The PromptResult class wraps every response from TestAgent.prompt(). It provides methods to inspect tool calls, performance metrics, errors, and conversation history.
Import
// PromptResult is returned by TestAgent.prompt()
// You don't import it directly
const result = await agent.prompt("...");
// result is a PromptResult
Text Response
text
The final text response from the LLM.
Value
string - The assistant’s text response. Empty string if no text response.
Example
const result = await agent.prompt("What is 2 + 2?");
console.log(result.text); // "2 + 2 equals 4."
Returns the names of all tools that were called.
Returns
string[] - Array of tool names in call order.
Example
const result = await agent.prompt("Add 2 and 3, then multiply by 4");
console.log(result.toolsCalled()); // ["add", "multiply"]
Checks if a specific tool was called.
hasToolCall(toolName: string): boolean
Parameters
| Parameter | Type | Description |
|---|
toolName | string | The tool name to check |
Returns
boolean - true if the tool was called.
Example
if (result.hasToolCall("add")) {
console.log("Addition was performed");
}
Returns detailed information about all tool calls.
getToolCalls(): ToolCall[]
Returns
ToolCall[] - Array of tool call objects.
| Property | Type | Description |
|---|
toolName | string | Name of the tool |
arguments | Record<any, any> | Arguments passed to the tool |
Example
const calls = result.getToolCalls();
for (const call of calls) {
console.log(`${call.toolName}(${JSON.stringify(call.arguments)})`);
}
// add({"a":2,"b":3})
// multiply({"a":5,"b":4})
Returns the arguments passed to a specific tool.
getToolArguments(toolName: string): Record<string, unknown> | undefined
Parameters
| Parameter | Type | Description |
|---|
toolName | string | The tool name |
Returns
Record<string, unknown> | undefined - The arguments, or undefined if tool wasn’t called.
If the tool was called multiple times, returns arguments from the first call. Use getToolCalls() to access all calls.
Example
const args = result.getToolArguments("add");
console.log(args); // { a: 2, b: 3 }
Error Handling
hasError()
Checks if an error occurred.
Returns
boolean - true if an error occurred.
Example
if (result.hasError()) {
console.error("Something went wrong");
}
getError()
Returns the error message if one occurred.
getError(): string | undefined
Returns
string | undefined - The error message, or undefined if no error.
Example
if (result.hasError()) {
console.error("Error:", result.getError());
}
Latency Metrics
e2eLatencyMs()
Total wall-clock time for the prompt.
Returns
number - Milliseconds.
llmLatencyMs()
Time spent waiting for LLM API responses.
Returns
number - Milliseconds.
mcpLatencyMs()
Time spent executing MCP tools.
Returns
number - Milliseconds.
getLatency()
Returns the complete latency breakdown.
getLatency(): LatencyBreakdown
Returns
interface LatencyBreakdown {
e2eMs: number; // Total time
llmMs: number; // LLM API time
mcpMs: number; // Tool execution time
}
Example
const latency = result.getLatency();
console.log(`Total: ${latency.e2eMs}ms`);
console.log(`LLM: ${latency.llmMs}ms`);
console.log(`Tools: ${latency.mcpMs}ms`);
Token Usage
totalTokens()
Total tokens used (input + output).
Tokens used for input (prompt + context).
outputTokens()
Tokens generated by the LLM.
Example
console.log(`Input: ${result.inputTokens()}`);
console.log(`Output: ${result.outputTokens()}`);
console.log(`Total: ${result.totalTokens()}`);
Conversation History
getMessages()
Returns the full conversation as a CoreMessage[] array.
getMessages(): CoreMessage[]
Returns
CoreMessage[] - The full conversation message format used by the SDK.
Example
const messages = result.getMessages();
for (const msg of messages) {
console.log(`[${msg.role}]:`, msg.content);
}
getUserMessages()
Returns only user messages.
getUserMessages(): CoreMessage[]
getAssistantMessages()
Returns only assistant messages.
getAssistantMessages(): CoreMessage[]
Returns only tool result messages.
getToolMessages(): CoreMessage[]
Example
const toolMsgs = result.getToolMessages();
for (const msg of toolMsgs) {
console.log("Tool result:", msg.content);
}
Returns HTML snapshot payloads captured during tool execution for MCP Apps (one entry per relevant tool call when replay data was collected).
getWidgetSnapshots(): EvalWidgetSnapshotInput[]
Returns
EvalWidgetSnapshotInput[] — metadata plus inline HTML (before upload) or storage ids after reporting. Empty if no MCP App tools ran or if TestAgent was created without mcpClientManager.
Why the manager matters
MCP App UIs reference HTML via ui.resourceUri. That HTML is fetched with MCP resources/read, which only the connected MCPClientManager can perform. The model’s tool result is not a substitute for that document, so getWidgetSnapshots() stays empty unless you pass the same manager into new TestAgent({ …, mcpClientManager: manager }).
When you report results to MCPJam (for example via createEvalRunReporter or PromptResult.toEvalResult()), snapshots are uploaded and linked from the trace so the dashboard can replay widgets offline.
Example
const result = await agent.prompt("Open the chart widget");
const snapshots = result.getWidgetSnapshots();
console.log("Snapshots:", snapshots.length);
// After reporting, snapshots are merged into each eval result's trace on MCPJam
toEvalResult()
Builds an EvalResultInput for MCPJam reporting (messages, spans, tool calls, tokens, optional widget snapshots).
toEvalResult(
options?: Partial<Omit<EvalResultInput, "actualToolCalls" | "tokens" | "trace">> & {
failOnToolError?: boolean;
},
): EvalResultInput
passed field combines your explicit or inferred structural outcome with tool execution checks (see Tool execution and passed): by default, failures in the trace (MCP isError, errored tool spans, error-shaped tool-results) force passed: false even if you pass passed: true in options. Set failOnToolError: false in options to keep structural / explicit passed only.
See Tool execution and passed in the eval reporting reference.
Using as Context
Pass PromptResult as context for multi-turn conversations.
const r1 = await agent.prompt("Create a project");
// Single result as context
const r2 = await agent.prompt("Add a task", { context: r1 });
// Multiple results as context
const r3 = await agent.prompt("Show summary", { context: [r1, r2] });
Complete Example
const result = await agent.prompt("Add 100 and 200");
// Response
console.log("Text:", result.text);
// Tool calls
console.log("Tools:", result.toolsCalled());
console.log("Has add?", result.hasToolCall("add"));
console.log("Add args:", result.getToolArguments("add"));
for (const call of result.getToolCalls()) {
console.log(` ${call.toolName}:`, call.arguments);
}
// Errors
if (result.hasError()) {
console.error("Error:", result.getError());
}
// Performance
console.log("Latency:", result.e2eLatencyMs(), "ms");
console.log(" LLM:", result.llmLatencyMs(), "ms");
console.log(" Tools:", result.mcpLatencyMs(), "ms");
// Tokens
console.log("Tokens:", result.totalTokens());
console.log(" Input:", result.inputTokens());
console.log(" Output:", result.outputTokens());
// History
console.log("Messages:", result.getMessages().length);
