> ## Documentation Index
> Fetch the complete documentation index at: https://docs.internal.nscale.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Plan policy-aware burn-in reruns for standup devices

> Compute policy-aware rerun plans for a site's standup devices.

This planner is non-mutating. Its queryset uses the Job model only so
authorization requires the same ``job:create`` scope as dispatch.
Multi-node reruns currently cover the rack-acceptance gate only.



## OpenAPI

````yaml /openapi/fleet-manager-openapi.yaml post /api/v1/burn-in/sites/{site_id}/rerun-plans/
openapi: 3.0.3
info:
  title: Fleet Manager API
  version: 1.0.0
  description: API for the Nscale Fleet Manager
servers: []
security: []
paths:
  /api/v1/burn-in/sites/{site_id}/rerun-plans/:
    post:
      tags:
        - Burn-in
      summary: Plan policy-aware burn-in reruns for standup devices
      description: |-
        Compute policy-aware rerun plans for a site's standup devices.

        This planner is non-mutating. Its queryset uses the Job model only so
        authorization requires the same ``job:create`` scope as dispatch.
        Multi-node reruns currently cover the rack-acceptance gate only.
      operationId: api_v1_burn_in_sites_rerun_plans_create
      parameters:
        - in: path
          name: site_id
          schema:
            type: string
            format: uuid
          description: Site identifier.
          required: true
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RerunPlanRequest'
          application/x-www-form-urlencoded:
            schema:
              $ref: '#/components/schemas/RerunPlanRequest'
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/RerunPlanRequest'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RerunPlanResponse'
          description: ''
        '400':
          description: Device ids not part of the site.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication credentials were not provided or are invalid.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: You do not have permission to perform this action.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Unknown site_id.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
        - oauth2:
            - job:create
        - cookieAuth: []
components:
  schemas:
    RerunPlanRequest:
      type: object
      description: Request body for computing a site rerun plan.
      properties:
        device_ids:
          type: array
          items:
            type: string
            format: uuid
          description: Devices at the site to plan reruns for.
          minItems: 1
        mode:
          allOf:
            - $ref: '#/components/schemas/RerunPlanningModeEnum'
          default: non_passing
          description: >-
            non_passing reruns only requirements that are not currently passing;
            all also reruns passing requirements.


            * `non_passing` - NON_PASSING

            * `all` - ALL
      required:
        - device_ids
    RerunPlanResponse:
      type: object
      description: Computed rerun plan for the selected devices.
      properties:
        jobs:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanJob'
        skips:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanSkipGroup'
        excluded_devices:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanExcludedDevice'
      required:
        - excluded_devices
        - jobs
        - skips
    ErrorResponse:
      type: object
      description: >-
        Uniform error body for every 4xx/5xx response. `detail` is a
        human-readable message, always present, safe to display to end users.
        `code` is the machine-readable identifier. `field_errors` lists
        per-input-field validation messages and is empty for non-field errors
        (auth, permission, not-found, conflict, server).
      required:
        - detail
        - code
        - field_errors
      properties:
        detail:
          type: string
        code:
          $ref: '#/components/schemas/ErrorCodeEnum'
        field_errors:
          type: array
          items:
            $ref: '#/components/schemas/FieldError'
    RerunPlanningModeEnum:
      enum:
        - non_passing
        - all
      type: string
      description: |-
        * `non_passing` - NON_PASSING
        * `all` - ALL
    RerunPlanJob:
      type: object
      description: One job the plan would create.
      properties:
        workflow_name:
          $ref: '#/components/schemas/RerunWorkflowNameEnum'
        topology:
          allOf:
            - $ref: '#/components/schemas/RerunPlanTopology'
          nullable: true
          description: Rack-acceptance topology identity; null for single-node jobs.
        resource_class:
          type: string
        policy_digest:
          type: string
        devices:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanDevice'
        parameters:
          $ref: '#/components/schemas/RerunPlanParameters'
      required:
        - devices
        - parameters
        - policy_digest
        - resource_class
        - topology
        - workflow_name
    RerunPlanSkipGroup:
      type: object
      description: >-
        Devices skipped for one topology, resource class, requirement, and
        reason.
      properties:
        device_ids:
          type: array
          items:
            type: string
            format: uuid
          minItems: 1
        topology:
          allOf:
            - $ref: '#/components/schemas/RerunPlanTopology'
          nullable: true
          description: Rack-acceptance topology identity; null for single-node skips.
        resource_class:
          type: string
        requirement_name:
          type: string
        reason:
          $ref: '#/components/schemas/RerunPlanSkipReasonEnum'
      required:
        - device_ids
        - reason
        - requirement_name
        - resource_class
        - topology
    RerunPlanExcludedDevice:
      type: object
      description: One selected device excluded from planning entirely.
      properties:
        device_id:
          type: string
          format: uuid
        reason:
          $ref: '#/components/schemas/RerunPlanExcludedDeviceReasonEnum'
      required:
        - device_id
        - reason
    ErrorCodeEnum:
      type: string
      description: >-
        Stable machine-readable error identifier. New members may be added
        within this API version; clients must tolerate unknown values.
      enum:
        - error
        - invalid
        - parse_error
        - authentication_failed
        - not_authenticated
        - permission_denied
        - not_found
        - method_not_allowed
        - not_acceptable
        - unsupported_media_type
        - conflict
        - enrollment_infrastructure_reference_pending
        - enrollment_infrastructure_reference_changed
        - unprocessable_entity
        - throttled
        - service_unavailable
    FieldError:
      type: object
      description: One input field's validation messages.
      required:
        - field
        - messages
      properties:
        field:
          type: string
          description: >-
            Dotted path to the offending input field, or to the collection row
            when the whole row is invalid (e.g. `filters.end_date`,
            `memberships.0.role`, `memberships.0`).
        messages:
          type: array
          minItems: 1
          items:
            type: string
    RerunWorkflowNameEnum:
      enum:
        - SingleNodeBurnInWorkflow
        - MultiNodeBurnInCollectiveWorkflow
      type: string
      description: |-
        * `SingleNodeBurnInWorkflow` - SINGLE_NODE
        * `MultiNodeBurnInCollectiveWorkflow` - MULTI_NODE_COLLECTIVE
    RerunPlanTopology:
      type: object
      description: Topology identity for one atomic rack-acceptance rerun cohort.
      properties:
        id:
          type: string
          format: uuid
        unit:
          $ref: '#/components/schemas/StandupTopologyUnitEnum'
        label:
          type: string
      required:
        - id
        - label
        - unit
    RerunPlanDevice:
      type: object
      description: One device's share of a planned job.
      properties:
        device_id:
          type: string
          format: uuid
        device_name:
          type: string
        resolutions:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanResolution'
      required:
        - device_id
        - device_name
        - resolutions
    RerunPlanParameters:
      type: object
      description: The ordered-test burn-in payload a planned job would dispatch with.
      properties:
        partition:
          type: string
          nullable: true
        max_wait_time_seconds:
          type: number
          format: double
          nullable: true
        tests:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanTestSpec'
      required:
        - max_wait_time_seconds
        - partition
        - tests
    RerunPlanSkipReasonEnum:
      enum:
        - projection_pending
        - already_satisfied
        - no_policy_satisfying_parameter_source
        - policy_changed
        - workflow_unavailable
        - device_ineligible
        - device_contended
        - already_dispatched
        - topology_cohort_blocked
      type: string
      description: >-
        * `projection_pending` - PROJECTION_PENDING

        * `already_satisfied` - ALREADY_SATISFIED

        * `no_policy_satisfying_parameter_source` -
        NO_POLICY_SATISFYING_PARAMETER_SOURCE

        * `policy_changed` - POLICY_CHANGED

        * `workflow_unavailable` - WORKFLOW_UNAVAILABLE

        * `device_ineligible` - DEVICE_INELIGIBLE

        * `device_contended` - DEVICE_CONTENDED

        * `already_dispatched` - ALREADY_DISPATCHED

        * `topology_cohort_blocked` - TOPOLOGY_COHORT_BLOCKED
    RerunPlanExcludedDeviceReasonEnum:
      enum:
        - no_acceptance_policy
        - no_single_node_requirements
        - no_rerun_requirements
      type: string
      description: |-
        * `no_acceptance_policy` - NO_ACCEPTANCE_POLICY
        * `no_single_node_requirements` - NO_SINGLE_NODE_REQUIREMENTS
        * `no_rerun_requirements` - NO_RERUN_REQUIREMENTS
    StandupTopologyUnitEnum:
      enum:
        - nvlink-domain
        - pod
        - rack
      type: string
      description: |-
        * `nvlink-domain` - NVLINK_DOMAIN
        * `pod` - POD
        * `rack` - RACK
    RerunPlanResolution:
      type: object
      description: Why one device or topology cohort reruns one requirement.
      properties:
        requirement_name:
          type: string
        verdict:
          allOf:
            - $ref: '#/components/schemas/StandupGateVerdictEnum'
          description: >-
            The current verdict this rerun addresses. Never `pending` — a rerun
            is only planned against a requirement that has been evaluated.


            * `pass` - PASS

            * `missing-evidence` - MISSING_EVIDENCE

            * `stale-evidence` - STALE_EVIDENCE

            * `topology-incomplete` - TOPOLOGY_INCOMPLETE

            * `execution-error` - EXECUTION_ERROR

            * `threshold-failure` - THRESHOLD_FAILURE

            * `pending` - PENDING
        selected_option:
          $ref: '#/components/schemas/RerunPlanParameterOption'
        options:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanParameterOption'
      required:
        - options
        - requirement_name
        - selected_option
        - verdict
    RerunPlanTestSpec:
      type: object
      description: One test entry in a planned job payload.
      properties:
        slug:
          $ref: '#/components/schemas/TestSlugEnum'
        params:
          type: object
          additionalProperties:
            $ref: '#/components/schemas/JsonValue'
          description: >-
            Test parameters exactly as they will run (free-form per test
            schema).
      required:
        - params
        - slug
    StandupGateVerdictEnum:
      enum:
        - pass
        - missing-evidence
        - stale-evidence
        - topology-incomplete
        - execution-error
        - threshold-failure
        - pending
      type: string
      description: |-
        * `pass` - PASS
        * `missing-evidence` - MISSING_EVIDENCE
        * `stale-evidence` - STALE_EVIDENCE
        * `topology-incomplete` - TOPOLOGY_INCOMPLETE
        * `execution-error` - EXECUTION_ERROR
        * `threshold-failure` - THRESHOLD_FAILURE
        * `pending` - PENDING
    RerunPlanParameterOption:
      type: object
      description: One policy-satisfying test and its provenance.
      properties:
        source:
          allOf:
            - $ref: '#/components/schemas/RerunParameterSourceEnum'
          description: |-
            Where this exact test configuration came from.

            * `last_used_preset` - LAST_USED_PRESET
            * `default_preset` - DEFAULT_PRESET
        test:
          $ref: '#/components/schemas/RerunPlanTestSpec'
        source_test_execution_id:
          type: string
          format: uuid
          nullable: true
        source_job:
          allOf:
            - $ref: '#/components/schemas/RerunPlanSourceJob'
          nullable: true
        presets:
          type: array
          items:
            $ref: '#/components/schemas/RerunPlanPreset'
      required:
        - presets
        - source
        - source_job
        - source_test_execution_id
        - test
    TestSlugEnum:
      enum:
        - multi-node.hello-world
        - multi-node.iperf-matrix
        - multi-node.nccl-all-gather
        - multi-node.nccl-all-reduce
        - multi-node.nccl-all-reduce-multi-rack
        - multi-node.nccl-all-to-all
        - multi-node.nvloom
        - multi-node.pairwise-net-gpu.bw
        - multi-node.pairwise-net-gpu.lat
        - multi-node.pairwise-net.bw
        - multi-node.pairwise-net.lat
        - multi-node.s3-elbencho
        - multi-node.storage-elbencho
        - multi-node.training-gpt-oss-120b
        - multi-node.training-llama3-1-405b
        - multi-node.training-llama3-70b
        - multi-node.training-nemotron-24x2h
        - multi-node.training-nemotron-checkpoint
        - multi-node.training-nemotron-h
        - multi-node.training-nemotron-h-multi-rack
        - multi-node.training-qwen3-235b
        - single-node.babelstream
        - single-node.dcgmi-diag
        - single-node.gpu-fryer
        - single-node.hello-world
        - single-node.hpl-cpu
        - single-node.hpl-gpu
        - single-node.lmbench-lat-mem-rd
        - single-node.memtester
        - single-node.nccl-all-gather
        - single-node.nccl-all-reduce
        - single-node.nccl-all-reduce-loopback
        - single-node.nccl-all-to-all
        - single-node.node-health-check
        - single-node.nvme-fio
        - single-node.nvme-self-test
        - single-node.storage-elbencho
        - single-node.stream
        - single-node.stress-ng-cpu
        - single-node.training-llama3-8b
        - single-node.training-nemotronh-8b
      type: string
      description: >-
        * `multi-node.hello-world` - multi-node.hello-world

        * `multi-node.iperf-matrix` - multi-node.iperf-matrix

        * `multi-node.nccl-all-gather` - multi-node.nccl-all-gather

        * `multi-node.nccl-all-reduce` - multi-node.nccl-all-reduce

        * `multi-node.nccl-all-reduce-multi-rack` -
        multi-node.nccl-all-reduce-multi-rack

        * `multi-node.nccl-all-to-all` - multi-node.nccl-all-to-all

        * `multi-node.nvloom` - multi-node.nvloom

        * `multi-node.pairwise-net-gpu.bw` - multi-node.pairwise-net-gpu.bw

        * `multi-node.pairwise-net-gpu.lat` - multi-node.pairwise-net-gpu.lat

        * `multi-node.pairwise-net.bw` - multi-node.pairwise-net.bw

        * `multi-node.pairwise-net.lat` - multi-node.pairwise-net.lat

        * `multi-node.s3-elbencho` - multi-node.s3-elbencho

        * `multi-node.storage-elbencho` - multi-node.storage-elbencho

        * `multi-node.training-gpt-oss-120b` - multi-node.training-gpt-oss-120b

        * `multi-node.training-llama3-1-405b` -
        multi-node.training-llama3-1-405b

        * `multi-node.training-llama3-70b` - multi-node.training-llama3-70b

        * `multi-node.training-nemotron-24x2h` -
        multi-node.training-nemotron-24x2h

        * `multi-node.training-nemotron-checkpoint` -
        multi-node.training-nemotron-checkpoint

        * `multi-node.training-nemotron-h` - multi-node.training-nemotron-h

        * `multi-node.training-nemotron-h-multi-rack` -
        multi-node.training-nemotron-h-multi-rack

        * `multi-node.training-qwen3-235b` - multi-node.training-qwen3-235b

        * `single-node.babelstream` - single-node.babelstream

        * `single-node.dcgmi-diag` - single-node.dcgmi-diag

        * `single-node.gpu-fryer` - single-node.gpu-fryer

        * `single-node.hello-world` - single-node.hello-world

        * `single-node.hpl-cpu` - single-node.hpl-cpu

        * `single-node.hpl-gpu` - single-node.hpl-gpu

        * `single-node.lmbench-lat-mem-rd` - single-node.lmbench-lat-mem-rd

        * `single-node.memtester` - single-node.memtester

        * `single-node.nccl-all-gather` - single-node.nccl-all-gather

        * `single-node.nccl-all-reduce` - single-node.nccl-all-reduce

        * `single-node.nccl-all-reduce-loopback` -
        single-node.nccl-all-reduce-loopback

        * `single-node.nccl-all-to-all` - single-node.nccl-all-to-all

        * `single-node.node-health-check` - single-node.node-health-check

        * `single-node.nvme-fio` - single-node.nvme-fio

        * `single-node.nvme-self-test` - single-node.nvme-self-test

        * `single-node.storage-elbencho` - single-node.storage-elbencho

        * `single-node.stream` - single-node.stream

        * `single-node.stress-ng-cpu` - single-node.stress-ng-cpu

        * `single-node.training-llama3-8b` - single-node.training-llama3-8b

        * `single-node.training-nemotronh-8b` -
        single-node.training-nemotronh-8b
    JsonValue:
      description: Any JSON value.
      nullable: true
      anyOf:
        - type: string
        - type: number
        - type: integer
        - type: boolean
        - type: array
          items:
            $ref: '#/components/schemas/JsonValue'
        - type: object
          additionalProperties:
            $ref: '#/components/schemas/JsonValue'
    RerunParameterSourceEnum:
      enum:
        - last_used_preset
        - default_preset
      type: string
      description: |-
        * `last_used_preset` - LAST_USED_PRESET
        * `default_preset` - DEFAULT_PRESET
    RerunPlanSourceJob:
      type: object
      description: A historical burn-in job whose complete parameters were validated.
      properties:
        id:
          type: string
          format: uuid
        parameters:
          $ref: '#/components/schemas/RerunPlanParameters'
      required:
        - id
        - parameters
    RerunPlanPreset:
      type: object
      description: A current JobPreset associated with a safe parameter option.
      properties:
        id:
          type: string
          format: uuid
        label:
          type: string
        device_type_id:
          type: string
          format: uuid
        is_default:
          type: boolean
        nscale_preset:
          type: boolean
        parameters:
          $ref: '#/components/schemas/RerunPlanParameters'
        attribution:
          allOf:
            - $ref: '#/components/schemas/RerunPresetAttributionEnum'
          description: >-
            configured_default is explicit configuration; inferred_exact_match
            means the historical job payload exactly matches this current
            preset.


            * `inferred_exact_match` - INFERRED_EXACT_MATCH

            * `configured_default` - CONFIGURED_DEFAULT
      required:
        - attribution
        - device_type_id
        - id
        - is_default
        - label
        - nscale_preset
        - parameters
    RerunPresetAttributionEnum:
      enum:
        - inferred_exact_match
        - configured_default
      type: string
      description: |-
        * `inferred_exact_match` - INFERRED_EXACT_MATCH
        * `configured_default` - CONFIGURED_DEFAULT
  securitySchemes:
    oauth2:
      type: oauth2
      flows: {}
    cookieAuth:
      type: apiKey
      in: cookie
      name: sessionid

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.