---
title: "Start an agent run in the background"
method: POST
path: "/computers/{id}/agent/runs"
tags: ["Agents"]
---

# Start an agent run in the background

`POST /computers/{id}/agent/runs`

## Request

- Base URL: `https://app.mandala.computer/api/v1`
- URL: `https://app.mandala.computer/api/v1/computers/{id}/agent/runs`
- Auth: HTTP bearer

Give the computer a job and walk away: the same loop as `POST /computers/{id}/agent`, with the same body except `stream` (refused) and `store: false` (refused: a background run is kept so it can be read back), started and then read back by id instead of streamed. The run goes on when this request ends, and is not cut at the edge after 120 seconds the way a non-streaming agent call is.

This answers `202` once the run holds the computer, with the run as it stands (`status: "running"`). What refuses a run before that — an unknown or just-deleted computer (`404`), one not running (`409`), one already driven or whose workspace is changing (`409` with `reason: "contention"`), a credential refused, the funded credit hold — is answered here as its own status with `{error, reason?, top_up_url?}`, and no run is recorded. Everything after it, the model API’s errors included, ends the run as `failed` with that `error`.

Poll `GET /agent/runs/{run}` for its steps, cost and ending, or cancel it with `POST /agent/runs/{run}/cancel`. A run keeps its thread as the agent route does, and `thread_id` on the run says which. `X-Model-Key` is held in memory for the run’s life and never stored. The run uses the API key that started it: deleting that key stops it at its next step, as on the agent route. A run the control plane was executing when it restarted is marked `interrupted`, with the steps it had taken; it is not resumed. Inspect the desktop before starting another.

The screenshot each step returns, the one the model is shown next, is kept with the run for seven days (within per-run and per-account size limits) so the run can be replayed step by step on the computer’s Activities tab in the dashboard. Those screenshots show whatever was on the screen, so treat them as being as sensitive as the desktop. They are deleted with the run, and with its computer.

Requires the `member` role or higher.

## Path parameters

- `id` string, required

## Headers

- `X-Model-Key` string

## Request body

- object
  - `prompt` string, required: What you want done, in plain language. Required.
  - `system` string: A system prompt for the model. Requires your own X-Model-Key.
  - `max_cost_usd` number: As on `POST /computers/{id}/agent`.
  - `max_steps` integer: As on `POST /computers/{id}/agent`: defaults to 20, at most 100.
  - `provider` 'anthropic' | 'openai': As on `POST /computers/{id}/agent`.
  - `model` string: As on `POST /computers/{id}/agent`.
  - `thread_id` string: A thread to continue, as on `POST /computers/{id}/agent`.
  - `store` boolean: As on `POST /computers/{id}/agent`. Default `true`.
  - `messages` object[]: As on `POST /computers/{id}/agent`.
    - `role` 'user' | 'assistant', required
    - `content` string, required

## Response `202`

The run, running.

- AgentRun
  - `id` string, required: `run_` and twenty-four hex characters.
  - `computer_id` string, required
  - `thread_id` string, nullable, required: The thread the run is kept in, once it is: `null` until a new thread has something in it (a run that has not acted yet, or failed before it did), and when the thread was deleted. Continue it with `thread_id` on the next run.
  - `status` 'running' | 'completed' | 'failed' | 'cancelled' | 'interrupted', required: `completed`: the loop ended on its own, and `result.stop` says how — only `end_turn` means the task was finished. `failed`: see `error`. `cancelled`: stopped by a cancel. `interrupted`: the control plane restarted while it was going (`error.status` 503), or the run stopped without its ending being recorded (`error.status` 500); it was not resumed.
  - `prompt` string, required: The prompt, at most 32,000 characters of it.
  - `model` string, required: The model the run was started with.
  - `max_steps` integer, required
  - `steps` integer, required: How many actions it has taken so far.
  - `cost_usd` number: Funded runs: the charge so far, in USD.
  - `result` AgentResult
    - `cost_usd` number: Cumulative AI credit charge in USD, present on funded runs only.
    - `steps` integer, required: How many actions the loop took — a count; the actions themselves are `steps_taken`.
    - `stop` string, required: Why the loop ended: `end_turn` (the model finished), `max_steps` (it reached `max_steps`), `refusal` (the model declined), `pause_turn` (the model kept pausing its turn), `rate_limited` (your rate budget ran out mid-run), `credits_exhausted` (funded credits unavailable), `max_cost` (the next reservation would exceed max_cost_usd), or another stop reason the model itself gave, such as `max_tokens`. OpenAI also reports `incomplete` for an unfinished response and `safety_check` when action approval is needed. Only `end_turn` means the task was finished; the others are a run that stopped, and the work it did to the desktop stands.
    - `text` string, required: The model’s closing text — its answer, or why it could not get there.
    - `usage` AgentUsage, required
      - `input_tokens` integer, required: Input tokens, the cache reads and writes below included.
      - `output_tokens` integer, required
      - `cache_read_tokens` integer, required
      - `cache_write_tokens` integer, required: Provider-reported cache writes; zero only when absent. OpenAI reads input_tokens_details.cache_write_tokens.
    - `thread_id` string: The thread this exchange was kept in; send it as `thread_id` to continue. Absent with `store: false`.
    - `steps_taken` AgentStep[]: Every action, in order. On the `stream: false` body only; the stream’s `done` event carries the other fields, and each action arrived before it as a `step` event.
      - `cost_usd` number: Cumulative funded run charge in USD. Multiple tools in one reply repeat the same total; do not sum these fields.
      - `credits_remaining_usd` number: Available account AI credits after this model call; may be negative after an overrun. Omitted if the post-debit balance lookup is unavailable.
      - `n` integer, required: Its position in the run, from 1.
      - `tool` string, required: The tool the model reached for, e.g. `computer` or `bash`.
      - `action` string: The provider-native action within it, e.g. `left_click`, `zoom` or OpenAI `click`. Absent for `bash`.
      - `detail` string: What the platform did with it, in one line.
      - `error` string: Present when an action failed or was refused. On an Anthropic run the model is told and the loop goes on. On an OpenAI run a failed batch or `bash` command ends the run as a failure, after the actions the desktop acknowledged; input is not replayed.
  - `error` object
    - `error` string, required: What went wrong, in a sentence.
    - `status` integer, required: The status the agent route would have answered it with.
    - `reason` string: The one-word classification, where there is one — see `Error`.
    - `top_up_url` string: Where to add credits, when the run failed for want of them.
  - `steps_taken` AgentStep[], required: Every action so far, in order. Empty in a list.
    - `cost_usd` number: Cumulative funded run charge in USD. Multiple tools in one reply repeat the same total; do not sum these fields.
    - `credits_remaining_usd` number: Available account AI credits after this model call; may be negative after an overrun. Omitted if the post-debit balance lookup is unavailable.
    - `n` integer, required: Its position in the run, from 1.
    - `tool` string, required: The tool the model reached for, e.g. `computer` or `bash`.
    - `action` string: The provider-native action within it, e.g. `left_click`, `zoom` or OpenAI `click`. Absent for `bash`.
    - `detail` string: What the platform did with it, in one line.
    - `error` string: Present when an action failed or was refused. On an Anthropic run the model is told and the loop goes on. On an OpenAI run a failed batch or `bash` command ends the run as a failure, after the actions the desktop acknowledged; input is not replayed.
  - `created_at` string, required
  - `updated_at` string, required: When it last took a step or changed status.
  - `ended_at` string, nullable, required: When it ended; `null` while running.

## Other responses

- `400`: The request was malformed — a bad resolution string, a missing `command`, a `{pid}` or `{window}` that is not one. It is also what a well-formed request gets when the thing it names cannot be acted on and never will be — a restore onto a computer that is gone, for instance. Either way it is final: the message says what is wrong, and sending it again unchanged answers the same. That is the whole difference from a `503`, which means ask again shortly.
- `401`: Platform authentication required or refused: reason is missing, invalid, or revoked, with WWW-Authenticate: Bearer (invalid_token for invalid/revoked).
- `402`: Your plan refused this: a quota, or a payment that has not gone through. On an agent run it can instead be `Insufficient AI credits` with `top_up_url` (a run funded by the account’s AI credits), or the model provider’s own billing refusal of your `X-Model-Key`, relayed.
- `403`: The credential is recognized but its holder lacks the required role or membership, or the holder/account is suspended, or the holder has not verified their email address. An ordinary denial for too low a role may carry no `reason`. The email one carries none either, and its message begins `Verify your email before`: it answers a create, a clone of a computer or a snapshot, a new API key and a new SSH key, and is cleared by verifying the address in the dashboard. `reason: "revoked"` marks authority that is gone: a suspended account or a lost membership (refused as the request arrives, or if it happens while the request is in flight), or a role that was lowered while the request was in flight. The message identifies the refusal; replacing a valid key alone does not restore authority, and sending the same call again does not help.
- `404`: No such resource in your scope — a computer, snapshot, secret, webhook, SSH key, API key, workspace, operation and so on — or no such endpoint; a confirmed missing guest file is no such file in the guest.
- `405`: This public path exists but does not accept that method. Allow lists only its public methods, with HEAD for GET and metadata OPTIONS.
- `409`: Refused for the state something is in — resizing a computer that is running, running a command on one that is stopped, taking a snapshot while another capture of it is running. WHETHER RETRYING HELPS IS IN THE BODY, NOT THE STATUS, and this is the one thing to take from this entry. Some of these describe a state that is passing: a guest agent still inside its boot window, a guest agent busy with another call, a move already running on the account. Those clear on their own and the same request works a moment later. The rest describe a DECISION about the request you sent — the size does not fit, the computer is the wrong one for this, the saved session cannot travel — and no amount of retrying turns one of those into a yes. A client that treats 409 as uniformly transient loops forever on half of them. Where the platform can say which it is, it sends `reason` beside `error` — one word, meant to be switched on rather than read: `contention` and `starting` clear on their own, `unavailable` means the computer is not running and only starting it helps, `running` means the computer is running and only stopping it helps (a resize), `unsupported` means waiting will not change the answer — this computer cannot do it at all, or it needs another step first, which the message names (a stop, or removing its secret bindings, for example) — `exists` means a create-only upload found its path taken, `name_taken` means a secret of that name is already in that scope, `stale_revision` means a secret changed since the `revision_id` you sent was read (or a computer’s bound list since the `version` you sent), and `stale_capture` means the screenshot capture you named is no longer held: a newer one replaced it, or its host’s daemon restarted or the computer moved. `starting` covers the two minutes after a start or a restart, and after a reboot from inside the guest on a computer last cold-started recently enough to report one (a stop and a start gives an older one that); a guest agent that is still silent after that is a `502`. Match on that and never on the sentence, which is prose and is rewritten. **Absent means no classification was given** — treat it, and any word you do not recognise, as no answer, because not every refusal here has one yet. It is what the guest routes answer: the clipboard on a stopped computer used to be a 409 indistinguishable from a clipboard whose selection was claimed for an instant, and a blanket retry loop spun against the first until its deadline. Every 409 that clears on its own carries `contention` or `starting`: a host busy with another build or with no room for one, an operation already running on the same computer or snapshot (a capture, a copy, a delete, a restore or clone reading it, another agent run), a lock another request holds, a move or a delivery settling. So a 409 with no word, or with any other word, is not one that waiting fixes: read the sentence for the step it names. The ones worth knowing by name, because each has a next step that is not "wait": A resize past what the computer’s host can run carries `move`, an object rather than a message: `{"required":true,"possible":true}` means another host in this region could run it and the computer has to be moved there first — `POST /computers/{id}/move` with the same sizing fields is how you agree to that, and it is a separate call because relocating a computer is not something a resize should do to you quietly. `possible:false` means nowhere in the region can, and the size is the thing to change. The move itself then refuses for the things it re-decides at the moment it runs, and only one of those is worth waiting on: a computer that is running or suspended has to be stopped or resumed-and-stopped by you, a size that fits where it already is wants an ordinary resize instead, and a region with nowhere to put it wants a smaller size. `Another computer on this account is being moved right now` is the one that clears by itself, and it carries `reason: "contention"` — one move runs per account, and `GET /moves` says which. And the terminal socket refuses twice over: `reason: "unavailable"` with `resume_required: true` on a suspended computer, which clears when you start it and not before, and `reason: "unsupported"` on a running computer whose hardware carries no terminal channel — one last started before interactive terminals existed — which needs a stop and a start. Not a restart, which resets the same machine, and not a retry, which never comes good.
- `413`: What you sent, or asked for, is past a size limit. A JSON request body is capped at 1 MiB unless the route states its own limit: `POST /computers/{id}/exec` takes up to 4 MiB, and some routes take less; guest file transfers, template documents and the clipboard have limits of their own. The message names the limit that applied.
- `429`: You are asking faster than your plan allows. `Retry-After` says how many seconds to wait, and every metered response — anything past authentication and the re-check that your credential’s authority still holds — carries `RateLimit-Remaining`, so you do not have to be refused to find out. A `401`, a `403` from that re-check, an `OPTIONS` answer and an unexpected `500` carry none. The budget is spent in proportion to what a call costs rather than per request. What a call costs, in budget units, by kind (each operation’s exact figure is its `x-rate-cost` in the OpenAPI document): 1 to read one thing; 5 for a listing that spans the fleet, and 5 for a call into a running guest such as a screenshot or an exec; 10 for a power change and 10 to move file bytes; 25 for `GET /usage`, `GET /credits`, creating a public URL, and creating, rotating or testing a webhook; 50 to capture a snapshot; 100 to create, clone or restore a computer, and 100 to start an agent run, whose actions are then charged as they happen. The account-wide budget, as what an idle caller may spend at once and what refills each minute: No plan 1200 at once and 1200 a minute; Solo 4800 at once and 4800 a minute; Studio 12000 at once and 12000 a minute; Swarm 21600 at once and 21600 a minute. A single API key gets half of either. A `401` for a missing or unusable credential costs nothing: it is refused before anything is metered. A few refusals at the door cost one unit: a `403` because the role is too low or the route refuses an API key confined to a workspace, a `404` for a path that matches nothing, a `405`, and an `Idempotency-Key` answered from its stored result or still in progress. Everything else is charged in full when it is admitted, before it is carried out, so a refusal after that has spent the whole cost: a `400`, `402` or `409` from the route, a `403` its handler sends (on most routes, a suspended account included), and a model provider’s `401` on an agent run. The budget belongs to the account and is shared across everything on it, and any single API key may spend at most half of it. `RateLimit-Limit` is whichever of those two is binding on the request that carried it — usually the per-key half, and the account-wide figure when other keys have already spent more of it than this one has. All three `RateLimit-*` headers describe the same one, so `limit` minus `remaining` is what has been spent against it. A few `429`s are not about this budget, say so in their message, and can carry no `Retry-After`: a model provider’s rate limit relayed on an agent run. The cap on forks of one snapshot waiting for their secrets sends its own bounded expiry-based `Retry-After` with `reason: "contention"` (see `POST /snapshots/{id}/clone`).
- `500`: The application could not finish this: an unexpected exception, a build that broke, or a storage fault. Application refusals carry the request correlation ID; unexpected internal details are not returned.
- `503`: Something this depends on — a hypervisor, a store, or a host’s capacity — could not answer or take this right now. A read can be retried shortly. A change answered `503` may or may not have happened — a failure after the request was sent is answered the same way, with or without a warning in the message — so read the current state before retrying anything that is not safe to repeat, such as a create or a command. On the collection reads, `allow_partial=1` accepts a knowingly short answer instead. Also `reason: "draining"`, with a `Retry-After` header: the platform is about to restart for an update and is not starting new agent runs for a few minutes. Runs already going are not affected. Nothing was started, held, charged or recorded for this request, so send the same one again after `Retry-After` seconds. Answered before anything streams, as an `Error` body.

---

[API](https://skmtc.dev/mandala/apis/mandala-computer-api.md) · [All operations](https://skmtc.dev/mandala/apis/mandala-computer-api/llms.txt) · [OpenAPI document](https://skmtc.dev/mandala/apis/mandala-computer-api/revisions/2afbb87fa703?raw)