> ## Documentation Index > Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt > Use this file to discover all available pages before exploring further. # Run a run again > Repeats a run and answers with the new one, which names the run it came from. The kind of the source decides the form: a run the platform launched drives the agent again and scores the new sessions, while a run that scored sessions which already existed scores them again and creates none. A run the client performed carries no kind to read, so its own evaluations name the sessions and metrics to score again; no new session is created, because only that client can produce one. A repetition that scores sessions answers with a "report" of what it scored, skipped and failed; one that drives the agent again reports null there, because that work is queued. ## OpenAPI ````yaml https://api.galtea.ai/openapi.json post /runs/{id}/relaunch openapi: 3.0.0 info: version: 1.0.0 title: Product Management Service API description: API documentation for Product Management Service contact: name: Galtea AI servers: - url: https://api.galtea.ai security: - bearerAuth: [] tags: [] externalDocs: description: Galtea Platform Documentation url: https://docs.galtea.ai paths: /runs/{id}/relaunch: post: tags: - runs summary: Run a run again description: >- Repeats a run and answers with the new one, which names the run it came from. The kind of the source decides the form: a run the platform launched drives the agent again and scores the new sessions, while a run that scored sessions which already existed scores them again and creates none. A run the client performed carries no kind to read, so its own evaluations name the sessions and metrics to score again; no new session is created, because only that client can produce one. A repetition that scores sessions answers with a "report" of what it scored, skipped and failed; one that drives the agent again reports null there, because that work is queued. operationId: relaunchRun parameters: - schema: type: string description: Run ID example: run_123 required: true description: Run ID name: id in: path requestBody: required: false content: application/json: schema: type: object properties: versionId: type: string minLength: 1 example: version_123 description: >- Run the repetition against a different version. Only for a run the platform launched itself; a run that scored existing sessions refuses it, because those sessions already name their version. useCurrentTestCases: type: boolean example: false description: >- Resolve the original request again instead of repeating the exact rows that ran, so test cases added since are included. On a run that scored existing sessions it also drops the metrics the source recorded, so the repetition scores with each specification's links as they stand today, which can change the metric set and the credit cost. Defaults to false, which keeps the repetition comparable with its source. responses: '201': description: Run launched again successfully content: application/json: schema: $ref: '#/components/schemas/RelaunchedRun' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/Error' security: - bearerAuth: [] components: schemas: RelaunchedRun: type: object properties: id: type: string example: run_123 productId: type: string example: product_123 versionId: type: string nullable: true example: version_123 userId: type: string nullable: true example: user_123 ordinal: type: integer example: 42 description: Per-product launch number, starting at 1 and never reused customId: type: string nullable: true example: nightly-regression description: Caller-supplied label relaunchedFromRunId: type: string nullable: true example: run_122 description: The run this one repeats, when POST /runs/{id}/relaunch minted it openedBy: type: string enum: - LAUNCH - CALLER example: LAUNCH description: >- LAUNCH when a launch endpoint opened the run, which then closes when that launch ends. CALLER when POST /runs opened it, which only POST /runs/{id}/close ends. status: type: string enum: - RUNNING - COMPLETED - FAILED - CANCELLED example: COMPLETED evaluationCount: type: integer example: 120 description: Evaluations this run launched sessionCount: type: integer example: 30 description: Distinct sessions covered by the evaluations of this run kind: type: string nullable: true enum: - GENERATE_INFERENCES - EVALUATE_SESSION - EVALUATE_SESSION_BATCH - REPLAY_METRIC - null example: GENERATE_INFERENCES description: >- The shape of work the platform performed. Null on a run the caller opened, and on one several scoring calls filled. jobId: type: string nullable: true description: >- Queue job the run dispatched, when it queued one. Null on a run the caller opened, and on one several scoring calls filled. error: type: string nullable: true description: Why the run failed, when it did request: type: object nullable: true additionalProperties: nullable: true description: >- The launch request as the platform received it. Null on a run the caller opened, and on one several scoring calls filled. resolvedInputs: type: object nullable: true additionalProperties: nullable: true description: >- What the request resolved to at dispatch: test cases, sessions and metrics. Keys depend on `kind`. Null on a run the caller opened, and on one several scoring calls filled. createdAt: type: string format: date-time finishedAt: type: string format: date-time nullable: true deletedAt: type: string format: date-time nullable: true report: type: object nullable: true properties: sessionsEvaluated: type: integer example: 28 description: Sessions the repetition scored sessionsFailed: type: integer example: 1 description: Sessions the repetition tried to score and could not evaluationsCreated: type: integer example: 56 failures: type: array items: type: object properties: sessionId: type: string error: type: string required: - sessionId - error description: One entry per failed session, naming why it failed message: type: string example: >- 28 sessions evaluated, 56 evaluations created. 2 skipped: 2 whose specification the run being repeated did not score. description: >- Human-readable outcome. A skipped session counts toward neither total, so this is the only place its cause is named. required: - sessionsEvaluated - sessionsFailed - evaluationsCreated - failures - message description: >- What the scoring did, for a repetition that scores sessions inside the request. Null when the repetition drives the agent again, whose work is queued and reports on the new run itself instead. required: - id - productId - versionId - userId - ordinal - customId - relaunchedFromRunId - openedBy - status - evaluationCount - sessionCount - kind - jobId - error - request - resolvedInputs - finishedAt - deletedAt - report Error: type: object properties: error: type: string example: Error type message: type: string example: Error message description securitySchemes: bearerAuth: type: http scheme: bearer description: >- API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (`gsk_*`) and legacy (`gsk-`) API keys are accepted, e.g. `Authorization: Bearer gsk_...` or `Authorization: Bearer gsk-...`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.