@netlify/agent-runner-cli 1.90.1 → 1.90.2

package/dist/skills/netlify-ai-gateway/SKILL.md

@@ -1,10 +1,12 @@
 ---
 name: netlify-ai-gateway
-description: Use Netlify AI Gateway for AI inference in Netlify Functions and server-side code. Use when adding AI/LLM features with OpenAI, Anthropic, or Google Gemini without managing API keys.
+description: Use Netlify AI Gateway for AI inference in Netlify Functions and server-side code. Use when adding AI/LLM features with OpenAI, Anthropic, or Google Gemini without managing API keys. Must be read before selecting or changing any AI model. Contains the list of supported models.
 ---
 
 # Netlify AI Gateway
 
+> **IMPORTANT:** Only use models listed in the "Available Models" section below. AI Gateway does not support every model a provider offers. Using an unsupported model will cause runtime errors.
+
 Zero-config AI inference for Netlify projects. Netlify automatically injects environment variables so official
 provider SDKs work without API keys or configuration.
 
@@ -87,7 +89,7 @@ const response = await openai.responses.create({
 console.log(response.output_text)
 ```
 
-### Google Gemini
+### Gemini
 
 ```bash
 npm install @google/genai
@@ -201,24 +203,6 @@ for (const item of response.output) {
 }
 ```
 
-### Google Gemini (Imagen)
-
-```typescript
-import { GoogleGenAI } from '@google/genai'
-
-const ai = new GoogleGenAI({})
-
-const response = await ai.models.generateImages({
-  model: 'imagen-4.0-generate-001',
-  prompt: 'A cute otter in a river',
-  config: { numberOfImages: 1 },
-})
-
-for (const image of response.generatedImages) {
-  const imageBytes = image.image.imageBytes
-}
-```
-
 ## Netlify Functions
 
 Full example of a Netlify Function using AI Gateway:
@@ -354,64 +338,13 @@ const response = await fetch(`${process.env.ANTHROPIC_BASE_URL}/v1/messages`, {
 
 ## Available Models
 
-Key models per provider. For the latest list, see https://docs.netlify.com/build/ai-gateway/overview/.
-
-### Anthropic
-
-- `claude-opus-4-6`
-- `claude-opus-4-5-20251101`
-- `claude-opus-4-1-20250805`
-- `claude-sonnet-4-5-20250929`
-- `claude-sonnet-4-20250514`
-- `claude-haiku-4-5-20251001`
-- `claude-3-7-sonnet-20250219`
-- `claude-3-5-haiku-20241022`
-
-### OpenAI
+For the latest list, see https://docs.netlify.com/build/ai-gateway/overview/.
 
-- `gpt-5.2`
-- `gpt-5.1`
-- `gpt-5.1-codex`
-- `gpt-5`
-- `gpt-5-mini`
-- `gpt-5-nano`
-- `gpt-4.1`
-- `gpt-4.1-mini`
-- `gpt-4.1-nano`
-- `gpt-4o`
-- `gpt-4o-mini`
-- `o3`
-- `o3-mini`
-- `o4-mini`
-- `gpt-image-1` (image generation)
-- `codex-mini-latest`
-
-### Google Gemini
-
-- `gemini-3-pro-preview`
-- `gemini-3-flash-preview`
-- `gemini-2.5-pro`
-- `gemini-2.5-flash`
-- `gemini-2.5-flash-lite`
-- `gemini-2.0-flash`
-- `gemini-2.0-flash-lite`
-- `imagen-4.0-generate-001` (image generation)
-- `veo-3.0-generate-preview` (video generation)
+<!-- AVAILABLE_MODELS -->
 
 ## Rate Limits
 
-Tokens per minute (TPM) are scoped per **account** across all projects. Both input and output tokens count.
-For Anthropic, cached tokens are excluded; for other providers, cached tokens are included.
-For the latest limits, see https://docs.netlify.com/build/ai-gateway/overview/.
-
-| Model | Free | Personal | Pro |
-|-------|------|----------|-----|
-| claude-sonnet-4-5-20250929 | 18,000 | 90,000 | 180,000 |
-| gpt-5 | 18,000 | 90,000 | 180,000 |
-| gpt-4o-mini | 250,000 | 500,000 | 750,000 |
-| gemini-2.5-pro | 24,000 | 120,000 | 240,000 |
-
-Set up rate limiting rules on your functions to prevent abuse from client-side callers.
+Tokens per minute (TPM) are scoped per **account** across all projects. For current limits per model and plan tier, see https://docs.netlify.com/build/ai-gateway/overview/.
 
 ## Limitations
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@netlify/agent-runner-cli",
   "type": "module",
-  "version": "1.90.1",
+  "version": "1.90.2",
   "description": "CLI tool for running Netlify agents",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",