Batch Get Conversation Events

Get a batch of local events given their ids, returning null for any missing item.

GET /api/conversations/{conversation_id}/events

Try it

200

[
  {
    "llm_response_id": "<string>",
    "kind": "Condensation",
    "id": "<string>",
    "timestamp": "<string>",
    "source": "environment",
    "forgotten_event_ids": [
      "<string>"
    ],
    "summary": "<string>",
    "summary_offset": 1
  }
]

Path Parameters

conversation_id · string<uuid> · required

Body

application/json

Response

200

application/json

(Condensation · object | CondensationRequest · object | CondensationSummaryEvent · object | ConversationErrorEvent · object | ConversationStateUpdateEvent · object | LLMCompletionLogEvent · object | ActionEvent · object | MessageEvent · object | AgentErrorEvent · object | ObservationEvent · object | UserRejectObservation · object | SystemPromptEvent · object | TokenEvent · object | PauseEvent · object | null)[]

Successful Response

Condensation

CondensationRequest

CondensationSummaryEvent

ConversationErrorEvent

ConversationStateUpdateEvent

LLMCompletionLogEvent

ActionEvent

MessageEvent

AgentErrorEvent

ObservationEvent

UserRejectObservation

SystemPromptEvent

TokenEvent

PauseEvent

This action indicates a condensation of the conversation history is happening.

llm_response_id · string · required

Completion or Response ID of the LLM response that generated this event

kind · string · default: Condensation

Allowed value: "Condensation"

id · string

Unique event id (ULID/UUID)

timestamp · string

Event timestamp

source · enum<string> · default: environment

Available options: agent, user, environment

forgotten_event_ids · string[]

The IDs of the events that are being forgotten (removed from the View given to the LLM).

summary · string | null

An optional summary of the events being forgotten.

summary_offset · integer | null

An optional offset to the start of the resulting view indicating where the summary should be inserted.

Required range: x >= 0