> ## 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. # Search the golden set > The AI SDR's Golden set: every kept dialogue, with counts by tier, kind, source, scenario, sender profile and who kept it (golden_by), and the edits waiting for a Keep (filter proposed). filter.q finds a dialogue by what was said; sort used_count desc orders by the replies it was read before. mode semantic lists the rows nearest to the text in filter.q the way the agent picks them, each with its similarity. page_size 0 returns counts alone. Contract: - MCP tool `search_agent_examples`, registry package `mcp.unibox/agent_examples`, mount `unibox.agent-memory`. - Operation `search`, response envelope `search`. - Flags: read only. ## OpenAPI ````yaml /api-reference/unibox/openapi.yaml post /api/agent-examples/search 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-examples/search: post: tags: - agent_examples summary: Search the golden set description: >- The AI SDR's Golden set: every kept dialogue, with counts by tier, kind, source, scenario, sender profile and who kept it (golden_by), and the edits waiting for a Keep (filter proposed). filter.q finds a dialogue by what was said; sort used_count desc orders by the replies it was read before. mode semantic lists the rows nearest to the text in filter.q the way the agent picks them, each with its similarity. page_size 0 returns counts alone. Contract: - MCP tool `search_agent_examples`, registry package `mcp.unibox/agent_examples`, mount `unibox.agent-memory`. - Operation `search`, response envelope `search`. - Flags: read only. operationId: search_agent_examples requestBody: required: false content: application/json: schema: $ref: '#/components/schemas/SearchAgentExamplesRequest' responses: '200': description: '`search` success envelope.' content: application/json: schema: $ref: '#/components/schemas/SearchAgentExamplesResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: SearchAgentExamplesRequest: type: object description: Request body of `search_agent_examples`. properties: filter: type: object properties: q: type: string maxLength: 4000 description: >- Free text over the situation, the answer and the note (forget takes it too); in mode semantic, the situation to match, required there. sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_eg_ description: Golden set row sid (ub_eg_…). in: type: array items: type: string minLength: 18 maxLength: 18 pattern: ^ub_eg_ description: Golden set row sid (ub_eg_…). additionalProperties: false description: Row sid(s), ub_eg_ prefix. agent_sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_ag_ additionalProperties: false description: >- Whose Golden set (ub_ag_…, block 10, 2026-10-30); left out, the team's default agent's. sender_profile_sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_sp_ in: type: array items: type: string minLength: 18 maxLength: 18 pattern: ^ub_sp_ is_null: type: boolean additionalProperties: false description: >- What one sender profile's replies taught (ub_sp_…); { is_null: true } for the pairs typed by hand. conversation_sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_cv_ in: type: array items: type: string minLength: 18 maxLength: 18 pattern: ^ub_cv_ additionalProperties: false description: The rows read from one thread (ub_cv_…). message_sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_ms_ in: type: array items: type: string minLength: 18 maxLength: 18 pattern: ^ub_ms_ additionalProperties: false description: Whether a message is in the set already (ub_ms_…). document_sid: type: object properties: eq: type: string minLength: 18 maxLength: 18 pattern: ^ub_cu_ in: type: array items: type: string minLength: 18 maxLength: 18 pattern: ^ub_cu_ is_null: type: boolean additionalProperties: false description: >- The dialogues kept from one conversations upload (ub_cu_…); { is_null: true } for every other source. tier: type: object properties: eq: type: string enum: - golden - auto in: type: array items: type: string enum: - golden - auto additionalProperties: false description: '{ eq: "golden" } is what people vouched for.' source: type: object properties: eq: type: string enum: - history - own_send - approved_edit - remembered - document - manual in: type: array items: type: string enum: - history - own_send - approved_edit - remembered - document - manual additionalProperties: false description: Where the rows came from. kind: type: object properties: eq: type: string enum: - reply - followup in: type: array items: type: string enum: - reply - followup additionalProperties: false description: reply or followup; mode semantic takes a plain value. channel: type: object properties: eq: type: string enum: - linkedin - email in: type: array items: type: string enum: - linkedin - email is_null: type: boolean additionalProperties: false description: >- The channel the answers went on; mode semantic takes a plain value and adds the rows with none. scenario_key: type: object properties: eq: type: string in: type: array items: type: string is_null: type: boolean additionalProperties: false description: The classified scenario of the situation. embedding_state: type: object properties: eq: type: string enum: - pending - ready - failed in: type: array items: type: string enum: - pending - ready - failed additionalProperties: false description: >- { eq: "failed" } lists the rows whose vector could not be written. proposed: type: object properties: eq: type: boolean ne: type: boolean additionalProperties: false description: >- true: the edits waiting for a Keep (From your edits); false: the rows in the set. golden_by: type: object properties: eq: type: string minLength: 18 maxLength: 18 in: type: array items: type: string minLength: 18 maxLength: 18 is_null: type: boolean additionalProperties: false description: >- Who kept the row, by the actor sid in its golden_by identity (us_mb_… for a member); { is_null: true } for the rows nobody kept by hand (block AC5). answered_at: type: object properties: gte: type: string lte: type: string gt: type: string lt: type: string additionalProperties: false description: ISO 8601 range of when the answers went out. created_at: type: object properties: gte: type: string lte: type: string gt: type: string lt: type: string additionalProperties: false description: ISO 8601 range. deleted_at: type: object properties: is_null: type: boolean additionalProperties: false description: >- Default scope is the live rows; forgotten ones stay out of every read. description: >- Field filters, ANDed: {field: {eq | ne | in | nin | gte | lte | gt | lt | is_null}}; q inside it is free text. Omit for every row. include: type: array items: type: string enum: - usage - thread description: Relations to attach to every item; omit for the bare rows. sort: type: object properties: field: type: string enum: - created_at - answered_at - used_count - last_used_at - seen_count - golden_at description: The column to order by. direction: type: string enum: - asc - desc description: asc or desc; default desc. required: - field description: One column and its direction; omit for the default order. page_size: type: integer minimum: 0 maximum: 500 description: 0..500, default 50; 0 = counts only, 1 = the first row. cursor: type: string nullable: true description: pagination.next_cursor of the previous page. mode: type: string enum: - words - semantic description: >- words (default): the list with its counts, q as free text; semantic: the rows nearest to the situation in filter.q, as the agent's pick reads them, up to 50, each with its similarity, no cursor. SearchAgentExamplesResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - search items: type: array items: type: object properties: item: type: object properties: sid: type: string description: Golden set row sid (ub_eg_…). team_sid: type: string description: Owning team (ts_tm_…, external - gs.service.id). agent_sid: type: string nullable: true description: >- The AI SDR whose Golden set the row is in (ub_ag_…, block 10, 2026-10-30); null on a row from before, read as the team's default's. tier: type: string enum: - golden - auto description: >- golden: a person vouched for it (Remember, a pair by hand, a Keep, a promotion), picked ahead; auto: learned by rule from the team's own sends. source: type: string enum: - history - own_send - approved_edit - remembered - document - manual description: >- history (the history walk's harvest), own_send (a person's reply in a live thread), approved_edit (an agent draft a person edited), remembered, manual (a pair typed by hand), document (kept from a conversations upload, block AC5). kind: type: string enum: - reply - followup description: >- reply: the team's answer to the lead's message; followup: our message after the lead went quiet. situation: type: string description: >- What the answer responds to: the lead's message(s), or our unanswered message for a follow-up. Names are placeholders: {lead}, {lead_company}, {sender}. answer: type: string description: >- The team's answer as it went out (or as the person wrote it), names as placeholders. sender_profile_sid: type: string nullable: true description: >- The sender profile that answered (ub_sp_…); null on a pair typed by hand. conversation_sid: type: string nullable: true description: >- The thread the pair was read from (ub_cv_…); null on a pair typed by hand. message_sid: type: string nullable: true description: >- The outbound message the answer is (ub_ms_…); one row per message. Null on a pair typed by hand. document_sid: type: string nullable: true description: >- The conversations upload the dialogue was kept from (ub_cu_…, block AC5); null on every other source. channel: type: string nullable: true enum: - linkedin - email description: >- The channel the answer went on; null on a pair typed by hand (read on every channel). scenario_key: type: string nullable: true description: >- The classified scenario of the situation (interested, objection, ...) when known. context_before: type: string nullable: true description: >- Our message before the lead's, the context the situation reads against; null on a follow-up. draft_text: type: string nullable: true description: >- approved_edit only: the agent's draft before the person's edit, beside the answer they sent. note: type: string nullable: true description: A person's note on when the row applies, max 512 chars. seen_count: type: integer minimum: 1 description: >- How often the same answer was met across the team's threads. used_count: type: integer minimum: 0 description: How many agent turns the row was shown to. last_used_at: type: string nullable: true description: >- ISO 8601 UTC of the last turn that read it; null when none did. answered_at: type: string nullable: true description: ISO 8601 UTC, when the answer went out. embedding_state: type: string enum: - pending - ready - failed description: >- pending until the vector is written, ready when the pick can read it, failed after three tries (an edit of the situation sends it back to pending). embedding_model: type: string nullable: true description: provider/model that wrote the vector; null while pending. golden_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 made the row golden; null on an auto row. golden_at: type: string nullable: true description: ISO 8601 UTC, when it became golden; null on an auto row. proposed_at: type: string nullable: true description: >- Set while an edited draft waits for a person's Keep (From your edits): such a row is never picked. Null once in the set. 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: >- The actor whose write bore the row (the system for the harvest). deleted_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 forgot it; null on a live row. created_at: type: string description: ISO 8601 UTC. updated_at: type: string description: ISO 8601 UTC. deleted_at: type: string nullable: true description: ISO 8601 UTC once forgotten; null on a live row. required: - sid - team_sid - agent_sid - tier - source - kind - situation - answer - sender_profile_sid - conversation_sid - message_sid - document_sid - channel - scenario_key - context_before - draft_text - note - seen_count - used_count - last_used_at - answered_at - embedding_state - embedding_model - golden_by - golden_at - proposed_at - created_by - deleted_by - created_at - updated_at - deleted_at included: type: object properties: similarity: type: number minimum: 0 maximum: 1 description: >- mode semantic only: how near the row is to the text searched, (1 + cosine) / 2, best first. used_30d: type: integer minimum: 0 description: >- include usage: the agent turns that read the row in the last 30 days (used_count on the row counts every turn). last_uses: type: array items: type: object properties: at: type: string nullable: true description: ISO 8601 UTC of the turn. conversation_sid: type: string description: The thread it wrote on (ub_cv_…). run_sid: type: string description: >- The turn (ub_rn_…): get_agent_run reads how the reply was made. run_outcome: type: string nullable: true description: >- What became of that reply (AgentRunOutcomeEnum: written, edited, unsure, waiting, handed, test); null while none. lead_name: type: string nullable: true description: The lead of that thread. outcome: type: object nullable: true properties: kind: type: string description: >- booked, signed_up, registered (the Playbook's end), their_link, confirmed_time, gave_contact (the lead's own evidence), handed (a person took the thread), replied (the lead wrote again), back_on (the lead named a date and the plan waits until it: at is the date), no_reply. at: type: string nullable: true description: ISO 8601 UTC of what happened; null on no_reply. required: - kind - at description: >- What happened on that thread after the reply; null when the thread is gone. required: - at - conversation_sid - run_sid - run_outcome - lead_name - outcome description: >- include usage: the newest three turns that read the row, whatever their age, newest first. lead_name: type: string nullable: true description: >- include thread: the lead of the thread the pair was read from (or the lead the upload named); null on a pair typed by hand. lead_company: type: string nullable: true description: >- include thread: the lead's company, from the linked person or the upload; null when unknown. sender_profile_name: type: string nullable: true description: >- include thread: the sender profile whose person answered; null on a pair typed by hand or uploaded. dialogue: type: object properties: channel: type: string nullable: true description: >- linkedin or email; null on a dialogue typed by hand with no channel. origin: type: object properties: kind: type: string description: >- workflow (a workflow's message opened the thread), person (a person's own first touch), lead (the lead wrote first), history (the history walk), upload (a conversations upload), typed (a pair typed by hand). workflow_name: type: string nullable: true description: The workflow, when one opened the thread. ordinal: type: integer nullable: true description: >- Our message before the kept reply counted among our messages on the thread, from 1 ("from the workflow's message 2"). required: - kind - workflow_name - ordinal before: type: object nullable: true properties: message_sid: type: string nullable: true description: >- The message (ub_ms_…); null on a dialogue typed by hand or uploaded. author: type: string description: >- person (a person wrote it), agent (the AI SDR's draft went out), workflow (a workflow's message). author_name: type: string nullable: true description: The sender profile whose person wrote it. text: type: string description: The message as it went out. at: type: string nullable: true description: ISO 8601 UTC. required: - message_sid - author - author_name - text - at description: >- Our message before the lead's; null when the lead wrote first. theirs: type: object nullable: true properties: message_sid: type: string nullable: true text: type: string description: >- The lead's message(s) the reply answered, as written (several joined by a blank line). at: type: string nullable: true required: - message_sid - text - at description: >- What they wrote; null on a follow-up to our own unanswered message. kept: type: object properties: message_sid: type: string nullable: true description: >- The message (ub_ms_…); null on a dialogue typed by hand or uploaded. author: type: string description: >- person (a person wrote it), agent (the AI SDR's draft went out), workflow (a workflow's message). author_name: type: string nullable: true description: The sender profile whose person wrote it. text: type: string description: The message as it went out. at: type: string nullable: true description: ISO 8601 UTC. draft_text: type: string nullable: true description: >- The agent's draft before the person's edit; null when the reply went as drafted or a person wrote it. edits: type: array nullable: true items: type: object properties: op: type: string description: >- equal (both texts), del (the draft's own words, struck), ins (the person's own, written). text: type: string required: - op - text description: >- The edit against the draft, word by word, in order; null when there was no draft to mark against. required: - message_sid - author - author_name - text - at - draft_text - edits description: The kept reply. next: type: object nullable: true properties: message_sid: type: string nullable: true text: type: string at: type: string nullable: true required: - message_sid - text - at description: >- The lead's next message after the kept reply; null when none came. outcome: type: object nullable: true properties: kind: type: string description: >- booked, signed_up, registered (the Playbook's end), their_link, confirmed_time, gave_contact (the lead's own evidence), handed (a person took the thread), replied (the lead wrote again), back_on (the lead named a date and the plan waits until it: at is the date), no_reply. at: type: string nullable: true description: ISO 8601 UTC of what happened; null on no_reply. required: - kind - at description: >- What happened after the kept reply; null on a dialogue with no thread. takes: type: object properties: words: type: integer description: The kept reply's words. sentences: type: integer description: Its sentences. ask: type: object properties: kind: type: string description: >- time_slots (times or days offered), question, link (a booking link), none. count: type: integer description: The slots or questions counted. question_before: type: boolean description: >- Whether a question stands before the ask that ends it. required: - kind - count - question_before register: type: object properties: kind: type: string description: >- du, sie (the German registers), first_name (the lead addressed by name), formal, unknown. as_they_wrote: type: boolean nullable: true description: >- Whether the register matches the lead's own; null when either side cannot be read. required: - kind - as_they_wrote number: type: object properties: kind: type: string description: exact (one figure), range, none. text: type: string nullable: true description: The figure as written ("627 EUR a month"). required: - kind - text required: - words - sentences - ask - register - number description: >- What the agent takes from the reply, read by rule: the length, the ask, the register, the number. required: - channel - origin - before - theirs - kept - next - outcome - takes description: >- include dialogue (get only): the whole dialogue around the kept reply and what the agent takes from it. required: - item - included pagination: type: object properties: next_cursor: type: string nullable: true has_more: type: boolean total_count: type: integer nullable: true required: - next_cursor - has_more - total_count applied_filters: type: object additionalProperties: {} includes: type: array items: type: string 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 counts: type: object properties: total_count: type: integer minimum: 0 description: Rows matching the filter (full filter scope, not the page). groups: type: object properties: tier: anyOf: - type: object additionalProperties: {} - type: array items: {} description: Rows by tier (golden, auto); an absent key means zero. kind: anyOf: - type: object additionalProperties: {} - type: array items: {} description: Rows by kind (reply, followup). source: anyOf: - type: object additionalProperties: {} - type: array items: {} description: Rows by source. scenario_key: anyOf: - type: object additionalProperties: {} - type: array items: {} description: Rows by scenario key, __null for the rows with none. sender_profile_sid: anyOf: - type: object additionalProperties: {} - type: array items: {} description: Rows by sender profile, __null for the pairs typed by hand. golden_by: anyOf: - type: object additionalProperties: {} - type: array items: {} description: >- Rows by who kept them (the actor sid of golden_by), __null for the rows nobody kept by hand (block AC5). proposed: anyOf: - type: object additionalProperties: {} - type: array items: {} description: >- true: the edits waiting for a Keep (From your edits); false: the rows in the set. required: - tier - kind - source - scenario_key - sender_profile_sid - golden_by - proposed required: - total_count - groups required: - success - operation - items - pagination - applied_filters - includes - 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.