slen.ai
Начать

Выполните флоу и прочитайте его вызовы модели

Отправьте запрос через флоу, привязанный к коду операции, прочитайте операции — вызовы модели во флоу — со всеми попытками за ними и получите список холдов этих вызовов.

Две вещи на этой странице носят одно имя. Запрос к флоу называет код операции, и POST /v1/operations/execute выполняет флоу, привязанный к этому коду. Операция — это ещё и запись об одном вызове модели во флоу; два чтения этой страницы показывают список таких записей и одну запись со всеми попытками за ней. Последняя операция страницы показывает список холдов этих вызовов. Консоль показывает те же записи на странице Операции, на её вкладке Операции — экран описан в статье Операции, авторизации и реестр.

Выполнение и операция

  • POST /v1/operations/execute отвечает выполнением: одним проходом флоу, которое называет execution_id. Выполнение читают снова через GET /v1/executions/{id}/status и GET /v1/executions/{id}.

  • Операция — это один вызов модели, который называет operation_id. Одна операция открывается на каждый вызов модели, который делает флоу.

  • Идентификатор выполнения — не идентификатор операции: на него GET /v1/operations/{id} отвечает 404 с кодом operation_not_found.

Запись о вызове модели

Операция открывается, когда узел AI-модель вот-вот вызовет модель, после того как деньги на вызов зарезервированы. Она начинается со статуса pending и заканчивается одним из трёх статусов.

СтатусЧто он значит
completedМодель ответила
failedВызов закончился без ответа модели
uncertainНеизвестно, чем закончился вызов: провайдер не ответил вовремя или принял вызов на выполнение в фоне, и его не удалось об этом вызове спросить

Холд вызова со статусом uncertain не возвращается сразу: провайдеру, возможно, уже заплатили, поэтому холд держится, пока не истечёт. Такой вызов Slen тоже не повторяет. Когда ответ на вызов потерян, об этом сообщает событие вебхука operation.uncertain. Вызов, который провайдер выполняет в фоне, тоже сообщает, чем он закончился: operation.completed — когда провайдер ответил, operation.failed — когда вызов не удался, operation.uncertain — когда спросить провайдера о вызове больше не удалось. Чтобы найти вызовы с неизвестным исходом без вебхука, выберите операции по статусу, как в примере ниже.

Попытка — это один вызов одного подключения провайдера. Когда пул модели после сбоя переходит к другому подключению, операция получает следующую попытку с очередным номером. Попытка говорит, какое подключение и какую модель она использовала и чем она закончилась. Её cost остаётся null, пока вызов не закрыт.

  • Список содержит операции проекта ключа, сначала самые новые. Попытки он не показывает: attempts там — пустой список. Чтобы их увидеть, прочитайте одну операцию.

  • Операция не хранит ни промпт, ни ответ модели.

  • Попытка называет своё подключение и свой пул: connection_name и pool_name, рядом с ними — provider и connection_deleted. Имя равно null, если пул с тех пор удалён (pool_id остаётся) или если подключение или пул вне досягаемости ключа. Удалённое подключение сохраняет имя. finish_reason — почему провайдер остановился, так, как он это сообщил.

  • flow_execution называет выполнение и узел, вызовом модели которого является операция: execution_id, flow_id и node_key. Когда выполнение вне досягаемости ключа, это null, и это поле есть только при чтении одной операции, не в списке.

Поиск и нумерованные страницы

q ищет по списку. Цифры, которые являются ID операции проекта, находят ровно эту операцию, какой бы старой она ни была: окно from и to к ней не применяется, а status и operation_code — применяются. Любой другой текст находит операции, у которых external_user_id равен этому тексту или начинается с него, внутри окна; % и _ там — обычные символы. На q длиннее 190 символов ответ — 422. Значение входит в адрес, поэтому external_user_id, который является адресом e-mail, попадает в историю браузеров и в журналы доступа.

Список читают курсором, как любой список, — Список по страницам, — или по номеру страницы. Отправьте page, и в meta придут page, limit, total и anchor. total считается до 10 000; дальше он остаётся 10 000, а total_capped равен true. Отправляйте anchor первой страницы со всеми остальными страницами: считаются только операции с ID не больше него, поэтому операция, открытая за это время, не сдвигает строки со страницы на страницу. На page вместе с cursor и на anchor без page ответ — 422.

Холды вызовов

GET /v1/authorizations показывает список холдов проекта, самые новые — первыми: по одному на каждый вызов модели, с тем, сколько вызов должен был стоить, сколько было зарезервировано и сколько списано. Он требует разрешения read и читает окно не длиннее семи дней, как список операций, — курсором или по номеру страницы. operation_code оставляет холды одного кода операции. Что значит каждый статус холда, объясняет статья Как работает резервирование бюджета, а консоль показывает те же холды на вкладке Авторизации экрана Операции.

Операции

Описания операций и полей приведены на английском.

Запустить флоу, привязанный к операции

POST /v1/operations/execute

  • Разрешение: gateway:write
  • Нужен Idempotency-Key
  • Доступно в SDK для PHP и Node.js

The caller names what it wants done, never a model or a pool. Answers 202 when the flow parked at a queue or approval node — waiting_on says on what — and also when execution_mode: async handed the run to a queue worker, where the status is queued and nothing has walked yet. Both carry retry_after_seconds. Idempotent.

The Idempotency-Key belongs to the execution it opened, and no copy of the answer is kept beside it: a repeated key with the same body is answered from that execution as it is now (replayed: true) and runs nothing. 202 with retry_after_seconds while it has not finished — queued, waiting, or running when the retry met a walk still under way (a synchronous run may outlast the caller's timeout) — and 200 with the outcome once it has: output of a completed run, error_code and error_message of one that was refused or failed, even when the first answer was an error envelope — error repeats the two as {code, message}, on a replay exactly as on the first answer. The same key with a different body is 409 idempotency_conflict.

A flow that refuses is not an HTTP error: a reject node answers 200 with status: rejected. A walk that throws is one: the execution is closed — failed, rejected when the gateway refused to spend (policy_denied, customer_blocked, budget_exceeded, insufficient_credits, an overrun), uncertain when the provider's answer was lost — with the same code in its error_code, and the answer is the error envelope with the status of what threw. The code of the envelope and the code of the row are one and the same, also for what is wrong with the setup rather than refused by a policy: customer_not_found (404), model_not_allowed (403), cost_calculation_failed (422) and ledger_unavailable (503) close the execution failed with that code.

A synchronous run that outlives the running ceiling (15 minutes by default) is closed failed with execution_lost while its walk is still under way. Whatever that walk goes on to compute is not the outcome of the execution, and the call is answered with the execution as its row has it — 200, failed, execution_lost, no output, replayed: false — exactly what a repeated key is told afterwards. A model call the walk did make is paid for, and cost.actual arrives.

A model node routes a refusal to spend into its deny port when something is connected to it — policy_denied, customer_blocked, budget_exceeded, insufficient_credits, overrun_stopped — and then the flow decides what the caller hears. The setup errors above are never routed.

403 customer_blocked — the context.user_id names a customer that is blocked (POST /v1/customers/{externalUserId}/block). Nothing is created: no execution, no hold. A repeated key of an execution opened before the block is still answered by that execution. A run already under way — queued, or parked at an approval — meets the block at its next model node that takes credits: the hold is refused, and the execution closes rejected with customer_blocked (a model node with something on its deny port routes it there, like a policy refusal). A run whose operation has no price in credits takes no hold and finishes.

404 flow_not_found — no flow is bound to the operation, the flow was never published, or it is archived. Nothing is created for such a call — no execution, no hold — so the same key runs once the flow is un-archived. An execution parked before its flow was archived still finishes, and the key of an execution that exists is answered by it whatever became of the flow or its binding since: the 404 is for a key that opened nothing.

Параметры

ПараметрОписание
Idempotency-Key обязательно

headerstring

Replay guard for a financial write. The same key returns the original result with the original status and never charges twice; a different body under a used key answers idempotency_conflict.

  • Максимальная длина: 190

Тело запроса

application/json
{
  "operation": "generate_email",
  "input": {},
  "context": {
    "user_id": "74438200973594624",
    "credit_type": "default"
  },
  "execution_mode": "sync"
}

Ответы

200

The finished run

application/json
{
  "data": {
    "execution_id": "74438200973594624",
    "status": "running",
    "operation": "generate_email",
    "output": {},
    "error_code": "string",
    "error_message": "string",
    "cost": {
      "estimated": "0.02700000",
      "actual": "0.02700000"
    },
    "cache": {
      "hit": true,
      "cached_at": "2026-10-02T09:30:00Z"
    },
    "waiting_on": {
      "node_key": "string",
      "type": "queue_node",
      "resume_at": "2026-10-02T09:30:00Z"
    },
    "trace_url": "string",
    "retry_after_seconds": 1,
    "error": {
      "code": "string",
      "message": "string"
    },
    "replayed": true
  }
}
202

The run has not finished: it parked, was queued, or — on a repeated key — is still walking. Come back after retry_after_seconds.

application/json
{
  "data": {
    "execution_id": "74438200973594624",
    "status": "running",
    "operation": "generate_email",
    "output": {},
    "error_code": "string",
    "error_message": "string",
    "cost": {
      "estimated": "0.02700000",
      "actual": "0.02700000"
    },
    "cache": {
      "hit": true,
      "cached_at": "2026-10-02T09:30:00Z"
    },
    "waiting_on": {
      "node_key": "string",
      "type": "queue_node",
      "resume_at": "2026-10-02T09:30:00Z"
    },
    "trace_url": "string",
    "retry_after_seconds": 1,
    "error": {
      "code": "string",
      "message": "string"
    },
    "replayed": true
  }
}

Ошибки

СтатусКодыКогда
400

Malformed request — e.g. the Idempotency-Key header is missing

401

No credential, or one that is not valid

402

Refused because of money: budget_exceeded, operation_limit_exceeded, concurrency_limit_exceeded, insufficient_credits, overrun_stopped, overrun_approval_required

403

Authenticated, but not allowed: scope (insufficient_scope), policy or tenant (not_a_member); a blocked end customer (customer_blocked); an act only a signed-in person may take (session_required); the role rule on members and invitations (member_forbidden, invite_forbidden); a write to the organization's own rows, or a read of the audit journal, by a caller that does not reach every project (project_access_restricted)

404

No such resource for this tenant. Somebody else's resource — and a resource of a project the caller does not reach — answers the same way on purpose: the two must not be distinguishable.

409

State conflict: idempotency clash, stale draft, illegal transition; the last owner of an organization (last_owner); the owned-organization limit (organization_limit_reached); an end customer with credit history that cannot be deleted (customer_has_history)

422

Validation failure or a semantically impossible request. Field-level validation from the framework answers {"message", "errors"}; domain refusals answer the standard error envelope. An Idempotency-Key longer than 190 characters is invalid_request in that envelope.

429

Rate limited for this API key

500

The walk broke and the execution is closed as failed (uncertain for operation_uncertain). 500: unrouted_port (a node left by a port nothing is connected to), step_limit_exceeded, unknown_node, node_type_not_supported, execution_conflict. 502: provider_error, http_request_failed. 503: pool_exhausted, ledger_unavailable (the spend ledger could not be reached when a model node asked for its hold: a flow is never served in degraded mode, so the provider was not called for that node and nothing was spent on it; with the database gone before the request arrived the answer is service_unavailable from the connection check instead, and no execution exists). 504: provider_timeout, execution_timeout, or operation_uncertain when we do not know whether the money was spent. execution_timeout is the walk stopping itself between two nodes. While the run has not paid for a model answer, no node of any type is started once its current stretch is older than its deadline (two minutes by default) — an unpaid tail of transform or http_request nodes does not run to the end. Once a model answer has been paid for, no further model call is started past that deadline and no http_request past the tail deadline (four minutes by default) — the remaining nodes that call nobody still run. A model call that was paid for before the stop is settled as for a completed run, so a retry under a new Idempotency-Key pays again. A model call entered before the deadline finishes the attempt in flight and starts no new one past it: the call then ends as pool_exhausted, with the code of its last attempt. An exhausted pool is the caller's answer only when the model node has an edge on neither rate_limit nor error: it leaves by rate_limit when that port is connected, otherwise by error when that one is. A pool_exhausted that reaches the caller as the gateway raised it carries error.details.last_error_code and, when the provider gave a hint, Retry-After

502

The walk broke and the execution is closed as failed (uncertain for operation_uncertain). 500: unrouted_port (a node left by a port nothing is connected to), step_limit_exceeded, unknown_node, node_type_not_supported, execution_conflict. 502: provider_error, http_request_failed. 503: pool_exhausted, ledger_unavailable (the spend ledger could not be reached when a model node asked for its hold: a flow is never served in degraded mode, so the provider was not called for that node and nothing was spent on it; with the database gone before the request arrived the answer is service_unavailable from the connection check instead, and no execution exists). 504: provider_timeout, execution_timeout, or operation_uncertain when we do not know whether the money was spent. execution_timeout is the walk stopping itself between two nodes. While the run has not paid for a model answer, no node of any type is started once its current stretch is older than its deadline (two minutes by default) — an unpaid tail of transform or http_request nodes does not run to the end. Once a model answer has been paid for, no further model call is started past that deadline and no http_request past the tail deadline (four minutes by default) — the remaining nodes that call nobody still run. A model call that was paid for before the stop is settled as for a completed run, so a retry under a new Idempotency-Key pays again. A model call entered before the deadline finishes the attempt in flight and starts no new one past it: the call then ends as pool_exhausted, with the code of its last attempt. An exhausted pool is the caller's answer only when the model node has an edge on neither rate_limit nor error: it leaves by rate_limit when that port is connected, otherwise by error when that one is. A pool_exhausted that reaches the caller as the gateway raised it carries error.details.last_error_code and, when the provider gave a hint, Retry-After

503

The walk broke and the execution is closed as failed (uncertain for operation_uncertain). 500: unrouted_port (a node left by a port nothing is connected to), step_limit_exceeded, unknown_node, node_type_not_supported, execution_conflict. 502: provider_error, http_request_failed. 503: pool_exhausted, ledger_unavailable (the spend ledger could not be reached when a model node asked for its hold: a flow is never served in degraded mode, so the provider was not called for that node and nothing was spent on it; with the database gone before the request arrived the answer is service_unavailable from the connection check instead, and no execution exists). 504: provider_timeout, execution_timeout, or operation_uncertain when we do not know whether the money was spent. execution_timeout is the walk stopping itself between two nodes. While the run has not paid for a model answer, no node of any type is started once its current stretch is older than its deadline (two minutes by default) — an unpaid tail of transform or http_request nodes does not run to the end. Once a model answer has been paid for, no further model call is started past that deadline and no http_request past the tail deadline (four minutes by default) — the remaining nodes that call nobody still run. A model call that was paid for before the stop is settled as for a completed run, so a retry under a new Idempotency-Key pays again. A model call entered before the deadline finishes the attempt in flight and starts no new one past it: the call then ends as pool_exhausted, with the code of its last attempt. An exhausted pool is the caller's answer only when the model node has an edge on neither rate_limit nor error: it leaves by rate_limit when that port is connected, otherwise by error when that one is. A pool_exhausted that reaches the caller as the gateway raised it carries error.details.last_error_code and, when the provider gave a hint, Retry-After

504

The walk broke and the execution is closed as failed (uncertain for operation_uncertain). 500: unrouted_port (a node left by a port nothing is connected to), step_limit_exceeded, unknown_node, node_type_not_supported, execution_conflict. 502: provider_error, http_request_failed. 503: pool_exhausted, ledger_unavailable (the spend ledger could not be reached when a model node asked for its hold: a flow is never served in degraded mode, so the provider was not called for that node and nothing was spent on it; with the database gone before the request arrived the answer is service_unavailable from the connection check instead, and no execution exists). 504: provider_timeout, execution_timeout, or operation_uncertain when we do not know whether the money was spent. execution_timeout is the walk stopping itself between two nodes. While the run has not paid for a model answer, no node of any type is started once its current stretch is older than its deadline (two minutes by default) — an unpaid tail of transform or http_request nodes does not run to the end. Once a model answer has been paid for, no further model call is started past that deadline and no http_request past the tail deadline (four minutes by default) — the remaining nodes that call nobody still run. A model call that was paid for before the stop is settled as for a completed run, so a retry under a new Idempotency-Key pays again. A model call entered before the deadline finishes the attempt in flight and starts no new one past it: the call then ends as pool_exhausted, with the code of its last attempt. An exhausted pool is the caller's answer only when the model node has an edge on neither rate_limit nor error: it leaves by rate_limit when that port is connected, otherwise by error when that one is. A pool_exhausted that reaches the caller as the gateway raised it carries error.details.last_error_code and, when the provider gave a hint, Retry-After

Заголовки

  • X-Request-Id
  • Retry-After429

Тело каждой ошибки — конверт ошибки.

Список операций

GET /v1/operations

  • Разрешение: read

Параметры

ПараметрОписание
cursor необязательно

querystring

The meta.next_cursor of the previous page.

limit необязательно

queryinteger

Page size (default 30).

  • Минимум: 1
  • Максимум: 100
page необязательно

queryinteger

The page number, from 1. Turns the list into its numbered form: the answer's meta is a PageMeta (with total) instead of a CursorMeta. Together with cursor it is a 422; without page the answer is the cursor page, unchanged. A page past the last one is an empty data with the same total.

  • Минимум: 1
  • Максимум: 10000
anchor необязательно

querystring

The meta.anchor of the first numbered page: only rows with an id at or below it are counted and paged, so rows written after the first page do not shift pages 2..N. Without it the newest matching row is the anchor, and the answer names it. Only with page (422 otherwise).

  • Шаблон: ^\d{1,20}$
q необязательно

querystring

Search. Digits that are the id of an operation of the project find exactly that operation, past the window — the id carries its own moment, so from / to (and the default last 7 days) do not apply to it; status and operation_code still do. Anything else — and digits that are no operation of the project — is an external_user_id: equal to it or starting with it, inside the window. % and _ are characters, not patterns. An empty value is no search. The value lands in the URL; an external_user_id that is an e-mail address is then in browser history and access logs.

  • Максимальная длина: 190
operation_code необязательно

querystring

  • Максимальная длина: 120
status необязательно

queryOperationStatus

  • Одно из: pending, completed, failed, uncertain
from необязательно

querystring

Window start, ISO-8601 — a value with an offset is the moment it names, one without is read as UTC. The rule of the three lists that take this parameter (/v1/operations, /v1/authorizations, /v1/ledger-entries): from and to are given together or not at all, to must not precede from, and the window must not exceed 7 days. Naming neither end selects the last 7 days rather than the whole table — an unbounded range is the one query shape that cannot use the (project_id, created_at, id) index. Anything else answers 422 invalid_date_range. The analytics read their window by another rule (WindowFrom).

  • Формат: date-time
to необязательно

querystring

Window end, ISO-8601, inclusive. See from for the window rule of the three lists: both ends together, to >= from, at most 7 days, otherwise 422 invalid_date_range.

  • Формат: date-time

Ответы

200

One page of operations — a cursor page, or a numbered one with page

application/json
{
  "data": [
    {
      "operation_id": "74438200973594624",
      "operation_code": "generate_email",
      "external_user_id": "user_8421",
      "status": "pending",
      "attempts": [
        {
          "attempt_id": "74438200973594624",
          "attempt_number": 1,
          "connection_id": "74438200973594624",
          "pool_id": "74438200973594624",
          "model_code": "gpt-4o-mini",
          "model_price_id": "74438200973594624",
          "status": "pending",
          "error_code": "string",
          "provider_request_id": "74438200973594624",
          "input_tokens": 1,
          "output_tokens": 1,
          "cost": "0.02700000",
          "cost_multiplier": "string",
          "latency_ms": 1,
          "started_at": "2026-10-02T09:30:00Z",
          "completed_at": "2026-10-02T09:30:00Z",
          "pool_name": "string",
          "connection_name": "string",
          "connection_deleted": true,
          "provider": "string",
          "finish_reason": "string"
        }
      ],
      "created_at": "2026-10-02T09:30:00Z",
      "updated_at": "2026-10-02T09:30:00Z",
      "flow_execution": {
        "execution_id": "74438200973594624",
        "flow_id": "74438200973594624",
        "node_key": "string"
      }
    }
  ],
  "meta": {
    "limit": 1,
    "next_cursor": "string"
  }
}

Ошибки

СтатусКодыКогда
401

No credential, or one that is not valid

403

Authenticated, but not allowed: scope (insufficient_scope), policy or tenant (not_a_member); a blocked end customer (customer_blocked); an act only a signed-in person may take (session_required); the role rule on members and invitations (member_forbidden, invite_forbidden); a write to the organization's own rows, or a read of the audit journal, by a caller that does not reach every project (project_access_restricted)

422

Validation failure or a semantically impossible request. Field-level validation from the framework answers {"message", "errors"}; domain refusals answer the standard error envelope. An Idempotency-Key longer than 190 characters is invalid_request in that envelope.

Заголовки

  • X-Request-Id

Тело каждой ошибки — конверт ошибки.

Один запрос со всеми попытками провайдеров

GET /v1/operations/{id}

  • Разрешение: read

The way to find out what an uncertain operation actually did.

Параметры

ПараметрОписание
id обязательно

pathId

Snowflake identifier, as a string.

  • Шаблон: ^\d+$
  • Пример: 74438200973594624

Ответы

200

The operation and its attempts

application/json
{
  "data": {
    "operation_id": "74438200973594624",
    "operation_code": "generate_email",
    "external_user_id": "user_8421",
    "status": "pending",
    "attempts": [
      {
        "attempt_id": "74438200973594624",
        "attempt_number": 1,
        "connection_id": "74438200973594624",
        "pool_id": "74438200973594624",
        "model_code": "gpt-4o-mini",
        "model_price_id": "74438200973594624",
        "status": "pending",
        "error_code": "string",
        "provider_request_id": "74438200973594624",
        "input_tokens": 1,
        "output_tokens": 1,
        "cost": "0.02700000",
        "cost_multiplier": "string",
        "latency_ms": 1,
        "started_at": "2026-10-02T09:30:00Z",
        "completed_at": "2026-10-02T09:30:00Z",
        "pool_name": "string",
        "connection_name": "string",
        "connection_deleted": true,
        "provider": "string",
        "finish_reason": "string"
      }
    ],
    "created_at": "2026-10-02T09:30:00Z",
    "updated_at": "2026-10-02T09:30:00Z",
    "flow_execution": {
      "execution_id": "74438200973594624",
      "flow_id": "74438200973594624",
      "node_key": "string"
    }
  }
}

Ошибки

СтатусКодыКогда
401

No credential, or one that is not valid

403

Authenticated, but not allowed: scope (insufficient_scope), policy or tenant (not_a_member); a blocked end customer (customer_blocked); an act only a signed-in person may take (session_required); the role rule on members and invitations (member_forbidden, invite_forbidden); a write to the organization's own rows, or a read of the audit journal, by a caller that does not reach every project (project_access_restricted)

404

No such resource for this tenant. Somebody else's resource — and a resource of a project the caller does not reach — answers the same way on purpose: the two must not be distinguishable.

Заголовки

  • X-Request-Id

Тело каждой ошибки — конверт ошибки.

Список холдов

GET /v1/authorizations

  • Разрешение: read

Параметры

ПараметрОписание
cursor необязательно

querystring

The meta.next_cursor of the previous page.

limit необязательно

queryinteger

Page size (default 30).

  • Минимум: 1
  • Максимум: 100
page необязательно

queryinteger

The page number, from 1. Turns the list into its numbered form: the answer's meta is a PageMeta (with total) instead of a CursorMeta. Together with cursor it is a 422; without page the answer is the cursor page, unchanged. A page past the last one is an empty data with the same total.

  • Минимум: 1
  • Максимум: 10000
anchor необязательно

querystring

The meta.anchor of the first numbered page: only rows with an id at or below it are counted and paged, so rows written after the first page do not shift pages 2..N. Without it the newest matching row is the anchor, and the answer names it. Only with page (422 otherwise).

  • Шаблон: ^\d{1,20}$
operation_code необязательно

querystring

  • Максимальная длина: 120
from необязательно

querystring

Window start, ISO-8601 — a value with an offset is the moment it names, one without is read as UTC. The rule of the three lists that take this parameter (/v1/operations, /v1/authorizations, /v1/ledger-entries): from and to are given together or not at all, to must not precede from, and the window must not exceed 7 days. Naming neither end selects the last 7 days rather than the whole table — an unbounded range is the one query shape that cannot use the (project_id, created_at, id) index. Anything else answers 422 invalid_date_range. The analytics read their window by another rule (WindowFrom).

  • Формат: date-time
to необязательно

querystring

Window end, ISO-8601, inclusive. See from for the window rule of the three lists: both ends together, to >= from, at most 7 days, otherwise 422 invalid_date_range.

  • Формат: date-time

Ответы

200

One page of reservations — a cursor page, or a numbered one with page

application/json
{
  "data": [
    {
      "reservation_id": "74438200973594624",
      "status": "authorized",
      "model_code": "gpt-4o-mini",
      "operation_code": "generate_email",
      "external_user_id": "user_8421",
      "idempotency_key": "order-42:email",
      "estimated_cost": "0.02700000",
      "reserved_amount": "0.02700000",
      "captured_amount": "0.02700000",
      "overrun_amount": "0.02700000",
      "estimated_input_tokens": 1,
      "estimated_output_tokens": 1,
      "max_output_tokens": 1,
      "safety_multiplier": "string",
      "estimation_strategy": "fixed",
      "model_price_id": "74438200973594624",
      "customer_hold_id": "74438200973594624",
      "customer_hold_credits": "12.5000",
      "currency": "USD",
      "expires_at": "2026-10-02T09:30:00Z",
      "created_at": "2026-10-02T09:30:00Z"
    }
  ],
  "meta": {
    "limit": 1,
    "next_cursor": "string"
  }
}

Ошибки

СтатусКодыКогда
401

No credential, or one that is not valid

403

Authenticated, but not allowed: scope (insufficient_scope), policy or tenant (not_a_member); a blocked end customer (customer_blocked); an act only a signed-in person may take (session_required); the role rule on members and invitations (member_forbidden, invite_forbidden); a write to the organization's own rows, or a read of the audit journal, by a caller that does not reach every project (project_access_restricted)

422

Validation failure or a semantically impossible request. Field-level validation from the framework answers {"message", "errors"}; domain refusals answer the standard error envelope. An Idempotency-Key longer than 190 characters is invalid_request in that envelope.

Заголовки

  • X-Request-Id

Тело каждой ошибки — конверт ошибки.

Примеры

Выполнить флоу

Флоу, привязанный к generate_email, ответил сразу, поэтому статус — completed, а в output лежит то, что вернул флоу. cost.actual здесь — null: вызов модели закрывается после ответа.

Terminal
curl https://api.slen.ai/api/v1/operations/execute \
  -H "Authorization: Bearer $SLEN_API_KEY" \
  -H "Idempotency-Key: order-42:email" \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "generate_email",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Write a short follow-up email."
        }
      ]
    }
  }'
200 OK
{
  "data": {
    "execution_id": "74438200973594700",
    "status": "completed",
    "operation": "generate_email",
    "output": {
      "model": "gpt-4o",
      "content": "Hi Ada, just checking in on the proposal I sent last week.",
      "finish_reason": "stop",
      "tool_calls": null,
      "usage": {
        "input_tokens": 14,
        "output_tokens": 16,
        "cached_input_tokens": 0
      }
    },
    "error": null,
    "error_code": null,
    "error_message": null,
    "cost": {
      "estimated": "0.00412500",
      "actual": null
    },
    "cache": {
      "hit": false,
      "cached_at": null
    },
    "replayed": false,
    "waiting_on": null,
    "trace_url": "/v1/executions/74438200973594700"
  }
}

Найти вызовы с неизвестным исходом

Фильтр оставляет операции со статусом uncertain одного кода операции, ID клиента которых начинается с user_84, на первой нумерованной странице. Среди них — один вызов для user_8421.

Terminal
curl "https://api.slen.ai/api/v1/operations?q=user_84&operation_code=generate_email&status=uncertain&page=1" \
  -H "Authorization: Bearer $SLEN_API_KEY"
200 OK
{
  "data": [
    {
      "operation_id": "74442181054119936",
      "operation_code": "generate_email",
      "external_user_id": "user_8421",
      "status": "uncertain",
      "attempts": [],
      "created_at": "2026-10-02T09:12:04+00:00",
      "updated_at": "2026-10-02T09:13:04+00:00"
    }
  ],
  "meta": {
    "limit": 30,
    "page": 1,
    "total": 1,
    "total_capped": false,
    "anchor": "74442181054119936"
  }
}

Прочитать вызов с его попытками

У вызова была одна попытка, через пул Primary. Подключение не ответило вовремя, поэтому попытка — uncertain, и в ней нет ни токенов, ни стоимости, ни finish_reason. Вызов — это вызов модели узла model одного флоу, и flow_execution называет его выполнение.

Terminal
curl https://api.slen.ai/api/v1/operations/74442181054119936 \
  -H "Authorization: Bearer $SLEN_API_KEY"
200 OK
{
  "data": {
    "operation_id": "74442181054119936",
    "operation_code": "generate_email",
    "external_user_id": "user_8421",
    "status": "uncertain",
    "attempts": [
      {
        "attempt_id": "74442181058314240",
        "attempt_number": 1,
        "connection_id": "74438912450035712",
        "pool_id": "74438955400675328",
        "model_code": "gpt-4o-mini",
        "model_price_id": "1108",
        "status": "uncertain",
        "error_code": "operation_uncertain",
        "provider_request_id": null,
        "input_tokens": null,
        "output_tokens": null,
        "cost": null,
        "cost_multiplier": "1.0000",
        "latency_ms": 60004,
        "started_at": "2026-10-02T09:12:04+00:00",
        "completed_at": "2026-10-02T09:13:04+00:00",
        "pool_name": "Primary",
        "connection_name": "OpenAI production",
        "connection_deleted": false,
        "provider": "openai",
        "finish_reason": null
      }
    ],
    "created_at": "2026-10-02T09:12:04+00:00",
    "updated_at": "2026-10-02T09:13:04+00:00",
    "flow_execution": {
      "execution_id": "74442180941398016",
      "flow_id": "74438623450128384",
      "node_key": "model"
    }
  }
}

Получить холды одной операции

Запрос оставляет холды generate_email за последние семь дней, по двадцать на страницу.

Terminal
curl "https://api.slen.ai/api/v1/authorizations?operation_code=generate_email&limit=20" \
  -H "Authorization: Bearer $SLEN_API_KEY"

Что читать дальше

Собрано из openapi b070e1f, sdk contract 5cc7055, php ae4a53b, node 84bc62d