Band D closed. CORE's governance engine is now constitutionally coherent: no enforcement logic lives in src/, no impact classification lives in decorators, no operational threshold lives as a hardcoded literal. The rules that govern autonomous behaviour are declared in .intent/ and enforced from there.
This release closes the gap between a system that behaves constitutionally and one that is auditable as constituti | | `v2.4.0` | 2026-05-02 | High | v2.4.0 — Consequence Chain Band B closed. CORE's autonomous-operation gate G3 (Consequence Chain) is materialized. The Finding → Proposal → Approval → Execution → File changes → New findings causality chain is now queryable end-to-end. This release closes the operational form of the two-log problem — the gap between what was decided (action log) and what changed because of it (consequence log). Without that chain, autonomous operation cannot be audited, debugged, or trusted in regulated environm | | `v2.3.0` | 2026-04-24 | High | ## What ships Band A — Attribution closes. Workers now own every Blackboard INSERT; services may only UPDATE pre-attributed rows. The architectural cut is enforced constitutionally: `architecture.blackboard.worker_only_inserts` is active at blocking severity, so the invariant cannot silently erode. ## What closed - **ADR-011** — Workers own blackboard attribution; services do not post. The decision that Band A closes around. - **ADR-010** — Wired the §7 + §7a Finding/Proposal contract: termin | | `v2.2.2` | 2026-02-28 | Low | **Historic milestone**: CORE successfully governed its own major refactoring cycle with **zero constitutional violations** maintained throughout. ### Changed - Completed deep modularity refactoring (4 big files → 17 focused single-responsibility modules) - Hardened Mind/Will/Body separation (fixed layer leaks, tracing exclusions, race conditions) - Switched planning to deterministic `passive_gate` (no more unnecessary LLM calls) - Unified `IntentGuard.check_transaction` API for cleaner co | | `v2.2.0` | 2026-01-08 | Low | ## 🎯 Universal Workflow Pattern — The Operating System This release establishes the **foundational architecture for autonomous operations at scale**. CORE now has a universal orchestration model that closes all loops, enables self-correction everywhere, and provides the substrate for fully autonomous conversational operation. ### Philosophy Shift **Before 2.2.0**: Collection of autonomous capabilities with ad-hoc orchestration **After 2.2.0**: Universal workflow pattern that compose | | `v2.0.0` | 2025-11-28 | Low | # 🎯 Major Milestone: A2 Autonomy Achieved CORE has achieved **Level 2 Autonomy** - autonomous code generation with constitutional governance. ## 🚀 Key Achievements - ✨ **70-80% autonomous code generation success rate** (up from 0%) - 🎯 **100% semantic placement accuracy** (up from 45%) - 🧠 **Semantic infrastructure operational**: 513 symbols, 66 module anchors, 48 policy chunks - 🛡️ **Constitutional compliance enforcement** preventing AI agents from "going off the rails" - 🔄 * | | `v1.0.0` | 2025-10-01 | Low | # Changelog All notable changes to this project will be documented in this file. ## [1.0.0] - A1 Release - 2023-10-01 ### Added - **A1 Autonomy Activated**: The system can now autonomously execute simple, self-healing tasks via the `micro-proposal` workflow. - **Database as Single Source of Truth**: All operational knowledge (CLI commands, LLM resources, cognitive roles, domains) is now managed in a PostgreSQL database, eliminating YAML file drift. - **Transactional Integration Workf | | `v0.2.0` | 2025-08-15 | Low | # v0.2.0 — MVP: Autonomous Application Generation (2025-08-15) **Highlights** - First MVP that can autonomously scaffold a governed application from a high-level goal. - Nightly constitutional audit + capability drift checks in CI. - Starter Kit: default profile shipped. - CLI: `core-admin new`, `core-admin agent scaffold`, `core-admin proposals ...`. **Upgrade notes** - Use Python 3.11+. - Install with `poetry install`. - Run checks locally: `black --check . && ruff check . && pyte | ## Dependency audit - **Score**: 100/100 - **Total deps**: 0 - **Resolved**: 0 - **Unresolved**: 0 - **License conflicts**: 0 - **Warnings**: 0 - **Scanned**: 2026-04-27 ## Citation - HTML: https://www.freshcrate.ai/projects/CORE - Markdown: https://www.freshcrate.ai/projects/CORE.md - Dependencies JSON: https://www.freshcrate.ai/api/projects/CORE/deps _Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._