RunConfig
type RunConfig = object;
Configures settings for the entire agent run.
Properties
Section titled “Properties”groupId?
Section titled “groupId?”optional groupId: string;
A grouping identifier to use for tracing, to link multiple traces from the same conversation or process. For example, you might use a chat thread ID.
handoffInputFilter?
Section titled “handoffInputFilter?”optional handoffInputFilter: HandoffInputFilter;
A global input filter to apply to all handoffs. If Handoff.inputFilter
is set, then that
will take precedence. The input filter allows you to edit the inputs that are sent to the new
agent. See the documentation in Handoff.inputFilter
for more details.
inputGuardrails?
Section titled “inputGuardrails?”optional inputGuardrails: InputGuardrail[];
A list of input guardrails to run on the initial run input.
model?
Section titled “model?”optional model: string | Model;
The model to use for the entire agent run. If set, will override the model set on every agent. The modelProvider passed in below must be able to resolve this model name.
modelProvider
Section titled “modelProvider”modelProvider: ModelProvider;
The model provider to use when looking up string model names. Defaults to OpenAI.
modelSettings?
Section titled “modelSettings?”optional modelSettings: ModelSettings;
Configure global model settings. Any non-null values will override the agent-specific model settings.
outputGuardrails?
Section titled “outputGuardrails?”optional outputGuardrails: OutputGuardrail<AgentOutputType<unknown>>[];
A list of output guardrails to run on the final output of the run.
traceId?
Section titled “traceId?”optional traceId: string;
A custom trace ID to use for tracing. If not provided, we will generate a new trace ID.
traceIncludeSensitiveData
Section titled “traceIncludeSensitiveData”traceIncludeSensitiveData: boolean;
Whether we include potentially sensitive data (for example: inputs/outputs of tool calls or LLM generations) in traces. If false, we’ll still create spans for these events, but the sensitive data will not be included.
traceMetadata?
Section titled “traceMetadata?”optional traceMetadata: Record<string, any>;
An optional dictionary of additional metadata to include with the trace.
tracingDisabled
Section titled “tracingDisabled”tracingDisabled: boolean;
Whether tracing is disabled for the agent run. If disabled, we will not trace the agent run.
workflowName?
Section titled “workflowName?”optional workflowName: string;
The name of the run, used for tracing. Should be a logical name for the run, like “Code generation workflow” or “Customer support agent”.