remora/docs/spec/api/openapi.yaml

openapi: 3.2.0
$self: https://remora.invalid/spec/api/openapi.yaml
jsonSchemaDialect: https://spec.openapis.org/oas/3.2/dialect/2025-09-17
info:
  title: Remora API
  version: 1.0.0
  description: Public job management and service-authenticated worker operations.
servers:
  - url: /api
security:
  - oidc: []
paths:
  /v1/jobs:
    post:
      operationId: submitJob
      parameters:
        - $ref: '#/components/parameters/IdempotencyKey'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/JobSubmission'
      responses:
        '202':
          description: Accepted, or the original accepted response for the same key and fingerprint.
          headers:
            Idempotency-Expires-At:
              $ref: '#/components/headers/IdempotencyExpiresAt'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        '409':
          $ref: '#/components/responses/IdempotencyConflict'
        default:
          $ref: '#/components/responses/Error'
    get:
      operationId: listJobs
      parameters:
        - $ref: '#/components/parameters/Cursor'
        - $ref: '#/components/parameters/Limit'
        - name: include_deleted
          in: query
          schema:
            type: boolean
            default: false
      responses:
        '200':
          description: Authorized keyset page bound to one snapshot and filter.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobPage'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}:
    parameters:
      - $ref: '#/components/parameters/JobId'
    get:
      operationId: getJob
      responses:
        '200':
          description: Current authorized job projection.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        '404':
          $ref: '#/components/responses/NotFound'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}/result:
    parameters:
      - $ref: '#/components/parameters/JobId'
    get:
      operationId: getJobResult
      responses:
        '200':
          description: Visible committed manifest-rooted result.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResultDescriptor'
        '404':
          $ref: '#/components/responses/NotFound'
        '409':
          $ref: '#/components/responses/PreconditionFailed'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}/cancel:
    parameters:
      - $ref: '#/components/parameters/JobId'
    post:
      operationId: cancelJob
      parameters:
        - $ref: '#/components/parameters/IdempotencyKey'
      responses:
        '202':
          description: Cancellation intent accepted or prior response replayed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}/soft-delete:
    parameters:
      - $ref: '#/components/parameters/JobId'
    post:
      operationId: softDeleteJob
      parameters:
        - $ref: '#/components/parameters/IdempotencyKey'
      responses:
        '200':
          description: Job hidden, or prior response replayed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}/restore:
    parameters:
      - $ref: '#/components/parameters/JobId'
    post:
      operationId: restoreJob
      parameters:
        - $ref: '#/components/parameters/IdempotencyKey'
      responses:
        '200':
          description: Soft-deleted job restored, or prior response replayed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        default:
          $ref: '#/components/responses/Error'
  /v1/jobs/{job_id}/hard-delete:
    parameters:
      - $ref: '#/components/parameters/JobId'
    post:
      operationId: hardDeleteJob
      parameters:
        - $ref: '#/components/parameters/IdempotencyKey'
      responses:
        '202':
          description: Durable deletion operation created or replayed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeletionOperation'
        default:
          $ref: '#/components/responses/Error'
  /v1/deletions/{operation_id}:
    parameters:
      - name: operation_id
        in: path
        required: true
        schema:
          $ref: '#/components/schemas/OpaqueId'
    get:
      operationId: getDeletionOperation
      responses:
        '200':
          description: Current deletion operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeletionOperation'
        '404':
          $ref: '#/components/responses/NotFound'
        default:
          $ref: '#/components/responses/Error'
  /v1/events:
    get:
      operationId: connectEvents
      parameters:
        - name: cursor
          in: query
          description: Opaque authorization-bound replay cursor from an HTTP snapshot or prior frame.
          schema:
            type: string
            minLength: 16
            maxLength: 2048
      responses:
        '101':
          description: WebSocket frames conform to events.schema.json. An absent, invalid, expired, or unauthorized cursor yields resync_required.
        default:
          $ref: '#/components/responses/Error'
  /internal/v1/jobs/{job_id}/claim:
    parameters:
      - $ref: '#/components/parameters/JobId'
    post:
      operationId: claimJob
      security:
        - serviceAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClaimRequest'
      responses:
        '200':
          description: Allocated authority or replay of the same claim operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AttemptAuthority'
        default:
          $ref: '#/components/responses/Error'
  /internal/v1/attempts/{attempt_id}/renew:
    parameters:
      - $ref: '#/components/parameters/AttemptId'
    post:
      operationId: renewAttempt
      security:
        - serviceAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AttemptMutation'
      responses:
        '204':
          description: Renewed or duplicate operation accepted.
        '409':
          $ref: '#/components/responses/PreconditionFailed'
        default:
          $ref: '#/components/responses/Error'
  /internal/v1/attempts/{attempt_id}/progress:
    parameters:
      - $ref: '#/components/parameters/AttemptId'
    post:
      operationId: reportAttemptProgress
      security:
        - serviceAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AttemptProgressRequest'
      responses:
        '204':
          description: Current progress accepted or duplicate ignored.
        '409':
          $ref: '#/components/responses/PreconditionFailed'
        default:
          $ref: '#/components/responses/Error'
  /internal/v1/attempts/{attempt_id}/outcome:
    parameters:
      - $ref: '#/components/parameters/AttemptId'
    post:
      operationId: reportAttemptOutcome
      security:
        - serviceAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AttemptOutcomeRequest'
      responses:
        '200':
          description: Durable outcome projection or replay of the same operation.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Job'
        '409':
          $ref: '#/components/responses/PreconditionFailed'
        default:
          $ref: '#/components/responses/Error'
components:
  securitySchemes:
    oidc:
      type: openIdConnect
      openIdConnectUrl: https://identity.invalid/.well-known/openid-configuration
    serviceAuth:
      type: mutualTLS
  parameters:
    IdempotencyKey:
      name: Idempotency-Key
      in: header
      required: true
      description: Subject- and operation-scoped key retained for at least 24 hours.
      schema:
        type: string
        pattern: '^[A-Za-z0-9._~-]{16,128}$'
    Cursor:
      name: cursor
      in: query
      schema:
        type: string
        minLength: 16
        maxLength: 2048
    Limit:
      name: limit
      in: query
      schema:
        type: integer
        minimum: 1
        maximum: 200
        default: 50
    JobId:
      name: job_id
      in: path
      required: true
      schema:
        $ref: '#/components/schemas/OpaqueId'
    AttemptId:
      name: attempt_id
      in: path
      required: true
      schema:
        $ref: '#/components/schemas/OpaqueId'
  headers:
    IdempotencyExpiresAt:
      description: Earliest time at which the server may forget this key.
      schema:
        type: string
        format: date-time
  responses:
    Error:
      description: Structured error with user-safe detail only.
      content:
        application/problem+json:
          schema:
            $ref: '#/components/schemas/ApiError'
    NotFound:
      description: Missing or unauthorized resource; the response does not distinguish them.
      content:
        application/problem+json:
          schema:
            $ref: '#/components/schemas/ApiError'
    IdempotencyConflict:
      description: The key exists with a different canonical request fingerprint.
      content:
        application/problem+json:
          schema:
            $ref: '#/components/schemas/ApiError'
    PreconditionFailed:
      description: Durable authority, fence, phase, or lifecycle precondition failed.
      content:
        application/problem+json:
          schema:
            $ref: '#/components/schemas/ApiError'
  schemas:
    OpaqueId:
      type: string
      pattern: '^[A-Za-z0-9][A-Za-z0-9_-]{7,127}$'
    Target:
      type: object
      additionalProperties: false
      required: [store, bucket, prefix]
      properties:
        store:
          type: string
          minLength: 1
          maxLength: 128
        bucket:
          type: string
          pattern: '^[a-z0-9][a-z0-9.-]{1,61}[a-z0-9]$'
        prefix:
          type: string
          maxLength: 1024
    HttpSource:
      type: object
      additionalProperties: false
      required: [kind, url]
      properties:
        kind:
          const: http
        url:
          type: string
          format: uri
          maxLength: 8192
        credential_ref:
          type: string
          maxLength: 512
    ObjectStoreSource:
      type: object
      additionalProperties: false
      required: [kind, store, bucket, key]
      properties:
        kind:
          const: object_store
        store:
          type: string
          minLength: 1
          maxLength: 128
        bucket:
          type: string
          minLength: 3
          maxLength: 63
        key:
          type: string
          minLength: 1
          maxLength: 4096
        version_id:
          type: string
          maxLength: 1024
        credential_ref:
          type: string
          maxLength: 512
    HuggingFaceSource:
      type: object
      additionalProperties: false
      required: [kind, repository_type, repository_id, revision]
      properties:
        kind:
          const: hugging_face
        repository_type:
          type: string
          enum: [model, dataset, space]
        repository_id:
          type: string
          pattern: '^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$'
        revision:
          type: string
          minLength: 1
          maxLength: 256
        include:
          type: array
          maxItems: 1024
          uniqueItems: true
          items:
            type: string
            minLength: 1
            maxLength: 1024
        credential_ref:
          type: string
          maxLength: 512
    Source:
      oneOf:
        - $ref: '#/components/schemas/HttpSource'
        - $ref: '#/components/schemas/ObjectStoreSource'
        - $ref: '#/components/schemas/HuggingFaceSource'
      discriminator:
        propertyName: kind
        mapping:
          http: '#/components/schemas/HttpSource'
          object_store: '#/components/schemas/ObjectStoreSource'
          hugging_face: '#/components/schemas/HuggingFaceSource'
    JobSubmission:
      type: object
      additionalProperties: false
      required: [source, target]
      properties:
        source:
          $ref: '#/components/schemas/Source'
        target:
          $ref: '#/components/schemas/Target'
        label:
          type: string
          minLength: 1
          maxLength: 200
    JobPhase:
      type: string
      enum: [Queued, Running, RetryWait, Cancelling, Succeeded, Failed, Cancelled]
    JobLifecycle:
      type: string
      enum: [visible, soft_deleted, hard_deleting, hard_deleted]
    AttemptAuthority:
      type: object
      additionalProperties: false
      required: [attempt_id, fence, worker_incarnation]
      properties:
        attempt_id:
          $ref: '#/components/schemas/OpaqueId'
        fence:
          type: integer
          minimum: 1
        worker_incarnation:
          $ref: '#/components/schemas/OpaqueId'
    Progress:
      type: object
      additionalProperties: false
      required: [attempt_id, fence, completed_bytes, completed_members, observed_at]
      properties:
        attempt_id:
          $ref: '#/components/schemas/OpaqueId'
        fence:
          type: integer
          minimum: 1
        completed_bytes:
          type: integer
          minimum: 0
        total_bytes:
          type: [integer, 'null']
          minimum: 0
        completed_members:
          type: integer
          minimum: 0
        total_members:
          type: [integer, 'null']
          minimum: 0
        observed_at:
          type: string
          format: date-time
    CheckpointProjection:
      type: object
      additionalProperties: false
      required: [reusable, validated_bytes, validated_members]
      properties:
        reusable:
          type: boolean
        validated_bytes:
          type: integer
          minimum: 0
        validated_members:
          type: integer
          minimum: 0
    JobFailure:
      oneOf:
        - type: object
          additionalProperties: false
          required: [class, retryable, message]
          properties:
            class:
              type: string
              enum: [validation, authorization, source_not_found, source_changed, cancelled]
            retryable:
              const: false
            message:
              type: string
              maxLength: 500
            safe_details:
              type: object
              additionalProperties:
                type: [string, integer, boolean, 'null']
        - type: object
          additionalProperties: false
          required: [class, retryable, message]
          properties:
            class:
              type: string
              enum: [transient_source, transient_target, integrity, capacity, internal, lost_attempt]
            retryable:
              const: true
            message:
              type: string
              maxLength: 500
            safe_details:
              type: object
              additionalProperties:
                type: [string, integer, boolean, 'null']
    AttemptRuntimeFailure:
      type: object
      additionalProperties: false
      required: [class, message]
      properties:
        class:
          type: string
          enum: [authorization, source_not_found, source_changed, transient_source, transient_target, integrity, capacity, internal]
        message:
          type: string
          maxLength: 500
        safe_details:
          type: object
          additionalProperties:
            type: [string, integer, boolean, 'null']
    ResultDescriptor:
      type: object
      additionalProperties: false
      required: [kind, manifest, member_count, total_bytes]
      properties:
        kind:
          const: manifest
        manifest:
          $ref: '#/components/schemas/ObjectIdentity'
        member_count:
          type: integer
          minimum: 1
        total_bytes:
          type: integer
          minimum: 0
    ObjectIdentity:
      type: object
      additionalProperties: false
      required: [store, bucket, key]
      properties:
        store:
          type: string
        bucket:
          type: string
        key:
          type: string
        version_id:
          type: string
        checksum:
          type: string
    Job:
      type: object
      additionalProperties: false
      required: [id, owner, revision, phase, lifecycle, source, target, authoritative_attempt, progress, checkpoint, result, failure, created_at, updated_at, event_cursor]
      properties:
        id:
          $ref: '#/components/schemas/OpaqueId'
        owner:
          $ref: '#/components/schemas/OpaqueId'
        revision:
          type: integer
          minimum: 1
        phase:
          $ref: '#/components/schemas/JobPhase'
        lifecycle:
          $ref: '#/components/schemas/JobLifecycle'
        source:
          $ref: '#/components/schemas/Source'
        target:
          $ref: '#/components/schemas/Target'
        authoritative_attempt:
          oneOf:
            - $ref: '#/components/schemas/AttemptAuthority'
            - type: 'null'
        progress:
          oneOf:
            - $ref: '#/components/schemas/Progress'
            - type: 'null'
        checkpoint:
          oneOf:
            - $ref: '#/components/schemas/CheckpointProjection'
            - type: 'null'
        result:
          oneOf:
            - $ref: '#/components/schemas/ResultDescriptor'
            - type: 'null'
        failure:
          oneOf:
            - $ref: '#/components/schemas/JobFailure'
            - type: 'null'
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
        event_cursor:
          type: string
          minLength: 16
    JobPage:
      type: object
      additionalProperties: false
      required: [items, next_cursor, event_cursor]
      properties:
        items:
          type: array
          items:
            $ref: '#/components/schemas/Job'
        next_cursor:
          type: [string, 'null']
        event_cursor:
          type: string
          minLength: 16
    DeletionOperation:
      type: object
      additionalProperties: false
      required: [id, job_id, state, created_at, updated_at]
      properties:
        id:
          $ref: '#/components/schemas/OpaqueId'
        job_id:
          $ref: '#/components/schemas/OpaqueId'
        state:
          type: string
          enum: [queued, running, retry_wait, completed]
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
    ApiError:
      type: object
      additionalProperties: false
      required: [code, message, request_id]
      properties:
        code:
          type: string
          enum: [invalid_request, unauthenticated, forbidden, not_found, idempotency_conflict, precondition_failed, cursor_invalid, cursor_expired, rate_limited, unavailable, internal]
        message:
          type: string
          maxLength: 500
        request_id:
          $ref: '#/components/schemas/OpaqueId'
        fields:
          type: array
          maxItems: 100
          items:
            type: object
            additionalProperties: false
            required: [pointer, code]
            properties:
              pointer:
                type: string
                maxLength: 500
              code:
                type: string
                maxLength: 100
    ClaimRequest:
      type: object
      additionalProperties: false
      required: [operation_id, worker_incarnation]
      properties:
        operation_id:
          $ref: '#/components/schemas/OpaqueId'
        worker_incarnation:
          $ref: '#/components/schemas/OpaqueId'
    AttemptMutation:
      type: object
      required: [operation_id, fence, worker_incarnation]
      properties:
        operation_id:
          $ref: '#/components/schemas/OpaqueId'
        fence:
          type: integer
          minimum: 1
        worker_incarnation:
          $ref: '#/components/schemas/OpaqueId'
    AttemptProgressRequest:
      unevaluatedProperties: false
      allOf:
        - $ref: '#/components/schemas/AttemptMutation'
        - type: object
          required: [progress]
          properties:
            progress:
              $ref: '#/components/schemas/Progress'
    AttemptOutcomeRequest:
      unevaluatedProperties: false
      allOf:
        - $ref: '#/components/schemas/AttemptMutation'
        - type: object
          required: [outcome]
          properties:
            outcome:
              oneOf:
                - type: object
                  additionalProperties: false
                  required: [kind, result]
                  properties:
                    kind:
                      const: success
                    result:
                      $ref: '#/components/schemas/ResultDescriptor'
                - type: object
                  additionalProperties: false
                  required: [kind, failure]
                  properties:
                    kind:
                      const: failure
                    failure:
                      $ref: '#/components/schemas/AttemptRuntimeFailure'