oh-my-claudecode-opencode 0.1.0

package/README.md

@@ -0,0 +1,361 @@
+# oh-my-claudecode-opencode (omco)
+
+> 🔄 **OpenCode port of [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) v3.0.11**
+
+**oh-my-claudecode-opencode** (omco) - Multi-agent orchestration plugin that brings [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) features to [OpenCode](https://github.com/opencode-ai/opencode).
+
+Like Sisyphus condemned to roll his boulder eternally, this plugin ensures your AI assistant **never stops until the task is complete**.
+
+---
+
+## 🎯 What is this?
+
+This project **ports the powerful features** of [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) v3.0.11 (a Claude Code plugin) to the **OpenCode platform**.
+
+| Original (Claude Code) | This Port (OpenCode) |
+|------------------------|----------------------|
+| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | **oh-my-claudecode-opencode** (omco) |
+| Shell hooks + Node.js bridge | Native TypeScript plugin API |
+| Stop hook (proactive blocking) | session.idle event (reactive) |
+
+### Key Features Ported
+- ✅ Ultrawork Mode (maximum intensity parallel execution)
+- ✅ Ralph Loop (self-referential completion loop)
+- ✅ TODO Continuation Enforcer
+- ✅ PRD-based task tracking
+- ✅ Notepad memory system (`<remember>` tags)
+- ✅ Background agent orchestration
+- ✅ Session state persistence
+
+---
+
+## Features
+
+### Core Capabilities
+
+- **TODO Continuation Enforcer** - Automatically reminds the assistant to complete pending tasks
+- **Ultrawork Mode** - Maximum intensity parallel execution triggered by keywords
+- **Ralph Loop** - Self-referential loop that continues until verified completion
+- **Background Agents** - Run explore/librarian agents in parallel without blocking
+- **Agent Usage Reminder** - Encourages using specialized agents over direct tool calls
+
+### Specialized Agents
+
+> **Note:** New agent names are available with backward compatibility for legacy names.
+
+| Agent (New) | Alias (Legacy) | Model | Purpose |
+|-------------|----------------|-------|---------|
+| `architect` | `oracle` | Opus | Strategic architecture & debugging advisor (READ-ONLY) |
+| `architect-medium` | `oracle-medium` | Sonnet | Balanced architectural analysis (READ-ONLY) |
+| `architect-low` | `oracle-low` | Haiku | Fast architectural checks (READ-ONLY) |
+| `researcher` | `librarian` | Sonnet | Documentation & reference researcher |
+| `researcher-low` | `librarian-low` | Haiku | Quick documentation lookup |
+| `explore` | - | Haiku | Fast codebase search |
+| `explore-medium` | - | Sonnet | Deeper codebase analysis |
+| `designer` | `frontend-engineer` | Sonnet | UI/UX designer-developer |
+| `designer-low` | `frontend-engineer-low` | Haiku | Fast UI changes |
+| `designer-high` | `frontend-engineer-high` | Opus | Complex UI architecture |
+| `writer` | `document-writer` | Haiku | Technical documentation |
+| `executor` | `sisyphus-junior` | Sonnet | Focused task executor |
+| `executor-low` | `sisyphus-junior-low` | Haiku | Simple task execution |
+| `executor-high` | `sisyphus-junior-high` | Opus | Complex multi-file tasks |
+| `planner` | `prometheus` | Opus | Strategic planning |
+| `analyst` | `metis` | Opus | Pre-planning analysis |
+| `critic` | `momus` | Opus | Plan review |
+| `vision` | `multimodal-looker` | Sonnet | Visual/media analysis |
+| `qa-tester` | - | Sonnet | Interactive CLI testing |
+
+## Installation
+
+```bash
+# Using npm
+npm install oh-my-claudecode-opencode
+
+# Using bun
+bun add oh-my-claudecode-opencode
+
+# Using pnpm
+pnpm add oh-my-claudecode-opencode
+```
+
+Then add to your OpenCode configuration:
+
+```json
+{
+  "plugins": ["oh-my-claudecode-opencode"]
+}
+```
+
+## Usage
+
+### Ultrawork Mode
+
+Trigger maximum performance mode by including keywords in your prompt:
+
+```
+ultrawork: Implement the authentication system with tests
+```
+
+or
+
+```
+ulw refactor the database layer
+```
+
+Keywords: `ultrawork`, `ulw`, `uw`
+
+### Slash Commands
+
+| Command | Description |
+|---------|-------------|
+| `/ultrawork <task>` | Maximum intensity parallel execution |
+| `/ralph-loop <task>` | Completion guarantee loop |
+| `/ultrawork-ralph <task>` | Combined max intensity + completion guarantee |
+| `/ultraqa <goal>` | QA cycling workflow |
+| `/ralplan <task>` | Iterative planning with Planner/Architect/Critic |
+| `/plan <task>` | Start planning session |
+| `/review <plan>` | Review plan with Critic |
+| `/doctor` | Diagnose installation issues |
+| `/cancel-ralph` | Cancel Ralph Loop |
+| `/cancel-ultraqa` | Cancel UltraQA |
+
+### Ralph Loop
+
+Start a self-referential loop that continues until the task is verified complete:
+
+```
+/ralph-loop "Implement user registration with email verification"
+```
+
+Cancel with:
+
+```
+/cancel-ralph
+```
+
+### Background Agents
+
+The plugin provides tools for running agents in the background:
+
+```typescript
+// Run explore agent in background
+background_task(agent="explore", prompt="Find all authentication-related files")
+
+// Run librarian for documentation research
+background_task(agent="librarian", prompt="Find JWT best practices documentation")
+
+// Get results when ready
+background_output(task_id="...")
+
+// Cancel all background tasks
+background_cancel(all=true)
+```
+
+### Call Agents Directly
+
+```typescript
+// Synchronous call
+call_omo_agent(
+  subagent_type="oracle",
+  prompt="Review this architecture decision...",
+  run_in_background=false
+)
+
+// Async call
+call_omo_agent(
+  subagent_type="explore",
+  prompt="Find all React components",
+  run_in_background=true
+)
+```
+
+## Configuration
+
+Create `.opencode/omco.json` in your project:
+
+```json
+{
+  "disabled_hooks": [],
+  "background_task": {
+    "max_concurrent": 5,
+    "timeout_ms": 300000
+  },
+  "ralph_loop": {
+    "max_iterations": 50,
+    "idle_timeout_ms": 30000
+  },
+  "todo_continuation": {
+    "idle_threshold_ms": 15000,
+    "reminder_interval_ms": 60000
+  },
+  "ultrawork": {
+    "keywords": ["ultrawork", "ulw", "uw"],
+    "auto_parallel": true
+  }
+}
+```
+
+### Configuration Options
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `disabled_hooks` | Hooks to disable | `[]` |
+| `background_task.max_concurrent` | Max parallel background tasks | `5` |
+| `background_task.timeout_ms` | Background task timeout | `300000` |
+| `ralph_loop.max_iterations` | Max loop iterations | `50` |
+| `ralph_loop.idle_timeout_ms` | Idle time before continuation | `30000` |
+| `todo_continuation.idle_threshold_ms` | Idle threshold for TODO check | `15000` |
+| `ultrawork.keywords` | Trigger keywords | `["ultrawork", "ulw", "uw"]` |
+
+### Model Provider Configuration
+
+By default, oh-my-claudecode-opencode uses **GitHub Copilot Claude 4.5 models** for the three tiers:
+
+| Tier | Default Model |
+|------|---------------|
+| `haiku` | `github-copilot/claude-haiku-4.5` |
+| `sonnet` | `github-copilot/claude-sonnet-4.5` |
+| `opus` | `github-copilot/claude-opus-4.5` |
+
+To use other providers like Google or OpenAI, configure `model_mapping.tierDefaults`:
+
+```json
+{
+  "model_mapping": {
+    "tierDefaults": {
+      "haiku": "google/gemini-3-flash",
+      "sonnet": "google/gemini-3-pro-low",
+      "opus": "openai/gpt-5.2"
+    }
+  }
+}
+```
+
+**Model Format**: Always use `provider/model-name` format (e.g., `github-copilot/claude-sonnet-4.5`, `google/gemini-3-flash`)
+
+**Tier Semantics**:
+| Tier | Purpose | Typical Use |
+|------|---------|-------------|
+| `haiku` | Fast, cheap | explore, simple lookups, quick checks |
+| `sonnet` | Balanced | executor, designer, most agents |
+| `opus` | Most capable | architect, planner, complex reasoning |
+
+**Partial Configuration**: You only need to specify tiers you want to override. Unspecified tiers fall back to Copilot Claude defaults.
+
+**Per-Agent Override**: Override specific agents with either a tier or concrete model:
+
+```json
+{
+  "agents": {
+    "architect": { "model": "openai/gpt-5.2" },
+    "explore": { "tier": "sonnet" },
+    "executor": { "model": "google/gemini-3-pro-low", "temperature": 0.3 }
+  }
+}
+```
+
+**Debug Logging**: Enable model resolution logging:
+
+```json
+{
+  "model_mapping": {
+    "debugLogging": true
+  }
+}
+```
+
+### Disabling Hooks
+
+```json
+{
+  "disabled_hooks": [
+    "agent-usage-reminder",
+    "keyword-detector"
+  ]
+}
+```
+
+Available hooks:
+- `todo-continuation-enforcer`
+- `keyword-detector`
+- `ralph-loop`
+- `session-recovery`
+- `agent-usage-reminder`
+
+## How It Works
+
+### TODO Continuation Enforcer
+
+When the assistant has incomplete TODO items and becomes idle:
+
+1. Plugin detects idle state (no tool calls for configured threshold)
+2. Checks if pending/in_progress TODOs exist
+3. Injects continuation prompt:
+
+```
+[SYSTEM REMINDER - TODO CONTINUATION]
+Incomplete tasks remain in your todo list. Continue working on the next pending task.
+Proceed without asking for permission. Mark each task complete when finished.
+Do not stop until all tasks are done.
+```
+
+### Ralph Loop
+
+Self-referential execution loop:
+
+1. User invokes `/ralph-loop "task description"`
+2. Plugin creates PRD (Product Requirements Document) if not exists
+3. Monitors for completion signals (`<promise>DONE</promise>`)
+4. Re-injects task prompt on idle until completion
+5. Tracks iterations to prevent infinite loops
+
+### Ultrawork Mode
+
+When triggered:
+
+1. Injects high-intensity system prompt
+2. Encourages parallel execution
+3. Minimizes confirmation requests
+4. Maximizes throughput
+
+## Development
+
+```bash
+# Clone the repo
+git clone https://github.com/devswha/oh-my-claudecode-opencode.git
+cd oh-my-claudecode-opencode
+
+# Install dependencies
+bun install
+
+# Build
+bun run build
+
+# Type check
+bun run typecheck
+
+# Run tests
+bun test
+```
+
+## Philosophy
+
+Named after Sisyphus from Greek mythology - condemned to roll a boulder up a hill for eternity. Like Sisyphus, this plugin embodies **persistence**:
+
+- Tasks are tracked until completion
+- The assistant cannot simply "give up"
+- Work continues until the boulder reaches the summit
+
+> "The struggle itself toward the heights is enough to fill a man's heart. One must imagine Sisyphus happy." - Albert Camus
+
+## Credits
+
+This project is an **OpenCode port** of [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) by [@Yeachan-Heo](https://github.com/Yeachan-Heo).
+
+Special thanks to:
+- [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) - The original Claude Code plugin this project ports
+- [OpenCode](https://github.com/opencode-ai/opencode) - The target platform
+
+## License
+
+MIT

package/assets/AGENTS.md

@@ -0,0 +1,357 @@
+# Assets
+
+**Parent:** [../AGENTS.md](../AGENTS.md)
+
+## Porting Context
+
+oh-my-claudecode 설정 스키마를 OpenCode 형식으로 변환한 JSON 스키마. omo-omcs.schema.json은 oh-my-claudecode의 설정 스키마를 기반으로 하며, OpenCode 환경에 맞게 조정되었다. IDE 자동완성 및 검증 지원을 제공한다.
+
+## Overview
+
+This directory contains static project assets, primarily the JSON schema definition for omo-omcs configuration validation.
+
+## Key Files
+
+### `omo-omcs.schema.json`
+**Purpose**: JSON Schema for configuration file validation
+**Schema Version**: Draft-07
+**Usage**: Provides IDE autocomplete and validation for `.opencode/omo-omcs.json`
+
+## Schema Structure
+
+### Root Configuration Object
+
+The schema defines a comprehensive configuration structure for the omo-omcs plugin:
+
+```json
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "omo-omcs Configuration",
+  "description": "Configuration schema for Oh My OpenCode Sisyphus plugin",
+  "type": "object"
+}
+```
+
+### Configuration Properties
+
+#### `disabled_hooks`
+**Type**: Array of strings
+**Description**: List of hooks to disable
+**Enum Values**:
+- `todo-continuation-enforcer` - Disable TODO continuation prompts
+- `keyword-detector` - Disable ultrawork/ralph keyword detection
+- `ralph-loop` - Disable ralph-loop mode
+- `session-recovery` - Disable session recovery
+- `agent-usage-reminder` - Disable agent usage reminders
+
+**Example**:
+```json
+{
+  "disabled_hooks": ["todo-continuation-enforcer", "agent-usage-reminder"]
+}
+```
+
+#### `background_task`
+**Type**: Object
+**Description**: Background task execution configuration
+
+**Properties**:
+- `max_concurrent` (integer, 1-10, default: 5)
+  - Maximum concurrent background tasks
+
+- `timeout_ms` (integer, 1000-600000, default: 300000)
+  - Default timeout in milliseconds (5 minutes)
+
+**Example**:
+```json
+{
+  "background_task": {
+    "max_concurrent": 3,
+    "timeout_ms": 120000
+  }
+}
+```
+
+#### `ralph_loop`
+**Type**: Object
+**Description**: Ralph-loop persistence mode configuration
+
+**Properties**:
+- `max_iterations` (integer, 1-100, default: 50)
+  - Maximum iterations before forced stop
+
+- `idle_timeout_ms` (integer, 5000-300000, default: 30000)
+  - Idle timeout before continuation prompt (30 seconds)
+
+- `prd_path` (string, default: ".omc/prd.json")
+  - Path to PRD file for structured tracking
+
+**Example**:
+```json
+{
+  "ralph_loop": {
+    "max_iterations": 75,
+    "idle_timeout_ms": 20000,
+    "prd_path": ".omc/requirements.json"
+  }
+}
+```
+
+#### `todo_continuation`
+**Type**: Object
+**Description**: TODO continuation enforcer configuration
+
+**Properties**:
+- `idle_threshold_ms` (integer, 5000-120000, default: 15000)
+  - Time before checking for incomplete TODOs (15 seconds)
+
+- `reminder_interval_ms` (integer, 10000-300000)
+  - Interval between reminder prompts
+
+**Example**:
+```json
+{
+  "todo_continuation": {
+    "idle_threshold_ms": 10000,
+    "reminder_interval_ms": 30000
+  }
+}
+```
+
+## IDE Integration
+
+### VSCode Setup
+
+Enable schema validation in VSCode:
+
+1. **Option 1: In config file**
+   ```json
+   {
+     "$schema": "node_modules/oh-my-ssalsyphus/assets/omo-omcs.schema.json",
+     "disabled_hooks": []
+   }
+   ```
+
+2. **Option 2: In VSCode settings.json**
+   ```json
+   {
+     "json.schemas": [
+       {
+         "fileMatch": [".opencode/omo-omcs.json"],
+         "url": "./node_modules/oh-my-ssalsyphus/assets/omo-omcs.schema.json"
+       }
+     ]
+   }
+   ```
+
+### Benefits
+- **Autocomplete**: IDE suggests valid property names
+- **Validation**: Real-time error checking
+- **Documentation**: Hover tooltips show property descriptions
+- **Type checking**: Prevents invalid values (wrong types, out of range)
+
+## Schema Validation Examples
+
+### Valid Configuration
+```json
+{
+  "$schema": "node_modules/oh-my-ssalsyphus/assets/omo-omcs.schema.json",
+  "disabled_hooks": ["agent-usage-reminder"],
+  "background_task": {
+    "max_concurrent": 8,
+    "timeout_ms": 180000
+  },
+  "ralph_loop": {
+    "max_iterations": 100,
+    "idle_timeout_ms": 25000,
+    "prd_path": ".omc/prd.json"
+  },
+  "todo_continuation": {
+    "idle_threshold_ms": 20000
+  }
+}
+```
+
+### Invalid Examples
+
+#### Out of Range
+```json
+{
+  "background_task": {
+    "max_concurrent": 15  // ❌ Max is 10
+  }
+}
+```
+
+#### Invalid Hook Name
+```json
+{
+  "disabled_hooks": ["invalid-hook"]  // ❌ Not in enum
+}
+```
+
+#### Wrong Type
+```json
+{
+  "ralph_loop": {
+    "max_iterations": "50"  // ❌ Should be integer, not string
+  }
+}
+```
+
+## Schema Maintenance
+
+### Updating the Schema
+
+When adding new config options:
+
+1. **Add to Zod schema** (`src/config/index.ts`):
+   ```typescript
+   const ConfigSchema = z.object({
+     new_feature: z.object({
+       enabled: z.boolean().optional()
+     }).optional()
+   });
+   ```
+
+2. **Add to JSON schema** (`assets/omo-omcs.schema.json`):
+   ```json
+   {
+     "properties": {
+       "new_feature": {
+         "type": "object",
+         "properties": {
+           "enabled": {
+             "type": "boolean",
+             "default": false
+           }
+         }
+       }
+     }
+   }
+   ```
+
+3. **Update documentation** (this file)
+
+4. **Add validation test** (`tests/config.test.ts`)
+
+### Schema Versioning
+
+- Schema follows JSON Schema Draft-07
+- Breaking changes require major version bump
+- New optional properties = minor version bump
+- Clarifications/docs = patch version bump
+
+## Package Export
+
+The schema is exported via package.json:
+
+```json
+{
+  "exports": {
+    "./schema.json": "./assets/omo-omcs.schema.json"
+  }
+}
+```
+
+Usage in user projects:
+```json
+{
+  "$schema": "node_modules/oh-my-ssalsyphus/schema.json"
+}
+```
+
+## Validation Tools
+
+### Manual Validation
+
+```bash
+# Install ajv-cli
+npm install -g ajv-cli
+
+# Validate config
+ajv validate \
+  -s node_modules/oh-my-ssalsyphus/assets/omo-omcs.schema.json \
+  -d .opencode/omo-omcs.json
+```
+
+### Programmatic Validation
+
+```typescript
+import Ajv from 'ajv';
+import schema from 'oh-my-ssalsyphus/schema.json';
+
+const ajv = new Ajv();
+const validate = ajv.compile(schema);
+
+const config = { /* ... */ };
+const valid = validate(config);
+
+if (!valid) {
+  console.error(validate.errors);
+}
+```
+
+## Schema Features
+
+### Property Constraints
+- **Type enforcement**: string, integer, boolean, array, object
+- **Range validation**: minimum, maximum for integers
+- **Enum validation**: Fixed set of allowed values
+- **Default values**: Auto-filled by IDE
+- **Required properties**: Currently all optional
+
+### Additional Validation
+- `additionalProperties: false` - Prevent unknown properties
+- Descriptions for all properties - IDE tooltips
+- Default values documented - User guidance
+
+## Common Patterns
+
+### Timeout Configuration
+All timeouts use milliseconds:
+- 1000ms = 1 second
+- 60000ms = 1 minute
+- 300000ms = 5 minutes
+
+### Iteration Limits
+Prevent infinite loops:
+- `max_iterations`: 1-100 (ralph-loop)
+- `max_concurrent`: 1-10 (background tasks)
+
+### Path Configuration
+Use relative paths from project root:
+- `.omc/prd.json` - PRD file
+- `.omc/progress.txt` - Progress tracking
+
+## Integration Points
+
+- **Config Loader**: `/home/calvin/workspace/omo-omcs/src/config/` - Uses Zod for runtime validation
+- **Documentation**: `/home/calvin/workspace/omo-omcs/docs/` - Schema usage in README
+- **Tests**: `/home/calvin/workspace/omo-omcs/tests/` - Schema validation tests
+
+## Future Enhancements
+
+### Planned Schema Features
+- **Agent-specific config**: Override settings per agent
+- **Mode presets**: Predefined mode combinations
+- **Notification settings**: Configure toast/prompt behavior
+- **Logging config**: Debug levels, output formats
+- **Performance tuning**: Token limits, parallelization settings
+
+### Schema Improvements
+- **$ref support**: Reusable schema definitions
+- **Conditional schemas**: If/then/else validation
+- **Pattern properties**: Dynamic property names
+- **Dependencies**: Property interdependencies
+- **Examples**: Inline config examples
+
+## Dependencies
+
+- None (pure JSON schema)
+
+## Related Documentation
+
+- [Config System](../src/config/AGENTS.md) - Runtime config loading
+- [Documentation](../docs/AGENTS.md) - Usage examples
+- [JSON Schema Spec](https://json-schema.org/draft-07/schema) - Schema reference