> ## 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. # Stop an in-flight observation request > Stops one accepted observation request without deleting the thread. Turns already committed remain in memory and turns_processed reports how much was kept. Cancelling a completed request returns its real status. ## OpenAPI ````yaml /openapi.yaml post /v1/agents/{agent_id}/threads/{thread_id}/observe/{observation_id}/cancel 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}/observe/{observation_id}/cancel: post: tags: - Threads summary: Stop an in-flight observation request description: > Stops one accepted observation request without deleting the thread. Turns already committed remain in memory and turns_processed reports how much was kept. Cancelling a completed request returns its real status. operationId: cancel_observation parameters: - $ref: '#/components/parameters/AgentId' - $ref: '#/components/parameters/ThreadId' - $ref: '#/components/parameters/ObservationId' - $ref: '#/components/parameters/EndUser' responses: '200': description: Observation request status after cancellation content: application/json: schema: $ref: '#/components/schemas/ObservationStatusResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' components: parameters: AgentId: name: agent_id in: path required: true description: Unique managed memory-agent identifier. schema: type: string maxLength: 32 pattern: ^agent_[0-9A-HJKMNP-TV-Z]{26}$ 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}$ ObservationId: name: observation_id in: path required: true description: Identifier of an accepted observation request, scoped to the thread. schema: type: string maxLength: 30 pattern: ^obs_[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: ObservationStatusResponse: type: object required: - agent_id - thread_id - observation_id - status - turns_total - turns_processed properties: agent_id: $ref: '#/components/schemas/AgentId' thread_id: $ref: '#/components/schemas/ThreadId' observation_id: $ref: '#/components/schemas/ObservationId' status: type: string enum: - queued - converting - processing - committed - failed - cancelled - interrupted description: > `queued`, `converting`, and `processing`: still running; poll again. `interrupted`: a Priors restart paused the request, and it resumes by itself where it stopped, with nothing charged again; keep polling. `committed`, `failed`, and `cancelled` are final and never change. turns_total: type: integer minimum: 0 description: > Turns in this observation request. For a document upload this is the number of pieces it was split into, because one piece is exactly one turn. turns_processed: type: integer minimum: 0 description: > Turns read so far. Memory for a turn is written shortly after it is read, so reaching turns_total does not mean completion. Only status committed does. queue_depth: type: integer minimum: 0 description: > Observation jobs still pending ahead of this one on this thread. Zero means this thread's backlog is drained. error: type: string nullable: true description: Failure detail when status is failed. queued: type: boolean description: > True while the job waits its turn behind another file this agent is reading (the status is `converting` meanwhile). It starts by itself. Nothing to do. resumed_at: type: string format: date-time nullable: true description: > When a Priors restart paused this request and it resumed where it stopped, with nothing charged again. Null when it ran without a break. Show "resumed after an update, nothing to do" instead of an error. learning: allOf: - $ref: '#/components/schemas/ObservationLearning' nullable: true description: > Set when a job that ended `failed` or `cancelled` has settled: which of its turns were not learned into memory, and what was refunded for them. Null while the job runs, when it committed, and for an `interrupted` job, which resumes by itself. additionalProperties: false AgentId: type: string pattern: ^agent_[0-9A-HJKMNP-TV-Z]{26}$ description: Server-generated agent identifier. ThreadId: type: string pattern: ^thread_[0-9A-HJKMNP-TV-Z]{26}$ description: Server-generated thread identifier. ObservationId: type: string pattern: ^obs_[0-9A-HJKMNP-TV-Z]{26}$ description: Server-generated observation identifier. ObservationLearning: type: object description: > The turns of an observation job that were not learned into memory. They are never learned later, so send them again to have them learned. required: - status - not_learned_turns - reason - message - action properties: status: type: string enum: - not_learned not_learned_turns: type: array description: > The turns not learned, as 1-based inclusive ranges of the job's turns (turn 1 is the first observation the job was sent). items: type: object required: - first - last properties: first: type: integer minimum: 1 last: type: integer minimum: 1 additionalProperties: false reason: type: string description: > Stable machine code for why, for example generation_failed, model_unavailable, generation_timeout, generation_unparseable, memory_commit_shortfall, embedder_mismatch, earlier_turn_failed, queue_full, job_failed (the job stopped on an error of its own) or cancelled. Treat an unrecognised code like generation_failed. message: type: string description: A sentence to show a person. refunded_credits: type: string nullable: true pattern: ^-?\d+(\.\d+)?$ description: > Credits refunded for the input side of the turns not learned, as a decimal string. Null when nothing was refunded because nothing was charged. action: type: string enum: - resend description: Send the turns in not_learned_turns again. 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 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' Forbidden: description: | The credential is valid but may not take this action. 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' 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.