Skip to main content

Interface: LoopContext

Defined in: packages/agentos/src/orchestration/runtime/LoopController.ts:65

Execution context provided to the LoopController by the caller. Abstracts away the underlying LLM/GMI implementation so the loop logic remains provider-agnostic.

Properties

addToolResults()

addToolResults: (results) => void

Defined in: packages/agentos/src/orchestration/runtime/LoopController.ts:84

Feed tool results back into the conversation so the next generateStream call has access to them. Typically appends tool messages to the message list.

Parameters

results

LoopToolCallResult[]

Returns

void


executeTool()

executeTool: (toolCall) => Promise<LoopToolCallResult>

Defined in: packages/agentos/src/orchestration/runtime/LoopController.ts:78

Execute a single tool call and return its result. Implementations should never throw — instead return a result with success: false and a populated error field.

Parameters

toolCall

LoopToolCallRequest

Returns

Promise<LoopToolCallResult>


generateStream()

generateStream: () => AsyncGenerator<LoopChunk, LoopOutput, undefined>

Defined in: packages/agentos/src/orchestration/runtime/LoopController.ts:71

Async generator that streams chunks during a single LLM inference pass. Must return a LoopOutput as its generator return value (the value passed to the final done: true result from .next()).

Returns

AsyncGenerator<LoopChunk, LoopOutput, undefined>