Skip to main content
POST
JavaScript
Stop an objective that is still working, a run gone off the rails, a loop you want to end, a task no longer needed.

Cancellation is asynchronous

The call accepts the request and returns; it does not wait for the objective to stop. The worker finishes what it is mid-flight on, then settles the objective into STATE_CANCELLED and appends a cancelled event. So poll the state, or watch the stream for that event, rather than assuming the objective is stopped the instant the call returns. Cancelling is idempotent and safe to repeat: a cancel on an objective that has already settled returns 200 and does nothing further. Only a nonexistent objective id is a 404.

Cancelled is one of four terminal states

STATE_CANCELLED is terminal, alongside STATE_FINALIZED, STATE_TIMED_OUT, and STATE_FAILED. A cancelled objective cannot be resumed or continued, so start a new one for fresh work. Its events, tool calls, and context windows remain readable for the life of the objective.

Get an objective

Poll state until it reads STATE_CANCELLED.

Continue an objective

The opposite move, for a WAITING objective you want to keep going.

Stream objective events

Watch for the cancelled event instead of polling.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

workspaceId
string
required
Example:

"workspace_01HXKD2E5NQM3T9AYWCF133E3Q"

objectiveId
string
required

The ID of the objective. Supports "external_id:" prefix for external IDs.

Example:

"obj_01HXKD2E5NQM3T9AYWCFQAZGFV"

Body

application/json
reason
string

Optional reason for cancellation

Response

OK

Objective is the data for an objective. It contains the snapshotted fields for the selected agent and variation. Secrets are returned only with their names, and the output definition is copied from the agent's configuration.

metadata
object
required

Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)

configSnapshot
object
required

The snapshot of the agent and the variation selected (either explicitly or by sampling) will be set here. Cadenya stores the point-in-time snapshot of the configuration used to start an objective and maintains it throughout the entire lifecycle so that changes to agents and variations in the middle of a cycle don't impact the objective itself

state
enum<string>
required
read-only

The current lifecycle state of the objective.

Available options:
STATE_UNSPECIFIED,
STATE_PENDING,
STATE_RUNNING,
STATE_WAITING,
STATE_FAILED,
STATE_CANCELLED,
STATE_FINALIZED,
STATE_TIMED_OUT
systemPrompt
string
required
read-only

system_prompt is read-only, derived from the selected variation's prompt

firstUserMessage
string
required

The first user message in the LLM chat history, either provided explicitly at creation or rendered from the variation's first_user_message_template.

stateMessage
string
read-only

Optional human-readable detail about the current state (e.g. a failure reason).

info
object

Read-only aggregated info about this objective's execution

parentObjectiveId
string
read-only

A parent objective means the objective was spawned off using a separate agent to complete an objective

Example:

"obj_01HXKD2E5NQM3T9AYWCFQAZGFV"

secrets
object[]

Secrets that can be used in the headers for tool calls using the secret interpolation format.

systemPromptData
object
read-only

Arbitrary data rendered into the variation's system_prompt_template

memoryCascade
object[]

Memory layers/entries layered over the baseline cascade inherited from the selected variation — element-level rules over inherited styles, in CSS terms.

Array order is resolution order: EARLIER elements are more specific and are consulted first. Entries pinned via memory_entry_id behave as single-entry layers at their position.

System-managed layers (e.g., episodic) cannot be referenced here; they attach themselves automatically based on the episodic key.

Size cap: the TOTAL effective cascade (this field + the variation's memory layer assignments) must not exceed 10 entries. A request that would produce a larger cascade is rejected with InvalidArgument.

output
object
read-only

The output of the objective, populated when the objective completes. Will match the schema of output_json_schema or output_json_inferred. This will only be set if the state of the objective is set to STATE_FINALIZED

firstUserMessageData
object
read-only

Arbitrary data rendered into the variation's first_user_message_template

episodicMemory
object

If the agent variation that is selected has episodic memory enabled, then this key is used to create/update a memory layer specific to the episodic memory. The layer may have a TTL configured by the variation.

pinnedParameters
object
read-only

Parameters forced onto this objective's tool calls, as provided at creation. See CreateObjectiveRequest.pinned_parameters for semantics.