opc-agent 4.1.24 → 4.2.0

package/CHANGELOG.md

@@ -1,119 +1,59 @@
-# Changelog
-
-All notable changes to OPC Agent will be documented in this file.
-
-The format is based on [Keep a Changelog](https://keepachangelog.com/), and this project adheres to [Semantic Versioning](https://semver.org/).
-
-## [4.1.16] - 2025-04-18
-
-### Added
-- Full TUI terminal chat with streaming, markdown rendering, and slash commands
-- One-line install script for macOS/Linux (`install.sh`) and Windows (`install.ps1`)
-- `opc doctor` now checks tool availability and wiring (tools health check)
-
-### Fixed
-- TUI input handling and display improvements
-
-## [4.1.15] - 2025-04-15
-
-### Added
-- 20 new integration tools: Jira, Slack, Notion, Linear, Confluence, Trello, Asana, Zendesk, HubSpot, Salesforce, and more
-- Total built-in tools count reaches **53**
-
-## [4.1.14] - 2025-04-12
-
-### Fixed
-- Process keep-alive reliability — agents no longer exit unexpectedly on channel disconnect
-- 33 built-in tools fully wired to runtime (previously some were declared but not connected)
-
-## [4.1.12] - 2025-04-08
-
-### Added
-- Memory compaction — distilled memory reduces storage and improves recall relevance
-- Automatic deduplication of similar memory entries
-
-## [4.1.11] - 2025-04-05
-
-### Added
-- Knowledge Evolve Engine v2.1 — improved clustering, deduplication, and refinement pipeline
-- Ollama-local knowledge distillation (zero API cost)
-
-## [4.1.8] - 2025-03-28
-
-### Added
-- Voice message support (STT/TTS)
-- Whisper integration for speech-to-text
-- Azure Speech and Volcano Engine TTS providers
-- Voice channel support in Telegram and Web UI
-
-## [4.1.7] - 2025-03-22
-
-### Added
-- 40 built-in skills: productivity, knowledge, creative, and developer skill packs
-- ProactiveAgent — agents can initiate conversations based on triggers and schedules
-- `opc skill list` and `opc skill add` CLI commands
-
-## [4.1.6] - 2025-03-18
-
-### Added
-- SQLite persistent memory with full-text search (FTS5)
-- AgentSkills.io format support for skill discovery and sharing
-- Memory search across conversations with relevance ranking
-
-### Changed
-- Default memory provider switched from JSON file to SQLite
-
-## [4.1.5] - 2025-03-14
-
-### Added
-- SkillLearner — agents can learn new skills from demonstrations
-- UserProfiler — automatic user preference tracking and personalization
-
-## [4.1.4] - 2025-03-10
-
-### Added
-- `.npmignore` for cleaner package publishing
-- Local cron scheduler (no external dependencies)
-- FileBackedStore for persistent key-value storage
-
-### Fixed
-- Package size reduced by 60% with proper npmignore
-
-## [4.1.3] - 2025-03-06
-
-### Added
-- Smart model recommendation based on task complexity and available providers
-- `opc setup` auto-detects local Ollama models
-
-## [4.1.2] - 2025-03-02
-
-### Changed
-- Ollama-first UX overhaul — local models are now the default, cloud providers optional
-- `opc init` defaults to Ollama if detected, guides API key setup otherwise
-
-### Fixed
-- Ollama connection reliability on slow startup
-
-## [4.1.1] - 2025-02-26
-
-### Changed
-- Studio UI improvements: better agent card layout, real-time status indicators
-- Dark mode support in Studio
-
-### Fixed
-- Studio WebSocket reconnection on network interruption
-
-## [4.1.0] - 2025-02-20
-
-### Added
-- Initial CLI with `opc init`, `opc run`, `opc chat`, `opc studio` commands
-- Web-based Studio GUI at `http://localhost:4000`
-- OAD (Open Agent Definition) YAML configuration format
-- Multi-channel support: Telegram, Discord, Slack, WeChat, Email
-- OpenAI, Anthropic, Ollama, Azure model providers
-- Basic memory with learn/recall cycle
-- MCP Protocol server and client
-- A2A Protocol support
-- OpenTelemetry tracing
-- `opc doctor` with 13 health checks
-- `opc eval` evaluation framework
+# Changelog
+
+## [4.2.0] - 2026-04-21
+
+### New Features
+- **Priority Queue / Fast Mode** — Priority-aware request routing with per-session `/fast` toggle. Fast-mode requests are processed first and routed through provider priority endpoints (OpenAI, Anthropic, Google). Includes concurrency control, batch tier, and custom provider endpoint registration.
+- **Gateway Registry** — Advanced multi-gateway tool provider pattern. Register multiple remote tool gateways with subscription-based access, per-tool quota tracking, auto-retry with backoff, and unified invocation routing across gateways. Complements the existing single-gateway `ToolGateway`.
+
+### Improvements
+- New `FastModeManager` for per-session priority state management
+- `PriorityQueue` with weighted dequeue, provider concurrency limits, and drain support
+- `ToolGatewayRegistry` for routing tool calls across multiple gateway providers
+
+## [2.0.0] - 2026-04-18
+
+### Major Features
+- **Interactive CLI** (`opc chat`) — Full TUI with streaming, slash commands, history
+- **Daemon Mode** (`opc start/stop/status`) — Run agents as background processes
+- **Cron Scheduler** — Built-in job scheduling with cron expressions
+- **Autonomous Skill Learning** — Agents create and improve skills from experience
+- **Sub-Agent System** — Spawn parallel sub-agents for task delegation
+- **Built-in Tools** — File operations, web fetch, shell exec, datetime
+- **MCP Client** — Connect to external MCP servers via JSON-RPC
+- **Telegram Channel** — Dual-mode (polling + webhook) with Markdown support
+- **Discord Channel** — Gateway WebSocket with auto-reconnect
+- **Slack Channel** — Real Events API + chat.postMessage
+- **SOUL.md + CONTEXT.md** — Agent personality and project context files
+- **Analytics** — Wired into runtime for message tracking, skill usage, errors
+
+### Enhanced
+- `/health` endpoint returns comprehensive agent info
+- `opc init` generates SOUL.md, CONTEXT.md, and richer project templates
+- OAD config supports scheduler, learning, and tools sections
+- 204 tests passing
+
+### CLI Commands
+init, chat, run, dev, start, stop, status, jobs, skills, info, build, test, analytics, brain, logs, score, search, deploy, publish, install, plugin, tool, workflow, migrate
+
+## 1.4.0 (2026-04-18)
+- feat: wire Analytics into AgentRuntime (message timing, skill usage, error tracking)
+- feat: expose analytics snapshot on /health and /api/dashboard endpoints
+- feat: enhanced /health endpoint with agent name, version, uptime, memory type, skills, channels
+- feat: Slack channel — real Events API webhook server + chat.postMessage via fetch
+- feat: WebChannel metadata setters (version, memory type, skills, channels, analytics provider)
+- feat: AgentRuntime.getAnalytics() and getConfig() accessors
+
+## 1.3.1 (2026-04-17)
+- fix: remove residual DTV/marketplace references
+- fix: duplicate WatchPattern export
+
+## 1.3.0 (2026-04-17)
+- feat: Traces collection (OpenTelemetry-style)
+- feat: DeepBrain exporter
+- feat: brain/logs/score CLI commands
+
+## 1.2.0
+- Initial public release
+- 11 channels, plugins, analytics
+- Declarative OAD configuration

package/COMPETITIVE-GAP.md

@@ -1,92 +1,92 @@
-# OPC vs OpenClaw vs Hermes — 体验差距对照表
-
-## 状态说明
-- ✅ OPC 已有且不差于竞品
-- 🟡 OPC 有但不如竞品
-- ❌ OPC 缺失，竞品有
-- 🔵 OPC 独有优势
-
----
-
-## 一、安装 & 初始化
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 1 | 一行安装 | `npx openclaw@latest init` | `curl \| sh` one-liner | `npm i -g opc-agent && opc init` | 🟡 两步 vs 一步 | P1 |
-| 2 | 本地模型支持 | ✅ 支持 Ollama | ✅ 支持 | ✅ v4.1.4 Ollama-first | ✅ | - |
-| 3 | 智能模型推荐 | ❌ 手动选 | ❌ 手动选 | ✅ 硬件检测 + 分级推荐 | 🔵 领先 | - |
-| 4 | Setup Wizard | 交互式向导 | `hermes setup` 向导 | 交互式模板+LLM选择 | ✅ | - |
-| 5 | 迁移工具 | - | 从 OpenClaw 迁移 | ❌ 无迁移工具 | ❌ | P3 |
-| 6 | Doctor 诊断 | ❌ 无 | ❌ 无 | ✅ `opc doctor` 11项检查 | 🔵 领先 | - |
-| 7 | `npx opc-agent init` 一行启动 | - | - | ❌ 需要先全局安装 | 🟡 | P1 |
-
-## 二、自主学习 & 技能进化
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 8 | Agent 自写 Skill | ✅ AgentSkills | ✅ 自动创建 Skill MD | ❌ 代码未实现 | ❌ 关键差距 | P0 |
-| 9 | 学习触发条件 | 自动 | 5步闭环(execute→evaluate→extract→refine→retrieve) | ❌ | ❌ | P0 |
-| 10 | Skill 格式标准 | AgentSkills | agentskills.io MD | 无标准 | ❌ | P0 |
-| 11 | 预置 Skill 数量 | 100+ ClawHub | 40+ bundled | 12 模板 | 🟡 | P2 |
-| 12 | Skill 市场 | ClawHub | 社区共享 | ❌ 无 | ❌ | P3 |
-| 13 | 知识进化(evolve) | ❌ | ❌ | ✅ DeepBrain evolve 架构 | 🔵 领先 | - |
-| 14 | 多层知识体系 | ❌ | ❌ | ✅ 行业→岗位→工位→Agent | 🔵 领先 | - |
-
-## 三、用户建模 & 记忆
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 15 | USER.md 用户画像 | Workspace MD | ✅ USER.md + Honcho | ❌ 无 | ❌ | P1 |
-| 16 | SOUL.md 人格 | ✅ | ❌ | ✅ | ✅ | - |
-| 17 | 持久记忆 | SQLite + Memory | SQLite + FTS5 | FileBackedStore JSON | 🟡 | P2 |
-| 18 | 对话历史搜索 | ✅ | FTS5 全文搜索 | ❌ | ❌ | P2 |
-
-## 四、渠道 & 交互
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 19 | 多渠道(TG/Discord/Slack) | ✅ 全部 | ✅ TG/Discord/Slack | ✅ 代码有 | ✅ | - |
-| 20 | Web UI 聊天 | ✅ | ✅ | ✅ | ✅ | - |
-| 21 | Studio 管理面板 | 无(CLI only) | 无(CLI only) | ✅ OPC Studio | 🔵 领先 | - |
-| 22 | CLI 对话模式 | ❌ | ✅ `hermes chat` | ❌ | 🟡 | P2 |
-
-## 五、开发者体验
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 23 | TypeScript SDK | ❌ | ❌ | ✅ | 🔵 领先 | - |
-| 24 | A2A 协议 | ❌ | ❌ | ✅ | 🔵 领先 | - |
-| 25 | MCP 协议 | ✅ | ✅ | ✅ | ✅ | - |
-| 26 | Workstation 模板 | ❌ | ❌ | ✅ 100+ 角色 | 🔵 领先 | - |
-| 27 | `npx opc-agent` 零安装运行 | ✅ npx openclaw | ❌ | ❌ | 🟡 | P1 |
-
-## 六、自动化 & 调度
-
-| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
-|---|--------|----------|--------|----------|------|--------|
-| 28 | Cron 定时任务 | ✅ Heartbeat | ❌ | ✅ cron-engine | ✅ | - |
-| 29 | 主动触达 | ✅ Proactive | ❌ | 🟡 有 cron 但无主动逻辑 | 🟡 | P2 |
-
----
-
-## 优先级行动计划
-
-### P0 — 今天必须启动（自主学习闭环）
-1. **#8 Agent 自写 Skill** — 实现 auto-skill-creation
-2. **#9 学习触发条件** — 实现 5 步闭环
-3. **#10 Skill 格式标准** — 采用 agentskills.io 兼容格式
-
-### P1 — 今天尽量完成（安装体验 + 用户建模）
-4. **#1/#7/#27 一行安装** — 支持 `npx opc-agent init`
-5. **#15 USER.md 用户建模** — Agent 自动学习用户偏好
-
-### P2 — 本周完成
-6. **#11 更多预置 Skill** — 扩充到 40+
-7. **#17 SQLite 持久记忆** — 替代 JSON
-8. **#18 对话历史搜索** — FTS5
-9. **#22 CLI 对话模式** — `opc chat`
-10. **#29 主动触达** — Agent 主动发消息
-
-### P3 — 后续
-11. **#5 迁移工具** — 从 OpenClaw/Hermes 迁移
-12. **#12 Skill 市场** — OPC Hub
+# OPC vs OpenClaw vs Hermes — 体验差距对照表
+
+## 状态说明
+- ✅ OPC 已有且不差于竞品
+- 🟡 OPC 有但不如竞品
+- ❌ OPC 缺失，竞品有
+- 🔵 OPC 独有优势
+
+---
+
+## 一、安装 & 初始化
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 1 | 一行安装 | `npx openclaw@latest init` | `curl \| sh` one-liner | `npm i -g opc-agent && opc init` | 🟡 两步 vs 一步 | P1 |
+| 2 | 本地模型支持 | ✅ 支持 Ollama | ✅ 支持 | ✅ v4.1.4 Ollama-first | ✅ | - |
+| 3 | 智能模型推荐 | ❌ 手动选 | ❌ 手动选 | ✅ 硬件检测 + 分级推荐 | 🔵 领先 | - |
+| 4 | Setup Wizard | 交互式向导 | `hermes setup` 向导 | 交互式模板+LLM选择 | ✅ | - |
+| 5 | 迁移工具 | - | 从 OpenClaw 迁移 | ❌ 无迁移工具 | ❌ | P3 |
+| 6 | Doctor 诊断 | ❌ 无 | ❌ 无 | ✅ `opc doctor` 11项检查 | 🔵 领先 | - |
+| 7 | `npx opc-agent init` 一行启动 | - | - | ❌ 需要先全局安装 | 🟡 | P1 |
+
+## 二、自主学习 & 技能进化
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 8 | Agent 自写 Skill | ✅ AgentSkills | ✅ 自动创建 Skill MD | ❌ 代码未实现 | ❌ 关键差距 | P0 |
+| 9 | 学习触发条件 | 自动 | 5步闭环(execute→evaluate→extract→refine→retrieve) | ❌ | ❌ | P0 |
+| 10 | Skill 格式标准 | AgentSkills | agentskills.io MD | 无标准 | ❌ | P0 |
+| 11 | 预置 Skill 数量 | 100+ ClawHub | 40+ bundled | 12 模板 | 🟡 | P2 |
+| 12 | Skill 市场 | ClawHub | 社区共享 | ❌ 无 | ❌ | P3 |
+| 13 | 知识进化(evolve) | ❌ | ❌ | ✅ DeepBrain evolve 架构 | 🔵 领先 | - |
+| 14 | 多层知识体系 | ❌ | ❌ | ✅ 行业→岗位→工位→Agent | 🔵 领先 | - |
+
+## 三、用户建模 & 记忆
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 15 | USER.md 用户画像 | Workspace MD | ✅ USER.md + Honcho | ❌ 无 | ❌ | P1 |
+| 16 | SOUL.md 人格 | ✅ | ❌ | ✅ | ✅ | - |
+| 17 | 持久记忆 | SQLite + Memory | SQLite + FTS5 | FileBackedStore JSON | 🟡 | P2 |
+| 18 | 对话历史搜索 | ✅ | FTS5 全文搜索 | ❌ | ❌ | P2 |
+
+## 四、渠道 & 交互
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 19 | 多渠道(TG/Discord/Slack) | ✅ 全部 | ✅ TG/Discord/Slack | ✅ 代码有 | ✅ | - |
+| 20 | Web UI 聊天 | ✅ | ✅ | ✅ | ✅ | - |
+| 21 | Studio 管理面板 | 无(CLI only) | 无(CLI only) | ✅ OPC Studio | 🔵 领先 | - |
+| 22 | CLI 对话模式 | ❌ | ✅ `hermes chat` | ❌ | 🟡 | P2 |
+
+## 五、开发者体验
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 23 | TypeScript SDK | ❌ | ❌ | ✅ | 🔵 领先 | - |
+| 24 | A2A 协议 | ❌ | ❌ | ✅ | 🔵 领先 | - |
+| 25 | MCP 协议 | ✅ | ✅ | ✅ | ✅ | - |
+| 26 | Workstation 模板 | ❌ | ❌ | ✅ 100+ 角色 | 🔵 领先 | - |
+| 27 | `npx opc-agent` 零安装运行 | ✅ npx openclaw | ❌ | ❌ | 🟡 | P1 |
+
+## 六、自动化 & 调度
+
+| # | 体验点 | OpenClaw | Hermes | OPC 现状 | 差距 | 优先级 |
+|---|--------|----------|--------|----------|------|--------|
+| 28 | Cron 定时任务 | ✅ Heartbeat | ❌ | ✅ cron-engine | ✅ | - |
+| 29 | 主动触达 | ✅ Proactive | ❌ | 🟡 有 cron 但无主动逻辑 | 🟡 | P2 |
+
+---
+
+## 优先级行动计划
+
+### P0 — 今天必须启动（自主学习闭环）
+1. **#8 Agent 自写 Skill** — 实现 auto-skill-creation
+2. **#9 学习触发条件** — 实现 5 步闭环
+3. **#10 Skill 格式标准** — 采用 agentskills.io 兼容格式
+
+### P1 — 今天尽量完成（安装体验 + 用户建模）
+4. **#1/#7/#27 一行安装** — 支持 `npx opc-agent init`
+5. **#15 USER.md 用户建模** — Agent 自动学习用户偏好
+
+### P2 — 本周完成
+6. **#11 更多预置 Skill** — 扩充到 40+
+7. **#17 SQLite 持久记忆** — 替代 JSON
+8. **#18 对话历史搜索** — FTS5
+9. **#22 CLI 对话模式** — `opc chat`
+10. **#29 主动触达** — Agent 主动发消息
+
+### P3 — 后续
+11. **#5 迁移工具** — 从 OpenClaw/Hermes 迁移
+12. **#12 Skill 市场** — OPC Hub

package/CONTRIBUTING.md

@@ -1,36 +1,36 @@
-# Contributing
-
-Thanks for your interest in contributing!
-
-## Getting Started
-
-1. Fork the repo
-2. Clone your fork
-3. Install dependencies: `npm install`
-4. Create a branch: `git checkout -b feat/my-feature`
-5. Make your changes
-6. Run tests: `npm test`
-7. Commit: `git commit -m "feat: description"`
-8. Push and open a PR
-
-## Commit Convention
-
-- `feat:` New feature
-- `fix:` Bug fix
-- `docs:` Documentation
-- `test:` Tests
-- `refactor:` Refactoring
-- `chore:` Build/tooling
-
-## Code Style
-
-- TypeScript
-- Run `npm run lint` before committing (if available)
-
-## Questions?
-
-Open a Discussion or Issue.
-
-## License
-
-By contributing, you agree that your contributions will be licensed under Apache-2.0.
+# Contributing
+
+Thanks for your interest in contributing!
+
+## Getting Started
+
+1. Fork the repo
+2. Clone your fork
+3. Install dependencies: `npm install`
+4. Create a branch: `git checkout -b feat/my-feature`
+5. Make your changes
+6. Run tests: `npm test`
+7. Commit: `git commit -m "feat: description"`
+8. Push and open a PR
+
+## Commit Convention
+
+- `feat:` New feature
+- `fix:` Bug fix
+- `docs:` Documentation
+- `test:` Tests
+- `refactor:` Refactoring
+- `chore:` Build/tooling
+
+## Code Style
+
+- TypeScript
+- Run `npm run lint` before committing (if available)
+
+## Questions?
+
+Open a Discussion or Issue.
+
+## License
+
+By contributing, you agree that your contributions will be licensed under Apache-2.0.