Defined in: [src/types/agent.ts:442](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L442) Result returned by the agent loop. ## Constructors ### Constructor ```ts new AgentResult(data): AgentResult; ``` Defined in: [src/types/agent.ts:507](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L507) #### Parameters | Parameter | Type | | --- | --- | | `data` | { `stopReason`: [`StopReason`](/pr-cms-5548/docs/api/typescript/StopReason/index.md); `lastMessage`: [`Message`](/pr-cms-5548/docs/api/typescript/Message/index.md); `invocationState`: [`InvocationState`](/pr-cms-5548/docs/api/typescript/InvocationState/index.md); `traces?`: [`AgentTrace`](/pr-cms-5548/docs/api/typescript/AgentTrace/index.md)\[\]; `metrics?`: [`AgentMetrics`](/pr-cms-5548/docs/api/typescript/AgentMetrics/index.md); `invocationContext?`: [`InvocationContext`](/pr-cms-5548/docs/api/typescript/InvocationContext/index.md); `structuredOutput?`: `output`<`ZodType`\>; `interrupts?`: [`Interrupt`](/pr-cms-5548/docs/api/typescript/Interrupt/index.md)\[\]; `checkpoint?`: `Checkpoint`; } | | `data.stopReason` | [`StopReason`](/pr-cms-5548/docs/api/typescript/StopReason/index.md) | | `data.lastMessage` | [`Message`](/pr-cms-5548/docs/api/typescript/Message/index.md) | | `data.invocationState` | [`InvocationState`](/pr-cms-5548/docs/api/typescript/InvocationState/index.md) | | `data.traces?` | [`AgentTrace`](/pr-cms-5548/docs/api/typescript/AgentTrace/index.md)\[\] | | `data.metrics?` | [`AgentMetrics`](/pr-cms-5548/docs/api/typescript/AgentMetrics/index.md) | | `data.invocationContext?` | [`InvocationContext`](/pr-cms-5548/docs/api/typescript/InvocationContext/index.md) | | `data.structuredOutput?` | `output`<`ZodType`\> | | `data.interrupts?` | [`Interrupt`](/pr-cms-5548/docs/api/typescript/Interrupt/index.md)\[\] | | `data.checkpoint?` | `Checkpoint` | #### Returns `AgentResult` ## Properties ### type ```ts readonly type: "agentResult"; ``` Defined in: [src/types/agent.ts:443](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L443) --- ### stopReason ```ts readonly stopReason: StopReason; ``` Defined in: [src/types/agent.ts:448](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L448) The stop reason from the final model response. --- ### lastMessage ```ts readonly lastMessage: Message; ``` Defined in: [src/types/agent.ts:453](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L453) The last message added to the messages array. --- ### traces? ```ts readonly traces?: AgentTrace[]; ``` Defined in: [src/types/agent.ts:459](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L459) Local execution traces collected during the agent invocation. Contains timing and hierarchy of operations within the agent loop. --- ### structuredOutput? ```ts readonly structuredOutput?: output; ``` Defined in: [src/types/agent.ts:465](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L465) The validated structured output from the LLM, if a schema was provided. Type represents any validated Zod schema output. --- ### metrics? ```ts readonly metrics?: AgentMetrics; ``` Defined in: [src/types/agent.ts:471](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L471) Aggregated metrics for the agent’s loop execution. Tracks cycle counts, token usage, tool execution stats, and model latency. --- ### invocationContext? ```ts readonly invocationContext?: InvocationContext; ``` Defined in: [src/types/agent.ts:482](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L482) The invocation context this call ran in. Its `usage` covers the whole request (this agent, its nested calls, and auxiliary calls), unlike [metrics](#metrics), which covers this agent only; for a nested call that set its own limits, it is that call’s context and covers its share. Pass it as [InvokeOptions.invocationContext](/pr-cms-5548/docs/api/typescript/InvokeOptions/index.md#invocationcontext) to continue on the same limits and usage. It is live, so work that finishes after this call returns (for example a background task) still adds to it. --- ### invocationState ```ts readonly invocationState: InvocationState; ``` Defined in: [src/types/agent.ts:490](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L490) Per-invocation state passed into the agent, threaded through hooks and tools, and surfaced here at the end of the invocation. See [InvocationState](/pr-cms-5548/docs/api/typescript/InvocationState/index.md) for details. Always defined — defaults to `{}` when no `invocationState` was provided in [InvokeOptions](/pr-cms-5548/docs/api/typescript/InvokeOptions/index.md). --- ### interrupts? ```ts readonly interrupts?: Interrupt[]; ``` Defined in: [src/types/agent.ts:496](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L496) Interrupts that caused the agent to stop, when `stopReason` is `'interrupt'`. Contains the unanswered interrupts that require human input to resume. --- ### checkpoint? ```ts readonly checkpoint?: Checkpoint; ``` Defined in: [src/types/agent.ts:505](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L505) **`Experimental`** Checkpoint captured when the agent paused for durable execution. Populated only when `stopReason` is `'checkpoint'`. See the experimental checkpoint module for usage. ## Accessors ### contextSize #### Get Signature ```ts get contextSize(): number; ``` Defined in: [src/types/agent.ts:546](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L546) The total prompt the model processed on the last invocation, including cached tokens. Convenience accessor that delegates to `metrics.latestContextSize`. Returns `undefined` when no metrics or invocations are available. ##### Returns `number` --- ### projectedContextSize #### Get Signature ```ts get projectedContextSize(): number; ``` Defined in: [src/types/agent.ts:556](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L556) Projected context size for the next model call (total prompt including cached tokens plus the generated output from the last call). Convenience accessor that delegates to `metrics.projectedContextSize`. Returns `undefined` when no metrics or invocations are available. ##### Returns `number` ## Methods ### toJSON() ```ts toJSON(): object; ``` Defined in: [src/types/agent.ts:571](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L571) Custom JSON serialization that excludes traces, metrics, invocationContext, and invocationState. Traces and metrics are excluded to avoid sending large payloads over the wire in API responses; `invocationContext` is excluded because it is live and can still change; `invocationState` is excluded because its values are caller-owned and may not be serializable (see [InvocationState](/pr-cms-5548/docs/api/typescript/InvocationState/index.md)). All four remain accessible via their properties for debugging. #### Returns `object` Object representation for safe serialization --- ### toString() ```ts toString(): string; ``` Defined in: [src/types/agent.ts:591](https://github.com/strands-agents/harness-sdk/blob/main/strands-ts/src/types/agent.ts#L591) Extracts a string representation of the result. Priority order: 1. `interrupts` serialized as JSON, if any are present 2. `structuredOutput` serialized as JSON 3. Text from `textBlock`, `reasoningBlock`, and `citationsBlock` content blocks #### Returns `string` String representation of the result: JSON for interrupts/structuredOutput, or text content joined by newlines.