> ## Documentation Index > Fetch the complete documentation index at: https://www.sapientpriors.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Complete one conversational turn > Resolves the authenticated caller's agent and thread, retrieves memory context, generates the answer, records the turn, and returns source citations as one API-owned operation. ## OpenAPI ````yaml /openapi.yaml post /v1/agents/{agent_id}/threads/{thread_id}/chat openapi: 3.0.3 info: title: Priors API description: > Priors gives you memory agents. An agent learns from the observations you send it and answers from what it learned. You call this API from your own backend with a partner API key. The key identifies your organization, which owns every agent, thread, observation, source, and memory it creates. Another organization receives 404 for those identifiers. Send `X-SP-End-User` alongside the key to act for one named person on your side. version: 0.1.0 servers: - url: https://app.sapientpriors.com/api description: Production security: - partnerKey: [] tags: - name: Agents description: Create, read, update, and delete memory agents. - name: Threads description: 'Conversations under an agent: create them, teach them, and ask them.' - name: Sources description: Files an agent learned from, and the citations that point back to them. - name: Authentication description: What your key resolves to, and the limits that apply to it. - name: Billing description: Your organization's credits and charges. paths: /v1/agents/{agent_id}/threads/{thread_id}/chat: post: tags: - Threads summary: Complete one conversational turn description: > Resolves the authenticated caller's agent and thread, retrieves memory context, generates the answer, records the turn, and returns source citations as one API-owned operation. operationId: chat parameters: - $ref: '#/components/parameters/AgentId' - $ref: '#/components/parameters/ThreadId' - $ref: '#/components/parameters/EndUser' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatRequest' responses: '200': description: Completed conversational turn content: application/json: schema: $ref: '#/components/schemas/ChatResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '404': $ref: '#/components/responses/NotFound' '409': $ref: '#/components/responses/AgentNotReady' '429': $ref: '#/components/responses/TooManyRequests' '503': $ref: '#/components/responses/ServiceUnavailable' components: parameters: AgentId: name: agent_id in: path required: true description: Unique managed memory-agent identifier. schema: type: string maxLength: 32 pattern: ^agent_[0-9A-HJKMNP-TV-Z]{26}$ ThreadId: name: thread_id in: path required: true description: Unique thread identifier scoped to the agent. schema: type: string maxLength: 33 pattern: ^thread_[0-9A-HJKMNP-TV-Z]{26}$ EndUser: name: X-SP-End-User in: header required: false description: > Your own identifier for the person this request acts for: an account number, a row id, anything stable on your side. It works only with a partner API key. The value is not stored. Priors hashes it together with your organization id, so two clients that send the same string are still two different people. With the header, you reach the threads that same person created and no others. A new thread is recorded against that person, and `GET /v1/agents/{agent_id}` returns that person's conversations only. Without the header, the key acts as the organization and reaches every thread on every agent it owns. Learned memory is shared across the agent either way. Only the thread list narrows. Sent with anything that is not a partner API key, the header returns 400 instead of being ignored. Sent empty or as whitespace, it also returns 400, and it is never read as absent: absent means the whole organization, which is wider access than you asked for. Surrounding whitespace is removed. The 255-character limit is measured on the value as sent. schema: type: string minLength: 1 maxLength: 255 pattern: \S schemas: ChatRequest: type: object required: - turn_id - message properties: turn_id: type: string minLength: 1 maxLength: 200 message: type: string minLength: 1 maxLength: 2000 timestamp: type: string format: date-time nullable: true image_source_id: allOf: - $ref: '#/components/schemas/ImageSourceId' nullable: true image_source_ids: type: array maxItems: 10 nullable: true items: $ref: '#/components/schemas/ImageSourceId' detail: $ref: '#/components/schemas/Detail' additionalProperties: false ChatResponse: type: object required: - agent_id - thread_id - turn_id - message - memory_context - model - duration_ms - stages - citations properties: agent_id: $ref: '#/components/schemas/AgentId' thread_id: $ref: '#/components/schemas/ThreadId' turn_id: type: string message: type: string memory_context: type: string model: type: string duration_ms: type: integer minimum: 0 stages: type: array items: $ref: '#/components/schemas/ChatStage' citations: type: array items: $ref: '#/components/schemas/Citation' learning: type: array items: $ref: '#/components/schemas/LearningItem' description: > Turns in this thread that were not learned: writing their memory failed after an earlier response was already returned, and no earlier response reported them. Each one is reported at least once. `GET .../threads/{thread_id}/learning` is the full record. Empty when every turn so far was learned or is still being learned. additionalProperties: false ImageSourceId: type: string pattern: ^img_[0-9a-f]{32}$ description: Server-generated image-source identifier accepted by chat. Detail: type: string enum: - brief - standard - detailed default: standard description: > How much the agent writes: the length of `response_context` on `observe-and-enrich` and `observe-and-respond`, and of the answer on `chat`. `brief`: only the most important facts, in 2 to 4 sentences; use it for short replies such as a chat widget, a notification, or an SMS. `standard` (the default): the normal length; use it for most questions. `detailed`: every relevant fact, date, name, number, and direct quote the memories hold, with a list or table when the question asks for one or there are many items; use it for reports, audits, the history of a customer, and "list everything" questions. This is an instruction to the agent, not a cut: the text is never trimmed to fit. For a hard limit on size, use `max_context_chars`. AgentId: type: string pattern: ^agent_[0-9A-HJKMNP-TV-Z]{26}$ description: Server-generated agent identifier. ThreadId: type: string pattern: ^thread_[0-9A-HJKMNP-TV-Z]{26}$ description: Server-generated thread identifier. ChatStage: type: object required: - name - duration_ms properties: name: type: string enum: - memory_context - final_generation - turn_learning duration_ms: type: integer minimum: 0 additionalProperties: false Citation: type: object required: - source_id - label - media_type - href - verified properties: source_id: $ref: '#/components/schemas/SourceId' label: type: string media_type: type: string href: type: string description: Same-origin authenticated download path for the source. verified: type: boolean description: > True when the model looked at this source on this turn, which is the case for an image attached to the turn. False when the link comes from a memory the source produced earlier. additionalProperties: false LearningItem: type: object description: > Whether one turn of a request was learned into memory. A turn is not learned when writing its memory failed after the response was returned. It is never learned later: send it again to have it learned. required: - request_id - role - status properties: request_id: type: string description: > The id you know the request by: the `request_id` you sent to `observe-and-respond` or `observe-and-enrich` (or the `x-request-id` header of its response), or the `turn_id` of a `chat` message. role: type: string enum: - user - assistant description: > `user` is the turn you sent. `assistant` is the answer Priors wrote and learned (`chat`, and `observe-and-respond` with `learn_reply`). status: type: string enum: - learned - pending - not_learned description: > `learned`: in memory. `pending`: still being learned. `not_learned`: will never be learned; send it again. The `learning` lists on responses carry only `not_learned`. reason: type: string nullable: true description: > Stable machine code for why a turn was not learned, for example `generation_failed`, `model_unavailable`, `generation_timeout`, `generation_unparseable`, `memory_commit_shortfall`, `embedder_mismatch`, or `earlier_turn_failed` (dropped because a turn before it failed). Treat an unknown code like `generation_failed`. Null unless `not_learned`. message: type: string nullable: true description: A sentence to show a person. Null unless `not_learned`. refunded_credits: type: string nullable: true pattern: ^-?\d+(\.\d+)?$ description: > Credits refunded for this turn, as a decimal string. Null when nothing was refunded for it: nothing was charged, or it is an answer Priors wrote, which was delivered and stays charged. action: type: string nullable: true enum: - resend - null description: '`resend` when `not_learned`, else null.' additionalProperties: false ErrorResponse: type: object required: - error - code - request_id properties: error: type: string code: type: string description: > Machine-readable condition. Branch on this rather than on the status where the two differ. All three of these can arrive as a 5xx and they want different handling: `service_unavailable` (503) is a dependency outage worth retrying, `service_not_configured` (503) is the same transport failure that retrying will NEVER clear because a feature is not switched on for your organization, and `internal_error` (500) is a defect that will fail the same way again. Known values: invalid_request, unauthorized, forbidden, payment_required, not_found, agent_not_found, thread_not_found, conflict, agent_quota_exceeded, duplicate_upload_in_progress, document_already_ingested, document_uploaded_elsewhere, agent_not_ready, payload_too_large, rate_limit_exceeded, service_unavailable, service_not_configured, answer_model_unavailable, internal_error, and the document codes an upload can return (unsupported_document, document_needs_ocr, encrypted_document, malformed_document, empty_document, document_too_large, document_too_complex, document_too_many_turns, document_too_many_pages, document_too_large_for_ocr, document_pages_unexpected, document_service_unavailable, ocr_busy, ocr_failed, ingestion_failed). answer_model_unavailable is a narrower `service_unavailable` (503): the model that writes the visible reply could not be reached after retries. It is worth its own code because it is the one dependency whose outage a caller may want to word differently -- the turn produced no answer at all, and retrying shortly is the right advice. agent_not_found and thread_not_found are narrower `not_found`s, sent so a client can tell WHICH resource vanished and recover accordingly without matching on the English message. Treat any unrecognised value as the status code's default meaning rather than rejecting the response. request_id: type: string description: > Server-issued identifier for this request. Include it when reporting a problem so the call can be correlated with server logs. details: type: string description: | Present on a 429. Names which control refused the request: `user` Your per-subject window, counted against `X-SP-End-User`. `organization` Your organization's ceiling, across every key you hold. `capacity` The service is at capacity. Retry. `ingestion-organization` Too much of your own document work is already running. `ingestion-capacity` As above, service-wide. additionalProperties: false SourceId: type: string pattern: ^(?:img|src)_[0-9a-f]{32}$ description: Server-generated uploaded-source identifier. responses: BadRequest: description: > The request is not one this route can act on, and sending it again unchanged does not help. Usually the payload: a field missing, or a value out of range. It is also the credential and the headers around it, and each of these is refused rather than ignored: `X-SP-End-User` sent empty, or longer than 255 characters; and a key on a request that carries `Sec-Fetch-Site`, which only a browser sets. `code` is `invalid_request` throughout. `error` says which of these it was. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' Unauthorized: description: Missing or invalid credentials content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' NotFound: description: > No such id, or it is not one this key reaches. It is never a 403, so a key cannot be used to learn which ids exist. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' AgentNotReady: description: Agent exists but its dependencies are still initializing or failed content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' TooManyRequests: description: > A rate window or an admission control refused the request. `Retry-After` carries the seconds to wait, and `details` names which control refused. Nothing was learned and nothing was charged. headers: Retry-After: description: Seconds to wait before retrying. Always at least 1. required: true schema: type: integer minimum: 1 X-RateLimit-Limit: description: Requests the refusing window admits in its period. schema: type: integer minimum: 1 X-RateLimit-Remaining: description: Requests left in the current window. Zero on a refusal. schema: type: integer minimum: 0 X-RateLimit-Reset: description: Unix timestamp (seconds) at which the window admits again. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' ServiceUnavailable: description: > A required dependency could not complete the request. Distinct from a 500 by design: the body's `code` is `service_unavailable`, which says the request may succeed on a later attempt, where `internal_error` says it will not. Check the code before retrying. The same 503 carries `service_not_configured` when a feature this route needs is not switched on for your organization. The transport failure is identical and the wait is not: that one answers the same on every attempt until we change the configuration. Contact us. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' securitySchemes: partnerKey: type: http scheme: bearer description: > Your API key, shaped `sp__`, sent as `Authorization: Bearer sp_...`. It identifies your organization, not a person. Your organization owns the agents, holds the credit, and is billed. Every key your organization holds reaches the same things, so you rotate a key by minting the new one, deploying it, and revoking the old one. Keep the key on your server. A request that carries a `Sec-Fetch-Site` header is refused with 400, because only a browser sets that header. Priors sends no CORS headers, so a browser blocks the call before it leaves the page. The secret is shown once when the key is minted and is stored only as a hash. A lost secret is replaced, never recovered. An administrator of your organization mints and revokes keys in the Priors application, under Settings. There is no endpoint for it: a key reaches your whole organization, so issuing one is an act of administration. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.