Agent( )

Pattern

Call Options: prepareCall

Dynamically configure one ToolLoopAgent per request with callOptionsSchema and prepareCall. A customer-support agent rewrites instructions, gates tools, tunes reasoning effort, and injects RAG context based on account tier and urgency.

IntermediateJun 2026View the full pattern on desktop
Call Options: prepareCall preview

Problems solved

  • Configure one ToolLoopAgent per request with prepareCall
  • Inject per-user RAG context into instructions at runtime
  • Gate tools by account tier with activeTools
  • Tune reasoning effort from request urgency

Use cases

  • Multi-tier customer support agents
  • Per-user RAG injection
  • Role-based tool access
  • Runtime provider option selection

AI SDK APIs

ToolLoopAgentcallOptionsSchemaprepareCallactiveToolsproviderOptionstoolgateway

Tags

aiagentscall-optionsprepare-calldynamic-configragtool-loop-agentai-sdkagent-api

Requirements

Node.js
24+
Memory
512MB
Other
  • OpenAI API key

Environment variables

External services

openai

Ready to use?

View the full interactive pattern with live preview and copy the source code.

View the pattern on desktop

Related patterns

Tool Context: experimental_contextInject request-scoped context (user identity, database handles, session) into ToolLoopAgent tools via experimental_context, so the model never supplies sensitive identity in tool inputs.Jun 2026
Loop Control: stopWhenDemonstrate ToolLoopAgent loop control with stopWhen. Covers stepCountIs, hasToolCall, combined conditions, and a custom StopCondition with step timeline visualization.Jun 2026
PrepareStep: Trim Message HistoryDemonstrate ToolLoopAgent prepareStep for trimming long message history. Pre-seeded 24-message conversation shows context compression on the first run with per-step trim telemetry.Jun 2026
Structured Agent Output: Output.choiceDemonstrate structured agent outputs using ToolLoopAgent with Output.choice. Constrain agent outputs to predefined choices for predictable, type-safe responses.Nov 2025