AgentKit Studio
Guides

Deploy to the Cloud

Turn a successful build into a managed cloud instance: pick a spec, run the check, confirm creation, then read deployment states and unconfirmed outcomes.

A cloud deployment turns one successful build's frozen version into a 7×24 managed runtime instance. The instance keeps its own id, spec, and persistent disk, so conversation history survives a rebuild.

Prerequisites

  • At least one locally created agent with a SUCCEEDED build.
  • Subaccount AK/SK configured. A primary account cannot create cloud resources.
  • A connected AgentEngine Server; without one the deploy section reports "cloud publishing unavailable" and only bundle export works.

Steps

Open Build and deploy

Go to Operations → Build and deploy. The page numbers three steps:

StepNumberPurpose
Build1Freeze the current prompt, models, and resource bindings
Deploy2Create or update the cloud instance
Cloud instances3Deployment records and operations

Step 2 stays dimmed with "You can deploy after a successful build" until a build succeeds.

Select the agent and build

  1. Pick a target in the top-right Target agent selector.
  2. Choose a SUCCEEDED version in the Frozen version dropdown; failed versions are not selectable.

Only the latest built revision deploys directly

When the current revision differs from the latest successful build, step 1 reports "Configuration updated to r<n>". Rebuild first, or you will deploy the previous configuration.

Choose the deployment target

The Deploy to dropdown has two options:

OptionBehavior
Update the current instance of "<instance>"Reuses the existing instance id, spec, and disk, switching only the frozen version
Create a new cloud instanceCreates a new instance with the spec chosen below, and a new instance id and bill

When updating an existing instance, Runtime image becomes a switch: "Use the currently recommended runtime image". Turn it off to target a different image version.

Choose the instance spec

When creating an instance, the CPU-to-memory ratio must be 1:2, 1:4, or 1:8:

Group (ratio)CoresExample
General · 1:21 / 2 / 4 / 8 / 16Default 2 cores → 4 GB
More memory · 1:41 / 2 / 4 / 8 / 162 cores → 8 GB
More memory · 1:81 / 2 / 4 / 8 / 162 cores → 16 GB

When updating an existing instance the spec is read-only and shows the current value.

Confirm conversation storage

Storage is a fixed 20 GiB persistent disk mounted at /home/node in the runtime container. Agent state, conversation history, and the workspace all live under that directory and survive an instance rebuild.

Billed per day; back up before deleting

The disk is billed per day. Back up anything you need before deleting an instance — the directory does not come back. A temporary-storage option no longer exists: it only changed the daily bill while an instance rebuild silently dropped conversation history.

Run the deployment check

Choose Check deployment (or Check update for an existing instance). The check is read-only, creates no cloud resources, and returns a deployment check result panel:

RowContent
Deployment locationEnvironment (pre-online renders as "pre-production") · region
Instance specCPU cores / memory GB · 1 instance
Conversation storage20 GiB · /home/node
RuntimeRuntime type · current image version
Target runtime imageImage version · digest — the deployment identity to verify before an upgrade
Bound resourcesN models · N MCPs · N skills · N cloud resources
OperatorSubaccount user name, or "Primary account"

The check verifies three things: the frozen version, resource credentials, and deployment location and quota. If any fails, the check fails and you never reach the confirm button.

Do not skip the warnings below it; they concern billing and irreversible operations, for example "One replica is created at the selected spec; actual billing follows the platform".

Confirm creation

Choose Confirm creating the cloud instance. The page reports "Deployment submitted; progress updates automatically" and the record appears under step 3.

Never create again when the submit outcome is unconfirmed

If the page reports "Submit outcome unconfirmed; keep this page open and reconcile the deployment record", do not refresh and retry creation. Use Reconcile creation result on that record in step 3 to reconcile with the same request identity; retrying really does create a second instance.

The 10 deployment states you care about

The list refreshes every 5 seconds and pauses polling while the page is in the background. There are 19 states in total; day to day you only need these 10:

StateLabelMeaningWhat to do
PREPAREDPending submitThe record exists but is not submittedNothing
UPLOADINGUploading runtime bundleThe frozen bundle is uploadingWait
CREATINGCreatingThe platform is creating the cloud agentWait
PROVISIONINGPreparing instanceThe instance exists and is being preparedWait
CONFIGURINGConfiguring access tokenThe access token is being writtenWait
TOKEN_PENDINGWaiting for configurationThe token is written and pendingIf it stays here for minutes, use Repair access configuration
STARTINGStartingThe endpoint is up and version probing is runningWait
READYReadyThe instance is usableChoose Start conversation
ACTION_REQUIREDAction requiredA human must step in; the instance may still be runningRead the failure code under Details first
FAILEDFailedCreation failedRead code and message under Details

Look up the rest as needed: UPLOADED (uploaded, awaiting creation), AVAILABLE_UPDATING (endpoint up, platform updating — chat is fine, do not upgrade now), DELETING (deleting), DELETED (deleted; only visible with "Show deleted" enabled).

Handling *_UNKNOWN states

The four _UNKNOWN states mean the platform did not confirm the outcome of the last write. They never advance on their own and need a human to reconcile:

StateLabelAction
UPLOAD_UNKNOWNUpload outcome unconfirmedChoose Reconcile creation result; creation continues once the bundle is confirmed
CREATE_UNKNOWNCreation outcome unconfirmedChoose Reconcile creation result. Never create again — reconciliation claims the instance that already exists
UPDATE_UNKNOWNUpdate outcome unconfirmedChoose Refresh status to trigger version probing; a passing probe moves it to READY
DELETE_UNKNOWNDelete outcome unconfirmedChoose Refresh status; it settles on DELETED once the cloud record is gone

These four, together with ACTION_REQUIRED, FAILED, and TOKEN_PENDING, count as "needs attention". When another agent has such records, the list header reports "N deployments of other agents need attention"; choose View all to widen the scope.

What success looks like

  • The record shows READY with a green tone.
  • Start conversation appears on the row (only for READY and AVAILABLE_UPDATING).
  • Expanding Details shows the cloud agent, runtime, runtime image (with digest), build, and conversation storage.
  • Logs returns runtime output, or "No logs yet" when the instance has produced none.

Common errors

CodeCauseFix
CLOUD_SUBACCOUNT_REQUIREDThe current identity is not a verified subaccount, or it differs from the deployment recordUpdate cloud credentials in settings; the primary account is never used as a substitute
DEPLOYMENT_AGENT_UNSUPPORTEDThe target is not a locally created agent buildDeploy locally created agents only
DEPLOYMENT_RESOURCE_INVALIDThe CPU-to-memory ratio is not 1:2, 1:4, or 1:8Pick from the spec dropdown
DEPLOYMENT_TYPE_INVALIDInvalid deployment typeStart the deployment from the UI instead of hand-crafting requests
KS3_BUCKET_REQUIREDThe account default bucket cannot be determinedVerify cloud identity, or set an explicit KS3 bucket in advanced settings
MCP_CREDENTIAL_MISSINGA bound MCP lacks valid credentialsFill in the MCP credentials and re-run the check
DEPLOYMENT_ENV_CONFLICTMultiple MCPs produced conflicting credential env varsRemove the duplicate MCP binding
MANAGED_RUNTIME_MODEL_INVALIDThe bundle has no default modelSet a model on the agent and rebuild
DEPLOYMENT_ACCOUNT_CHANGEDCloud credentials or environment differ from the recordSwitch back to the original configuration before managing it
DEPLOYMENT_CREATE_UNCONFIRMEDCreation is not confirmed yetReconcile creation result first; never create again
DEPLOYMENT_PROVENANCE_MISMATCHThe cloud agent does not match the frozen deployment recordStop managing it and verify the instance provenance
DEPLOYMENT_RECORD_CORRUPTThe local deployment record is corruptKeep the file and reconcile against the cloud; never resubmit creation

On this page