diff --git a/.claude/rules/tool-priority.md b/.claude/rules/tool-priority.md index f7926fcc..5469001e 100644 --- a/.claude/rules/tool-priority.md +++ b/.claude/rules/tool-priority.md @@ -22,6 +22,10 @@ Always reach for these codingbuddy tools before any OMC equivalent: | `get_agent_details` | Agent profile and expertise lookup | | `get_project_config` | Tech stack, architecture, language settings | | `prepare_parallel_agents` | Ready-to-use prompts for parallel specialist agents | +| `pr_quality_report` | Run specialist agents on changed files for PR quality | +| `create_briefing` | Capture session state for cross-session recovery | +| `resume_session` | Load previous session briefing | +| `get_rule_impact_report` | Rule effectiveness analytics | --- diff --git a/CHANGELOG.md b/CHANGELOG.md index a5e8e9cf..008622c3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,57 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [5.2.0] - 2026-04-03 + +### Added + +#### PR Guardian +- `pr_quality_report` MCP tool for automated PR quality analysis (#1120) +- Quality Gate step in /ship skill — runs specialist checks before PR creation (#1123) + +#### Context Rescue +- `create_briefing` MCP tool for session state capture (#1122) +- `resume_session` MCP tool for cross-session recovery (#1124) +- Briefing recovery detection on session-start (#1125) + +#### Session Intelligence +- `SessionAnalyzer` module for git diff analysis and untested file detection (#1128) +- Intelligence Report in session stop hook — shows what you did, gaps, and insights (#1130) +- Auto-create GitHub issues for untested files (opt-in) (#1132) + +#### Rule Impact Dashboard +- Rule event tracking in MCP handlers (#1129) +- `rule-stats.json` writer service for aggregated rule metrics (#1131) +- `get_rule_impact_report` MCP tool for quantified rule effectiveness (#1133) + +#### Plugin Marketplace Phase 1 +- Plugin manifest schema and validator (#1135) +- `codingbuddy install` command — git-based plugin installation (#1136) +- `codingbuddy plugins` and `codingbuddy uninstall` commands (#1137) + +#### Plugin Marketplace Phase 2 +- `codingbuddy search` command for plugin discovery via registry (#1169) +- Registry resolver in install command — install by name (#1170) +- `codingbuddy update` command for plugin upgrades (#1171) + +#### Skill Discovery +- `list_skills` switched to filesystem-based discovery — all 48 skills now visible (#1162) +- `triggers` field in SKILL.md frontmatter for `recommend_skills` (#1163) +- CI validation test for skill/agent discoverability (#1164) + +### Changed + +#### TUI Refactor +- Removed TUI auto-open from session-start hook (#1112) +- Removed TUI auto-launch from MCP server bootstrap (#1113) +- Adopted single TUI multi-session model — `codingbuddy tui` manual start (#1111) + +### Fixed +- Flaky TUI tests — replaced `setTimeout(0)` tick with robust `flushInk` utility (#1118) +- TaskMaestro review cycle automation and idle worker nudging (#1143) +- File overlap detection includes implicit shared files (barrel exports, module files) (#1145) +- Auto-issue module review fixes — safe import pattern (#1149) + ## [5.1.3] - 2026-04-01 ### Added diff --git a/CLAUDE.md b/CLAUDE.md index fe044bbc..a864590b 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -34,7 +34,7 @@ codingbuddy/ **Principle:** codingbuddy first, OMC for unique features only. -- **codingbuddy FIRST**: `parse_mode`, `dispatch_agents`, `analyze_task`, `update_context`, `generate_checklist`, `search_rules` +- **codingbuddy FIRST**: `parse_mode`, `dispatch_agents`, `analyze_task`, `update_context`, `generate_checklist`, `search_rules`, `pr_quality_report`, `create_briefing`, `resume_session`, `get_rule_impact_report` - **OMC only**: LSP tools, AST grep, Python REPL, state/notepad, git-master, build-fix, deepsearch, team/swarm See [`.claude/rules/tool-priority.md`](.claude/rules/tool-priority.md) for full details. diff --git a/README.md b/README.md index 39d6919d..699d8805 100644 --- a/README.md +++ b/README.md @@ -100,17 +100,21 @@ Start coding with `PLAN`, `ACT`, `EVAL`, or `AUTO` keywords. --- -## What's New in v5.1.2 +## What's New in v5.2.0 -**StatusLine HUD** — Real-time session metrics right in the Claude Code UI: current mode, estimated cost, cache hit rate, and context usage. +**PR Guardian** — `pr_quality_report` MCP tool runs specialist agents on changed files, integrated with `/ship` quality gate for automated PR quality checks. -``` -◕‿◕ CB v5.1.2 | PLAN 🟢 | 12m | ~$0.23 | Cache:87% | Ctx:45% -``` +**Context Rescue** — `create_briefing` and `resume_session` tools enable cross-session recovery, preserving decisions and context across conversation boundaries. + +**Session Intelligence** — SessionAnalyzer generates Intelligence Reports in the stop hook, providing actionable insights from every coding session. + +**Rule Impact Dashboard** — Event tracking, stats writer, and impact reporting measure which rules actually prevent issues — proving your AI coding is improving. + +**Plugin Marketplace** — Full plugin lifecycle with `install`, `search`, `update`, `plugins`, and `uninstall` CLI commands, plus registry resolver for discovering community plugins. -**tmux Sidebar** — Run Claude Code inside tmux and get an auto-configured TUI dashboard sidebar with agent status, checklists, and metrics. +**Skill Discovery** — Filesystem-based `list_skills` with `triggers` frontmatter in SKILL.md for automatic skill activation based on context. -**Release Validation** — Two new MCP tools: `validate_plugin_manifest` for schema-based plugin.json validation, and `pre_release_check` for comprehensive pre-release checks with ecosystem auto-detection (Node.js, Python, Go, Rust, Java). +**TUI** — Single multi-session model with manual `codingbuddy tui` launch. Auto-open removed for cleaner MCP server startup. --- diff --git a/apps/mcp-server/README.md b/apps/mcp-server/README.md index 4c190823..e74ceb99 100644 --- a/apps/mcp-server/README.md +++ b/apps/mcp-server/README.md @@ -21,6 +21,11 @@ npx codingbuddy init |---------|-------------| | `codingbuddy init` | Analyze project and generate configuration | | `codingbuddy mcp` | Start MCP server (stdio mode by default) | +| `codingbuddy install ` | Install plugin from git URL or registry | +| `codingbuddy search ` | Search plugins in registry | +| `codingbuddy plugins` | List installed plugins | +| `codingbuddy update [name]` | Update outdated plugins | +| `codingbuddy uninstall ` | Uninstall plugin | | `codingbuddy --help` | Show help | | `codingbuddy --version` | Show version | @@ -45,6 +50,10 @@ npx codingbuddy init | `get_code_conventions` | **🆕** Get project code conventions from config files (tsconfig, eslint, prettier, editorconfig, markdownlint) | | `generate_checklist` | Generate contextual checklists including conventions domain | | `analyze_task` | Comprehensive task analysis with risk assessment | +| `pr_quality_report` | Run specialist agents on changed files for PR quality | +| `create_briefing` | Capture session state for cross-session recovery | +| `resume_session` | Load previous session briefing | +| `get_rule_impact_report` | Rule effectiveness analytics | ### MCP Prompts diff --git a/apps/mcp-server/package.json b/apps/mcp-server/package.json index 499eaa93..7481848c 100644 --- a/apps/mcp-server/package.json +++ b/apps/mcp-server/package.json @@ -1,6 +1,6 @@ { "name": "codingbuddy", - "version": "5.1.3", + "version": "5.2.0", "description": "Multi-AI Rules MCP Server - One source of truth for AI coding rules across all AI assistants", "author": "JeremyDev87", "license": "MIT", diff --git a/docs/tui-troubleshooting.md b/docs/tui-troubleshooting.md index c878da96..cf763c69 100644 --- a/docs/tui-troubleshooting.md +++ b/docs/tui-troubleshooting.md @@ -553,6 +553,16 @@ ps aux | grep codingbuddy - For npx users: ensure you're using the latest published version. - For local development: run `yarn build && yarn build:tui` in `apps/mcp-server/`. +## v5.2.0 Changes + +Starting with v5.2.0, the TUI model has changed: + +- **Auto-open removed** — The TUI no longer launches automatically with the MCP server. This eliminates stdout conflicts and simplifies server startup. +- **Manual start** — Use `codingbuddy tui` (or `npx codingbuddy tui`) to launch the TUI dashboard manually. +- **Single multi-session model** — One TUI instance connects to all running MCP server instances, displaying sessions in a unified view. + +If you were relying on `--tui` flag or auto-open behavior, update your workflow to use `codingbuddy tui` as a separate command. + ## Related Documentation - [TUI User Guide](./tui-guide.md) - How to run and configure the TUI diff --git a/packages/claude-code-plugin/.claude-plugin/plugin.json b/packages/claude-code-plugin/.claude-plugin/plugin.json index 3e2aa97f..07821a68 100644 --- a/packages/claude-code-plugin/.claude-plugin/plugin.json +++ b/packages/claude-code-plugin/.claude-plugin/plugin.json @@ -1,6 +1,6 @@ { "name": "codingbuddy", - "version": "5.1.3", + "version": "5.2.0", "description": "PLAN/ACT/EVAL workflow with auto-detection, specialist agents, and reusable skills for systematic TDD development", "author": { "name": "JeremyDev87", diff --git a/packages/rules/package.json b/packages/rules/package.json index c0cbf699..9ec91667 100644 --- a/packages/rules/package.json +++ b/packages/rules/package.json @@ -1,6 +1,6 @@ { "name": "codingbuddy-rules", - "version": "5.1.3", + "version": "5.2.0", "description": "AI coding rules for consistent practices across AI assistants", "main": "index.js", "types": "index.d.ts",