agentic-flow 1.1.14 → 1.2.1

package/dist/utils/cli.js

@@ -16,8 +16,16 @@ export function parseArgs() {
     }
     // Check for MCP command
     if (args[0] === 'mcp') {
+        const mcpSubcommand = args[1];
+        // MCP Manager commands (CLI configuration)
+        const managerCommands = ['add', 'list', 'remove', 'enable', 'disable', 'update', 'test', 'info', 'export', 'import'];
+        if (managerCommands.includes(mcpSubcommand)) {
+            options.mode = 'mcp-manager';
+            return options;
+        }
+        // MCP Server commands (start/stop server)
         options.mode = 'mcp';
-        options.mcpCommand = args[1] || 'start'; // default to start
+        options.mcpCommand = mcpSubcommand || 'start'; // default to start
         options.mcpServer = args[2] || 'all'; // default to all servers
         return options;
     }

package/dist/utils/modelOptimizer.js

@@ -16,6 +16,7 @@ const MODEL_DATABASE = {
         speed_score: 85,
         cost_score: 20,
         tier: 'flagship',
+        supports_tools: true,
         strengths: ['reasoning', 'coding', 'analysis', 'production'],
         weaknesses: ['cost'],
         bestFor: ['coder', 'reviewer', 'architecture', 'planner', 'production-validator']
@@ -30,6 +31,7 @@ const MODEL_DATABASE = {
         speed_score: 90,
         cost_score: 30,
         tier: 'flagship',
+        supports_tools: true,
         strengths: ['multimodal', 'speed', 'general-purpose', 'vision'],
         weaknesses: ['cost'],
         bestFor: ['researcher', 'analyst', 'multimodal-tasks']
@@ -44,6 +46,7 @@ const MODEL_DATABASE = {
         speed_score: 75,
         cost_score: 50,
         tier: 'flagship',
+        supports_tools: true,
         strengths: ['reasoning', 'large-context', 'math', 'analysis'],
         weaknesses: ['speed'],
         bestFor: ['planner', 'architecture', 'researcher', 'code-analyzer']
@@ -59,8 +62,9 @@ const MODEL_DATABASE = {
         speed_score: 80,
         cost_score: 100,
         tier: 'cost-effective',
+        supports_tools: false, // DeepSeek R1 does NOT support tool/function calling
         strengths: ['reasoning', 'coding', 'math', 'value', 'free'],
-        weaknesses: ['newer-model'],
+        weaknesses: ['newer-model', 'no-tool-use'],
         bestFor: ['coder', 'pseudocode', 'specification', 'refinement', 'tester']
     },
     'deepseek-chat-v3': {
@@ -73,6 +77,7 @@ const MODEL_DATABASE = {
         speed_score: 90,
         cost_score: 100,
         tier: 'cost-effective',
+        supports_tools: true,
         strengths: ['cost', 'speed', 'coding', 'development', 'free'],
         weaknesses: ['complex-reasoning'],
         bestFor: ['coder', 'reviewer', 'tester', 'backend-dev', 'cicd-engineer']
@@ -88,6 +93,7 @@ const MODEL_DATABASE = {
         speed_score: 98,
         cost_score: 98,
         tier: 'balanced',
+        supports_tools: true,
         strengths: ['speed', 'cost', 'interactive'],
         weaknesses: ['quality'],
         bestFor: ['researcher', 'planner', 'smart-agent']
@@ -102,6 +108,7 @@ const MODEL_DATABASE = {
         speed_score: 95,
         cost_score: 100,
         tier: 'balanced',
+        supports_tools: true,
         strengths: ['open-source', 'versatile', 'coding', 'free', 'fast'],
         weaknesses: ['smaller-model'],
         bestFor: ['coder', 'reviewer', 'base-template-generator', 'tester']
@@ -116,6 +123,7 @@ const MODEL_DATABASE = {
         speed_score: 85,
         cost_score: 90,
         tier: 'balanced',
+        supports_tools: true,
         strengths: ['multilingual', 'coding', 'reasoning'],
         weaknesses: ['english-optimized'],
         bestFor: ['researcher', 'coder', 'multilingual-tasks']
@@ -131,6 +139,7 @@ const MODEL_DATABASE = {
         speed_score: 95,
         cost_score: 99,
         tier: 'budget',
+        supports_tools: true,
         strengths: ['ultra-low-cost', 'speed'],
         weaknesses: ['quality', 'complex-tasks'],
         bestFor: ['simple-tasks', 'testing']
@@ -146,6 +155,7 @@ const MODEL_DATABASE = {
         speed_score: 30,
         cost_score: 100,
         tier: 'local',
+        supports_tools: false,
         strengths: ['privacy', 'offline', 'zero-cost'],
         weaknesses: ['quality', 'speed'],
         bestFor: ['privacy-tasks', 'offline-tasks']
@@ -197,8 +207,14 @@ export class ModelOptimizer {
         const taskComplexity = criteria.taskComplexity || this.inferComplexity(criteria.task);
         // Set default priority to balanced if not specified
         const priority = criteria.priority || 'balanced';
+        // Filter models that support tools if required
+        let availableModels = Object.entries(MODEL_DATABASE);
+        if (criteria.requiresTools) {
+            availableModels = availableModels.filter(([key, model]) => model.supports_tools !== false);
+            logger.info(`Filtered to ${availableModels.length} models with tool support`);
+        }
         // Score all models
-        const scoredModels = Object.entries(MODEL_DATABASE).map(([key, model]) => {
+        const scoredModels = availableModels.map(([key, model]) => {
             // Calculate overall score based on priority
             let overall_score;
             switch (priority) {

package/docs/.claude-flow/metrics/performance.json

@@ -1,5 +1,5 @@
 {
-  "startTime": 1759680310468,
+  "startTime": 1759762593440,
   "totalTasks": 1,
   "successfulTasks": 1,
   "failedTasks": 0,

package/docs/.claude-flow/metrics/task-metrics.json

@@ -1,10 +1,10 @@
 [
   {
-    "id": "cmd-hooks-1759680310618",
+    "id": "cmd-hooks-1759762593563",
     "type": "hooks",
     "success": true,
-    "duration": 8.211029999999994,
-    "timestamp": 1759680310627,
+    "duration": 24.05694200000005,
+    "timestamp": 1759762593587,
     "metadata": {}
   }
 ]

package/docs/INDEX.md

@@ -54,10 +54,35 @@ Multi-model router configuration and usage.
 - [Router Config Reference](router/ROUTER_CONFIG_REFERENCE.md) - Configuration options
 - [Top 20 Models Matrix](router/TOP20_MODELS_MATRIX.md) - Model comparison guide
 
-### ✅ [Validation & Testing](validation/)
-Test results and quality assurance reports.
+### ✅ [Testing & Validation](testing/)
+Current test results, validation reports, and quality assurance.
 
-- [Validation README](validation/README.md) - Overview and archived reports
+- [Testing Overview](testing/README.md) - Current testing documentation
+- [Agent System Validation](testing/AGENT-SYSTEM-VALIDATION.md) - Multi-agent testing
+- [Final Testing Summary](testing/FINAL-TESTING-SUMMARY.md) - Comprehensive coverage
+- [Regression Test Results](testing/REGRESSION-TEST-RESULTS.md) - Regression testing
+- [Streaming & MCP Validation](testing/STREAMING-AND-MCP-VALIDATION.md) - Integration tests
+
+### 🔍 [MCP Validation](mcp-validation/)
+Model Context Protocol implementation and validation.
+
+- [MCP Validation Overview](mcp-validation/README.md) - MCP testing documentation
+- [Implementation Summary](mcp-validation/IMPLEMENTATION-SUMMARY.md) - MCP implementation
+- [CLI Validation Report](mcp-validation/MCP-CLI-VALIDATION-REPORT.md) - CLI tool testing
+- [Strange Loops Test](mcp-validation/strange-loops-test.md) - Advanced patterns
+
+### 📦 [Releases](releases/)
+Version-specific release notes and publishing documentation.
+
+- [Release Overview](releases/README.md) - Release documentation index
+- [v1.2.0 Release](releases/RELEASE-v1.2.0.md) - Latest stable release
+- [v1.2.0 Publishing Guide](releases/NPM-PUBLISH-GUIDE-v1.2.0.md) - Publishing process
+- [v1.2.1 Hotfix](releases/HOTFIX-v1.2.1.md) - Critical fixes
+
+### 🗄️ [Validation Archive](validation/)
+Historical validation reports and test archives.
+
+- [Validation Archive](validation/README.md) - Archived test reports
 
 ### 📦 [Archived](archived/)
 Historical documentation, completed implementations, and validation reports.
@@ -103,13 +128,15 @@ Historical documentation, completed implementations, and validation reports.
 ### Path 2: Developers (1.5 hours)
 1. [Architecture Overview](architecture/EXECUTIVE_SUMMARY.md) - System design (20 min)
 2. [Implementation Examples](guides/IMPLEMENTATION_EXAMPLES.md) - Code patterns (40 min)
-3. [Integration Guides](integrations/) - External services (30 min)
+3. [Integration Guides](integrations/) - External services (20 min)
+4. [Testing Documentation](testing/) - Quality assurance (10 min)
 
 ### Path 3: System Architects (2 hours)
 1. [Research Summary](architecture/RESEARCH_SUMMARY.md) - Technical findings (30 min)
 2. [Multi-Model Router Plan](architecture/MULTI_MODEL_ROUTER_PLAN.md) - Router architecture (45 min)
-3. [Integration Status](architecture/INTEGRATION-STATUS.md) - Current state (30 min)
+3. [Integration Status](architecture/INTEGRATION-STATUS.md) - Current state (20 min)
 4. [Router Documentation](router/) - Configuration and usage (15 min)
+5. [MCP Validation](mcp-validation/) - Protocol implementation (10 min)
 
 ---
 
@@ -192,5 +219,15 @@ Historical reports, completed implementations, and superseded guides are in the
 
 ---
 
-**Documentation Status**: ✅ Organized and up-to-date
-**Last Updated**: October 5, 2025
+**Documentation Status**: ✅ Reorganized and up-to-date
+**Last Updated**: October 6, 2025
+
+## 📋 Recent Documentation Updates
+
+**v2.0 Reorganization (Oct 6, 2025)**:
+- Created dedicated `releases/` directory for version-specific documentation
+- Consolidated testing reports into `testing/` directory
+- Separated MCP validation into dedicated `mcp-validation/` section
+- Added comprehensive READMEs to all major sections
+- Archived historical v1.1.x releases for cleaner navigation
+- Improved documentation index with better categorization

package/docs/archived/RELEASE-SUMMARY-v1.1.14-beta.1.md

@@ -0,0 +1,336 @@
+# v1.1.14-beta.1 Release Summary
+
+**Date:** 2025-10-05
+**Status:** ✅ **PUBLISHED & LIVE**
+**NPM:** https://www.npmjs.com/package/agentic-flow/v/1.1.14-beta.1
+**GitHub:** https://github.com/ruvnet/agentic-flow/releases/tag/v1.1.14-beta.1
+
+---
+
+## 🎉 Major Achievement
+
+**Fixed critical OpenRouter proxy bug that was causing 100% failure rate!**
+
+From **0% success** → **80% success** (8 out of 10 models working)
+
+---
+
+## Installation & Usage
+
+### Install Beta Version
+```bash
+# Install globally
+npm install -g agentic-flow@beta
+
+# Or use with npx (no installation needed)
+npx agentic-flow@beta --help
+```
+
+### Quick Start
+```bash
+# List available agents
+npx agentic-flow@beta --list
+
+# Run with Anthropic (default)
+npx agentic-flow@beta --agent coder --task "Write Python hello world"
+
+# Run with OpenRouter (99% cost savings!)
+npx agentic-flow@beta --agent coder --task "Write Python hello world" \
+  --provider openrouter --model "openai/gpt-4o-mini"
+
+# Run with Grok 4 Fast (FREE!)
+npx agentic-flow@beta --agent coder --task "Write Python hello world" \
+  --provider openrouter --model "x-ai/grok-4-fast"
+```
+
+---
+
+## ✅ Verified Working
+
+### NPX Command
+```bash
+$ npx agentic-flow@beta --version
+agentic-flow v1.1.14-beta.1
+
+$ npx agentic-flow@beta --help
+🤖 Agentic Flow v1.1.14-beta.1 - AI Agent Orchestration with OpenRouter Support
+[Full help output shown]
+
+$ npx agentic-flow@beta --agent coder --task "hello world" --provider anthropic
+✅ Completed! [Working perfectly]
+```
+
+### OpenRouter Models (8/10 = 80%)
+
+| Model | Status | Time | Cost/M Tokens | Use Case |
+|-------|--------|------|---------------|----------|
+| **openai/gpt-4o-mini** | ✅ | 7s | $0.15 | Best value |
+| **openai/gpt-3.5-turbo** | ✅ | 5s | $0.50 | Fastest |
+| **meta-llama/llama-3.1-8b-instruct** | ✅ | 14s | $0.06 | Open source |
+| **anthropic/claude-3.5-sonnet** | ✅ | 11s | $3.00 | Highest quality |
+| **mistralai/mistral-7b-instruct** | ✅ | 6s | $0.25 | Fast & efficient |
+| **google/gemini-2.0-flash-exp** | ✅ | 6s | Free | Free tier |
+| **x-ai/grok-4-fast** | ✅ | 8s | Free | #1 most popular! |
+| **z-ai/glm-4.6** | ✅ | 5s | Varies | Fixed in this release |
+
+### Known Issues (2/10)
+| Model | Issue | Workaround |
+|-------|-------|------------|
+| **meta-llama/llama-3.3-70b-instruct** | Intermittent timeout | Use llama-3.1-8b instead |
+| **x-ai/grok-4** | Too slow (60s+) | Use grok-4-fast instead |
+
+---
+
+## 💰 Cost Savings
+
+### Comparison vs Claude Direct API
+
+| Model | Cost | vs Claude ($3/M) | Savings |
+|-------|------|------------------|---------|
+| GPT-4o-mini | $0.15/M | $2.85 | **95%** |
+| Llama 3.1 8B | $0.06/M | $2.94 | **98%** |
+| Mistral 7B | $0.25/M | $2.75 | **92%** |
+| GPT-3.5-turbo | $0.50/M | $2.50 | **83%** |
+| Grok 4 Fast | Free | $3.00 | **100%** |
+| Gemini 2.0 Flash | Free | $3.00 | **100%** |
+
+**Average savings: ~94% across all working models**
+
+---
+
+## 🔧 What Was Fixed
+
+### Critical Bug
+**TypeError: anthropicReq.system?.substring is not a function**
+
+**Root Cause:**
+- Anthropic API allows `system` field to be string OR array of content blocks
+- Claude Agent SDK sends it as array (for prompt caching)
+- Proxy assumed string only → called `.substring()` on array → crash
+- Result: 100% failure rate
+
+**Solution:**
+```typescript
+// Before (BROKEN)
+interface AnthropicRequest {
+  system?: string;
+}
+
+// After (FIXED)
+interface AnthropicRequest {
+  system?: string | Array<{ type: string; text?: string; [key: string]: any }>;
+}
+
+// Safe extraction logic
+if (typeof anthropicReq.system === 'string') {
+  originalSystem = anthropicReq.system;
+} else if (Array.isArray(anthropicReq.system)) {
+  originalSystem = anthropicReq.system
+    .filter(block => block.type === 'text' && block.text)
+    .map(block => block.text)
+    .join('\n');
+}
+```
+
+---
+
+## 📊 Testing Results
+
+### Regression Tests
+- ✅ Anthropic Direct: No regressions
+- ✅ Google Gemini: No regressions
+- ✅ OpenRouter: Fixed from 0% → 80%
+
+### MCP Tools
+- ✅ All 15 tools working through OpenRouter proxy
+- ✅ File operations validated (Write, Read, Bash)
+- ✅ Tool format conversion working (Anthropic ↔ OpenAI)
+
+### Performance
+- GPT-3.5-turbo: 5s (fastest)
+- Mistral 7B: 6s
+- Gemini 2.0 Flash: 6s
+- GPT-4o-mini: 7s
+- Grok 4 Fast: 8s
+- Claude 3.5 Sonnet: 11s
+- Llama 3.1 8B: 14s
+
+---
+
+## 📖 Documentation
+
+### Technical Details
+- [OPENROUTER-FIX-VALIDATION.md](docs/archived/OPENROUTER-FIX-VALIDATION.md) - Technical validation
+- [OPENROUTER-SUCCESS-REPORT.md](docs/archived/OPENROUTER-SUCCESS-REPORT.md) - Comprehensive report
+- [FINAL-TESTING-SUMMARY.md](FINAL-TESTING-SUMMARY.md) - Complete testing summary
+- [REGRESSION-TEST-RESULTS.md](REGRESSION-TEST-RESULTS.md) - Regression validation
+- [V1.1.14-BETA-READY.md](V1.1.14-BETA-READY.md) - Beta readiness assessment
+
+### Quick Reference
+- **66+ specialized agents** available
+- **111 MCP tools** for coordination
+- **4 providers:** Anthropic, OpenRouter, Gemini, ONNX
+- **400+ models** via OpenRouter
+- **Zero breaking changes** - fully backward compatible
+
+---
+
+## 🚀 Example Usage
+
+### Basic Code Generation
+```bash
+# With Anthropic (highest quality)
+npx agentic-flow@beta --agent coder --task "Create REST API with Express"
+
+# With OpenRouter GPT-4o-mini (best value)
+npx agentic-flow@beta --agent coder --task "Create REST API with Express" \
+  --provider openrouter --model "openai/gpt-4o-mini"
+
+# With Grok 4 Fast (free!)
+npx agentic-flow@beta --agent coder --task "Create REST API with Express" \
+  --provider openrouter --model "x-ai/grok-4-fast"
+```
+
+### Multi-Agent Workflows
+```bash
+# Research task with cheaper model
+npx agentic-flow@beta --agent researcher \
+  --task "Research best practices for microservices" \
+  --provider openrouter --model "openai/gpt-3.5-turbo"
+
+# Code review with high-quality model
+npx agentic-flow@beta --agent reviewer \
+  --task "Review my authentication code" \
+  --provider openrouter --model "anthropic/claude-3.5-sonnet"
+
+# Testing with fast model
+npx agentic-flow@beta --agent tester \
+  --task "Create Jest tests for my API" \
+  --provider openrouter --model "mistralai/mistral-7b-instruct"
+```
+
+### Configuration
+```bash
+# Interactive wizard
+npx agentic-flow@beta config
+
+# Set OpenRouter API key
+npx agentic-flow@beta config set OPENROUTER_API_KEY "sk-or-..."
+
+# List configuration
+npx agentic-flow@beta config list
+```
+
+---
+
+## 🐛 Reporting Issues
+
+This is a **beta release** - please test and report any issues:
+
+**GitHub Issues:** https://github.com/ruvnet/agentic-flow/issues
+
+When reporting, please include:
+- Model being used
+- Task description
+- Error message (if any)
+- Output received
+- Expected behavior
+
+---
+
+## 🔄 Upgrade Path
+
+### From v1.1.13 → v1.1.14-beta.1
+
+**Changes:**
+- OpenRouter proxy now functional (was 100% broken)
+- No breaking changes to API
+- All existing code continues to work
+- New: 8 OpenRouter models now available
+
+**Migration:**
+```bash
+# Update to beta
+npm install agentic-flow@beta
+
+# Or use npx (always gets latest)
+npx agentic-flow@beta [commands]
+```
+
+**Rollback if needed:**
+```bash
+npm install agentic-flow@1.1.13
+```
+
+---
+
+## 🎯 Next Steps
+
+### Before Stable Release (v1.1.14)
+1. ⏳ User beta testing feedback
+2. ⏳ Test DeepSeek models with proper API keys
+3. ⏳ Debug Llama 3.3 70B timeout issue
+4. ⏳ Test streaming responses
+5. ⏳ Performance benchmarking
+6. ⏳ Additional model validation
+
+### Future Enhancements (v1.2.0)
+1. Auto-detect best model for task
+2. Automatic failover between models
+3. Model capability detection
+4. Streaming response support
+5. Cost optimization features
+6. Performance metrics dashboard
+
+---
+
+## 📈 Success Metrics
+
+### Before v1.1.14-beta.1
+- OpenRouter success rate: **0%** (100% failure)
+- Working models: 0
+- Cost savings: Not available
+- User complaints: High
+
+### After v1.1.14-beta.1
+- OpenRouter success rate: **80%** (8/10 working)
+- Working models: 8
+- Cost savings: Up to **99%**
+- MCP tools: All 15 working
+- Most popular model: ✅ Working (Grok 4 Fast)
+
+---
+
+## ✅ Release Checklist
+
+- [x] Core bug fixed (anthropicReq.system)
+- [x] 10 models tested (8 working)
+- [x] Popular models validated (Grok 4 Fast)
+- [x] MCP tools working (all 15)
+- [x] File operations confirmed
+- [x] No regressions in baseline providers
+- [x] Documentation complete
+- [x] Changelog updated
+- [x] Package version updated
+- [x] TypeScript build successful
+- [x] Git tag created
+- [x] NPM published with beta tag
+- [x] GitHub release created
+- [x] npx command verified
+- [x] User communication prepared
+
+---
+
+## 🙏 Credits
+
+**Debugging time:** ~4 hours
+**Lines changed:** ~50
+**Models tested:** 10
+**Success rate:** 80%
+**Impact:** Unlocked 400+ models via OpenRouter
+
+**Built with:** [Claude Code](https://claude.com/claude-code)
+
+---
+
+**Ready for production after beta testing!** 🚀