@defai.digital/automatosx 8.2.0 → 8.3.2

package/CHANGELOG.md

@@ -2,6 +2,22 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+## [8.3.0] - 2025-11-17
+
+### Fixed
+- **Critical**: Added backward compatibility for provider names (claude-code, gemini-cli, openai)
+- Fixed config reset test to handle optional version field
+- Fixed router circuit breaker test to match v8.3.0 behavior (3 failures threshold)
+- Removed obsolete providers.test.ts (tested SDK features removed in v8.3.0)
+
+### Changed
+- Skipped streaming workflow tests (feature removed in CLI-only refactoring)
+
+### Improved
+- Achieved 100% test pass rate (112/112 unit tests, 9/9 integration tests)
+- Reduced test failures from 43 to 0
+- Comprehensive test suite improvements and cleanup
+
 ## [7.6.0] - 2025-11-04
 
 ### Added

package/README.md

@@ -2,10 +2,10 @@
 
 **From Idea to Production in Minutes: The AI Workforce Platform with Persistent Memory**
 
-AutomatosX is the only AI CLI that combines declarative workflow specs, policy-driven cost optimization, and a persistent AI workforce. Write a YAML spec, and AutomatosX generates your entire project—plans, infrastructure, tests, and execution—while remembering everything and optimizing every API call.
+AutomatosX is a pure CLI orchestration platform for AI agents. It wraps around `claude`, `gemini`, and `codex` commands to provide multi-agent orchestration, persistent memory, and workflow automation. Simple, focused, and easy to integrate with your existing AI workflow.
 
 [![npm version](https://img.shields.io/npm/v/@defai.digital/automatosx.svg)](https://www.npmjs.com/package/@defai.digital/automatosx)
-[![License](https://img.shields.io/badge/license-Elastic%202.0-orange.svg)](LICENSE)
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
 [![TypeScript](https://img.shields.io/badge/TypeScript-100%25-blue.svg)](https://www.typescriptlang.org/)
 [![Tests](https://img.shields.io/badge/tests-2,423+%20passing-brightgreen.svg)](#)
 [![npm](https://img.shields.io/npm/dt/%40defai.digital%2Fautomatosx.svg?label=total%20downloads&color=blue)](https://www.npmjs.com/package/@defai.digital/automatosx)
@@ -13,11 +13,9 @@ AutomatosX is the only AI CLI that combines declarative workflow specs, policy-d
 [![Windows](https://img.shields.io/badge/Windows-10+-blue.svg)](https://www.microsoft.com/windows)
 [![Ubuntu](https://img.shields.io/badge/Ubuntu-24.04-blue.svg)](https://ubuntu.com)
 
-**Status**: ✅ **Production Ready** | v7.0.0 | 20 Specialized Agents | Spec-Kit 100% Complete | Policy-Driven Routing | Auto-Generation
+**Status**: ✅ **Production Ready** | v8.3.0 | 20 Specialized Agents | Pure CLI Orchestration | Simplified Architecture
 
-> 🎉 **NEW in v7.0.0**: Unified setup command (`ax setup`), natural language-first design (slash commands removed), enhanced force mode with complete cleanup. See [Migration from v6.x](#migration-from-v6x) for upgrade details.
-
-> ⚠️ **Note on Cost Estimation (v6.5.11+)**: Cost estimation is **disabled by default** due to frequent pricing changes. The cost optimization features described below are still functional (routing, free-tier prioritization, policy constraints), but specific dollar amounts are not shown unless you enable cost estimation in `automatosx.config.json`. See [Cost Estimation Configuration](#cost-estimation-configuration) for details.
+> 🎉 **NEW in v8.3.0**: Major simplification! Removed ~36,000 lines of code including policy routing, free-tier management, and SDK providers. AutomatosX is now a pure CLI orchestration wrapper around `claude`, `gemini`, and `codex` commands. Simpler, faster, easier to maintain. See [Migration Guide](MIGRATION.md) for upgrade details.
 
 ---
 
@@ -34,10 +32,10 @@ AutomatosX is **the only AI platform** that gives you:
 | Feature | What It Does | Value |
 |---------|--------------|-------|
 | 📋 **Spec-Kit Integration** | Define workflows in YAML. Generate plans, DAGs, scaffolding, and tests automatically. | Ship projects 10x faster |
-| 💰 **Policy-Driven Routing** | Set cost/latency/privacy constraints. AutomatosX picks the optimal AI provider for every request. | Save 60-80% on AI costs |
 | 🧠 **Persistent Memory** | Every conversation is remembered. Agents get perfect context automatically. | Never repeat yourself again |
 | 🤝 **Multi-Agent Orchestration** | 20 specialized agents delegate tasks to each other. You manage the project, not the details. | Focus on strategy, not micromanagement |
-| 🔍 **Complete Observability** | Trace every routing decision, cost, and latency. Debug with confidence. | Production-grade reliability |
+| 🔧 **Pure CLI Wrapper** | Works with your existing `claude`, `gemini`, `codex` CLIs. No API keys needed. | Simple integration |
+| 🔍 **Complete Observability** | Trace every execution and decision. Debug with confidence. | Production-grade reliability |
 
 ---
 
@@ -84,83 +82,6 @@ ax run workflow.ax.yaml
 
 ---
 
-## 💬 **Interactive CLI** (New in v7.1.0!)
-
-Experience a ChatGPT-style conversational interface directly in your terminal:
-
-```bash
-# Start interactive mode
-ax cli
-
-╭─────────────────────────────────────────────────────╮
-│   AutomatosX Interactive CLI v7.1.0                 │
-│   Type /help for commands, /exit to quit            │
-│   Using: Gemini 2.5 Flash                           │
-╰─────────────────────────────────────────────────────╯
-
-ax> I need to implement JWT authentication
-
-AI: I'll help you implement JWT authentication. Let me search our
-    memory for existing auth patterns...
-
-    Found 2 relevant patterns. Would you like me to:
-    1. Show implementation plan
-    2. Delegate to backend agent
-    3. Start coding immediately
-
-ax> Delegate to backend agent
-
-AI: @backend implement JWT authentication with refresh tokens
-
-    [Backend agent working...]
-    ✓ Dependencies installed
-    ✓ Auth middleware created
-    ✓ Token refresh endpoint added
-    ✓ Tests generated
-
-ax> /save jwt-implementation
-Conversation saved: jwt-implementation
-
-ax> /exit
-```
-
-### Key Features
-
-- 🤖 **Natural Conversations** - Multi-turn discussions with full context
-- 🔄 **Real-time Streaming** - See responses as they're generated
-- 💾 **Save & Resume** - Continue conversations later with `/save` and `/load`
-- 🎯 **Agent Delegation** - Route tasks to specialists: `@backend`, `@security`, etc.
-- 📝 **13 Slash Commands** - `/help`, `/memory`, `/agents`, `/export`, and more
-- 🎨 **Beautiful Output** - Markdown rendering and syntax-highlighted code blocks
-- ⚡ **Fast & Efficient** - Powered by Gemini free tier (1,500 requests/day)
-
-### Quick Examples
-
-```bash
-# Start a coding session
-ax cli
-ax> @backend create a REST API for user management
-ax> @security audit the authentication code
-ax> /save user-management-api
-
-# Search your knowledge base
-ax cli
-ax> /memory search "authentication patterns"
-ax> Show me the JWT implementation we used last time
-
-# Work across sessions
-ax cli
-ax> /load user-management-api
-ax> Let's add rate limiting to these endpoints
-ax> /export  # Export to markdown for documentation
-```
-
-**📖 Full Guide**: [Interactive CLI Documentation](docs/cli-interactive.md)
-
-**Alternative Commands**: `ax interactive`, `ax chat`
-
----
-
 ## 🗣️ **Recommended**: Natural Language Interface
 
 AutomatosX is designed to work seamlessly with AI assistants using natural language commands. This is the **recommended way** to use AutomatosX:
@@ -1208,9 +1129,107 @@ ax setup -f
   - [Gemini CLI](https://ai.google.dev/gemini-api/docs/cli) (recommended - cheapest)
   - [OpenAI Codex](https://platform.openai.com/docs/guides/code) (fastest)
   - [Claude Code](https://claude.ai/code) (most capable)
+  - [Grok CLI](#-grok-cli-configuration-new-in-v831) (X.AI or self-hosted GLM 4.6)
 
 [➡️ Full Installation Guide](docs/getting-started/installation.md)
 
+### 🤖 Grok CLI Configuration (New in v8.3.1)
+
+AutomatosX now supports Grok CLI with **two endpoints**:
+
+#### Option 1: X.AI Official Grok (Recommended)
+
+```bash
+# 1. Run setup to create .grok/settings.json
+ax setup
+
+# 2. Edit .grok/settings.json
+{
+  "baseURL": "https://api.x.ai/v1",
+  "model": "grok-3-fast",
+  "apiKey": "xai-your-key-here"
+}
+
+# 3. Enable in automatosx.config.json
+"grok": { "enabled": true }
+
+# 4. Verify
+ax doctor grok
+ax providers list
+```
+
+**Get X.AI API Key**: https://console.x.ai/api-keys
+
+#### Option 2: Z.AI GLM 4.6 (Code-Optimized)
+
+```bash
+# Edit .grok/settings.json
+{
+  "baseURL": "https://api.z.ai/api/coding/paas/v4",
+  "model": "glm-4.6",
+  "apiKey": "your-zai-key"
+}
+```
+
+**Get Z.AI API Key**: https://z.ai/developer
+
+#### Option 3: Self-Hosted GLM 4.6 API Server
+
+**Use your own local coding system with AutomatosX!**
+
+You can point AutomatosX to your own GLM 4.6 API server for complete control:
+
+```bash
+# Edit .grok/settings.json
+{
+  "baseURL": "http://localhost:8000/v1",  # Your local API server
+  "model": "glm-4.6",
+  "apiKey": "your-local-api-key"  # Optional if your server requires it
+}
+```
+
+**Benefits of Self-Hosted:**
+- 🏠 Complete data privacy - all processing stays local
+- 💰 No usage costs - run as much as you want
+- ⚡ Lower latency - no network round trips
+- 🔧 Full customization - fine-tune the model for your needs
+- 🔒 Enterprise security - meets corporate requirements
+
+**Popular GLM 4.6 API Server Implementations:**
+- [vLLM](https://github.com/vllm-project/vllm) - Fast inference server
+- [Text Generation Inference](https://github.com/huggingface/text-generation-inference) - HuggingFace's solution
+- [Ollama](https://ollama.ai) - Easy local deployment
+- Custom FastAPI/Flask wrapper around GLM 4.6
+
+**Example Docker Setup:**
+```bash
+# Run GLM 4.6 API server locally
+docker run -d \
+  -p 8000:8000 \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  vllm/vllm-openai:latest \
+  --model THUDM/glm-4-6 \
+  --port 8000
+
+# Configure AutomatosX to use it
+# Edit .grok/settings.json with baseURL: "http://localhost:8000/v1"
+```
+
+**📄 License Note for Self-Hosted/Commercial Use:**
+
+AutomatosX is licensed under Apache 2.0 for **non-commercial use**. For commercial use or to remove license restrictions:
+
+- 💼 **Commercial License**: Visit https://license.defai.digital/automatosx
+- 📋 **Custom Terms**: Available for enterprise deployments
+- 🤝 **Volume Discounts**: Contact us for team/organization pricing
+
+**See [GROK.md](GROK.md) for complete setup guide, including:**
+- Model comparison (grok-3-fast vs glm-4.6)
+- Environment variable configuration
+- Switching between endpoints
+- Troubleshooting guide
+- Cost optimization tips
+
 ---
 
 ## 🗺️ Roadmap
@@ -1366,7 +1385,27 @@ npm run build
 
 ## 📄 License
 
-Elastic License 2.0 - See [LICENSE](LICENSE) for details.
+AutomatosX is dual-licensed:
+
+- **Apache License 2.0** - See [LICENSE](LICENSE) for code licensing
+- **Commercial License with OpenRAIL-M** - See [COMMERCIAL-LICENSE.md](COMMERCIAL-LICENSE.md) for commercial use and model restrictions
+
+### TL;DR - When Do You Need a Commercial License?
+
+**✅ FREE for**:
+- Research and academic use
+- Personal projects
+- Startups with < $2M revenue AND < $2M funding
+
+**❌ Commercial License Required for**:
+- Companies with ≥ $2M annual revenue OR ≥ $2M total funding
+- Competitive products against DEFAI's offerings
+- SaaS or managed services built on AutomatosX
+- Commercial redistribution or embedding
+
+**Learn more**: See [COMMERCIAL-LICENSE.md](COMMERCIAL-LICENSE.md) for full details.
+
+**Get a commercial license**: https://license.defai.digital/automatox
 
 Copyright 2025 DEFAI Private Limited