Retrieves a specific agent revision.
Returns the immutable snapshot of an agent's configuration at the given revision number: its `definition` (provider, prompts, tools and capability configs), the input parameter schema, the integration slots and contacts it declares, and its authorship. The body reads back in the same vocabulary the authoring endpoints accept, so a revision fetched here can be edited and posted to `PUT .../draft` or `POST .../revisions` unchanged. The revision identifier may be a numeric version, or pass `draft` to inspect the in-progress unsaved revision being edited. Deployed revisions are read-only; use the create-agent-revisions endpoints to fork a new draft and deploy it with `POST .../revisions/{revision}:deploy`.
Authorization
Bearer JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.
In: header
Path Parameters
The unique identifier of the agent.
The revision identifier.
The tenant identifier
Response Body
curl -X GET "https://api.fruxon.com/v1/tenants/string/agents/string/revisions/string"{
"agentId": "string",
"agentRevision": 0,
"comment": "string",
"definition": {
"description": "string",
"provider": {
"providerId": "string",
"model": "string",
"parameters": {},
"fallbacks": [],
"builtInTools": [],
"tenantConfigId": "00000000-0000-0000-0000-000000000000"
},
"systemPrompt": {
"template": "string"
},
"userPrompt": {
"template": "string"
},
"tools": [
{
"toolKey": null,
"integrationConfigId": null,
"integrationConfig": null,
"humanApproval": null,
"repeatGuard": null,
"durableEffect": null,
"pinnedParameters": null
}
],
"skills": [
{
"skillId": "string",
"tools": []
}
],
"sessionConfig": {
"enabled": false,
"maxTurns": 0,
"summarizeOverflow": false,
"windowReserve": 0,
"maxToolResponseTokens": 0,
"enableSearchTool": false,
"enableTicketManagement": false,
"enableSupportCases": false,
"supportCaseProfileEnabled": false,
"captureSystemPromptInTrace": false,
"deferVolatilePromptToHistoryTail": false
},
"naturalSilence": {
"enabled": false
},
"memoryConfig": {
"enabled": false,
"maxAutoInject": 0,
"sharedOnly": false
},
"assetConfig": {
"enabled": false,
"assetIds": [
"string"
]
},
"maxToolLoops": 0,
"allowedSecretIds": [
"00000000-0000-0000-0000-000000000000"
],
"judge": {
"enabled": false,
"rubric": {
"metrics": [],
"customInstructions": null,
"referenceAnswer": null,
"includeToolTranscript": false
},
"providerOverride": {
"providerId": "string",
"model": "string",
"parameters": {},
"fallbacks": [],
"builtInTools": [],
"tenantConfigId": null
},
"failureMode": "LOG_ONLY",
"passThreshold": 0,
"failureMessage": "string",
"samples": 0,
"maxRetries": 0,
"sampleRate": 0
},
"delegation": {
"enabled": false,
"allowNestedSpawn": false,
"deadlineMinutes": 0
},
"network": {
"enabled": false,
"conductorAgentId": "string"
},
"escalation": {
"enabled": false
},
"asyncExecution": {
"mode": "AGENT_DECIDES"
},
"relevanceCheck": {
"modelOverride": "string",
"maxOutputTokens": 0,
"contextTurns": 0,
"systemPromptOverride": "string"
},
"outputContract": {
"format": "TEXT",
"schema": "string"
}
},
"parametersMetadata": [
{
"name": "string",
"index": 0,
"type": "STRING",
"typeName": "STRING",
"integerRange": {
"min": 0,
"max": 0
},
"floatRange": {
"min": 0,
"max": 0
},
"options": [],
"asset": {
"providers": null,
"contentTypes": null,
"vectorized": false
},
"displayName": "string",
"description": "string",
"required": false,
"secret": false,
"secretResolvable": false,
"defaultValue": "string",
"jsonSchema": null,
"minLength": 0,
"maxLength": 0,
"pattern": "string",
"validator": "string",
"uiHint": "CODE",
"rules": []
}
],
"outputContract": {
"format": "TEXT",
"schema": "string"
},
"integrationSlots": [
{
"id": "00000000-0000-0000-0000-000000000000",
"integrationId": "string",
"displayName": "string",
"tenantConfigId": "00000000-0000-0000-0000-000000000000"
}
],
"integrationBindings": {},
"assets": [
{
"id": "string",
"displayName": "string",
"description": "string",
"sourceType": "string",
"vectorized": true,
"ragAssetId": "00000000-0000-0000-0000-000000000000",
"assetLink": "string"
}
],
"slots": [
{
"name": "string",
"displayName": "string",
"description": "string",
"requiredKind": "ANY"
}
],
"createdBy": "string",
"actor": "string",
"createdAt": 0
}{
"type": "string",
"title": "string",
"status": 0,
"detail": "string",
"instance": "string",
"property1": null,
"property2": null
}Gets agent revision cost split by environment.
At least one `environment` query parameter is required; repeat the param to compare multiple environments side-by-side (`?environment=production&environment=staging`). Unknown slugs (not present in the tenant's environments table) are rejected with 400 — silent-empty would mask FE typos that drift from real config.
Gets aggregated per-model token usage for a specific agent revision or all revisions.
Returns one row per `(provider, model)` pair seen in this revision's executions, summing input tokens, output tokens, and call counts so callers can rank model spend and detect drift after a revision change. Pass `*` as the revision to aggregate across every revision the agent has ever run, which is useful for top-of-funnel dashboards; pass a specific revision number to attribute usage to one deployed version. Pair with the revision cost endpoints for dollar-cost breakdowns rather than raw tokens.