Loading pattern preview
BlocksTools & Utilities
Tool Input Lifecycle Hooks
Tool Input Lifecycle Hooks
Explore tool input lifecycle hooks: onInputStart, onInputDelta, and onInputAvailable. See how to track tool input generation in real-time during streaming.
Use this when you want UI state, like a spinner or progress label, to react to tool input starting, streaming, and becoming fully available.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Observe tool input generation with onInputStart
- Stream partial tool arguments via onInputDelta
- React when full tool input becomes available with onInputAvailable
Use cases
Products and workflows this pattern is designed to support.
- Debugging streaming tool argument construction
- UI spinners tied to tool input lifecycle events
- Teaching AI SDK tool input hooks
- Monitoring long tool-argument generation
Compare with
Similar patterns, and when each one is the better fit.
Multi-Step Tool PatternUse this when a chat agent must call several typed tools in a row, feeding each result into the next step, with a step limit to stop runaway loops.
Tool ApprovalUse this when a destructive action, such as deleting a file, needs an in-chat confirm or deny step built only on the AI SDK's own approval flow.
Tool API ContextUse this when you call generateText or streamText directly and want one tool definition to adapt to each user's preferences or session settings.
Loop Control: stopWhenUse this when you are tuning at which step an agent loop halts and want to see each step on a timeline as your stop rules trigger.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
OPENAI_API_KEYGet key
Capabilities
AI SDK APIs
streamTextconvertToModelMessagestooluseChatonInputStartonInputDeltaonInputAvailableProviders
OpenAI
Files added
6 files
app/page.tsxapp/layout.tsxapp/api/tool-input-lifecycle/route.tscomponents/input-lifecycle-demo.tsxtools/weather.tstools/weather-ui.tsx
Dependencies
15 total
npm packages
7AISDKshadcn/uilucide-reactNext.jsReactstreamdownZod
Registry components
alertemptyinput-groupseparatormessage-scrollermessagebubbletooltip
Critical files
1 file
tools/weather.tsWeather tool demonstrating all three tool input lifecycle hooks: onInputStart, onInputDelta, and onInputAvailable. Core pattern for monitoring tool input generation.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 512MB
