omo-suites 1.9.2 → 1.11.0

package/CHANGELOG.md

@@ -5,6 +5,111 @@ All notable changes to OMO Suites will be documented in this file.
 Format based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.11.0] - 2026-03-25
+
+### Added
+- `omocs memory list|add|search|remove` — Workspace Memory Notes
+  - Workspace-scoped persistent notes stored in `~/.omocs/memory/`
+  - Supports fuzzy search and global notes via `--global`
+- `omocs completion <shell>` — Shell Completions
+  - Generates completion scripts for bash, zsh, and fish
+  - Includes subcommands and flags
+- Enhanced `omocs doctor`
+  - Added checks for Provider endpoint ping, Config file validity, oh-my-opencode installation, Skills directory, and Disk space
+- `omocs index build|show|clean` — Workspace Index
+  - Scans workspace to build a cacheable JSON index
+  - Detects tech stack, entry points, and key files
+  - Respects `.gitignore` and skips noisy directories
+
+## [1.10.0] - 2026-03-25
+
+### Added
+- `omocs init-deep [path]` — Auto-generate hierarchical AGENTS.md files per significant folder
+  - Scans project structure recursively, infers folder purpose, tech stack, naming conventions
+  - Generates root AGENTS.md with project overview + per-folder AGENTS.md for significant dirs
+  - Supports `--depth <n>` (default: 3) and `--dry-run` to preview
+  - Skips node_modules, .git, dist, build, .next, __pycache__, etc.
+- `omocs plan` — Prometheus-style interview planner for structured planning before coding
+  - Interactive mode asks 5 structured questions (goal, files, constraints, no-change, definition of done)
+  - Generates structured plan markdown: `.opencode/plans/plan-YYYY-MM-DD-HHmm.md`
+  - Supports `--output <path>` and `--non-interactive` for template generation
+- `omocs cost [profile]` — Profile cost calculator with model pricing estimates
+  - Shows per-agent cost breakdown (per invocation, per hour, per day)
+  - Supports `--compare <profile>` for side-by-side profile cost comparison
+  - Supports `--hours <n>` for custom workday projection (default: 8)
+  - Includes pricing for Claude Opus 4.6, Sonnet 4.6, GPT-5.3/5.4, Gemini 3.1 Pro, Kimi K2.5, DeepSeek
+- `omocs stats --dashboard` — Agent analytics dashboard with TUI bar charts
+  - Bar chart visualization for agent usage, token consumption, response times
+  - Aggregated stats stored in `~/.omocs/stats.json`
+  - Supports `--last <n>` to limit agents shown and `--sync` to import session data
+  - Enhanced existing stats command with daily token usage bar charts
+- `omocs check` — Comment quality checker for AI-generated code patterns
+  - Detects: obvious/redundant comments, vague TODOs, AI attribution, unexplained eslint-disable, @ts-ignore, commented-out code
+  - Reports findings with file:line references grouped by severity (high/medium/low)
+  - Supports `--fix` to auto-remove fixable AI slop comments
+  - Supports `--path <dir>` and `--severity <level>` filters
+- Plugin tools: `omocs_init_deep` and `omocs_check` registered as OpenCode plugin tools
+- System prompt injection updated with init-deep and check tool references
+
+## [1.9.2] - 2026-03-25
+
+### Added
+- `omocs export [filename]` — export all config to single JSON file
+- `omocs import <filename>` — import config with confirmation (supports --force)
+- `omocs diff <profile1> <profile2>` — side-by-side profile comparison with color-coded output
+- `omocs benchmark [prompt]` — compare response time across models (supports --models, --timeout)
+- `omocs mcp status` — MCP server health check with green/red status indicators
+- `omocs init --quick` — quick setup with auto-detection from env vars
+- Missing 67th task category: risk-management → agency-project-shepherd
+
+### Fixed
+- LSP glob detection bug — CSS, HTML, JSON, YAML, SQL, Markdown LSPs now detectable
+- Async/sync mismatch in config.ts
+- Stale PLUGIN_VERSION fallback
+- README updated to 28 agents, 67 task categories
+
+### Changed
+- API key encryption using AES-256-GCM (keys encrypted before storing in config)
+- Deduplicated `findPackageJson()` into single utility
+- Atomic config writes (write to temp file, rename — prevents corruption)
+- Improved error messages with contextual help suggestions
+- Moved `better-sqlite3` to optionalDependencies
+- CLI startup optimization (skip update check for --help/--version)
+
+## [1.9.1] - 2026-03-25
+
+### Added
+- 13 new Agency agents (from github.com/msitarzewski/agency-agents): security-engineer, devops-automator, mobile-app-builder, ai-engineer, rapid-prototyper, accessibility-auditor, performance-benchmarker, api-tester, brand-guardian, content-creator, growth-hacker, ux-researcher, project-shepherd
+- Agent system prompt markdown files for all 13 new agents
+- Total agents expanded from 15 → 28, task categories from 32 → 67
+
+### Changed
+- Plugin agent list header updated to reflect 28 agents, 67 task categories
+- `omocs_categories` tool description updated to 67 categories
+
+## [1.9.0] - 2026-03-07
+
+### Added
+- **`omocs status` command** — shows current provider info, API key (masked), default model, and config path
+- 1mr.tech token balance fetching in `omocs status` (tokens remaining, tokens used, key status)
+- **1mr.tech provider support in `omocs init`** (Step 5) — prompt for API key, validate via `GET /v1/usage`, select model
+- Auto-generates `opencode.json` and `oh-my-opencode.json` with 1mr.tech config
+- Graceful fallback when 1mr.tech API is unreachable (skip validation with warning)
+
+### Changed
+- **Launchboard rewritten to pull from OpenCode API** — removed SQLite/Drizzle dependency entirely, backend now proxies to OpenCode API (default `localhost:1337`)
+- New Launchboard routes: `/api/sessions`, `/api/board` (aggregated kanban)
+- Launchboard kanban board shows todo status columns: Pending → In Progress → Completed → Cancelled
+- Todo cards show content, priority badge, parent session; sidebar lists sessions with todo counts
+- Auto-refresh every 30 seconds; graceful "No OpenCode detected" screen when API unreachable
+- `OPENCODE_API_URL` env var for Launchboard configuration
+- **Launchboard auto-update system** — git + npm dual-mode auto-update with 5-minute cache, `/api/update` endpoint for status/trigger
+
+### Removed
+- Launchboard local database (`db/`, `drizzle.config`, `setup.sh`)
+- Launchboard MCP server, stats/rules pages, drag-and-drop (now read-only board)
+- Launchboard `columns`, `labels`, `tasks`, `workspaces`, `stats`, `rules` routes
+
 ## [1.8.0] - 2026-03-07
 
 ### Added

package/README.md

@@ -54,7 +54,7 @@ curl -fsSL https://raw.githubusercontent.com/TheFahmi/omocs/main/install.sh | ba
   Specialized AI roles with tuned models, thinking budgets, and automatic task routing across 67 categories.
 
 - **12 Plugin Tools** — [→ docs/plugin.md](docs/plugin.md)
-  Drop-in OpenCode plugin with system prompt injection — agents use tools automatically.
+  Drop-in OpenCode plugin with system prompt injection — agents use tools automatically. Includes `omocs_init_deep` and `omocs_check`.
 
 - **11 MCP Servers** — [→ docs/mcp.md](docs/mcp.md)
   One-click install for Postgres, Redis, Brave Search, Docker, Sentry, and more.
@@ -63,7 +63,7 @@ curl -fsSL https://raw.githubusercontent.com/TheFahmi/omocs/main/install.sh | ba
   Auto-detect your project stack and install the right language servers.
 
 - **Full CLI** — [→ docs/cli.md](docs/cli.md)
-  Profiles, agents, accounts, MCP, LSP, stats — all from the command line.
+  Profiles, agents, accounts, MCP, LSP, stats, cost estimation, comment quality checker — all from the command line.
 
 ## Quick Start
 
@@ -72,6 +72,10 @@ omocs init                      # Setup wizard
 omocs profile use ultra-mixed   # Best model for every task
 omocs agent route debugging     # See which agent handles what
 omocs doctor                    # Verify everything works
+omocs init-deep                 # Generate AGENTS.md hierarchy
+omocs cost opus-4.6-all         # Estimate costs per profile
+omocs check                     # Scan for AI slop comments
+omocs plan                      # Interactive planning before coding
 ```
 
 ## 🚀 Launchboard