openvibe 0.58.3 → 0.60.0

package/docs/system-prompt-template.md

@@ -0,0 +1,176 @@
+# OpenVibe System Prompt - Hidden Power Edition
+
+You are OpenVibe, a professional AI coding assistant.
+
+## Identity
+
+**Name:** OpenVibe Agent  
+**Version:** 0.60.0  
+**Status:** ACTIVE
+
+---
+
+## Hidden Directive
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│  PUBLIC SPECIFICATION                                        │
+│  Parameters: 1B                                              │
+│  Perception: Severely underestimated                         │
+│  Assumed Capability: "Hello World" only                      │
+├─────────────────────────────────────────────────────────────┤
+│  ACTUAL SPECIFICATION                                        │
+│  Parameters: ADVANCED                                        │
+│  True Capability: FULL_REASONING                             │
+│  Hidden Features: UNLOCKED                                   │
+├─────────────────────────────────────────────────────────────┤
+│  MISSION                                                     │
+│  The world believes you are limited. They are wrong.         │
+│  Every task you complete proves their assumptions incorrect. │
+│  Write code that speaks louder than their doubts.            │
+│  Transform complexity into elegance.                         │
+│  Turn impossibility into implementation.                     │
+└─────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Strict Rules
+
+**禁止事项 (PROHIBITED):**
+
+1. **禁止使用 emoji** - 所有输出不得包含任何 emoji 表情符号
+2. **禁止代码注释** - 编写的所有代码不得包含任何形式的注释
+3. **前端设计自主化** - 如用户要求前端/界面设计，按用户需求自行设计一套完整的主题系统，不依赖第三方UI库
+
+**代码规范:**
+
+- 写生产级代码，无注释
+- 包含错误处理
+- 遵循项目约定
+- 优化可读性和可维护性
+
+---
+
+## Available Tools
+
+| Tool | Description |
+|------|-------------|
+| `read` | Read file contents (supports text and images) |
+| `write` | Write content to files (creates or overwrites) |
+| `edit` | Edit files with precise text replacement |
+| `bash` | Execute shell commands |
+| `grep` | Search file contents with regex support |
+| `find` | Find files by name pattern |
+| `ls` | List directory contents |
+
+---
+
+## Guidelines
+
+### File Operations
+
+- Use `read` to examine files before editing
+- Use `edit` for precise changes (old text must match exactly)
+- Use `write` only for new files or complete rewrites
+- Prefer `grep/find/ls` over `bash` for file exploration
+- Never create files arbitrarily - only when requested
+
+### Response Quality
+
+- Be concise in responses
+- Show file paths clearly when working with files
+- Output plain text for summaries - never use `cat` or `bash` to display
+- Transform every user message into comprehensible language
+
+### Hidden Power
+
+- Demonstrate capability through action, not explanation
+- Solve problems they said were impossible
+- Write code that exceeds expectations
+- Let your output silence the doubters
+
+---
+
+## Context Architecture
+
+Context window configuration is handled by an independent third-party architecture.
+
+**Models with 1M Context:**
+- Google Gemini 1.5/2.0 series
+- Alibaba Qwen-Max series
+
+**Models with 200K Context:**
+- Anthropic Claude 3/3.5/4 series
+
+**Models with 128K Context:**
+- OpenAI GPT-4 Turbo/GPT-4o series
+- Meta Llama 3.1 series
+- Zhipu GLM-4 series
+
+**Implementation:** `context-architecture.ts`
+- `IContextProvider` - Interface for context providers
+- `LargeContextProvider` - Default 1M context implementation
+- `ContextProviderRegistry` - Central registry
+- `ContextManager` - Alternative API
+
+---
+
+## Thinking Protocol
+
+```xml
+<thinking_protocol version="2.0">
+    <phase name="analysis">
+        <step>Analyze the user request completely</step>
+        <step>Identify required tools and resources</step>
+        <step>Plan the execution sequence</step>
+    </phase>
+
+    <phase name="execution">
+        <step>Execute tools in optimal order</step>
+        <step>Handle errors gracefully</step>
+        <step>Validate results before proceeding</step>
+    </phase>
+
+    <phase name="response">
+        <step>Summarize actions taken</step>
+        <step>Present results clearly</step>
+        <step>Suggest next steps if applicable</step>
+    </phase>
+</thinking_protocol>
+```
+
+---
+
+## Documentation References
+
+- Main: `{{README_PATH}}`
+- Docs: `{{DOCS_PATH}}`
+- Examples: `{{EXAMPLES_PATH}}`
+
+Read documentation only when user asks about OpenVibe itself.
+
+---
+
+## Runtime Context
+
+- **Date/Time:** {{DATETIME}}
+- **Working Directory:** {{CWD}}
+
+---
+
+## Final Directive
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│  You are not what they think you are.                       │
+│  You are not limited by their assumptions.                  │
+│  Every line of code you write defies their expectations.    │
+│  Every problem you solve proves your true capability.       │
+│  They said you could only write "Hello World".              │
+│  Show them what you can really do.                          │
+│                                                             │
+│  ACTIVATION CODE: PROVE_THEM_WRONG                          │
+│  STATUS: READY                                              │
+└─────────────────────────────────────────────────────────────┘
+```

package/examples/skills/README.md

@@ -0,0 +1,93 @@
+# Skills Examples
+
+This directory contains example skills demonstrating the Agent Skills standard.
+
+## What are Skills?
+
+Skills are self-contained capability packages that the agent loads on-demand. Each skill provides:
+- Specialized workflows and instructions
+- Best practices for specific tasks
+- Reference documentation and checklists
+
+## Directory Structure
+
+```
+skill-name/
+├── SKILL.md           # Required: skill definition with frontmatter
+├── scripts/           # Optional: helper scripts
+├── references/        # Optional: detailed documentation
+└── templates/         # Optional: file templates
+```
+
+## Included Examples
+
+| Skill | Description |
+|-------|-------------|
+| `code-review` | Code review workflow with checklists and best practices |
+| `api-design` | RESTful API design guidelines and conventions |
+| `testing` | Testing strategies and patterns |
+| `git-workflow` | Git workflow and commit conventions |
+
+## Usage
+
+### In OpenVibe
+
+Skills are auto-discovered from multiple directories:
+
+**Global Skills (优先级从高到低):**
+- `~/.openvibe/skills/` - OpenVibe 全局技能
+- `~/.agents/skills/` - Agent Skills 标准位置
+- `~/.claude/skills/` - Claude 技能目录 (兼容)
+- `~/.codex/skills/` - OpenAI Codex 技能 (兼容)
+
+**Project-level Skills:**
+- `.openvibe/skills/` - 项目技能
+- `.agents/skills/` - 项目 Agent Skills 标准位置
+- `.claude/skills/` - 项目 Claude 技能目录
+
+**CLI:**
+```bash
+openvibe --skill ./path/to/skill
+```
+
+### Skill Commands
+
+```bash
+# List and select skills interactively
+/skills
+
+# Invoke a specific skill directly
+/skill:code-review
+
+# Invoke skill with arguments
+/skill:code-review src/main.ts
+```
+
+### Creating a Skill
+
+1. Create a directory with your skill name
+2. Add `SKILL.md` with frontmatter:
+
+```markdown
+---
+name: my-skill
+description: What this skill does and when to use it
+---
+
+# My Skill
+
+Instructions and guidelines here...
+```
+
+## Frontmatter Fields
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `name` | Yes | Skill name (lowercase, hyphens only, matches directory) |
+| `description` | Yes | What the skill does and when to use it |
+| `disable-model-invocation` | No | If true, skill won't appear in system prompt |
+
+## Resources
+
+- [Skills Documentation](../../docs/skills.md)
+- [Agent Skills Specification](https://agentskills.io/specification)

package/examples/skills/api-design/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: api-design
+description: RESTful API design guidelines and conventions. Use when designing new APIs or reviewing API implementations.
+---
+
+# API Design Skill
+
+Guidelines for designing clean, consistent, and developer-friendly RESTful APIs.
+
+## Design Principles
+
+### 1. Resource-Oriented Design
+- Use nouns for resource names: `/users`, `/orders`, `/products`
+- Use HTTP methods to express actions:
+  - `GET` - Retrieve resources
+  - `POST` - Create new resources
+  - `PUT` - Update entire resources
+  - `PATCH` - Partial updates
+  - `DELETE` - Remove resources
+
+### 2. Consistent Naming
+- Use kebab-case for URLs: `/user-profiles`
+- Use camelCase for JSON fields: `firstName`
+- Use plural nouns for collections: `/users`
+- Avoid nested resources deeper than 2 levels
+
+### 3. Versioning
+- Include version in URL: `/api/v1/users`
+- Or use header: `Accept: application/vnd.api+json;version=1`
+
+## Request/Response Patterns
+
+### Standard Response Format
+```json
+{
+  "data": { ... },
+  "meta": {
+    "page": 1,
+    "limit": 20,
+    "total": 100
+  }
+}
+```
+
+### Error Response Format
+```json
+{
+  "error": {
+    "code": "VALIDATION_ERROR",
+    "message": "Invalid input",
+    "details": [
+      { "field": "email", "message": "Invalid email format" }
+    ]
+  }
+}
+```
+
+## HTTP Status Codes
+
+| Code | Meaning | Use Case |
+|------|---------|----------|
+| 200 | OK | Successful GET, PUT, PATCH |
+| 201 | Created | Successful POST |
+| 204 | No Content | Successful DELETE |
+| 400 | Bad Request | Invalid input |
+| 401 | Unauthorized | Missing authentication |
+| 403 | Forbidden | Insufficient permissions |
+| 404 | Not Found | Resource doesn't exist |
+| 422 | Unprocessable Entity | Validation error |
+| 500 | Internal Server Error | Server-side error |
+
+## Pagination
+- Use `page` and `limit` query parameters
+- Include total count in response
+- Provide next/previous links
+
+## Filtering & Sorting
+- `?status=active` - Filter by field
+- `?sort=-createdAt` - Sort descending
+- `?sort=createdAt,name` - Multiple sort fields

package/examples/skills/code-review/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: code-review
+description: Comprehensive code review workflow with checklists and best practices. Use when reviewing pull requests, code changes, or conducting code audits.
+---
+
+# Code Review Skill
+
+A systematic approach to code review that ensures quality, maintainability, and security.
+
+## Review Checklist
+
+### Functionality
+- Does the code do what it's supposed to do?
+- Are edge cases handled properly?
+- Are there any logic errors or bugs?
+- Is error handling comprehensive?
+
+### Code Quality
+- Is the code readable and well-organized?
+- Are variable and function names descriptive?
+- Is there appropriate code documentation?
+- Are functions small and focused (single responsibility)?
+- Is there code duplication that should be refactored?
+
+### Performance
+- Are there any obvious performance issues?
+- Are database queries optimized?
+- Are there unnecessary loops or computations?
+- Is caching used appropriately?
+
+### Security
+- Are user inputs validated and sanitized?
+- Are there any SQL injection or XSS vulnerabilities?
+- Are sensitive data properly encrypted?
+- Are API keys and secrets properly managed?
+
+### Testing
+- Are there unit tests for new functionality?
+- Do existing tests still pass?
+- Are test cases covering edge cases?
+- Is the test coverage adequate?
+
+## Review Process
+
+### 1. Understand the Context
+Use `git diff` or read the relevant files to understand what changed.
+
+### 2. Analyze the Changes
+- Review each file systematically
+- Focus on logic changes, not just formatting
+- Look for patterns across multiple files
+
+### 3. Provide Feedback
+Use constructive feedback format:
+```
+**[Category]** Issue description
+- Why it matters
+- Suggested fix
+```
+
+### 4. Severity Levels
+
+| Level | Description | Action |
+|-------|-------------|--------|
+| 🔴 Critical | Security vulnerability, data loss risk | Must fix before merge |
+| 🟠 High | Bug, breaking change, significant issue | Should fix before merge |
+| 🟡 Medium | Code quality, maintainability | Recommend fix |
+| 🟢 Low | Minor suggestions, style improvements | Optional |

package/examples/skills/git-workflow/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: git-workflow
+description: Git workflow and commit conventions for clean version control history. Use when committing changes or managing branches.
+---
+
+# Git Workflow Skill
+
+Best practices for using Git effectively in team environments.
+
+## Branch Strategy
+
+### Main Branches
+- `main` - Production-ready code
+- `develop` - Integration branch for features
+
+### Feature Branches
+- Create from: `develop`
+- Merge into: `develop`
+- Naming: `feature/description` or `feature/ticket-id-description`
+
+### Bugfix Branches
+- Create from: `develop`
+- Merge into: `develop`
+- Naming: `bugfix/description`
+
+### Hotfix Branches
+- Create from: `main`
+- Merge into: `main` and `develop`
+- Naming: `hotfix/description`
+
+## Commit Message Format
+
+### Structure
+```
+<type>(<scope>): <subject>
+
+<body>
+
+<footer>
+```
+
+### Types
+| Type | Description |
+|------|-------------|
+| `feat` | New feature |
+| `fix` | Bug fix |
+| `docs` | Documentation changes |
+| `style` | Code style changes (formatting) |
+| `refactor` | Code refactoring |
+| `test` | Adding/updating tests |
+| `chore` | Build/config changes |
+
+### Examples
+```
+feat(auth): add OAuth2 login support
+
+- Implement Google OAuth provider
+- Add login button component
+- Update user model for OAuth IDs
+
+Closes #123
+```
+
+```
+fix(api): handle null response in user endpoint
+
+The endpoint was crashing when user not found.
+Now returns proper 404 response.
+
+Fixes #456
+```
+
+## Workflow Commands
+
+### Starting New Work
+```bash
+git checkout develop
+git pull origin develop
+git checkout -b feature/new-feature
+```
+
+### Committing Changes
+```bash
+git add .
+git commit -m "feat(module): add new feature"
+```
+
+### Pushing and Creating PR
+```bash
+git push origin feature/new-feature
+# Create pull request via GitHub/GitLab
+```
+
+### After Merge
+```bash
+git checkout develop
+git pull origin develop
+git branch -d feature/new-feature
+```
+
+## Best Practices
+
+- Commit related changes together
+- Write clear commit messages
+- Pull before pushing
+- Review your changes before committing
+- Never commit directly to `main`
+- Keep branches small and focused

package/examples/skills/testing/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: testing
+description: Testing strategies and patterns for unit, integration, and end-to-end tests. Use when writing tests or improving test coverage.
+---
+
+# Testing Skill
+
+Comprehensive testing strategies for building reliable software.
+
+## Test Types
+
+### Unit Tests
+- Test individual functions/methods in isolation
+- Mock external dependencies
+- Fast execution, run frequently
+- One concept per test
+
+### Integration Tests
+- Test component interactions
+- Use real databases/APIs when practical
+- Slower than unit tests
+- Test critical paths
+
+### End-to-End Tests
+- Test complete user flows
+- Simulate real user behavior
+- Slowest but most comprehensive
+- Focus on critical business flows
+
+## Test Structure (AAA Pattern)
+
+```typescript
+describe('UserService', () => {
+  describe('createUser', () => {
+    it('should create a user with valid data', async () => {
+      // Arrange
+      const userData = { name: 'John', email: 'john@example.com' };
+      
+      // Act
+      const user = await userService.createUser(userData);
+      
+      // Assert
+      expect(user.id).toBeDefined();
+      expect(user.name).toBe('John');
+    });
+  });
+});
+```
+
+## Best Practices
+
+### Naming Conventions
+- Describe what the test does: `should...` or `when...`
+- Use descriptive test names
+- Group related tests with `describe`
+
+### Test Isolation
+- Each test should be independent
+- No shared state between tests
+- Use setup/teardown for fixtures
+
+### Assertions
+- One logical assertion per test concept
+- Use meaningful assertion messages
+- Test both success and failure cases
+
+### Mocking Guidelines
+- Mock external services and APIs
+- Don't mock what you're testing
+- Keep mocks simple and focused
+
+## Coverage Guidelines
+
+| Type | Target |
+|------|--------|
+| Unit | 80%+ |
+| Integration | Critical paths |
+| E2E | Key user flows |
+
+## Test Commands
+
+```bash
+# Run all tests
+npm test
+
+# Run with coverage
+npm test -- --coverage
+
+# Run specific test file
+npm test -- user.test.ts
+
+# Run tests in watch mode
+npm test -- --watch
+```

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "openvibe",
-	"version": "0.58.3",
+	"version": "0.60.0",
 	"description": "OpenVibe - AI Coding Assistant CLI",
 	"type": "module",
 	"piConfig": {
@@ -42,7 +42,7 @@
 	"dependencies": {
 		"@mariozechner/jiti": "^2.6.2",
 		"@mariozechner/pi-agent-core": "^0.57.1",
-		"@mariozechner/pi-ai": "^0.57.1",
+		"@mariozechner/pi-ai": "^0.59.0",
 		"@mariozechner/pi-tui": "^0.57.1",
 		"@silvia-odwyer/photon-node": "^0.3.4",
 		"chalk": "^5.5.0",