> ## Documentation Index > Fetch the complete documentation index at: https://docs.lightdash.com/llms.txt > Use this file to discover all available pages before exploring further. # Get AI agent thread dump > Download a sanitized debug dump of an AI agent thread for troubleshooting. Requires AI_COPILOT_THREAD_DUMP_ENABLED on the instance. ## OpenAPI ````yaml https://raw.githubusercontent.com/lightdash/lightdash/refs/heads/main/packages/backend/src/generated/swagger.json get /api/v1/aiAgents/admin/threads/{threadUuid}/dump openapi: 3.0.0 info: title: Lightdash API version: 1.194.0 description: > Open API documentation for all public Lightdash API endpoints. # Authentication Before you get started, you might need to create a Personal Access Token to authenticate via the API. You can create a token by following this guide: https://docs.lightdash.com/references/personal_tokens license: name: MIT contact: name: Lightdash Support email: support@lightdash.com url: https://docs.lightdash.com/help-and-contact/contact/contact_info/ servers: - url: / security: [] tags: - name: My Account description: These routes allow users to manage their own user account. - name: Organizations description: >- Each user is a member of a single organization. These routes allow users to manage their organization. Most actions are only available to admin users. - name: Projects description: >- Projects belong to a single organization. These routes allow users to manage their projects, browse content, and execute queries. Users inside an organization might have access to a project from an organization-level role or they might be granted access to a project directly. - name: Spaces description: >- Spaces allow you to organize charts and dashboards within a project. They also allow granular access to content by allowing you to create private spaces, which are only accessible to the creator and admins. - name: Roles & Permissions description: >- These routes allow users to manage roles and permissions for their organization. externalDocs: url: https://docs.lightdash.com/references/roles - name: Query description: >- These routes allow users to execute and manage queries against their data warehouse. This includes metric queries, SQL queries, and retrieving query results. paths: /api/v1/aiAgents/admin/threads/{threadUuid}/dump: get: summary: Get AI agent thread dump description: >- Download a sanitized debug dump of an AI agent thread for troubleshooting. Requires AI_COPILOT_THREAD_DUMP_ENABLED on the instance. operationId: getAdminThreadDump parameters: - in: path name: threadUuid required: true schema: $ref: '#/components/schemas/UUID' responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ApiAiAgentThreadDumpResponse' default: description: Error content: application/json: schema: $ref: '#/components/schemas/ApiErrorPayload' security: [] components: schemas: UUID: type: string format: uuid description: |- Stringified UUIDv4. See [RFC 4112](https://tools.ietf.org/html/rfc4122) pattern: >- [0-9A-Fa-f]{8}-[0-9A-Fa-f]{4}-4[0-9A-Fa-f]{3}-[89ABab][0-9A-Fa-f]{3}-[0-9A-Fa-f]{12} ApiAiAgentThreadDumpResponse: $ref: '#/components/schemas/ApiSuccess_AiAgentThreadDump_' ApiErrorPayload: properties: error: properties: data: $ref: '#/components/schemas/AnyType' description: Optional data containing details of the error message: type: string description: A friendly message summarising the error name: type: string description: Unique name for the type of error statusCode: type: number format: integer description: HTTP status code required: - name - statusCode type: object status: type: string enum: - error nullable: false required: - error - status type: object description: |- The Error object is returned from the api any time there is an error. The message contains ApiSuccess_AiAgentThreadDump_: properties: results: $ref: '#/components/schemas/AiAgentThreadDump' status: type: string enum: - ok nullable: false required: - results - status type: object AnyType: description: |- This AnyType is an alias for any The goal is to make it easier to identify any type in the codebase without having to eslint-disable all the time These are only used on legacy `any` types, don't use it for new types. This is added on a separate file to avoid circular dependencies. AiAgentThreadDump: properties: turns: items: $ref: '#/components/schemas/AiAgentThreadDumpTurn' type: array agent: allOf: - $ref: '#/components/schemas/AiAgentThreadDumpAgent' nullable: true title: type: string nullable: true createdFrom: $ref: '#/components/schemas/AiThreadCreatedFrom' userUuid: type: string nullable: true agentUuid: type: string nullable: true threadUuid: type: string projectUuid: type: string organizationUuid: type: string defaultProvider: type: string lightdashVersion: type: string generatedAt: type: string schemaVersion: type: number enum: - 1 nullable: false required: - turns - agent - title - createdFrom - userUuid - agentUuid - threadUuid - projectUuid - organizationUuid - defaultProvider - lightdashVersion - generatedAt - schemaVersion type: object AiAgentThreadDumpTurn: properties: artifacts: items: $ref: '#/components/schemas/AiAgentThreadDumpArtifact' type: array toolCalls: items: $ref: '#/components/schemas/AiAgentThreadDumpToolCall' type: array tokenUsage: allOf: - $ref: '#/components/schemas/AiPromptTokenUsage' nullable: true modelConfig: properties: modelProvider: type: string modelName: type: string required: - modelProvider - modelName type: object nullable: true steers: items: type: string type: array feedback: properties: comment: type: string nullable: true score: type: number format: double required: - comment - score type: object nullable: true interrupted: type: boolean error: type: string nullable: true assistant: type: string nullable: true user: type: string hidden: type: boolean respondedAt: type: string nullable: true createdAt: type: string promptUuid: type: string required: - artifacts - toolCalls - tokenUsage - modelConfig - steers - feedback - interrupted - error - assistant - user - hidden - respondedAt - createdAt - promptUuid type: object AiAgentThreadDumpAgent: $ref: >- #/components/schemas/Pick_AiAgentSummary.uuid-or-name-or-instruction-or-tags-or-integrations-or-modelConfig-or-enableDataAccess-or-enableSelfImprovement-or-enableContentTools-or-enableUserContext-or-enableSqlMode-or-adminOnly-or-version_ AiThreadCreatedFrom: type: string enum: - slack - web_app - evals - scheduler AiAgentThreadDumpArtifact: properties: dashboardConfig: allOf: - $ref: '#/components/schemas/Record_string.unknown_' nullable: true chartConfig: allOf: - $ref: '#/components/schemas/Record_string.unknown_' nullable: true description: type: string nullable: true title: type: string nullable: true artifactType: type: string enum: - chart - dashboard versionNumber: type: number format: double versionUuid: type: string artifactUuid: type: string required: - dashboardConfig - chartConfig - description - title - artifactType - versionNumber - versionUuid - artifactUuid type: object AiAgentThreadDumpToolCall: properties: isError: type: boolean resultOmitted: type: string nullable: true result: type: string nullable: true args: {} source: type: string enum: - lightdash - mcp name: type: string parentToolCallId: type: string nullable: true toolCallId: type: string required: - isError - resultOmitted - result - args - source - name - parentToolCallId - toolCallId type: object AiPromptTokenUsage: properties: finalStepTotalTokens: type: number format: double description: >- Final step's total — the proxy for resident context size, drives compaction. totalTokens: type: number format: double description: 'Billing figure: tokens summed across every step of the run.' required: - totalTokens type: object description: >- Persisted shape. `finalStepTotalTokens` is absent on rows written before it existed. Pick_AiAgentSummary.uuid-or-name-or-instruction-or-tags-or-integrations-or-modelConfig-or-enableDataAccess-or-enableSelfImprovement-or-enableContentTools-or-enableUserContext-or-enableSqlMode-or-adminOnly-or-version_: properties: name: type: string uuid: type: string version: type: number format: double integrations: items: properties: channelId: type: string type: type: string enum: - slack nullable: false required: - channelId - type type: object type: array tags: items: type: string type: array nullable: true instruction: type: string nullable: true enableDataAccess: type: boolean enableSelfImprovement: type: boolean enableContentTools: type: boolean enableUserContext: type: boolean enableSqlMode: type: boolean adminOnly: type: boolean modelConfig: allOf: - $ref: '#/components/schemas/AiAgentModelConfig' nullable: true required: - name - uuid - version - integrations - tags - instruction - enableDataAccess - enableSelfImprovement - enableContentTools - enableUserContext - enableSqlMode - adminOnly - modelConfig type: object description: From T, pick a set of properties whose keys are in the union K Record_string.unknown_: properties: {} additionalProperties: {} type: object description: Construct a type with a set of properties K of type T AiAgentModelConfig: properties: reasoning: type: boolean modelProvider: type: string modelName: type: string required: - modelProvider - modelName type: object ````