feat(providers): derive imageToText serviceKind from the OCR registry

This commit is contained in:
Xiangzhe
2026-08-13 17:50:39 -03:00
parent e911807066
commit 91de8b3f82
2 changed files with 24 additions and 4 deletions

View File

@@ -13,9 +13,11 @@
* 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.
*
* Kinds without a backing registry (imageToText, webSearch, webFetch, llm) are
* still declared explicitly via `serviceKinds` on the provider entry; callers
* union the two sources.
* `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";
@@ -58,7 +60,8 @@ export function getRegistryMediaKinds(providerId: string): RegistryMediaKind[] {
/**
* Full set of serviceKinds for a provider: the explicitly declared ones (llm,
* web*, imageToText) unioned with the media kinds derived from the registries.
* 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,
@@ -66,5 +69,8 @@ export function resolveProviderServiceKinds(
): 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];
}

View File

@@ -0,0 +1,14 @@
import { test } from "node:test";
import assert from "node:assert/strict";
import { resolveProviderServiceKinds } from "../../open-sse/config/mediaServiceKinds.ts";
test("OCR-registry providers derive imageToText without manual declaration", () => {
assert.ok(resolveProviderServiceKinds("mistral", undefined).includes("imageToText"));
assert.ok(
resolveProviderServiceKinds("azure-document-intelligence", undefined).includes("imageToText")
);
});
test("non-OCR providers do not gain imageToText implicitly", () => {
assert.ok(!resolveProviderServiceKinds("groq", undefined).includes("imageToText"));
});