Vercel AI SDK 4.x Core, `streamText` & Multi-Step Tool Calling Skill

Build streaming, tool-calling AI agents in TypeScript using the Vercel AI SDK (`streamText`, `generateObject`, `maxSteps`, and provider-agnostic model rout

---
name: vercel-ai-sdk
description: Build streaming, tool-calling AI agents in TypeScript using the Vercel AI SDK (`streamText`, `generateObject`, `maxSteps`, and provider-agnostic model routing). Use when working with Vercel AI SDK, TypeScript, Streaming UI, Zod Schemas.
triggers:
  - vercel ai sdk
  - vercel ai sdk
  - typescript
---

# Vercel AI SDK 4.x Core, `streamText` & Multi-Step Tool Calling Skill

## 1. When to Use This Skill
Load `skill-vercel-ai-sdk` whenever an engineering or operations task involves **Vercel AI SDK, TypeScript, Streaming UI, Zod Schemas**. Specifically:
- Build streaming, tool-calling AI agents in TypeScript using the Vercel AI SDK (`streamText`, `generateObject`, `maxSteps`, and provider-agnostic model routing).
- Designing, reviewing, or debugging production configurations without guesswork or deprecated flags.
- Running deterministic pre-flight and post-execution verification checks before reporting completion.

## 2. Prerequisites & Required Environment
- **Target Stack:** Vercel AI SDK, TypeScript, Streaming UI, Zod Schemas
- **Permissions:** Read-only inspection by default; ask for explicit confirmation before executing destructive mutations or production deployments.
- **Reference Repository:** `https://sdk.vercel.ai/docs`

## 3. Step-by-Step Execution Playbook
1. **Context & Configuration Discovery:**
   Inspect existing project manifests (`package.json`, `wrangler.jsonc`, schema files, or environment declarations) before proposing changes. Never overwrite existing bindings or credentials blindly.
2. **Deterministic Implementation:**
   Apply the canonical patterns for **Vercel AI SDK**:
   - Enforce strict schema/type validation at every external boundary.
   - Include explicit error handling, structured logging, and idempotency keys on all mutating calls.
   - Keep secrets in environment variables or secret stores—never hardcode tokens in source files.
3. **Verification & Regression Gate:**
   Run the verification commands below and inspect both exit codes and output payloads before marking the task complete.

## 4. Reference Commands & CLI Workflow
```bash
npm i ai @ai-sdk/openai @ai-sdk/anthropic
npx next build
```

## 5. Edge Cases & Anti-Hallucination Guardrails
- **Zero Unverified Claims:** Never claim a deployment, migration, or API call succeeded without inspecting the command output or HTTP status code.
- **Rollback Readiness:** Always record the previous state or migration version so changes can be reverted cleanly if downstream health checks fail.

Synthesized Engineering Blueprint & Setup Guide