diff --git a/README.md b/README.md index 50ebeab..22b490b 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ Magic Shell is an open-source CLI tool that translates plain English (or any nat ## Features - **Natural Language Translation**: Describe what you want to do in plain English -- **Multiple AI Providers**: OpenCode Zen (with free models!), OpenRouter, and custom models (LM Studio, Ollama, OpenAI-compatible) +- **Multiple AI Providers**: OpenCode Zen (with free models!), OpenRouter, Vercel AI Gateway, Cloudflare AI Gateway, Workers AI, and custom models (LM Studio, Ollama, OpenAI-compatible) - **Custom Model Support**: Add your own local or remote models with secure API key storage - **Project Context Aware**: Opt-in detection of package.json scripts, Makefile targets, etc. - **Interactive TUI Mode**: Full-featured terminal interface with themes @@ -104,7 +104,7 @@ mshell | `msh --add-model` | Add custom model (LM Studio, Ollama, etc.) | | `msh --list-custom` | List custom models | | `msh --remove-model ` | Remove custom model | -| `msh --provider ` | Set provider (opencode-zen or openrouter) | +| `msh --provider ` | Set provider (OpenCode Zen, OpenRouter, gateways, Workers AI, or custom) | | `msh --thinking ` | Set thinking level (off, low, medium, high) | | `msh --themes` | List available themes | | `msh --theme ` | Set color theme | @@ -185,23 +185,23 @@ OpenCode Zen provides curated models optimized for coding tasks, including **fre **Free Models:** -- `minimax-m2.5-free` - MiniMax's free model (default) -- `ling-2.6-flash-free` - Ling's free flash model -- `hy3-preview-free` - Hy3 preview model -- `nemotron-3-super-free` - NVIDIA Nemotron free trial model -- `trinity-large-preview-free` - Trinity large preview model +- `deepseek-v4-flash-free` - DeepSeek's free fast open-source model (default) +- `mimo-v2.5-free` - Xiaomi's free long-context MiMo model +- `north-mini-code-free` - North's free coding model +- `nemotron-3-ultra-free` - NVIDIA Nemotron free trial model - `big-pickle` - OpenCode stealth model - `gpt-5-nano` - OpenAI's free lightweight GPT model **Premium Models:** -- Claude Sonnet 4.6, Claude Opus 4.7, Claude Haiku 4.5 -- Kimi K2.6, Kimi K2 Thinking -- DeepSeek V4 Pro -- GLM 5.1 +- Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5, Claude Fable 5 +- Kimi K2.6 +- DeepSeek V4 Pro, DeepSeek V4 Flash +- GLM 5.2, GLM 5.1 +- Qwen3.7 Max, Qwen3.7 Plus - MiMo V2.5, MiMo V2.5 Pro - MiniMax M2.7 -- Gemini 3.1 Pro, Gemini 3 Flash +- Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3 Flash - GPT 5.5, GPT 5.5 Pro, GPT 5.4 Mini/Nano, GPT 5.3 Codex - And more... @@ -211,17 +211,14 @@ Get your API key at: https://opencode.ai/auth Access to a wide variety of models from different providers. -**Free Models:** - -- MiniMax M2.5 Free - -**Premium Models:** +**Open-source and open-weight highlights:** -- MiMo V2.5, MiMo V2.5 Pro -- Kimi K2.6, Kimi K2 Thinking +- Kimi K2.7 Code, Kimi K2.6 - DeepSeek V4 Pro, DeepSeek V4 Flash -- GLM 5.1, GLM 5 Turbo -- MiniMax M2.7 +- GLM 5.2, GLM 5.1, GLM 5 Turbo +- Qwen3.7 Max, Qwen3.7 Plus +- MiniMax M3, MiniMax M2.7 +- MiMo V2.5, MiMo V2.5 Pro - And many more... Get your API key at: https://openrouter.ai/keys @@ -303,7 +300,7 @@ Configuration is stored in `~/.magic-shell/config.json`. ```json { "provider": "opencode-zen", - "defaultModel": "minimax-m2.5-free", + "defaultModel": "deepseek-v4-flash-free", "thinkingLevel": "low", "safetyLevel": "moderate", "dryRunByDefault": false, @@ -326,11 +323,16 @@ Configuration is stored in `~/.magic-shell/config.json`. ### Environment Variables -| Variable | Description | -| ---------------------- | ----------------------------- | -| `OPENCODE_ZEN_API_KEY` | API key for OpenCode Zen | -| `OPENROUTER_API_KEY` | API key for OpenRouter | -| `DEBUG_API=1` | Enable API response debugging | +| Variable | Description | +| -------------------------------- | ----------------------------------- | +| `OPENCODE_ZEN_API_KEY` | API key for OpenCode Zen | +| `OPENROUTER_API_KEY` | API key for OpenRouter | +| `AI_GATEWAY_API_KEY` | API key for Vercel AI Gateway | +| `CLOUDFLARE_AI_GATEWAY_API_KEY` | API key/token for Cloudflare Gateway | +| `CLOUDFLARE_API_TOKEN` | API token for Workers AI | +| `CLOUDFLARE_ACCOUNT_ID` | Account ID for Cloudflare providers | +| `CLOUDFLARE_AI_GATEWAY_ID` | Gateway ID for Cloudflare Gateway | +| `DEBUG_API=1` | Enable API response debugging | ## Themes @@ -583,6 +585,13 @@ MIT License - see [LICENSE](LICENSE) for details. ## Release Notes +### v0.2.22 - Model Catalog and Release Prep + +- Refreshed OpenCode Zen and OpenRouter model registries with current June 2026 open-source/open-weight entries +- Updated the default free Zen model to `deepseek-v4-flash-free` +- Added Zen routing support for Qwen models on the Messages endpoint +- Updated release docs and website provider surfaces for the refreshed provider/model set + ### v0.2.20 - Thinking Controls and Zen Free Models - Added `--thinking ` and `thinkingLevel` config support (`off`, `low`, `medium`, `high`) - Added provider-specific reasoning controls for supported OpenRouter, OpenCode Zen, gateway, and custom models diff --git a/website/SCHEMA-IMPLEMENTATION.md b/website/SCHEMA-IMPLEMENTATION.md index 5b52e45..4029849 100644 --- a/website/SCHEMA-IMPLEMENTATION.md +++ b/website/SCHEMA-IMPLEMENTATION.md @@ -42,11 +42,11 @@ The website implements comprehensive JSON-LD structured data to help search engi - Application category: DeveloperApplication - Operating systems: macOS, Linux, Windows -- Version: 0.2.14 +- Version: 0.2.22 - Price: Free ($0) - Download URL (npm) - Feature list (10 key features) -- Requirements: Node.js 18.0.0+ +- Requirements: Bun 1.3.14+ - Code repository - License: MIT - Screenshots/images diff --git a/website/SCHEMA-SUMMARY.md b/website/SCHEMA-SUMMARY.md index 4af008b..d61b477 100644 --- a/website/SCHEMA-SUMMARY.md +++ b/website/SCHEMA-SUMMARY.md @@ -89,13 +89,13 @@ Comprehensive schema.org structured data has been implemented for the Magic Shel ### SoftwareApplication Schema - ✅ Free pricing ($0) -- ✅ Version 0.2.14 +- ✅ Version 0.2.22 - ✅ Cross-platform (macOS, Linux, Windows) - ✅ 10 feature highlights - ✅ npm download link - ✅ GitHub repository link - ✅ MIT license -- ✅ Requirements (Node.js 18+) +- ✅ Requirements (Bun 1.3.14+) ### HowTo Schema @@ -144,7 +144,7 @@ Comprehensive schema.org structured data has been implemented for the Magic Shel - [ ] View page source and verify JSON-LD is present - [ ] Check JSON syntax is valid (no trailing commas, proper quotes) - [ ] Verify all URLs are fully qualified (https://mshell.dev/...) -- [ ] Confirm version number is current (0.2.14) +- [ ] Confirm version number is current (0.2.22) - [ ] Review FAQ answers for accuracy ### After Deployment @@ -265,7 +265,7 @@ Comprehensive schema.org structured data has been implemented for the Magic Shel ```astro // In Schema.astro, line ~60 -"softwareVersion": "0.2.14", // ← Update this +"softwareVersion": "0.2.22", // ← Update this ``` ### Add FAQ Question diff --git a/website/SCHEMA-VALIDATION.md b/website/SCHEMA-VALIDATION.md index 9e9bde9..4773b86 100644 --- a/website/SCHEMA-VALIDATION.md +++ b/website/SCHEMA-VALIDATION.md @@ -88,7 +88,7 @@ schemas.forEach((s, i) => { **Check for:** - [ ] All URLs are fully qualified (https://mshell.dev/...) -- [ ] Version number matches current release (0.2.14) +- [ ] Version number matches current release (0.2.22) - [ ] Feature list is accurate and up-to-date - [ ] FAQ answers match actual functionality - [ ] HowTo steps are clear and actionable diff --git a/website/TEST-SCHEMA.md b/website/TEST-SCHEMA.md index a2c7c6b..689c860 100644 --- a/website/TEST-SCHEMA.md +++ b/website/TEST-SCHEMA.md @@ -59,7 +59,7 @@ npm run preview **SoftwareApplication:** - ✅ Name: "Magic Shell" -- ✅ Version: "0.2.14" +- ✅ Version: "0.2.22" - ✅ Price: "0" - ✅ Operating systems listed - ✅ 10 features in featureList diff --git a/website/src/components/FAQSchema.astro b/website/src/components/FAQSchema.astro index 3801ab3..3edb94d 100644 --- a/website/src/components/FAQSchema.astro +++ b/website/src/components/FAQSchema.astro @@ -11,7 +11,7 @@ const faqSchema = { "name": "What is Magic Shell?", "acceptedAnswer": { "@type": "Answer", - "text": "Magic Shell is an open-source CLI tool that translates natural language into shell commands using AI. It supports multiple AI providers (OpenCode Zen with free models, and OpenRouter), includes a beautiful interactive TUI mode, and features comprehensive safety analysis to protect against dangerous commands." + "text": "Magic Shell is an open-source CLI tool that translates natural language into shell commands using AI. It supports multiple AI providers (OpenCode Zen with free models, OpenRouter, Vercel AI Gateway, Cloudflare AI Gateway, Workers AI, and custom models), includes a beautiful interactive TUI mode, and features comprehensive safety analysis to protect against dangerous commands." } }, { @@ -27,7 +27,7 @@ const faqSchema = { "name": "Is Magic Shell free to use?", "acceptedAnswer": { "@type": "Answer", - "text": "Yes, Magic Shell is completely free and open-source under the MIT license. It supports free AI models through OpenCode Zen (including minimax-m2.5-free, ling-2.6-flash-free, hy3-preview-free, nemotron-3-super-free, trinity-large-preview-free, big-pickle, and gpt-5-nano) as well as premium models from various providers. You can also use custom local models with LM Studio or Ollama at no cost." + "text": "Yes, Magic Shell is completely free and open-source under the MIT license. It supports free AI models through OpenCode Zen (including deepseek-v4-flash-free, mimo-v2.5-free, north-mini-code-free, nemotron-3-ultra-free, big-pickle, and gpt-5-nano) as well as premium models from various providers. You can also use custom local models with LM Studio or Ollama at no cost." } }, { @@ -35,7 +35,7 @@ const faqSchema = { "name": "What AI providers does Magic Shell support?", "acceptedAnswer": { "@type": "Answer", - "text": "Magic Shell supports OpenCode Zen (recommended, with free models), OpenRouter, and custom OpenAI-compatible endpoints. You can also add custom models from LM Studio, Ollama, or any OpenAI-compatible API. Each provider offers different models with varying capabilities and pricing." + "text": "Magic Shell supports OpenCode Zen (recommended, with free models), OpenRouter, Vercel AI Gateway, Cloudflare AI Gateway, Workers AI, and custom OpenAI-compatible endpoints. You can also add custom models from LM Studio, Ollama, or any OpenAI-compatible API. Each provider offers different models with varying capabilities and pricing." } }, { diff --git a/website/src/components/Schema.astro b/website/src/components/Schema.astro index b5f8dc9..d058ac1 100644 --- a/website/src/components/Schema.astro +++ b/website/src/components/Schema.astro @@ -21,13 +21,13 @@ const organizationSchema = { "logo": `${baseUrl}/favicon.svg`, "description": "Transform natural language into terminal commands with AI-powered translation and built-in safety features", "sameAs": [ - "https://github.com/designxdevelop/magic-shell" + "https://github.com/austin-thesing/magic-shell" ], "foundingDate": "2026", "founder": { "@type": "Person", "name": "Austin Thesing", - "url": "https://github.com/designxdevelop/magic-shell" + "url": "https://github.com/austin-thesing" } }; @@ -59,10 +59,10 @@ const softwareSchema = type === 'homepage' ? { "name": "Magic Shell", "applicationCategory": "DeveloperApplication", "operatingSystem": "macOS, Linux, Windows", - "description": "Open-source CLI tool that translates natural language into shell commands using AI. Supports multiple AI providers, includes a beautiful interactive TUI mode, and features comprehensive safety analysis.", + "description": "Open-source CLI tool that translates natural language into shell commands using AI. Supports OpenCode Zen, OpenRouter, AI gateways, Workers AI, and custom models.", "url": baseUrl, "downloadUrl": "https://www.npmjs.com/package/@austinthesing/magic-shell", - "softwareVersion": "0.2.14", + "softwareVersion": "0.2.22", "offers": { "@type": "Offer", "price": "0", @@ -71,7 +71,7 @@ const softwareSchema = type === 'homepage' ? { "author": { "@type": "Person", "name": "Austin Thesing", - "url": "https://github.com/designxdevelop/magic-shell" + "url": "https://github.com/austin-thesing" }, "publisher": { "@id": `${baseUrl}/#organization` @@ -79,7 +79,7 @@ const softwareSchema = type === 'homepage' ? { "screenshot": `${baseUrl}/og-image.png`, "featureList": [ "Natural language to terminal command translation", - "Multiple AI providers (OpenCode Zen, OpenRouter)", + "Multiple AI providers (OpenCode Zen, OpenRouter, AI gateways, Workers AI, custom models)", "Interactive TUI mode with 8 themes", "Command safety analysis with multi-level checks", "Project context awareness", @@ -89,13 +89,13 @@ const softwareSchema = type === 'homepage' ? { "Command history tracking", "Auto-update checking" ], - "requirements": "Node.js 18.0.0 or higher", + "requirements": "Bun 1.3.14 or higher", "installUrl": `${baseUrl}/getting-started/installation/`, "softwareHelp": { "@type": "WebPage", "url": `${baseUrl}/getting-started/installation/` }, - "codeRepository": "https://github.com/designxdevelop/magic-shell", + "codeRepository": "https://github.com/austin-thesing/magic-shell", "programmingLanguage": { "@type": "ComputerLanguage", "name": "TypeScript" @@ -119,7 +119,7 @@ const howToSchema = type === 'homepage' ? { "tool": [ { "@type": "HowToTool", - "name": "Node.js or Bun runtime" + "name": "Bun runtime" }, { "@type": "HowToTool", @@ -144,7 +144,7 @@ const howToSchema = type === 'homepage' ? { "@type": "HowToStep", "position": 2, "name": "Configure API Key", - "text": "Set up your API key for OpenCode Zen or OpenRouter to enable AI-powered command translation", + "text": "Set up your API key for OpenCode Zen, OpenRouter, an AI gateway, Workers AI, or a custom provider to enable AI-powered command translation", "itemListElement": [ { "@type": "HowToDirection", @@ -209,7 +209,7 @@ const articleSchema = type === 'article' && title ? { "author": { "@type": "Person", "name": "Austin Thesing", - "url": "https://github.com/designxdevelop/magic-shell" + "url": "https://github.com/austin-thesing" }, "publisher": { "@id": `${baseUrl}/#organization` diff --git a/website/src/components/TransformHero.astro b/website/src/components/TransformHero.astro index 79579ec..358cb53 100644 --- a/website/src/components/TransformHero.astro +++ b/website/src/components/TransformHero.astro @@ -34,7 +34,7 @@ import InstallBlock from "./InstallBlock.astro"; - + @@ -82,13 +82,13 @@ import InstallBlock from "./InstallBlock.astro"; magic-shell
- grok-3 + deepseek-v4-flash-free
Provider: opencode-zen - Model: grok-3 + Model: deepseek-v4-flash-free Safe Mode
diff --git a/website/src/content/docs/features/providers.mdx b/website/src/content/docs/features/providers.mdx index d78ecad..e8af07b 100644 --- a/website/src/content/docs/features/providers.mdx +++ b/website/src/content/docs/features/providers.mdx @@ -15,11 +15,10 @@ OpenCode Zen provides curated models optimized for coding tasks. It's the defaul | Model | Description | |-------|-------------| -| `minimax-m2.5-free` | MiniMax's free model (default) | -| `ling-2.6-flash-free` | Ling's free flash model | -| `hy3-preview-free` | Hy3 preview model | -| `nemotron-3-super-free` | NVIDIA Nemotron free trial model | -| `trinity-large-preview-free` | Trinity large preview model | +| `deepseek-v4-flash-free` | DeepSeek's free fast open-source model (default) | +| `mimo-v2.5-free` | Xiaomi's free long-context MiMo model | +| `north-mini-code-free` | North's free coding model | +| `nemotron-3-ultra-free` | NVIDIA Nemotron free trial model | | `big-pickle` | OpenCode stealth model | | `gpt-5-nano` | OpenAI's free lightweight GPT model | @@ -28,15 +27,19 @@ OpenCode Zen provides curated models optimized for coding tasks. It's the defaul | Model | Description | |-------|-------------| | `claude-sonnet-4-6` | Anthropic's latest Sonnet model | -| `claude-opus-4-7` | Anthropic's latest Opus model | +| `claude-opus-4-8` | Anthropic's latest Opus model | | `claude-haiku-4-5` | Anthropic's latest fast model | | `kimi-k2.6` | Moonshot's latest Kimi model | -| `kimi-k2-thinking` | Kimi K2 with extended reasoning | | `deepseek-v4-pro` | DeepSeek's latest high-context model | +| `deepseek-v4-flash` | DeepSeek's latest fast model | +| `glm-5.2` | Z.ai's latest long-context GLM model | | `glm-5.1` | Z.ai's latest GLM model | +| `qwen3.7-max` | Qwen's latest high-capability open-weight model | +| `qwen3.7-plus` | Qwen's latest long-context open-weight model | | `mimo-v2.5` | Xiaomi's latest long-context MiMo model | | `mimo-v2.5-pro` | Xiaomi's latest pro MiMo model | | `minimax-m2.7` | MiniMax's latest model | +| `gemini-3.5-flash` | Google's latest fast Gemini model | | `gemini-3.1-pro` | Google's high-end Gemini model | | `gemini-3-flash` | Google's fast Gemini model | | `gpt-5.5` | OpenAI's latest flagship GPT model | @@ -44,7 +47,7 @@ OpenCode Zen provides curated models optimized for coding tasks. It's the defaul | `gpt-5.3-codex` | OpenAI's latest coding-focused GPT model | ### Get an API Key @@ -64,11 +67,14 @@ OpenRouter provides access to models from many providers through a single API. |-------|-------------| | `xiaomi/mimo-v2.5` | Xiaomi's latest long-context MiMo model | | `xiaomi/mimo-v2.5-pro` | Xiaomi's latest pro MiMo model | +| `moonshotai/kimi-k2.7-code` | Moonshot's latest open-weight coding model | | `moonshotai/kimi-k2.6` | Moonshot's latest Kimi model | | `deepseek/deepseek-v4-pro` | DeepSeek's latest high-context model | | `deepseek/deepseek-v4-flash` | DeepSeek's latest fast model | +| `z-ai/glm-5.2` | Z.ai's latest long-context GLM model | | `z-ai/glm-5.1` | Z.ai's latest GLM model | | `z-ai/glm-5-turbo` | Z.ai's latest fast GLM model | +| `minimax/minimax-m3` | MiniMax's latest open-weight multimodal model | | `minimax/minimax-m2.7` | MiniMax's latest model | | `openai/gpt-latest` | OpenAI GPT latest alias | | `openai/gpt-5.5` | OpenAI's latest flagship GPT model | @@ -76,7 +82,7 @@ OpenRouter provides access to models from many providers through a single API. | `anthropic/claude-sonnet-latest` | Claude Sonnet latest alias | | `anthropic/claude-sonnet-4.6` | Anthropic's latest Sonnet model | | `anthropic/claude-opus-latest` | Claude Opus latest alias | -| `anthropic/claude-opus-4.7` | Anthropic's latest Opus model | +| `anthropic/claude-opus-4.8` | Anthropic's latest Opus model | ### Get an API Key @@ -119,7 +125,7 @@ Press `Ctrl+X S` to open the provider switcher. msh --models # Set default model -msh --model minimax-m2.5-free +msh --model deepseek-v4-flash-free ``` ### Via TUI @@ -130,10 +136,10 @@ Press `Ctrl+X M` to open the model picker. | Use Case | Recommended Model | |----------|------------------| -| Quick commands | `minimax-m2.5-free` | +| Quick commands | `deepseek-v4-flash-free` | | Complex git operations | `claude-sonnet-4-6` | -| System administration | `ling-2.6-flash-free` or `minimax-m2.7` | -| Multi-step tasks | `claude-opus-4-7` or `kimi-k2-thinking` | +| System administration | `deepseek-v4-flash-free` or `minimax-m2.7` | +| Multi-step tasks | `claude-opus-4-8` or `qwen3.7-max` | | Learning/experimenting | Any free model | ## Environment Variables diff --git a/website/src/content/docs/getting-started/configuration.mdx b/website/src/content/docs/getting-started/configuration.mdx index 7226155..8562b5c 100644 --- a/website/src/content/docs/getting-started/configuration.mdx +++ b/website/src/content/docs/getting-started/configuration.mdx @@ -14,7 +14,7 @@ msh --setup ``` This will guide you through: -1. Selecting a provider (OpenCode Zen, OpenRouter, or custom models) +1. Selecting a provider (OpenCode Zen, OpenRouter, Vercel AI Gateway, Cloudflare AI Gateway, Workers AI, or custom models) 2. Entering your API key (if needed) 3. Choosing a default model @@ -29,7 +29,7 @@ This will guide you through: 3. Copy your API key @@ -51,6 +51,14 @@ export OPENCODE_ZEN_API_KEY="your-key-here" # OpenRouter export OPENROUTER_API_KEY="your-key-here" + +# Vercel AI Gateway +export AI_GATEWAY_API_KEY="your-key-here" + +# Cloudflare providers +export CLOUDFLARE_API_TOKEN="your-token" +export CLOUDFLARE_ACCOUNT_ID="your-account-id" +export CLOUDFLARE_AI_GATEWAY_API_KEY="your-gateway-token" ``` Add these to your shell profile (`~/.bashrc`, `~/.zshrc`, etc.) for persistence. @@ -96,7 +104,7 @@ Magic Shell stores configuration in `~/.magic-shell/config.json`: ```json { "provider": "opencode-zen", - "defaultModel": "minimax-m2.5-free", + "defaultModel": "deepseek-v4-flash-free", "safetyLevel": "moderate", "dryRunByDefault": false, "theme": "opencode" @@ -107,8 +115,8 @@ Magic Shell stores configuration in `~/.magic-shell/config.json`: | Option | Description | Default | |--------|-------------|---------| -| `provider` | AI provider (`opencode-zen`, `openrouter`, or `custom`) | `opencode-zen` | -| `defaultModel` | Default model ID | `minimax-m2.5-free` | +| `provider` | AI provider (`opencode-zen`, `openrouter`, `vercel-ai-gateway`, `cloudflare-ai-gateway`, `workers-ai`, or `custom`) | `opencode-zen` | +| `defaultModel` | Default model ID | `deepseek-v4-flash-free` | | `safetyLevel` | Safety strictness (`strict`, `moderate`, `relaxed`) | `moderate` | | `dryRunByDefault` | Always show commands without executing | `false` | | `theme` | Color theme name | `opencode` | diff --git a/website/src/content/docs/getting-started/installation.mdx b/website/src/content/docs/getting-started/installation.mdx index d02a620..a5cd3bf 100644 --- a/website/src/content/docs/getting-started/installation.mdx +++ b/website/src/content/docs/getting-started/installation.mdx @@ -23,11 +23,11 @@ yarn global add @austinthesing/magic-shell ## From Source -**Prerequisites:** [Bun](https://bun.sh) runtime (v1.0 or higher) +**Prerequisites:** [Bun](https://bun.sh) runtime (v1.3.14 or higher) ```bash # Clone the repository -git clone https://github.com/designxdevelop/magic-shell.git +git clone https://github.com/austin-thesing/magic-shell.git cd magic-shell # Install dependencies diff --git a/website/src/content/docs/index.mdx b/website/src/content/docs/index.mdx index 38c8546..34721ed 100644 --- a/website/src/content/docs/index.mdx +++ b/website/src/content/docs/index.mdx @@ -10,7 +10,7 @@ hero: icon: right-arrow variant: primary - text: View on GitHub - link: https://github.com/designxdevelop/magic-shell + link: https://github.com/austin-thesing/magic-shell icon: external --- @@ -44,7 +44,7 @@ msh "find all files larger than 100MB" [Get started →](/getting-started/first-command/) - Choose between OpenCode Zen (with free models!), OpenRouter, or add custom models for local endpoints. + Choose OpenCode Zen, OpenRouter, AI gateways, Workers AI, or custom local endpoints. [Learn more →](/features/providers/) diff --git a/website/src/content/docs/reference/changelog.mdx b/website/src/content/docs/reference/changelog.mdx index fb16b02..33d2cc5 100644 --- a/website/src/content/docs/reference/changelog.mdx +++ b/website/src/content/docs/reference/changelog.mdx @@ -3,6 +3,24 @@ title: Changelog description: Release notes and version history for Magic Shell --- +## v0.2.22 - Model Catalog and Release Prep + +**Released:** June 16, 2026 + +### What's New + +- Refreshed OpenCode Zen with the current free model set, including `deepseek-v4-flash-free`, `mimo-v2.5-free`, `north-mini-code-free`, `nemotron-3-ultra-free`, `big-pickle`, and `gpt-5-nano` +- Added current OpenRouter open-source/open-weight highlights, including `moonshotai/kimi-k2.7-code`, `z-ai/glm-5.2`, `minimax/minimax-m3`, `qwen/qwen3.7-max`, and `qwen/qwen3.7-plus` +- Updated OpenCode Zen Qwen model routing to use the Messages endpoint documented by Zen + +### Improvements + +- Updated the default model to `deepseek-v4-flash-free` +- Refreshed release-facing README, provider docs, config docs, and FAQ schema copy +- Updated website dependency lockfiles for release prep + +--- + ## v0.2.20 - Thinking Controls and Zen Free Models **Released:** May 1, 2026 @@ -117,6 +135,7 @@ Magic Shell transforms natural language into terminal commands with AI-powered t | Version | Date | Highlights | |---------|------|------------| +| v0.2.22 | Jun 16, 2026 | Model catalog and release prep | | v0.2.20 | May 1, 2026 | Thinking controls and Zen free models | | v0.2.19 | May 1, 2026 | AI Gateway providers | | v0.2.18 | May 1, 2026 | Model registry refresh | diff --git a/website/src/content/docs/reference/cli-options.mdx b/website/src/content/docs/reference/cli-options.mdx index a8745ba..e7a21f5 100644 --- a/website/src/content/docs/reference/cli-options.mdx +++ b/website/src/content/docs/reference/cli-options.mdx @@ -25,7 +25,7 @@ msh [options] [query] | Option | Description | |--------|-------------| | `--setup` | Run the setup wizard for API key configuration | -| `--provider ` | Set AI provider (`opencode-zen` or `openrouter`) | +| `--provider ` | Set AI provider (`opencode-zen`, `openrouter`, `vercel-ai-gateway`, `cloudflare-ai-gateway`, or `workers-ai`) | | `--model ` | Set default model (including custom models) | | `--models` | List available models for current provider | | `--add-model` | Add custom model (LM Studio, Ollama, etc.) | @@ -90,6 +90,15 @@ msh --provider openrouter # Switch back to OpenCode Zen msh --provider opencode-zen + +# Switch to Vercel AI Gateway +msh --provider vercel-ai-gateway + +# Switch to Cloudflare AI Gateway +msh --provider cloudflare-ai-gateway + +# Switch to Workers AI +msh --provider workers-ai ``` ### Change Model @@ -151,6 +160,11 @@ msh --setup |----------|-------------| | `OPENCODE_ZEN_API_KEY` | API key for OpenCode Zen provider | | `OPENROUTER_API_KEY` | API key for OpenRouter provider | +| `AI_GATEWAY_API_KEY` | API key for Vercel AI Gateway | +| `CLOUDFLARE_AI_GATEWAY_API_KEY` | API key/token for Cloudflare AI Gateway | +| `CLOUDFLARE_API_TOKEN` | API token for Workers AI | +| `CLOUDFLARE_ACCOUNT_ID` | Account ID for Cloudflare providers | +| `CLOUDFLARE_AI_GATEWAY_ID` | Gateway ID for Cloudflare AI Gateway | | `DEBUG_API=1` | Enable API debugging output | ## Commands diff --git a/website/src/content/docs/reference/config-file.mdx b/website/src/content/docs/reference/config-file.mdx index 337f128..8568225 100644 --- a/website/src/content/docs/reference/config-file.mdx +++ b/website/src/content/docs/reference/config-file.mdx @@ -18,10 +18,12 @@ Magic Shell stores configuration in `~/.magic-shell/config.json`. ```json { "provider": "opencode-zen", - "defaultModel": "minimax-m2.5-free", + "defaultModel": "deepseek-v4-flash-free", "thinkingLevel": "low", "safetyLevel": "moderate", "dryRunByDefault": false, + "cloudflareAccountId": "", + "cloudflareAiGatewayId": "default", "repoContext": false, "theme": "opencode", "blockedCommands": [], @@ -40,6 +42,10 @@ The AI provider to use for translations. |-------|-------------| | `"opencode-zen"` | OpenCode Zen (default, has free models) | | `"openrouter"` | OpenRouter | +| `"vercel-ai-gateway"` | Vercel AI Gateway | +| `"cloudflare-ai-gateway"` | Cloudflare AI Gateway | +| `"workers-ai"` | Cloudflare Workers AI | +| `"custom"` | Custom OpenAI-compatible endpoint | ```json { @@ -53,12 +59,47 @@ The model ID to use for translations. ```json { - "defaultModel": "minimax-m2.5-free" + "defaultModel": "deepseek-v4-flash-free" } ``` Run `msh --models` to see available models for your provider. +### provider API key fallbacks + +Provider API keys are stored in your system keychain when secure storage is available. If +keychain storage is unavailable, Magic Shell can use these config fields as fallbacks: + +| Field | Provider | +|-------|----------| +| `opencodeZenApiKey` | OpenCode Zen | +| `openrouterApiKey` | OpenRouter | +| `vercelAiGatewayApiKey` | Vercel AI Gateway | +| `cloudflareAiGatewayApiKey` | Cloudflare AI Gateway | +| `workersAiApiKey` | Cloudflare Workers AI | + +Environment variables take precedence over both keychain and config-file values. + +### cloudflareAccountId + +Cloudflare account ID used by Cloudflare AI Gateway and Workers AI. + +```json +{ + "cloudflareAccountId": "your-account-id" +} +``` + +### cloudflareAiGatewayId + +Cloudflare AI Gateway ID. Defaults to `default`. + +```json +{ + "cloudflareAiGatewayId": "default" +} +``` + ### thinkingLevel Controls provider thinking/reasoning depth for supported models. @@ -208,7 +249,7 @@ msh --remove-model # Remove a custom model ```json { "provider": "opencode-zen", - "defaultModel": "minimax-m2.5-free", + "defaultModel": "deepseek-v4-flash-free", "safetyLevel": "strict", "dryRunByDefault": true, "theme": "nord" @@ -220,7 +261,7 @@ msh --remove-model # Remove a custom model ```json { "provider": "opencode-zen", - "defaultModel": "minimax-m2.5-free", + "defaultModel": "deepseek-v4-flash-free", "safetyLevel": "relaxed", "dryRunByDefault": false, "theme": "dracula" diff --git a/website/src/content/docs/reference/keyboard-shortcuts.mdx b/website/src/content/docs/reference/keyboard-shortcuts.mdx index 2064c15..e956e53 100644 --- a/website/src/content/docs/reference/keyboard-shortcuts.mdx +++ b/website/src/content/docs/reference/keyboard-shortcuts.mdx @@ -62,6 +62,10 @@ Opens the model picker. Shows: Switches between AI providers: - OpenCode Zen - OpenRouter +- Vercel AI Gateway +- Cloudflare AI Gateway +- Cloudflare Workers AI +- Custom models If the target provider isn't configured, prompts for API key. diff --git a/website/src/pages/index.astro b/website/src/pages/index.astro index 8c7bcab..dc10f08 100644 --- a/website/src/pages/index.astro +++ b/website/src/pages/index.astro @@ -29,7 +29,7 @@ import TerminalWindow from "../components/TerminalWindow.astro"; /> Documentation - GitHub - Issues + GitHub + Issues

- MIT License. Created by Austin Thesing + MIT License. Created by Austin Thesing