Loading preview…
Loading preview…
Lightweight ToolLoopAgent pattern for Anthropic ephemeral cache control through Vercel AI Gateway: cached system instructions with cacheControl and reports cache read/write tokens.
Loading preview…
Requirements, wiring steps, and what this pattern adds to your project.
Pick how you want to pull this pattern in — then wire env vars and routes the same way.
Install from the preview toolbar
Copy the install command above and run it in your project — Pro patterns include a short-lived token.
Add environment variables to .env.local
AI_GATEWAY_API_KEY
Point client fetches at your API routes
Replace preview `/view/.../api/...` paths with `/api/...` in the installed files.
Customize the agent and tool files
Adapt prompts, tools, and stop conditions for your product — Copy for AI in the toolbar helps seed that work.
Run your dev server and open the pattern route
Install dependencies if needed, then start the app and verify responses.
AI_GATEWAY_API_KEYGet keyAI SDK APIs
ToolLoopAgentgatewayproviderOptionsinstructionsstepCountIsProviders
app/page.tsxapp/layout.tsxapp/api/cache-anthropic/route.tslib/cache-anthropic-agent.tslib/build-cached-instructions.tslib/cache-metrics.tslib/stable-system-prompt.tslib/request-utils.tsREADME.mdnpm packages
5
Registry components
lib/build-cached-instructions.tsBuilds SystemModelMessage instructions with providerOptions.anthropic.cacheControl ephemeral breakpoint.
lib/cache-anthropic-agent.tsToolLoopAgent uses buildAnthropicCachedInstructions() as instructions (not messages).
Loading preview…
Early-bird pricing — limited time

Open on desktop for the interactive preview.
Lightweight ToolLoopAgent pattern for Anthropic ephemeral cache control through Vercel AI Gateway: cached system instructions with cacheControl and reports cache read/write tokens.