Skip to main content
This page documents all 23 public types in the Runs family in source order. Use the table of contents to jump to a type.

​
AnalyzeEvent

One progress or completion event from run analysis. Runs model · 2 fields Fields
required · str
required · dict[str, Any]

​
BenchmarkStatus

Lifecycle states for a benchmark run. Runs enum · 5 members Members

​
DatasetVersion

Exact dataset release saved for a run. Runs model · 2 fields Fields
required · str · constraints:
required · str | None · constraints:

​
FailureCategory

Coarse classification of a task or run failure. Runs enum · 5 members Members

​
FetchBenchmarkResponse

Current state of one benchmark run. Runs model · 12 fields Fields
required · str
required · UUID
required · BenchmarkDetails
required · str
optional · str | None · default:
optional · str | None · default:
optional · float | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:

​
FetchBenchmarkMetadataResponse

Stored launch metadata for one run. Runs model · 11 fields Fields
required · UUID
required · str
required · AWSBenchmarkArguments | LocalBenchmarkArguments
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · ProjectResponse | None · default:

​
FetchBenchmarksRequest

Filters and pagination for listing benchmark runs. Runs model · 13 fields Fields
optional · list[str] | None · default:
optional · list[str] | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · list[BenchmarkStatus] | None · default:
optional · list[str] | None · default:
optional · datetime | None · default:
optional · datetime | None · default:
optional · Order · default:
optional · str | None · default:
optional · int · default: · constraints:
optional · int · default: · constraints:

​
FetchBenchmarksResponse

Page of benchmark runs. Runs model · 3 fields Fields
required · list[BenchmarkTableRow]
optional · int | None · default:
optional · str | None · default:

​
FilterOptionsResponse

Values available for run filters in the caller’s organization. Runs model · 5 fields Fields
required · list[str]
required · list[str]
required · list[str]
required · list[str]
required · list[str]

​
FinalViewResponse

Inline final results for a benchmark run. Runs model · 13 fields Fields
required · UUID
required · str
required · datetime
required · datetime | None
required · BenchmarkStatus
required · str | None
required · AWSBenchmarkArguments | LocalBenchmarkArguments
required · int | None
required · FinalEvaluation | None
required · AverageTaskBreakdown | None
required · dict[str, dict[str, Any]] | None
required · dict[str, str] | None
optional · dict[str, FailureCategory] | None · default:

​
Order

Sort order for run listings. Runs enum · 2 members Members

​
RetryMode

Supported retry strategies. Runs enum · 2 members Members

​
RetryOrResumeBenchmarkResponse

Response returned after retrying or resuming a run. Runs model · 1 field Fields
required · str

​
RunStreamEvent

Represents one message on a run’s live update stream, as yielded by runs.events(). The stream sends an update every few seconds while the run is going, then ends with one complete, error or disconnect. Runs model · 3 fields Fields
required · Literal[‘update’, ‘complete’, ‘error’, ‘disconnect’]
optional · FetchBenchmarkResponse | None · default:
optional · str | None · default:

​
ResultsExistResponse

Whether the canonical result file already exists in S3. Runs model · 1 field Fields
required · bool

​
S3UploadResultsResponse

URLs returned when final results are uploaded to S3. Runs model · 4 fields Fields
required · str
required · str
required · str
optional · int · default:

​
ShedBenchmarkRequest

A concurrency limit below the run’s current one; dry_run only previews the tasks to stop. Runs model · 2 fields Fields
required · int · constraints:
optional · bool · default:

​
ShedBenchmarkResponse

The new limit and the newest tasks stopped (or, on a dry run, selected) to get under it. Runs model · 3 fields Fields
required · UUID
required · int
required · list[str]

​
StartBenchmarkResponse

Response returned after starting a run. Runs model · 16 fields Fields
required · str
required · str
required · UUID
required · int
required · datetime
required · int
optional · DatasetVersion | None · default:
optional · str | None · default:
required · str
required · str
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · str | None · default:
optional · ProjectResponse | None · default:

​
StopBenchmarkResponse

Response returned after stopping a run. Runs model · 1 field Fields
required · str

​
UpdateBenchmarkConcurrencyRequest

A positive concurrency limit for an active run. Runs model · 1 field Fields
required · int · constraints:

​
UpdateBenchmarkConcurrencyResponse

The run state after changing its concurrency limit. Runs model · 3 fields Fields
required · UUID
required · BenchmarkStatus
required · int

​
TaskStatus

Lifecycle states for one benchmark task. Runs enum · 7 members Members