feat(provider): add Chenzk API OpenAI-compatible gateway

Registers Chenzk (chenzk.top) as a new API-key gateway provider — an
OpenAI-compatible aggregator exposing GPT/Claude/DeepSeek/GLM model groups
behind one endpoint. Adapted to OmniRoute's directory-per-provider registry
(open-sse/config/providers/registry/) and metadata catalog
(src/shared/constants/providers/apikey/gateways.ts), following the same
passthrough-models pattern already used for kenari/x5lab/sumopod (live
/v1/models catalog resolves the model list instead of a hardcoded array).

Co-authored-by: Ahmad Putra Cahyo <CahyokPutraDev99@users.noreply.github.com>
Inspired-by: https://github.com/decolua/9router/pull/2437

open-sse/config/providers/index.ts

@@ -151,6 +151,7 @@ import { gigachatProvider } from "./registry/gigachat/index.ts";
 import { devin_cliProvider } from "./registry/devin-cli/index.ts";
 import { auggieProvider } from "./registry/auggie/index.ts";
 import { chutesProvider } from "./registry/chutes/index.ts";
+import { chenzkProvider } from "./registry/chenzk/index.ts";
 import { factoryProvider } from "./registry/factory/index.ts";
 import { databricksProvider } from "./registry/databricks/index.ts";
 import { rekaProvider } from "./registry/reka/index.ts";
@@ -336,6 +337,7 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   "devin-cli": devin_cliProvider,
   auggie: auggieProvider,
   chutes: chutesProvider,
+  chenzk: chenzkProvider,
   factory: factoryProvider,
   databricks: databricksProvider,
   reka: rekaProvider,

open-sse/config/providers/registry/chenzk/index.ts

@@ -0,0 +1,15 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+export const chenzkProvider: RegistryEntry = {
+  id: "chenzk",
+  alias: "chenzk",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://chenzk.top/v1/chat/completions",
+  authType: "apikey",
+  authHeader: "bearer",
+  modelsUrl: "https://chenzk.top/v1/models",
+  defaultContextLength: 128000,
+  models: [],
+  passthroughModels: true,
+};

src/shared/constants/config.ts

@@ -23,6 +23,7 @@ export const PROVIDER_ENDPOINTS = {
   sumopod: "https://ai.sumopod.com/v1/chat/completions",
   x5lab: "https://api.x5lab.dev/v1/chat/completions",
   kenari: "https://kenari.id/v1/chat/completions",
+  chenzk: "https://chenzk.top/v1/chat/completions",
   openai: "https://api.openai.com/v1/chat/completions",
   anthropic: "https://api.anthropic.com/v1/messages",
   gemini: "https://generativelanguage.googleapis.com/v1beta/models",

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

@@ -579,6 +579,19 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
     apiHint:
       "X5Lab exposes an OpenAI-compatible chat completions endpoint at https://api.x5lab.dev/v1/chat/completions, plus a live /v1/models catalog. OmniRoute uses the OpenAI protocol and lists models via passthrough.",
   },
+  chenzk: {
+    id: "chenzk",
+    alias: "chenzk",
+    name: "Chenzk API",
+    icon: "hub",
+    color: "#10B981",
+    textIcon: "CZ",
+    passthroughModels: true,
+    website: "https://chenzk.top",
+    apiHint:
+      "Create an API key at https://chenzk.top/token, then paste it here as a Bearer token. " +
+      "OpenAI-compatible endpoint at https://chenzk.top/v1, with a live /v1/models catalog.",
+  },
   kenari: {
     id: "kenari",
     alias: "kenari",

tests/unit/chenzk-provider-2437.test.ts

@@ -0,0 +1,49 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+const { APIKEY_PROVIDERS } = await import("../../src/shared/constants/providers.ts");
+const { PROVIDER_ENDPOINTS } = await import("../../src/shared/constants/config.ts");
+const { REGISTRY: providerRegistry } = await import("../../open-sse/config/providerRegistry.ts");
+
+const CHENZK_CHAT_URL = "https://chenzk.top/v1/chat/completions";
+const CHENZK_MODELS_URL = "https://chenzk.top/v1/models";
+
+// Port of decolua/9router#2437 ("feat: add Chenzk API provider"), adapted to
+// OmniRoute's directory-per-provider registry (`open-sse/config/providers/registry/`)
+// and the `src/shared/constants/providers/apikey/*` metadata catalog, instead of
+// upstream's flat `open-sse/providers/registry/*.js` + hardcoded model array. Chenzk
+// exposes a "New API"-style OpenAI-compatible gateway with a live /v1/models catalog,
+// so — matching the sibling kenari/x5lab/sumopod gateways already in this catalog —
+// models are resolved via passthrough rather than a speculative hardcoded list.
+test("Chenzk is registered as an OpenAI-compatible API-key gateway", () => {
+  const entry = APIKEY_PROVIDERS.chenzk;
+  assert.ok(entry, "APIKEY_PROVIDERS.chenzk must be defined");
+  assert.equal(entry.id, "chenzk");
+  assert.equal(entry.alias, "chenzk");
+  assert.equal(entry.name, "Chenzk API");
+  assert.equal(entry.website, "https://chenzk.top");
+  assert.equal(entry.passthroughModels, true);
+});
+
+test("Chenzk exposes the OpenAI-compatible chat completions endpoint", () => {
+  assert.equal(PROVIDER_ENDPOINTS.chenzk, CHENZK_CHAT_URL);
+});
+
+test("Chenzk registry entry uses OpenAI format with bearer API-key auth and passthrough models", () => {
+  const entry = providerRegistry.chenzk;
+  assert.ok(entry, "providerRegistry.chenzk must be defined");
+  assert.equal(entry.id, "chenzk");
+  assert.equal(entry.alias, "chenzk");
+  assert.equal(entry.format, "openai");
+  assert.equal(entry.executor, "default");
+  assert.equal(entry.authType, "apikey");
+  assert.equal(entry.authHeader, "bearer");
+  assert.equal(entry.baseUrl, CHENZK_CHAT_URL);
+  assert.equal(entry.modelsUrl, CHENZK_MODELS_URL);
+  assert.equal(entry.passthroughModels, true);
+  assert.deepEqual(
+    entry.models,
+    [],
+    "Chenzk ships no speculative seeded models — live catalog via passthrough only"
+  );
+});