> ## Documentation Index > Fetch the complete documentation index at: https://docs.cloudhumans.com/llms.txt > Use this file to discover all available pages before exploring further. # Get a conversation summary > Lean conversation summary — status, resolution and messages — by CloudChat conversation id or your helpdesk's ticket id. An id from a project your credentials don't cover answers the same 404 as an id that does not exist. ## OpenAPI ````yaml api-reference/specs/claudia/v1.json GET /v1/conversations/{id}/summary openapi: 3.0.1 info: title: Claudia API version: 1.0.0 servers: - url: https://api.cloudhumans.com/claudia description: Production - url: https://api.cloudhumans.com/claudia/staging description: Staging security: - bearerAuth: [] tags: - name: MCP Servers description: >- The MCP servers your agents can call tools on. Registering one here is what makes its tools selectable in an agent; the credentials it needs are stored encrypted and never read back. - name: Knowledge Base Content description: Read, search and edit the content that answers your customers. - name: Content Quality description: Rewrites proposed for content that is answering your customers badly. - name: Playground description: >- Talk to one of your agents as if you were a customer, without touching a real conversation. - name: Project Settings description: >- Read and change how a ClaudIA project behaves — the settings screens of the ClaudIA app, as an API. - name: Content Improvements description: Answers Claudia proposes for questions your content does not cover yet. - name: Knowledge Bases description: The knowledge bases your account can manage. - name: Content Sources description: The sites Claudia crawls to keep a knowledge base in sync. - name: Agents description: >- The AI agents (assistants) configured for your tenant: the orchestrator (supervisor) and its specialists (react). Reads answer the same passthrough shape the platform stores; creates land as DRAFTS a human reviews and publishes in the app. - name: Agent Tools description: >- The tool catalog your agents can be given, aggregated across every MCP server registered for the tenant. This is the same catalog an assistant's mcp_servers[].tools whitelist is validated against. - name: Conversations description: >- Read access to a conversation's lean investigation summary — messages, status and resolution — and the execution trace behind one of its processed messages, without the internal processing state the hub UI's full read carries. paths: /v1/conversations/{id}/summary: get: tags: - Conversations summary: Get a conversation summary description: >- Lean conversation summary — status, resolution and messages — by CloudChat conversation id or your helpdesk's ticket id. An id from a project your credentials don't cover answers the same 404 as an id that does not exist. operationId: getConversationSummary parameters: - name: id in: path description: >- CloudChat conversation id (UUID) or your helpdesk's ticket id — when using a ticket id, `project` is required required: true schema: type: string - name: project in: query description: >- Project the conversation belongs to. REQUIRED when `id` is a helpdesk ticket id — those are only unique within a project, so without it a ticket id cannot be resolved and answers 404. Ignored for a CloudChat conversation id, which is globally unique. Discover your projects with `listMyClaudiaProjects`. required: false schema: type: string responses: '200': description: The conversation summary. content: application/json: schema: $ref: '#/components/schemas/ConversationSummary' '400': description: The request could not be answered as written. content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Missing, expired or invalid credentials. '403': description: The credentials hold no account allowed to manage this content. content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: No conversation reachable with your credentials matches this id. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit applied by the API gateway. Back off and retry. components: schemas: ConversationSummary: type: object required: - cloudChatId - projectName - status - statusAt - createdAt - messages properties: cloudChatId: type: string description: >- CloudChat's own id for this conversation (UUID). Stable, and the id this endpoint resolves without a `project`. example: 3f1c8a52-1c4e-4d0a-9a1b-2f6de2a3c111 helpdeskId: type: string description: >- The id this conversation carries in your helpdesk — the ticket number your agents quote. Absent for a conversation that never reached a helpdesk. It is also the correlation key for a ticket-side investigation. example: '48219' projectName: type: string description: >- The ClaudIA project this conversation belongs to. Always present; it is the project your credentials were checked against to return this at all. example: acme_support status: type: string description: >- Lifecycle state: `Open`, `Resolved` or `Closed`. `Resolved` means ClaudIA finished the conversation itself; read `resolutionReason` for how. example: Resolved statusAt: type: string description: >- When the conversation entered its current `status` — opened, resolved or closed at (ISO-8601). example: '2026-08-10T18:20:41' createdAt: type: string description: When the conversation was created (ISO-8601). example: '2026-08-10T14:32:05' resolutionReason: type: string description: >- Why the conversation ended the way it did, when ClaudIA recorded a reason. Absent while it is still open, and for a conversation that ended without one. example: FORWARD_TO_HUMAN isN2: type: boolean description: >- Whether the conversation was handed to a human (N2). Absent when the platform never recorded either way — read that as unknown, not as false. example: false tag: type: string description: >- The resolution/classification tag the platform attached, when it attached one. Free text set per project, so treat it as a label to read, not a fixed vocabulary. example: order_status messages: type: array description: >- Every turn of the conversation, oldest first — customer messages, ClaudIA's replies, and any internal notes (`private: true`). Attachments and transcriptions are dropped. items: $ref: '#/components/schemas/ConversationMessage' description: >- One conversation reduced to what an investigation reads: how it ended, when, and the turns that got there. The internal per-message processing state the hub UI reads is not here. Error: required: - error type: object properties: error: type: string description: What went wrong. example: 'Forbidden: token holds no claim for the requested account' description: Something the caller needs to fix. ConversationMessage: type: object required: - role - content - sendAt - private properties: id: type: string description: >- Identifies this turn. Absent for a turn the platform stored without an id (older conversations). example: 6683f1c2a4b19e0012ab34cd role: type: string description: >- Who spoke: `USER` (the customer) or `AGENT` (ClaudIA, or a human answering in its place). example: USER content: type: string description: What was said, as text. example: Onde está meu pedido? sendAt: type: string description: When the turn was sent (ISO-8601). example: '2026-08-10T14:32:05' private: type: boolean description: >- True for an internal note the customer never saw. A reply the platform recorded as private did NOT reach the customer, however finished it reads. example: false description: One turn of the conversation, reduced to what an investigation reads. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ````