> ## Documentation Index > Fetch the complete documentation index at: https://docs.valkyrie.vals.ai/llms.txt > Use this file to discover all available pages before exploring further. # Runs types > Public runs models and enums exported by the Valkyrie Python SDK. This page documents all 15 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**

{"event"}required · str

{"data"}required · dict\[str, Any]

***

`BenchmarkStatus`

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

{"IN_PROGRESS"}


        {"'IN_PROGRESS'"}

{"STOPPING"}


        {"'STOPPING'"}

{"STOPPED"}


        {"'STOPPED'"}

{"FINISHED"}


        {"'FINISHED'"}

{"ERROR"}


        {"'ERROR'"}

***

`FetchBenchmarkResponse`

Current state of one benchmark run. Runs model · 11 fields **Fields**

{"benchmark_name"}required · str

{"benchmark_id"}required · UUID

{"details"}required · BenchmarkDetails

{"s3_bucket_url"}required · str

{"label"}optional · str | None · default: {"None"}

{"final_score"}optional · float | None · default: {"None"}

{"error_message"}optional · str | None · default: {"None"}

{"executor_release_id"}optional · str | None · default: {"None"}

{"current_execution_release_id"}optional · str | None · default: {"None"}

{"executor_artifact_digest"}optional · str | None · default: {"None"}

{"executor_protocol_version"}optional · str | None · default: {"None"}

***

`FetchBenchmarkMetadataResponse`

Stored launch metadata for one run. Runs model · 9 fields **Fields**

{"benchmark_id"}required · UUID

{"benchmark_name"}required · str

{"benchmark_arguments"}required · BenchmarkArguments

{"started_by_email"}optional · str | None · default: {"None"}

{"executor_release_id"}optional · str | None · default: {"None"}

{"current_execution_release_id"}optional · str | None · default: {"None"}

{"executor_artifact_uri"}optional · str | None · default: {"None"}

{"executor_artifact_digest"}optional · str | None · default: {"None"}

{"executor_protocol_version"}optional · str | None · default: {"None"}

***

`FetchBenchmarksRequest`

Filters and pagination for listing benchmark runs. Runs model · 13 fields **Fields**

{"agent_name"}optional · list\[str] | None · default: {"None"}

{"benchmark_name"}optional · list\[str] | None · default: {"None"}

{"model"}optional · str | None · default: {"None"}

{"dataset"}optional · str | None · default: {"None"}

{"label"}optional · str | None · default: {"None"}

{"status"}optional · list\[BenchmarkStatus] | None · default: {"None"}

{"started_by"}optional · list\[str] | None · default: {"None"}

{"started_after"}optional · datetime | None · default: {"None"}

{"started_before"}optional · datetime | None · default: {"None"}

{"order_by"}optional · Order · default: {"Order.DESC"}

{"cursor"}optional · str | None · default: {"None"}

{"limit"}optional · int · default: {"50"} · constraints: {">= 1; <= 500"}

{"offset"}optional · int · default: {"0"} · constraints: {">= 0"}

***

`FetchBenchmarksResponse`

Page of benchmark runs. Runs model · 3 fields **Fields**

{"benchmarks"}required · list\[BenchmarkTableRow]

{"total_count"}optional · int | None · default: {"None"}

{"next_cursor"}optional · str | None · default: {"None"}

***

`FinalViewResponse`

Inline final results for a benchmark run. Runs model · 12 fields **Fields**

{"benchmark_id"}required · UUID

{"benchmark_name"}required · str

{"started_at"}required · datetime

{"finished_at"}required · datetime | None

{"status"}required · BenchmarkStatus

{"error_message"}required · str | None

{"benchmark_arguments"}required · BenchmarkArguments

{"tasks_stopped"}required · int | None

{"final_evaluation"}required · FinalEvaluation | None

{"average_task_breakdown"}required · AverageTaskBreakdown | None

{"evaluation_results"}required · dict\[str, dict\[str, Any]] | None

{"task_errors"}required · dict\[str, str] | None

***

`Order`

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

{"ASC"}


        {"'asc'"}

{"DESC"}


        {"'desc'"}

***

`RetryMode`

Supported retry strategies. Runs enum · 2 members **Members**

{"AUTO"}


        {"'auto'"}

{"FROM_SCRATCH"}


        {"'from_scratch'"}

***

`RetryOrResumeBenchmarkResponse`

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

{"status"}required · str

***

`ResultsExistResponse`

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

{"exists"}required · bool

***

`S3UploadResultsResponse`

URLs returned when final results are uploaded to S3. Runs model · 4 fields **Fields**

{"s3_url"}required · str

{"presigned_url"}required · str

{"console_url"}required · str

{"expires_in"}optional · int · default: {"86400"}

***

`StartBenchmarkResponse`

Response returned after starting a run. Runs model · 12 fields **Fields**

{"benchmark_name"}required · str

{"agent_name"}required · str

{"benchmark_id"}required · UUID

{"concurrency"}required · int

{"started_at"}required · datetime

{"task_count"}required · int

{"cloudwatch_url"}required · str

{"s3_bucket_url"}required · str

{"executor_release_id"}optional · str | None · default: {"None"}

{"current_execution_release_id"}optional · str | None · default: {"None"}

{"executor_artifact_digest"}optional · str | None · default: {"None"}

{"executor_protocol_version"}optional · str | None · default: {"None"}

***

`StopBenchmarkResponse`

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

{"status"}required · str

***

`TaskStatus`

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

{"PENDING"}


        {"'PENDING'"}

{"BUILDING"}


        {"'BUILDING'"}

{"IN_PROGRESS"}


        {"'IN_PROGRESS'"}

{"EVALUATING"}


        {"'EVALUATING'"}

{"STOPPED"}


        {"'STOPPED'"}

{"FINISHED"}


        {"'FINISHED'"}

{"ERROR"}


        {"'ERROR'"}