AiRunRequest ai.run-request@1
Generated at from
openvibe-contracts v0.33.0 and
openvibe-sdk v0.5.0.
- Version
- 1.0.0
- Owner
- ai
- Visibility
- first-party
- Status
- active
- Compatibility
- backward
- Decision
- ADR-015
- Schema
https://openvibe.network/contracts/ai/run-request.v1.json
Body of POST /api/v1/runs on OpenVibe.AI (capability ai.run.create; ADR-015). Runs the newest active version of a workflow (or the given active or deprecated version) on input that must match that workflow version's own input schema; per-workflow input and output schemas live in AI's registry (GET /api/v1/workflows/:key), not here. The token's ns claim limits which workflow namespaces may run (403 capability.namespace_denied). ?wait=ms waits for the result: 201 finished or served from cache, 202 still queued/running (poll GET /api/v1/runs/:id), 200 an idempotent replay. Errors are problem+json: 404 workflow.not_found, 409 workflow.inactive, 409 idempotency.conflict, 413 input.too_large, 422 input.invalid, 429 quota.exceeded or queue.full with Retry-After. The direct operations POST /api/v1/{chat,generate,summarize,classify,extract,enrich,embed} take the same fields (except workflow and version) with the input fields at the top level and run workflow ai.<op>. target (EntityRef): what the output is about, part of the cache scope and a run filter. attribution (EntityRef): what the spend is attributed to for quotas and usage. on_behalf_of (SubjectRef): the person or actor the caller acts for, part of the cache scope and per-actor quotas.
Fields
| Field | Type | Required | Description | Constraints |
|---|---|---|---|---|
workflow | string | yes | Workflow key, <namespace>.<name> (live.chat_reply, news.summarize_story, network.site_copy…). |
|
version | integer | Pin a workflow version (active or deprecated). Omitted: the newest active version. |
| |
input | object | Workflow input; validated against the workflow version's input_schema. Default {}. | ||
target | common.entity-ref | |||
attribution | common.entity-ref | |||
on_behalf_of | identity.subject-ref | |||
idempotency_key | string | Same (requester, key) returns the existing run; a different workflow or input under it is 409 idempotency.conflict. The Idempotency-Key header is used when this is absent. |
| |
options | object |
| ||
options.cache | boolean | false skips the scoped cache lookup and store. |
| |
options.debug | boolean | Keep raw prompts and responses in the request log, only when AI runs with raw debug logging on. |
|
Examples
From the contract's own test fixtures: valid ones validate, rejected ones must fail.
Valid: minimal
{
"workflow": "network.site_copy",
"input": {
"sites": []
}
}Valid: news-summary
{
"workflow": "news.summarize_story",
"input": {
"topic": "Transit strike",
"sources": [
{
"source_type": "news.item",
"source_id": "itm_42",
"url": "https://example.com/a",
"title": "Strike begins"
}
]
},
"target": {
"service": "news",
"type": "story",
"id": "sty_01JAB2C3D4E5F6G7H8J9K0MNPQ"
},
"idempotency_key": "news:story:sty_01JAB2C3:v3",
"options": {
"cache": false
}
}Rejected: local-user-id
{
"workflow": "live.chat_reply",
"on_behalf_of": {
"type": "user",
"id": "42"
}
}Rejected: no-workflow
{
"input": {
"text": "hi"
}
}Rejected: unnamespaced-workflow
{
"workflow": "summarize",
"input": {}
}Validate
const contracts = require('openvibe-contracts');
contracts.validate('ai.run-request@1', value); // { valid, errors: [{ path, message }] }