> ## Documentation Index > Fetch the complete documentation index at: https://docs.getsales.io/llms.txt > Use this file to discover all available pages before exploring further. # Keep dialogues from an upload > Keep dialogues from an upload (Keep N dialogues): picks, the ids of the dialogues to keep. Each becomes a golden row of the Golden set (source document, the upload's sid as document_sid) that the agent reads from once embedded; a dialogue whose answer the set holds already counts as a twin and is not written twice. 409 upload_not_found on an upload applied or discarded; 422 unknown_row on an id the upload did not find. Contract: - MCP tool `apply_agent_conversation_upload`, registry package `mcp.unibox/agent_conversation_uploads`, mount `unibox.agent-memory`. - Operation `action`, response envelope `action`. - Flags: none. ## OpenAPI ````yaml /api-reference/unibox/openapi.yaml post /api/agent-conversation-uploads/{sid}/apply openapi: 3.0.3 info: title: 'GetSales public contract: gs.service.unibox' description: >- The team inbox and the AI SDR: every LinkedIn and email thread in one place (conversations, messages, the timeline events), the manual tasks a thread spawns, the sender profiles the team speaks through with their LinkedIn account and mailboxes, and the one agent per team with its scenarios, plans and runs. GENERATED. This document is projected from the Zod MCP tool registry in `product/mcp/gs.mcp` (one tool per public endpoint, 1:1). Do not edit it by hand; edit the tool definition and regenerate with `pnpm openapi:public`. Surface: the public `/api` contract of `gs.service.unibox`, 125 operations. This is the only OpenAPI document the platform publishes. Internal (`/internal`) and health endpoints are deliberately absent: they are not part of any contract, they can change without notice, and the service source is their only description. Conventions: - Auth is a bearer JWT, optionally narrowed by the `Team-SID` header. - Every success body is an MCP envelope: `success: true` plus one typed `operation` shape (`search`, `get`, `create`, `update`, `delete`, `metrics`, `group_by`, `action`), and a `meta` block with `trace_id` for support. - Every failure is the same `McpError` envelope with a code from a fixed 16-code taxonomy, so a client maps errors once. - Lists page with `page_size` (0 to 500, default 50) plus an opaque forward `cursor`; `page_size: 0` returns counts only. - On `GET` and `DELETE`, object-valued query parameters (`filter`, `sort`) travel as JSON text and array-valued ones repeat as `name[]=value`. - The MCP-only `_meta` field (usage analytics) never reaches the backend and is not part of this contract. version: '1.0' contact: name: GetSales url: https://getsales.io email: support@getsales.io license: name: Proprietary url: https://getsales.io/terms servers: - url: https://beta.getsales.io/unibox/v1 description: >- Production (the gateway path on the beta ring; the origin is provisioned per DEPLOY_MAP.md) security: - BearerJwt: [] TeamSid: [] tags: - name: agent_answers description: >- Registry package `mcp.unibox/agent_answers`, served on MCP mount `unibox.knowledge`. - name: agent_conversation_uploads description: >- Registry package `mcp.unibox/agent_conversation_uploads`, served on MCP mount `unibox.agent-memory`. - name: agent_examples description: >- Registry package `mcp.unibox/agent_examples`, served on MCP mount `unibox.agent-memory`. - name: agent_hints description: >- Registry package `mcp.unibox/agent_hints`, served on MCP mount `unibox.agent-memory`. - name: agent_plans description: >- Registry package `mcp.unibox/agent_plans`, served on MCP mount `unibox.agent`. - name: agent_runs description: >- Registry package `mcp.unibox/agent_runs`, served on MCP mount `unibox.agent-memory`. - name: agent_scenarios description: >- Registry package `mcp.unibox/agent_scenarios`, served on MCP mount `unibox.agent`. - name: agent_source_parses description: >- Registry package `mcp.unibox/agent_source_parses`, served on MCP mount `unibox.knowledge`. - name: agent_sources description: >- Registry package `mcp.unibox/agent_sources`, served on MCP mount `unibox.knowledge`. - name: agent_tests description: >- Registry package `mcp.unibox/agent_tests`, served on MCP mount `unibox.agent-memory`. - name: agents description: >- Registry package `mcp.unibox/agents`, served on MCP mount `unibox.website`. - name: conversation_events description: >- Registry package `mcp.unibox/conversation_events`, served on MCP mount `unibox.inbox`. - name: conversations description: >- Registry package `mcp.unibox/conversations`, served on MCP mount `unibox.inbox`. - name: messages description: >- Registry package `mcp.unibox/messages`, served on MCP mount `unibox.inbox`. - name: sender_profiles description: >- Registry package `mcp.unibox/sender_profiles`, served on MCP mount `unibox.sender-profiles`. - name: tasks description: Registry package `mcp.unibox/tasks`, served on MCP mount `unibox.inbox`. - name: timeline description: >- Registry package `mcp.unibox/timeline`, served on MCP mount `unibox.inbox`. paths: /api/agent-conversation-uploads/{sid}/apply: post: tags: - agent_conversation_uploads summary: Keep dialogues from an upload description: >- Keep dialogues from an upload (Keep N dialogues): picks, the ids of the dialogues to keep. Each becomes a golden row of the Golden set (source document, the upload's sid as document_sid) that the agent reads from once embedded; a dialogue whose answer the set holds already counts as a twin and is not written twice. 409 upload_not_found on an upload applied or discarded; 422 unknown_row on an id the upload did not find. Contract: - MCP tool `apply_agent_conversation_upload`, registry package `mcp.unibox/agent_conversation_uploads`, mount `unibox.agent-memory`. - Operation `action`, response envelope `action`. - Flags: none. operationId: apply_agent_conversation_upload parameters: - name: sid in: path required: true description: Conversations upload sid (ub_cu_…). schema: type: string minLength: 18 maxLength: 18 pattern: ^ub_cu_ description: Conversations upload sid (ub_cu_…). requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ApplyAgentConversationUploadRequest' responses: '200': description: '`action` success envelope.' content: application/json: schema: $ref: '#/components/schemas/ApplyAgentConversationUploadResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: ApplyAgentConversationUploadRequest: type: object description: Request body of `apply_agent_conversation_upload`. properties: picks: type: array items: type: integer minimum: 1 minItems: 1 maxItems: 500 description: The ids of the dialogues to keep, among the pairs the upload found. required: - picks ApplyAgentConversationUploadResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - action action: type: string description: kebab-case verb; matches the route segment. item: type: object nullable: true properties: sid: type: string description: Conversations upload sid (ub_cu_…). team_sid: type: string description: Owning team (ts_tm_…, external - gs.service.id). agent_sid: type: string description: The team's agent (ub_ag_…). status: type: string enum: - found - applied - discarded description: >- found (the dialogues wait for the OK), applied (the kept ones are rows of the Golden set), discarded (closed with nothing kept). created_by: type: object properties: actor_type: type: string enum: - user - support - api_key - system - agent actor_sid: type: string nullable: true team_sid: type: string actor_name: type: string nullable: true description: >- The OAuth client that acted ("Claude", "n8n"); null for a user, an API key or a system job. oauth_client_sid: type: string nullable: true description: The acting OAuth client (id_oc_*); null off the OAuth path. reason: type: string nullable: true description: >- Why a system actor wrote the row (snapshot_capture_job, ...); null otherwise. permissions: type: object additionalProperties: {} description: >- Internal audit context: the grant set the actor held at write time. Not a contract. cluster_id: type: integer nullable: true description: 'Internal audit context: the cluster that served the write.' trace_id: type: string nullable: true description: >- Internal audit context: the trace id of the request that wrote the row. required: - actor_type - actor_sid - team_sid - permissions description: Who uploaded it. file: type: object nullable: true properties: name: type: string description: The file's name as uploaded. format: type: string enum: - csv - json description: csv or json. bytes: type: integer description: Its size; 5 MB at most. required: - name - format - bytes description: >- The file it came in as (the bytes are not kept); null when the threads came in the request's body. counts: type: object properties: threads: type: integer description: The threads read. messages: type: integer description: The messages with words. pairs: type: integer description: The dialogues paired, 500 at most. skipped: type: integer description: >- Our messages that paired with nothing (an opener, a continuation the same day) and the pairs over the cap. required: - threads - messages - pairs - skipped description: What was read. pairs: type: array items: type: object properties: id: type: integer description: 'The pair''s id within the upload, from 1: what apply names.' thread: type: string description: The thread the pair was read from, as the file named it. lead: type: string nullable: true description: >- The lead's name as the file gave it; null when it gave none. company: type: string nullable: true description: The lead's company as the file gave it. channel: type: string nullable: true enum: - linkedin - email description: The channel the file named for the thread; null when none. kind: type: string enum: - reply - followup description: >- reply: our reply to the lead's message; followup: our message a day or more after our own unanswered one. before: type: string nullable: true description: >- Our message before the lead's, names as placeholders; null on a follow-up. theirs: type: string description: >- What the lead wrote (the situation), names as placeholders ({lead}, {lead_company}, {sender}). ours: type: string description: >- The reply of ours that followed (the answer), names as placeholders. at: type: string nullable: true description: ISO 8601 UTC of our reply, when the file dated it. answer_hash: type: string description: >- sha256 of the answer, lower-cased with whitespace folded: the key a kept row is found by. required: - id - thread - lead - company - channel - kind - before - theirs - ours - at - answer_hash description: >- The dialogues found, each with its id, the lead and the company, what they wrote, what was answered and when. applied: type: object nullable: true properties: kept: type: integer description: The dialogues written as golden rows. twins: type: integer description: >- The picked dialogues whose answer the set held already: counted on their row, not written twice. example_sids: type: array items: type: string description: The rows written (ub_eg_…). required: - kept - twins - example_sids description: What apply did; null until applied. applied_by: type: object nullable: true properties: actor_type: type: string enum: - user - support - api_key - system - agent actor_sid: type: string nullable: true team_sid: type: string actor_name: type: string nullable: true description: >- The OAuth client that acted ("Claude", "n8n"); null for a user, an API key or a system job. oauth_client_sid: type: string nullable: true description: The acting OAuth client (id_oc_*); null off the OAuth path. reason: type: string nullable: true description: >- Why a system actor wrote the row (snapshot_capture_job, ...); null otherwise. permissions: type: object additionalProperties: {} description: >- Internal audit context: the grant set the actor held at write time. Not a contract. cluster_id: type: integer nullable: true description: 'Internal audit context: the cluster that served the write.' trace_id: type: string nullable: true description: >- Internal audit context: the trace id of the request that wrote the row. required: - actor_type - actor_sid - team_sid - permissions description: Who kept the dialogues; null until applied. applied_at: type: string nullable: true description: ISO 8601 UTC when the dialogues were kept; null until then. created_at: type: string description: ISO 8601 UTC. updated_at: type: string description: ISO 8601 UTC. required: - sid - team_sid - agent_sid - status - created_by - file - counts - pairs - applied - applied_by - applied_at - created_at - updated_at result: type: object additionalProperties: {} meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - operation - action - item - result - meta McpError: type: object properties: success: type: boolean enum: - false error: type: object properties: code: type: string enum: - validation_failed - nothing_to_update - not_found - relation_not_found - invalid_transition - limit_exceeded - payment_required - duplicate_rejected - conflict - delete_blocked - unauthorized - forbidden - rate_limited - internal_error - service_unavailable - not_implemented message: type: string recoverable: type: boolean suggestion: type: string field_errors: type: object additionalProperties: type: array items: type: object properties: rule: type: string message: type: string required: - rule - message blockers: type: array items: type: object properties: type: type: string description: >- Machine-readable blocker type (active_flow, pending_tasks, …). severity: type: string enum: - hard - soft description: >- hard = external action required; soft = acknowledge is enough. description: type: string entity_sid: type: string nullable: true count: type: integer resolution: type: string description: 'Hard: tool name to call. Soft: code for acknowledge[].' resolution_hint: type: string required: - type - severity - description - entity_sid - resolution - resolution_hint context: type: object additionalProperties: {} required: - code - message - recoverable meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - error responses: McpClientError: description: >- MCP error envelope. `error.code` is one of validation_failed, nothing_to_update, not_found, relation_not_found, invalid_transition, limit_exceeded, payment_required, duplicate_rejected, conflict, delete_blocked, unauthorized, forbidden, rate_limited, not_implemented. content: application/json: schema: $ref: '#/components/schemas/McpError' McpServerError: description: >- MCP error envelope with `error.code` internal_error or service_unavailable. content: application/json: schema: $ref: '#/components/schemas/McpError' securitySchemes: BearerJwt: type: http scheme: bearer bearerFormat: JWT description: >- Access token issued by gs.service.id. Its `access_identity` claim carries `team_sid`, `actor_sid` and `actor_type`, and that team scope is authoritative. TeamSid: type: apiKey in: header name: Team-SID description: >- Team scope for tokens that do not carry one. Ignored when the token already names a team. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.