> ## Documentation Index > Fetch the complete documentation index at: https://docs.alakazam.gg/llms.txt > Use this file to discover all available pages before exploring further. # Review an episode (confirm or overrule the machine verdict) > Record a human verdict on one GENERATED episode of this campaign's runs: `confirm` keeps the machine gate verdict, `overrule` flips it (an accepted episode drops out of delivery; a rejected one is kept). Only graded episodes (machine status accept/reject) are reviewable , a pending or still-rendering episode returns 409. Unreviewed episodes trust the machine verdict at delivery. Reviewing is FREE, billing happens once, at deliver time. ## OpenAPI ````yaml /forge-api-v1.yaml post /api/workbench/campaigns/{campaign_id}/review openapi: 3.0.3 info: title: Alakazam Forge API version: '1.0' description: | The Forge Dataset Workbench API: upload or import robotics datasets, audit them, propose and run augmentation campaigns, review, and deliver. Served by the Forge workbench service at forge.alakazam.gg (not api.alakazam.gg). servers: - url: https://forge.alakazam.gg description: Forge (Dataset Workbench) security: [] tags: - name: Dataset Workbench description: | **Served at `https://forge.alakazam.gg`** (not the main API host). The Forge Dataset Workbench is the client surface of the robotics data-augmentation service: bring a LeRobot robot dataset, a public Hugging Face repo, a resumable chunked upload, or a one-click curated sample, and walk one owner-scoped **campaign** through the spine Source & Health → Sample → Transform → Run + Verify → Deliver, leaving with a verified augmented dataset. Every endpoint requires a **Supabase user access token** (`Authorization: Bearer …`, the `UserAuth` scheme); a missing or invalid token returns `401`, and another user's campaigns, runs, and uploads read as `404`. Errors use the platform envelope `{"detail": "…"}`. Nothing bills until **Deliver**, which charges 1 credit per never-before-billed kept episode from your credits wallet. - name: Playground batches description: | The Forge playground's "describe a change" flow is not a REST surface on this host: a described change is submitted as a **scenario batch** through the platform (the Supabase RPC `create_scenario_batch`) and its progress/results stream back over Supabase realtime on the `scenario_batches` table. For the equivalent public REST surface, see **Scenario Studio** (`/v1/scenario-batches`). paths: /api/workbench/campaigns/{campaign_id}/review: servers: - url: https://forge.alakazam.gg description: Forge (Dataset Workbench) post: tags: - Dataset Workbench summary: Review an episode (confirm or overrule the machine verdict) description: > Record a human verdict on one GENERATED episode of this campaign's runs: `confirm` keeps the machine gate verdict, `overrule` flips it (an accepted episode drops out of delivery; a rejected one is kept). Only graded episodes (machine status accept/reject) are reviewable , a pending or still-rendering episode returns 409. Unreviewed episodes trust the machine verdict at delivery. Reviewing is FREE, billing happens once, at deliver time. parameters: - name: campaign_id in: path required: true schema: type: string requestBody: required: true content: application/json: schema: type: object required: - episode - verdict properties: episode: type: string description: >- The generated episode's `name` (from the run job's episodes). verdict: type: string enum: - confirm - overrule note: type: string description: Optional reviewer note stored on the verdict. responses: '200': description: The updated campaign content: application/json: schema: $ref: '#/components/schemas/WorkbenchCampaign' '400': description: Verdict must be confirm or overrule content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Authentication required content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: >- Campaign not found, or the episode is not part of this campaign's runs. content: application/json: schema: $ref: '#/components/schemas/Error' '409': description: Episode is not graded yet, review it when verification finishes. content: application/json: schema: $ref: '#/components/schemas/Error' security: - UserAuth: [] components: schemas: WorkbenchCampaign: type: object description: > A Dataset Workbench campaign (owner view): one walk of the augmentation spine over one source dataset. `stage` is the FURTHEST stage reached and never rolls back. Internal bookkeeping (owner, dataset/cache locations) is never surfaced. The set of already-billed episodes is tracked server-side but not exposed here, the deliver response reports how many episodes each delivery billed. properties: campaign_id: type: string example: camp_1f2e3d4c5b6a name: type: string description: >- Display name, the repo's last path segment, the sample's label, or the upload's campaign_name. repo_id: type: string description: >- The source dataset: a Hugging Face repo id, or the upload's name for uploaded datasets. engine: type: string description: >- The augmentation engine (embodiment + pipeline) this campaign runs on. stage: type: string enum: - source - sample - transform - run - deliver description: Furthest stage reached on the spine (monotonic). episodes: type: integer description: Episode count of the SOURCE dataset. health: type: object nullable: true additionalProperties: true description: >- The dataset health report once computed (null before): episode count, detected `classes` ({class: count}), the active `target_class` + `class_column`, `arm_split`, release stats, the `eligible_pool`, `exclusions`, and a motion-envelope `p99_summary`. health_status: type: string enum: - idle - computing - ready - failed description: >- Health lifecycle. `failed` carries no report; re-POST …/health to retry. sample: type: object nullable: true description: >- The saved sample (null until POST …/sample): the selected SOURCE episodes the transforms operate on. properties: selected: type: array items: type: integer count: type: integer plan: type: object nullable: true description: The saved transformation plan (null until POST …/plan). properties: transformations: type: array items: type: object additionalProperties: true description: >- One transformation, e.g. { kind: "newtraj", params: { n_candidates, n_target } }. saved_utc: type: string format: date-time run_ids: type: array items: type: string description: Run job ids, oldest first. Poll each at GET /api/aug/jobs/{job_id}. reviews: type: object description: >- Per-episode human verdicts, keyed by episode name: { verdict: confirm|overrule, by, at, note? }. Unreviewed episodes trust the machine gate verdict. additionalProperties: type: object properties: verdict: type: string enum: - confirm - overrule by: type: string example: owner at: type: string format: date-time note: type: string delivery: type: object nullable: true additionalProperties: true description: >- Delivery state (null until POST …/deliver): `status` walks exporting → exported (→ publishing → published when a target_repo was given) or `failed` (with `error`), plus `export_dir`, `count`, the exported `episodes`, per-`families` counts, a `format_note`, and timestamps. dataset_source: type: string nullable: true description: >- `sample`, `upload`, or `remote_uri` (imported from S3/GCS/Azure/https via source_uri); absent for a plain Hugging Face repo campaign. provenance: type: object nullable: true additionalProperties: true description: >- Where the dataset came from, e.g. { source: sample, sample_id, opened_utc } or { source: upload, upload_id, manifest_sha, files, layout_notes, ingested_utc }. target_class: type: string nullable: true description: >- Per-campaign target-class override chosen via POST …/target (absent = the engine default). created_utc: type: string format: date-time updated_utc: type: string format: date-time cost: type: object description: Computed render spend across the campaign's runs. properties: renders: type: integer est_usd: type: number head_stats: type: object description: >- Cumulative per-head accept/reject yield across the campaign's prior runs ({head episode: {accepted, rejected}}), the learned-yield seed a top-up run carries forward. additionalProperties: type: object properties: accepted: type: integer rejected: type: integer Error: type: object properties: detail: type: string description: Human-readable error message. errors: type: array items: type: string description: Field-level validation errors (e.g. on 422 from POST /v1/worlds). schemaVersion: type: string required: - detail securitySchemes: UserAuth: type: http scheme: bearer description: > Either a Supabase user access token (from a password login, or the passwordless magic-link flow) or a long-lived `forge_sk_…` API key. Both are sent as `Authorization: Bearer ` and resolve to the same owner, so every endpoint accepts either. Session tokens expire in ~1h; API keys do not expire and are the credential for MCP clients, CI, and partner integrations. ````