Fetch a 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