Kind: Function
Source: atloria-monorepo/libs/agent-core/src/benchmark/swebench-evaluator.ts
Convert a TaskResult to SWE-bench prediction format. Used for both successful and failed tasks (autosubmit pattern — even partial patches are worth submitting).
Signature
tsfunction buildPrediction(result: TaskResult, modelName: string): SWEBenchPrediction
Parameters
| Name | Type |
|---|---|
result | TaskResult |
modelName | string |
Returns: SWEBenchPrediction
Was this page helpful?