@ralph-orchestrator/ralph-cli 2.7.0 → 2.8.1

package/CHANGELOG.md

@@ -6,6 +6,27 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [2.8.0] - 2026-03-10
+
+### Added
+
+- `ralph mcp serve` for exposing Ralph as a workspace-scoped MCP server over stdio.
+- User-scoped default config discovery and support for per-user Ralph defaults.
+- TUI update availability notices in the header.
+- Human guidance can now trigger a clean restart request flow.
+
+### Changed
+
+- Consolidated the core preset set around the maintained workflows and refreshed preset docs, examples, and evaluation tooling.
+- Refined PDD and code-task guidance to reduce Ralph-specific noise and improve handoff quality.
+
+### Fixed
+
+- Hardened multi-hat preset event contracts, late-event recovery, active hat display, and downstream debug/review handoffs.
+- Preserved runtime limits from core config when using hats.
+- Fixed headless loop runner backend selection.
+- Made restart resumption use the required single-command shell flow and added contract coverage for it.
+
 ## [2.7.0] - 2026-03-06
 
 ### Added
@@ -137,7 +158,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 - Modularized codebase and fixed TUI mode
 
-[Unreleased]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.7.0...HEAD
+[Unreleased]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.8.0...HEAD
+[2.8.0]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.7.0...v2.8.0
 [2.7.0]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.6.0...v2.7.0
 [2.6.0]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.5.1...v2.6.0
 [2.5.1]: https://github.com/mikeyobrien/ralph-orchestrator/compare/v2.5.0...v2.5.1

package/README.md

@@ -7,6 +7,7 @@
 [![Coverage](https://img.shields.io/badge/coverage-65%25-yellowgreen)](coverage/index.html)
 [![Mentioned in Awesome Claude Code](https://awesome.re/mentioned-badge.svg)](https://github.com/hesreallyhim/awesome-claude-code)
 [![Docs](https://img.shields.io/badge/docs-mkdocs-blue)](https://mikeyobrien.github.io/ralph-orchestrator/)
+[![Discord](https://img.shields.io/discord/1482421188700667906?label=Discord&logo=discord&logoColor=white)](https://discord.gg/XWUyeUNffh)
 
 A hat-based orchestration framework that keeps AI agents in a loop until the task is done.
 
@@ -72,6 +73,24 @@ ralph web --frontend-port 8080         # custom frontend port
 ralph web --legacy-node-api            # opt into deprecated Node tRPC backend
 ```
 
+### MCP Server Workspace Scope
+
+`ralph mcp serve` is scoped to a single workspace root per server instance.
+
+```bash
+ralph mcp serve --workspace-root /path/to/repo
+```
+
+Precedence is:
+
+1. `--workspace-root`
+2. `RALPH_API_WORKSPACE_ROOT`
+3. current working directory
+
+For multi-repo use, run one MCP server instance per repo/workspace. Ralph's current
+control-plane APIs persist config, tasks, loops, planning sessions, and collections
+under a single workspace root, so server-per-workspace is the deterministic model.
+
 **Requirements:**
 - Rust toolchain (for `ralph-api`)
 - Node.js >= 18 + npm (for the frontend)
@@ -99,6 +118,16 @@ npm run dev:legacy-server  # deprecated Node backend (optional)
 npm run test             # all frontend/backend workspace tests
 ```
 
+## MCP Server Mode
+
+Ralph can run as an MCP server over stdio for MCP-compatible clients:
+
+```bash
+ralph mcp serve
+```
+
+Use this mode from an MCP client configuration rather than an interactive terminal workflow.
+
 ## What is Ralph?
 
 Ralph implements the [Ralph Wiggum technique](https://ghuntley.com/ralph/) — autonomous task completion through continuous iteration. It supports:
@@ -107,7 +136,7 @@ Ralph implements the [Ralph Wiggum technique](https://ghuntley.com/ralph/) — a
 - **Hat System** — Specialized personas coordinating through events
 - **Backpressure** — Gates that reject incomplete work (tests, lint, typecheck)
 - **Memories & Tasks** — Persistent learning and runtime work tracking
-- **31 Presets** — TDD, spec-driven, debugging, and more
+- **5 Supported Builtins** — `code-assist`, `debug`, `research`, `review`, and `pdd-to-code-assist`, with more patterns documented as examples
 
 ## RObot (Human-in-the-Loop)
 
@@ -157,6 +186,13 @@ Contributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines
 
 MIT License — See [LICENSE](LICENSE) for details.
 
+## 💬 Community & Support
+
+Join the **ralph-orchestrator** community to discuss AI agent patterns, get help with your implementation, or contribute to the roadmap.
+
+* **Discord**: [Join our server](https://discord.gg/XWUyeUNffh) to chat with the maintainers and other users in real-time.
+* **GitHub Issues**: For bug reports and formal feature requests, please use the [Issue Tracker](https://github.com/mikeyobrien/ralph-orchestrator/issues).
+
 ## Acknowledgments
 
 - **[Geoffrey Huntley](https://ghuntley.com/ralph/)** — Creator of the Ralph Wiggum technique

package/npm-shrinkwrap.json

@@ -23,7 +23,7 @@
       "hasInstallScript": true,
       "license": "MIT",
       "name": "@ralph-orchestrator/ralph-cli",
-      "version": "2.7.0"
+      "version": "2.8.1"
     },
     "node_modules/@isaacs/balanced-match": {
       "engines": {
@@ -515,5 +515,5 @@
     }
   },
   "requires": true,
-  "version": "2.7.0"
+  "version": "2.8.1"
 }

package/package.json

@@ -1,5 +1,5 @@
 {
-  "artifactDownloadUrl": "https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.7.0",
+  "artifactDownloadUrl": "https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.8.1",
   "bin": {
     "ralph": "run-ralph.js"
   },
@@ -62,7 +62,7 @@
       "zipExt": ".tar.xz"
     }
   },
-  "version": "2.7.0",
+  "version": "2.8.1",
   "volta": {
     "node": "18.14.1",
     "npm": "9.5.0"