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

# List RAFT rounds

> This workspace's RAFT rounds, newest first (max 200), read-only. A round samples prompts, generates candidates, keeps judge-approved winners, and distills them into an SFT job (produced_job_id). Rounds are started from the dashboard today; there is no public start endpoint yet, so this surface is observability parity. Requires an owner/admin key.



## OpenAPI

````yaml /openapi.json get /v1/raft/rounds
openapi: 3.1.0
info:
  title: Omnia Management API
  description: >-
    The management API behind the improvement loop: capture and setup, request
    logs and datasets, grades (labels), judges (criteria), evals and deploy
    gates, fine-tuning and reinforcement learning, dedicated GPU endpoints, and
    model aliases and versions. Authenticated with a workspace API key
    (sk_sovereign_...). The inference API (chat, embeddings, rerank, responses)
    is OpenAI-compatible and documented separately.


    Responses are snake_case, list endpoints on the loop products use the
    {"object": "list", "data": [...]} envelope, and refusals use the same nested
    error shape the gateway emits: {"error": {"message", "type", "code"}}.
    Request bodies on the loop products (logs, labels, criteria, evals,
    datasets, aliases) are snake_case; the training and infrastructure products
    (fine-tuning, GRPO, environment tools, dedicated, model-version adoption)
    validate camelCase bodies, and each schema below says which it is. Endpoints
    that spend money require a key minted by a workspace owner or admin and
    return 403 otherwise.
  version: 1.0.0
servers:
  - url: https://gateway.omnia-voice.com
    description: Production
  - url: https://platform.omnia-voice.com/api
    description: Production (legacy alias — same API, older base URL)
security:
  - bearerAuth: []
paths:
  /v1/raft/rounds:
    get:
      tags:
        - Reinforcement learning
      summary: List RAFT rounds
      description: >-
        This workspace's RAFT rounds, newest first (max 200), read-only. A round
        samples prompts, generates candidates, keeps judge-approved winners, and
        distills them into an SFT job (produced_job_id). Rounds are started from
        the dashboard today; there is no public start endpoint yet, so this
        surface is observability parity. Requires an owner/admin key.
      operationId: listRaftRounds
      responses:
        '200':
          description: The rounds.
          content:
            application/json:
              schema:
                type: object
                properties:
                  rounds:
                    type: array
                    items:
                      $ref: '#/components/schemas/RaftRound'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
components:
  schemas:
    RaftRound:
      type: object
      properties:
        id:
          type: string
        status:
          type: string
          description: >-
            SKIPPED is a real outcome, not a crash: the round finished but no
            prompt cleared the winner floor, so there was nothing to train on.
          enum:
            - RUNNING
            - COMPLETED
            - SKIPPED
            - FAILED
        criterion_name:
          type: string
          description: The judge whose scores picked winners.
        policy_model:
          type: string
        prompt_count:
          type: integer
        candidates_per_prompt:
          type: integer
        winners_count:
          type: integer
        giveups_count:
          type: integer
          description: Prompts with zero winners; they feed the GRPO-candidate queue.
        produced_job_id:
          type:
            - string
            - 'null'
          description: >-
            The SFT job a COMPLETED round produced. Cross-link it into GET
            /v1/fine_tuning/jobs/{id}.
        skip_reason:
          type:
            - string
            - 'null'
          description: Set only for SKIPPED rounds.
        budget_usd:
          type:
            - number
            - 'null'
          description: >-
            The round's hard spend cap. Null on rounds created before budgets
            existed.
        spent_usd:
          type: number
          description: >-
            Ledger-true rollout + judge spend under this round's billing prefix.
            0 for pre-budget rounds, whose spend wasn't round-scoped.
        created_at:
          type: string
        completed_at:
          type:
            - string
            - 'null'
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
              description: >-
                invalid_request_error, insufficient_quota, rate_limit_error, or
                api_error.
            code:
              type: string
              description: >-
                Machine-stable cause, e.g. invalid_api_key, not_found,
                insufficient_permissions, precondition_failed.
          required:
            - message
            - type
            - code
      description: >-
        Every refusal — gateway and management API alike — uses this one
        envelope.
  responses:
    Unauthorized:
      description: Missing, malformed, or revoked API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              message: Invalid API key
              type: invalid_request_error
              code: invalid_api_key
    Forbidden:
      description: The key lacks the required owner/admin permission.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your workspace API key, e.g. `sk_sovereign_...`, sent as `Authorization:
        Bearer <key>`.

````