fix(anthropic-vertex): correct multi-region endpoints (#116757)

Co-authored-by: Peter Steinberger <steipete@macos.shared>

extensions/anthropic-vertex/index.test.ts

@@ -102,6 +102,19 @@ describe("anthropic-vertex provider plugin", () => {
     expect(result.provider.models[4]?.thinkingLevelMap).toEqual({ xhigh: null, max: "max" });
   });
 
+  it.each([
+    { region: "global", baseUrl: "https://aiplatform.googleapis.com" },
+    { region: "us", baseUrl: "https://aiplatform.us.rep.googleapis.com" },
+    { region: "eu", baseUrl: "https://aiplatform.eu.rep.googleapis.com" },
+    { region: "us-east5", baseUrl: "https://us-east5-aiplatform.googleapis.com" },
+  ])("publishes the SDK endpoint for the $region location", ({ region, baseUrl }) => {
+    expect(
+      buildAnthropicVertexProvider({
+        env: { GOOGLE_CLOUD_LOCATION: region },
+      }).baseUrl,
+    ).toBe(baseUrl);
+  });
+
   it.each(["global", "us", "eu"])("publishes Opus 5 for the %s endpoint", (region) => {
     const provider = buildAnthropicVertexProvider({
       env: { GOOGLE_CLOUD_LOCATION: region },
@@ -194,7 +207,7 @@ describe("anthropic-vertex provider plugin", () => {
         name: "Claude Sonnet 5",
         api: "anthropic-messages",
         provider: "anthropic-vertex",
-        baseUrl: "https://us-aiplatform.googleapis.com",
+        baseUrl: "https://aiplatform.us.rep.googleapis.com",
         reasoning: true,
         input: ["text", "image"],
         contextWindow: 1_000_000,
@@ -235,7 +248,7 @@ describe("anthropic-vertex provider plugin", () => {
         name: "Claude Opus 5",
         api: "anthropic-messages",
         provider: "anthropic-vertex",
-        baseUrl: "https://us-aiplatform.googleapis.com",
+        baseUrl: "https://aiplatform.us.rep.googleapis.com",
         reasoning: false,
         input: ["text"],
         cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },

extensions/anthropic-vertex/provider-catalog.ts

@@ -238,7 +238,9 @@ export function buildAnthropicVertexProvider(params?: {
   const baseUrl =
     normalizeLowercaseStringOrEmpty(region) === "global"
       ? "https://aiplatform.googleapis.com"
-      : `https://${region}-aiplatform.googleapis.com`;
+      : region === "us" || region === "eu"
+        ? `https://aiplatform.${region}.rep.googleapis.com`
+        : `https://${region}-aiplatform.googleapis.com`;
 
   return {
     baseUrl,

extensions/anthropic-vertex/region.test.ts

@@ -25,6 +25,12 @@ describe("anthropic vertex region helpers", () => {
     ).toBe("europe-west4");
   });
 
+  it.each(["us", "eu"])("parses the %s multi-region Vertex endpoint", (region) => {
+    expect(
+      resolveAnthropicVertexRegionFromBaseUrl(`https://aiplatform.${region}.rep.googleapis.com`),
+    ).toBe(region);
+  });
+
   it("treats the global Vertex endpoint as global", () => {
     expect(resolveAnthropicVertexRegionFromBaseUrl("https://aiplatform.googleapis.com")).toBe(
       "global",

extensions/anthropic-vertex/stream-runtime.test.ts

@@ -589,6 +589,24 @@ describe("createAnthropicVertexStreamFn", () => {
 });
 
 describe("createAnthropicVertexStreamFnForModel", () => {
+  it.each(["us", "eu"])("preserves the %s multi-region SDK endpoint", (region) => {
+    const { deps, anthropicVertexCtorMock, googleAuthClient } = createStreamDeps();
+    const streamFn = createAnthropicVertexStreamFnForModel(
+      { baseUrl: `https://aiplatform.${region}.rep.googleapis.com` },
+      { GOOGLE_CLOUD_PROJECT_ID: "vertex-project" } as NodeJS.ProcessEnv,
+      deps,
+    );
+
+    void streamFn(makeModel({ id: "claude-sonnet-5", maxTokens: 128_000 }), { messages: [] }, {});
+
+    expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
+      googleAuth: googleAuthClient,
+      projectId: "vertex-project",
+      region,
+      baseURL: `https://aiplatform.${region}.rep.googleapis.com/v1`,
+    });
+  });
+
   it("derives project and region from the model and env", () => {
     const { deps, anthropicVertexCtorMock, googleAuthClient } = createStreamDeps();
     const streamFn = createAnthropicVertexStreamFnForModel(

packages/ai/src/transports/anthropic-payload-policy.test.ts

@@ -0,0 +1,36 @@
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { resolveAnthropicEphemeralCacheControl } from "./anthropic-payload-policy.js";
+
+describe("resolveAnthropicEphemeralCacheControl", () => {
+  afterEach(() => {
+    vi.unstubAllEnvs();
+  });
+
+  it.each([
+    "https://aiplatform.googleapis.com",
+    "https://us-east5-aiplatform.googleapis.com",
+    "https://aiplatform.us.rep.googleapis.com",
+    "https://aiplatform.eu.rep.googleapis.com",
+  ])("preserves env-configured long retention for the official %s endpoint", (baseUrl) => {
+    vi.stubEnv("OPENCLAW_CACHE_RETENTION", "long");
+
+    expect(resolveAnthropicEphemeralCacheControl(baseUrl, undefined)).toEqual({
+      type: "ephemeral",
+      ttl: "1h",
+    });
+  });
+
+  it("keeps env-configured long retention restricted for custom proxy endpoints", () => {
+    vi.stubEnv("OPENCLAW_CACHE_RETENTION", "long");
+
+    expect(
+      resolveAnthropicEphemeralCacheControl("https://proxy.example.test/vertex", undefined),
+    ).toEqual({ type: "ephemeral" });
+  });
+
+  it("preserves explicitly configured long retention for custom proxy endpoints", () => {
+    expect(
+      resolveAnthropicEphemeralCacheControl("https://proxy.example.test/vertex", "long"),
+    ).toEqual({ type: "ephemeral", ttl: "1h" });
+  });
+});

packages/ai/src/transports/anthropic-payload-policy.ts

@@ -56,6 +56,8 @@ function isLongTtlEligibleEndpoint(baseUrl: string | undefined): boolean {
   return (
     hostname === "api.anthropic.com" ||
     hostname === "aiplatform.googleapis.com" ||
+    hostname === "aiplatform.us.rep.googleapis.com" ||
+    hostname === "aiplatform.eu.rep.googleapis.com" ||
     hostname.endsWith("-aiplatform.googleapis.com")
   );
 }