List Steps | Letta

1 from letta_client import Letta 2 3 client = Letta( 4 token="YOUR_TOKEN", 5 ) 6 client.steps.list()

1 [ 2 { 3 "id": "foo", 4 "origin": "foo", 5 "provider_id": "foo", 6 "job_id": "foo", 7 "agent_id": "foo", 8 "provider_name": "foo", 9 "provider_category": "foo", 10 "model": "foo", 11 "model_endpoint": "foo", 12 "context_window_limit": 42, 13 "completion_tokens": 42, 14 "prompt_tokens": 42, 15 "total_tokens": 42, 16 "completion_tokens_details": {}, 17 "tags": [ 18 "foo" 19 ], 20 "tid": "foo", 21 "trace_id": "foo", 22 "messages": [ 23 { 24 "role": "assistant", 25 "created_by_id": "foo", 26 "last_updated_by_id": "foo", 27 "created_at": "foo", 28 "updated_at": "foo", 29 "id": "message-123e4567-e89b-12d3-a456-426614174000", 30 "agent_id": "foo", 31 "model": "foo", 32 "content": [ 33 { 34 "type": "omitted_reasoning" 35 } 36 ], 37 "name": "foo", 38 "tool_calls": [ 39 { 40 "id": "foo", 41 "function": { 42 "arguments": "foo", 43 "name": "foo" 44 }, 45 "type": "foo" 46 } 47 ], 48 "tool_call_id": "foo", 49 "step_id": "foo", 50 "otid": "foo", 51 "tool_returns": [ 52 { 53 "status": "success", 54 "stdout": [ 55 "foo" 56 ], 57 "stderr": [ 58 "foo" 59 ] 60 } 61 ], 62 "group_id": "foo", 63 "sender_id": "foo", 64 "batch_item_id": "foo" 65 } 66 ], 67 "feedback": "positive" 68 } 69 ]

List steps with optional pagination and date filters. Dates should be provided in ISO 8601 format (e.g. 2025-01-29T15:01:19-08:00)

Query parameters

beforestringOptional

Return steps before this step ID

afterstringOptional

Return steps after this step ID

limitintegerOptionalDefaults to 50

Maximum number of steps to return

orderstringOptionalDefaults to desc

Sort order (asc or desc)

start_datestringOptional

Return steps after this ISO datetime (e.g. “2025-01-29T15:01:19-08:00”)

end_datestringOptional

Return steps before this ISO datetime (e.g. “2025-01-29T15:01:19-08:00”)

modelstringOptional

Filter by the name of the model used for the step

agent_idstringOptional

Filter by the ID of the agent that performed the step

trace_idslist of stringsOptional

Filter by trace ids returned by the server

feedbackenumOptional

Filter by feedback

Allowed values:

has_feedbackbooleanOptional

Filter by whether steps have feedback (true) or not (false)

tagslist of stringsOptional

Filter by tags

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_detailsobject or null

Metadata for the agent.

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.

messageslist of objects or null

The messages generated during this step.

feedbackenum or null

The feedback for this step. Must be either 'positive' or 'negative'.

Allowed values:

Headers

Query parameters

Response