Fetch a Task Run | Rightbrain Docs — Build reliable AI agents

{
  "task_id": "019f8a00-1c3d-7e42-b8f1-2a5c9d4e7b60",
  "task_revision_id": "019f8a01-4b3d-7e52-9c02-3b6d8f1a5c71",
  "response": {
    "category": "billing",
    "priority": "high",
    "summary": "Customer was double-charged for their Pro plan renewal and wants a refund."
  },
  "run_data": {
    "submitted": {
      "body": "I was billed twice for my Pro subscription on the 3rd and the 5th. Please refund the duplicate charge.",
      "plan": "Pro",
      "subject": "Charged twice this month"
    },
    "integration_tool_calls": [],
    "mcp_tool_calls": []
  },
  "id": "019f8a04-8e60-7b85-af37-6e9fb14d8fa4",
  "created": "2026-07-24T10:02:17Z",
  "input_tokens": 186,
  "output_tokens": 42,
  "total_tokens": 228,
  "input_processor_timing": 0.00015282,
  "llm_call_timing": 1.346,
  "charged_credits": "1.00",
  "model_name": "claude-sonnet-5",
  "task_name": "Support Ticket Triage",
  "output_modality": "json",
  "files": [],
  "is_error": false,
  "llm_retries": 0,
  "used_fallback_model": false,
  "user_id": "019f6c10-1a2b-7c3d-8e4f-5a6b7c8d9e01",
  "input_processor_charged_credits": "0.00"
}

Retrieve detailed information about a specific task run.

Task runs provide a complete record of task executions, including:

Input parameters and configuration used
Execution status and timing information
Resource usage metrics (e.g., tokens consumed, credits charged)
Structured output and processing metadata
Error information if the run failed
Fallback model information if the primary model failed

Response Fields:

Timing Metrics:

input_processor_timing: Time in seconds spent running input processors (e.g., 0.00015282)
llm_call_timing: Time in seconds for the LLM API call (e.g., 1.346)

Resource Usage:

charged_credits: Credits charged for this execution as a string (e.g., "1.00")
input_tokens: Number of input tokens processed
output_tokens: Number of output tokens generated
total_tokens: Combined token count

Retry & Fallback Information:

llm_retries: Number of retry attempts made before success or failure
used_fallback_model: Boolean indicating if fallback model was used
primary_failure_reason: Reason why the primary model failed (if applicable)
fallback_llm_model_id: ID of the fallback model used (if applicable)

Input Data:

run_data.submitted: The original input parameters as submitted

This endpoint is useful for:

Monitoring task execution progress
Debugging failed runs and understanding failover behavior
Auditing task usage and performance
Retrieving task results
Analyzing reliability and fallback model usage

Errors:

Returns 400 if the task run ID is not a valid UUID format
Returns 422 if the request body fails validation
Returns 404 if the task run is not found
Returns 403 if the user lacks permission to access the task run

Retrieve detailed information about a specific task run. Task runs provide a complete record of task executions, including: - Input parameters and configuration used - Execution status and timing information - Resource usage metrics (e.g., tokens consumed, credits charged) - Structured output and processing metadata - Error information if the run failed - Fallback model information if the primary model failed **Response Fields:** *Timing Metrics:* - `input_processor_timing`: Time in seconds spent running input processors (e.g., `0.00015282`) - `llm_call_timing`: Time in seconds for the LLM API call (e.g., `1.346`) *Resource Usage:* - `charged_credits`: Credits charged for this execution as a string (e.g., `"1.00"`) - `input_tokens`: Number of input tokens processed - `output_tokens`: Number of output tokens generated - `total_tokens`: Combined token count *Retry & Fallback Information:* - `llm_retries`: Number of retry attempts made before success or failure - `used_fallback_model`: Boolean indicating if fallback model was used - `primary_failure_reason`: Reason why the primary model failed (if applicable) - `fallback_llm_model_id`: ID of the fallback model used (if applicable) *Input Data:* - `run_data.submitted`: The original input parameters as submitted This endpoint is useful for: - Monitoring task execution progress - Debugging failed runs and understanding failover behavior - Auditing task usage and performance - Retrieving task results - Analyzing reliability and fallback model usage Errors: - Returns 400 if the task run ID is not a valid UUID format - Returns 422 if the request body fails validation - Returns 404 if the task run is not found - Returns 403 if the user lacks permission to access the task run

Authentication

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

Path parameters

org_idstringRequiredformat: "uuid"

The unique identifier of the organization.

project_idstringRequiredformat: "uuid"

The unique identifier of the project.

task_idstringRequiredformat: "uuid"

The specific Task to reference.

task_run_idstringRequiredformat: "uuid"

The specific Task Run to reference.

Response

Successfully retrieved task run information

task_idstringformat: "uuid"

The unique identifier of the Task associated with this run.

task_revision_idstringformat: "uuid"

The unique identifier of the Task Revision associated with this run.

responsestring or map from strings to any

The structured response from the Task execution.

run_dataobject

Additional data about the Task execution, including submitted inputs. submitted is absent on runs that failed before their input was recorded, so the object can be empty.

idstringformat: "uuid"

The unique identifier of the Task Run.

createdstring

The timestamp when the Task Run was created.

input_tokensinteger

The number of tokens submit as input to the model.

output_tokensinteger

The number of tokens generated and output by the model.

total_tokensinteger

The total token usage for the TaskRun.

input_processor_timingdouble or null

The execution time for the TaskRun in seconds.

llm_call_timingdouble or null

The execution time for the TaskRun in seconds.

charged_creditsstring or nullformat: "^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$"

The total credits charged for the TaskRun.

model_namestring or nullOptional

Name of the LLM model associated with the task revision used for this run.

task_namestring or nullOptional

Name of the task associated with this run.

output_modalityenum or nullOptional

Output modality configured on the associated task.

fileslist of objectsOptionalDefaults to []

List of file metadata objects with enriched information including download URLs.

is_errorbooleanOptionalDefaults to false

llm_retriesintegerOptionalDefaults to 0

Number of retry attempts made during LLM execution.

used_fallback_modelbooleanOptionalDefaults to false

Whether the fallback model was used

primary_failure_reasonstring or nullOptional

Reason the primary model failed

fallback_llm_model_idstring or nullOptionalformat: "uuid"

Fallback model that was used

user_idstring or nullOptionalformat: "uuid"

The unique identifier of the User who executed the task.

reporting_group_idstring or nullOptionalformat: "uuid"

The ID of the reporting group to associate with this task run

referencestring or nullOptional<=64 characters

An optional reference identifier for this task run

context_idstring or nullOptional<=64 characters

An optional context ID for grouping related task runs

rag_retrieval_timingdouble or nullOptional

The task RAG retrieval time in seconds.

rag_query_rewrite_input_tokensinteger or nullOptional

Input tokens used by the task RAG query rewrite model.

rag_query_rewrite_output_tokensinteger or nullOptional

Output tokens used by the task RAG query rewrite model.

rag_query_rewrite_total_tokensinteger or nullOptional

Total tokens used by the task RAG query rewrite model.

mcp_tool_timingdouble or nullOptional

Total time spent waiting on MCP tool calls in seconds.

input_processor_charged_creditsstring or nullOptionalformat: "^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$"

Credits charged for input processor work during this task run.

reporting_groupobject or nullOptional

The reporting group associated with this task run

event_trigger_idlist of strings or nullOptional

Webhook trigger event IDs associated with this TaskRun, if any.

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error