mindforge-cc 3.0.0 → 5.0.0

package/CHANGELOG.md

@@ -1,5 +1,116 @@
 # Changelog
 
+## [5.0.0-alpha.2] — Predictive Reliability & Supply Chain Trust — 2026-03-28
+
+🚀 **MindForge v5.0.0 — Pillars III & IV Implementation**
+
+This update adds the next two critical architectural pillars to the v5 Enterprise roadmap, focusing on long-term session reliability and a verifiable asset supply chain.
+
+### Pillar III: Predictive Agentic Reliability (PAR)
+
+- **Advanced Loop Detection**: Implemented **S03 (Semantic Mirroring)** and **S04 (Infinite Decomposition)** patterns in the `StuckMonitor`.
+- **Context Density Refactorer**: New proactive utility that triggers context summarization and handoffs when reasoning-to-action density falls below 30%.
+- **C2C Arbitrage**: Integrated **Confidence-to-Cost** threshold gating into the `AutoRunner` to prevent low-value autonomous drift.
+- **Self-Healing Integration**: Automated triggering of "hindsight injection" and state repair when PAR patterns are detected.
+
+### Pillar IV: Supply Chain Trust (ZTS)
+
+- **Agentic SBOM**: Implemented the `NexusTracer` manifest generator, producing real-time `MANIFEST.sbom.json` files for every reasoning chain.
+- **7-Dimension Certification (7D)**: Re-architected the `skill-validator` with a weighted scoring system covering Schema, Triggers, Security, Clarity, and Examples.
+- **Enterprise-Grade Enforcement**: Strict `--enterprise` mode requirement for a minimum **7.0/10.0** certification score.
+- **Model/Skill Telemetry**: Integrated real-time tracking of asset provenance and usage history in the audit stream.
+
+## [5.0.0-alpha.1] — Federated Intelligence & Policy Orchestration — 2026-03-28
+
+🚀 **MindForge v5.0.0 — The Enterprise "Beast" Release**
+
+This landmark release transforms MindForge into a distributed, governable, and cryptographically verified agentic operating system. V5 introduces the first two pillars of the Enterprise Architecture: Federated Intelligence Mesh (FIM) and Agentic Policy Orchestrator (APO).
+
+### Pillar I: Federated Intelligence Mesh (FIM)
+
+- **Enterprise Intelligence Service (EIS)**: Implemented `eis-client.js` for secure, authenticated communication with the organizational knowledge hub.
+- **Delta-Sync Protocol**: Implemented `federated-sync.js` with timestamp-based delta pulls, significantly reducing synchronization latency.
+- **ZTAI-Signed Provenance**: Every knowledge item in the mesh is cryptographically tied to the DID of the originating agent.
+- **Hybrid Knowledge Graph**: Extended `knowledge-graph.js` to seamlessly resolve local nodes and remote federated nodes.
+
+### Pillar II: Agentic Policy Orchestrator (APO)
+
+- **Policy-as-Code (PaC)**: Implemented `policy-engine.js` for intent-based evaluation of agent actions against organizational security rules.
+- **RBAC Manager**: Implemented `rbac-manager.js` for mapping DIDs to project roles and binding permissions to ZTAI Trust Tiers.
+- **Policy Interceptor**: Deep integration into `auto-runner.js`, enforcing a pre-flight governance gate before every autonomous wave.
+- **Default Enterprise Policies**: Shipped with initial security guardrails for engine and infrastructure protection.
+
+### Hardening ("Beast" Mode)
+
+- **ZTAI Interlock**: All mesh and policy operations now utilize the hardware-enclave (simulated) signing engine for Tier 3 principals.
+- **Dynamic Intent Extraction**: Autonomous intents are now derived in real-time from active session identities.
+- **Conflict Resolution (LWW)**: Hardened the federated sync with Last-Write-Wins conflict resolution logic.
+
+---
+
+## [4.3.0] — Enterprise Mesh & Proactive Equilibrium — 2026-03-28
+
+🚀 **MindForge v4.3.0 — The Maturity Release**
+
+This major update completes the **MindForge V4 Roadmap**, introducing autonomous financial governance and self-healing reliability engines. It also includes a comprehensive structural reorganization of the framework for enterprise scalability.
+
+### Key Pillars (v4.3.0)
+
+- **Autonomous FinOps Hub (Pillar V)**: Implemented `ModelBroker` for dynamic **C2C (Confidence-to-Cost)** routing and `FinOpsHub` for real-time ROI tracking.
+- **Proactive Equilibrium (Pillar VI)**: Implemented `WaveFeedbackLoop` for divergence detection and `TemporalHindsight` for autonomous state recovery (RCA/Repair).
+- **Structural Reorganization**: Migrated all core engine implementation files from `.mindforge/` logic directories to a standardized `bin/` domain architecture.
+- **Global Memory Sync**: Enhanced `SemanticHub` to support organizational-level knowledge sharing via `~/.mindforge/`.
+- **Hardenened ZTAI Beast Mode**: HSM-simulated signing for Tier 3 principals and automated audit integrity manifests.
+
+🚀 **MindForge v4.2.0 — The Security Revolution**
+
+This update introduces **Zero-Trust Agentic Identity (ZTAI)**, a core pillar of the MindForge enterprise security architecture. It establishes a DID-based identity system with cryptographic signing for all agentic actions, ensuring non-repudiable audit trails and tiered governance.
+
+### Key Pillars (v4.2.0)
+
+- **ZTAI Identity Engine**: Core manager for DID generation (`did:mindforge:<uuid>`) and Ed25519 key pair lifecycle.
+- **Cryptographic Audit Signing**: All reasoning traces and spans are signed by the originating agent, ensuring log integrity.
+- **Trust-Tiered Governance**: 4-tier authorization model (0-3) for granular permission control across the agentic mesh.
+- **Identity-Lock Engine**: Automated security gate in the `WaveExecutor` that blocks unauthorized Tier 3 actions.
+- **Trust Verifier**: Real-time cryptographic validation of the `AUDIT.jsonl` log for cross-session integrity.
+- **Beast Mode Hardening**: session-based key rotation and hardware security module (HSM) hook placeholders.
+
+---
+
+## [4.1.0] — MindForge Nexus (Observability & Tracing) — 2026-03-27
+
+🚀 **MindForge v4.1.0 — The Observability Revolution**
+
+This update introduces **MindForge Nexus**, a high-fidelity observability and tracing system designed for the agentic mesh. It enables deep visibility into agentic "thought chains" and parallel swarm execution through OpenTelemetry-compatible tracing.
+
+### Key Pillars (v4.1.0)
+
+- **Nexus Tracer Engine**: Core engine for managing hierarchical spans and trace context propagation across the mesh.
+- **Agentic Reasoning Tracing (ART)**: New audit event type `reasoning_trace` for capturing granular agentic thought cycles.
+- **Hierarchical Span Orchestration**: Universal ART fields (`trace_id`, `span_id`, `parent_span_id`) integrated into all audit events.
+- **Mesh-Integrated Tracing**: Direct injection of tracing protocols into the `Wave Executor` and `Swarm Controller`.
+- **Nexus Dashboard Spec**: Architectural blueprint for real-time trace visualization and reasoning heatmaps.
+- **ZTAI Observability**: Integrated trust-tier visibility for secure execution monitoring.
+
+---
+
+## [4.0.0] — Dynamic Multi-Agent Swarms (Agentic Mesh) — 2026-03-27
+
+🚀 **MindForge v4.0.0 — The Mesh Revolution**
+
+This landmark release introduces **Dynamic Multi-Agent Swarms (Agentic Mesh)**, shifting MindForge from sequential subagent execution to a parallel, task-aware, and verifiable cluster-based orchestration system. V4 enables mass-scale autonomous engineering through ephemeral specialist clusters and zero-trust resonance.
+
+### Key Pillars (v4.0.0)
+
+- **Dynamic Swarm Orchestration**: The new `SwarmController` analyzes task complexity and spawns ephemeral clusters of specialist personas in parallel.
+- **Micro-Persona Factory**: On-the-fly persona specialization using task-specific knowledge injection via `Context7`.
+- **Wave Executor (Mesh Mode)**: Refactored parallel execution engine with shared `SWARM-STATE` synchronization and leader-led synthesis.
+- **ZTAI (Zero-Trust Agentic Identity)**: DID-based cryptographic signing for swarm actions and multi-tier trust enforcement.
+- **Enterprise specialist Library**: 12+ pre-defined swarm templates including `AIEngineeringSwarm`, `IdentityTrustSwarm`, `DataMeshSwarm`, and `IncidentResponseSwarm`.
+- **HITL Governance Gates**: Human-in-the-loop decision gates for high-risk (Tier 3) architectural and compliance-heavy operations.
+
+---
+
 ## [3.0.0] — Reactive Autonomous Intelligence — 2026-03-27
 
 🚀 **MindForge v3.0.0 — The Architecture Revolution**
@@ -406,28 +517,28 @@ partners with full governance, observability, and enterprise integration.
 
 ### What ships in v1.0.0
 
-**36 commands** across 7 workflow categories  
-**10 core skill packs** with three-tier registry (Core/Org/Project)  
-**8 specialised agent personas** covering all engineering roles  
-**Wave-based parallel execution** with dependency graph and automatic compaction  
-**Enterprise integrations**: Jira, Confluence, Slack, GitHub, GitLab  
-**Three-tier governance**: Tier 1 (auto) / Tier 2 (peer review) / Tier 3 (compliance)  
-**Five non-bypassable compliance gates** (secret detection, CRITICAL findings, tests, CVEs, GDPR)  
-**Intelligence layer**: health engine, difficulty scorer, anti-pattern detector, team profiling  
-**Public skills registry**: npm-based `mindforge-skill-*` ecosystem  
-**CI/CD integration**: GitHub Actions, GitLab CI, Jenkins adapters  
-**@mindforge/sdk**: TypeScript SDK with client, event stream, and command builders  
-**Monorepo support**: npm/pnpm/Nx/Turborepo/Lerna workspace detection  
-**AI PR Review**: Claude API-powered code review with context loading  
-**Self-update mechanism**: version check, changelog diff, scope-preserving apply  
-**Version migration engine**: schema migration from v0.1.0 through v1.0.0  
-**Plugin system**: extensible via `mindforge-plugin-*` npm namespace  
-**Token usage optimiser**: profiling and efficiency strategies  
-**50-point production readiness checklist**: fully verified before this release  
-
-**20 Architecture Decision Records** documenting every major design choice  
-**15 test suites** with 3× consecutive run requirement  
-**Complete reference documentation**: commands, security, ADR index, threat model  
+**36 commands** across 7 workflow categories
+**10 core skill packs** with three-tier registry (Core/Org/Project)
+**8 specialised agent personas** covering all engineering roles
+**Wave-based parallel execution** with dependency graph and automatic compaction
+**Enterprise integrations**: Jira, Confluence, Slack, GitHub, GitLab
+**Three-tier governance**: Tier 1 (auto) / Tier 2 (peer review) / Tier 3 (compliance)
+**Five non-bypassable compliance gates** (secret detection, CRITICAL findings, tests, CVEs, GDPR)
+**Intelligence layer**: health engine, difficulty scorer, anti-pattern detector, team profiling
+**Public skills registry**: npm-based `mindforge-skill-*` ecosystem
+**CI/CD integration**: GitHub Actions, GitLab CI, Jenkins adapters
+**@mindforge/sdk**: TypeScript SDK with client, event stream, and command builders
+**Monorepo support**: npm/pnpm/Nx/Turborepo/Lerna workspace detection
+**AI PR Review**: Claude API-powered code review with context loading
+**Self-update mechanism**: version check, changelog diff, scope-preserving apply
+**Version migration engine**: schema migration from v0.1.0 through v1.0.0
+**Plugin system**: extensible via `mindforge-plugin-*` npm namespace
+**Token usage optimiser**: profiling and efficiency strategies
+**50-point production readiness checklist**: fully verified before this release
+
+**20 Architecture Decision Records** documenting every major design choice
+**15 test suites** with 3× consecutive run requirement
+**Complete reference documentation**: commands, security, ADR index, threat model
 
 ### Stable interface contract
 See ADR-020. All 36 commands, HANDOFF.json schema, AUDIT event types,

package/MINDFORGE.md

@@ -1,110 +1,79 @@
-# MINDFORGE.md — Project Constitution
-
-## NON-OVERRIDABLE RULES (read-only — these cannot be changed in MINDFORGE.md)
-
-The following CLAUDE.md behaviors are governance primitives and cannot be
-disabled or overridden by MINDFORGE.md:
-
-- Security auto-trigger for auth/payment/PII changes
-- Plan-first rule (no implementation without a PLAN)
-- Secret detection gate
-- AUDIT writing requirement
-- Critical security and secret-related quality gates
-
-Any attempted override is ignored and logged.
-
-## Parsing rule for multiline values
-Values wrapped in triple quotes are parsed as a verbatim multi-line string from
-the first `"""` to the next `"""`.
-
-## Model validation
-If a configured model is unavailable, fallback to `inherit` and warn.
-
-## Project identity
-NAME=MindForge
-VERSION=2.0.0
-DESCRIPTION=Enterprise agentic framework with Multi-Model Intelligence Layer
-MINDFORGE_VERSION_REQUIRED=2.0.0
-
-## Model preferences
-PLANNER_MODEL=claude-opus-4-5
-EXECUTOR_MODEL=claude-sonnet-4-5
-REVIEWER_MODEL=claude-sonnet-4-5
-VERIFIER_MODEL=claude-sonnet-4-5
-SECURITY_MODEL=claude-opus-4-5
-DEBUG_MODEL=claude-opus-4-5
-RESEARCH_MODEL=gemini-1.5-pro
-QA_MODEL=claude-4-5-sonnet
-QUICK_MODEL=claude-4-5-haiku
-
-## Cost Management
-MODEL_COST_WARN_USD=1.00
-MODEL_COST_HARD_LIMIT_USD=10.00
-MODEL_PREFER_CHEAP_BELOW_DIFFICULTY=2.0
-REQUIRE_CROSS_REVIEW=false
-
-## Execution behavior
-TIER1_AUTO_APPROVE=true
-WAVE_CONFIRMATION_REQUIRED=false
-AUTO_DISCUSS_PHASE=false
-VERIFY_PASS_RATE_WARNING_THRESHOLD=0.75
-COMPACTION_THRESHOLD_PCT=70
-MAX_TASKS_PER_PHASE=15
-
-## Quality standards
-MIN_TEST_COVERAGE_PCT=80
-MAX_FUNCTION_LINES=40
-MAX_CYCLOMATIC_COMPLEXITY=10
-REQUIRE_ADR_FOR_ALL_DECISIONS=false
-BLOCK_ON_MEDIUM_SECURITY_FINDINGS=false
-
-## Skills behavior
-ALWAYS_LOAD_SKILLS=security-review
-DISABLED_SKILLS=
-MAX_FULL_SKILL_INJECTIONS=3
-
-## Governance
-DISCUSS_PHASE_REQUIRED_ABOVE_DIFFICULTY=3.5
-ANTIPATTERN_SENSITIVITY=standard
-BLOCK_ON_HIGH_ANTIPATTERNS=false
-
-## Autonomous mode settings
-AUTO_MODE_DEFAULT_TIMEOUT_MINUTES=120
-AUTO_PUSH_ON_WAVE_COMPLETE=false
-AUTO_NODE_REPAIR_BUDGET=2
-AUTO_PLAN_AMBIGUITY_THRESHOLD=3.5
-SLACK_WEBHOOK_URL=
-
-## Browser Runtime
-BROWSER_PORT=7338
-BROWSER_HEADLESS=true
-DEV_SERVER_URL=http://localhost:3000
-AUTO_RUN_QA_AFTER_UI_WAVES=true
-BROWSER_IDLE_TIMEOUT_MINUTES=30
-AUTO_RUN_UI_REVIEW_AFTER_UI_WAVES=true
-UI_PHASE_ACCESSIBILITY_STANDARD=WCAG_AA
-
-## Project-specific agent instructions
-ADDITIONAL_AGENT_INSTRUCTIONS="""
-- Check packages/shared before creating utilities.
-- Backend middleware semantics follow Fastify conventions.
-- Keep dependency direction one-way from frontend to backend APIs.
-- Prefer date-fns for date manipulation.
-"""
-
-## Project-specific forbidden patterns
-PROJECT_FORBIDDEN_PATTERNS="""
-- No direct DB access from frontend packages
+# MINDFORGE.md — Parameter Registry (v4.1.0-alpha.nexus)
+
+## 1. IDENTITY & VERSIONING
+
+[NAME]    = MindForge
+[VERSION] = 4.2.0-alpha.ztai
+[STABLE]  = false
+[MODE]    = "Zero-Trust Identity"
+[REQUIRED_CORE_VERSION] = 4.2.0
+
+## 2. INTELLIGENCE TOGGLES (V4 UPDATES)
+
+[SWARM_ORCHESTRATION] = true
+[AUTO_SWARM_THRESHOLD] = 7.0
+[CONTEXT7_DEPTH] = "EXTENDED"
+[DYNAMISM_LEVEL] = 5
+[REACTIVE_MODE] = true
+[CONTEXT_SHARDING] = true
+[ADS_LOOP_ENFORCED]  = true
+[TEMPORAL_VISION]    = true
+[RAG_2_AUTO_SHADOW] = true
+[ENABLE_ART_TRACING] = true
+[ENABLE_ZTAI] = true
+[ZTAI_KEY_TYPE] = "Ed25519"
+[NEXUS_TRACE_RETENTION_DAYS] = 30
+
+---
+
+## 3. MODEL TOPOLOGY
+
+# Persona to Model mapping
+[PLANNER]  = claude-opus-4-5
+[EXECUTOR] = claude-sonnet-4-5
+[REVIEWER] = claude-sonnet-4-5
+[VERIFIER] = claude-sonnet-4-5
+[SECURITY] = claude-opus-4-5
+[DEBUG]    = claude-opus-4-5
+[RESEARCH] = gemini-1.5-pro
+[QA]       = claude-4-5-sonnet
+
+---
+
+## 4. GOVERNANCE & ECONOMICS
+
+# Limits and safety gates
+[COST_WARN_USD]       = 2.00
+[COST_HARD_LIMIT_USD] = 25.00
+[ADS_DEBATE_ROUNDS]   = 2
+[MIN_SOUL_SCORE]      = 7.0
+[REQUIRE_ADR]         = true
+[BLOCK_ON_SECURITY]   = true
+
+---
+
+## 5. RESOURCE GEOMETRY
+
+# Paths and ports
+[BROWSER_PORT]    = 7338
+[DASHBOARD_PORT]  = 7339
+[API_URL]         = <http://localhost:3000>
+[SHARD_RETAIN_DAYS] = 7
+
+---
+
+## 6. PROJECT CONSTRAINTS
+
+# Static rules for the agent
+[FORBIDDEN] = """
+- No direct DB access from frontend
 - No synchronous I/O in API handlers
-- No console.log in API services
+- No console.log in production services
 - No TODO comments in committed code
 """
 
-## Self-Building Skills
-AUTO_CAPTURE_SKILLS=false
-AUTO_CAPTURE_MIN_PATTERN_COUNT=2
-AUTO_CAPTURE_MIN_CONFIDENCE=0.75
-LEARN_MODEL=inherit
-MARKETPLACE_REGISTRY=https://registry.mindforge.dev/v1
-MARKETPLACE_DAILY_FETCH_LIMIT=50
-SKILL_QUALITY_MIN_SCORE=60
+[INSTRUCTIONS] = """
+- Check packages/shared before creating utilities.
+- Backend middleware follows Fastify conventions.
+- Date manipulation using date-fns only.
+"""

package/README.md

@@ -1,19 +1,34 @@
-# MindForge — Enterprise Agentic Framework (v3.0.0-rc1)
+# MindForge — Enterprise Agentic Framework (v5.0.0)
 
-MindForge turns Claude Code and Antigravity into production-grade engineering
-partners with governance, observability, and a reactive autonomous intelligence engine.
-Release published: v3.0.0-rc1.
+MindForge turns AI coding agents into production-grade engineering partners with governance, multi-cloud resilience, and a non-bypassable Sovereign Reason Enclave.
+Release published: v5.0.0-PRO.
+
+## Installation & Setup
+
+### 🚀 Quick Start (No Install)
+
+Run MindForge immediately for a specific runtime without a permanent installation:
 
-# Install
 ```bash
-npx mindforge-cc@latest
+npx mindforge-cc@latest --claude --global
 ```
 
-# Install V3 (Latest)
+### 🌍 Global Installation
+
+Enable system-wide `/mindforge` commands for your primary AI coding runtime:
+
 ```bash
 npm install -g mindforge-cc@latest
 ```
 
+### 📂 Local Project Setup
+
+Initialize MindForge in an existing repository with specialized agent identities:
+
+```bash
+npx mindforge-cc@latest --claude --local
+```
+
 ---
 
 ## Why MindForge
@@ -21,6 +36,14 @@ npm install -g mindforge-cc@latest
 AI coding agents degrade over long sessions. Context fills up. Quality drops.
 Decisions get forgotten. MindForge fixes that with:
 
+- **Multi-Cloud Arbitrage (v5.0)** — Dynamic routing and provider hedging with low-latency arbitrage.
+- **Sovereign Reason Enclave (v5.0)** — TEE-simulated reasoning isolation and sanitization for confidential workloads.
+- **Human-Agent Handover (v5.0)** — Nexus State Bundles and mid-wave steering injection.
+- **Autonomous FinOps (v4.3)** — Dynamic **C2C** (Confidence-to-Cost) routing and Agentic ROI tracking.
+- **Proactive Equilibrium (v4.3)** — Real-time **Wave Divergence** monitoring and autonomous state recovery.
+- **MindForge Nexus (v4.1)** — High-fidelity **ART** (Agentic Reasoning Tracing).
+- **Zero-Trust Identity (v4.2)** — DID-signed non-repudiable audit logs with HSM/Enclave support.
+- **Global Intelligence Mesh (v4.2)** — Cross-repo knowledge sharing and Ghost Pattern Detection.
 - **Context Sharding (v3)** — relevance-dense memory management (40% token savings)
 - **Adversarial Synthesis (v3)** — zero-drift logic through red/blue model debate
 - **Temporal Vision (v3)** — full history scrubbing and hindsight state repair
@@ -42,94 +65,22 @@ Decisions get forgotten. MindForge fixes that with:
 ---
 
 
-## Install
-
-### Claude Code (global)
-
-```bash
-npx mindforge-cc@latest --claude --global
-```
-
-
-### Claude Code (local)
-
-```bash
-npx mindforge-cc@latest --claude --local
-```
-
-### Quick Start
-
-```bash
-# Install the latest stable version
-npm install -g mindforge-cc
-
-# Or try the v2.0.0-alpha (latest features)
-npm install -g mindforge-cc@alpha
-
-# Or try the V3 Release (latest features)
-npm install -g mindforge-cc@latest
-```
-
-
-### Antigravity
-
-```bash
-npx mindforge-cc@latest --antigravity --global
-```
-
-Local installs use `agents/` by default. Legacy `.agent/` is supported for existing projects.
-
-Optional: add bin utilities on local install
-```bash
-npx mindforge-cc@latest --claude --local --with-utils
-```
-
-Optional: minimal project scaffolding
-```bash
-npx mindforge-cc@latest --claude --local --minimal
-```
-
-
-### Cursor
-
-```bash
-npx mindforge-cc@latest --cursor --local
-```
-
-
-### Gemini CLI
-
-```bash
-npx mindforge-cc@latest --gemini --global
-```
-
-
-### GitHub Copilot
-
-```bash
-npx mindforge-cc@latest --copilot --local
-```
+## 🛠️ Configuration & Runtimes
 
+MindForge adapts to your existing engineering environment via runtime flags:
 
-### OpenCode
+| Runtime | Global Command | Local Setup |
+| :--- | :--- | :--- |
+| **Claude Code** | `mindforge-cc --claude --global` | `mindforge-cc --claude --local` |
+| **Antigravity** | `mindforge-cc --antigravity --global` | `mindforge-cc --antigravity --local` |
+| **Cursor** | `mindforge-cc --cursor --global` | `mindforge-cc --cursor --local` |
+| **GitHub Copilot** | `mindforge-cc --copilot --global` | `mindforge-cc --copilot --local` |
+| **Gemini CLI** | `mindforge-cc --gemini --global` | `mindforge-cc --gemini --local` |
 
-```bash
-npx mindforge-cc@latest --opencode --global
-```
-
-
-### Specific Runtime (Universal)
-
-```bash
-npx mindforge-cc@latest --runtime <name>
-```
-
-
-### Multiple runtimes
-
-```bash
-npx mindforge-cc@latest --runtime claude,cursor --local
-```
+### Advanced Setup Options
+- **Combined Runtimes**: `mindforge-cc --runtime claude,cursor --local`
+- **With Utilities**: `mindforge-cc --local --with-utils` (Installs specialized bin scripts)
+- **Minimalist**: `mindforge-cc --local --minimal` (Only basic protocols, no persona library)
 
 ---
 
@@ -341,19 +292,38 @@ See `.mindforge/production/token-optimiser.md`.
 
 ---
 
----
+## What's new in v4.3 (Enterprise Mesh & Equilibrium)
+
+MindForge V4.3 matures the framework for enterprise mission-critical environments.
+
+- **Autonomous FinOps Hub**: Automated budget enforcement and dynamic model selection based on task complexity (C2C).
+- **Proactive Equilibrium**: Real-time divergence detection (Wave Monitoring) and autonomous repair loops.
+- **Structural Reorganization**: Production-grade `bin/` directory architecture for all core implementation logic.
+- **Enhanced ZTAI**: Asymmetric cryptographic signatures for all and simulated HSM support.
+
+## What's new in v4.2 (Identity & Memory)
+
+MindForge V4.2 focuses on **Identity** and **Memory** within the agentic swarm.
 
-## What's new in v3.0.0-rc1
+- **ZTAI Beast Mode**: Every agent action is cryptographically signed using asymmetric keys. Tier 3 agents use a simulated **Secure Enclave (HSM)** for top-level non-repudiation.
+- **Audit Integrity**: High-fidelity audit manifests generated with **Merkle-root** cumulative hash chains.
+- **Semantic Hub**: Synchronization between local repository memory and the global organizational store (`~/.mindforge/`).
+- **Ghost Pattern Detection**: Proactive risk detection that warns agents when a proposed design matches a past organizational failure.
 
-🚀 **The Reactive Intelligence Era**
+## What's new in v4.1 (Nexus)
 
-MindForge V3 transforms the framework from a "disciplined workflow engine" into a **Reactive Autonomous Intelligence**.
+🚀 **The High-Fidelity Observability Era**
+
+MindForge V4.1 introduces **Nexus**, the definitive observability layer for autonomous agents.
+
+- **Agentic Reasoning Tracing (ART)**: Deep visibility into "thought chains" and parallel mesh reasoning via hierarchical spans.
+- **Trace Context Propagation**: OpenTelemetry-compatible trace IDs across waves, tasks, and swarm clusters.
+- **Reasoning Heatmaps**: Automated visualization of adversarial disagreement and consensus synthesis.
+- **Mesh Visibility**: Live tracing of ephemeral specialist clusters in the agentic mesh.
+
+---
 
-- **Context Sharding (SRD)**: Achieve a **40% reduction in token waste** via relevance-dense memory management.
-- **Adversarial Decision Synthesis (ADS)**: Zero-drift architectural logic through a 3-model debate and SOUL-scoring engine.
-- **Temporal Vision**: Full-fidelity history navigation, hindsight state injection, and automated repair.
-- **RAG 2.0 (Auto-Shadowing)**: Background pattern retrieval from the local knowledge graph without manual prompts.
-- **V3 Core Guide**: New definitive architecture guide in `docs/architecture/V3-CORE.md`.
+## What's new in v4.0.0 (Swarm)
 
 ---
 

package/RELEASENOTES.md

@@ -1,41 +1,58 @@
-# MindForge v2.1.1 — Core Migration & Persona Expansion
-
+# MindForge v5.0.0 — Enterprise Pillars V, VI, VII
 ## Top Summary
+The v5.0.0 release completes the MindForge Enterprise architecture with the final three pillars: Multi-Cloud Arbitrage, Sovereign Reason Enclaves (SRE), and Dynamic Human-Agent Handover (DHH).
+
+## Highlights
+- **Pillar V: Multi-Cloud Arbitrage**: Intelligent routing across Vertex AI, Bedrock, and Azure with low-latency hedging and autonomous Provider Fallback protocols.
+- **Pillar VI: Sovereign Reason Enclaves (SRE)**: Simulated TEE-based reasoning isolation for confidential workloads, ensuring zero-visibility thought-chains and automatic sanitization of reasoning traces in global logs.
+- **Pillar VII: Dynamic Human-Agent Handover (DHH)**: Automated packaging of "Nexus State Bundles" for human review when confidence scores drop, featuring real-time "Human Steering" injection into the autonomous stream.
+- **Hardening: Beast Mode Phase 2**: Built-in Chaos Mode for provider reliability stress-testing and mandatory state hashing for all handover bundles.
+
+---
+
+# MindForge v4.3.0 — Enterprise Mesh & Proactive Equilibrium
 
-MindForge v2.1.1 is a major structural update that finalizes the migration of the MindForge framework into the MindForge ecosystem. This release establishes a unified `.agent/` asset structure, expands the persona count from 8 to 32+, and hardens the 4-pillar workflow (`plan`, `execute`, `verify`, `ship`) for enterprise-scale AI orchestration.
+## Top Summary
+MindForge v4.3.0 introduces the **Enterprise Intelligence Mesh**, finalizing the v4 roadmap with autonomous FinOps and self-healing reliability. This release also implements **ZTAI Beast Mode**, hardens agentic identity with asymmetric cryptographic signing, and introduces simulated Secure Enclaves (HSM) for Tier 3 principal agents.
 
 ## Highlights
 
-- **Unified .agent/ Structure**: 120+ framework assets consolidated for maximum compatibility across Claude Code, Antigravity, and Cursor.
-- **32-Persona Expansion**: Integrated advanced personas including `advisor-researcher`, `nyquist-auditor`, and `ui-auditor`.
-- **Zero-Watermark Integrity**: 100% removal of legacy rebranding fragments across the entire core and documentation.
-- **Enterprise Manifest**: Single source of truth via `file-manifest.json` for multi-project codebase intelligence.
-- **Hardened Governance**: Unified settings and non-bypassable quality gates across all runtimes.
+- **Pillar V: Autonomous FinOps Hub**: Dynamic **C2C (Confidence-to-Cost)** model routing and real-time Agentic ROI tracking.
+- **Pillar VI: Proactive Equilibrium**: Real-time **Wave Divergence** monitoring and autonomous **Temporal Hindsight** repair loops.
+- **Global Intelligence Mesh**: Synchronizes local project memory with a repository-agnostic organizational store (`~/.mindforge/`).
+- **Ghost Pattern Detection**: Proactive risk detection that warns agents when a proposed design matches a past organizational failure.
+- **ZTAI Beast Mode**: Every agent action in the mesh is now cryptographically signed using Ed25519 asymmetric keys.
+- **Secure Enclave (HSM) Simulation**: Tier 3 agents (Principal/Architect) now use simulated hardware-secured enclaves for signing.
+- **Audit Integrity Manifests**: Automated generation of Merkle-root based manifests for the `AUDIT.jsonl` log.
+- **Tiered Governance**: Full integration of Trust Tiers [0-3] across the 32-persona library.
 
 ## Developer Experience
 
-- **Consolidated Documentation**: Modernized guides for Skills Authoring, Architecture, and Persona-based engineering.
-- **Enhanced Hooks**: New lifecycle hooks for better context monitoring and real-time status reporting.
-- **Command Parity**: Full support for `/mindforge:browse`, `/mindforge:remember`, and `/mindforge:costs`.
+- **New Command Hooks**: Integration of `semantic-hub` and `ztai-archiver` into the core planning and execution loops.
+- **Enhanced PERSONAS.md**: Detailed trust-tier mappings for all specialists.
+- **Proactive Risk Warnings**: Real-time "Ghost Pattern" matches surfaced during the `/mindforge:plan-phase` process.
 
 ## Quality & Stability
 
-- **Grep-Audit Verified**: Verified zero residual branding through recursive deep scanning.
-- **Path-Aligned Workflows**: All 60+ workflows now strictly follow the v2.1.1 directory standards.
-- **Cross-IDE Tested**: Core features validated across multiple AI-native IDE runtimes.
+- **Verified Identity**: 100% of Tier 3 actions require valid cryptographic signatures.
+- **Tamper-Detection**: Audit manifestations allow for historical integrity verification of the entire session.
+- **Cross-Repo Intelligence**: Validated knowledge sharing between isolated project workspaces via the Semantic Hub.
 
-## Getting Started
+## Upgrade Notes
 
-- Install: `npx mindforge-cc@latest --claude --local`
-- Verify Health: `/mindforge:health`
-- Docs Entry: `README.md`
+- Projects on v4.1.0 should run `/mindforge:update --apply` to enable the ZTAI and Mesh features.
+- Initial global sync will occur automatically upon the first `plan-phase` or `execute-phase`.
+- Legacy memory stores will be semantically indexed for the global store during the first sync.
 
-## Upgrade Notes
+---
 
-- Projects on v1.0.0 or v2.0.0 should run `/mindforge:migrate` to align with the new path standards.
-- Residual custom skills in legacy folders may need manual relocation to `.agent/skills/`.
+# MindForge v4.1.0 — Nexus & High-Fidelity Observability
 
-## Breaking Changes
+## Highlights
+- **MindForge Nexus**: Agentic Reasoning Tracing (ART) for deep visibility into thought chains.
+- **Trace Context Propagation**: OpenTelemetry-compatible tracing across parallel waves and swarm clusters.
+
+---
 
-- Legacy `.agent/workflows` (without YAML frontmatter) is no longer automatically registered in Antigravity mode.
-- See `docs/upgrade.md` for detailed migration paths.
+# MindForge v2.1.1 — Core Migration & Persona Expansion
+...