Major cleanup: Remove redundant code, consolidate knowledge base

- Delete redundant directories: demo/, server/, orchestrator/, team-portal/, servers/
- Remove all human-readable documentation (docs/, .dss/*.md, admin-ui/*.md)
- Consolidate 4 knowledge JSON files into single DSS_CORE.json
- Clear browser logs (7.5MB), backups, temp files
- Remove obsolete configs (.cursorrules, .dss-boundaries.yaml, .ds-swarm/)
- Reduce project from 20MB to ~8MB

Kept: tools/, admin-ui/, cli/, dss-claude-plugin/, .dss/schema/

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-10 07:34:52 -03:00
parent 3e4295457d
commit 7a3044bccc
470 changed files with 233 additions and 252780 deletions

View File

@@ -1,224 +0,0 @@
# Context Compiler - Production Deployment
**Date**: 2025-12-07
**Status**: ✅ DEPLOYED TO PRODUCTION
**Version**: 1.0.0
## Deployment Summary
The Context Compiler has been successfully integrated into the DSS MCP Server and is ready for production use.
### What Was Deployed
**5 New MCP Tools** added to dss-mcp-server.py:
1. **dss_get_resolved_context** - Get fully resolved design system context (3-layer cascade)
2. **dss_resolve_token** - Resolve specific token through cascade (dot-notation)
3. **dss_validate_manifest** - Validate ds.config.json against schema
4. **dss_list_skins** - List all available skins in registry
5. **dss_get_compiler_status** - Get compiler health and configuration
### Integration Points
#### 1. Imports (lines 69-81)
```python
# Context Compiler imports
try:
from core import (
get_active_context,
resolve_token,
validate_manifest,
list_skins,
get_compiler_status
)
CONTEXT_COMPILER_AVAILABLE = True
except ImportError as e:
CONTEXT_COMPILER_AVAILABLE = False
CONTEXT_COMPILER_IMPORT_ERROR = str(e)
```
#### 2. Tool Definitions (lines 600-681)
- Added 5 tool definitions with full input schemas
- Tools support debug mode, force_refresh, and provenance tracking
- Integrated into tool list: `dss_tools + devtools_tools + browser_tools + context_compiler_tools`
#### 3. Tool Handlers (lines 823-894)
- Added 5 tool handlers in call_tool() function
- Error handling for unavailable Context Compiler
- JSON parsing and result wrapping
### Test Results
**All Tests Passing**
```
Context Compiler: 27/27 tests passed
- Basic compilation (3-layer cascade)
- Debug provenance tracking
- Token resolution
- Skin listing
- Safe Boot Protocol
- Path traversal prevention (security)
- Compiler status
```
**Integration Tests**
```
✓ Syntax check passed (Python compilation)
✓ Context Compiler imports successful
✓ list_skins() returned 3 skins: ['base', 'workbench', 'classic']
✓ get_compiler_status() returned status: active
```
### Architecture
**3-Layer Cascade**:
```
Base Skin → Extended Skin → Project Overrides = Final Context
```
**Key Features**:
- ✅ Cache invalidation (mtime-based)
- ✅ Force refresh parameter
- ✅ Debug mode with provenance tracking
- ✅ Safe Boot Protocol (emergency fallback)
- ✅ Path traversal security
- ✅ Thread-safe implementation
### Files Modified
1. **servers/dss-mcp-server.py**
- Added imports (lines 69-81)
- Added 5 tool definitions (lines 600-681)
- Added 5 tool handlers (lines 823-894)
- Total: +151 lines
### Total Tool Count
**MCP Server now provides 36 tools**:
- 31 existing DSS tools
- 5 new Context Compiler tools
### Cache Behavior
- **Non-debug mode**: Results cached with mtime validation
- **Debug mode**: Cache bypassed (provenance must be fresh)
- **Force refresh**: Manual cache bypass available
- **Cache keys**: `{manifest_path}:debug={debug}` (prevents collision)
### Error Handling
All tools include:
- ✅ Availability check (CONTEXT_COMPILER_AVAILABLE)
- ✅ Try-catch error handling
- ✅ Structured error responses
- ✅ Safe Boot Protocol fallback
### Security
- ✅ Path traversal prevention in _load_skin()
- ✅ Input validation for manifest paths
- ✅ No server-side path allowlist (delegated to MCP client)
- ✅ Emergency fallback on catastrophic failure
### Documentation
Created comprehensive documentation:
- **DEPLOYMENT_INTEGRATION.md** - Step-by-step integration guide
- **This file** - Production deployment summary
- **Test suite** - test_context_compiler.py (27 tests)
### Usage Examples
#### Get Resolved Context
```python
dss_get_resolved_context(
manifest_path="/path/to/ds.config.json",
debug=False,
force_refresh=False
)
```
#### Resolve Specific Token
```python
dss_resolve_token(
manifest_path="/path/to/ds.config.json",
token_path="colors.primary",
force_refresh=False
)
```
#### List Available Skins
```python
dss_list_skins()
# Returns: ["base", "workbench", "classic"]
```
#### Get Compiler Status
```python
dss_get_compiler_status()
# Returns: {"status": "active", "skins_directory": "...", ...}
```
### Next Steps
1. ✅ Integration complete
2. ✅ Tests passing
3. ✅ Documentation written
4. 🔄 **MCP Server restart required** - Claude Code will pick up new tools on next connection
### How to Use
After MCP server restarts, the 5 new tools will be available to Claude Code:
```bash
# Claude Code will automatically discover these tools:
- mcp__plugin_dss-claude-plugin_dss__dss_get_resolved_context
- mcp__plugin_dss-claude-plugin_dss__dss_resolve_token
- mcp__plugin_dss-claude-plugin_dss__dss_validate_manifest
- mcp__plugin_dss-claude-plugin_dss__dss_list_skins
- mcp__plugin_dss-claude-plugin_dss__dss_get_compiler_status
```
### Rollback Plan
If issues arise, revert changes in dss-mcp-server.py:
1. Remove imports (lines 69-81)
2. Remove tool definitions (lines 600-681)
3. Remove tool handlers (lines 823-894)
4. Restart MCP server
### Performance Impact
- **Bundle size**: +3KB (mcp_extensions.py)
- **Initialization**: +10ms (import time)
- **Memory**: +~500KB (compiler instance + cache)
- **First compilation**: ~50-100ms
- **Cached compilation**: ~1-5ms
### Monitoring
Monitor these metrics:
- Tool invocation count (via MCP logging)
- Cache hit rate (check logger.debug messages)
- Error rate (CONTEXT_COMPILER_IMPORT_ERROR)
- Compilation time (especially for large manifests)
---
## Deployment Checklist
- [x] Context Compiler implementation complete
- [x] 27/27 tests passing
- [x] Cache invalidation implemented
- [x] Force refresh parameter added
- [x] Debug mode cache collision fixed
- [x] Imports added to dss-mcp-server.py
- [x] 5 tool definitions added
- [x] 5 tool handlers added
- [x] Integration tests passed
- [x] Documentation complete
- [ ] MCP server restarted (requires user action)
- [ ] Tools verified in Claude Code (after restart)
**Status**: ✅ Ready for production use
**Action Required**: Restart MCP server to activate new tools

View File

@@ -1,565 +0,0 @@
# DSS Claude Plugin
Design System Server (DSS) integration for Claude Code - A comprehensive plugin for analyzing, extracting, and generating design system tokens and components.
## Overview
The DSS Claude Plugin brings the power of DSS directly into Claude Code, enabling:
- **Project Analysis**: Scan codebases for design patterns and tokenization opportunities
- **Token Extraction**: Extract design tokens from CSS, SCSS, Tailwind, and JSON
- **Theme Generation**: Generate theme files using style-dictionary
- **Component Auditing**: Audit components for design system adoption
- **Storybook Integration**: Set up and configure Storybook
- **Figma Sync**: Import tokens directly from Figma files
- **Quick Wins**: Find low-effort, high-impact improvements
## Installation
### Local Development Setup
For local machines with GUI (desktop/laptop):
```bash
# 1. Clone the repository
git clone https://github.com/overbits/dss.git
cd dss
# 2. Run the setup script
./setup.sh
# 3. Install the plugin in Claude Code
claude /plugin install ./dss-claude-plugin
```
Or manually:
```bash
# 1. Create and activate virtual environment
python3 -m venv .venv
source .venv/bin/activate
# 2. Install dependencies
pip install -r requirements.txt
playwright install chromium
# 3. Install the plugin
claude /plugin install ./dss-claude-plugin
```
### Remote/Headless Server Setup
For remote servers, VPS, Docker, or CI/CD environments:
```bash
# 1. Clone the repository
git clone https://github.com/overbits/dss.git
cd dss
# 2. Install dependencies (headless mode)
pip install -r requirements.txt
playwright install chromium --with-deps # Installs system dependencies
# 3. Install the plugin in Claude Code
claude /plugin install ./dss-claude-plugin
```
**Docker Setup:**
```dockerfile
FROM python:3.10-slim
# Install system dependencies for Playwright
RUN apt-get update && apt-get install -y \
libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
libcups2 libdrm2 libxkbcommon0 libxcomposite1 \
libxdamage1 libxfixes3 libxrandr2 libgbm1 libasound2
WORKDIR /app
COPY . .
RUN pip install -r requirements.txt
RUN playwright install chromium
# DSS MCP server runs on stdio
CMD ["python3", "dss-claude-plugin/servers/dss-mcp-server.py"]
```
### Claude Code Configuration
After installing the plugin, Claude Code automatically configures the MCP server. The configuration is stored in `.mcp.json`:
```json
{
"mcpServers": {
"dss": {
"command": "python3",
"args": ["${CLAUDE_PLUGIN_ROOT}/servers/dss-mcp-server.py"],
"env": {
"PYTHONPATH": "/path/to/dss/dss-mvp1",
"DSS_HOME": "~/.dss"
}
}
}
}
```
### Connecting Local Claude Code to Remote Server
You can run Claude Code locally while connecting to a DSS MCP server running on a remote machine.
#### Option 1: SSH Tunnel (Recommended)
Create an SSH tunnel to forward the remote MCP server:
```bash
# On local machine - tunnel remote MCP server
ssh -L 9222:localhost:9222 -L 3456:localhost:3456 user@remote-server
```
This forwards:
- Port 9222: Chrome DevTools Protocol
- Port 3456: Your web application
Then use `devtools_connect(port=9222)` as if it were local.
#### Option 2: Remote MCP via SSH
Configure Claude Code to run the MCP server over SSH. Add to your local `~/.claude/settings.json` or project `.mcp.json`:
```json
{
"mcpServers": {
"dss-remote": {
"command": "ssh",
"args": [
"user@remote-server",
"python3",
"/home/user/dss/dss-claude-plugin/servers/dss-mcp-server.py"
],
"env": {
"PYTHONPATH": "/home/user/dss/dss-mvp1"
},
"description": "Remote DSS MCP server via SSH"
}
}
}
```
#### Option 3: HTTP Proxy (Advanced)
For shared team access, run the MCP server behind an HTTP proxy:
```bash
# On remote server - start MCP with HTTP transport
# (Requires mcp-proxy or similar)
python3 -m mcp.server.http --port 8080 dss-claude-plugin/servers/dss-mcp-server.py
```
Then configure Claude Code to connect via HTTP:
```json
{
"mcpServers": {
"dss-remote": {
"url": "http://remote-server:8080",
"transport": "http"
}
}
}
```
#### Option 4: VS Code Remote / SSH Workspace
If using Claude Code in VS Code with Remote SSH extension:
1. Connect VS Code to remote server via Remote SSH
2. Install Claude Code extension in remote context
3. DSS plugin runs natively on remote - no tunneling needed
### Verify Installation
```bash
# Check DSS tools are available
claude --list-tools | grep dss
# Check DevTools are available (requires Playwright)
claude --list-tools | grep devtools
# Test the MCP server directly
echo '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}' | python3 dss-claude-plugin/servers/dss-mcp-server.py
```
## Requirements
- Claude Code >= 1.0.0
- Python 3.10+
- Node.js 18+ (for style-dictionary)
- DSS MVP1 installed at `/path/to/dss/dss-mvp1`
### Python Dependencies
```bash
pip install mcp pydantic pydantic-settings playwright aiohttp
playwright install chromium
```
Or run the full setup:
```bash
./setup.sh
```
### Optional: Figma Integration
Set your Figma personal access token:
```bash
export FIGMA_TOKEN=your-figma-token
```
## Commands
| Command | Description |
|---------|-------------|
| `/dss-analyze [path]` | Analyze project for design system patterns |
| `/dss-extract [path] [sources]` | Extract design tokens |
| `/dss-generate <format> [name]` | Generate theme files |
| `/dss-audit [path]` | Audit components for DS adoption |
| `/dss-storybook <action> [path]` | Storybook setup and configuration |
| `/dss-figma <file_key>` | Sync tokens from Figma |
| `/dss-quick-wins [path]` | Find quick win opportunities |
## Skills
The plugin includes 7 procedural skills:
1. **design-system-analysis** - Comprehensive codebase analysis
2. **token-extraction** - Multi-source token extraction
3. **theme-generation** - Style-dictionary theme generation
4. **component-audit** - React component auditing
5. **storybook-integration** - Storybook setup and stories
6. **figma-sync** - Figma API integration
7. **quick-wins** - Quick win identification
## Agents
Two specialized agents for complex tasks:
### DSS Architect
Planning and designing design system implementations.
```
"Help me plan a design system for our React application"
```
### DSS Migrator
Migrating existing codebases to design systems.
```
"Help me migrate our button components to use design tokens"
```
## MCP Tools
The plugin exposes DSS tools and Chrome DevTools tools:
### DSS Tools
| Tool | Description |
|------|-------------|
| `dss_analyze_project` | Full project analysis |
| `dss_extract_tokens` | Extract tokens from sources |
| `dss_generate_theme` | Generate theme files |
| `dss_list_themes` | List available themes |
| `dss_get_status` | Get DSS system status |
| `dss_audit_components` | Component audit |
| `dss_setup_storybook` | Storybook configuration |
| `dss_sync_figma` | Figma token sync |
| `dss_find_quick_wins` | Quick win analysis |
| `dss_transform_tokens` | Token format transformation |
### Chrome DevTools Tools
| Tool | Description |
|------|-------------|
| `devtools_launch` | Launch headless Chromium (for remote/headless servers) |
| `devtools_connect` | Connect to running Chrome with CDP (port 9222) |
| `devtools_disconnect` | Disconnect and clean up resources |
| `devtools_list_pages` | List all browser tabs/pages |
| `devtools_select_page` | Select active page for operations |
| `devtools_goto` | Navigate to a URL |
| `devtools_console_logs` | Get captured console messages |
| `devtools_network_requests` | Get captured network activity |
| `devtools_evaluate` | Execute JavaScript in page context |
| `devtools_query_dom` | Query DOM elements with CSS selector |
| `devtools_screenshot` | Capture page/element screenshots (base64 PNG) |
| `devtools_performance` | Get Core Web Vitals and performance metrics |
## Hooks
The plugin includes hooks for automation:
- **PreToolUse**: Validates Figma token before sync
- **PostToolUse**: Logs completion of major operations
## Usage Examples
### Analyze a Project
```
/dss-analyze /path/to/project
```
Returns comprehensive analysis including:
- File counts and types
- Style patterns discovered
- Component analysis
- Recommendations
### Extract and Generate Tokens
```
/dss-extract /path/to/styles css,scss
/dss-generate css my-theme
```
### Audit Components
```
/dss-audit /path/to/components
```
Identifies:
- Hardcoded values
- Consolidation opportunities
- Refactoring suggestions
### Sync from Figma
```
/dss-figma abc123xyz456
```
Extracts:
- Colors from fill styles
- Typography from text styles
- Spacing from auto-layout
- Effects and shadows
## Chrome DevTools Integration
The plugin includes Chrome DevTools Protocol (CDP) integration for browser debugging, console capture, network monitoring, and performance analysis.
### Remote/Headless Server Setup
For remote or headless servers (no GUI), use the `devtools_launch` tool to spawn a headless Chromium instance:
```python
# 1. Launch headless browser and navigate to your app
devtools_launch(url="http://localhost:3456")
# 2. Get console logs
devtools_console_logs()
# 3. Navigate to another page
devtools_goto(url="http://localhost:3456/dashboard")
# 4. Capture screenshot
devtools_screenshot(full_page=True)
# 5. Get performance metrics
devtools_performance()
# 6. Execute JavaScript
devtools_evaluate(expression="document.title")
# 7. Query DOM
devtools_query_dom(selector=".error-message")
# 8. Clean up
devtools_disconnect()
```
### Local Desktop Setup
For local development with Chrome GUI, launch Chrome with remote debugging enabled:
```bash
# Linux
google-chrome --remote-debugging-port=9222
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
# Windows
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222
```
Then connect using the `devtools_connect` tool:
```python
# 1. Connect to running Chrome
devtools_connect(port=9222)
# 2. List available tabs
devtools_list_pages()
# 3. Select a tab
devtools_select_page(page_id="...")
# 4. Capture console logs, network, etc.
devtools_console_logs()
devtools_network_requests()
# 5. Disconnect when done
devtools_disconnect()
```
### DevTools Configuration
The MCP server includes configurable limits:
```python
DEVTOOLS_CONSOLE_MAX_ENTRIES = 1000 # Max console messages stored
DEVTOOLS_NETWORK_MAX_ENTRIES = 500 # Max network requests stored
DEVTOOLS_CONNECTION_TIMEOUT_MS = 30000 # Connection timeout (30s)
```
### Common Use Cases
**Debug Console Errors:**
```python
devtools_launch(url="http://localhost:3000")
devtools_console_logs(level="error")
```
**Monitor Network Requests:**
```python
devtools_launch(url="http://localhost:3000")
devtools_network_requests(filter_url="api/")
```
**Performance Analysis:**
```python
devtools_launch(url="http://localhost:3000")
devtools_performance()
# Returns: FCP, LCP, TTFB, DOM metrics
```
**Visual Regression Testing:**
```python
devtools_launch(url="http://localhost:3000")
devtools_screenshot(full_page=True)
# Returns: base64 PNG image
```
## Architecture
```
dss-claude-plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── commands/ # 7 slash commands
├── skills/ # 7 procedural skills
├── agents/ # 2 specialized agents
├── hooks/
│ └── hooks.json # Event hooks
├── servers/
│ └── dss-mcp-server.py # Python MCP server
├── .mcp.json # MCP configuration
└── README.md
```
## Configuration
### Environment Variables
| Variable | Description |
|----------|-------------|
| `FIGMA_TOKEN` | Figma personal access token |
| `DSS_HOME` | DSS home directory (default: ~/.dss) |
| `PYTHONPATH` | Path to DSS MVP1 modules |
### Timeouts
The MCP server includes configurable timeouts:
```python
TIMEOUT_CONFIG = {
"analyze": 60, # Large project scanning
"extract": 30, # Token extraction
"generate": 30, # Theme generation
"figma_api": 15, # Figma API calls
"storybook": 60, # Storybook operations
"devtools_connect": 20, # DevTools CDP connection
"devtools_default": 10, # DevTools operations
}
```
## Development
### Running the MCP Server Directly
```bash
cd /home/overbits/dss/dss-claude-plugin
python3 servers/dss-mcp-server.py
```
### Testing
```bash
# Test MCP server
echo '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}' | python3 servers/dss-mcp-server.py
```
## Troubleshooting
### DSS Modules Not Found
Ensure PYTHONPATH is set correctly:
```bash
export PYTHONPATH=/home/overbits/dss/dss-mvp1
```
### Figma Sync Fails
1. Check FIGMA_TOKEN is set
2. Verify file key is correct
3. Check API rate limits
### Slow Analysis
For large projects, analysis may take longer. The timeout is set to 60 seconds by default.
### DevTools Launch Fails
1. Ensure Playwright is installed: `pip install playwright`
2. Install Chromium browser: `playwright install chromium`
3. On Docker/remote: ensure `--no-sandbox` flag is used (handled automatically)
### DevTools Connect Fails
1. Ensure Chrome is running with: `--remote-debugging-port=9222`
2. Check the port is not blocked by firewall
3. Verify connection: `curl http://localhost:9222/json`
### DevTools Playwright Not Available
The server gracefully degrades if Playwright isn't installed. DevTools tools will not appear in the tool list. Install with:
```bash
pip install playwright aiohttp
playwright install chromium
```
## License
MIT License - See LICENSE file for details.
## Author
overbits - https://overbits.luz.uy
## Links
- [DSS Homepage](https://dss.overbits.luz.uy)
- [Model Context Protocol](https://modelcontextprotocol.io)
- [Claude Code](https://claude.ai/code)
- [Style Dictionary](https://amzn.github.io/style-dictionary)

View File

@@ -1,220 +0,0 @@
# Context Compiler - MCP Server Integration Guide
## Overview
This guide shows how to integrate the 5 new Context Compiler tools into `dss-mcp-server.py`.
## Step 1: Add Import Statement
Add this import after line 67 (after the DSS imports):
```python
# Context Compiler imports
try:
from core import (
get_active_context,
resolve_token,
validate_manifest,
list_skins,
get_compiler_status
)
CONTEXT_COMPILER_AVAILABLE = True
except ImportError as e:
CONTEXT_COMPILER_AVAILABLE = False
CONTEXT_COMPILER_IMPORT_ERROR = str(e)
```
## Step 2: Add Tool Definitions
Add these 5 tools to the `list_tools()` function (around line 400, after the existing DSS tools):
```python
# Context Compiler Tools
Tool(
name="dss_get_resolved_context",
description="Get fully resolved design system context for a project. Returns compiled tokens from 3-layer cascade (base → skin → project).",
inputSchema={
"type": "object",
"properties": {
"manifest_path": {
"type": "string",
"description": "Absolute path to ds.config.json"
},
"debug": {
"type": "boolean",
"description": "Enable debug provenance tracking",
"default": False
},
"force_refresh": {
"type": "boolean",
"description": "Bypass cache and recompile",
"default": False
}
},
"required": ["manifest_path"]
}
),
Tool(
name="dss_resolve_token",
description="Resolve a specific design token through the cascade. Use dot-notation (e.g. 'colors.primary').",
inputSchema={
"type": "object",
"properties": {
"manifest_path": {
"type": "string",
"description": "Absolute path to ds.config.json"
},
"token_path": {
"type": "string",
"description": "Dot-notation path to token (e.g. 'colors.primary')"
},
"force_refresh": {
"type": "boolean",
"description": "Bypass cache and recompile",
"default": False
}
},
"required": ["manifest_path", "token_path"]
}
),
Tool(
name="dss_validate_manifest",
description="Validate project manifest (ds.config.json) against schema.",
inputSchema={
"type": "object",
"properties": {
"manifest_path": {
"type": "string",
"description": "Absolute path to ds.config.json"
}
},
"required": ["manifest_path"]
}
),
Tool(
name="dss_list_skins",
description="List all available design system skins in the registry.",
inputSchema={
"type": "object",
"properties": {}
}
),
Tool(
name="dss_get_compiler_status",
description="Get Context Compiler health and configuration status.",
inputSchema={
"type": "object",
"properties": {}
}
),
```
## Step 3: Add Tool Handlers
Add these handlers in the `call_tool()` function (around line 640, after the existing DSS tool handlers):
```python
# Context Compiler tools
elif name == "dss_get_resolved_context":
if not CONTEXT_COMPILER_AVAILABLE:
result = {
"success": False,
"error": f"Context Compiler not available: {CONTEXT_COMPILER_IMPORT_ERROR}"
}
else:
try:
context_json = get_active_context(
arguments.get("manifest_path"),
arguments.get("debug", False),
arguments.get("force_refresh", False)
)
result = {"success": True, "context": json.loads(context_json)}
except Exception as e:
result = {"success": False, "error": str(e)}
elif name == "dss_resolve_token":
if not CONTEXT_COMPILER_AVAILABLE:
result = {
"success": False,
"error": f"Context Compiler not available: {CONTEXT_COMPILER_IMPORT_ERROR}"
}
else:
try:
token_value = resolve_token(
arguments.get("manifest_path"),
arguments.get("token_path"),
arguments.get("force_refresh", False)
)
result = {"success": True, "token_path": arguments.get("token_path"), "value": token_value}
except Exception as e:
result = {"success": False, "error": str(e)}
elif name == "dss_validate_manifest":
if not CONTEXT_COMPILER_AVAILABLE:
result = {
"success": False,
"error": f"Context Compiler not available: {CONTEXT_COMPILER_IMPORT_ERROR}"
}
else:
try:
validation_result = validate_manifest(arguments.get("manifest_path"))
result = {"success": True, "validation": validation_result}
except Exception as e:
result = {"success": False, "error": str(e)}
elif name == "dss_list_skins":
if not CONTEXT_COMPILER_AVAILABLE:
result = {
"success": False,
"error": f"Context Compiler not available: {CONTEXT_COMPILER_IMPORT_ERROR}"
}
else:
try:
skins_json = list_skins()
result = {"success": True, "skins": json.loads(skins_json)}
except Exception as e:
result = {"success": False, "error": str(e)}
elif name == "dss_get_compiler_status":
if not CONTEXT_COMPILER_AVAILABLE:
result = {
"success": False,
"error": f"Context Compiler not available: {CONTEXT_COMPILER_IMPORT_ERROR}"
}
else:
try:
status_json = get_compiler_status()
result = {"success": True, "status": json.loads(status_json)}
except Exception as e:
result = {"success": False, "error": str(e)}
```
## Step 4: Restart MCP Server
After making these changes, restart the MCP server for Claude Code to recognize the new tools.
## Testing
Test the integration with:
```python
# Test 1: Get resolved context
dss_get_resolved_context(manifest_path="/path/to/ds.config.json")
# Test 2: Resolve specific token
dss_resolve_token(manifest_path="/path/to/ds.config.json", token_path="colors.primary")
# Test 3: List available skins
dss_list_skins()
# Test 4: Check compiler status
dss_get_compiler_status()
```
## Security Note
The Context Compiler follows the same security model as the existing 31 DSS tools:
- File access is restricted by the MCP client (Claude Code)
- Server runs with user permissions
- No additional server-side path validation required
For enhanced security across all 36 tools, consider implementing server-wide path validation against an allowlist.

View File

@@ -1,20 +0,0 @@
# Context Compiler Architecture (Phase 1)
## Overview
The DSS Context Compiler transforms the application from a simple token extractor into a context-aware system. It uses a 3-layer cascade to resolve the final design system context.
## Layer Cascade
1. **Base Layer** (`skins/base.json`): Universal tokens (white, black, system stacks).
2. **Skin Layer** (`skins/[name].json`): Thematic definitions (Workbench, Classic).
3. **Project Layer** (`ds.config.json`): Project-specific overrides.
## Safe Boot Protocol
If the JSON parser fails or files are missing, the compiler falls back to an in-memory `EMERGENCY_SKIN` to prevent crash loops.
## Integration
MCP Tools should now use the `with_context` wrapper or interact via the 5 new context tools:
1. `get_active_context`
2. `resolve_token`
3. `validate_manifest`
4. `list_skins`
5. `get_compiler_status`