runsSteps

List Steps For Run

Get messages associated with a run with filtering options. Args: run_id: ID of the run before: A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. after: A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. limit: Maximum number of steps to return order: Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order. Returns: A list of steps associated with the run.

Path parameters

run_idstringRequired

Headers

AuthorizationstringRequired

Header authentication of the form Bearer <token>

Query parameters

beforestring or nullOptional
Cursor for pagination
afterstring or nullOptional
Cursor for pagination
limitinteger or nullOptionalDefaults to 100
Maximum number of messages to return
orderstringOptionalDefaults to desc

Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order.

Response

Successful Response
idstring
The id of the step. Assigned by the database.
originstring or null
The surface that this agent step was initiated from.
provider_idstring or null
The unique identifier of the provider that was configured for this step
job_idstring or null
The unique identifier of the job that this step belongs to. Only included for async calls.
agent_idstring or null
The ID of the agent that performed the step.
provider_namestring or null
The name of the provider used for this step.
provider_categorystring or null
The category of the provider used for this step.
modelstring or null
The name of the model used for this step.
model_endpointstring or null
The model endpoint url used for this step.
context_window_limitinteger or null
The context window limit configured for this step.
completion_tokensinteger or null
The number of tokens generated by the agent during this step.
prompt_tokensinteger or null
The number of tokens in the prompt during this step.
total_tokensinteger or null
The total number of tokens processed by the agent during this step.
completion_tokens_detailsmap from strings to any or null
Metadata for the agent.
stop_reasonenum or null
The stop reason associated with the step.
tagslist of strings or null
Metadata tags.
tidstring or null
The unique identifier of the transaction that processed this step.
trace_idstring or null
The trace id of the agent step.
feedbackenum or null
The feedback for this step. Must be either 'positive' or 'negative'.
Allowed values:
project_idstring or null

The project that the agent that executed this step belongs to (cloud only).

error_typestring or null

The type/class of the error that occurred

error_datamap from strings to any or null
Error details including message, traceback, and additional context
statusenum or null

Step status: pending, success, or failed

Allowed values:
messageslist of objects or nullDeprecated

The messages generated during this step. Deprecated: use GET /v1/steps/{step_id}/messages endpoint instead

Errors