mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-26 09:02:11 +03:00
fa0b0effbe
* feat(ocr): transformation layer on ocrRegistry (Mistral shape canonical)
* feat(ocr): Azure Document Intelligence provider (prebuilt-read, analyze+poll)
* feat(ocr): generic dispatch with per-provider transformation and DI poll loop
* test(ocr): align sanitized-500 assert with HR#12 error sanitization
The test's own title ("returns a sanitized 500") describes the new
behavior mandated by HR#12 (never leak err.message in a response body).
The old regex asserted the pre-sanitization leak (`OCR request failed:
socket closed`) as expected output, which contradicted its own title
and the sanitization this task intentionally introduced in
open-sse/handlers/ocr.ts. Scoped to this single assertion only.
* fix(ocr): fail fast on non-ok poll responses instead of misleading 504
pollOcrOperation now checks pollRes.ok and returns a sanitized 502
immediately (logging the upstream status via console.error) instead of
looping until the 30-attempt cap and surfacing a misleading timeout for
what was actually an auth/upstream error during polling.
* feat(ocr): route/docs for multi-provider /v1/ocr
- Route: map the connection's providerSpecificData.baseUrl onto
credentials.baseUrl (resolveOcrCredentials) so azure-document-intelligence
connections resolve their endpoint the same way every other custom-endpoint
provider does (src/lib/providers/validation/*); previously handleOcr only
saw a baseUrl when a caller set it directly, so the DB-backed Azure
connection endpoint was never forwarded.
- v1OcrSchema.model is already a free-form string, no schema change needed.
- Docs: add the /v1/ocr provider table + example + Azure poll-flow note to
API_REFERENCE.md, and describe the provider/model prefix + async poll
behavior in openapi.yaml.
- Test: tests/unit/ocr-route-contract.test.ts covers getAllOcrModels/
parseOcrModel for both providers and resolveOcrCredentials's mapping.
* feat(providers): derive imageToText serviceKind from the OCR registry
* feat(providers): chutes imageToText (dots.ocr seed)
* chore(quality): rebaseline gateways.ts file-size for imageToText serviceKinds
Same rebaseline as #10275 (frozen 1250 -> 1252): this branch adds the chutes
serviceKinds declaration, the second of the two data lines.
* chore(quality): rebaseline deadExports for the OCR/image-to-text series
---------
Co-authored-by: Xiangzhe <bakryun0718@proton.me>
77 lines
3.3 KiB
TypeScript
77 lines
3.3 KiB
TypeScript
/**
|
|
* Media serviceKinds — derived from the backend registries.
|
|
*
|
|
* The dashboard's `/dashboard/media-providers/[kind]` pages list a provider
|
|
* under a media kind when the provider supports it. Historically this relied on
|
|
* a hand-maintained `serviceKinds` array on every provider in providers.ts,
|
|
* which had drifted badly: ~48 providers were wired into the audio/video/music/
|
|
* image/embedding registries (backend works) but declared no `serviceKinds`, so
|
|
* they never appeared in the UI.
|
|
*
|
|
* This module makes the registries the single source of truth: a provider that
|
|
* appears as a key in a media registry supports that kind, full stop. The UI
|
|
* derives membership from here instead of duplicating it by hand, so adding a
|
|
* provider to a registry automatically surfaces it — no second edit, no drift.
|
|
*
|
|
* `imageToText` is additionally derived from `OCR_PROVIDERS` (see
|
|
* `resolveProviderServiceKinds`): a provider registered in the OCR registry gets
|
|
* `imageToText` for free, no manual `serviceKinds` edit needed. Kinds without any
|
|
* backing registry (webSearch, webFetch, llm) are still declared explicitly via
|
|
* `serviceKinds` on the provider entry; callers union declared + derived sources.
|
|
*/
|
|
import { AUDIO_TRANSCRIPTION_PROVIDERS, AUDIO_SPEECH_PROVIDERS } from "./audioRegistry.ts";
|
|
import { VIDEO_PROVIDERS } from "./videoRegistry.ts";
|
|
import { MUSIC_PROVIDERS } from "./musicRegistry.ts";
|
|
import { IMAGE_PROVIDERS } from "./imageRegistry.ts";
|
|
import { EMBEDDING_PROVIDERS } from "./embeddingRegistry.ts";
|
|
import { OCR_PROVIDERS } from "./ocrRegistry.ts";
|
|
|
|
/** Media kinds whose provider membership is defined by a backend registry. */
|
|
export const MEDIA_KIND_REGISTRIES = {
|
|
stt: AUDIO_TRANSCRIPTION_PROVIDERS,
|
|
tts: AUDIO_SPEECH_PROVIDERS,
|
|
video: VIDEO_PROVIDERS,
|
|
music: MUSIC_PROVIDERS,
|
|
image: IMAGE_PROVIDERS,
|
|
embedding: EMBEDDING_PROVIDERS,
|
|
ocr: OCR_PROVIDERS,
|
|
} as const satisfies Record<string, Record<string, unknown>>;
|
|
|
|
export type RegistryMediaKind = keyof typeof MEDIA_KIND_REGISTRIES;
|
|
|
|
export const REGISTRY_MEDIA_KINDS: readonly RegistryMediaKind[] = Object.freeze(
|
|
Object.keys(MEDIA_KIND_REGISTRIES) as RegistryMediaKind[]
|
|
);
|
|
|
|
/**
|
|
* Media serviceKinds a provider supports, derived from the backend registries.
|
|
* Returns the kinds (e.g. `["tts","video","music"]`) for which `providerId`
|
|
* appears as a registry key. Empty array if the provider serves no media.
|
|
*/
|
|
export function getRegistryMediaKinds(providerId: string): RegistryMediaKind[] {
|
|
const kinds: RegistryMediaKind[] = [];
|
|
for (const kind of REGISTRY_MEDIA_KINDS) {
|
|
if (Object.prototype.hasOwnProperty.call(MEDIA_KIND_REGISTRIES[kind], providerId)) {
|
|
kinds.push(kind);
|
|
}
|
|
}
|
|
return kinds;
|
|
}
|
|
|
|
/**
|
|
* Full set of serviceKinds for a provider: the explicitly declared ones (llm,
|
|
* web*, imageToText) unioned with the media kinds derived from the registries,
|
|
* plus `imageToText` derived from the OCR registry when not already declared.
|
|
*/
|
|
export function resolveProviderServiceKinds(
|
|
providerId: string,
|
|
declared: readonly string[] | undefined
|
|
): string[] {
|
|
const set = new Set<string>(declared ?? []);
|
|
for (const kind of getRegistryMediaKinds(providerId)) set.add(kind);
|
|
if (Object.prototype.hasOwnProperty.call(OCR_PROVIDERS, providerId)) {
|
|
set.add("imageToText");
|
|
}
|
|
return [...set];
|
|
}
|