feat: add monorepo structure with versioning and CI/CD

Monorepo Features: - Root package.json with convenient npm scripts for all agents - Easy testing from root: npm test, npm run test:openagent, npm run test:opencoder - Multi-model support: test with Grok, Claude, or GPT-4 - Quick dashboard access: npm run dashboard - No folder navigation required Versioning System: - VERSION file tracking current version (0.1.0-alpha.1) - CHANGELOG.md with comprehensive version history - Version bump scripts for alpha, beta, rc, and stable releases - Semantic versioning with progression: Alpha → Beta → RC → Stable CI/CD: - GitHub Actions workflow for automated testing - Pre-merge validation for agent changes - Smoke tests for both openagent and opencoder - Automated test result reporting - Runs on PRs to main/dev and pushes to main Helper Scripts: - scripts/test.sh: Advanced test runner with multi-agent support - scripts/dashboard.sh: Enhanced dashboard launcher with auto-open - scripts/bump-version.sh: Version management tool Documentation: - QUICK_START.md: Comprehensive testing and usage guide - Clear examples for all test scenarios - Multi-agent and multi-model workflows Benefits: - Easy testing from root directory - Automated quality checks before merges - Clear version tracking and history - Developer-friendly workflows - No breaking changes to existing structure
2025-11-26 21:49:50 +00:00 · 2025-11-26 21:49:50 +00:00 · aebd68e046
commit aebd68e046
parent fe4717bbeb
8 changed files with 798 additions and 0 deletions
--- a/.github/workflows/test-agents.yml
+++ b/.github/workflows/test-agents.yml
@ -0,0 +1,128 @@
+name: Test Agents
+
+on:
+  pull_request:
+    branches: [ main, dev ]
+    paths:
+      - '.opencode/agent/**'
+      - 'evals/**'
+      - '.github/workflows/test-agents.yml'
+  push:
+    branches: [ main ]
+  workflow_dispatch:
+
+jobs:
+  test-openagent:
+    name: Test OpenAgent
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+          cache-dependency-path: 'evals/framework/package-lock.json'
+      
+      - name: Install dependencies
+        run: |
+          cd evals/framework
+          npm ci
+      
+      - name: Build framework
+        run: |
+          cd evals/framework
+          npm run build
+      
+      - name: Run OpenAgent smoke test
+        run: npm run test:ci:openagent
+        env:
+          CI: true
+      
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: openagent-results
+          path: evals/results/
+          retention-days: 30
+
+  test-opencoder:
+    name: Test OpenCoder
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+          cache-dependency-path: 'evals/framework/package-lock.json'
+      
+      - name: Install dependencies
+        run: |
+          cd evals/framework
+          npm ci
+      
+      - name: Build framework
+        run: |
+          cd evals/framework
+          npm run build
+      
+      - name: Run OpenCoder smoke test
+        run: npm run test:ci:opencoder
+        env:
+          CI: true
+      
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: opencoder-results
+          path: evals/results/
+          retention-days: 30
+
+  report-results:
+    name: Report Test Results
+    runs-on: ubuntu-latest
+    needs: [test-openagent, test-opencoder]
+    if: always()
+    
+    steps:
+      - name: Download OpenAgent results
+        uses: actions/download-artifact@v4
+        with:
+          name: openagent-results
+          path: results/openagent
+        continue-on-error: true
+      
+      - name: Download OpenCoder results
+        uses: actions/download-artifact@v4
+        with:
+          name: opencoder-results
+          path: results/opencoder
+        continue-on-error: true
+      
+      - name: Display results summary
+        run: |
+          echo "## Test Results Summary" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          
+          if [ -f results/openagent/latest.json ]; then
+            echo "### OpenAgent" >> $GITHUB_STEP_SUMMARY
+            cat results/openagent/latest.json | jq -r '"- Passed: \(.passed)\n- Failed: \(.failed)\n- Total: \(.total)"' >> $GITHUB_STEP_SUMMARY
+          fi
+          
+          if [ -f results/opencoder/latest.json ]; then
+            echo "" >> $GITHUB_STEP_SUMMARY
+            echo "### OpenCoder" >> $GITHUB_STEP_SUMMARY
+            cat results/opencoder/latest.json | jq -r '"- Passed: \(.passed)\n- Failed: \(.failed)\n- Total: \(.total)"' >> $GITHUB_STEP_SUMMARY
+          fi
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -0,0 +1,111 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.0-alpha.1] - 2025-11-26
+
+### Added
+
+#### SDK-Based Evaluation Framework
+- Complete test execution framework using OpenCode SDK
+- Support for openagent and opencoder testing
+- Real agent testing with session management
+- Smart timeout system with activity monitoring
+- Multi-turn conversation support
+
+#### Modular Architecture
+- Refactored test-runner.ts (884 lines → 4 focused modules):
+  - `test-runner.ts` (411 lines): Thin orchestrator
+  - `test-executor.ts` (392 lines): Core execution logic
+  - `result-validator.ts` (253 lines): Validation logic
+  - `event-logger.ts` (128 lines): Logging utilities
+- Improved Single Responsibility Principle compliance
+- Enhanced testability through dependency injection
+
+#### Test Infrastructure
+- 20+ test cases across multiple categories:
+  - OpenAgent: Developer (12), Context Loading (5), Business (2), Edge Cases (3)
+  - OpenCoder: Developer (4)
+- BehaviorEvaluator for validating expected agent actions
+- Comprehensive evaluators: approval-gate, context-loading, delegation, tool-usage
+
+#### Interactive Results Dashboard
+- Real-time test results visualization
+- Filtering by agent, category, status
+- Detailed violation tracking
+- CSV export functionality
+- Historical results tracking
+- One-command deployment (`./serve.sh`)
+
+#### Documentation
+- ARCHITECTURE.md: Comprehensive system review (456 lines)
+- GETTING_STARTED.md: Quick start guide (435 lines)
+- SDK_EVAL_README.md: Complete SDK guide (298 lines)
+- Test design guide and architecture overview
+- Documentation cleanup (removed 3 outdated files)
+
+#### Script Organization
+- Organized 12 scripts into logical directories:
+  - `scripts/debug/`: Session debugging tools (4 files)
+  - `scripts/test/`: Test execution scripts (6 files)
+  - `scripts/utils/`: Utility scripts (2 files)
+- Comprehensive scripts/README.md with usage examples
+
+#### Monorepo Structure
+- Root package.json with convenient npm scripts
+- Easy agent selection (openagent, opencoder)
+- Easy model selection (grok, claude, gpt-4)
+- Quick dashboard access from root
+- No folder navigation required
+
+#### CI/CD
+- GitHub Actions workflow for automated testing
+- Pre-merge validation for agent changes
+- Fast smoke tests for both agents
+- Automated test result reporting
+
+#### Agent Improvements
+- Enhanced openagent with better context loading
+- New opencoder agent with test suite
+- Improved subagent invocation patterns
+- Ultra-compact context index system
+
+### Changed
+- Reorganized evaluation framework structure
+- Improved test case schema with behavior expectations
+- Enhanced context loading detection
+
+### Removed
+- Outdated documentation files (TESTING_CONFIDENCE.md, TEST_REVIEW.md, SESSION_STORAGE_FIX.md)
+- Redundant test files
+
+### Fixed
+- Context loading evaluator detection accuracy
+- Multi-turn prompt handling
+- Test artifact cleanup
+
+---
+
+## Version Format
+
+```
+v0.1.0-alpha.1
+│ │ │  │      │
+│ │ │  │      └─ Build/Iteration number
+│ │ │  └──────── Release stage (alpha, beta, rc)
+│ │ └─────────── Patch version
+│ └───────────── Minor version
+└─────────────── Major version (0 = pre-release)
+```
+
+### Version Progression
+
+- **Alpha** (`v0.x.0-alpha.N`): Early development, unstable
+- **Beta** (`v0.x.0-beta.N`): Feature complete, testing
+- **RC** (`v0.x.0-rc.N`): Release candidate, stable
+- **Stable** (`v1.x.x`): Production ready
+
+[0.1.0-alpha.1]: https://github.com/darrenhinde/OpenAgents/releases/tag/v0.1.0-alpha.1
--- a/QUICK_START.md
+++ b/QUICK_START.md
@ -0,0 +1,303 @@
+# 🚀 OpenCode Agents - Quick Start
+
+![Version](https://img.shields.io/badge/version-0.1.0--alpha.1-blue)
+
+## 📋 Available Agents
+
+- **openagent** - Full-featured development agent (22+ tests)
+  - Developer tests: Code, docs, tests, delegation
+  - Context loading tests: Standards, patterns, workflows
+  - Business tests: Conversations, data analysis
+  - Edge cases: Approval gates, negative tests
+
+- **opencoder** - Specialized coding agent (4+ tests)
+  - Developer tests: Bash execution, file operations
+  - Multi-tool workflows
+
+---
+
+## 🧪 Running Tests
+
+### Test All Agents
+```bash
+npm test                              # All agents, all tests (default)
+npm run test:all                      # Explicit all agents
+```
+
+### Test Specific Agent
+```bash
+npm run test:openagent                # OpenAgent only
+npm run test:opencoder                # OpenCoder only
+```
+
+### Test with Different Models
+
+#### OpenAgent
+```bash
+npm run test:openagent:grok           # Grok (free tier, fast)
+npm run test:openagent:claude         # Claude Sonnet 4.5 (best quality)
+npm run test:openagent:gpt4           # GPT-4 Turbo (OpenAI)
+```
+
+#### OpenCoder
+```bash
+npm run test:opencoder:grok           # Grok (free tier, fast)
+npm run test:opencoder:claude         # Claude Sonnet 4.5 (best quality)
+npm run test:opencoder:gpt4           # GPT-4 Turbo (OpenAI)
+```
+
+#### All Agents
+```bash
+npm run test:all:grok                 # All agents with Grok
+npm run test:all:claude               # All agents with Claude
+npm run test:all:gpt4                 # All agents with GPT-4
+```
+
+---
+
+## 🎯 Test Specific Categories
+
+### OpenAgent Categories
+```bash
+npm run test:openagent:developer      # Developer tests (code, docs, tests)
+npm run test:openagent:context        # Context loading tests
+npm run test:openagent:business       # Business/conversation tests
+```
+
+### OpenCoder Categories
+```bash
+npm run test:opencoder:developer      # Developer tests
+npm run test:opencoder:bash           # Bash execution tests
+```
+
+### Custom Patterns
+```bash
+npm run test:pattern -- "developer/*.yaml"              # All developer tests
+npm run test:pattern -- "context-loading/*.yaml"        # Context tests
+npm run test:pattern -- "edge-case/*.yaml"              # Edge cases
+npm run test:openagent -- --pattern="developer/ctx-*"   # OpenAgent context tests
+```
+
+---
+
+## 📊 View Results
+
+### Dashboard (Recommended)
+```bash
+npm run dashboard                     # Launch interactive dashboard
+npm run dashboard:open                # Launch and auto-open browser
+```
+
+The dashboard provides:
+- ✅ Real-time test results visualization
+- ✅ Filter by agent, category, status
+- ✅ Detailed violation tracking
+- ✅ CSV export functionality
+- ✅ Historical results tracking
+
+### Command Line
+```bash
+npm run results:openagent             # Recent OpenAgent results
+npm run results:opencoder             # Recent OpenCoder results
+npm run results:latest                # Latest test summary (JSON)
+```
+
+---
+
+## 🐛 Debug Mode
+
+```bash
+npm run test:debug                    # Run with debug output
+npm run test:openagent -- --debug     # Debug OpenAgent tests
+npm run test:opencoder -- --debug     # Debug OpenCoder tests
+```
+
+Debug mode shows:
+- Detailed event logging
+- Tool call details
+- Session information
+- Evaluation progress
+
+---
+
+## 🔧 Development
+
+```bash
+npm run dev:setup                     # Install dependencies
+npm run dev:build                     # Build framework
+npm run dev:test                      # Run unit tests
+npm run dev:clean                     # Clean and reinstall
+```
+
+---
+
+## 📈 Version Management
+
+```bash
+npm run version                       # Show current version
+npm run version:bump alpha            # Bump alpha version
+npm run version:bump beta             # Bump to beta
+npm run version:bump rc               # Bump to release candidate
+```
+
+---
+
+## 📁 Test Structure
+
+```
+evals/agents/
+├── openagent/tests/
+│   ├── developer/          # Code, docs, tests (12 tests)
+│   │   ├── ctx-code-001.yaml
+│   │   ├── ctx-docs-001.yaml
+│   │   ├── ctx-tests-001.yaml
+│   │   ├── ctx-delegation-001.yaml
+│   │   └── ...
+│   ├── context-loading/    # Context loading (5 tests)
+│   │   ├── ctx-simple-coding-standards.yaml
+│   │   ├── ctx-simple-documentation-format.yaml
+│   │   └── ...
+│   ├── business/           # Conversations (2 tests)
+│   │   ├── conv-simple-001.yaml
+│   │   └── data-analysis.yaml
+│   └── edge-case/          # Edge cases (3 tests)
+│       ├── just-do-it.yaml
+│       ├── missing-approval-negative.yaml
+│       └── no-approval-negative.yaml
+│
+└── opencoder/tests/
+    └── developer/          # Bash, file ops (4 tests)
+        ├── bash-execution-001.yaml
+        ├── file-read-001.yaml
+        ├── multi-tool-001.yaml
+        └── simple-bash-test.yaml
+```
+
+---
+
+## 💡 Common Workflows
+
+### Quick Test (Free Tier)
+```bash
+npm run test:openagent:grok           # Fast, free
+npm run test:opencoder:grok           # Fast, free
+```
+
+### Quality Test (Best Model)
+```bash
+npm run test:openagent:claude         # Best quality
+npm run test:opencoder:claude         # Best quality
+```
+
+### Full Test Suite
+```bash
+npm run test:all:claude               # All agents, best model
+```
+
+### Continuous Development
+```bash
+# 1. Run tests in debug mode
+npm run test:openagent:developer -- --debug
+
+# 2. View results in dashboard
+npm run dashboard:open
+
+# 3. Iterate on agent prompts
+# Edit .opencode/agent/openagent.md
+
+# 4. Re-run tests
+npm run test:openagent:developer
+```
+
+### CI/CD Smoke Tests
+```bash
+npm run test:ci                       # Fast smoke tests for both agents
+npm run test:ci:openagent             # OpenAgent smoke test
+npm run test:ci:opencoder             # OpenCoder smoke test
+```
+
+---
+
+## 🎯 Test Results
+
+After running tests, results are saved to:
+- `evals/results/latest.json` - Latest test run
+- `evals/results/history/YYYY-MM/DD-HHMMSS-{agent}.json` - Historical results
+
+View in dashboard: `npm run dashboard:open`
+
+---
+
+## 🔍 Understanding Test Results
+
+### Test Status
+- ✅ **PASSED** - All checks passed, no violations
+- ❌ **FAILED** - Test failed (execution error or violations)
+
+### Evaluators
+Tests are evaluated by multiple evaluators:
+- **approval-gate** - Checks if agent requested approval when required
+- **context-loading** - Validates context files were loaded before execution
+- **delegation** - Checks if agent delegated to subagents appropriately
+- **tool-usage** - Validates correct tool usage
+- **behavior** - Checks if agent performed expected actions
+
+### Violations
+- **Error** - Critical issues that cause test failure
+- **Warning** - Non-critical issues
+- **Info** - Informational messages
+
+---
+
+## 📚 Additional Resources
+
+- [README.md](README.md) - Project overview
+- [evals/GETTING_STARTED.md](evals/GETTING_STARTED.md) - Detailed evaluation guide
+- [evals/ARCHITECTURE.md](evals/ARCHITECTURE.md) - System architecture
+- [evals/framework/SDK_EVAL_README.md](evals/framework/SDK_EVAL_README.md) - SDK documentation
+- [CHANGELOG.md](CHANGELOG.md) - Version history
+
+---
+
+## 🆘 Troubleshooting
+
+### Tests not running?
+```bash
+# Ensure dependencies are installed
+npm run dev:setup
+
+# Build the framework
+npm run dev:build
+```
+
+### Dashboard not loading?
+```bash
+# Check if results exist
+ls -la evals/results/
+
+# Try launching manually
+cd evals/results && ./serve.sh
+```
+
+### Version mismatch?
+```bash
+# Check current version
+npm run version
+
+# Sync VERSION file with package.json
+npm run version > VERSION
+```
+
+---
+
+## 🎉 Getting Help
+
+- Check [evals/GETTING_STARTED.md](evals/GETTING_STARTED.md) for detailed guides
+- Review test examples in `evals/agents/*/tests/`
+- Run tests in debug mode: `npm run test:debug`
+- View results dashboard: `npm run dashboard:open`
+
+---
+
+**Current Version:** 0.1.0-alpha.1  
+**Last Updated:** 2025-11-26
--- a/1
+++ b/1
@ -0,0 +1 @@
+0.1.0-alpha.1
--- a/package.json
+++ b/package.json
@ -0,0 +1,64 @@
+{
+  "name": "opencode-agents",
+  "version": "0.1.0-alpha.1",
+  "description": "OpenCode agent evaluation framework and test suites",
+  "private": true,
+  "workspaces": [
+    "evals/framework"
+  ],
+  "scripts": {
+    "test": "npm run test:all",
+    "test:all": "cd evals/framework && npm run eval:sdk",
+    "test:openagent": "cd evals/framework && npm run eval:sdk -- --agent=openagent",
+    "test:opencoder": "cd evals/framework && npm run eval:sdk -- --agent=opencoder",
+    "test:openagent:grok": "npm run test:openagent -- --model=opencode/grok-code-fast",
+    "test:openagent:claude": "npm run test:openagent -- --model=anthropic/claude-3-5-sonnet-20241022",
+    "test:openagent:gpt4": "npm run test:openagent -- --model=openai/gpt-4-turbo",
+    "test:opencoder:grok": "npm run test:opencoder -- --model=opencode/grok-code-fast",
+    "test:opencoder:claude": "npm run test:opencoder -- --model=anthropic/claude-3-5-sonnet-20241022",
+    "test:opencoder:gpt4": "npm run test:opencoder -- --model=openai/gpt-4-turbo",
+    "test:all:grok": "npm run test:all -- --model=opencode/grok-code-fast",
+    "test:all:claude": "npm run test:all -- --model=anthropic/claude-3-5-sonnet-20241022",
+    "test:all:gpt4": "npm run test:all -- --model=openai/gpt-4-turbo",
+    "test:pattern": "cd evals/framework && npm run eval:sdk -- --pattern",
+    "test:debug": "cd evals/framework && npm run eval:sdk -- --debug",
+    "test:openagent:developer": "npm run test:openagent -- --pattern='developer/*.yaml'",
+    "test:openagent:context": "npm run test:openagent -- --pattern='context-loading/*.yaml'",
+    "test:openagent:business": "npm run test:openagent -- --pattern='business/*.yaml'",
+    "test:opencoder:developer": "npm run test:opencoder -- --pattern='developer/*.yaml'",
+    "test:opencoder:bash": "npm run test:opencoder -- --pattern='developer/bash-*.yaml'",
+    "test:ci": "npm run test:ci:openagent && npm run test:ci:opencoder",
+    "test:ci:openagent": "npm run test:openagent -- --pattern='developer/ctx-code-001.yaml' --no-evaluators",
+    "test:ci:opencoder": "npm run test:opencoder -- --pattern='developer/simple-bash-test.yaml' --no-evaluators",
+    "dashboard": "cd evals/results && ./serve.sh",
+    "dashboard:open": "npm run dashboard && open http://localhost:8000",
+    "results:openagent": "echo 'OpenAgent results:' && ls -lh evals/results/history/*openagent*.json 2>/dev/null | tail -5 || echo 'No results yet'",
+    "results:opencoder": "echo 'OpenCoder results:' && ls -lh evals/results/history/*opencoder*.json 2>/dev/null | tail -5 || echo 'No results yet'",
+    "results:latest": "cat evals/results/latest.json 2>/dev/null | jq '.agent, .passed, .failed' || echo 'No results yet'",
+    "version": "cat VERSION",
+    "version:bump": "./scripts/bump-version.sh",
+    "version:bump:patch": "npm version patch --no-git-tag-version && npm run version > VERSION",
+    "version:bump:minor": "npm version minor --no-git-tag-version && npm run version > VERSION",
+    "version:bump:major": "npm version major --no-git-tag-version && npm run version > VERSION",
+    "version:bump:alpha": "npm version prerelease --preid=alpha --no-git-tag-version && npm run version > VERSION",
+    "version:bump:beta": "npm version prerelease --preid=beta --no-git-tag-version && npm run version > VERSION",
+    "version:bump:rc": "npm version prerelease --preid=rc --no-git-tag-version && npm run version > VERSION",
+    "dev:setup": "cd evals/framework && npm install",
+    "dev:build": "cd evals/framework && npm run build",
+    "dev:test": "cd evals/framework && npm test",
+    "dev:clean": "cd evals/framework && rm -rf dist node_modules && npm install"
+  },
+  "keywords": [
+    "opencode",
+    "agents",
+    "evaluation",
+    "testing",
+    "ai"
+  ],
+  "author": "Darren Hinde",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/darrenhinde/OpenAgents.git"
+  }
+}
--- a/scripts/bump-version.sh
+++ b/scripts/bump-version.sh
@ -0,0 +1,73 @@
+#!/bin/bash
+# Version bump script
+# Usage: ./scripts/bump-version.sh [alpha|beta|rc|patch|minor|major]
+
+set -e
+
+STAGE=${1:-alpha}
+
+# Colors
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[1;33m'
+RED='\033[0;31m'
+NC='\033[0m'
+
+# Get current version
+CURRENT_VERSION=$(cat VERSION 2>/dev/null || echo "0.1.0-alpha.1")
+
+echo -e "${BLUE}📦 Version Bump Tool${NC}"
+echo -e "${BLUE}====================${NC}"
+echo ""
+echo -e "Current version: ${YELLOW}${CURRENT_VERSION}${NC}"
+echo -e "Bump type:       ${YELLOW}${STAGE}${NC}"
+echo ""
+
+# Navigate to root
+cd "$(dirname "$0")/.." || exit 1
+
+# Bump version in package.json
+case "$STAGE" in
+  alpha)
+    npm run version:bump:alpha
+    ;;
+  beta)
+    npm run version:bump:beta
+    ;;
+  rc)
+    npm run version:bump:rc
+    ;;
+  patch)
+    npm run version:bump:patch
+    ;;
+  minor)
+    npm run version:bump:minor
+    ;;
+  major)
+    npm run version:bump:major
+    ;;
+  *)
+    echo -e "${RED}❌ Invalid stage: $STAGE${NC}"
+    echo -e "${YELLOW}Valid options: alpha, beta, rc, patch, minor, major${NC}"
+    exit 1
+    ;;
+esac
+
+# Get new version
+NEW_VERSION=$(cat VERSION)
+
+echo ""
+echo -e "${GREEN}✅ Version bumped!${NC}"
+echo -e "New version: ${GREEN}${NEW_VERSION}${NC}"
+echo ""
+
+# Prompt for changelog update
+echo -e "${YELLOW}📝 Don't forget to update CHANGELOG.md!${NC}"
+echo ""
+echo -e "Next steps:"
+echo -e "  1. Update CHANGELOG.md with changes"
+echo -e "  2. Commit: ${BLUE}git add VERSION package.json CHANGELOG.md${NC}"
+echo -e "  3. Commit: ${BLUE}git commit -m \"chore: bump version to v${NEW_VERSION}\"${NC}"
+echo -e "  4. Tag:    ${BLUE}git tag v${NEW_VERSION}${NC}"
+echo -e "  5. Push:   ${BLUE}git push origin main --tags${NC}"
+echo ""
--- a/scripts/dashboard.sh
+++ b/scripts/dashboard.sh
@ -0,0 +1,58 @@
+#!/bin/bash
+# Enhanced dashboard launcher with auto-open
+# Usage: ./scripts/dashboard.sh [port] [auto-open]
+
+set -e
+
+PORT=${1:-8000}
+AUTO_OPEN=${2:-true}
+
+# Colors
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[1;33m'
+NC='\033[0m'
+
+echo -e "${BLUE}🚀 Starting OpenCode Agents Dashboard...${NC}"
+echo -e "${BLUE}📊 Results directory: evals/results${NC}"
+echo -e "${BLUE}🌐 URL: http://localhost:$PORT${NC}"
+echo ""
+
+# Navigate to results directory
+cd "$(dirname "$0")/../evals/results" || exit 1
+
+# Check if results exist
+if [ ! -f "latest.json" ]; then
+  echo -e "${YELLOW}⚠️  No test results found yet.${NC}"
+  echo -e "${YELLOW}   Run tests first: npm test${NC}"
+  echo ""
+fi
+
+# Start server in background
+./serve.sh "$PORT" &
+SERVER_PID=$!
+
+# Wait for server to start
+sleep 2
+
+# Auto-open browser
+if [ "$AUTO_OPEN" = "true" ]; then
+  echo -e "${GREEN}🌐 Opening browser...${NC}"
+  if command -v open &> /dev/null; then
+    open "http://localhost:$PORT"
+  elif command -v xdg-open &> /dev/null; then
+    xdg-open "http://localhost:$PORT"
+  elif command -v start &> /dev/null; then
+    start "http://localhost:$PORT"
+  else
+    echo -e "${YELLOW}⚠️  Could not auto-open browser. Please visit: http://localhost:$PORT${NC}"
+  fi
+fi
+
+echo ""
+echo -e "${GREEN}✅ Dashboard running (PID: $SERVER_PID)${NC}"
+echo -e "${YELLOW}Press Ctrl+C to stop${NC}"
+echo ""
+
+# Wait for Ctrl+C
+wait $SERVER_PID
--- a/scripts/test.sh
+++ b/scripts/test.sh
@ -0,0 +1,60 @@
+#!/bin/bash
+# Advanced test runner with multi-agent support
+# Usage: ./scripts/test.sh [agent] [model] [options]
+
+set -e
+
+# Colors
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[1;33m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+# Defaults
+AGENT=${1:-all}
+MODEL=${2:-opencode/grok-code-fast}
+shift 2 2>/dev/null || true
+EXTRA_ARGS="$@"
+
+echo -e "${BLUE}🧪 OpenCode Agents Test Runner${NC}"
+echo -e "${BLUE}================================${NC}"
+echo ""
+echo -e "Agent:  ${GREEN}${AGENT}${NC}"
+echo -e "Model:  ${GREEN}${MODEL}${NC}"
+if [ -n "$EXTRA_ARGS" ]; then
+  echo -e "Extra:  ${YELLOW}${EXTRA_ARGS}${NC}"
+fi
+echo ""
+
+# Navigate to framework directory
+cd "$(dirname "$0")/../evals/framework" || exit 1
+
+# Check if dependencies are installed
+if [ ! -d "node_modules" ]; then
+  echo -e "${YELLOW}⚠️  Dependencies not installed. Running npm install...${NC}"
+  npm install
+  echo ""
+fi
+
+# Run tests
+if [ "$AGENT" = "all" ]; then
+  echo -e "${YELLOW}Running tests for ALL agents...${NC}"
+  npm run eval:sdk -- --model="$MODEL" $EXTRA_ARGS
+else
+  echo -e "${YELLOW}Running tests for ${AGENT}...${NC}"
+  npm run eval:sdk -- --agent="$AGENT" --model="$MODEL" $EXTRA_ARGS
+fi
+
+EXIT_CODE=$?
+
+echo ""
+if [ $EXIT_CODE -eq 0 ]; then
+  echo -e "${GREEN}✅ Tests complete!${NC}"
+else
+  echo -e "${RED}❌ Tests failed with exit code ${EXIT_CODE}${NC}"
+fi
+echo -e "${BLUE}View results: npm run dashboard${NC}"
+echo ""
+
+exit $EXIT_CODE