diff --git a/AGENTS.md b/AGENTS.md index 55bc8f7b6..2f8f5a548 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -28,7 +28,7 @@ Target-specific workflows built on the same engine: - **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control. ```bash curl -sSL https://strix.ai/install | bash # install - export STRIX_LLM="openrouter/z-ai/glm-5.3" # any LiteLLM model id, or openai/zai/glm-5.3 with LLM_API_BASE=https://ai-gateway.vercel.sh/v1 + export STRIX_LLM="openrouter/z-ai/glm-5.3" # any LiteLLM model id, or vercel_ai_gateway/zai/glm-5.3 export LLM_API_KEY="" strix -n -t ./ --scan-mode quick --max-budget 10 # headless scan; always use -n ``` diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 84a3230c2..1a1e40a64 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -31,7 +31,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g 3. **Configure your LLM provider** ```bash - export STRIX_LLM="openrouter/z-ai/glm-5.3" # or openai/zai/glm-5.3 with LLM_API_BASE=https://ai-gateway.vercel.sh/v1 + export STRIX_LLM="openrouter/z-ai/glm-5.3" # or vercel_ai_gateway/zai/glm-5.3 export LLM_API_KEY="your-api-key" ``` diff --git a/docs/index.mdx b/docs/index.mdx index b3f840135..fff6deaae 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -79,9 +79,8 @@ Strix uses a graph of specialized agents for comprehensive security testing: curl -sSL https://strix.ai/install | bash # Configure -export STRIX_LLM="openai/zai/glm-5.3" +export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3" export LLM_API_KEY="your-api-key" -export LLM_API_BASE="https://ai-gateway.vercel.sh/v1" # Scan strix --target ./your-app diff --git a/docs/llm-providers/overview.mdx b/docs/llm-providers/overview.mdx index ce285f6e2..c00351271 100644 --- a/docs/llm-providers/overview.mdx +++ b/docs/llm-providers/overview.mdx @@ -11,7 +11,7 @@ Set your model and API key: | Model | Provider | Configuration | | --------------------- | ------------------------- | -------------------------------- | -| GLM-5.3 (recommended) | Vercel AI Gateway | `openai/zai/glm-5.3` | +| GLM-5.3 (recommended) | Vercel AI Gateway | `vercel_ai_gateway/zai/glm-5.3` | | GLM-5.3 (recommended) | OpenRouter | `openrouter/z-ai/glm-5.3` | | GPT-6.1 Sol | OpenAI | `openai/gpt-6.1-sol` | | Claude Opus 5.5 | Anthropic | `anthropic/claude-opus-5-5` | @@ -27,9 +27,8 @@ Frontier OpenAI, Anthropic and Gemini models need a cyber access program for sec ```bash Vercel AI Gateway -export STRIX_LLM="openai/zai/glm-5.3" +export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3" export LLM_API_KEY="your-api-key" -export LLM_API_BASE="https://ai-gateway.vercel.sh/v1" ``` ```bash OpenRouter diff --git a/docs/llm-providers/vercel-ai-gateway.mdx b/docs/llm-providers/vercel-ai-gateway.mdx index f661b4b9e..5937a2385 100644 --- a/docs/llm-providers/vercel-ai-gateway.mdx +++ b/docs/llm-providers/vercel-ai-gateway.mdx @@ -10,30 +10,29 @@ description: "Configure Strix with models through Vercel AI Gateway" Create an [AI Gateway API key](https://vercel.com/docs/ai-gateway/authentication-and-byok), then configure Strix: ```bash -export STRIX_LLM="openai/zai/glm-5.3" +export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3" export LLM_API_KEY="your-ai-gateway-api-key" -export LLM_API_BASE="https://ai-gateway.vercel.sh/v1" ``` -The first `openai/` segment tells Strix to use its OpenAI-compatible client. The remaining value is the [AI Gateway model ID](https://vercel.com/docs/ai-gateway/models-and-providers). +The `vercel_ai_gateway/` prefix selects the Gateway. The remaining value is the [AI Gateway model ID](https://vercel.com/docs/ai-gateway/models-and-providers). ## Available Models -Access any model on the Gateway using the format `openai//`: +Access any model on the Gateway using the format `vercel_ai_gateway//`: | Model | Configuration | |-------|---------------| -| GLM-5.3 (recommended) | `openai/zai/glm-5.3` | -| GPT-6.1 Sol | `openai/openai/gpt-6.1-sol` | -| GPT-6 Astra | `openai/openai/gpt-6-astra` | -| Claude Opus 5.5 | `openai/anthropic/claude-opus-5.5` | -| Claude Sonnet 5.5 | `openai/anthropic/claude-sonnet-5.5` | -| Gemini 4 Argon | `openai/google/gemini-4-argon` | -| Gemini 3.8 Flash | `openai/google/gemini-3.8-flash` | -| DeepSeek V4.1 Flash | `openai/deepseek/deepseek-v4.1-flash-1017` | -| DeepSeek V4 Pro | `openai/deepseek/deepseek-v4-pro` | -| Kimi K3.1 Pro | `openai/moonshotai/kimi-k3.1-pro` | -| GLM-5.3 Flash | `openai/zai/glm-5.3-flash` | +| GLM-5.3 (recommended) | `vercel_ai_gateway/zai/glm-5.3` | +| GPT-6.1 Sol | `vercel_ai_gateway/openai/gpt-6.1-sol` | +| GPT-6 Astra | `vercel_ai_gateway/openai/gpt-6-astra` | +| Claude Opus 5.5 | `vercel_ai_gateway/anthropic/claude-opus-5.5` | +| Claude Sonnet 5.5 | `vercel_ai_gateway/anthropic/claude-sonnet-5.5` | +| Gemini 4 Argon | `vercel_ai_gateway/google/gemini-4-argon` | +| Gemini 3.8 Flash | `vercel_ai_gateway/google/gemini-3.8-flash` | +| DeepSeek V4.1 Flash | `vercel_ai_gateway/deepseek/deepseek-v4.1-flash-1017` | +| DeepSeek V4 Pro | `vercel_ai_gateway/deepseek/deepseek-v4-pro` | +| Kimi K3.1 Pro | `vercel_ai_gateway/moonshotai/kimi-k3.1-pro` | +| GLM-5.3 Flash | `vercel_ai_gateway/zai/glm-5.3-flash` | OpenAI, Anthropic and Gemini models keep their provider safeguards on the Gateway. Security testing with them needs [Daybreak](https://openai.com/daybreak/), [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) or [Fairwind](https://deepmind.google/fairwind-program/) access. diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx index 866fdbc23..4838923c4 100644 --- a/docs/quickstart.mdx +++ b/docs/quickstart.mdx @@ -29,9 +29,8 @@ Set your LLM provider. We recommend GLM-5.3 through [Vercel AI Gateway](/llm-pro ```bash Vercel AI Gateway -export STRIX_LLM="openai/zai/glm-5.3" +export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3" export LLM_API_KEY="your-api-key" -export LLM_API_BASE="https://ai-gateway.vercel.sh/v1" ``` ```bash OpenRouter