Agent( )

Pattern

Loop Control: stopWhen

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

IntermediateJun 2026View the full pattern on desktop
Loop Control: stopWhen preview

Problems solved

  • Stop agent loops with stepCountIs
  • Halt when a specific tool is called via hasToolCall
  • Combine multiple stopWhen conditions
  • Implement custom StopCondition logic over step history

Use cases

  • Budgeting agent steps in long tool loops
  • Stopping when a completion tool fires
  • Preventing runaway tool-calling agents
  • Visualizing step timelines for loop control

AI SDK APIs

ToolLoopAgentstopWhenstepCountIshasToolCallStopConditiontoolgateway

Tags

aiagentsloop-controlstop-whenstep-count-ishas-tool-calltool-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

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 pattern →
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 pattern →
Call Options: prepareCall preview

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.

aiagents+7
View pattern →
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 pattern →