refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

- Bug B1-B7: media UI m.kind||m.type, serviceKinds, gemini mediaPriority, schema kind, models/info lookup by kind
- Dead code D1-D6: safeParseJSON, drop PROVIDER_ENDPOINTS, orphan fetcher, GITHUB_CONFIG derive, getProviderConfig internal, legacy kiro file
- Translator concerns: toOpenAIUsage, toOpenAIFinish (gemini/kiro/ollama + fix kiro tool finish), thinking effort maps
- Reorg helpers/ → concerns/ (logic) + formats/ (per-format) + schema/ (pure enums: roles/blocks/finishReasons/defaults)
- Wire ~280 hardcoded role/block/finish/default literals to schema enums across 20+ files
- collapseTextParts + extractTextContent dedup
- Normalize translator fn names to openaiToXRequest / xToOpenAIResponse
- Golden tests lock behavior; 0 regression (byte-for-byte providers/alias, 26=26 known fails)

Co-authored-by: Cursor <cursoragent@cursor.com>

src/app/api/providers/[id]/test/testUtils.js

@@ -2,9 +2,8 @@ import { getProviderConnectionById, updateProviderConnection } from "@/lib/local
 import { resolveConnectionProxyConfig } from "@/lib/network/connectionProxy";
 import { testProxyUrl } from "@/lib/network/proxyTest";
 import { isOpenAICompatibleProvider, isAnthropicCompatibleProvider } from "@/shared/constants/providers";
-import { PROVIDER_ENDPOINTS } from "@/shared/constants/config";
 import { getDefaultModel } from "open-sse/config/providerModels.js";
-import { resolveOllamaLocalHost } from "open-sse/config/providers.js";
+import { resolveOllamaLocalHost, PROVIDERS } from "open-sse/config/providers.js";
 import {
   refreshProviderCredentials,
   shouldRefreshCredentials,
@@ -474,7 +473,7 @@ async function testApiKeyConnection(connection, effectiveProxy = null) {
       }
       case "volcengine-ark":
       case "byteplus": {
-        const res = await fetchWithConnectionProxy(PROVIDER_ENDPOINTS[connection.provider], {
+        const res = await fetchWithConnectionProxy(PROVIDERS[connection.provider]?.baseUrl, {
           method: "POST",
           headers: { "Authorization": `Bearer ${connection.apiKey}`, "content-type": "application/json" },
           body: JSON.stringify({ model: getDefaultModel(connection.provider), max_tokens: 1, messages: [{ role: "user", content: "test" }] }),

src/app/api/providers/validate/route.js

@@ -3,8 +3,7 @@ import { getProviderNodeById } from "@/models";
 import { isOpenAICompatibleProvider, isAnthropicCompatibleProvider, isCustomEmbeddingProvider, AI_PROVIDERS } from "@/shared/constants/providers";
 import { getDefaultModel } from "open-sse/config/providerModels.js";
 import { resolveOllamaLocalHost, resolveXiaomiTokenplanBaseUrl, PROVIDERS } from "open-sse/config/providers.js";
-import { openaiToCommandCode } from "open-sse/translator/request/openai-to-commandcode.js";
-import { PROVIDER_ENDPOINTS } from "@/shared/constants/config";
+import { openaiToCommandCodeRequest } from "open-sse/translator/request/openai-to-commandcode.js";
 import { normalizeProviderId } from "@/lib/providerNormalization";
 
 // Probe a webSearch/webFetch provider using its searchConfig/fetchConfig.
@@ -326,7 +325,7 @@ export async function POST(request) {
         }
         case "volcengine-ark":
         case "byteplus": {
-          const res = await fetch(PROVIDER_ENDPOINTS[provider], {
+          const res = await fetch(PROVIDERS[provider]?.baseUrl, {
             method: "POST",
             headers: {
               "Authorization": `Bearer ${apiKey}`,
@@ -400,7 +399,7 @@ export async function POST(request) {
         case "commandcode": {
           const cfg = PROVIDERS.commandcode;
           const model = getDefaultModel("commandcode");
-          const payload = openaiToCommandCode(model, {
+          const payload = openaiToCommandCodeRequest(model, {
             messages: [{ role: "user", content: "ping" }],
             max_tokens: 1,
             stream: false,

src/app/api/v1/models/info/route.js

@@ -40,7 +40,8 @@ function buildInfo({ alias, providerId, model, kind, providerInfo }) {
 }
 
 // id format: "{alias}/{modelId}" - alias may also be providerId
-function lookup(fullId) {
+// requestedKind: optional, disambiguates duplicate ids across kinds (e.g. gemini-2.5-pro llm vs stt)
+function lookup(fullId, requestedKind) {
   if (!fullId || !fullId.includes("/")) return null;
   const slash = fullId.indexOf("/");
   const alias = fullId.slice(0, slash);
@@ -50,7 +51,9 @@ function lookup(fullId) {
 
   // PROVIDER_MODELS lookup (by alias key, fallback to providerId)
   const list = PROVIDER_MODELS[alias] || PROVIDER_MODELS[providerId] || [];
-  const m = list.find((x) => x.id === modelId);
+  const m = requestedKind
+    ? list.find((x) => x.id === modelId && (x.kind || x.type || "llm") === requestedKind)
+    : list.find((x) => x.id === modelId);
   if (m) {
     const kind = m.kind || m.type || "llm";
     return buildInfo({ alias, providerId, model: m, kind, providerInfo });
@@ -82,13 +85,14 @@ export async function OPTIONS() {
 export async function GET(request) {
   const { searchParams } = new URL(request.url);
   const id = searchParams.get("id");
+  const kind = searchParams.get("kind");
   if (!id) {
     return Response.json(
       { error: { message: "Missing required query param: id (e.g. ?id=openai/dall-e-3)", type: "invalid_request_error" } },
       { status: 400, headers: { "Access-Control-Allow-Origin": "*" } },
     );
   }
-  const info = lookup(id);
+  const info = lookup(id, kind);
   if (!info) {
     return Response.json(
       { error: { message: `Model not found: ${id}`, type: "not_found" } },