> ## Documentation Index > Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt > Use this file to discover all available pages before exploring further. # Ask the AI Assistant, streaming its work > Run one turn and stream it as Server-Sent Events: a `step` frame for each thing the AI Assistant actually did (read_context when the workspace has a business context, then plan, then one apply_action per action it applied), one `turn` frame naming the saved user message's sequence once it is saved (the Stop route is addressed by it), `delta` frames carrying the whole reply so far (assign, never append), then exactly one `result` frame with the same body the non-streaming route returns, the reply carrying its action cards, sent once the reply is saved. The last `delta` always equals the saved reply. A turn that could not run ends in one `error` frame whose `reason` is `limit`, `paused` or `not_found`; any other failure is an `error` frame with no reason. A turn that breaks while running still ends in a `result` whose reply carries `failed`, and so does a stopped one, its reply reading `Stopped by you`. Closing the connection does not cancel the turn: it finishes and saves its reply, so reopening the conversation shows the answer. ## OpenAPI ````yaml /openapi.json post /assistant/chat/conversations/{conversation_id}/messages/stream/ openapi: 3.1.0 info: contact: email: support@getoneprofile.ai name: Oneprofile Support description: >- REST API reference for Oneprofile, the GTM data layer for your CRM. Manage tables, enrichments, and integrations. Authenticate with an API key to get started. termsOfService: https://www.getoneprofile.ai/terms title: API Reference | Oneprofile version: '0.0' servers: - url: https://api.getoneprofile.ai security: [] tags: - description: >- The docked AI Assistant: its general chat about the workspace and the product, streamed as Server-Sent Events, and the one list of a person's threads across every assistant, with pin, rename, delete and the search-to-table link. name: assistant - description: >- Granted workspace actions: what the AI Assistant proposed or applied in a conversation, the approve, dismiss and undo decisions on each card, the workspace's approval threshold and default grants, and the eight verbs. name: workspace-actions - description: >- The agent builder's saved conversations: threads of prompt edits, the turns recorded on them, and the one-time import from the browser. name: agent-assistant - description: >- The Getting started checklist: a workspace's progress through the six steps from its first people search to its first launched sequence. name: onboarding - description: Sender profiles, connected mailboxes, tags, and the Google connect flow. name: senders - description: The workspace do-not-contact list, enforced before every send. name: suppression - description: >- The workspace's recontact rule: how long before anyone hears from us again. name: contact_cooldown - description: 'Sequence authoring: the graph, the table-backed audience, previews.' name: sequences - description: >- The LinkedIn channel: connecting an account to a sender, its safety limits and history, and the protocol the browser extension speaks. name: linkedin - description: >- The approval queue: everything waiting on a person across every sender and channel, and the workspace's manual or automatic modes per channel. name: outreach - description: 'The unified outreach inbox: threads, replies, labels, events.' name: inbox - description: 'The AI reply layer: workspace settings, drafts, and approval.' name: inbox-ai - description: Notification rules, per-user preferences, and the Slack connection. name: notifications - description: Endpoints for seeing all available integration types. name: integration-types - description: Endpoints for creating and managing integrations. name: integrations - description: Endpoints for the generic OAuth install/claim app-listings engine. name: app-listings - description: Endpoints for creating and managing API keys. name: apikey - description: Endpoints for managing billing and subscription information. name: billing - description: Endpoints for creating and managing tables. name: tables - description: Endpoints for table columns, formula previews, and on-demand column runs. name: table-columns - description: Endpoints for table rows and manual cell edits. name: table-rows - description: Endpoints for observing and cancelling table recompute runs. name: table-runs - description: >- Endpoints for org-shared per-column display preferences: hidden, pinned, width, and colour tint. name: table-ui-prefs - description: >- Endpoints for the org-shared names given to the column tint palette: what this organisation calls each colour. Org-level, not per-table. name: table-column-color-labels - description: >- Endpoints for the enrichment action catalog, model list, presets, draft generation, and saved agents. name: table-enrichments - description: >- Endpoints for teaching a saved agent from example rows: training sessions, per-row feedback, and the proposed prompt to approve. name: agent-training - description: >- The durable audit trail of a table's enrichment actions: configured, edited, run, cancelled, and settled cost. name: table-enrichment-audit-logs - description: Endpoints for saving and applying column templates. name: table-templates - description: Server-sent change feed for a table's grid. name: table-events - description: 'Endpoints for org-shared saved table views: sort, filters, hidden columns.' name: table-views - description: >- The per-table AI Assistant: named conversations, the column suggestions a build turn produces, and the questions an analyze turn answers. name: table-assistant - description: >- Endpoints for PER-USER table preferences: favourites and recently opened. Unlike the rest of the table surface these are personal, so two members of one organisation legitimately see different answers. name: table-user-prefs - description: >- Endpoints for building a table from an uploaded CSV: upload and preview the inferred columns, commit the reviewed mapping, then poll the row load. name: table-imports - description: Endpoint for downloading a table's rows as CSV. name: table-export - description: >- Endpoints for the integration a table imports from: attach and preview it, promote imported fields into columns, and run the import on demand. name: table-sources - description: >- Endpoints for a table's recurring import cadence: set it, pause it, and read the next fire times. name: table-schedules - description: >- Endpoints for pushing a table's rows out to a connected integration: list writable destinations, derive their write capabilities, and map export columns. name: table-writeback - description: >- Endpoints backing a lookup column's setup: the connections whose records a column could read, and the identity fields one record type can be looked up by. name: table-integration-lookup - description: >- Endpoints for sourcing leads from the lead database: count and preview matches, land them in a table, and keep saved searches. Alongside people and company searches, leads can be sourced from buying signals — what a company or person just did — with a catalogue endpoint behind the picker that builds them. name: find-leads - description: >- Endpoints for discovering a domain's subdomains from public certificate logs and landing the results in a table. name: find-subdomains - description: Endpoints for the credit balance meter and usage reporting. name: credits - description: >- Endpoints for the workspace referral program: the shareable link, the friends who joined through it, and claiming a code after signup. name: referral - description: >- Endpoints for the affiliate program's own dashboard: enrolling and claiming a code, the summary, stats and activity feed, the commission ledger, and identity verification and payouts. name: affiliate - description: >- Endpoints for the design partner program's customer surface: whether this workspace is a design partner, the badges its feedback has earned, and sending and reading that feedback. name: design-partner - description: >- Endpoints for the org-level AI business context — company description, ideal customer profile, buyer personas, interest signals and social proof — plus domain-based generation and the reference documents whose summaries ride alongside those fields. name: ai-context - description: >- Endpoints for the signed-in user's Google Drive connection: starting and finishing the OAuth grant, checking or dropping it, and minting the short-lived token the Google Picker needs. name: google-drive paths: /assistant/chat/conversations/{conversation_id}/messages/stream/: post: tags: - assistant summary: Ask the AI Assistant, streaming its work description: >- Run one turn and stream it as Server-Sent Events: a `step` frame for each thing the AI Assistant actually did (read_context when the workspace has a business context, then plan, then one apply_action per action it applied), one `turn` frame naming the saved user message's sequence once it is saved (the Stop route is addressed by it), `delta` frames carrying the whole reply so far (assign, never append), then exactly one `result` frame with the same body the non-streaming route returns, the reply carrying its action cards, sent once the reply is saved. The last `delta` always equals the saved reply. A turn that could not run ends in one `error` frame whose `reason` is `limit`, `paused` or `not_found`; any other failure is an `error` frame with no reason. A turn that breaks while running still ends in a `result` whose reply carries `failed`, and so does a stopped one, its reply reading `Stopped by you`. Closing the connection does not cancel the turn: it finishes and saves its reply, so reopening the conversation shows the answer. operationId: stream_workspace_chat_message parameters: - in: path name: conversation_id required: true schema: format: uuid title: Conversation Id type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/WorkspaceChatMessageCreateSchema' required: true responses: '200': content: text/event-stream: schema: $ref: '#/components/schemas/WorkspaceChatTurnResponseSchema' type: string description: >- A stream of Server-Sent Events. The final `result` frame's `data` is a turn; an `error` frame's `data` is a stream error. '401': content: text/event-stream: schema: $ref: '#/components/schemas/UnauthorizedResponse' description: Unauthorized '403': content: text/event-stream: schema: $ref: '#/components/schemas/ForbiddenResponse' description: Forbidden '422': content: text/event-stream: schema: $ref: '#/components/schemas/UnprocessableEntityResponse' description: Invalid request made to the API. '500': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Internal server error. '502': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Bad gateway error. '503': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Service unavailable. security: - HTTPBearer: [] components: schemas: WorkspaceChatMessageCreateSchema: description: Send the AI Assistant a message. properties: prompt: maxLength: 4000 minLength: 1 title: Prompt type: string required: - prompt title: WorkspaceChatMessageCreateSchema type: object WorkspaceChatTurnResponseSchema: description: |- Both halves of one turn, as saved. The user message too, not just the reply: the client drew its own copy before sending and reconciles it against this one. properties: assistant_message: $ref: '#/components/schemas/WorkspaceChatMessageReadSchema' user_message: $ref: '#/components/schemas/WorkspaceChatMessageReadSchema' required: - user_message - assistant_message title: WorkspaceChatTurnResponseSchema type: object UnauthorizedResponse: properties: detail: description: The detail of why the request is unauthorized. title: Detail type: string required: - detail title: UnauthorizedResponse type: object ForbiddenResponse: properties: detail: description: The detail of why the request is forbidden. title: Detail type: string required: - detail title: ForbiddenResponse type: object UnprocessableEntityResponse: properties: detail: description: >- The detail of the error. This is the error message to show to the user. You should also use the issues field to show more detailed error messages per field. Use this field for a single liner error message. title: Detail type: string issues: description: >- The issues that caused the error. There can be multiple issues. Each issue is a user-facing error message. items: $ref: '#/components/schemas/UnprocessableEntityIssue' title: Issues type: array required: - detail - issues title: UnprocessableEntityResponse type: object ServerErrorResponse: properties: detail: description: The detail of why the server returned an error. title: Detail type: string required: - detail title: ServerErrorResponse type: object WorkspaceChatMessageReadSchema: description: |- One message in a conversation, with the action cards a reply raised. Deliberately leaves out why a failed turn failed and what it cost: the first can carry a supplier's own words, and neither is the customer's. The cards ride on the message so a transcript renders them under the right reply without a second request. properties: actions: description: >- The actions this reply proposed or applied, in the order the AI Assistant named them, as they stand now. Empty for user messages and replies that acted on nothing. items: $ref: '#/components/schemas/ActionProposalReadSchema' title: Actions type: array content: title: Content type: string conversation_id: format: uuid title: Conversation Id type: string created_at: format: date-time title: Created At type: string id: format: uuid title: Id type: string role: $ref: '#/components/schemas/WorkspaceChatRole' sequence: title: Sequence type: integer status: $ref: '#/components/schemas/WorkspaceChatStatus' steps: description: >- The trail this turn showed while it ran, as it was shown. Empty for user messages. items: $ref: '#/components/schemas/AiStep' title: Steps type: array required: - id - conversation_id - sequence - role - status - content - steps - actions - created_at title: WorkspaceChatMessageReadSchema type: object UnprocessableEntityIssue: properties: input: anyOf: - type: string - type: integer - type: number - type: boolean - items: {} type: array - additionalProperties: true type: object description: The user's input that caused the error. title: Input loc: description: >- The location of the error. Always contains 1 or 2 elements. The first element is the type of location (e.g. 'body', 'query', 'path', 'header'). The second element is the name of the field that caused the error. If the error is not related to a specific field, the second element is not present. items: type: string title: Loc type: array msg: description: The message of the error. The error message to show to the user. title: Msg type: string type: description: >- The type of the error. Useful for frontend code to handle different types of errors. title: Type type: string required: - loc - msg - type - input title: UnprocessableEntityIssue type: object ActionProposalReadSchema: description: >- One action the assistant proposed or applied, and what became of it: the card. Prices are quoted in credits, never tenths, and never as a raw id: who decided is a display name resolved at this boundary. ``applied_result`` is the verb's own record of what it made (the new column's id, the rows enrolled), for the card's link and its Undo. properties: applied_result: anyOf: - additionalProperties: true type: object - type: 'null' title: Applied Result can_undo: description: 'Whether Undo applies now: undoable and applied.' title: Can Undo type: boolean conversation_id: anyOf: - format: uuid type: string - type: 'null' title: Conversation Id decided_at: anyOf: - format: date-time type: string - type: 'null' title: Decided At decided_by_display_name: anyOf: - type: string - type: 'null' title: Decided By Display Name error: anyOf: - type: string - type: 'null' description: Why an approval failed to apply, in plain words; null otherwise. title: Error grantable: description: >- Whether the card may offer Approve and allow in this conversation: only a pending proposal of a verb that is not a send. title: Grantable type: boolean id: format: uuid title: Id type: string message_id: anyOf: - format: uuid type: string - type: 'null' title: Message Id origin: $ref: '#/components/schemas/ProposalOrigin' price_credits: anyOf: - type: number - type: 'null' description: >- The published price of the operation when it was proposed, in credits; null when free. title: Price Credits price_label: description: '"Free", "1 credit" or "N credits", as the card says it.' title: Price Label type: string proposed_at: format: date-time title: Proposed At type: string status: $ref: '#/components/schemas/ProposalStatus' summary: title: Summary type: string undoable: description: Whether the verb can be reversed at all. title: Undoable type: boolean undone_at: anyOf: - format: date-time type: string - type: 'null' title: Undone At undone_by_display_name: anyOf: - type: string - type: 'null' title: Undone By Display Name verb: $ref: '#/components/schemas/WorkspaceVerb' verb_label: title: Verb Label type: string required: - id - origin - conversation_id - message_id - verb - verb_label - summary - price_credits - price_label - status - proposed_at - decided_at - decided_by_display_name - applied_result - undone_at - undone_by_display_name - error - undoable - can_undo - grantable title: ActionProposalReadSchema type: object WorkspaceChatRole: description: Who wrote a message. enum: - user - assistant title: WorkspaceChatRole type: string WorkspaceChatStatus: description: |- Whether a turn finished. A reply is written PENDING in the same transaction as the person's message, before the model is called, and filled in as COMPLETE or FAILED once the turn is saved. So a question is never on disk without a reply row under it: a crashed turn is saved FAILED rather than dropped, and a turn whose process died between the two transactions is a reply still pending, which the abandoned-turn sweep fails. Either way the user sees a reply they can retry instead of a question with nothing under it. enum: - pending - complete - failed title: WorkspaceChatStatus type: string AiStep: additionalProperties: false description: >- One thing an AI turn did, as the wire spells it. Field-for-field identical to ``table_live_updates.TableCellActivityStepSchema`` ON PURPOSE, and the duplication is the design. That schema sits in the table stratum's kernel, which the lead search, inbox and sequence surfaces have no business importing; this one sits under every surface equally. Because the two agree exactly, the frontend's ``TimelineStep`` renders both with no conversion and no second component, which is the property worth protecting. ``test_ai_step_mirrors_the_cell_activity_step`` pins them together. Plain strings rather than enums, for the same reason the cell schema uses them: the vocabulary is open, clients must tolerate tokens they have not learned yet, and a new action should never be able to break a running dashboard. properties: action: description: >- What kind of move this was, e.g. `read_table`, `plan`, `write_column`. title: Action type: string detail: default: '' description: >- The step's input: the instruction, the column it read, the query it ran. maxLength: 500 title: Detail type: string duration_ms: anyOf: - type: integer - type: 'null' description: Wall clock for the work this step describes, never an estimate. title: Duration Ms observation: default: '' description: >- One line on what came back. The half that makes a step worth reading. maxLength: 500 title: Observation type: string outcome: default: completed description: >- `completed`, `failed`, `refused` or `stopped`. Clients must tolerate new tokens. title: Outcome type: string thought: anyOf: - type: string - type: 'null' description: >- The model's stated reasoning for choosing this step. Set by the agent loop; the assistant surfaces leave it null, and the renderer simply omits the rung. title: Thought required: - action title: AiStep type: object ProposalOrigin: description: |- Which surface raised a proposal. Kept as its own enum rather than reusing the thread-store origins: a scheduled search proposes with no conversation behind it at all, and the activity feed needs to say so. enum: - chat - agent - scheduled_search title: ProposalOrigin type: string ProposalStatus: description: >- Where one proposed action stands. PROPOSED waits on a person. APPLIED happened, and may be undone where the verb allows it. UNDONE is applied-then-reversed and stays on the record: Undo reverses the workspace change, never the spend, and a trail that forgot the spend would be lying. DISMISSED is a person saying no. FAILED is an approval whose apply raised; the error stays with the row so the card can say why instead of vanishing. enum: - proposed - applied - undone - dismissed - failed title: ProposalStatus type: string WorkspaceVerb: description: |- The eight things an AI may do to a workspace. Exactly eight, not sixty: today's cell-level actions all run against one cell, and building a table, adding contacts to a sequence and starting a search had no home at all. Anything new here is a product decision about what an assistant may touch, not a convenience for a planner. enum: - create_table_from_search - add_column - run_column - enrich_rows - add_contacts_to_sequence - push_to_destination - call_endpoint - start_search title: WorkspaceVerb type: string securitySchemes: HTTPBearer: scheme: bearer type: http ````