Add Google Vertex AI provider (#1163)

# Summary * Adds first-class **Google Vertex AI provider** using `@ai-sdk/google-vertex`. * Supports **Gemini 2.5** models and partner **MaaS (Model Garden)** models via full publisher IDs. * New **Vertex-specific settings UI** for Project, Location, and Service Account JSON. * Implements a **“thinking” toggle** for Gemini 2.5 Flash * Pro: always on * Flash: toggleable * Flash Lite: none * Fixes *“AI not found”* for Vertex built-ins by mapping to `publishers/google` paths. * Hardens **cross-platform file ops** and ensures all tests pass. --- # What’s New ### Vertex AI Provider * Uses `@ai-sdk/google-vertex` with `googleAuthOptions.credentials` from pasted Service Account JSON. * Configurable **project** and **location**. * Base URL → `/projects/{project}/locations/{location}` * Built-ins: `publishers/google/models/<id>` * Partner MaaS: `publishers/<partner>/models/...` ### Built-in Vertex Models * `gemini-2.5-pro` * `gemini-2.5-flash` * `gemini-2.5-flash-lite` ### Thinking Behavior * Vertex + Google marked as thinking-capable. * Pro: always thinking * Flash: toggle in UI * Flash Lite: none ### Vertex Settings UI * New **Google Vertex AI panel** for Project ID, Location, Service Account JSON. * Keys encrypted like other secrets. --- # Fixes * **Model resolution:** built-ins auto-map to `publishers/google/models/<id>`. * **Partner MaaS support:** full publisher IDs work directly (e.g. DeepSeek). * **Cross-platform paths:** normalize file ops with `toPosixPath`, preserve `safeJoin` semantics. --- # Why This Is Better * Users can select **Vertex alongside other providers**. * **More models** available through Model Garden. * **Dedicated setup UI** reduces misconfig. * **Thinking toggle** gives control over cost vs. reasoning depth. --- # Files Changed * **Provider & Models**: `language_model_helpers.ts`, `get_model_client.ts` * **Streaming**: `chat_stream_handlers.ts` * **Schemas & Encryption**: `schemas.ts`, `settings.ts` * **Settings UI**: `VertexConfiguration.tsx`, `ApiKeyConfiguration.tsx` * **Models UI**: `ModelsSection.tsx` (Flash toggle) * **Setup Detection**: `useLanguageModelProviders.ts` * **Path Utils**: `path_utils.ts`, `response_processor.ts` * **Deps**: `package.json` → `@ai-sdk/google-vertex@3.0.16` --- # Tests & Validation * **TypeScript**: `npm run ts` → ✅ * **Lint**: `npm run lint` → ✅ * **Unit tests**: `npm test` → ✅ 231 passed, 0 failed --- # Migration / Notes * No breaking changes. * For Vertex usage: * Ensure Vertex AI API is enabled. * Service Account needs `roles/aiplatform.user`. * Region must support model (e.g. `us-central1`). * Thinking toggle currently affects **only** Gemini 2.5 Flash. --- # Manual QA 1. Configure Vertex with Project/Location/Service Account JSON. 2. Test built-ins: * `gemini-2.5-pro` * `gemini-2.5-flash` (toggle on/off) * `gemini-2.5-flash-lite` 3. Test MaaS partner model (e.g., DeepSeek) via full publisher ID. 4. Verify other providers remain unaffected.  --- ## Summary by cubic Adds a first-class Google Vertex AI provider with Gemini 2.5 models, a Vertex settings panel, and a “thinking” toggle for Gemini 2.5 Flash. Also fixes model resolution for Vertex and hardens cross-platform file operations. - **New Features** - Vertex AI provider via @ai-sdk/google-vertex with project, location, and service account JSON. - Built-in models: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite. - “Thinking” support: Pro always on; Flash toggle in Models UI; Flash Lite none. - MaaS partners supported via full publisher paths (e.g., publishers/<partner>/models/...). - Vertex settings UI with encrypted service account key storage. - **Bug Fixes** - Built-in Vertex models auto-map to publishers/google/models/<id>. - Consistent file ops across platforms using toPosixPath. - Vertex readiness detection requires project/location/service account JSON. - Streaming “thinking” behavior respects Vertex Flash toggle and Pro always-on.  --------- Co-authored-by: Md Rakibul Islam Rocky <mdrirocky08@gmail.com> Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com> Co-authored-by: Will Chen <willchen90@gmail.com>
2025-09-09 08:41:12 +03:00
parent e962964afe
commit 4db6d63b72
11 changed files with 588 additions and 36 deletions
--- a/src/components/settings/ApiKeyConfiguration.tsx
+++ b/src/components/settings/ApiKeyConfiguration.tsx
@@ -7,6 +7,7 @@ import {
  AccordionTrigger,
 } from "@/components/ui/accordion";
 import { AzureConfiguration } from "./AzureConfiguration";
+import { VertexConfiguration } from "./VertexConfiguration";
 import { Input } from "@/components/ui/input";
 import { Button } from "@/components/ui/button";
 import { UserSettings } from "@/lib/schemas";
@@ -51,6 +52,10 @@ export function ApiKeyConfiguration({
  if (provider === "azure") {
    return <AzureConfiguration envVars={envVars} />;
  }
+  // Special handling for Google Vertex AI which uses service account credentials
+  if (provider === "vertex") {
+    return <VertexConfiguration />;
+  }

  const envApiKey = envVarName ? envVars[envVarName] : undefined;
  const userApiKey = settings?.providerSettings?.[provider]?.apiKey?.value;
--- a/src/components/settings/ProviderSettingsPage.tsx
+++ b/src/components/settings/ProviderSettingsPage.tsx
@@ -75,8 +75,20 @@ export function ProviderSettingsPage({ provider }: ProviderSettingsPageProps) {
      ? !!(envVars["AZURE_API_KEY"] && envVars["AZURE_RESOURCE_NAME"])
      : false;

+  // Special handling for Vertex configuration status
+  const vertexSettings = settings?.providerSettings?.vertex as any;
+  const isVertexConfigured = Boolean(
+    vertexSettings?.projectId &&
+      vertexSettings?.location &&
+      vertexSettings?.serviceAccountKey?.value,
+  );
+
  const isConfigured =
-    provider === "azure" ? isAzureConfigured : isValidUserKey || hasEnvKey; // Configured if either is set
+    provider === "azure"
+      ? isAzureConfigured
+      : provider === "vertex"
+        ? isVertexConfigured
+        : isValidUserKey || hasEnvKey; // Configured if either is set

  // --- Save Handler ---
  const handleSaveKey = async () => {
--- a/src/components/settings/VertexConfiguration.tsx
+++ b/src/components/settings/VertexConfiguration.tsx
@@ -0,0 +1,141 @@
+import { useState, useEffect } from "react";
+import { Input } from "@/components/ui/input";
+import { Button } from "@/components/ui/button";
+import { Textarea } from "@/components/ui/textarea";
+import { Alert, AlertDescription, AlertTitle } from "@/components/ui/alert";
+import { Info, CheckCircle2 } from "lucide-react";
+import { useSettings } from "@/hooks/useSettings";
+import type { UserSettings, VertexProviderSetting } from "@/lib/schemas";
+
+export function VertexConfiguration() {
+  const { settings, updateSettings } = useSettings();
+  const existing =
+    (settings?.providerSettings?.vertex as VertexProviderSetting) ?? {};
+
+  const [projectId, setProjectId] = useState(existing.projectId || "");
+  const [location, setLocation] = useState(existing.location || "");
+  const [serviceAccountKey, setServiceAccountKey] = useState(
+    existing.serviceAccountKey?.value || "",
+  );
+  const [saving, setSaving] = useState(false);
+  const [error, setError] = useState<string | null>(null);
+  const [saved, setSaved] = useState(false);
+
+  useEffect(() => {
+    setProjectId(existing.projectId || "");
+    setLocation(existing.location || "");
+    setServiceAccountKey(existing.serviceAccountKey?.value || "");
+  }, [settings?.providerSettings?.vertex]);
+
+  const onSave = async () => {
+    setError(null);
+    setSaved(false);
+    try {
+      // If provided, ensure the service account JSON parses
+      if (serviceAccountKey) {
+        JSON.parse(serviceAccountKey);
+      }
+    } catch (e: any) {
+      setError("Service account JSON is invalid: " + e.message);
+      return;
+    }
+
+    setSaving(true);
+    try {
+      const settingsUpdate: Partial<UserSettings> = {
+        providerSettings: {
+          ...settings?.providerSettings,
+          vertex: {
+            ...existing,
+            projectId: projectId.trim() || undefined,
+            location: location || undefined,
+            serviceAccountKey: serviceAccountKey
+              ? { value: serviceAccountKey }
+              : undefined,
+          },
+        },
+      };
+      await updateSettings(settingsUpdate);
+      setSaved(true);
+    } catch (e: any) {
+      setError(e?.message || "Failed to save Vertex settings");
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const isConfigured = Boolean(
+    (projectId.trim() && location && serviceAccountKey) ||
+      (existing.projectId &&
+        existing.location &&
+        existing.serviceAccountKey?.value),
+  );
+
+  return (
+    <div className="space-y-4">
+      <div className="grid grid-cols-1 gap-4">
+        <div>
+          <label className="block text-sm font-medium mb-1">Project ID</label>
+          <Input
+            value={projectId}
+            onChange={(e) => setProjectId(e.target.value)}
+            placeholder="your-gcp-project-id"
+          />
+        </div>
+        <div>
+          <label className="block text-sm font-medium mb-1">Location</label>
+          <Input
+            value={location}
+            onChange={(e) => setLocation(e.target.value)}
+            placeholder="us-central1"
+          />
+          <p className="mt-1 text-xs text-muted-foreground">
+            If you see a "model not found" error, try a different region. Some
+            partner models (MaaS) are only available in specific locations
+            (e.g., us-central1, us-west2).
+          </p>
+        </div>
+        <div>
+          <label className="block text-sm font-medium mb-1">
+            Service Account JSON Key
+          </label>
+          <Textarea
+            value={serviceAccountKey}
+            onChange={(e) => setServiceAccountKey(e.target.value)}
+            placeholder="Paste the full JSON contents of your service account key here"
+            className="min-h-40"
+          />
+        </div>
+      </div>
+
+      <div className="flex items-center gap-2">
+        <Button onClick={onSave} disabled={saving}>
+          {saving ? "Saving..." : "Save Settings"}
+        </Button>
+        {saved && !error && (
+          <span className="flex items-center text-green-600 text-sm">
+            <CheckCircle2 className="h-4 w-4 mr-1" /> Saved
+          </span>
+        )}
+      </div>
+
+      {!isConfigured && (
+        <Alert variant="default">
+          <Info className="h-4 w-4" />
+          <AlertTitle>Configuration Required</AlertTitle>
+          <AlertDescription>
+            Provide Project, Location, and a service account JSON key with
+            Vertex AI access.
+          </AlertDescription>
+        </Alert>
+      )}
+
+      {error && (
+        <Alert variant="destructive">
+          <AlertTitle>Save Error</AlertTitle>
+          <AlertDescription>{error}</AlertDescription>
+        </Alert>
+      )}
+    </div>
+  );
+}
--- a/src/hooks/useLanguageModelProviders.ts
+++ b/src/hooks/useLanguageModelProviders.ts
@@ -2,7 +2,7 @@ import { useQuery } from "@tanstack/react-query";
 import { IpcClient } from "@/ipc/ipc_client";
 import type { LanguageModelProvider } from "@/ipc/ipc_types";
 import { useSettings } from "./useSettings";
-import { cloudProviders } from "@/lib/schemas";
+import { cloudProviders, VertexProviderSetting } from "@/lib/schemas";

 export function useLanguageModelProviders() {
  const ipcClient = IpcClient.getInstance();
@@ -20,6 +20,18 @@ export function useLanguageModelProviders() {
    if (queryResult.isLoading) {
      return false;
    }
+    // Vertex uses service account credentials instead of an API key
+    if (provider === "vertex") {
+      const vertexSettings = providerSettings as VertexProviderSetting;
+      if (
+        vertexSettings?.serviceAccountKey?.value &&
+        vertexSettings?.projectId &&
+        vertexSettings?.location
+      ) {
+        return true;
+      }
+      return false;
+    }
    if (providerSettings?.apiKey?.value) {
      return true;
    }
--- a/src/ipc/handlers/chat_stream_handlers.ts
+++ b/src/ipc/handlers/chat_stream_handlers.ts
@@ -667,28 +667,53 @@ This conversation includes one or more image attachments. When the user uploads
          } else {
            logger.log("sending AI request");
          }
+          // Build provider options with correct Google/Vertex thinking config gating
+          const providerOptions: Record<string, any> = {
+            "dyad-engine": {
+              dyadRequestId,
+            },
+            "dyad-gateway": getExtraProviderOptions(
+              modelClient.builtinProviderId,
+              settings,
+            ),
+            openai: {
+              reasoningSummary: "auto",
+            } satisfies OpenAIResponsesProviderOptions,
+          };
+
+          // Conditionally include Google thinking config only for supported models
+          const selectedModelName = settings.selectedModel.name || "";
+          const providerId = modelClient.builtinProviderId;
+          const isVertex = providerId === "vertex";
+          const isGoogle = providerId === "google";
+          const isPartnerModel = selectedModelName.includes("/");
+          const isGeminiModel = selectedModelName.startsWith("gemini");
+          const isFlashLite = selectedModelName.includes("flash-lite");
+
+          // Keep Google provider behavior unchanged: always include includeThoughts
+          if (isGoogle) {
+            providerOptions.google = {
+              thinkingConfig: {
+                includeThoughts: true,
+              },
+            } satisfies GoogleGenerativeAIProviderOptions;
+          }
+
+          // Vertex-specific fix: only enable thinking on supported Gemini models
+          if (isVertex && isGeminiModel && !isFlashLite && !isPartnerModel) {
+            providerOptions.google = {
+              thinkingConfig: {
+                includeThoughts: true,
+              },
+            } satisfies GoogleGenerativeAIProviderOptions;
+          }
+
          return streamText({
            maxOutputTokens: await getMaxTokens(settings.selectedModel),
            temperature: await getTemperature(settings.selectedModel),
            maxRetries: 2,
            model: modelClient.model,
-            providerOptions: {
-              "dyad-engine": {
-                dyadRequestId,
-              },
-              "dyad-gateway": getExtraProviderOptions(
-                modelClient.builtinProviderId,
-                settings,
-              ),
-              google: {
-                thinkingConfig: {
-                  includeThoughts: true,
-                },
-              } satisfies GoogleGenerativeAIProviderOptions,
-              openai: {
-                reasoningSummary: "auto",
-              } satisfies OpenAIResponsesProviderOptions,
-            },
+            providerOptions,
            system: systemPrompt,
            messages: chatMessages.filter((m) => m.content),
            onError: (error: any) => {
--- a/src/ipc/shared/language_model_helpers.ts
+++ b/src/ipc/shared/language_model_helpers.ts
@@ -8,6 +8,7 @@ import { eq } from "drizzle-orm";

 export const PROVIDERS_THAT_SUPPORT_THINKING: (keyof typeof MODEL_OPTIONS)[] = [
  "google",
+  "vertex",
  "auto",
 ];

@@ -144,6 +145,26 @@ export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
      dollarSigns: 2,
    },
  ],
+  vertex: [
+    // Vertex Gemini 2.5 Pro
+    {
+      name: "gemini-2.5-pro",
+      displayName: "Gemini 2.5 Pro",
+      description: "Vertex Gemini 2.5 Pro",
+      maxOutputTokens: 65_536 - 1,
+      contextWindow: 1_048_576,
+      temperature: 0,
+    },
+    // Vertex Gemini 2.5 Flash
+    {
+      name: "gemini-2.5-flash",
+      displayName: "Gemini 2.5 Flash",
+      description: "Vertex Gemini 2.5 Flash",
+      maxOutputTokens: 65_536 - 1,
+      contextWindow: 1_048_576,
+      temperature: 0,
+    },
+  ],
  openrouter: [
    {
      name: "qwen/qwen3-coder",
@@ -270,6 +291,14 @@ export const CLOUD_PROVIDERS: Record<
    websiteUrl: "https://aistudio.google.com/app/apikey",
    gatewayPrefix: "gemini/",
  },
+  vertex: {
+    displayName: "Google Vertex AI",
+    hasFreeTier: false,
+    websiteUrl: "https://console.cloud.google.com/vertex-ai",
+    // Use the same gateway prefix as Google Gemini for Dyad Pro compatibility.
+    gatewayPrefix: "gemini/",
+    secondary: true,
+  },
  openrouter: {
    displayName: "OpenRouter",
    hasFreeTier: true,
--- a/src/ipc/utils/get_model_client.ts
+++ b/src/ipc/utils/get_model_client.ts
@@ -1,10 +1,15 @@
 import { createOpenAI } from "@ai-sdk/openai";
 import { createGoogleGenerativeAI as createGoogle } from "@ai-sdk/google";
 import { createAnthropic } from "@ai-sdk/anthropic";
+import { createVertex as createGoogleVertex } from "@ai-sdk/google-vertex";
 import { azure } from "@ai-sdk/azure";
 import { createOpenRouter } from "@openrouter/ai-sdk-provider";
 import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
-import type { LargeLanguageModel, UserSettings } from "../../lib/schemas";
+import type {
+  LargeLanguageModel,
+  UserSettings,
+  VertexProviderSetting,
+} from "../../lib/schemas";
 import { getEnvVar } from "./read_env";
 import log from "electron-log";
 import { getLanguageModelProviders } from "../shared/language_model_helpers";
@@ -216,6 +221,45 @@ function getRegularModelClient(
        backupModelClients: [],
      };
    }
+    case "vertex": {
+      // Vertex uses Google service account credentials with project/location
+      const vertexSettings = settings.providerSettings?.[
+        model.provider
+      ] as VertexProviderSetting;
+      const project = vertexSettings?.projectId;
+      const location = vertexSettings?.location;
+      const serviceAccountKey = vertexSettings?.serviceAccountKey?.value;
+
+      // Use a baseURL that does NOT pin to publishers/google so that
+      // full publisher model IDs (e.g. publishers/deepseek-ai/models/...) work.
+      const regionHost = `${location === "global" ? "" : `${location}-`}aiplatform.googleapis.com`;
+      const baseURL = `https://${regionHost}/v1/projects/${project}/locations/${location}`;
+      const provider = createGoogleVertex({
+        project,
+        location,
+        baseURL,
+        googleAuthOptions: serviceAccountKey
+          ? {
+              // Expecting the user to paste the full JSON of the service account key
+              credentials: JSON.parse(serviceAccountKey),
+            }
+          : undefined,
+      });
+      return {
+        modelClient: {
+          // For built-in Google models on Vertex, the path must include
+          // publishers/google/models/<model>. For partner MaaS models the
+          // full publisher path is already included.
+          model: provider(
+            model.name.includes("/")
+              ? model.name
+              : `publishers/google/models/${model.name}`,
+          ),
+          builtinProviderId: providerId,
+        },
+        backupModelClients: [],
+      };
+    }
    case "openrouter": {
      const provider = createOpenRouter({ apiKey });
      return {
--- a/src/lib/schemas.ts
+++ b/src/lib/schemas.ts
@@ -30,6 +30,7 @@ const providers = [
  "openai",
  "anthropic",
  "google",
+  "vertex",
  "auto",
  "openrouter",
  "ollama",
@@ -57,15 +58,35 @@ export type LargeLanguageModel = z.infer<typeof LargeLanguageModelSchema>;

 /**
 * Zod schema for provider settings
+ * Regular providers use only apiKey. Vertex has additional optional fields.
 */
-export const ProviderSettingSchema = z.object({
+export const RegularProviderSettingSchema = z.object({
  apiKey: SecretSchema.optional(),
 });

+export const VertexProviderSettingSchema = z.object({
+  // We make this undefined so that it makes existing callsites easier.
+  apiKey: z.undefined(),
+  projectId: z.string().optional(),
+  location: z.string().optional(),
+  serviceAccountKey: SecretSchema.optional(),
+});
+
+export const ProviderSettingSchema = z.union([
+  // Must use more specific type first!
+  // Zod uses the first type that matches.
+  VertexProviderSettingSchema,
+  RegularProviderSettingSchema,
+]);
+
 /**
 * Type derived from the ProviderSettingSchema
 */
 export type ProviderSetting = z.infer<typeof ProviderSettingSchema>;
+export type RegularProviderSetting = z.infer<
+  typeof RegularProviderSettingSchema
+>;
+export type VertexProviderSetting = z.infer<typeof VertexProviderSettingSchema>;

 export const RuntimeModeSchema = z.enum(["web-sandbox", "local-node", "unset"]);
 export type RuntimeMode = z.infer<typeof RuntimeModeSchema>;
--- a/src/main/settings.ts
+++ b/src/main/settings.ts
@@ -1,7 +1,12 @@
 import fs from "node:fs";
 import path from "node:path";
 import { getUserDataPath } from "../paths/paths";
-import { UserSettingsSchema, type UserSettings, Secret } from "../lib/schemas";
+import {
+  UserSettingsSchema,
+  type UserSettings,
+  Secret,
+  VertexProviderSetting,
+} from "../lib/schemas";
 import { safeStorage } from "electron";
 import { v4 as uuidv4 } from "uuid";
 import log from "electron-log";
@@ -114,6 +119,17 @@ export function readSettings(): UserSettings {
          encryptionType,
        };
      }
+      // Decrypt Vertex service account key if present
+      const v = combinedSettings.providerSettings[
+        provider
+      ] as VertexProviderSetting;
+      if (provider === "vertex" && v?.serviceAccountKey) {
+        const encryptionType = v.serviceAccountKey.encryptionType;
+        v.serviceAccountKey = {
+          value: decrypt(v.serviceAccountKey),
+          encryptionType,
+        };
+      }
    }

    // Validate and merge with defaults
@@ -171,6 +187,11 @@ export function writeSettings(settings: Partial<UserSettings>): void {
          newSettings.providerSettings[provider].apiKey.value,
        );
      }
+      // Encrypt Vertex service account key if present
+      const v = newSettings.providerSettings[provider] as VertexProviderSetting;
+      if (provider === "vertex" && v?.serviceAccountKey) {
+        v.serviceAccountKey = encrypt(v.serviceAccountKey.value);
+      }
    }
    const validatedSettings = UserSettingsSchema.parse(newSettings);
    fs.writeFileSync(filePath, JSON.stringify(validatedSettings, null, 2));