Agent( )
Pattern
INT·Jun 26

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.

View Full Pattern on Desktop
Call Options: prepareCall preview

Problems Solved

  • Configure one agent dynamically per request instead of many agents
  • Inject per-user RAG context into instructions at runtime
  • Gate tools by account tier with activeTools
  • Tune reasoning effort by request urgency

Use Cases

  • Multi-tier customer support agents
  • Per-user RAG injection
  • Role-based tool access
  • Runtime model and 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 Pattern on Desktop

Related Patterns

Loop Control: stopWhen preview

Loop Control: stopWhen

Demonstrate ToolLoopAgent loop control with stopWhen. Covers stepCountIs, hasToolCall, combined conditions, and a custom StopCondition with step timeline visualization.

aiagents+7
View →
PrepareStep: Trim Message History preview

PrepareStep: Trim Message History

Demonstrate ToolLoopAgent prepareStep for trimming long message history. Pre-seeded 24-message conversation shows context compression on the first run with per-step trim telemetry.

aiagents+6
View →
Tool Context: experimental_context preview

Tool Context: experimental_context

Inject request-scoped context (user identity, database handles, session) into ToolLoopAgent tools via experimental_context, so the model never supplies sensitive identity in tool inputs.

aiagents+7
View →
Structured Agent Output: Output.choice preview

Structured Agent Output: Output.choice

Demonstrate structured agent outputs using ToolLoopAgent with Output.choice. Constrain agent outputs to predefined choices for predictable, type-safe responses.

aiagents+5
View →
End of Pattern