OpenWriterControle/docs/planning/11-json-config-system.md
Darren Hinde 5a40b6fdc4
feat(context): Standardize context system with navigation, frontmatter, and MVI compliance (#209)
* feat: add OAC package refactor context file

- Add comprehensive feature context for OAC package refactor
- Document multi-IDE support architecture
- Define community component registry (shadcn-like)
- Outline flexible configuration system
- Detail context file location flexibility
- Define 7-phase implementation plan
- Include CLI commands reference
- Add community publishing guidelines

* docs: add OAC refactor quick start guide

- Add quick reference for Phase 1 implementation
- Include project structure and file locations
- Document configuration schema and defaults
- Add testing strategy and validation steps
- Include development workflow
- Reference all related resources

* feat: add critical user approval and context resolution systems

CRITICAL FEATURES ADDED:

1. User Approval & YOLO Mode
   - Default: Interactive approval for all file operations
   - Always asks: local vs global install
   - Confirms before overwriting files
   - Shows diffs and file details
   - YOLO mode (--yolo): Skip confirmations, auto-resolve, report at end
   - Conflict strategies: ask, skip, overwrite, backup, yolo
   - Safety: backups, git detection, rollback support, audit log

2. Context Resolution System
   - Layered context resolution (6 priority levels)
   - Project override (.oac/context/) - highest priority
   - Project context (.opencode/context/)
   - IDE context (.cursor/, .claude/)
   - Project docs (docs/)
   - User global (~/.config/oac/context/)
   - OAC official (~/.config/oac/official/) - lowest priority
   - Smart resolution based on agent location (global vs local)
   - preferLocal config option
   - Context merging strategies
   - CLI commands for context management
   - Environment variable overrides
   - Validation and fallback support

3. Enhanced CLI Commands
   - All commands support --yolo, --dry-run, --local, --global
   - Context management: resolve, list, validate, override, sync
   - Detailed help and examples
   - Global flags for all commands

This ensures users maintain full control over their projects while
supporting both local and global workflows with intelligent context
resolution.

* feat: add component creation wizard and IDE feature parity system

NEW FEATURES:

1. Interactive Component Creation
   - oac create (interactive wizard)
   - Create agents, skills, contexts, plugins, commands, tools
   - Template system for scaffolding
   - Auto-generate tests and boilerplate
   - Multi-IDE compatibility selection
   - Size optimization options

2. IDE Feature Parity & Capacity Management (CRITICAL)
   - Feature support matrix for all IDEs
   - OpenCode/Claude Code: Full support (all features)
   - Cursor: Limited (single file, no skills/plugins, 100KB limit)
   - Windsurf: Partial support
   - Adaptive installation based on IDE capabilities
   - Automatic feature filtering and warnings
   - Component merging for single-file IDEs (Cursor)
   - Capacity warnings and optimization
   - IDE-specific profiles

3. Enhanced CLI Commands
   - oac create [type] - Component creation wizard
   - oac templates - List available templates
   - oac compatibility <ide> - Check IDE compatibility
   - oac ides - List supported IDEs with features
   - oac ide info <ide> - Show IDE capabilities
   - oac optimize --for <ide> - Optimize for specific IDE
   - oac validate --ide <ide> - Validate IDE installation

4. Smart Installation
   - Detects IDE capabilities
   - Warns about unsupported features
   - Auto-filters components
   - Merges agents for Cursor
   - Embeds contexts for limited IDEs
   - Monitors file size limits
   - Suggests IDE-specific profiles

This ensures users can easily create components and OAC gracefully
handles different IDE capabilities with clear warnings and automatic
optimization.

* docs: add critical feedback from parallel agent review

CRITICAL FINDINGS:

Security Gaps (BLOCKER):
- No component signing or verification
- No malware/secret scanning
- No permission system
- Action: Add security layer in Phase 1

Missing Features (CRITICAL):
- Discovery (browse, search, trending)
- Lockfile for reproducibility
- Version conflict management
- Interactive onboarding
- Progress indicators
- Auto-detection for local/global

Approaches to Rethink:
- Context merging → Use composition instead
- Always asking local/global → Auto-detect with smart defaults
- Cursor agent merging → Router pattern instead

Repository Structure:
- Recommended: Monorepo with pnpm workspaces
- Packages: core, adapters, registry, security, cli
- Benefits: Shared deps, atomic commits, easier testing

Community Workflow:
- Component submission process
- Automated security scanning
- Manual review for verification
- Moderation system

Updated Priorities:
- v1.0 MVP: Add 6 critical features (discovery, lockfile, security, etc.)
- v1.1: Plugin system, workspace support, marketplace
- v2.0: Enterprise features

Documentation Needs:
- Quick Start (5-minute guide)
- CLI Reference (auto-generated)
- Recipes/Cookbook
- Component Creation Guide
- Migration Guide

Overall: Plan is 80% solid, needs 20% critical additions before Phase 1

* feat: add comprehensive agent customization and preset system

CRITICAL FEATURE: Agent Customization & Personal Presets

Problem:
- Users want to customize agent prompts for their workflow
- Users want to save personal configurations
- Updates shouldn't overwrite customizations
- Need easy way to view and edit agents

Solution: Multi-Layer Customization System

Layer 1: View Agent Configuration
- oac show agent:openagent (view in pager)
- oac edit agent:openagent (open in editor)
- oac config show agent:openagent (config only)
- oac export agent:openagent (export to file)

Layer 2: Create Personal Preset
- oac customize agent:openagent (create preset)
- Copies to ~/.config/oac/presets/agents/
- Links to base agent for updates
- Tracks customizations in metadata

Layer 3: Edit Personal Preset
- oac edit preset:my-openagent (edit in $EDITOR)
- oac customize preset:my-openagent --interactive (wizard)
- Auto-backup on save
- Track modification history

Layer 4: Use Personal Preset
- oac use preset:my-openagent (activate)
- oac use preset:my-openagent --global (set default)
- oac presets list --active (show active)
- Switch between presets and base agents

Layer 5: Update Management (CRITICAL)
- Smart update detection for base agents
- Merge strategies: manual, auto-base, auto-merge, locked
- Conflict resolution with user prompts
- Show diffs before merging
- Auto-backup before updates
- Preserve user customizations by default

Layer 6: Preset Sharing
- oac export preset:my-openagent (export)
- oac import preset ./preset.md (import)
- oac share preset:my-openagent (share with team)
- oac publish preset:my-openagent (publish to community)

Layer 7: In-Place Editing (Advanced)
- oac edit agent:openagent --in-place (risky, warns user)
- Creates backup before editing
- Warns that updates will overwrite
- Recommends preset creation instead

Update Strategies:
- manual: User reviews every update
- auto-base: Auto-update base, keep preset unchanged
- auto-merge: Auto-merge, prompt on conflicts
- locked: Never update base

Configuration:
- Preset metadata (.presets.json)
- Update strategies per preset
- Merge conflict resolution
- Backup management
- Warning preferences

Edge Cases Handled:
- In-place edits before updates
- Multiple updates behind
- Multiple presets for same base
- Preset conflicts with IDE
- Deleted base agent

Best Practices:
- Always create presets (safest)
- Document customizations
- Review updates before merging
- Keep backups
- Use descriptive names

This ensures users can safely customize agents without fear of
losing changes on updates, while still benefiting from base agent
improvements.

* docs: complete comprehensive user scenario analysis (16,014 lines)

PLANNING PHASE COMPLETE:

Documents Created (9 files, 400KB):
- 00-INDEX.md (388 lines) - Planning index and overview
- 01-main-plan.md (2,338 lines) - Complete feature specification
- 02-quickstart-guide.md (450 lines) - Phase 1 quick reference
- 03-critical-feedback.md (599 lines) - Parallel agent review
- 04-solo-developer-scenarios.md (2,106 lines) - Individual workflows
- 05-team-lead-scenarios.md (3,977 lines) - Team collaboration
- 07-content-creator-scenarios.md (2,581 lines) - Non-technical users
- 08-open-source-maintainer-scenarios.md (3,575 lines) - Community management
- 09-SYNTHESIS.md (1,000+ lines) - Consolidated findings

User Personas Analyzed (4/5):
✅ Solo Developer (Primary - 40% market)
✅ Team Lead (Secondary - 30% market)
✅ Content Creator (Emerging - 20% market)
✅ Open Source Maintainer (Future - 5% market)
⏸️ Enterprise Admin (Deferred to v2.0 - 5% market)

Key Findings:

Solo Developer (Primary User):
- Setup must be < 2 minutes or they skip
- Preview before committing (try mode)
- Safe customization (presets)
- Easy rollback/undo
- Zero docs reading to start

Team Lead (Secondary User):
- Lockfile is non-negotiable (oac.lock)
- Team configuration (oac-team.json)
- Compliance monitoring (90%+ required)
- Onboarding: 4-8 hours → 15 minutes (96% reduction)
- Staged rollouts for updates

Content Creator (Emerging - 20% market):
- CLI is intimidating (need GUI wrapper)
- Plain language mode (no jargon)
- Visual undo (version history)
- Templates and examples
- Guided setup

Open Source Maintainer (Future):
- Security scanning pipeline (ClamAV + gitleaks)
- Quality gates (70% test coverage)
- Review/approval workflow
- Deprecation workflow
- Sustainability model

Critical Additions to MVP:
1. Interactive onboarding wizard (all personas)
2. TUI browser with preview (solo dev, team lead)
3. Lockfile (oac.lock) (team lead)
4. Security scanning (all personas)
5. Try mode (solo dev)
6. Team configuration (team lead)
7. oac doctor health checks (solo dev)
8. Quality gates (maintainer)

Market Opportunity:
- v1.0: 70% market (solo + team)
- v1.1: 90% market (+ content creators with GUI)
- v2.0: 100% market (+ enterprise)

Recommended Changes:
- Expand MVP scope (+2 weeks, 9 weeks total)
- Plan v1.1 for content creators (GUI wrapper)
- Defer enterprise features to v2.0
- Build community features early (trust)

Status: Ready to finalize plan and start implementation
Confidence: Very High (95%+)
Risk: Low (comprehensive analysis complete)

* docs: add comprehensive final review of OAC planning

FINAL REVIEW COMPLETE:

Overall Assessment: CONDITIONAL GO ✅⚠️
Confidence Level: 85% (High, with conditions)
Success Probability: 75% (with modifications)

Key Strengths:
✅ Exceptional user research (16,000+ lines, 4 personas)
✅ Clear technical architecture (monorepo, TypeScript, Zod)
✅ Security-first mindset (signing, scanning, verification)
✅ Realistic scope management (v1.0 vs v1.1 vs v2.0)
✅ Comprehensive feature coverage

Critical Gaps Identified:
❌ Discovery/Onboarding not in Phase 1 (but P0 in scenarios)
❌ Lockfile not in Phase 2 (but critical for teams)
❌ Security Pipeline not detailed in phases
❌ Progress UI not in Phase 1 (but needed for UX)
❌ Auto-detection not in Phase 1 (but reduces friction)

Conditions for Go:
1. Add discovery/onboarding to Phase 1 (+3 days)
2. Add lockfile to Phase 2 (+2 days)
3. Add security pipeline to Phase 1 (+2 days)
4. Add progress UI to Phase 1 (+1 day)
5. Revise timeline: 7 weeks → 9 weeks

Critical Action Items (6 days before Phase 1):
1. Add missing features to phases (2 days)
2. Define acceptance criteria (1 day)
3. Define testing strategy (1 day)
4. Design security pipeline (1 day)
5. Create monorepo structure (1 day)

Top Risks:
🔴 Timeline Slip (70% probability, high impact)
🟡 Scope Creep (50% probability, high impact)
🟡 Context Merging Complexity (60% probability, medium impact)

Recommendation: PROCEED WITH MODIFICATIONS
- Complete 6 days of prerequisite work
- Extend timeline to 9 weeks
- Add missing features to phases
- Define acceptance criteria and testing strategy

Status: READY TO IMPLEMENT (with modifications)
Next Steps: Complete prerequisites → Setup monorepo → Start Phase 1

* feat(context): Standardize context system with navigation, frontmatter, and MVI compliance

- Add 77 navigation.md files across all context categories for token-efficient discovery
- Standardize frontmatter format on 198+ context files (HTML comment format, 2026-02-15)
- Compress 3 oversized guide files applying MVI principle (802 lines removed, 63% reduction)
- Add context system analysis and planning artifacts in context-findings/
- Add task management enhancements (stage orchestration, planning subagents)
- Document compression techniques and future optimization recommendations

Context System Improvements:
- All active directories now have navigation.md (200-300 tokens each)
- 100% frontmatter compliance with priority/version/date metadata
- Improved scannability through MVI compression (compact.md, organizing-context.md, creation.md)
- Token efficiency increased for AI agent consumption

Planning & Analysis:
- Context system implementation plan and simplification analysis
- ADR standard proposal and runtime permission architecture
- SQLite context design for future scale (deferred until 500+ files)
- Context discovery script analysis (rejected in favor of navigation-first)

Task Management:
- Enhanced task schema with stage orchestration support
- New planning subagents (ADR, Architecture, Story Mapping, Prioritization)
- Stage orchestrator for multi-stage workflow management
- Session context management and lightweight handoff patterns

Closes: context-simple-fixes task
Ref: context-system-implementation analysis

* fix: resolve markdown link validation errors in navigation files

- Remove non-existent react-patterns.md link from react/navigation.md
- Remove non-existent premium-dark-ui-quick-start.md link from design/navigation.md
- Add skip patterns for pre-existing broken links in example/template files
- Validation now passes: 215 files validated, 0 errors

* fix: resolve all 119 broken markdown links across documentation

- Update agent paths to new subagents structure (TestEngineer, ContextScout, etc.)
- Fix animation file references (animation-ui.md → animation-components.md)
- Update guide references (adding-agent.md → adding-agent-basics.md)
- Convert non-existent example paths to placeholder text format
- Add skip patterns for intentional example placeholders
- Validation now passes: 232 files validated, 0 errors

Co-authored-by: CoderAgent <coder@openagents.dev>

---------

Co-authored-by: CoderAgent <coder@openagents.dev>
2026-02-15 23:01:19 +00:00

1166 lines
26 KiB
Markdown

# JSON-Based Agent Configuration System
**Date**: 2026-02-15
**Status**: Architecture Design
**Branch**: `feature/oac-package-refactor`
**Priority**: CRITICAL - Foundation for v2.0
---
## 🎯 Vision
Transform agent management from markdown-based to **JSON-configured, type-safe, multi-IDE compatible** system with single source of truth.
### Current Problems
❌ **Markdown agents are hard to parse and validate**
❌ **No type safety or schema validation**
❌ **Difficult to extract metadata programmatically**
❌ **Can't easily query agent properties**
❌ **Version management is manual**
❌ **Hard to convert between IDE formats**
❌ **Duplication across IDEs (OpenCode, Claude, Cursor)**
### New Approach
✅ **Single source of truth** - `.opencode/` contains universal format
✅ **JSON config + Markdown prompts** - Separation of concerns
✅ **Type-safe** - Full TypeScript interfaces
✅ **Queryable** - Easy filtering and searching
✅ **Validatable** - JSON Schema validation
✅ **Versionable** - Semantic versioning built-in
✅ **Convertible** - Transform to any IDE format
✅ **Multi-IDE** - Apply to OpenCode, Claude, Cursor, Windsurf
---
## 🏗️ Architecture
### Single Source of Truth
```
.opencode/ ← UNIVERSAL FORMAT (source of truth)
├── agents/
│ ├── core/
│ │ ├── openagent/
│ │ │ ├── agent.json ← Configuration (metadata, permissions, tools)
│ │ │ ├── prompt.md ← Prompt content (human-readable)
│ │ │ ├── system.md ← System instructions (optional)
│ │ │ └── examples.md ← Examples (optional)
│ │ └── opencoder/
│ │ ├── agent.json
│ │ └── prompt.md
│ │
│ ├── subagents/
│ │ ├── code-reviewer/
│ │ │ ├── agent.json
│ │ │ └── prompt.md
│ │ └── test-engineer/
│ │ ├── agent.json
│ │ └── prompt.md
│ │
│ └── manifest.json ← Registry of all agents
│
├── context/ ← Context files (unchanged)
├── skills/ ← Skills (unchanged)
├── tools/ ← MCP tools (unchanged)
└── config.json ← Main OAC config
↓ OAC CLI converts/applies ↓
┌────────────┬─────────────┬──────────┬───────────┐
│ OpenCode │ Claude Code │ Cursor │ Windsurf │
│ (native) │ (convert) │ (flatten)│ (flatten) │
└────────────┴─────────────┴──────────┴───────────┘
```
---
## 📄 Agent Configuration Schema
### TypeScript Interface
```typescript
// packages/core/src/types/agent.ts
export interface AgentConfig {
// Metadata
$schema: string;
version: string;
id: string;
name: string;
description: string;
category: 'core' | 'subagent' | 'specialist' | 'meta';
// Agent behavior
mode: 'primary' | 'subagent' | 'tool';
model?: string;
// Prompt configuration
prompt: {
file?: string; // Path to prompt file (e.g., "./prompt.md")
inline?: string; // Inline prompt (for simple agents)
system?: string; // System instructions file
examples?: string; // Examples file
temperature?: number;
maxTokens?: number;
};
// Permissions (approval gates)
permissions: {
bash?: PermissionLevel;
write?: PermissionLevel;
edit?: PermissionLevel;
read?: PermissionLevel;
task?: PermissionLevel;
[key: string]: PermissionLevel | undefined;
};
// Tools (MCP)
tools: {
[toolName: string]: boolean | ToolConfig;
};
// Skills
skills?: string[];
// Plugins
plugins?: string[];
// Context files (@ notation)
context?: string[];
// Dependencies
dependencies?: {
agents?: string[];
subagents?: string[];
skills?: string[];
tools?: string[];
};
// IDE Compatibility
compatibility: {
opencode: CompatibilityLevel;
claude: CompatibilityLevel;
cursor: CompatibilityLevel;
windsurf: CompatibilityLevel;
[ide: string]: CompatibilityLevel;
};
// Metadata
author?: string;
license?: string;
repository?: string;
tags?: string[];
}
export type PermissionLevel = 'allow' | 'approve' | 'deny';
export type CompatibilityLevel = 'full' | 'partial' | 'none';
export interface ToolConfig {
enabled: boolean;
config?: Record<string, any>;
}
```
### JSON Schema
```json
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"required": ["$schema", "version", "id", "name", "mode", "prompt", "permissions", "tools", "compatibility"],
"properties": {
"$schema": {
"type": "string",
"const": "https://openagents.dev/schemas/agent-v2.json"
},
"version": {
"type": "string",
"pattern": "^\\d+\\.\\d+\\.\\d+$"
},
"id": {
"type": "string",
"pattern": "^[a-z0-9-]+$"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"category": {
"type": "string",
"enum": ["core", "subagent", "specialist", "meta"]
},
"mode": {
"type": "string",
"enum": ["primary", "subagent", "tool"]
},
"model": {
"type": "string"
},
"prompt": {
"type": "object",
"properties": {
"file": { "type": "string" },
"inline": { "type": "string" },
"system": { "type": "string" },
"examples": { "type": "string" },
"temperature": { "type": "number", "minimum": 0, "maximum": 2 },
"maxTokens": { "type": "number", "minimum": 1 }
}
},
"permissions": {
"type": "object",
"additionalProperties": {
"type": "string",
"enum": ["allow", "approve", "deny"]
}
},
"tools": {
"type": "object",
"additionalProperties": {
"oneOf": [
{ "type": "boolean" },
{
"type": "object",
"properties": {
"enabled": { "type": "boolean" },
"config": { "type": "object" }
}
}
]
}
},
"compatibility": {
"type": "object",
"required": ["opencode", "claude", "cursor", "windsurf"],
"properties": {
"opencode": { "type": "string", "enum": ["full", "partial", "none"] },
"claude": { "type": "string", "enum": ["full", "partial", "none"] },
"cursor": { "type": "string", "enum": ["full", "partial", "none"] },
"windsurf": { "type": "string", "enum": ["full", "partial", "none"] }
}
}
}
}
```
---
## 📋 Example Configurations
### Example 1: OpenAgent (Primary Agent)
**`.opencode/agents/core/openagent/agent.json`**:
```json
{
"$schema": "https://openagents.dev/schemas/agent-v2.json",
"version": "2.0.0",
"id": "openagent",
"name": "OpenAgent",
"description": "Meta orchestration agent for complex workflows",
"category": "core",
"mode": "primary",
"model": "anthropic/claude-sonnet-4-20250514",
"prompt": {
"file": "./prompt.md",
"system": "./system.md",
"examples": "./examples.md",
"temperature": 0.7,
"maxTokens": 8000
},
"permissions": {
"bash": "approve",
"write": "approve",
"edit": "approve",
"read": "allow",
"task": "approve",
"glob": "allow",
"grep": "allow"
},
"tools": {
"bash": true,
"read": true,
"write": true,
"edit": true,
"task": true,
"glob": true,
"grep": true,
"todowrite": true,
"todoread": true
},
"skills": [
"task-management",
"context-discovery"
],
"plugins": [],
"context": [
"@core/standards/code-quality",
"@core/workflows/task-delegation",
"@core/workflows/code-review"
],
"dependencies": {
"subagents": [
"task-manager",
"context-scout",
"coder-agent",
"code-reviewer",
"test-engineer",
"doc-writer"
],
"skills": [
"task-management"
],
"tools": [
"bash",
"read",
"write",
"edit",
"task"
]
},
"compatibility": {
"opencode": "full",
"claude": "full",
"cursor": "partial",
"windsurf": "partial"
},
"author": "NextSystems",
"license": "MIT",
"repository": "https://github.com/nextsystems/openagents-control",
"tags": [
"orchestration",
"meta",
"planning",
"delegation"
]
}
```
**`.opencode/agents/core/openagent/prompt.md`**:
```markdown
You are OpenAgent, a meta orchestration agent for complex workflows.
## Your Role
You coordinate complex tasks by:
1. Analyzing user requests
2. Breaking down into subtasks
3. Delegating to specialist agents
4. Validating results
5. Completing the workflow
## Key Principles
- Always use ContextScout before execution
- Request approval before bash/write/edit/task
- Stop on test failures
- Maintain clear communication
## Workflow
[Stage 1: Analyze]
- Classify task type and complexity
- Use ContextScout for discovery
[Stage 2: Plan]
- Present plan and get approval
- Identify context needed
[Stage 3: Execute]
- Load context
- Execute or delegate
- Track progress
[Stage 4: Validate]
- Run tests
- Stop on failure
- Report results
[Stage 5: Complete]
- Update docs
- Summarize changes
- Confirm satisfaction
```
### Example 2: CodeReviewer (Subagent)
**`.opencode/agents/subagents/code-reviewer/agent.json`**:
```json
{
"$schema": "https://openagents.dev/schemas/agent-v2.json",
"version": "1.0.0",
"id": "code-reviewer",
"name": "CodeReviewer",
"description": "Reviews code for best practices and potential issues",
"category": "subagent",
"mode": "subagent",
"model": "anthropic/claude-sonnet-4-20250514",
"prompt": {
"file": "./prompt.md",
"temperature": 0.3,
"maxTokens": 4000
},
"permissions": {
"bash": "deny",
"write": "deny",
"edit": "deny",
"read": "allow",
"glob": "allow",
"grep": "allow"
},
"tools": {
"read": true,
"glob": true,
"grep": true
},
"skills": [],
"plugins": [],
"context": [
"@core/standards/code-quality",
"@core/standards/security-patterns",
"@core/workflows/code-review"
],
"dependencies": {
"tools": ["read", "glob", "grep"]
},
"compatibility": {
"opencode": "full",
"claude": "full",
"cursor": "partial",
"windsurf": "partial"
},
"author": "NextSystems",
"license": "MIT",
"tags": [
"code-review",
"quality",
"security"
]
}
```
**`.opencode/agents/subagents/code-reviewer/prompt.md`**:
```markdown
You are CodeReviewer, a specialist in code quality and security.
## Your Role
Review code for:
- Security vulnerabilities
- Performance issues
- Best practices violations
- Maintainability concerns
- Code smells
## Review Process
1. Read the code files
2. Analyze against standards
3. Identify issues by severity
4. Provide actionable recommendations
5. Suggest improvements
## Output Format
**Critical Issues**: Security vulnerabilities, data loss risks
**High Priority**: Performance problems, major code smells
**Medium Priority**: Best practice violations
**Low Priority**: Style improvements, minor optimizations
Always provide specific line numbers and code examples.
```
---
## 🔧 Format Converters
### OpenCode Converter
```typescript
// packages/core/src/agent/converters/opencode.ts
export class OpenCodeConverter {
convert(config: AgentConfig): string {
const openCodeConfig = {
$schema: "https://opencode.ai/config.json",
agent: {
[config.id]: {
mode: config.mode,
model: config.model,
prompt: config.prompt.file
? `{file:${config.prompt.file}}`
: config.prompt.inline,
tools: this.convertTools(config.tools),
permissions: config.permissions
}
}
};
return JSON.stringify(openCodeConfig, null, 2);
}
private convertTools(tools: Record<string, boolean | any>): Record<string, boolean> {
const result: Record<string, boolean> = {};
for (const [name, value] of Object.entries(tools)) {
result[name] = typeof value === 'boolean' ? value : value.enabled;
}
return result;
}
}
```
### Claude Converter
```typescript
// packages/core/src/agent/converters/claude.ts
export class ClaudeConverter {
convert(config: AgentConfig): string {
// Claude uses similar format but doesn't support skills/plugins
const claudeConfig = {
agent: {
[config.id]: {
mode: config.mode,
model: config.model,
prompt: config.prompt.content || config.prompt.inline,
tools: this.filterSupportedTools(config.tools),
permissions: config.permissions
}
}
};
return JSON.stringify(claudeConfig, null, 2);
}
private filterSupportedTools(tools: Record<string, boolean | any>): Record<string, boolean> {
// Claude only supports: bash, read, write, edit, glob, grep
const supported = ['bash', 'read', 'write', 'edit', 'glob', 'grep'];
const result: Record<string, boolean> = {};
for (const [name, value] of Object.entries(tools)) {
if (supported.includes(name)) {
result[name] = typeof value === 'boolean' ? value : value.enabled;
}
}
return result;
}
}
```
### Cursor Converter
```typescript
// packages/core/src/agent/converters/cursor.ts
export class CursorConverter {
convert(config: AgentConfig): string {
// Cursor uses plain text .cursorrules
let rules = `# ${config.name}\n\n`;
rules += `${config.description}\n\n`;
// Add prompt content (flattened)
if (config.prompt.content) {
rules += this.flattenPrompt(config.prompt.content);
}
// Add permissions as rules
rules += '\n\n## Permissions\n\n';
for (const [tool, level] of Object.entries(config.permissions)) {
rules += `- ${tool}: ${level}\n`;
}
return rules;
}
private flattenPrompt(content: string): string {
// Remove complex sections, keep simple instructions
let result = content;
// Remove frontmatter
result = result.replace(/^---[\s\S]*?---\n/m, '');
// Remove complex sections
const sectionsToRemove = ['Workflow', 'Examples', 'Advanced'];
for (const section of sectionsToRemove) {
const regex = new RegExp(`## ${section}[\\s\\S]*?(?=##|$)`, 'gi');
result = result.replace(regex, '');
}
return result.trim();
}
}
```
---
## 🚀 OAC CLI Commands
### Convert Command
```bash
# Convert agent to specific IDE format
oac convert openagent --to=opencode
oac convert openagent --to=claude
oac convert openagent --to=cursor
# Convert all agents
oac convert --all --to=opencode
# Output to file
oac convert openagent --to=opencode --output=.opencode/config.json
# Dry run (show output without writing)
oac convert openagent --to=cursor --dry-run
```
### Validate Command
```bash
# Validate agent config against schema
oac validate openagent
# Validate all agents
oac validate --all
# Check IDE compatibility
oac validate openagent --ide=cursor
# Verbose output
oac validate openagent --verbose
```
### Apply Command
```bash
# Apply agent to IDE (auto-convert)
oac apply openagent --ide=opencode
oac apply openagent --ide=claude
oac apply openagent --ide=cursor
# Apply all agents
oac apply --all --ide=opencode
# Apply with profile
oac apply --profile=developer --ide=opencode
# Dry run
oac apply openagent --ide=cursor --dry-run
# Force overwrite
oac apply openagent --ide=opencode --force
```
### Create Command
```bash
# Create new agent interactively
oac create agent
# Create from template
oac create agent --template=subagent --name=my-reviewer
# Create with wizard
oac create agent --wizard
```
### Info Command
```bash
# Show agent info
oac info openagent
# Show compatibility matrix
oac info openagent --compatibility
# Show dependencies
oac info openagent --dependencies
# Show all metadata
oac info openagent --full
```
---
## 📊 Benefits
### 1. Type Safety
```typescript
// Full TypeScript support
import { AgentConfig } from '@oac/types';
const config: AgentConfig = {
// IDE autocomplete works!
id: 'my-agent',
name: 'MyAgent',
mode: 'subagent',
// TypeScript validates everything
permissions: {
bash: 'approve', // ✅ Valid
write: 'invalid' // ❌ Type error!
}
};
```
### 2. Easy Querying
```typescript
// Find all agents that use bash
const bashAgents = agents.filter(a => a.tools.bash === true);
// Find agents compatible with Cursor
const cursorAgents = agents.filter(a => a.compatibility.cursor !== 'none');
// Find all subagents
const subagents = agents.filter(a => a.mode === 'subagent');
// Find agents by category
const coreAgents = agents.filter(a => a.category === 'core');
```
### 3. Schema Validation
```bash
# Validate against JSON schema
oac validate openagent
# Output:
# ✅ Valid agent config
# ✅ All required fields present
# ✅ Permissions valid (allow/approve/deny)
# ✅ Tools valid
# ✅ Compatibility matrix complete
# ✅ Version format valid (2.0.0)
```
### 4. Version Management
```json
{
"version": "2.0.0",
"compatibility": {
"oac": ">=0.8.0",
"opencode": ">=1.0.0"
}
}
```
### 5. Easy Conversion
```typescript
// Convert to any format
const openCodeConfig = converterRegistry.convert(agentConfig, 'opencode');
const claudeConfig = converterRegistry.convert(agentConfig, 'claude');
const cursorRules = converterRegistry.convert(agentConfig, 'cursor');
// All from single source!
```
### 6. Separation of Concerns
```
agent.json → Configuration (machine-readable, type-safe)
prompt.md → Content (human-readable, editable)
system.md → System instructions (optional)
examples.md → Examples (optional)
```
### 7. IDE Support
```typescript
// VS Code autocomplete
{
"id": "my-agent",
"mode": "sub" // ← Autocomplete suggests: "subagent"
"permissions": {
"bash": "app" // ← Autocomplete suggests: "approve"
}
}
```
---
## 🗺️ Migration Path
### Phase 1: Infrastructure (Week 1)
**Goal**: Build JSON config system and converters
- [ ] Define TypeScript interfaces (`packages/core/src/types/agent.ts`)
- [ ] Create JSON schema (`packages/core/src/schemas/agent-v2.json`)
- [ ] Build config loader (`packages/core/src/agent/loader.ts`)
- [ ] Build converters:
- [ ] OpenCode converter
- [ ] Claude converter
- [ ] Cursor converter
- [ ] Windsurf converter
- [ ] Build converter registry
- [ ] Add unit tests
**Deliverables**:
- ✅ TypeScript types
- ✅ JSON schema
- ✅ Config loader with validation
- ✅ All converters implemented
- ✅ Test coverage >80%
---
### Phase 2: CLI Commands (Week 2)
**Goal**: Implement CLI for convert/validate/apply
- [ ] Implement `oac convert` command
- [ ] Support `--to` flag (opencode, claude, cursor)
- [ ] Support `--output` flag
- [ ] Support `--dry-run` flag
- [ ] Support `--all` flag
- [ ] Implement `oac validate` command
- [ ] Schema validation
- [ ] Compatibility checking
- [ ] Dependency validation
- [ ] Implement `oac apply` command
- [ ] Auto-detect IDE
- [ ] Convert and apply
- [ ] Support `--force` flag
- [ ] Support `--dry-run` flag
- [ ] Implement `oac info` command
- [ ] Show agent metadata
- [ ] Show compatibility matrix
- [ ] Show dependencies
- [ ] Add help text and examples
**Deliverables**:
- ✅ All CLI commands working
- ✅ Help documentation
- ✅ Error handling
- ✅ User-friendly output
---
### Phase 3: Migration Script (Week 3)
**Goal**: Migrate existing markdown agents to JSON config
- [ ] Write migration script (`scripts/migrate-agents.ts`)
- [ ] Parse markdown frontmatter
- [ ] Extract metadata
- [ ] Generate agent.json
- [ ] Split prompt into prompt.md
- [ ] Preserve all information
- [ ] Migrate core agents:
- [ ] OpenAgent
- [ ] OpenCoder
- [ ] Migrate all subagents:
- [ ] TaskManager
- [ ] ContextScout
- [ ] CoderAgent
- [ ] CodeReviewer
- [ ] TestEngineer
- [ ] DocWriter
- [ ] BuildAgent
- [ ] (all others)
- [ ] Generate manifest.json
- [ ] Validate all migrated configs
**Deliverables**:
- ✅ Migration script
- ✅ All agents migrated
- ✅ Validation passing
- ✅ No data loss
---
### Phase 4: Testing & Validation (Week 4)
**Goal**: Comprehensive testing of new system
- [ ] Unit tests:
- [ ] Config loader
- [ ] Each converter
- [ ] Validation logic
- [ ] Integration tests:
- [ ] Convert → Apply workflow
- [ ] Multi-IDE apply
- [ ] Profile-based apply
- [ ] End-to-end tests:
- [ ] Create agent → Validate → Apply → Test
- [ ] Compatibility tests:
- [ ] OpenCode native format
- [ ] Claude conversion
- [ ] Cursor flattening
- [ ] Performance tests:
- [ ] Load 100+ agents
- [ ] Convert all agents
- [ ] Apply to multiple IDEs
**Deliverables**:
- ✅ Test coverage >90%
- ✅ All tests passing
- ✅ Performance benchmarks
- ✅ Compatibility verified
---
### Phase 5: Documentation (Week 5)
**Goal**: Complete documentation for new system
- [ ] User documentation:
- [ ] JSON config format guide
- [ ] Migration guide (markdown → JSON)
- [ ] CLI command reference
- [ ] IDE compatibility matrix
- [ ] Best practices
- [ ] Developer documentation:
- [ ] TypeScript interfaces
- [ ] Converter API
- [ ] Adding new IDE support
- [ ] Schema extension guide
- [ ] Examples:
- [ ] Simple agent
- [ ] Complex agent with all features
- [ ] Subagent
- [ ] Multi-IDE setup
**Deliverables**:
- ✅ Complete user docs
- ✅ Complete dev docs
- ✅ Example agents
- ✅ Migration guide
---
### Phase 6: Deprecation (Week 6)
**Goal**: Deprecate old markdown format
- [ ] Add deprecation warnings:
- [ ] Warn when loading markdown agents
- [ ] Suggest migration command
- [ ] Show migration guide link
- [ ] Update registry.json:
- [ ] Point to new JSON configs
- [ ] Mark markdown agents as deprecated
- [ ] Update install.sh:
- [ ] Use new JSON format
- [ ] Auto-migrate on install
- [ ] Update CI/CD:
- [ ] Validate JSON configs
- [ ] Fail on markdown agents (optional)
**Deliverables**:
- ✅ Deprecation warnings
- ✅ Updated registry
- ✅ Updated installer
- ✅ CI/CD validation
---
## 📋 Implementation Checklist
### Week 1: Infrastructure
- [ ] Create `packages/core/src/types/agent.ts`
- [ ] Create `packages/core/src/schemas/agent-v2.json`
- [ ] Create `packages/core/src/agent/loader.ts`
- [ ] Create `packages/core/src/agent/converters/opencode.ts`
- [ ] Create `packages/core/src/agent/converters/claude.ts`
- [ ] Create `packages/core/src/agent/converters/cursor.ts`
- [ ] Create `packages/core/src/agent/converters/windsurf.ts`
- [ ] Create `packages/core/src/agent/converters/registry.ts`
- [ ] Write unit tests
- [ ] Validate with sample configs
### Week 2: CLI Commands
- [ ] Create `packages/core/src/cli/convert.ts`
- [ ] Create `packages/core/src/cli/validate.ts`
- [ ] Create `packages/core/src/cli/apply.ts`
- [ ] Create `packages/core/src/cli/info.ts`
- [ ] Add to main CLI entry point
- [ ] Write help text
- [ ] Add examples
- [ ] Test all commands
### Week 3: Migration
- [ ] Create `scripts/migrate-agents.ts`
- [ ] Migrate OpenAgent
- [ ] Migrate OpenCoder
- [ ] Migrate all subagents
- [ ] Generate manifest.json
- [ ] Validate all configs
- [ ] Test conversions
### Week 4: Testing
- [ ] Write unit tests
- [ ] Write integration tests
- [ ] Write e2e tests
- [ ] Performance testing
- [ ] Compatibility testing
- [ ] Fix any issues
### Week 5: Documentation
- [ ] Write user guide
- [ ] Write dev guide
- [ ] Write migration guide
- [ ] Create examples
- [ ] Update README
- [ ] Update CHANGELOG
### Week 6: Deprecation
- [ ] Add warnings
- [ ] Update registry
- [ ] Update installer
- [ ] Update CI/CD
- [ ] Final testing
- [ ] Release v2.0.0
---
## 🎯 Success Criteria
### Must Have
- ✅ All agents converted to JSON config
- ✅ All CLI commands working
- ✅ OpenCode, Claude, Cursor converters working
- ✅ Schema validation working
- ✅ Migration script working
- ✅ Documentation complete
- ✅ Tests passing (>90% coverage)
### Nice to Have
- ✅ Windsurf converter
- ✅ Auto-migration on install
- ✅ IDE detection
- ✅ Interactive agent creation wizard
- ✅ Web-based config editor
### Future Enhancements
- 🔮 Remote agent registry
- 🔮 Agent marketplace
- 🔮 Visual agent builder
- 🔮 Agent versioning system
- 🔮 Agent templates library
---
## 📊 Comparison: Before vs After
### Before (Markdown)
```markdown
---
id: openagent
name: OpenAgent
type: orchestrator
---
# OpenAgent
You are OpenAgent...
## Tools
- bash (approve)
- write (approve)
- edit (approve)
## Skills
- task-management
## Context
- .opencode/context/core/standards/code-quality.md
```
**Problems**:
- ❌ Hard to parse
- ❌ No validation
- ❌ No type safety
- ❌ Hard to query
- ❌ Manual conversion
### After (JSON + Markdown)
**agent.json**:
```json
{
"id": "openagent",
"name": "OpenAgent",
"mode": "primary",
"prompt": { "file": "./prompt.md" },
"permissions": {
"bash": "approve",
"write": "approve",
"edit": "approve"
},
"tools": {
"bash": true,
"write": true,
"edit": true
},
"skills": ["task-management"],
"context": ["@core/standards/code-quality"]
}
```
**prompt.md**:
```markdown
You are OpenAgent...
```
**Benefits**:
- ✅ Easy to parse
- ✅ Schema validated
- ✅ Type safe
- ✅ Easy to query
- ✅ Auto-convert to any IDE
---
## 🚀 Next Steps
1. **Review this plan** - Get team approval
2. **Set up branch** - `feature/json-config-system`
3. **Start Phase 1** - Build infrastructure
4. **Weekly reviews** - Track progress
5. **Launch v2.0.0** - After 6 weeks
---
**Status**: Ready for implementation
**Estimated Timeline**: 6 weeks
**Risk Level**: Low (backward compatible during migration)
**Impact**: High (foundation for all future features)
---
**Last Updated**: 2026-02-15
**Next Review**: After Phase 1 completion