feat(providers): chutes imageToText (dots.ocr seed)

open-sse/config/mediaServiceKinds.ts

@@ -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];
 }

src/shared/constants/providers/apikey/gateways.ts

@@ -932,6 +932,10 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
       "No free tier as of 2026 — Chutes moved to pay-as-you-go (free Early Access ended 2026-03).",
     authHint: "Bearer API key for the Chutes OpenAI-compatible gateway.",
     passthroughModels: true,
+    // dots.ocr (rednote-hilab/dots.ocr) is served via Chutes discovery — no static
+    // model entry needed (passthroughModels). Declare imageToText alongside llm
+    // (declaring serviceKinds means "llm" must be explicit too, see #10275).
+    serviceKinds: ["llm", "imageToText"],
   },
   // Factory AI ("Factory Droids") subscription gateway — the same backend the
   // local `droid` CLI shells into, exposed here as an OpenAI-compatible HTTP

tests/unit/imagetotext-derivation.test.ts

@@ -0,0 +1,21 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { resolveProviderServiceKinds } from "../../open-sse/config/mediaServiceKinds.ts";
+import { AI_PROVIDERS } from "../../src/shared/constants/providers.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"));
+});
+
+test("chutes declares llm + imageToText (dots.ocr seed, served via passthrough discovery)", () => {
+  const kinds = resolveProviderServiceKinds("chutes", AI_PROVIDERS.chutes.serviceKinds);
+  assert.ok(kinds.includes("imageToText"));
+  assert.ok(kinds.includes("llm"));
+});