mindforge-cc 9.0.0 → 10.0.0

package/docs/tutorial.md

@@ -1,162 +0,0 @@
-# MindForge v2.1.1 — Full Tutorial (Install → Advanced Usage)
-
-This tutorial walks a new user from installation to advanced usage. It is written for engineers who want to adopt MindForge in a real codebase.
-
----
-
-## 1. Install MindForge
-
-### Claude Code (local, per repo)
-
-```bash
-npx mindforge-cc@latest --claude --local
-```
-
-### Antigravity
-
-```bash
-npx mindforge-cc@latest --antigravity --local
-```
-
-### Specific Runtime (Universal)
-
-```bash
-npx mindforge-cc@latest --runtime <name>
-```
-
----
-
-## 2. Verify Installation
-
-Open your agentic runtime (Claude Code, Antigravity, etc.) in your repo and run:
-
-```bash
-/mindforge:health
-```
-
-If anything is wrong, run the repair command:
-
-```bash
-/mindforge:health --repair
-```
-
----
-
-## 3. Create a New Project
-
-```bash
-/mindforge:init-project
-```
-
-This command scaffolds the framework in `.agent/` and initializes project planning:
-
-- `.planning/PROJECT.md`: High-level vision and roadmap.
-- `.planning/REQUIREMENTS.md`: Functional and technical specs.
-- `.planning/STATE.md`: Real-time project health and milestone status.
-
----
-
-## 4. Onboarding an Existing Codebase
-
-```bash
-/mindforge:map-codebase
-```
-
-This command generates architectural insights:
-
-- `.planning/ARCHITECTURE.md`: Module relationships and data flow.
-- `.planning/CONVENTIONS.md`: Inferred coding styles and patterns.
-
----
-
-## 5. Unified Workflow (Phase 1)
-
-MindForge uses a 4-pillar iterative cycle:
-
-```bash
-/mindforge:plan-phase 1     # discuss → research → plan
-/mindforge:execute-phase 1  # parallel execution of task plans
-/mindforge:verify-phase 1   # UAT + automated validation
-/mindforge:ship 1           # generate release output + PR
-```
-
----
-
-## 6. High-Performance Personas
-
-MindForge v2.1.1 provides 32+ specialized personas. Each is a "digital twin" of a senior role.
-
-- To list all personas: `/mindforge:personas --list`
-- To switch persona: `/mindforge:personas --set executor`
-
----
-
-## 7. Real-time Dashboard
-
-Observable engineering is core to MindForge. Start the dashboard to see live agent activity:
-
-```bash
-/mindforge:dashboard --start --open
-```
-
-Visit `http://localhost:7339` for the premium web interface.
-
----
-
-## 8. Knowledge & Memory Management
-
-MindForge records architectural decisions to prevent regression.
-
-- Capture a note: `/mindforge:note "Preference: Use absolute imports for shared libs"`
-- Search memory: `/mindforge:remember --search "api patterns"`
-
----
-
-## 9. Self-Building Skills
-
-Learn new capabilities from documentation URL or local files:
-
-```bash
-/mindforge:learn https://docs.nextjs.org "nextjs-best-practices"
-```
-
----
-
-## 10. Security & Governance
-
-MindForge enforces strict compliance gates.
-
-```bash
-/mindforge:security-scan --deep
-```
-
-This checks for secrets, dependency vulnerabilities, and architectural drift.
-
----
-
-## 11. CI/CD Integration
-
-MindForge is designed for non-interactive execution in CI environments.
-
-- Set `CI=true` in your environment.
-- Use `/mindforge:ship --auto-pr` for automated delivery.
-
-See `docs/ci-cd-integration.md` for full pipeline examples.
-
----
-
-## 12. Troubleshooting
-
-If you hit issues, consult these specialized guides:
-
-- `docs/troubleshooting.md`: Common technical fixes.
-- `docs/faq.md`: Frequent questions and architectural patterns.
-- `docs/upgrade.md`: Migration guides between versions.
-
----
-
-## 13. Next Steps
-
-1. Configure your team preferences in `docs/Templates/Profile/user-profile.md`.
-2. Start your first Phase 1 planning.
-3. Join our community: `/mindforge:join-discord`.

package/docs/upgrade.md

@@ -1,58 +0,0 @@
-# MindForge Upgrade Guide (v2.0.0)
-
-This guide covers upgrades from v0.6.0 to v2.0.0.
-
-## 1. Check version
-```bash
-node -e "console.log(require('./package.json').version)"
-```
-
-## 2. Update MindForge
-```
-/mindforge:update
-/mindforge:update --apply
-```
-
-If the update fails, run:
-```bash
-npx mindforge-cc@latest --claude --local --force
-```
-
-## 3. Migrate schema files
-
-### v0.6.0 to v1.0.0
-```
-/mindforge:migrate --from v0.6.0 --to v1.0.0
-```
-
-### v1.0.0 to v2.0.0
-```
-/mindforge:migrate --from v1.0.0 --to v2.0.0
-```
-MindForge v2 uses an **additive-only** migration strategy. Existing data is never deleted; only new fields (like `runtime`, `agent_id`, and `model_group`) are backfilled into your `AUDIT.jsonl` and `token-usage.jsonl` files.
-
-## 4. Verify
-```
-/mindforge:health
-/mindforge:status
-```
-
-## 5. Known breaking changes
-
-### v1.0.0
-- `VERIFY_PASS_RATE_WARNING_THRESHOLD` now uses 0.0–1.0 (was 0–100)
-- `AUDIT.jsonl` now requires `session_id` (auto-backfilled)
-- `HANDOFF.json` now requires `plugin_api_version`
-
-### v2.0.0
-- **Multi-Runtime Entry Points**: If installing for Cursor or Copilot, ensure you use the correct `--local` flag to generate `.cursorrules` or `copilot-instructions.md`.
-- **Preambles**: Non-slash runtimes now have a mandatory preamble in their entry files.
-
-## 6. Rollback
-If anything goes wrong, restore the migration backup:
-```
-ls .planning/migration-backup-*
-cp .planning/migration-backup-<timestamp>/* .planning/
-```
-
-Then re-run `/mindforge:migrate --dry-run`.

package/docs/usp-features.md

@@ -1,102 +0,0 @@
-# MindForge: 32 Unique Selling Points & Core Features (v8.0.0 Celestial)
-
-MindForge is the enterprise's **Agentic OS**, built on the **CADIA v6.2 (Cross-Agentic Deterministic Intelligence Architecture)** framework. It provides a self-healing, self-optimizing environment for autonomous agent execution at scale.
-
----
-
-## The 16 Pillars of Celestial Intelligence
-
-1.  **Pillar I: Semantic Vector Consensus** (FIM v2) - Distributed knowledge merging.
-2.  **Pillar II: Dynamic Blast Radius** (APO v2) - Real-time risk scoring (CADIA).
-3.  **Pillar III: Predictive Agentic Reliability** (RES) - Heuristics to detect/interrupt reasoning loops.
-4.  **Pillar IV: Supply Chain Trust** (ZTAI) - Cryptographically signed skills and binary attestation.
-5.  **Pillar V: Multi-Cloud Arbitrage** (MCA) - Task-to-model affinity routing.
-6.  **Pillar VII: Hierarchical Intent Orchestration** (Nexus) - Tiered reasoning capture.
-7.  **Pillar VIII: AgRevOps ROI Engine** (Enterprise) - Quantifying economic value.
-8.  **Pillar IX: Autonomous Resource Harvesting** (ARH) - Real-time token arbitrage.
-9.  **Pillar X: Neural Drift Remediation** (NDR) - Proactive self-healing.
-10. **Pillar VI: Sovereign Reason Enclaves** (ZK-Audit) - Privacy-preserving audit trails.
-11. **Pillar XI: Post-Quantum Agentic Security** (PQAS) - Lattice-based signatures and bypasses.
-12. **Pillar XII: Proactive Semantic Homing** (Homing) - Proactive intent harvesting and mesh healing.
-13. **Pillar XV: Unified Persistence Layer** (v8) - Sub-millisecond SQL reasoning audits.
-14. **Pillar XVI: Federated Mesh Synthesis** (v8) - Cryptographically signed knowledge handoffs.
-15. **Pillar XVII: Autonomous Skill Evolution** (v8) - Self-generating skills from reasoning traces.
-16. **Pillar XVIII: Orbital Governance** (v8) - Hardware-attested safety gates (HSM).
-
----
-
-## 30 Elite Unique Selling Points (USPs)
-
-1.  **File-Driven Governance**: Behavior defined by Markdown/JSON, auditable like code.
-2.  **Wave-Based Parallel Execution**: Dependency-ordered clusters for speed without chaos.
-3.  **Non-Bypassable Compliance Gates**: 5 mandatory safety checks (Secrets, CVEs, Tests, etc.).
-4.  **Session Compaction & Continuity**: Machine-readable handoffs to preserve state across context turns.
-5.  **Production-Grade Installer**: Built-in update/uninstall and schema migration suite.
-6.  **Immutable Audit Trail**: Append-only `AUDIT.jsonl` for total transparency.
-7.  **Modular Skill Registry**: Extend capabilities without altering core engine files.
-8.  **Autonomous "Walk-Away" (v2)**: Intelligence repair (RETRY → DECOMPOSE) for independent work.
-9.  **Persistent Visual QA**: Browser runtime with visual diff verification.
-10. **Adversarial Multi-Model Review**: Cross-model validation (Gemini/Claude) for critical paths.
-11. **Automatic Semantic Shadowing**: RAG 2.0 with background pattern retrieval.
-12. **Temporal History Scrubbing**: "Time-Travel" dashboard to inspect and steer past states.
-13. **Self-Building Skills Platform**: Capture patterns from docs/npm into validated `SKILL.md` files.
-14. **Semantic Relevance Density (SRD)**: 40% reduction in token waste via tiered context sharding.
-15. **Red-Team Decision Synthesis**: Zero architectural drift through debate loops.
-16. **Hindsight Injection**: Correct logic errors on-the-fly via the Nexus temporal injector.
-17. **Dynamic Swarm Mesh**: Orchestrated specialist sub-agents with shared `SWARM-STATE`.
-18. **DID-Signed Identity (ZTAI)**: Non-repudiable logs backed by Decentralized Identifiers.
-19. **Sentinel Runtime Attestation**: Cryptographic integrity checks for every logic module.
-20. **Reasoning Entropy Scoring (RES)**: Proactive interruption of semantic deadlocks.
-21. **Nexus Temporal Slider**: High-fidelity dashboard for reasoning navigation.
-22. **AgRevOps Financial Governance**: Real-time dollar-value mapping per agentic cycle.
-23. **CADIA Blast Radius Optimizer**: Real-time architectural risk assessment (0-100).
-24. **Sovereign ROI Arbitrage**: Automated steering to lowest-cost/highest-value model tiers.
-25. **Ghost Pattern Detection**: Automated planning-phase detection of past architectural failures.
-26. **Sentinel Execution Center**: Centralized JIT attestation and reasoning guardrail enforcement.
-27. **Unified Persistence (Celestial DB)**: High-performance SQL engine for sub-millisecond reasoning audits.
-28. **Federated Mesh Synthesis**: Secure, signed knowledge exchange via MindForge Bundles (.mfb).
-29. **Autonomous Skill Evolution**: Trace-to-Skill mining loop for self-improving reasoning patterns.
-30. **Hardware-Bound Attestation**: HSM/Biometric security gates for critical architectural mutations.
-
----
-
-## Sovereign Core Feature Set
-
-### 1. Unified Intelligence Layer
-Unified API for Anthropic, OpenAI, and Gemini with persona-based routing and budget enforcement.
-
-### 2. Autonomous Workflow Engine
-End-to-end lifecycle management: `/plan` → `/execute` → `/verify` → `/ship`.
-
-### 3. Agentic Observability
-Real-time web dashboard for audit streams, reasoning heatmaps, and financial metrics.
-
-### 4. Zero-Trust Security
-Mandatory DID signatures, JIT skill attestation, and "Default Deny" posture for sensitive files.
-
-### 5. Multi-Project Memory (Global Mesh)
-Organizational-level knowledge sharing via the Global Intelligence Mesh.
-
----
-
-## Execution Guide (v6.1 Alpha)
-
-```bash
-# Core Cycle
-/mindforge:init-project
-/mindforge:plan-phase 1
-/mindforge:execute-phase 1
-/mindforge:verify-phase 1
-/mindforge:ship 1
-
-# Sovereign Commands
-/mindforge:auto --phase 1    # Autonomous Walk-Away
-/mindforge:costs --roi       # Detailed ROI analysis
-/mindforge:cross-review      # Adversarial review
-/mindforge:memory sync       # Global Mesh sync
-```
-
----
-
-## Summary
-MindForge v8.0.0 **Celestial Orchestration** represents the pinnacle of the Agentic OS evolution. By combining **Unified SQL Persistence** and **Federated Mesh Synthesis** with the core Sentinel security layer, it provides the first framework capable of local reasoning speed at a global federated scale with hardware-attested governance.

package/docs/workflow-atlas.md

@@ -1,57 +0,0 @@
-# 🗺️ MindForge Workflow Atlas
-
-This document classifies every workflow and action in the MindForge `.github/` directory, explaining their triggers, roles, and governance tiers.
-
----
-
-## 🏗️ The 5-Layer Plane Architecture (v2.0.0 — Recommended)
-
-These workflows form the modular "Enterprise" architecture implemented for enterprise-grade autonomy.
-
-### 1. Control Plane (`control-plane.yml`)
-- **Primary Trigger**: `push` or `pull_request` to `main` or `develop`.
-- **Role**: The Central Nervous System. It runs the `change-classifier.js` to assign a **Governance Tier (1-3)**. It enforces security gates and routes execution to other planes.
-- **Priority**: High. This is the non-bypassable entry point.
-
-### 2. Execution Plane (`execution-plane.yml`)
-- **Primary Trigger**: `workflow_call` (Exclusively invoked by the Control Plane).
-- **Role**: The Muscle. It handles the environment setup, project health checks (`mindforge-cli.js health`), and executes the agent in `--headless` mode.
-- **Verification**: Runs `npm test` and `npm run lint`.
-
-### 3. AI Intelligence Layer (`ai-intelligence.yml`)
-- **Primary Trigger**: `workflow_call` (Invoked by Control Plane specifically on Pull Requests).
-- **Role**: The Brain. Performs adversarial code reviews using **Claude** and **GPT-4o**. Posts a combined architectural review as a PR comment.
-
-### 4. Release Plane (`release-plane.yml`)
-- **Primary Trigger**: `push` of a version tag (e.g., `git push origin v1.2.3`).
-- **Role**: The Logistics. Automates building the package, publishing to **npm**, and drafting a GitHub Release with changelogs.
-
-### 5. Observability Plane (`observability-plane.yml`)
-- **Primary Trigger**: `workflow_run` (Auto-runs whenever the "MindForge Control Plane" completes).
-- **Role**: The Memory. Collects metrics on token costs, success rates, and audit logs to generate a summary of CI effectiveness.
-
----
-
-## 🏛️ Maintenance & Legacy Workflows
-
-These are existing workflows that provide secondary check-points or manual controls.
-
-| Workflow | Trigger | Role | Status |
-| :--- | :--- | :--- | :--- |
-| `mindforge-ci.yml` | `push` to `main` or `feat/**` | Basic health/test check for feature branches. | **Active** |
-| `mindforge-autonomous.yml` | `schedule` (Daily) or Manual | Runs deep maintenance or long-running tasks. | **Active** |
-| `mindforge-ai-review.yml` | PR Label: `needs-review` | Label-triggered deep AI review. | **Fallback** |
-| `mindforge-release.yml` | Tag: `v*` | Original release script. | **Redundant** |
-| `mindforge-observability.yml`| `workflow_run` of "Core CI" | Original observability collector. | **Redundant** |
-
----
-
-## 🚦 Trigger Logic Summary
-
-| Event | Workflow Triggered | Primary Action |
-| :--- | :--- | :--- |
-| **New PR** | `control-plane.yml` | Classify → Security Scan → AI PR Review |
-| **Commit to main** | `control-plane.yml` | Governance check → Execution |
-| **Push Tag (v*)** | `release-plane.yml` | Publish to npm → Create GitHub Release |
-| **Manual Reset** | `mindforge-autonomous.yml` | Run /mindforge:auto on specific phase |
-| **Midnight** | `mindforge-autonomous.yml` | Daily health & autonomous cleanup |