Files
esh-pfi-infrastructure/docs/asset-engine/services.schema.json
T
vh d3faeb0314 catalog-contract: add response-decomposition fields (audio_field, timestamps_field, audio_format_field)
asset_engine consumer needed to render kokoro-captioned, whose wire
shape is a JSON envelope carrying base64-encoded audio plus a
structured timestamps array. Modeling it as response.type=json
would force either a per-service-id renderer (forbidden by
brief §1.7) or extending the closed response-type vocabulary
(forbidden by brief §2.2 without a coordinated bump).

Resolution (per althing thread 01KRCF4W66X3): keep response.type
closed at the existing six values and decompose at the response
*field* level instead — the same flexibility seam already used by
mime / mime_from_field / output_field. Adds three optional keys:

  - audio_field: JSON key holding base64-encoded audio bytes
  - audio_format_field: JSON key holding the decoded audio MIME
  - timestamps_field: JSON key holding a structured timestamps array
    (independent of type, declared by any service emitting time-
    aligned markers)

Validators in CatalogResponse enforce sane combinations:
  - audio_field requires response.type=audio
  - audio_field forbids mime_from_field
  - audio_format_field requires audio_field

This is additive and backward-compatible — no catalog_version bump,
existing services parse unchanged. CATALOG-CONTRACT.md updated with
the new rows in the response-field table and a versioning-policy
row codifying that adding optional keys to response: doesn't bump.

kokoro-captioned re-shaped to use the new schema:
  response:
    type: audio
    audio_field: audio
    audio_format_field: audio_format
    timestamps_field: timestamps
And marked status: experimental until the asset_engine consumer's
audio-with-timestamps renderer ships.

JSON Schema regenerated to reflect the new Pydantic shape.

Pydantic-model side of this change lives in the asset_engine repo
at src/asset_engine/catalog.py — committed there separately.
2026-05-11 14:55:15 -07:00

651 lines
15 KiB
JSON

{
"$defs": {
"CatalogAuditEntry": {
"additionalProperties": false,
"properties": {
"service": {
"title": "Service",
"type": "string"
},
"seedable": {
"title": "Seedable",
"type": "boolean"
},
"model_deterministic": {
"title": "Model Deterministic",
"type": "boolean"
},
"image_tag_mutable": {
"title": "Image Tag Mutable",
"type": "boolean"
},
"notes": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Notes"
}
},
"required": [
"service",
"seedable",
"model_deterministic",
"image_tag_mutable"
],
"title": "CatalogAuditEntry",
"type": "object"
},
"CatalogField": {
"additionalProperties": false,
"description": "One request parameter, rendered as one form control.",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"type": {
"enum": [
"text",
"textarea",
"number",
"slider",
"select",
"bool",
"file",
"json"
],
"title": "Type",
"type": "string"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Label"
},
"required": {
"default": true,
"title": "Required",
"type": "boolean"
},
"optional": {
"default": false,
"title": "Optional",
"type": "boolean"
},
"default": {
"default": null,
"title": "Default"
},
"min": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Min"
},
"max": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Max"
},
"step": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Step"
},
"options": {
"anyOf": [
{
"items": {
"anyOf": [
{
"type": "string"
},
{
"$ref": "#/$defs/FieldOption"
}
]
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Options"
},
"source_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Url"
},
"source_jsonpath": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Jsonpath"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Description"
},
"max_length": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Max Length"
},
"accepted_types": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Accepted Types"
}
},
"required": [
"name",
"type"
],
"title": "CatalogField",
"type": "object"
},
"CatalogLatency": {
"additionalProperties": false,
"properties": {
"cold_start_s": {
"anyOf": [
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Cold Start S"
},
"warm_per_unit": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Warm Per Unit"
}
},
"title": "CatalogLatency",
"type": "object"
},
"CatalogModel": {
"additionalProperties": false,
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"revision": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Revision"
},
"image": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Image"
}
},
"required": [
"id"
],
"title": "CatalogModel",
"type": "object"
},
"CatalogReproducibility": {
"additionalProperties": false,
"properties": {
"seedable": {
"title": "Seedable",
"type": "boolean"
},
"deterministic": {
"title": "Deterministic",
"type": "boolean"
},
"notes": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Notes"
}
},
"required": [
"seedable",
"deterministic"
],
"title": "CatalogReproducibility",
"type": "object"
},
"CatalogResponse": {
"additionalProperties": false,
"description": "How to interpret the inference response.\n\nThe `type` is the *renderer dispatch* \u2014 what kind of asset the user\nultimately sees (audio player, text block, etc). The other fields\ndescribe how to *extract* that asset from the wire shape:\n\n - Raw-bytes wire (e.g. /v1/audio/speech returns raw audio):\n type: audio\n mime: audio/wav (or mime_from_field for dynamic)\n\n - JSON-envelope wire with base64-encoded asset (e.g. captioned\n speech returns {audio: <b64>, audio_format: ..., timestamps: ...}):\n type: audio\n audio_field: audio # JSON key with the base64 bytes\n audio_format_field: audio_format # JSON key with the MIME\n timestamps_field: timestamps # optional structured aside\n\n - JSON-envelope wire with text payload (e.g. ASR transcript):\n type: text\n output_field: text # JSON key with the text body\n timestamps_field: segments # optional, for ASR-with-timestamps\n\nRules:\n - When audio_field is set, the renderer expects a JSON envelope and\n will base64-decode that key. The wire MIME is application/json\n regardless of `mime`; `mime_from_field` is incompatible.\n - timestamps_field is independent of type \u2014 any service that\n emits structured timestamps alongside its primary output can\n declare it; the renderer extends accordingly.",
"properties": {
"type": {
"enum": [
"audio",
"image",
"video",
"text",
"json",
"file"
],
"title": "Type",
"type": "string"
},
"mime": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Mime"
},
"mime_from_field": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Mime From Field"
},
"output_field": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Output Field"
},
"audio_field": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Audio Field"
},
"audio_format_field": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Audio Format Field"
},
"timestamps_field": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Timestamps Field"
}
},
"required": [
"type"
],
"title": "CatalogResponse",
"type": "object"
},
"CatalogService": {
"additionalProperties": false,
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Description"
},
"category": {
"enum": [
"tts",
"asr",
"sfx",
"music",
"image",
"multimodal"
],
"title": "Category",
"type": "string"
},
"version": {
"title": "Version",
"type": "integer"
},
"status": {
"default": "ready",
"enum": [
"ready",
"catalog-deferred",
"experimental"
],
"title": "Status",
"type": "string"
},
"host": {
"title": "Host",
"type": "string"
},
"endpoint": {
"title": "Endpoint",
"type": "string"
},
"method": {
"default": "POST",
"title": "Method",
"type": "string"
},
"content_type": {
"default": "application/json",
"title": "Content Type",
"type": "string"
},
"model": {
"$ref": "#/$defs/CatalogModel"
},
"fields": {
"items": {
"$ref": "#/$defs/CatalogField"
},
"title": "Fields",
"type": "array"
},
"response": {
"$ref": "#/$defs/CatalogResponse"
},
"reproducibility": {
"$ref": "#/$defs/CatalogReproducibility"
},
"estimated_latency": {
"anyOf": [
{
"$ref": "#/$defs/CatalogLatency"
},
{
"type": "null"
}
],
"default": null
},
"license": {
"title": "License",
"type": "string"
},
"license_warning": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "License Warning"
},
"notes": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Notes"
}
},
"required": [
"id",
"name",
"category",
"version",
"host",
"endpoint",
"model",
"response",
"reproducibility",
"license"
],
"title": "CatalogService",
"type": "object"
},
"FieldOption": {
"additionalProperties": false,
"description": "A select option. May be just the value (when label = value) or {value, label}.",
"properties": {
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
},
{
"type": "number"
},
{
"type": "boolean"
}
],
"title": "Value"
},
"label": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Label"
}
},
"required": [
"value"
],
"title": "FieldOption",
"type": "object"
}
},
"additionalProperties": false,
"description": "Schema for the canonical inference-services catalog. The Python Pydantic model in asset_engine/catalog.py is the source of truth; this JSON Schema is a derived view for non-Python consumers.",
"properties": {
"catalog_version": {
"default": 1,
"title": "Catalog Version",
"type": "integer"
},
"generated_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Generated At"
},
"services": {
"items": {
"$ref": "#/$defs/CatalogService"
},
"title": "Services",
"type": "array"
},
"reproducibility_audit": {
"items": {
"$ref": "#/$defs/CatalogAuditEntry"
},
"title": "Reproducibility Audit",
"type": "array"
}
},
"required": [
"services"
],
"title": "Asset Engine \u2014 services.yaml catalog",
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://eshpfi.local/schemas/services.schema.json"
}