> ## Documentation Index > Fetch the complete documentation index at: https://api-docs.datagol.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Conversation Messages > Retrieves a chronologically ordered list of user messages, AI responses, and deep system agent routing execution data for a specific conversation thread. ## OpenAPI ````yaml /openapi/agents-openapi.yaml get /conversations/{conversationId}/messages openapi: 3.1.0 info: title: DataGOL Custom Agents API description: >- Complete API for creating, configuring, sharing, and interacting with Custom AI Agents on the DataGOL platform. Covers agent CRUD, permissions, conversations, and streaming. version: 1.0.0 contact: name: DataGOL Support url: https://datagol.ai servers: - url: https://be.datagol.ai description: Backend API (Production) — agent management, conversations, permissions - url: https://ai.datagol.ai description: AI Core (Production) — streaming, chat completion, conversation naming security: - ServiceAccountAuth: [] - BearerAuth: [] tags: - name: Custom Agents description: Create, read, and manage Custom AI Agents. - name: Permissions description: View and manage who has access to an agent. - name: Conversations description: Open and list conversation sessions backed by an agent. - name: Messaging description: Send messages and stream AI responses. - name: Reference Data description: >- Lookup APIs for workspaces, connectors, and team members used when building agent configs. paths: /conversations/{conversationId}/messages: get: tags: - Messaging summary: Get Conversation Messages description: >- Retrieves a chronologically ordered list of user messages, AI responses, and deep system agent routing execution data for a specific conversation thread. operationId: getConversationMessages parameters: - name: conversationId in: path required: true description: The unique UUID identifying the conversation thread. schema: type: string format: uuid example: 6718e680-194b-47fb-b8f6-029b35565b99 responses: '200': description: >- A JSON array containing the message history list along with agent analytics metadata. content: application/json: schema: type: array items: $ref: '#/components/schemas/ConversationMessage' example: - id: 7902 conversationId: c920e1f5-2ac7-4f17-aed7-b260e464c022 userId: 206 userQuery: Can you do a RFM analysis on this data? modelResponse: - code: null data: >- Here’s the plan and step-by-step pseudo-code for the RFM analysis, followed by a complete, executable Python script... ```python import pandas as pd import numpy as np... type: TEXT state: null message: null metadata: null uiMetadata: null messageMetadata: chainId: '1762280699' agentType: NewPythonAgent workbookId: null executionData: - content: |- ... response_type: dataframe - content: agent: Expert Selector model: o4-mini response_type: tool_start - content: input: 'Reasoning Effort: medium' action: Thinking response_type: tool_call - content: |- requires_dataset: true expert: "Data Analyst" confidence: 9 response_type: processing isPinned: false timestamp: '2025-11-04T18:24:59.695784Z' feedback: null components: schemas: ConversationMessage: type: object properties: id: type: integer description: Internal unique message identifier. example: 7902 conversationId: type: string format: uuid description: Back-reference to the parent conversation UUID. example: c920e1f5-2ac7-4f17-aed7-b260e464c022 userId: type: integer description: The structural ID of the user authoring the text. example: 206 userQuery: type: string description: The exact prompt raw input supplied by the user. example: Can you do some analysis on this data? modelResponse: type: array description: Content block payload parts yielded by the processing model. items: $ref: '#/components/schemas/ModelResponseBlock' uiMetadata: type: object nullable: true description: Client UI specific flags or tracking configurations. messageMetadata: $ref: '#/components/schemas/MessageMetadata' isPinned: type: boolean description: Flags whether this thread item was pinned in the interface. example: false timestamp: type: string format: date-time description: Message generation window log timestamp. example: '2025-11-04T18:24:59.695784Z' feedback: type: object nullable: true description: User satisfaction feedback payload data. ModelResponseBlock: type: object properties: code: type: string nullable: true description: Isolated code segment if format type requires extraction. data: type: string description: Main textual response or markdown block data string. example: Here's the plan and step-by-step pseudo-code for the RFM analysis... type: type: string description: Format payload classification tag. example: TEXT state: type: string nullable: true message: type: string nullable: true metadata: type: object nullable: true MessageMetadata: type: object properties: chainId: type: string description: Unique orchestration trace track ID. example: '1762280699' agentType: type: string description: The core executing processor class tag name. example: NewPythonAgent workbookId: type: string nullable: true executionData: type: array description: Step traces recording diagnostic multi-agent tool execution steps. items: $ref: '#/components/schemas/ExecutionTraceItem' ExecutionTraceItem: type: object properties: content: oneOf: - type: string description: Text data, raw code string, or HTML dataframe representations. - type: object description: Structured structural step metadata maps. example: agent: Expert Selector model: o4-mini response_type: type: string description: Internal node process event tags classification. example: tool_start securitySchemes: ServiceAccountAuth: type: apiKey in: header name: x-auth-token description: > For server-to-server or automated access, use a DataGOL Service Account key. Pass it via the `x-auth-token` header instead of `Authorization`: `x-auth-token: ` BearerAuth: type: http scheme: bearer bearerFormat: JWT description: > JWT token issued by the DataGOL Identity Provider. Embed `Authorization: Bearer ` in every request. Tokens contain `companyId`, `userId`, `roles`, and `permissions` claims. ````
user_id email full_name