feat(providers): declare imageToText serviceKind on major vision providers (#10275)

* feat(providers): declare imageToText serviceKind on major vision providers

The /dashboard/media-providers/imageToText category was empty by design:
imageToText has no backing registry and no catalog entry declared it.
Declare serviceKinds: ["llm", "imageToText"] on the 7 major vision-capable
providers (openai, anthropic, gemini, openrouter, mistral, xai, groq) so the
category lists them and the Modality Bridge ?tab=vision shortcut becomes
reachable from their provider detail pages.

"llm" is declared alongside because ProviderCard treats an EMPTY serviceKinds
as "regular LLM provider" — declaring only imageToText would silently hide the
inline Test button and the playground default (guarded by the new test).

Refs #9760

* chore(quality): rebaseline gateways.ts file-size for imageToText serviceKinds

The two serviceKinds declarations (openrouter here, chutes in #10291) add
exactly two data lines to the provider catalog. Frozen 1250 -> 1252 with the
justification recorded in the baseline key.

* chore(quality): rebaseline deadExports for the OCR/image-to-text series

---------

Co-authored-by: Xiangzhe <bakryun0718@proton.me>

config/quality/file-size-baseline.json

@@ -442,7 +442,7 @@
     "src/app/(dashboard)/dashboard/providers/[id]/components/modals/AddApiKeyModal.tsx": 1062,
     "src/app/(dashboard)/dashboard/providers/[id]/hooks/useProviderConnections.ts": 1051,
     "src/shared/components/ModelSelectModal.tsx": 1138,
-    "src/shared/constants/providers/apikey/gateways.ts": 1250,
+    "src/shared/constants/providers/apikey/gateways.ts": 1255,
     "open-sse/vendor/codex-chatgpt-web/bridge.ts": 1387,
     "_rebaseline_2026_08_11_v3850_merge_storm_provider_registry": "DRIFT do merge-storm 2026-08-11 (99 PRs mergeados no release/v3.8.50). AddApiKeyModal.tsx (PR #8949 ChatGPT Web provider) e useProviderConnections.ts/ModelSelectModal.tsx (PRs #9011 combo test-all, #9499 image combos) = UI nova legitima acima do cap; gateways.ts = god-file de catalogo de providers que cresceu com PRs #9009/#9421/#9468/#9594 (qualquer split arriscaria corromper o merge de novo — o proprio PR #9421 quebrou o arquivo); bridge.ts (PR #8949) = ponte Chromium vendored; proxyFetch.ts 1207->1220 = drift herdado de merges. Owner autorizou rebaseline com anotacao (2026-08-11).",
     "src/lib/modelCapabilities.ts": 1006,
@@ -609,5 +609,6 @@
   "_rebaseline_2026_08_06_9006_reconcile_onto_tip_2": "PR #9006 (fix/vertex-claude-catalog-dispatch) second rebase-onto-tip reconciliation. Same two files as _rebaseline_2026_08_04_9006_reconcile_onto_tip below, further inherited drift, still not this PR's own growth (verified via git diff against the fresh upstream/release/v3.8.50 merge-base — this PR's own commits still touch neither file): open-sse/executors/base.ts 1623->1640 (+17) and src/sse/handlers/chat.ts 1847->1881 (+34), both measured post-merge via split(\"\\n\").length. More already-merged release/v3.8.50 PRs grew these files without updating their baseline entries (same root cause as every other entry in this chain: fast-gates PR->release does not run check:file-size). No offending branch left to fix.",
   "_rebaseline_2026_08_12_v3850_basereds_round3": "Base-reds round 3 (#9985, 2026-08-12): ModelSelectModal.tsx 1135->1138 = base drift from the #10198 SWR/build repair (flagged as non-blocking drift by Release-Green run 31634993212, rebaselined here so the PR queue's Fast Quality Gates stop failing on inherited drift); gateways.ts 1215->1250 = base drift from the 08-12 merges (#10131 regolo/naga-ac repair, #9210 void-ai+helixmind) plus this PR restoring the chatanywhere metadata entry that round 2 dropped along with its duplicate (wave3 audited entry, +16 lines; same god-file no-split rationale as the 2026-08-11 annotation). Owner-authorized sweep (/sweep-reds).",
   "_rebaseline_2026_08_12_proxyfetch_redaction": "Base-reds round 3 (#9985): proxyFetch.ts 1220->1239 (+19) = redactProxyDetailsInMessage() helper closing the credential leak #10032 reintroduced (raw proxy URL with user:password appended to the propagated error, Hard Rule #12); irreducible security fix at the existing error-surface chokepoint. Covered by tests/unit/tls-proxy-context.test.ts (strengthened leak guards).",
-  "_rebaseline_2026_08_12_modelcapabilities_snapshot_routing": "Base-reds round 3 (#9985): modelCapabilities.ts crossed the new-file cap at 1006 (+~10) when the context/max-input-token override lookups were routed through the #9199 bulk snapshot (fixing 323 per-model SQLite reads per catalog prepare — auto-combo-context-advertising guard); cohesive change at the existing resolution chokepoints, not extractable. Covered by tests/unit/auto-combo-context-advertising.test.ts + model-capability-resolution-snapshot-9199.test.ts."
+  "_rebaseline_2026_08_12_modelcapabilities_snapshot_routing": "Base-reds round 3 (#9985): modelCapabilities.ts crossed the new-file cap at 1006 (+~10) when the context/max-input-token override lookups were routed through the #9199 bulk snapshot (fixing 323 per-model SQLite reads per catalog prepare — auto-combo-context-advertising guard); cohesive change at the existing resolution chokepoints, not extractable. Covered by tests/unit/auto-combo-context-advertising.test.ts + model-capability-resolution-snapshot-9199.test.ts.",
+  "_rebaseline_2026_08_14_imagetotext_servicekinds": "Image-to-Text category (#10275/#10291): gateways.ts grew 1250→1255 by data lines only — the serviceKinds: [\"llm\", \"imageToText\"] declarations on the openrouter and chutes catalog entries, plus the 3-line comment recording why chutes needs no static dots.ocr entry (passthroughModels discovery). No new logic or branching; the file is a provider catalog of declarative metadata. Splitting a catalog for five lines would be worse than the growth (semantic-families rule)."
 }

src/shared/constants/providers/apikey/frontier-labs.ts

@@ -11,6 +11,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     color: "#10A37F",
     textIcon: "OA",
     website: "https://platform.openai.com",
+    serviceKinds: ["llm", "imageToText"],
   },
   reka: {
     id: "reka",
@@ -52,6 +53,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     color: "#D97757",
     textIcon: "AN",
     website: "https://platform.claude.com",
+    serviceKinds: ["llm", "imageToText"],
   },
   gemini: {
     id: "gemini",
@@ -64,6 +66,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     hasFree: true,
     freeNote:
       "Free tier available through Google AI Studio; current per-model quotas and regional limits apply",
+    serviceKinds: ["llm", "imageToText"],
   },
   groq: {
     id: "groq",
@@ -75,6 +78,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     website: "https://groq.com",
     hasFree: true,
     freeNote: "Free tier: 30 RPM / 14.4K RPD — no credit card",
+    serviceKinds: ["llm", "imageToText"],
   },
   blackbox: {
     id: "blackbox",
@@ -96,6 +100,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     color: "#1DA1F2",
     textIcon: "XA",
     website: "https://x.ai",
+    serviceKinds: ["llm", "imageToText"],
   },
   mistral: {
     id: "mistral",
@@ -107,6 +112,7 @@ export const APIKEY_PROVIDERS_FRONTIER = {
     website: "https://mistral.ai",
     hasFree: true,
     freeNote: "Free Experiment tier: rate-limited access to all models, no credit card required",
+    serviceKinds: ["llm", "imageToText"],
   },
   perplexity: {
     id: "perplexity",

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

@@ -82,6 +82,7 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
     website: "https://openrouter.ai",
     hasFree: true,
     freeNote: "Free models at $0/token with :free suffix - 20 RPM / 200 RPD",
+    serviceKinds: ["llm", "imageToText"],
   },
   requesty: {
     id: "requesty",

tests/unit/imagetotext-service-kinds.test.ts

@@ -0,0 +1,42 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import { AI_PROVIDERS } from "../../src/shared/constants/providers.ts";
+import { resolveProviderServiceKinds } from "../../open-sse/config/mediaServiceKinds.ts";
+
+/**
+ * The Image-to-Text category (/dashboard/media-providers/imageToText) fills from
+ * providers whose resolved serviceKinds include "imageToText". It has no backing
+ * registry, so major vision-capable providers must declare it explicitly.
+ */
+const IMAGE_TO_TEXT_PROVIDERS = [
+  "openai",
+  "anthropic",
+  "gemini",
+  "openrouter",
+  "mistral",
+  "xai",
+  "groq",
+] as const;
+
+test("major vision providers declare the imageToText serviceKind", () => {
+  for (const id of IMAGE_TO_TEXT_PROVIDERS) {
+    const provider = AI_PROVIDERS[id] as { serviceKinds?: string[] } | undefined;
+    assert.ok(provider, `provider "${id}" missing from AI_PROVIDERS`);
+    const kinds = resolveProviderServiceKinds(id, provider.serviceKinds);
+    assert.ok(kinds.includes("imageToText"), `"${id}" must resolve the imageToText serviceKind`);
+  }
+});
+
+test("declaring imageToText keeps the llm kind (inline Test button + playground default)", () => {
+  // ProviderCard treats an EMPTY serviceKinds as "regular LLM provider"; once a
+  // provider declares any kind, "llm" must be declared too or the Test button
+  // and the playground default silently disappear.
+  for (const id of IMAGE_TO_TEXT_PROVIDERS) {
+    const provider = AI_PROVIDERS[id] as { serviceKinds?: string[] };
+    assert.ok(
+      (provider.serviceKinds ?? []).includes("llm"),
+      `"${id}" declares serviceKinds without "llm" — this hides the inline Test button`
+    );
+  }
+});