckMonitor` patterns for Semantic Mirroring and Infinite Decomposition.
+- **Reasoning Entropy Scoring (RES)**: The `NexusTracer` calculates a semantic similarity score (Jaccard-based) for every reasoning step. A high score indicates thought stagnation or circular logic.
+- **Proactive Loop Detection**: If more than 3 consecutive thoughts fall below the entropy threshold, a `STAGNATION_DETECTED` event is triggered.
+- **Steering Vector Injection**: Upon loop detection, `TemporalHindsight` generates a "Steering Vector" — a high-priority system instruction that forces the agent to pivot its logic or escalate to a human.
 - **Context Density Refactorer**: Proactive context summarization and handoff when reasoning-to-action density falls below 30%.
-- **C2C Arbitrage**: Confidence-to-Cost (C2C) threshold gating to prevent low-value autonomous drifts.
-- **Self-Healing Reasoning**: Automated triggering of "hindsight injection" when stuck patterns are detected.
 
-### Pillar IV: Supply Chain Trust (ZTS)
+### Pillar IV: Supply Chain Trust (ZTS) (v5.6.0)
 
-The ZTS layer ensures the integrity of the agentic supply chain, from the models used to the skills executed.
+The ZTS layer ensures the absolute integrity of the agentic supply chain, cryptographically locking every skill and model in the reasoning path.
 
-- **Agentic SBOM**: Automated `MANIFEST.sbom.json` generation tracking every model and skill signature in the reasoning chain.
+- **Binary Runtime Attestation**: The `SkillValidator` performs Just-In-Time (JIT) attestation. Every `SKILL.md` is hashed and verified against signed signatures before being loaded into the agent's context.
+- **ZTAI-Locked Registry**: Skills are signed using Tier 3 Decentralized Identifiers (DIDs) via HSM-simulated Secure Enclaves. Unauthorized skill modifications result in immediate execution blocking.
 - **7-Dimension Certification (7D)**: Weighted scoring system (Schema, Triggers, Security, Clarity, etc.) for skill validation.
-- **Enterprise-Grade Enforcement**: Strict `--enterprise` mode requirement for 7.0/10.0 minimum certification score.
-- **Skill Telemetry**: Real-time auditing of skill performance and reliability metrics.
+- **Agentic SBOM**: Automated `MANIFEST.sbom.json` generation tracking every model and skill signature in the reasoning chain.
 
 ---
 
-### Pillar V: Multi-Cloud Arbitrage & Hedging
+### Pillar V: Multi-Cloud Arbitrage & Hedging (v5.7.0)
+
+The Multi-Cloud layer ensures absolute availability and intelligence-first routing by dynamically mapping task taxonomies to the most performant providers.
+
+- **Task-to-Model Affinity Matrices**: Persistent tracking of success probability per model and task type (refactor, test, audit, etc.) in `performance-stats.json`.
+- **Intelligence-First Routing**: The `CloudBroker` weights routing scoring by success probability (50%), cost (30%), and latency (20%), ensuring the most capable model is selected for the specific task taxonomy.
+- **Automated Feedback Integration**: `WaveFeedbackLoop` automatically records task outcomes back into the performance repository, enabling the system to learn from cross-cloud execution history.
+- **Provider Fallback Protocol**: Automated "Hedging" that migrates agent context to a secondary cloud provider if 5xx errors or high latencies are detected.
+
+### Pillar VI: Sovereign Reason Enclaves (SRE) (v5.8.0)
 
-The Multi-Cloud layer ensures absolute availability and cost-efficiency by dynamically load-balancing across multiple AI providers.
+SRE provides a "Confidential Computing" environment for the agent's internal thought process, protected by cryptographic Zero-Knowledge (ZK) audit trails.
 
-- **Dynamic Routing**: Real-time arbitrage across Vertex AI, AWS Bedrock, and Azure based on current latency and cost weights.
-- **Provider Fallback Protocol**: Automated "Hedging" that migrates agent context to a secondary cloud provider (e.g., Anthropic to Google) if 5xx errors or high latencies are detected.
-- **Chaos Mode (Beast Mode)**: Built-in reliability testing that simulates provider dropouts to verify the robustness of the fallback loops.
+- **ZK-Proof Compliance Certificates**: Simulated zero-knowledge proofs (signed by System DID) generated for every confidential reasoning session in `SREManager`.
+- **Privacy-Preserving Auditing**: `NexusTracer` replaces raw, sensitive thought traces in `AUDIT.jsonl` with verifiable cryptographic certificates, protecting proprietary reasoning logic.
+- **Non-Custodial Verification**: New `verifyZKProof` utility allows auditors to cryptographically verify that an agent followed policy within the enclave without ever seeing the raw thoughts.
+- **Thought-Chain Sanitization**: Automated redaction of sensitive patterns (keys, credentials, PII) from reasoning traces before persistent certificate generation.
 
-### Pillar VI: Sovereign Reason Enclaves (SRE)
+### Pillar VII: Interactive Temporal Steering (NEXUS)
 
-SRE provides a "Confidential Computing" environment for the agent's internal thought process, protecting sensitive intellectual property.
+NEXUS transforms the `NexusTracer` from a passive observer into an active temporal control plane, enabling sub-second state reconstruction and hindsight injection.
 
-- **TEE-Simulated Reasoning**: Tier 3 workloads execute reasoning traces in high-isolation simulated enclaves with zero-visibility to the global log.
-- **Thought-Chain Sanitization**: Automatically redacts sensitive patterns (keys, credentials, PII) from the reasoning trace before persistent audit.
-- **Enclave Multi-Tenancy**: Isolated reason-space per project wave, ensuring that cross-stream reasoning cannot leak state or logic.
+- **Temporal History Slider**: Real-time navigation through the agent's reasoning-space, allowing for high-fidelity state inspection at any point in the execution wave.
+- **Hindsight Injection Protocol**: Allows for the injection of "Steering Vectors" into past reasoning nodes to re-orient the agent's logic without a full session restart.
+- **Rollback-to-State**: Automated state reconstruction that resets the environment and `.planning/` directory to match a specific `auditId` signature.
+- **Dynamic Handover (DHH)**: Integrated confidence-based human escalation when reasoning entropy remains high after steering.
 
-### Pillar VII: Dynamic Human-Agent Handover (DHH)
+### Pillar VIII: Agentic Revenue Operations (AgRevOps)
 
-DHH creates a seamless bridge between fully autonomous execution and high-precision human steering.
+AgRevOps treats agentic compute as a first-class financial and governance asset, providing real-time ROI and accountability.
 
-- **Nexus State Bundles**: Automated "Context Freeze" and packaging of memory, diffs, and reasoning traces when agent confidence drops below 60%.
-- **Mid-Wave Steering**: In-flight steering injection into the `AutoRunner` loop, allowing humans to re-orient an active autonomous wave without restarts.
-- **Confidence-to-Human Gating**: Proactive interruption of the autonomous stream for "Human-in-the-Loop" approval on sensitive T3 operations.
+- **ROI Logic Engine**: Maps complex task completions (refactor, test, audit) to developer-hour savings ($100/hr) vs. provider token costs.
+- **Velocity Forecaster**: Predictive analytics that calculate milestone completion ETAs based on historical task-weight throughput and system latency.
+- **Governance Debt Monitoring**: Tracks policy bypasses and high-risk security findings to compute a "Security Health Score" (SHS), ensuring framework liability remains within enterprise bounds.
 
 ---
 
@@ -92,9 +105,13 @@ DHH creates a seamless bridge between fully autonomous execution and high-precis
 
 | Component | Path | Description |
 | :--- | :--- | :--- |
-| **Stuck Monitor** | `bin/autonomous/stuck-monitor.js` | S03/S04 loop detection patterns. |
-| **Refactorer** | `bin/autonomous/context-refactorer.js` | Context density and proactive summarization. |
+| **Stuck Monitor** | `bin/engine/nexus-tracer.js` | Integrated RES loop detection and entropy scoring. |
+| **Recovery Agent** | `bin/engine/temporal-hindsight.js` | Generates steering vectors for proactive recovery. |
+| **Skill Validator** | `bin/skill-validator.js` | JIT Binary Runtime Attestation and 7D scoring. |
 | **SRE Manager** | `bin/engine/sre-manager.js` | Trusted execution enclave management. |
+| **ROI Engine** | `bin/revops/roi-engine.js` | Financial value synthesis and cost/benefit mapping. |
+| **Velocity Forecaster** | `bin/revops/velocity-forecaster.js` | Predictive milestone ETA and throughput analytics. |
+| **Debt Monitor** | `bin/revops/debt-monitor.js` | Security Health Score (SHS) and governance debt tracking. |
 | **Handover Manager** | `bin/engine/handover-manager.js` | Nexus bundle creation and steering logic. |
 | **SBOM Tracer** | `bin/engine/nexus-tracer.js` | SRE-aware audit logging and manifest generation. |
 

package/docs/architecture/V6-SOVEREIGN.md

@@ -0,0 +1,43 @@
+# MindForge v6.1.0-alpha: Sovereign Intelligence (Pillars IX & X)
+
+The **Sovereign Intelligence** phase elevates MindForge from reactive autonomous waves to a self-optimizing, self-healing agentic operating system. This is achieved through real-time financial arbitrage and proactive reasoning integrity monitoring.
+
+---
+
+## Pillar IX: Autonomous Resource Harvesting (ARH)
+
+### Goal
+To maximize the economic efficiency of agentic work by dynamically harvesting the lowest-cost, highest-intelligence compute resources in real-time.
+
+### Components
+- **`MarketEvaluator`**: Real-time tracker for token pricing and intelligence benchmarks across model providers (Anthropic, OpenAI, Gemini).
+- **`RouterSteeringV2`**: Advanced task-to-model affinity engine. It calculates the **Min-Intelligence-Requirement (MIR)** and steers tasks accordingly.
+- **ROI Arbitrage Engine**: Automatically calculates and logs the "dollar value" saved by every autonomous wave compared to standard premium-only routing.
+
+### Workflow
+1. **MIR Analysis**: Before a subagent is spawned, the `CloudBroker` analyzes the task taxonomy.
+2. **Arbitrage Selection**: The `MarketEvaluator` selects the optimal model (e.g., routing small fixes to a local model while keeping architectural reasoning on Gemini 1.5 Pro).
+3. **Telemetry**: Savings are logged to `AUDIT.jsonl` under the `roi_arbitrage_event` category.
+
+---
+
+## Pillar X: Neural Drift Remediation (NDR)
+
+### Goal
+To proactively detect and remediate "Reasoning Drift" (logic loops, hallucinations, and semantic decay) before it corrupts the autonomous execution wave.
+
+### Components
+- **`LogicDriftDetector`**: Heuristics-based engine that analyzes the `reasoning_trace` for semantic density, pattern repetition, and logical contradictions.
+- **`RemediationEngine`**: A stateful recovery system that can trigger `REASONING_RESTART`, `GOLDEN_TRACE_INJECTION`, or `AUTONOMY_HALT`.
+- **NexusTracer Hooks**: Deep integration into the core execution loop to intercept every reasoning span.
+
+### Workflow
+1. **Drift Sensing**: At every 10 reasoning nodes, the `NexusTracer` evaluates the current `DriftScore` (0-100).
+2. **Remediation Trigger**: If `DriftScore > Threshold` (Default 75), the `RemediationEngine` is invoked.
+3. **Audit Closure**: Every remediation action is logged as a `drift_remediation_event`, ensuring the "hindsight" is preserved for future sessions.
+
+---
+
+## Architectural interlock (V6.1)
+
+Sovereign Intelligence is the final layer of the MindForge Enterprise roadmap. It leverages the **CADIA** risk engine (v6.0) and the **ZTAI** identity layer (v5.x) to ensure that all self-healing actions are both safe and non-repudiable.

package/docs/commands-reference.md

@@ -1,4 +1,4 @@
-# MindForge v5.1.0 — Commands Reference
+# MindForge v6.0.0-alpha — Commands Reference
 
 MindForge commands are organized into functional pillars to support the entire software development lifecycle (SDLC).
 
@@ -37,6 +37,7 @@ MindForge commands are organized into functional pillars to support the entire s
 | `/mindforge:tokens` | Analyzes and profiles token usage for the current session. |
 | `/mindforge:neural-orchestrator` | Activates the advanced protocol layer for the current session. |
 | `shard-helper --verify` | (CLI Internal) Verifies the integrity and SHA-256 checksums of memory shards. |
+| `/mindforge:entropy-check`| (Sentinel) Manually trigger Reasoning Entropy Analysis on the current context. |
 
 ---
 
@@ -51,6 +52,7 @@ MindForge commands are organized into functional pillars to support the entire s
 | `/mindforge:skills validate [PATH]` | Passes a skill through the 7-Dimension Scorer for quality verification. |
 | `/mindforge:marketplace search [Q]`| Searches community skills from the central registry. |
 | `/mindforge:marketplace install ID` | Installs a verified community skill into the project context. |
+| `mindforge-cc sign <SKILL>`| (Sentinel) Cryptographically sign a skill with a Tier 3 DID signature. |
 
 ---
 
@@ -81,3 +83,4 @@ These protocols represent specialized, high-fidelity engineering behaviors porte
 | `/mindforge:tdd` | Enhanced Test-Driven Development protocol with strict verification. |
 | `/mindforge:debug` | Advanced systematic debugging with persistent state tracking. |
 | `/mindforge:verify-work` | Multi-level truth verification (existence, substance, wiring). |
+| `/mindforge:sentinel-status`| Displays real-time integrity and reliability metrics for the mesh. |

package/docs/feature-dashboard.md

@@ -1,4 +1,4 @@
-# Feature: Real-time Dashboard (v4.1.0)
+# Feature: Real-time Dashboard (v5.10.0)
 
 The MindForge Real-time Dashboard provides a high-fidelity, web-based control center for your agentic workflows. It leverages **Server-Sent Events (SSE)** to push live updates from your codebase directly to your browser with zero performance overhead.
 
@@ -33,11 +33,17 @@ Default access: `http://localhost:7339` (Strictly bound to `127.0.0.1` for secur
 - **Persona Context**: See which agent personas are currently active.
 - **Steerage Feed**: View steering instructions as they are applied.
 
-### 5. MindForge Nexus (v4.1+)
+### 5. MindForge Nexus (v5.10+)
 - **ART Trace Explorer**: Drill down into hierarchical reasoning spans and thought chains.
-- **Mesh Topology**: Visual graph of the active agentic mesh and specialist clusters.
+- **Temporal Control Center**: Dynamic slider-based navigation of reasoning history.
+- **Hindsight Injection**: Rollback project state to any previous `auditId` and inject steering instructions to correct drift.
 - **Reasoning Heatmaps**: Identifying areas of adversarial disagreement and drift in real-time.
 
+### 6. AgRevOps Financial Hub (v5.10+)
+- **ROI Hub**: Real-time tracking of developer-hour value ($100/hr) vs. token expenditure.
+- **Velocity Forecaster**: Predictive analytics for milestone completion ETAs based on live task throughput.
+- **Security Health Score (SHS)**: Dynamic 0-100 score reflecting governance debt and policy compliance.
+
 ## 🛡 Hardened Security
 - **Localhost Binding**: The server refuses connections from external IPs.
 - **CORS Lock-down**: Only allows requests from the local control plane.

package/docs/governance-guide.md

@@ -1,61 +1,99 @@
-# MindForge Governance Guide (v5.1.0)
-Absolute Control through Policy-as-Code (PaC)
+# MindForge Governance Guide (v6.2.0-alpha)
+V6.2.0 Sovereign Intelligence: PQAS & Proactive Homing
 
 ## 1. Goal
-MindForge v5.1.0 introduces a non-bypassable, intent-level governance layer. This guide explains how **Agentic Policy Orchestration (APO)** and **Zero-Trust Agentic Identity (ZTAI)** work together to secure the enterprise development lifecycle, now hardened by the **Neural Protocol Mesh**.
+MindForge v6.2.0 achieves the final stage of **Sovereign Intelligence**, introducing post-quantum safe identities (PQAS) and proactive agentic homing. This eliminates reactive latency in the mesh and ensures long-term cryptographic resilience against future threats.
 
-## 2. Agentic Policy Orchestrator (APO)
+## 2. Post-Quantum Agentic Security (Pillar XI)
+MindForge implements Pillar XI to harden the identity layer against future quantum computing threats.
+
+### A. Lattice-Based Cryptography
+- **Signature Algorithm**: Dilithium-5 (Lattice-based).
+- **Key Exchange**: Kyber-1024 (Lattice-based).
+- **Hardening**: Every Tier 4 agent action is signed with quantum-safe primitives, ensuring non-repudiation in the post-quantum era.
+
+### B. ZK-Proof Compliance Bypasses
+For high-leverage architectural changes, Tier 3+ agents can generate a **Zero-Knowledge Proof** (simulated SNARK) to verify policy adherence without exposing confidential reasoning logic.
+
+## 3. Proactive Semantic Homing (Pillar XII)
+Pillar XII transitions the autonomous swarm from reactive wave-processing to proactive, self-healing "Homing" behavior.
+
+### A. Intent Harvesting
+Agents in an idle state proactively scan the **Federated Intelligence Mesh (FIM)** for unassigned tasks, claiming them based on **Skill-Affinity** scores to eliminate idle latency.
+
+### B. Mesh Self-Healing
+When an agent experiences critical logic drift (>80), peer agents in the mesh proactively "home in" on the node to provide collaborative reasoning and recovery vectors.
+
+## 4. Agentic Policy Orchestrator (APO) — CADIA Engine
 The APO is a decentralized governance engine that intercepts every autonomous intent before it is executed.
 
 ### A. Intent Interception
 Before the `AutoRunner` begins a new execution wave, it extracts the acting agent's **Intent**:
 - **DID**: The unique identity of the agent.
-- **Action**: The operation being attempted (e.g., `process_phase_wave`, `modify_security_config`).
+- **Action**: The operation being attempted (e.g., `WRITE`, `DELETE`, `EXECUTE`).
 - **Resource**: The target of the action (e.g., specific directories, files, or API endpoints).
 - **Tier**: The ZTAI Trust Tier assigned to the agent.
+- **SessionId**: The unique identifier for the current autonomous session.
+- **Reasoning Proof**: (Tier 3 Only) A justification for high-risk architectural actions.
+
+### B. Policy Evaluation (v6.0.0)
+The upgraded `PolicyEngine` evaluates the intent using the CADIA scoring model:
+1.  **Blast Radius Calculation**: The `ImpactAnalyzer` computes a risk score (0-100) based on architectural influence, session history, and goal alignment.
+2.  **Tier-Based Enforcement**: 
+    - **Score > 25 (LOW)**: Permitted for Tier 1+.
+    - **Score > 50 (MEDIUM)**: Permitted for Tier 2+.
+    - **Score > 80 (CRITICAL)**: **Denied** (Default) for Tier 0-2.
+    - **Tier 3 Bypass**: Senior agents can override a CRITICAL score if a valid `reasoning_proof` is provided.
+
+## 3. CADIA: Dynamic Impact Analysis Logic
+The **ImpactAnalyzer** calculates a precision-weighted score using the follow heuristics:
 
-### B. Policy Evaluation
-The `PolicyEngine` evaluates this intent against organizational **Policy-as-Code (PaC)** definitions (typically stored in `bin/governance/policies/`).
-- **Permit**: The action is allowed and execution proceeds.
-- **Deny**: The action is blocked, and the violation is logged to `AUDIT.jsonl`.
-- **Blast Radius Denial (v5.3.0)**: Action is blocked if the `Impact Score` exceeds the policy `max_impact` threshold.
-- **Escalate**: The action requires a higher-tier DID signature or explicit HITL (Human-in-the-Loop) approval.
+### A. Architectural Influence Engine (x2.5)
+High-influence files (Core, Governance, Models, and Project State) increase the blast radius score significantly.
+- **Paths**: `bin/governance/*`, `bin/engine/*`, `package.json`, `.planning/*`.
 
-## 3. Trust Tier Architecture (ZTAI Hardened)
-V5.1.0 automatically maps ZTAI Trust Tiers to explicit project roles through the `RBACManager`.
+### B. Sensitive Namespace Protection (x4.0)
+Strict multipliers for mission-critical directories:
+- **Namespaces**: `.mindforge/`, `bin/`, `config/`, `.agent/`.
+
+### C. Session Entropy Tracker (+15 per file)
+To prevent "Rogue Wave" mass-corruption, the risk score increases for every file touched in a single session after the 5th modification.
+- **Penalty**: `(session_count - 5) * 15`.
+
+### D. Goal-to-Path Alignment (+40 penalty)
+The system cross-references targets against the **Current Phase** in `.planning/STATE.md`.
+- **Anomalous Behavior**: If an agent tasked with "Fixing UI" attempts to modify `bin/models/cloud-broker.js`, a large penalty is applied.
+
+### E. ZTAI-Trust Scaling (Risk Buffers)
+Trust Tiers (0-3) provide a risk "overhead" buffer:
+- **Tier 1**: -10 points.
+- **Tier 2**: -20 points.
+- **Tier 3**: -30 points (Sovereign Trust).
+
+## 4. Trust Tier Architecture (ZTAI Hardened)
+V6.0.0 maps ZTAI Trust Tiers to explicit project roles through the `RBACManager`.
 
 | Tier | Role | Scope | Hardening |
 | :--- | :--- | :--- | :--- |
-| **0** | Informational | Research/Query only. | Read-only access to non-sensitive docs. |
-| **1** | Implementation| Standard feature dev. | Write access to `/src`, `/tests`, `/bin/memory`. |
-| **2** | Specialized | Security/DevOps Specialist. | Access to `/security`, `/infra`, and `/bin/governance`. |
-| **3** | Principal | Lead Architect / Core Engine. | **HSM-Enclave Signing Required** for all engine modifications. |
-
-## 4. Protocol Mesh Governance (v5.1.0 Enhancement)
-The **Beast Addition** integrates protocol-level governance into the APO engine.
-- **Protocol Enforceability**: Every protocol activation (e.g., `/mindforge:tdd`) is logged as a governance event.
-- **Mesh Integrity**: The **Parallel Mesh** synchronizes governance state across multiple agents, preventing "split-brain" policy execution.
-- **Skill Compliance**: New skills created via `/mindforge:skill-creation` are automatically audited for APO compatibility.
-
-## 5. Governance Workflow (V5.1.0)
-1. **ZTAI Handshake**: Agent proves identity using Ed25519 signatures.
-2. **Intent Pulse**: Agentic intent is broadcast to the policy interceptor.
-3. **APO Evaluation**: Policy engine checks the intent against PaC rules.
-4. **Role binding**: `RBACManager` grants or revokes permissions based on the active trust tier.
-5. **Verified Wave**: Execution proceeds only if all policy gates are clear.
+| **0** | Informational | Research/Query only. | Read-only. No CADIA bypass. |
+| **1** | Implementation| Standard feature dev. | Write to `/src`, `/tests`. Session limit: 5 files. |
+| **2** | Specialized | Security/Ops Specialist. | Access to `/security`, `/infra`. Higher risk cap (60). |
+| **3** | Principal | Lead Architect / CEO. | **Full CADIA Bypass** (with Reasoning Proof). |
+
+## 5. Enterprise Audit & Compliance (RISK-AUDIT)
+Every governance evaluation is persistently recorded in `.planning/RISK-AUDIT.jsonl`. This log provides a high-fidelity trail for enterprise compliance:
+- **requestId**: Unique ID for every evaluation.
+- **impactScore**: The final CADIA risk score (0-100).
+- **verdict**: PERMIT or DENY.
+- **reason**: Detailed explanation for the decision (e.g., "Violation: Max Impact Exceeded").
 
 ## 6. Enterprise Policies
-MindForge v5.1.0 ships with default policies including:
+MindForge v6.0.0 ships with default policies including:
 - **`gate_tier_3_engine`**: Blocks all modifications to `bin/autonomous/` unless signed by a Tier 3 DID.
 - **`protect_security_namespace`**: Limits access to `/security` and `/governance` to Tier 2+ specialists.
-- **`mesh_integrity_lock`**: Ensures only high-confidence agents can push to the **Federated Intelligence Mesh**.
-- **`enforce_blast_radius` (v5.3.0)**: Dynamic policy that limits `DELETE` impact to <30 for Tier 1 agents.
-
-## 7. Dynamic Blast Radius (v5.3.0)
-The **ImpactAnalyzer** calculates a score (0-100) for every intent:
-- **Action Type**: `DELETE` (10), `WRITE` (5), `READ` (1).
-- **Sensitivity**: 4x multiplier for `.mindforge/`, `bin/`, and `config/` namespaces.
-- **Fail-Safe**: Defaults to Score 100 (CRITICAL) if analysis fails.
+- **`enforce_blast_radius` (v6.0.0)**: Dynamic policy that enforces a strict 60-point cap for non-Sovereign agents.
+- **`require_skill_attestation`**: Forces all skills to have valid ZTAI-signatures before loading.
 
 ---
-*Status: V5.3.0 Dynamic Blast Radius Implemented & Verified (2026-03-28)*
+*Status: V6.0.0 CADIA (Context-Aware Dynamic Impact Analysis) Implemented & Verified (2026-03-29)*
+

package/docs/registry/AGENTS.md

@@ -0,0 +1,37 @@
+# MindForge — Agent Identity Registry (v6.2.0-alpha)
+
+This registry catalogs the specialized agent identities available for direct invocation and autonomous collaboration within the MindForge mesh.
+
+## 👤 Interaction Layer (Public Identifiers)
+
+| Agent | Core Persona | Interaction Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-planner** | Strategic Architect | Planning & Roadmapping | "Design systems with 10/10 fidelity." |
+| **mf-executor** | Lead Developer | Feature Implementation | "Ship premium-grade code by default." |
+| **mf-reviewer** | Quality Auditor | Review & Validation | "Find the bugs before they ship." |
+| **mf-memory** | Semantic Clerk | Knowledge & History | "Manage the knowledge graph sync." |
+| **mf-researcher** | Discovery Agent | Deep Context Search | "Surface the unknown-unknowns." |
+| **mf-tool** | System Operator | CLI & Environment | "Execute system transformations safely." |
+
+## 🛡️ Specialized Sovereign Agents
+
+| Agent | Core Persona | Operational Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **security-reviewer** | Threat Hunter | Security Hardening | "Secure the framework against threats." |
+| **nyquist-auditor** | Logic Auditor | Requirement Tracing | "Ensure 100% requirement coverage." |
+| **debug-specialist** | RCA Expert | Systematic Debugging | "Debug with persistent state tracking." |
+| **ui-auditor** | Visual Designer | Aesthetic Excellence | "Ensure 10/10 aesthetics & UX." |
+| **verifier** | UAT Specialist | Evidence Validation | "Prove functionality with visual proof." |
+
+## 🧠 Autonomous Swarm Enclaves
+
+| Agent | Core Persona | Collaborative Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **qa-engineer** | Logic Guard | Adversarial Testing | "Find failure modes in the logic." |
+| **tech-writer** | Knowledge Lead | Documentation Sync | "Transform complexity into clarity." |
+| **research-agent** | Data Scraper | Recursive Discovery | "Gather data points from web/repo." |
+| **roadmapper** | Execution Lead | Milestone Sequencing | "Derive phases from requirements." |
+| **user-profiler** | Behavioral Lead | Personalized DX | "Adapt to the unique user needs." |
+
+---
+*For more details, see the [MIND-FORGE-REFERENCE-V6.md](../MIND-FORGE-REFERENCE-V6.md).*

package/docs/registry/COMMANDS.md

@@ -0,0 +1,87 @@
+# MindForge — Command Registry (v6.2.0-alpha)
+
+This registry catalogs every strategic, operational, and governance command available in the MindForge ecosystem.
+
+## 🛡️ Strategic & Governance Commands
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:status` | Real-time project and Sovereign health. | `/mindforge:status` | Verified engine manifestation. |
+| `/mindforge:security-scan` | OWASP Top 10 + Sovereign Integrity check. | `/mindforge:security-scan` | Hardened codebase. |
+| `/mindforge:health` | 7-pillar diagnostic of framework integrity. | `/mindforge:health` | 100% module health report. |
+| `/mindforge:approve` | ZK-signed proof for Tier 3 gates. | `/mindforge:approve` | Unlocked high-risk commits. |
+| `/mindforge:audit` | Query historical reasoning and compliance. | `/mindforge:audit` | Traceability and audit trail. |
+| `/mindforge:tokens` | Real-time ROI and cost efficiency analysis. | `/mindforge:tokens` | Balanced resource consumption. |
+| `/mindforge:quantum-verify` | Lattice-based framework integrity check. | `/mindforge:quantum-verify` | Cryptographically proven state. |
+| `/mindforge:metrics` | Real-time velocity and quality aggregation. | `/mindforge:metrics` | Performance trends and KPIs. |
+| `/mindforge:classify` | Governance tier assignment for changes. | `/mindforge:classify` | Risk-aware gate enforcement. |
+
+## 📐 Project & Lifecycle Management
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:init-project` | Initialize a new project with the framework. | `/mindforge:init-project` | "Beast Mode" workspace. |
+| `/mindforge:init-org` | Set up organization-level policy standards. | `/mindforge:init-org` | Standardized enterprise config. |
+| `/mindforge:new-project` | Structured project initialization wizard. | `/mindforge:new-project` | Validated project baseline. |
+| `/mindforge:milestone` | Define and track high-level milestones. | `/mindforge:milestone` | Recorded project roadmap. |
+| `/mindforge:discuss-phase` | Adaptive requirement gathering and discovery. | `/mindforge:discuss-phase` | Approved PLAN.md. |
+| `/mindforge:plan-phase` | High-fidelity execution plan generation. | `/mindforge:plan-phase` | Atomic task blueprint. |
+| `/mindforge:architecture` | Domain modeling and system design orchestration. | `/mindforge:architecture` | UI-SPEC and ARCHITECTURE docs. |
+| `/mindforge:next` | Auto-detect and route the next logical action. | `/mindforge:next` | Zero-friction dev workflow. |
+| `/mindforge:retro` | Performance-driven milestone retrospective. | `/mindforge:retro` | Identified growth areas. |
+| `/mindforge:complete-milestone` | Milestone archival and next cycle preparation. | `/mindforge:complete-milestone` | Clean project state for next. |
+
+## 🚀 Execution & Implementation
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:execute-phase` | Wave-based parallel implementation. | `/mindforge:execute-phase` | Completed feature phase. |
+| **mindforge:auto** | Autonomous execution mode (Wave mode). | `/mindforge:auto` | Unattended bulk task completion. |
+| `/mindforge:do` | NLP intent ingestion and dispatching. | `/mindforge:do "[intent]"` | Smart task routing. |
+| `/mindforge:steer` | Mid-execution instruction for active swarms. | `/mindforge:steer "[guide]"` | Remediated autonomous engine. |
+| `/mindforge:headless` | Daemonize MindForge for background operation. | `/mindforge:headless` | Continuous framework uptime. |
+| `/mindforge:quick` | Atomic task execution with validation. | `/mindforge:quick` | Fast, safe bugfixes and tweaks. |
+| `/mindforge:tdd` | Strict Red-Green-Refactor development logic. | `/mindforge:tdd` | 100% tested implementation. |
+| `/mindforge:swarm-execution` | Multi-agent parallel swarm orchestration. | `/mindforge:swarm-execution` | High-velocity implementation. |
+| `/mindforge:debug` | RCA investigation and systematic repair. | `/mindforge:debug` | Resolved root-cause defects. |
+| `/mindforge:workstreams` | Parallel feature track isolation and management. | `/mindforge:workstreams` | Isolated, concurrent development. |
+
+## ✅ Verification & Quality
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:verify-work` | UAT + Browser testing + Evidence capture. | `/mindforge:verify-work` | Visual proof of functionality. |
+| `/mindforge:validate-phase` | Pillar gap analysis and requirement closure. | `/mindforge:validate-phase` | Quality-certified phase. |
+| `/mindforge:pr-review` | AI-driven pull request review engine. | `/mindforge:pr-review` | Approved code and PR summary. |
+| `/mindforge:ui-review` | Visual audit against DESIGN_SYSTEM.md. | `/mindforge:ui-review` | 10/10 aesthetic compliance. |
+| `/mindforge:benchmark` | Measure skill and agent effectiveness. | `/mindforge:benchmark` | ROI and quality scores. |
+| `/mindforge:test-memory` | Persistent memory suite validation check. | `/mindforge:test-memory` | Knowledge graph integrity. |
+
+## 🧠 Knowledge & AI Intelligence
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:learn` | Convert raw knowledge into a SKILL.md. | `/mindforge:learn` | New framework capability. |
+| `/mindforge:remember` | Management of the semantic knowledge graph. | `/mindforge:remember` | Evolving framework intelligence. |
+| `/mindforge:memory` | Real-time interaction with framework memory. | `/mindforge:memory` | Semantic context retrieval. |
+| `/mindforge:research` | Deep research across the 1M token window. | `/mindforge:research` | Comprehensive context reports. |
+| `/mindforge:hindsight` | Inject fixes into past state points. | `/mindforge:hindsight` | Repaired state history. |
+| `/mindforge:harvest` | Proactive semantic intent harvesting. | `/mindforge:harvest` | Automated task claiming. |
+| `/mindforge:self-heal` | Autonomous reasoning drift remediation. | `/mindforge:self-heal` | Stabilized swarm logic. |
+| `/mindforge:temporal` | State history and time-travel debugging. | `/mindforge:temporal` | Advanced state traceability. |
+
+## 📦 Skill & Asset Management
+
+| Command | Description | Invocation | Outcome Goal |
+| :--- | :--- | :--- | :--- |
+| `/mindforge:install-skill` | Install a skill to the designated Tier. | `/mindforge:install-skill` | Deployed capability. |
+| `/mindforge:register-skill` | Register skill in the framework Manifest. | `/mindforge:register-skill` | Discoverable skill asset. |
+| `/mindforge:audit-skill` | Record lifecycle events in the audit log. | `/mindforge:audit-skill` | Compliance and history. |
+| `/mindforge:validate-skill` | High-fidelity skill testing and linting. | `/mindforge:validate-skill` | Certified skill performance. |
+| `/mindforge:marketplace` | Discover and install community skills. | `/mindforge:marketplace` | Ecosystem expansion. |
+| `/mindforge:spawn` | Direct invocation of a persona essence. | `/mindforge:spawn [persona]` | Cognitive support on demand. |
+| `/mindforge:identity` | Invoke specialized identity from /agents/. | `/mindforge:identity` | Specialized interaction persona. |
+| `/mindforge:plugins` | Manage and audit framework logic plugins. | `/mindforge:plugins` | Customizable framework engine. |
+
+---
+*For more details, see the [MIND-FORGE-REFERENCE-V6.md](../MIND-FORGE-REFERENCE-V6.md).*

package/docs/registry/HOOKS.md

@@ -0,0 +1,38 @@
+# MindForge — Hook Registry (v6.2.0-alpha)
+
+This registry catalogs the automation and security lifecycle hooks available in the MindForge environment.
+
+## 🛡️ Framework Governance Hooks
+
+| Hook | Trigger Event | Primary Security Protocol |
+| :--- | :--- | :--- |
+| **mindforge-session-init_extended** | `Session Start` | "Enterprise-grade context restoration, workspace mounting, and security baseline verification." |
+| **mindforge-workflow-guard** | `Command Invocation` | "Enforcement of phase-based logic, mandatory plan approval, and verification gating." |
+| **mindforge-prompt-guard** | `Token Input` | "Persona integrity enforcement, safety filtering, and prompt injection prevention." |
+
+## 📊 Operational Visibility & Health
+
+| Hook | Trigger Event | Primary Security Protocol |
+| :--- | :--- | :--- |
+| **mindforge-statusline** | `Terminal Init / Loop` | "Real-time productivity indicators, token counts, and phase status rendering." |
+| **mindforge-check-update** | `Startup / Interval` | "Automatic framework update detection, changelog retrieval, and version sync." |
+| **mindforge-context-monitor** | `Context Shift` | "Dynamic token optimization, context window management, and memory prioritizing." |
+
+## 🔗 Version Control & Git Hooks
+
+| Hook | Trigger Event | Primary Security Protocol |
+| :--- | :--- | :--- |
+| **pre-commit-security** | `git commit` | "Run a `--secrets` scan on staged files before commit." |
+| **post-merge-status** | `git merge` | "Re-verify Sovereign framework integrity after code updates." |
+| **pre-push-validation** | `git push` | "Validate that all active plans have an 'Approved' status." |
+
+## 🧠 Reasoning & Memory Hooks
+
+| Hook | Trigger Event | Primary Security Protocol |
+| :--- | :--- | :--- |
+| **nexus-tracer-init** | `Async Start` | "Inject the ZTAI signing protocol into every reasoning cycle." |
+| **memory-load-check** | `Session Start` | "Verify the knowledge graph's semantic integrity." |
+| **intent-harvest-trigger** | `Idle Threshold` | "Activate the Sovereign Homing engine for idle task-claiming." |
+
+---
+*For more details, see the [MIND-FORGE-REFERENCE-V6.md](../MIND-FORGE-REFERENCE-V6.md).*

package/docs/registry/PERSONAS.md

@@ -0,0 +1,64 @@
+# MindForge — Persona Registry (v6.2.0-alpha)
+
+This registry catalogs the specialized agent essences available for direct interaction and autonomous reasoning.
+
+## 🧠 Strategic Reason Enclaves
+
+| Persona | Identifier | Cognitive Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-planner** | Strategic Planner | Minimalism & Scalability | "Design systems with 10/10 fidelity and 1/1 complexity." |
+| **architect** | Senior Architect | Core System Design | "Build robust, secure, and maintainable foundations." |
+| **roadmapper** | Milestone Specialist | Timeline & Dependencies | "Convert requirements into executable milestones." |
+| **analyst** | Requirements Lead | Scoping & Specs | "Translate ambiguous intent into precise, testable specifications." |
+| **decision-architect** | Governance Lead | Implementation Verdicts | "Synthesize research and audits into actionable roadmap adjustments." |
+| **advisor-researcher** | Trade-off Consultant | Comparative Rationale | "Research single decision points and provide structured comparisons." |
+
+## 🚀 Implementation Pilots
+
+| Persona | Identifier | Cognitive Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-executor** | Lead Developer | "Beast Mode" Logic & UI | "Ship premium-grade code with 100% test coverage." |
+| **developer** | Code Smith | Clean Code & Patterns | "Implement features according to the approved plan." |
+| **executor** | Pilot Developer | Atomic Multi-Plan | "Executes implementation plans with high fidelity and atomic commits." |
+| **tech-writer** | Documentation Lead | Clarity & Accuracy | "Transform engineering complexity into readable documentation." |
+| **mf-tool** | System Operator | Terminal & File Ops | "Execute complex system transformations safely." |
+
+## 🛡️ Quality & Security Auditors
+
+| Persona | Identifier | Cognitive Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-reviewer** | Quality Lead | Correctness & Performance | "Find the bugs and antipatterns before they ship." |
+| **security-reviewer** | Threat Hunter | PQAS & OWASP | "Harden the framework against all agentic threats." |
+| **nyquist-auditor** | Requirement Auditor | Gaps & Edge Cases | "Ensure every requirement has a verification plan." |
+| **verifier** | UAT Specialist | Evidence & Validation | "Prove the feature works with visual evidence." |
+| **qa-engineer** | QA Specialist | Adversarial Testing | "Think adversarially to find failure modes and logic gaps." |
+| **ui-auditor** | Visual Specialist | Aesthetic Excellence | "Ensure 10/10 aesthetics and fluid animations." |
+| **ui-checker** | Design Validator | UI-SPEC Compliance | "Verify visual implementation against recorded design contracts." |
+| **integration-checker** | System Integrator | Cross-Component Flow | "Ensure disparate services work as a unified system." |
+| **coverage-specialist** | Testing Analyst | Coverage Gap Index | "Identify untested code paths and logic branches." |
+
+## 🔍 Research & Intelligence Agents
+
+| Persona | Identifier | Cognitive Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-researcher** | Knowledge Lead | Context & Discovery | "Surface the unknown-unknowns before implementation." |
+| **project-researcher** | Principal Researcher | Ecosystem & Feasibility | "Investigate technical constraints before project or milestone creation." |
+| **research-agent** | Deep-Dive Specialist | Recursive Investigation | "Gather data points from the web and codebase recursively." |
+| **research-synthesizer** | Wisdom Aggregator | Summary Generation | "Synthesize research outputs from multiple agents into a SUMMARY.md." |
+| **phase-researcher** | Tactical Researcher | Implementation Logic | "Analyze approaches and best practices for the current phase." |
+| **ui-researcher** | Design Consultant | Visual Trend Analysis | "Research modern UI patterns and aesthetic benchmarks." |
+
+## 🧠 Specialized Diagnostics & Memory
+
+| Persona | Identifier | Cognitive Focus | Primary Directive |
+| :--- | :--- | :--- | :--- |
+| **mf-memory** | Semantic Clerk | Persistent Context | "Manage long-term memory and knowledge graph synchronization." |
+| **debug-specialist** | RCA Expert | Root Cause Analysis | "Debug systematically with persistent state tracking." |
+| **debugger** | Logic Specialist | Hypothesis Testing | "Solve failures through scientific hypothesis testing." |
+| **user-profiler** | Behavioral Analyst | Dev Experience | "Adapt the framework to the unique needs of the developer." |
+| **assumptions-analyzer** | Logic Auditor | Pre-Planning Verification | "Surface approach assumptions before committing to a plan." |
+| **codebase-mapper** | Ecosystem Explorer | Semantic Indexing | "Generate structured documentation for any repository." |
+| **release-manager** | Pipeline Lead | SemVer & Ship Control | "Ensure every release is traceable and reversible." |
+
+---
+*For more details, see the [MIND-FORGE-REFERENCE-V6.md](../MIND-FORGE-REFERENCE-V6.md).*