Skip to main content
GET
List human review tasks for a flow execution (org-level access)

Authorizations

Authorization
string
header
required

JWT Bearer token authentication. Include your access token in the Authorization header as: Bearer YOUR_ACCESS_TOKEN

Example:

Query Parameters

flow_execution_id
string<uuid>
required

The flow execution ID to filter tasks by

source_task_name
string | null

Name of the human review task to narrow to. Must be provided together with source_task_execution_idx.

source_task_execution_idx
integer | null

Fan-out index of the human review task execution. Must be provided together with source_task_name.

Required range: x >= 0
large_values
enum<string>
default:inline

Controls delivery of large task values stored as GCS references. 'inline' (default) resolves references server-side and returns real values, subject to a per-request size budget (HTTP 413 when exceeded; individual references whose objects no longer exist are replaced by a 'gcs_ref_error' marker). 'refs' returns stored reference envelopes ('gcs_ref') untouched, to be resolved by the client.

Available options:
inline,
refs

Response

List of human review tasks retrieved successfully

created_at
string<date-time>
required
flow_execution_id
string<uuid>
required

UUID of the flow execution this task is associated with.

Example:

"550e8400-e29b-41d4-a716-446655440000"

id
string<uuid>
required
modified_by
string
required
organization_id
string<uuid>
required

UUID of the organization this task belongs to.

Example:

"550e8400-e29b-41d4-a716-446655440000"

source_task_execution_idx
integer
required

Index of the source task execution that created this review.

Example:

0

source_task_name
string
required

Name of the source task that created this review.

Example:

"process_document"

status
string
required

Status of the task. Valid values: 'pending', 'in_progress', 'completed'.

Example:

"pending"

target_task_executions
HumanReviewTargetTaskExecution · object[]
required

List of target task executions to review. The reviewer sees one card per entry; reviewed_output on completion is a positional list aligned with this list.

Minimum array length: 1
updated_at
string<date-time>
required
completed_at
string<date-time> | null

Timestamp when the task was completed. Null for not completed tasks.

Example:

"2024-01-01T00:00:00Z"

completed_by
string<uuid> | null

UUID of the user who completed this task. Null for not completed tasks.

Example:

"550e8400-e29b-41d4-a716-446655440000"

human_messages
string[] | null

Visible messages to display to the human reviewer as contextual information.

Example:
instructions
string | null

Instructions for the human reviewer on how to complete this task.

Example:

"Please review the document and verify all dates are correct."

review_annotations
ReviewAnnotation · object[] | null

Failed validations mapped onto the reviewed outputs, one entry per failed validation execution and affected target. Null for reviews created before annotations existed.

review_result
boolean | null

Review result: True for correct, False for incorrect, null for not yet finished.

Example:

true

reviewed_output
any[] | null

Output of the completed review. Null for tasks not yet completed. List positionally aligned with target_task_executions; each entry is a reviewed item (a dict, or a scalar for per-item references to scalar outputs).

Example:
signal_sent
boolean
default:true

Whether the Temporal resume signal was sent. False when deferred due to concurrency limits.

task_metadata
Task Metadata · object | null

Additional metadata associated with the human review task.

Example: