> ## Documentation Index > Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details. # List Simulation Runs > List simulation runs, optionally filtered by scenarioSetId or batchRunId. Set-level and unfiltered listings trim each run to its first few messages and report the trim as `messagesTruncated`; pass `include=messages` to read whole conversations, which caps the page at 20 runs, ending on a batch boundary. A batch-scoped listing always carries whole conversations. ## OpenAPI ````yaml GET /api/v1/simulation-runs openapi: 3.1.0 info: title: LangWatch API description: LangWatch openapi spec version: 1.0.0 servers: - url: https://app.langwatch.ai security: - project_api_key: [] paths: /api/v1/simulation-runs: get: description: >- List simulation runs, optionally filtered by scenarioSetId or batchRunId. Set-level and unfiltered listings trim each run to its first few messages and report the trim as `messagesTruncated`; pass `include=messages` to read whole conversations, which caps the page at 20 runs, ending on a batch boundary. A batch-scoped listing always carries whole conversations. operationId: getApiSimulationRuns parameters: - in: query name: scenarioSetId schema: type: string - in: query name: batchRunId schema: type: string - in: query name: limit schema: default: 20 type: integer exclusiveMinimum: 0 maximum: 100 - in: query name: cursor schema: type: string - in: query name: include schema: type: string const: messages description: >- Pass `messages` to read whole conversations instead of the first few messages of each run. The page size is capped at 20 runs when set, and ends on a batch boundary. responses: '200': description: Success content: application/json: schema: type: object properties: runs: type: array items: type: object properties: scenarioId: type: string batchRunId: type: string scenarioRunId: type: string scenarioSetId: type: string name: type: - string - 'null' description: type: - string - 'null' status: type: string results: anyOf: - type: object properties: verdict: type: - string - 'null' reasoning: type: - string - 'null' metCriteria: type: array items: type: string unmetCriteria: type: array items: type: string inconclusiveCriteria: description: >- Criteria the judge could not check because the evidence was missing. Each is also in `unmetCriteria`. type: array items: type: string criteria: description: >- Each criterion with its status (`passed`, `failed` or `inconclusive`) and the judge's reasoning for it, in the order the scenario declares them. Runs from SDKs before per-criterion verdicts carry an empty reasoning. type: array items: type: object properties: criterion: type: string requirement: type: string status: type: string enum: - passed - failed - inconclusive reasoning: default: '' type: string required: - criterion - status - reasoning additionalProperties: false error: type: - string - 'null' evaluations: description: >- One result per evaluator that ran on the scenario. Absent on a run with no evaluators, and on servers that predate evaluators. type: array items: type: object properties: evaluatorId: type: string name: type: string status: type: string enum: - passed - failed - scored - skipped - error required: type: boolean passed: type: boolean score: type: number label: type: string details: type: string cost: type: object properties: currency: type: string amount: type: number required: - currency - amount additionalProperties: false inputs: type: object propertyNames: type: string additionalProperties: type: string required: - evaluatorId - name - status - required additionalProperties: false additionalProperties: false - type: 'null' messages: type: array items: type: object properties: role: type: string content: type: string required: - role - content additionalProperties: false messagesTruncated: description: >- True when `messages` holds only the first few messages of a longer conversation. Pass `include=messages` to read them all. type: boolean timestamp: type: number updatedAt: type: number durationInMs: type: number totalCost: type: number roleCosts: type: object propertyNames: type: string additionalProperties: type: array items: type: number roleLatencies: type: object propertyNames: type: string additionalProperties: type: array items: type: number note: description: >- One short line saying why the run was started, as given when it was queued. Null on a run started without one. type: - string - 'null' scenarioVersion: description: >- The version of the scenario at the moment the run was queued. Null on runs recorded before versions existed. anyOf: - type: integer minimum: -9007199254740991 maximum: 9007199254740991 - type: 'null' platformUrl: type: string format: uri required: - scenarioId - batchRunId - scenarioRunId - name - description - status - results - messages - timestamp - updatedAt - durationInMs - platformUrl additionalProperties: false hasMore: type: boolean nextCursor: type: string required: - runs additionalProperties: false security: - project_api_key: [] components: securitySchemes: project_api_key: type: apiKey in: header name: X-Auth-Token description: >- Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.