> ## Documentation Index > Fetch the complete documentation index at: https://docs.devic.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get real-time chat history > Retrieves the real-time chat history from Redis cache. Use this endpoint to poll for results when using async mode. Returns status indicating if processing is still in progress. ## OpenAPI ````yaml GET /v1/assistants/{identifier}/chats/{chatUid}/realtime openapi: 3.0.0 info: title: Devic.ai Public API description: >- Devic.ai is an AI platform that allows you to create, manage, and use AI agents for various tasks. version: 1.0.0 contact: name: Devic.ai Support url: https://devic.ai x-logo: url: https://devic.ai/logo.png altText: Devic.ai Logo x-summary: Public API for interacting with Devic.ai platform servers: - url: https://api.devic.ai description: Production server - url: https://staging-api.devic.ai description: Staging server security: - bearerAuth: [] tags: - name: Environments description: >- The machine an agent works on and everything it may reach: sandbox, snapshot, knowledge, tools and encrypted variables - name: Sandboxes description: >- Start a real Linux machine on an environment, run commands and files on it, and save its snapshot - name: Projects description: Group agents, assistants, documents and costs into projects - name: Documents description: >- Knowledge base documents: create, version, attach and index markdown content for RAG - name: Document Folders description: Organise knowledge base documents into folders and attach them in bulk - name: Files description: Upload files and obtain shareable download URLs to attach to messages - name: Agents description: Endpoints related to AI agents and their operations - name: Assistants description: Endpoints for interacting with assistants and their specializations - name: Tool Servers description: Endpoints for managing tool servers and their tool definitions - name: Health description: API health check endpoints - name: Documentation description: Endpoints for retrieving markdown documentation - name: Integrations description: Connect third-party apps and turn them into tools - name: Triggers description: Start an agent or an assistant from an app event - name: Tenant Integrations description: Apps that each end user connects for themselves - name: Memory description: What an assistant remembers between conversations - name: Skills description: Reusable instruction packs for agents and assistants - name: Speech to Text description: Audio transcription - name: Tenants description: Tenants, subtenants and their usage - name: MCP Gateway description: One MCP endpoint over many servers, with visibility per user - name: Tenant Sessions description: Tokens that prove which end user is calling paths: /v1/assistants/{identifier}/chats/{chatUid}/realtime: get: tags: - Assistants summary: Get real-time chat history description: >- Retrieves the real-time chat history from Redis cache. Use this endpoint to poll for results when using async mode. Returns status indicating if processing is still in progress. operationId: getRealtimeChatHistory parameters: - name: identifier required: true in: path description: The unique identifier of the assistant specialization schema: type: string - name: chatUid required: true in: path description: The unique identifier of the chat conversation schema: type: string responses: '200': description: Real-time chat history retrieved successfully content: application/json: schema: $ref: '#/components/schemas/RealtimeChatHistoryDto' '400': description: Bad request — invalid or inconsistent payload '401': description: Unauthorized — missing or invalid API key '403': description: Forbidden — not reachable with this credential '404': description: Chat history not found security: - bearerAuth: [] components: schemas: RealtimeChatHistoryDto: type: object properties: chatUID: type: string example: 550e8400-e29b-41d4-a716-446655440000 clientUID: type: string example: client-123 chatHistory: type: array items: $ref: '#/components/schemas/ChatMessageDto' status: type: string enum: - processing - completed - error - handed_off - buffering - waiting_for_tool_response - limit_exceeded example: processing lastUpdatedAt: type: number example: 1706000000000 queuedMessages: type: number example: 0 pendingUserMessages: type: array items: $ref: '#/components/schemas/ChatMessageDto' pendingToolCalls: description: Pending tool calls awaiting client-side execution type: array items: $ref: '#/components/schemas/ToolCallDto' handedOffSubThreadId: type: string description: Subagent thread ID (when status is handed_off) example: 64f5a5b8c123456789abcdef stopReason: type: string description: System stop reason (e.g. max_chat_messages_reached, error) example: max_chat_messages_reached recalledMemories: description: >- Memory-recall events of the in-flight run (source, query, facts/entities surfaced) type: array items: type: string limitExceeded: type: object description: Usage-limit details (when status is limit_exceeded) required: - chatUID - clientUID - chatHistory - status - lastUpdatedAt ChatMessageDto: type: object description: A single message of a conversation, as the platform stored it. properties: uid: type: string description: Unique message id example: 75ecbcfc-a3be-43ba-8da6-b3e16e8d7280 chatUid: type: string description: Conversation this message belongs to example: 550e8400-e29b-41d4-a716-446655440000 role: type: string enum: - user - assistant - developer - tool description: >- Who the message is from. `developer` messages are the ones the platform injects (current date, injected context) and can be ignored by most clients. content: type: object description: Body of the message. properties: message: type: string description: The text. This is the field to render. example: I would recommend a 450 W monocrystalline panel. data: type: object additionalProperties: true description: >- Structured payload, when the assistant is configured with a structured output. files: type: array description: >- Files carried by the message, echoed in the same shape they were sent in. items: type: object properties: name: type: string example: invoice.pdf donwloadUrl: type: string example: https://files.devic.ai/uploads/invoice.pdf fileType: type: string enum: - IMAGE - DOCUMENT - VIDEO - AUDIO - ELECTRICITY_BILL - OTHER example: DOCUMENT timestamp: type: number description: Unix timestamp in milliseconds example: 1706000000000 userUID: type: string description: Identity the message was written under example: api-key:42 summary: type: string description: >- Short AI-generated summary of the message, unless summarisation was skipped example: The user asks which panels to install on a 60 m2 roof. contentSource: type: string description: >- Where `content.message` came from when the model did not write it. `finish_tool` means the reply was taken from the finish tool's `message` argument, so it can be read without parsing tool calls. Absent on messages the model wrote itself. example: finish_tool tool_calls: type: array items: $ref: '#/components/schemas/ToolCallDto' description: Tool calls the assistant made on this message tool_call_id: type: string description: On `tool` messages, the call this message answers example: call_abc123 latencyMs: type: number description: How long the model or the tool took, in milliseconds example: 1045 messageTokenUsage: type: object description: Tokens this message accounted for properties: inputTokens: type: number outputTokens: type: number inputCachedTokens: type: number inputCacheWriteTokens: type: number outputCachedTokens: type: number reasoningOutputTokens: type: number totalTokens: type: number provider: type: string model: type: string reasoningEffort: type: string enum: - none - minimal - low - medium - high - xhigh - max description: Reasoning effort recorded for this model response. messageCost: type: object description: What this message cost, at the pricing in force when it ran properties: inputCost: type: number outputCost: type: number inputCachedCost: type: number inputCacheWriteCost: type: number outputCachedCost: type: number reasoningOutputCost: type: number totalCost: type: number currency: type: string example: USD calculatedAt: type: number ToolCallDto: type: object properties: id: type: string example: call_abc123 description: Unique tool call ID type: type: string example: function description: Tool call type function: type: object description: Function call details example: name: get_user_location arguments: '{}' required: - id - type - function securitySchemes: bearerAuth: type: http scheme: bearer description: >- An API key from your Devic console, sent as `Authorization: Bearer `. An embedded front end sends a tenant-session token instead, so no API key reaches the browser, and an OAuth integration sends its access token. Missing, invalid or expired credentials get a `401`. See [Authentication](/api-reference/introduction#authentication). ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.