> ## Documentation Index > Fetch the complete documentation index at: https://docs.replicas.dev/llms.txt > Use this file to discover all available pages before exploring further. # Fork Workspace Chat > Continues an existing chat on another coding agent harness in the same workspace. The source chat is left unchanged. Returns as soon as the forked chat exists, with `fork.state` set to `preparing`. The sanitized transcript handoff and the first turn run in the background, after which `fork.state` becomes `ready` or `failed`. The workspace must be active. ## OpenAPI ````yaml /openapi.json post /v1/workspaces/{workspaceId}/chats/{chatId}/fork openapi: 3.1.0 info: title: Replica API version: 2.0.0 description: >- The Replica API allows you to programmatically manage cloud workspaces for AI agents. Use this API to manage environments (the org-scoped primitive workspaces are created from — including variables, files, skills, MCPs, warm hooks, start hooks, and warm pools), create and manage replicas, send messages, manage chats, stream events, read connected repositories and repository sets, and configure automations. servers: - url: https://api.replicas.dev description: Production API security: - apiKey: [] tags: - name: Environments description: >- Manage environments — the primitive that workspaces are created from. Variables, files, skills, MCPs, warm-hooks, and warm-pools are all scoped to an environment. Every organization has a singleton Global environment whose values apply to every workspace. Personal environments are scoped to the authenticated user and can be standalone or source-backed by a team environment. - name: Repository description: >- Read repositories and repository sets connected to your organization. Repositories are the underlying GitHub-connection layer; bind them to an environment to use them in workspaces. - name: Replica description: >- Manage replicas (workspaces) for AI agents. Workspace creation with `POST /v1/replica` accepts API keys and workspace engine-secret authentication. Other Replica operations also accept logged-in user JWTs from first-party clients. - name: Terminal description: Manage interactive terminal sessions in active workspaces - name: Tunnels description: Create short-lived authenticated transports to active workspaces - name: Preview description: Manage public preview URLs for workspace ports - name: Profile description: Read and update the authenticated user's profile - name: Credentials description: >- Manage coding-agent credentials for an organization or the authenticated user - name: Preferences description: Manage organization behavior preferences - name: Organization roles description: >- Manage custom roles and member role assignments. Organization admins retain full access independently of custom roles. - name: Slack description: Connect Slack identities and route threads to Replicas workspaces - name: Linear description: Connect Linear identities to Replicas accounts - name: Automation description: >- Create and manage automations that trigger replicas on a schedule or in response to events - name: Downloads description: Download Replicas applications - name: Media description: >- Read workspace media and obtain short-lived download or inline preview URLs - name: Analytics description: >- Read aggregated activity and usage metrics for your organization: compute minutes, workspaces created by source, and pull request throughput over a time range. - name: Presence description: >- Read and report ephemeral member presence: who is online, where they are (environment or workspace), and whether they are typing. Presence is backed by short-lived keys rather than the database and broadcast to other members over the events stream. - name: Plugins description: >- Install and manage native and Composio-backed workspace plugins. A plugin installs for a single environment, for the whole organization (which uses the Global environment), or for one member personally. A workspace uses the most specific installation available: personal, then its own environment, then the environment it was branched from, then Global. Composio Connect Links host managed OAuth, custom OAuth, API-key, bearer-token, basic, and dynamic OAuth authentication without exposing provider credentials to Replicas. paths: /v1/workspaces/{workspaceId}/chats/{chatId}/fork: post: tags: - Replica summary: Fork Workspace Chat description: >- Continues an existing chat on another coding agent harness in the same workspace. The source chat is left unchanged. Returns as soon as the forked chat exists, with `fork.state` set to `preparing`. The sanitized transcript handoff and the first turn run in the background, after which `fork.state` becomes `ready` or `failed`. The workspace must be active. operationId: forkWorkspaceChat parameters: - name: workspaceId in: path required: true schema: type: string format: uuid - name: chatId in: path required: true description: Chat to fork from schema: type: string format: uuid requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ForkChatRequest' responses: '201': description: Forked chat created content: application/json: schema: $ref: '#/components/schemas/ForkWorkspaceChatResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': description: The requested harness is not enabled for this organization '404': $ref: '#/components/responses/NotFound' '409': description: >- The workspace is not active, or the requested harness has no credentials configured in it '500': $ref: '#/components/responses/InternalServerError' components: schemas: ForkChatRequest: type: object description: >- Request body for continuing an existing chat on another coding agent harness properties: provider: type: string enum: - claude - codex - cursor - deepseek - fx - kimi - opencode - pi description: >- Harness to continue the chat on. It must have credentials connected in the workspace. model: type: string description: Model for the forked chat. Defaults to the harness default. thinkingLevel: type: string enum: - low - medium - high - xhigh - max - ultra - ultracode description: Reasoning effort for the forked chat title: type: string description: >- Title for the forked chat. Defaults to a title derived from the source chat. id: type: string format: uuid description: Optional client-generated chat ID. clientRequestId: type: string description: Opaque client-chosen id echoed back in the `chat.created` event enableInteractiveTools: type: boolean description: Allow the forked chat's first turn to use interactive tools required: - provider ForkWorkspaceChatResponse: type: object properties: chat: $ref: '#/components/schemas/WorkspaceChat' required: - chat WorkspaceChat: type: object properties: id: type: string format: uuid provider: type: string enum: - claude - codex - cursor - deepseek - fx - kimi - muse - opencode - pi title: type: string createdAt: type: string format: date-time updatedAt: type: string format: date-time processing: type: boolean parentChatId: type: - string - 'null' format: uuid lastMessageText: type: - string - 'null' fork: description: >- Fork lineage and progress, when this chat was forked from another chat in the workspace oneOf: - $ref: '#/components/schemas/ChatFork' - type: 'null' required: - id - provider - title - createdAt - updatedAt - processing - parentChatId Error: type: object properties: error: type: string description: Error message details: type: - string - 'null' description: Additional error details code: type: string description: Machine-readable error code when available required: - error ChatFork: type: object description: Set on a chat that was forked from another chat in the same workspace properties: source: type: object description: The chat this one was forked from properties: chatId: type: string format: uuid provider: type: string enum: - claude - codex - cursor - deepseek - fx - kimi - opencode - pi title: type: string required: - chatId - provider - title trigger: type: string enum: - manual - auto description: >- `manual` for a requested fork, `auto` when the source harness hit its usage limit and the owner opted into automatic fallback reason: type: string enum: - rate_limit - out_of_credits description: Why an automatic fork happened state: type: string enum: - preparing - ready - failed description: >- `preparing` while the transcript handoff is assembled; `processing` stays true until it leaves this state error: type: string description: Failure reason when `state` is `failed` startedAt: type: string format: date-time completedAt: type: string format: date-time required: - source - trigger - state - startedAt responses: BadRequest: description: Bad request - Missing or invalid parameters content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Unauthorized - Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/Error' NotFound: description: Resource not found content: application/json: schema: $ref: '#/components/schemas/Error' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: apiKey: type: http scheme: bearer description: >- API key authentication. Obtain your API key from the Replicas dashboard under Organization → Settings → API Keys. ````