Page through the steps of one turn of a session's trace, optionally only the failed ones.

GET

/v1/sessions/{session_id}/trace/turns/{turn}/steps

const url = 'https://app.everruns.com/api/v1/sessions/example/trace/turns/example/steps';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url https://app.everruns.com/api/v1/sessions/example/trace/turns/example/steps

Parameters

Path Parameters

session_id

required

string

Prefixed public identifier

turn

required

string

Prefixed public identifier

Query Parameters

from_step

integer format: int32

First step of the range, inclusive. Defaults to 1.

to_step

integer format: int32

Last step of the range, inclusive. Defaults to the turn’s last step.

errors_only

boolean

Only failed steps.

limit

integer format: int32

Steps per page, 1 to 500. Defaults to 100.

Responses

200

Success

application/json

A page of plain steps of one turn.

object

next_step

Step number to continue from, when more remain in the range.

integer | null format: int32

steps

required

Steps in step order.

Array<object>

A model call, tool call, approval, sub-agent or message. Empty fields are left out: a page carries hundreds of these.

object

child_session_id

Session a spawn_agent call started.

string | null

duration_ms

Wall time of the step; absent while running.

integer | null format: int64

end_sequence

Last event sequence of the step.

integer | null format: int32

input_tokens

Prompt tokens of a model call.

integer | null format: int32

kind

required

model, answer, tool, approval, agent or send.

string

model

Model that served the call, for model steps.

string | null

name

Tool name, or model for model calls.

string | null

narration

What the model said alongside this call (model calls and answers).

string | null

offset_ms

required

Start relative to the turn’s start.

integer format: int64

output_tokens

Completion tokens of a model call.

integer | null format: int32

requested_tool_call_ids

Tool calls this model call asked for.

Array<string>

result

Short result or error.

string | null

start_sequence

required

First event sequence of the step.

integer format: int32

started_at

required

When the step started.

string format: date-time

status

required

running, success, error or cancelled.

string

step

required

Per-turn step number, 1-based.

integer format: int32

target

What the call acted on, from the tool’s narration.

string | null

tool_call_id

Tool call identifier, for tool steps.

string | null

turn

required

Turn the step belongs to.

integer format: int32

Example

{
  "next_step": 101,
  "steps": [
    {
      "duration_ms": 269,
      "end_sequence": 21,
      "kind": "tool",
      "model": "gpt-6.1-sol",
      "name": "bash",
      "offset_ms": 3010,
      "start_sequence": 14,
      "status": "success",
      "step": 2,
      "tool_call_id": "call_PzDcvnFaUll8os3tPhWj",
      "turn": 1240
    }
  ]
}