Compare commits

..

3 Commits

Author SHA1 Message Date
Sean McGuire
e8f6ff1f86 add ws override 2026-05-27 11:01:51 -07:00
Sean McGuire
0c52ff66cc bump direct ws dep 2026-05-27 10:57:26 -07:00
Sean McGuire
f1b12a1111 bump turbo 2026-05-27 10:56:03 -07:00
28 changed files with 217 additions and 1310 deletions

View File

@ -1,5 +0,0 @@
---
"@browserbasehq/stagehand": patch
---
Add Claude Opus 4.8 to the supported CUA model whitelist.

View File

@ -1,5 +0,0 @@
---
"@browserbasehq/stagehand-server-v3": patch
---
Add SEA binary --version build metadata output.

View File

@ -1,6 +0,0 @@
---
"@browserbasehq/stagehand": minor
"@browserbasehq/stagehand-server-v3": minor
---
Forward constructor and request model configuration when initializing API-backed sessions.

View File

@ -23,7 +23,6 @@ export const modelToAgentProviderMap: Record<string, AgentProviderType> = {
"claude-sonnet-4-5-20250929": "anthropic",
"claude-opus-4-5-20251101": "anthropic",
"claude-opus-4-6": "anthropic",
"claude-opus-4-8": "anthropic",
"claude-sonnet-4-6": "anthropic",
"claude-haiku-4-5": "anthropic",
"claude-haiku-4-5-20251001": "anthropic",

View File

@ -453,7 +453,6 @@ export class AnthropicCUAClient extends AgentClient {
// Check if this is a Claude 4.6+ model that supports adaptive thinking
const isAdaptiveThinkingModel = [
"claude-opus-4-8",
"claude-opus-4-6",
"claude-sonnet-4-6",
].includes(modelBase);

View File

@ -106,8 +106,6 @@ interface ClientSessionStartParams extends Api.SessionStartRequest {
* Optional: when omitted, requests are sent without the x-model-api-key header
* and the server is expected to handle model authentication on its own. */
modelApiKey?: string;
/** Default model config for later action requests. Not sent to /sessions/start. */
defaultModelConfig?: ModelConfiguration;
}
/**
@ -117,11 +115,6 @@ type ApiResponse<T> =
| { success: true; data: T }
| { success: false; message: string };
type PreparedModelConfig = { modelName: string; apiKey?: string } & Record<
string,
unknown
>;
/**
* Union of all API request body types for type-safe execute() calls
*/
@ -187,7 +180,6 @@ export class StagehandAPIClient {
private sessionId?: string;
private modelApiKey?: string;
private modelProvider?: string;
private defaultModelConfig?: PreparedModelConfig;
private region?: BrowserbaseRegion;
private logger: (message: LogLine) => void;
private fetchWithCookies;
@ -213,7 +205,6 @@ export class StagehandAPIClient {
async init({
modelName,
modelApiKey,
defaultModelConfig,
domSettleTimeoutMs,
verbose,
systemPrompt,
@ -227,9 +218,6 @@ export class StagehandAPIClient {
this.modelProvider = modelName?.includes("/")
? modelName.split("/")[0]
: undefined;
this.defaultModelConfig = defaultModelConfig
? this.prepareModelConfig(defaultModelConfig)
: undefined;
// Store the region for multi-region API URL resolution
this.region = browserbaseSessionCreateParams?.region;
@ -300,18 +288,12 @@ export class StagehandAPIClient {
// eslint-disable-next-line @typescript-eslint/no-unused-vars
const { page: _, serverCache: enableCache, ...restOptions } = options;
serverCache = enableCache;
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
} else if (this.defaultModelConfig) {
restOptions.model = this.getDefaultModelConfig();
}
if (Object.keys(restOptions).length > 0) {
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
}
wireOptions = restOptions as unknown as Api.ActRequest["options"];
}
} else if (this.defaultModelConfig) {
wireOptions = {
model: this.getDefaultModelConfig(),
} as unknown as Api.ActRequest["options"];
}
// Build wire-format request body
@ -344,18 +326,12 @@ export class StagehandAPIClient {
// eslint-disable-next-line @typescript-eslint/no-unused-vars
const { page: _, serverCache: enableCache, ...restOptions } = options;
serverCache = enableCache;
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
} else if (this.defaultModelConfig) {
restOptions.model = this.getDefaultModelConfig();
}
if (Object.keys(restOptions).length > 0) {
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
}
wireOptions = restOptions as unknown as Api.ExtractRequest["options"];
}
} else if (this.defaultModelConfig) {
wireOptions = {
model: this.getDefaultModelConfig(),
} as unknown as Api.ExtractRequest["options"];
}
// Build wire-format request body
@ -385,18 +361,12 @@ export class StagehandAPIClient {
// eslint-disable-next-line @typescript-eslint/no-unused-vars
const { page: _, serverCache: enableCache, ...restOptions } = options;
serverCache = enableCache;
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
} else if (this.defaultModelConfig) {
restOptions.model = this.getDefaultModelConfig();
}
if (Object.keys(restOptions).length > 0) {
if (restOptions.model) {
restOptions.model = this.prepareModelConfig(restOptions.model);
}
wireOptions = restOptions as unknown as Api.ObserveRequest["options"];
}
} else if (this.defaultModelConfig) {
wireOptions = {
model: this.getDefaultModelConfig(),
} as unknown as Api.ObserveRequest["options"];
}
// Build wire-format request body
@ -418,22 +388,7 @@ export class StagehandAPIClient {
options?: Api.NavigateRequest["options"],
frameId?: string,
): Promise<SerializableResponse | null> {
const publicOptions = { ...(options ?? {}) } as NonNullable<
Api.NavigateRequest["options"]
> & { model?: unknown };
delete publicOptions.model;
const wireOptions = {
...publicOptions,
...(this.defaultModelConfig
? { model: this.getDefaultModelConfig() }
: {}),
};
const requestBody: Api.NavigateRequest = {
url,
options: Object.keys(wireOptions).length > 0 ? wireOptions : undefined,
frameId,
};
const requestBody: Api.NavigateRequest = { url, options, frameId };
return this.execute<SerializableResponse | null>({
method: "navigate",
@ -470,7 +425,7 @@ export class StagehandAPIClient {
cua: agentConfig.mode === undefined ? agentConfig.cua : undefined,
model: agentConfig.model
? this.prepareModelConfig(agentConfig.model)
: this.getDefaultModelConfig(),
: undefined,
executionModel: agentConfig.executionModel
? this.prepareModelConfig(agentConfig.executionModel)
: undefined,
@ -650,52 +605,40 @@ export class StagehandAPIClient {
* In API mode, we only attempt to load an API key from env vars when the
* model provider differs from the one used to init the session.
*/
private prepareModelConfig(model: ModelConfiguration): PreparedModelConfig {
private prepareModelConfig(
model: ModelConfiguration,
): { modelName: string; apiKey?: string } & Record<string, unknown> {
if (typeof model === "string") {
// Extract provider from model string (e.g., "openai/gpt-5-nano" -> "openai")
const provider = this.getModelProvider(model);
const inheritedDefault =
provider && provider === this.modelProvider
? this.getDefaultModelConfig()
: undefined;
const provider = model.includes("/") ? model.split("/")[0] : undefined;
const apiKey =
provider && provider !== this.modelProvider
? (loadApiKeyFromEnv(provider, this.logger) ?? this.modelApiKey)
: this.modelApiKey;
return {
...inheritedDefault,
modelName: model,
...(apiKey ? { apiKey } : {}),
};
}
const provider = this.getModelProvider(model.modelName);
const inheritedDefault =
provider && provider === this.modelProvider
? this.getDefaultModelConfig()
if (!model.apiKey) {
const provider = model.modelName?.includes("/")
? model.modelName.split("/")[0]
: undefined;
const apiKey =
!model.apiKey && provider && provider !== this.modelProvider
? (loadApiKeyFromEnv(provider, this.logger) ?? this.modelApiKey)
: !model.apiKey
? this.modelApiKey
: undefined;
const apiKey =
provider && provider !== this.modelProvider
? (loadApiKeyFromEnv(provider, this.logger) ?? this.modelApiKey)
: this.modelApiKey;
return {
...model,
...(apiKey ? { apiKey } : {}),
};
}
return {
...inheritedDefault,
...model,
...(apiKey ? { apiKey } : {}),
} as PreparedModelConfig;
}
private getDefaultModelConfig(): PreparedModelConfig | undefined {
return this.defaultModelConfig
? ({ ...this.defaultModelConfig } as PreparedModelConfig)
: undefined;
}
private getModelProvider(modelName: string | undefined): string | undefined {
return modelName?.includes("/") ? modelName.split("/")[0] : undefined;
return model as { modelName: string; apiKey: string } & Record<
string,
unknown
>;
}
private consumeFinishedEventData<T>(): T | null {

View File

@ -1,5 +1,6 @@
import type { LanguageModelV2Middleware } from "@ai-sdk/provider";
import {
ExperimentalNotConfiguredError,
UnsupportedAISDKModelProviderError,
UnsupportedModelError,
UnsupportedModelProviderError,
@ -69,37 +70,6 @@ const AISDKProvidersWithAPIKey: Record<string, AISDKCustomProvider> = {
gateway: createGateway,
};
type AISDKProviderClientOptions = ClientOptions & Record<string, unknown>;
export function toAISDKClientOptions(
subProvider: string,
clientOptions?: ClientOptions,
): AISDKProviderClientOptions | undefined {
if (!clientOptions || subProvider !== "vertex") {
return clientOptions as AISDKProviderClientOptions | undefined;
}
const { auth, providerOptions, ...rest } = clientOptions;
const vertexOptions = providerOptions?.vertex;
return {
...rest,
...(vertexOptions ?? {}),
...(auth?.type === "googleServiceAccount"
? {
googleAuthOptions: {
credentials: auth.credentials,
...(auth.scopes ? { scopes: auth.scopes } : {}),
...(auth.projectId ? { projectId: auth.projectId } : {}),
...(auth.universeDomain
? { universeDomain: auth.universeDomain }
: {}),
},
}
: {}),
};
}
const modelToProviderMap: { [key in AvailableModel]: ModelProvider } = {
"gpt-4.1": "openai",
"gpt-4.1-mini": "openai",
@ -136,12 +106,9 @@ export function getAISDKLanguageModel(
clientOptions?: ClientOptions,
middleware?: LanguageModelV2Middleware,
) {
const aiSdkClientOptions = toAISDKClientOptions(subProvider, clientOptions);
const hasValidOptions =
aiSdkClientOptions &&
Object.values(aiSdkClientOptions).some(
(v) => v !== undefined && v !== null,
);
clientOptions &&
Object.values(clientOptions).some((v) => v !== undefined && v !== null);
let model;
if (hasValidOptions) {
@ -152,7 +119,7 @@ export function getAISDKLanguageModel(
Object.keys(AISDKProvidersWithAPIKey),
);
}
const provider = creator(aiSdkClientOptions as ClientOptions);
const provider = creator(clientOptions);
model = provider(subModelName);
} else {
const provider = AISDKProviders[subProvider];
@ -196,6 +163,13 @@ export class LLMProvider {
const firstSlashIndex = modelName.indexOf("/");
const subProvider = modelName.substring(0, firstSlashIndex);
const subModelName = modelName.substring(firstSlashIndex + 1);
if (
subProvider === "vertex" &&
!options?.disableAPI &&
!options?.experimental
) {
throw new ExperimentalNotConfiguredError("Vertex provider");
}
const effectiveMiddleware = options?.middleware ?? this.middleware;
const languageModel = getAISDKLanguageModel(

View File

@ -462,7 +462,6 @@ export const AVAILABLE_CUA_MODELS = [
"openai/computer-use-preview-2025-03-11",
"anthropic/claude-opus-4-5-20251101",
"anthropic/claude-opus-4-6",
"anthropic/claude-opus-4-8",
"anthropic/claude-sonnet-4-6",
"anthropic/claude-haiku-4-5",
"anthropic/claude-haiku-4-5-20251001",

View File

@ -73,13 +73,9 @@ export const GoogleServiceAccountCredentialsSchema = z
.strict()
.meta({ id: "GoogleServiceAccountCredentials" });
export const GoogleServiceAccountAuthSchema = z
export const GoogleAuthOptionsSchema = z
.object({
type: z.literal("googleServiceAccount").meta({
description:
"Use inline Google Cloud service account credentials for provider authentication",
}),
credentials: GoogleServiceAccountCredentialsSchema.meta({
credentials: GoogleServiceAccountCredentialsSchema.optional().meta({
description: "Google Cloud service account credentials",
}),
scopes: z
@ -96,44 +92,18 @@ export const GoogleServiceAccountAuthSchema = z
}),
})
.strict()
.meta({ id: "GoogleServiceAccountAuth" });
.meta({ id: "GoogleAuthOptions" });
export const ModelAuthSchema = z
.discriminatedUnion("type", [GoogleServiceAccountAuthSchema])
.meta({ id: "ModelAuth" });
export const VertexProviderOptionsSchema = z
.object({
project: z.string().meta({
description: "Google Cloud project ID for Vertex AI models",
example: "my-gcp-project",
}),
location: z.string().meta({
description: "Google Cloud location for Vertex AI models",
example: "us-central1",
}),
baseURL: z.string().url().optional().meta({
description: "Base URL for the Vertex AI provider",
}),
headers: z.record(z.string(), z.string()).optional().meta({
description:
"Custom headers sent with every request to the Vertex AI provider",
}),
})
.strict()
.meta({ id: "VertexProviderOptions" });
export const ModelProviderOptionsSchema = z
.object({
vertex: VertexProviderOptionsSchema.meta({
description: "Vertex AI provider-specific settings",
}),
})
.strict()
.meta({ id: "ModelProviderOptions" });
const ModelConfigBaseSchema = z
export const ModelConfigObjectSchema = z
.object({
provider: z
.enum(["openai", "anthropic", "google", "microsoft", "bedrock", "vertex"])
.optional()
.meta({
description:
"AI provider for the model (or provide a baseURL endpoint instead)",
example: "openai",
}),
modelName: z.string().meta({
description:
"Model name string with provider prefix (e.g., 'openai/gpt-5-nano')",
@ -151,38 +121,19 @@ const ModelConfigBaseSchema = z
description:
"Custom headers sent with every request to the model provider",
}),
})
.strict();
export const GenericModelConfigObjectSchema = ModelConfigBaseSchema.extend({
provider: z
.enum(["openai", "anthropic", "google", "microsoft", "bedrock"])
.optional()
.meta({
description:
"AI provider for the model (or provide a baseURL endpoint instead)",
example: "openai",
project: z.string().optional().meta({
description: "Google Cloud project ID for Vertex AI models",
example: "my-gcp-project",
}),
})
.strict()
.meta({ id: "GenericModelConfigObject" });
export const VertexModelConfigObjectSchema = ModelConfigBaseSchema.extend({
provider: z.literal("vertex").meta({
description: "Vertex AI model provider",
}),
auth: ModelAuthSchema.meta({
description: "Vertex provider authentication configuration",
}),
providerOptions: ModelProviderOptionsSchema.meta({
description: "Vertex provider-specific model configuration",
}),
})
.strict()
.meta({ id: "VertexModelConfigObject" });
export const ModelConfigObjectSchema = z
.union([VertexModelConfigObjectSchema, GenericModelConfigObjectSchema])
location: z.string().optional().meta({
description: "Google Cloud location for Vertex AI models",
example: "us-central1",
}),
googleAuthOptions: GoogleAuthOptionsSchema.optional().meta({
description:
"google-auth-library options used to authenticate Vertex AI models",
}),
})
.meta({ id: "ModelConfigObject" });
/** Model configuration */
@ -1210,21 +1161,6 @@ export const Operations = {
// Shared types
export type Action = z.infer<typeof ActionSchema>;
export type ModelConfig = z.infer<typeof ModelConfigSchema>;
export type GenericModelConfigObject = z.infer<
typeof GenericModelConfigObjectSchema
>;
export type VertexModelConfigObject = z.infer<
typeof VertexModelConfigObjectSchema
>;
export type GoogleServiceAccountCredentials = z.infer<
typeof GoogleServiceAccountCredentialsSchema
>;
export type GoogleServiceAccountAuth = z.infer<
typeof GoogleServiceAccountAuthSchema
>;
export type ModelAuth = z.infer<typeof ModelAuthSchema>;
export type VertexProviderOptions = z.infer<typeof VertexProviderOptionsSchema>;
export type ModelProviderOptions = z.infer<typeof ModelProviderOptionsSchema>;
export type BrowserConfig = z.infer<typeof BrowserConfigSchema>;
export type SessionIdParams = z.infer<typeof SessionIdParamsSchema>;

View File

@ -1,4 +1,5 @@
import type { ClientOptions as AnthropicClientOptionsBase } from "@anthropic-ai/sdk";
import type { GoogleVertexProviderSettings as GoogleVertexProviderSettingsBase } from "@ai-sdk/google-vertex";
import type {
LanguageModelV2,
LanguageModelV2Middleware,
@ -30,26 +31,19 @@ export interface GoogleServiceAccountCredentials {
universe_domain?: string;
}
export interface GoogleServiceAccountAuth {
type: "googleServiceAccount";
credentials: GoogleServiceAccountCredentials;
export interface GoogleVertexAuthOptions {
credentials?: GoogleServiceAccountCredentials;
scopes?: string | string[];
projectId?: string;
universeDomain?: string;
}
export type ModelAuth = GoogleServiceAccountAuth;
export interface VertexProviderOptions {
project: string;
location: string;
baseURL?: string;
headers?: Record<string, string>;
}
export interface ModelProviderOptions {
vertex: VertexProviderOptions;
}
export type GoogleVertexProviderSettings = Pick<
GoogleVertexProviderSettingsBase,
"project" | "location" | "headers" | "baseURL"
> & {
googleAuthOptions?: GoogleVertexAuthOptions;
};
export type AnthropicJsonSchemaObject = {
definitions?: {
@ -119,11 +113,13 @@ export type ModelProvider =
*/
export type ThinkingEffort = "none" | "low" | "medium" | "high" | "max";
export type ClientOptions = (OpenAIClientOptions | AnthropicClientOptions) & {
export type ClientOptions = (
| OpenAIClientOptions
| AnthropicClientOptions
| GoogleVertexProviderSettings
) & {
apiKey?: string;
provider?: AgentProviderType;
auth?: ModelAuth;
providerOptions?: ModelProviderOptions;
baseURL?: string;
/** OpenAI organization ID */
organization?: string;

View File

@ -538,26 +538,6 @@ export class V3 {
);
}
private getApiDefaultModelConfig(): ModelConfiguration | undefined {
const clientOptions = Object.fromEntries(
Object.entries(this.modelClientOptions).filter(
([key, value]) => key !== "apiKey" && value !== undefined,
),
);
if (Object.keys(clientOptions).length === 0) {
return undefined;
}
return {
modelName: this.modelName,
...clientOptions,
...((this.modelClientOptions as { apiKey?: string }).apiKey
? { apiKey: (this.modelClientOptions as { apiKey?: string }).apiKey }
: {}),
} as ModelConfiguration;
}
private resolveLlmClient(model?: ModelConfiguration): LLMClient {
if (!model) {
return this.llmClient;
@ -1063,7 +1043,6 @@ export class V3 {
const { sessionId, available } = await this.apiClient.init({
modelName: this.modelName,
modelApiKey: this.modelClientOptions.apiKey,
defaultModelConfig: this.getApiDefaultModelConfig(),
domSettleTimeoutMs: this.domSettleTimeoutMs,
verbose: this.verbose,
systemPrompt: this.opts.systemPrompt,

View File

@ -36,30 +36,7 @@ describe("AnthropicCUAClient adaptive thinking", () => {
});
});
describe("Claude 4.6+ models (adaptive thinking)", () => {
it("should use thinking.type: 'adaptive' for claude-opus-4-8 when thinkingEffort is set", async () => {
const client = new AnthropicCUAClient(
"anthropic",
"claude-opus-4-8",
undefined,
{
apiKey: "test-key",
thinkingEffort: "high",
},
);
client.setViewport(1280, 720);
await client.getAction([{ role: "user", content: "test" }]);
expect(mockCreate).toHaveBeenCalledWith(
expect.objectContaining({
thinking: { type: "adaptive" },
output_config: { effort: "high" },
temperature: 1,
}),
);
});
describe("Claude 4.6 models (adaptive thinking)", () => {
it("should use thinking.type: 'adaptive' for claude-opus-4-6 when thinkingEffort is set", async () => {
const client = new AnthropicCUAClient(
"anthropic",

View File

@ -1,342 +0,0 @@
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { StagehandAPIClient } from "../../lib/v3/api.js";
import type { ModelConfiguration } from "../../lib/v3/types/public/model.js";
const vertexModel = {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
} as unknown as ModelConfiguration;
function createClientWithExecuteMock() {
const client = new StagehandAPIClient({
apiKey: "bb-test",
logger: vi.fn(),
});
const executeMock = vi.fn().mockResolvedValue({});
(
client as unknown as {
execute: typeof executeMock;
}
).execute = executeMock;
return { client, executeMock };
}
describe("StagehandAPIClient default model config", () => {
let originalFetch: typeof globalThis.fetch;
beforeEach(() => {
originalFetch = globalThis.fetch;
globalThis.fetch = vi.fn().mockResolvedValue(
new Response(
JSON.stringify({
success: true,
data: { sessionId: "sess-default-model", available: true },
}),
{
status: 200,
headers: { "Content-Type": "application/json" },
},
),
);
});
afterEach(() => {
globalThis.fetch = originalFetch;
vi.restoreAllMocks();
});
it("sends constructor Vertex model config on navigate bootstrap, act, observe, extract, and agent execute requests", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "vertex/gemini-2.5-flash",
defaultModelConfig: vertexModel,
});
await client.goto("https://example.com");
await client.act({ input: "click the login button" });
await client.observe({ instruction: "find the login button" });
await client.extract({ instruction: "extract the headline" });
await client.agentExecute({ mode: "dom" }, "click the login button");
expect(executeMock).toHaveBeenNthCalledWith(
1,
expect.objectContaining({
method: "navigate",
args: expect.objectContaining({
options: {
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
},
}),
}),
);
expect(executeMock).toHaveBeenNthCalledWith(
2,
expect.objectContaining({
method: "act",
args: expect.objectContaining({
options: {
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
},
}),
}),
);
expect(executeMock).toHaveBeenNthCalledWith(
3,
expect.objectContaining({
method: "observe",
args: expect.objectContaining({
options: expect.objectContaining({
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
}),
}),
}),
);
expect(executeMock).toHaveBeenNthCalledWith(
4,
expect.objectContaining({
method: "extract",
args: expect.objectContaining({
options: expect.objectContaining({
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
}),
}),
}),
);
expect(executeMock).toHaveBeenNthCalledWith(
5,
expect.objectContaining({
method: "agentExecute",
args: expect.objectContaining({
agentConfig: expect.objectContaining({
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
}),
}),
}),
);
});
it("prefers a per-call model over the constructor default model config", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "vertex/gemini-2.5-flash",
defaultModelConfig: vertexModel,
});
await client.act({
input: "click the login button",
options: {
model: {
modelName: "openai/gpt-4.1-mini",
apiKey: "sk-per-call",
},
},
});
expect(executeMock).toHaveBeenCalledWith(
expect.objectContaining({
args: expect.objectContaining({
options: expect.objectContaining({
model: {
modelName: "openai/gpt-4.1-mini",
apiKey: "sk-per-call",
},
}),
}),
}),
);
});
it("inherits constructor Vertex auth for a same-provider string model override", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "vertex/gemini-2.5-flash",
defaultModelConfig: vertexModel,
});
await client.observe({
instruction: "find the login button",
options: {
model: "vertex/gemini-2.0-flash",
},
});
expect(executeMock).toHaveBeenCalledWith(
expect.objectContaining({
method: "observe",
args: expect.objectContaining({
options: expect.objectContaining({
model: expect.objectContaining({
modelName: "vertex/gemini-2.0-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
}),
}),
}),
);
});
it("does not treat model as a public navigate option", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "openai/gpt-4.1-mini",
modelApiKey: "sk-header-only",
});
await client.goto("https://example.com", {
model: {
modelName: "openai/gpt-4o",
apiKey: "sk-per-call",
},
} as unknown as Parameters<StagehandAPIClient["goto"]>[1]);
expect(executeMock).toHaveBeenCalledWith(
expect.objectContaining({
method: "navigate",
args: expect.objectContaining({
options: undefined,
}),
}),
);
});
it("keeps constructor bootstrap config when a caller passes an unsupported navigate model", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "vertex/gemini-2.5-flash",
defaultModelConfig: vertexModel,
});
await client.goto("https://example.com", {
model: {
modelName: "openai/gpt-4o",
apiKey: "sk-per-call",
},
} as unknown as Parameters<StagehandAPIClient["goto"]>[1]);
expect(executeMock).toHaveBeenCalledWith(
expect.objectContaining({
method: "navigate",
args: expect.objectContaining({
options: {
model: expect.objectContaining({
modelName: "vertex/gemini-2.5-flash",
auth: expect.objectContaining({
type: "googleServiceAccount",
}),
providerOptions: {
vertex: expect.objectContaining({
project: "test-gcp-project",
location: "us-central1",
}),
},
}),
},
}),
}),
);
});
it("does not add a body model config when the constructor only provides a model API key", async () => {
const { client, executeMock } = createClientWithExecuteMock();
await client.init({
modelName: "openai/gpt-4.1-mini",
modelApiKey: "sk-header-only",
});
await client.act({ input: "click the login button" });
expect(executeMock).toHaveBeenCalledWith(
expect.objectContaining({
args: expect.objectContaining({
options: undefined,
}),
}),
);
});
});

View File

@ -73,8 +73,9 @@ describe("API model config schemas", () => {
const vertexModel = {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
project: "test-gcp-project",
location: "us-central1",
googleAuthOptions: {
credentials: {
type: "service_account",
project_id: "test-gcp-project",
@ -88,12 +89,6 @@ describe("API model config schemas", () => {
projectId: "test-gcp-project",
universeDomain: "googleapis.com",
},
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
};
it("preserves Vertex auth params for act requests", () => {
@ -116,20 +111,15 @@ describe("API model config schemas", () => {
model: {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
project: "test-gcp-project",
location: "us-central1",
googleAuthOptions: {
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
},
},
});
@ -141,11 +131,7 @@ describe("API model config schemas", () => {
if (typeof parsedModel !== "object" || parsedModel === null) {
throw new Error("Expected object model config");
}
if (!("auth" in parsedModel)) {
throw new Error("Expected Vertex auth config");
}
expect(parsedModel.auth).toEqual({
type: "googleServiceAccount",
expect(parsedModel.googleAuthOptions).toEqual({
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
@ -154,67 +140,6 @@ describe("API model config schemas", () => {
});
});
it("requires explicit Vertex provider configs to include service account auth and provider options", () => {
for (const model of [
{
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
},
{
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
},
]) {
const result = Api.ActRequestSchema.safeParse({
input: "click the search button",
options: { model },
});
expect(result.success).toBe(false);
}
});
it("requires provider vertex when passing Vertex auth and provider options", () => {
const result = Api.ActRequestSchema.safeParse({
input: "click the search button",
options: {
model: {
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
},
},
});
expect(result.success).toBe(false);
});
it("preserves Vertex auth params for agent model configs", () => {
const result = Api.AgentExecuteRequestSchema.safeParse({
agentConfig: {
@ -233,20 +158,6 @@ describe("API model config schemas", () => {
});
it("rejects Vertex key file paths and external credential sources", () => {
const topLevelLegacyShape = Api.ActRequestSchema.safeParse({
input: "click the search button",
options: {
model: {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
project: "test-gcp-project",
location: "us-central1",
googleAuthOptions: {},
},
},
});
expect(topLevelLegacyShape.success).toBe(false);
for (const blockedAuthOptions of [
{ keyFilename: "/etc/passwd" },
{ keyFile: "/etc/passwd" },
@ -258,7 +169,7 @@ describe("API model config schemas", () => {
model: {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: blockedAuthOptions,
googleAuthOptions: blockedAuthOptions,
},
},
});
@ -272,8 +183,7 @@ describe("API model config schemas", () => {
model: {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
googleAuthOptions: {
credentials: {
type: "external_account",
credential_source: {

View File

@ -1,9 +1,5 @@
import { describe, expect, it } from "vitest";
import {
getAISDKLanguageModel,
LLMProvider,
toAISDKClientOptions,
} from "../../lib/v3/llm/LLMProvider.js";
import { getAISDKLanguageModel } from "../../lib/v3/llm/LLMProvider.js";
describe("getAISDKLanguageModel", () => {
describe("ollama provider", () => {
@ -72,67 +68,3 @@ describe("getAISDKLanguageModel", () => {
});
});
});
describe("LLMProvider", () => {
it("allows Vertex models without experimental mode", () => {
const provider = new LLMProvider(() => {});
expect(() =>
provider.getClient(
"vertex/gemini-2.5-flash" as never,
{
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "stagehand@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\ntest\n-----END PRIVATE KEY-----\n",
},
},
providerOptions: {
vertex: {
project: "test-project",
location: "us-central1",
},
},
} as never,
{ experimental: false, disableAPI: false },
),
).not.toThrow();
});
it("adapts canonical Vertex auth into AI SDK googleAuthOptions", () => {
expect(
toAISDKClientOptions("vertex", {
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "stagehand@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\ntest\n-----END PRIVATE KEY-----\n",
},
projectId: "test-project",
universeDomain: "googleapis.com",
},
providerOptions: {
vertex: {
project: "test-project",
location: "us-central1",
},
},
}),
).toEqual({
project: "test-project",
location: "us-central1",
googleAuthOptions: {
credentials: {
client_email: "stagehand@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\ntest\n-----END PRIVATE KEY-----\n",
},
projectId: "test-project",
universeDomain: "googleapis.com",
},
});
});
});

View File

@ -3,30 +3,17 @@ import * as Stagehand from "@browserbasehq/stagehand";
describe("LLM and Agents public API types", () => {
describe("ModelConfiguration", () => {
it("accepts Vertex provider options in model config", () => {
const vertexConfig = {
provider: "vertex",
modelName: "vertex/gemini-3-flash-preview",
it("accepts Vertex headers in model config", () => {
const googleConfig = {
modelName: "google/gemini-3-flash-preview",
project: "test-project",
location: "global",
headers: {
"X-Goog-Priority": "high",
},
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
providerOptions: {
vertex: {
project: "test-project",
location: "global",
},
},
} satisfies Stagehand.ModelConfiguration;
void vertexConfig;
void googleConfig;
});
});
@ -57,7 +44,6 @@ describe("LLM and Agents public API types", () => {
"openai/gpt-5.5",
"anthropic/claude-opus-4-5-20251101",
"anthropic/claude-opus-4-6",
"anthropic/claude-opus-4-8",
"anthropic/claude-sonnet-4-6",
"anthropic/claude-haiku-4-5",
"anthropic/claude-haiku-4-5-20251001",
@ -75,12 +61,6 @@ describe("LLM and Agents public API types", () => {
>();
void expectedModels; // Mark as used to satisfy ESLint
});
it("includes Claude Opus 4.8 at runtime", () => {
expect(Stagehand.AVAILABLE_CUA_MODELS).toContain(
"anthropic/claude-opus-4-8",
);
});
});
describe("AgentProvider", () => {
@ -294,12 +274,6 @@ describe("LLM and Agents public API types", () => {
typeof Stagehand.modelToAgentProviderMap
>().toExtend<ExpectedModelToAgentProviderMap>();
});
it("routes Claude Opus 4.8 to Anthropic", () => {
expect(Stagehand.modelToAgentProviderMap["claude-opus-4-8"]).toBe(
"anthropic",
);
});
});
describe("Response", () => {

View File

@ -669,7 +669,6 @@ const agent = stagehand.agent({
| Anthropic | `anthropic/claude-sonnet-4-5-20250929` |
| Anthropic | `anthropic/claude-opus-4-5-20251101` |
| Anthropic | `anthropic/claude-opus-4-6` |
| Anthropic | `anthropic/claude-opus-4-8` |
| Google | `google/gemini-2.5-computer-use-preview-10-2025` |
| Google | `google/gemini-3-flash-preview` |
| Google | `google/gemini-3-pro-preview` |

View File

@ -72,7 +72,6 @@ interface AgentInstance {
- `"anthropic/claude-sonnet-4-5-20250929"`
- `"anthropic/claude-opus-4-5-20251101"`
- `"anthropic/claude-opus-4-6"`
- `"anthropic/claude-opus-4-8"`
- `"google/gemini-2.5-computer-use-preview-10-2025"`
- `"google/gemini-3-flash-preview"`
- `"google/gemini-3-pro-preview"`
@ -868,4 +867,4 @@ The following errors may be thrown by the `agent()` method:
- **StagehandDefaultError** - General execution error with detailed message
- **AgentAbortError** - Thrown when agent execution is cancelled via an `AbortSignal`
- **StreamingCallbacksInNonStreamingModeError** - Thrown when streaming-only callbacks (`onChunk`, `onFinish`, `onError`, `onAbort`) are used without `stream: true`
- **ExperimentalNotConfiguredError** - Thrown when experimental features (callbacks, signal, messages, streaming) are used without `experimental: true` in Stagehand constructor
- **ExperimentalNotConfiguredError** - Thrown when experimental features (callbacks, signal, messages, streaming) are used without `experimental: true` in Stagehand constructor

View File

@ -202,14 +202,9 @@ components:
- private_key
- client_email
additionalProperties: false
GoogleServiceAccountAuth:
GoogleAuthOptions:
type: object
properties:
type:
description: Use inline Google Cloud service account credentials for provider
authentication
type: string
const: googleServiceAccount
credentials:
description: Google Cloud service account credentials
$ref: "#/components/schemas/GoogleServiceAccountCredentials"
@ -226,71 +221,10 @@ components:
universeDomain:
description: Google Cloud universe domain
type: string
required:
- type
- credentials
additionalProperties: false
ModelAuth:
oneOf:
- $ref: "#/components/schemas/GoogleServiceAccountAuth"
VertexProviderOptions:
ModelConfigObject:
type: object
properties:
project:
description: Google Cloud project ID for Vertex AI models
example: my-gcp-project
type: string
location:
description: Google Cloud location for Vertex AI models
example: us-central1
type: string
baseURL:
description: Base URL for the Vertex AI provider
type: string
format: uri
headers:
description: Custom headers sent with every request to the Vertex AI provider
type: object
propertyNames:
type: string
additionalProperties:
type: string
required:
- project
- location
additionalProperties: false
ModelProviderOptions:
type: object
properties:
vertex:
description: Vertex AI provider-specific settings
$ref: "#/components/schemas/VertexProviderOptions"
required:
- vertex
additionalProperties: false
GenericModelConfigObject:
type: object
properties:
modelName:
description: Model name string with provider prefix (e.g., 'openai/gpt-5-nano')
example: openai/gpt-5.4-mini
type: string
apiKey:
description: API key for the model provider
example: sk-some-openai-api-key
type: string
baseURL:
description: Base URL for the model provider
example: https://api.openai.com/v1
type: string
format: uri
headers:
description: Custom headers sent with every request to the model provider
type: object
propertyNames:
type: string
additionalProperties:
type: string
provider:
description: AI provider for the model (or provide a baseURL endpoint instead)
example: openai
@ -301,12 +235,7 @@ components:
- google
- microsoft
- bedrock
required:
- modelName
additionalProperties: false
VertexModelConfigObject:
type: object
properties:
- vertex
modelName:
description: Model name string with provider prefix (e.g., 'openai/gpt-5-nano')
example: openai/gpt-5.4-mini
@ -327,26 +256,19 @@ components:
type: string
additionalProperties:
type: string
provider:
description: Vertex AI model provider
project:
description: Google Cloud project ID for Vertex AI models
example: my-gcp-project
type: string
const: vertex
auth:
description: Vertex provider authentication configuration
$ref: "#/components/schemas/ModelAuth"
providerOptions:
description: Vertex provider-specific model configuration
$ref: "#/components/schemas/ModelProviderOptions"
location:
description: Google Cloud location for Vertex AI models
example: us-central1
type: string
googleAuthOptions:
description: google-auth-library options used to authenticate Vertex AI models
$ref: "#/components/schemas/GoogleAuthOptions"
required:
- modelName
- provider
- auth
- providerOptions
additionalProperties: false
ModelConfigObject:
anyOf:
- $ref: "#/components/schemas/VertexModelConfigObject"
- $ref: "#/components/schemas/GenericModelConfigObject"
ModelConfig:
$ref: "#/components/schemas/ModelConfigObject"
Action:
@ -1397,6 +1319,56 @@ components:
acceptDownloads:
type: boolean
additionalProperties: false
ModelConfigObjectOutput:
type: object
properties:
provider:
description: AI provider for the model (or provide a baseURL endpoint instead)
example: openai
type: string
enum:
- openai
- anthropic
- google
- microsoft
- bedrock
- vertex
modelName:
description: Model name string with provider prefix (e.g., 'openai/gpt-5-nano')
example: openai/gpt-5.4-mini
type: string
apiKey:
description: API key for the model provider
example: sk-some-openai-api-key
type: string
baseURL:
description: Base URL for the model provider
example: https://api.openai.com/v1
type: string
format: uri
headers:
description: Custom headers sent with every request to the model provider
type: object
propertyNames:
type: string
additionalProperties:
type: string
project:
description: Google Cloud project ID for Vertex AI models
example: my-gcp-project
type: string
location:
description: Google Cloud location for Vertex AI models
example: us-central1
type: string
googleAuthOptions:
description: google-auth-library options used to authenticate Vertex AI models
$ref: "#/components/schemas/GoogleAuthOptions"
required:
- modelName
additionalProperties: false
ModelConfigOutput:
$ref: "#/components/schemas/ModelConfigObjectOutput"
ActionOutput:
description: Action object returned by observe and used by act
type: object
@ -1661,7 +1633,7 @@ components:
description: Model configuration object or model name string (e.g.,
'openai/gpt-5-nano')
anyOf:
- $ref: "#/components/schemas/ModelConfig"
- $ref: "#/components/schemas/ModelConfigOutput"
- type: string
variables:
description: Variables to substitute in the action instruction. Accepts flat
@ -1721,7 +1693,7 @@ components:
description: Model configuration object or model name string (e.g.,
'openai/gpt-5-nano')
anyOf:
- $ref: "#/components/schemas/ModelConfig"
- $ref: "#/components/schemas/ModelConfigOutput"
- type: string
timeout:
description: Timeout in ms for the extraction
@ -1766,7 +1738,7 @@ components:
description: Model configuration object or model name string (e.g.,
'openai/gpt-5-nano')
anyOf:
- $ref: "#/components/schemas/ModelConfig"
- $ref: "#/components/schemas/ModelConfigOutput"
- type: string
variables:
description: Variables whose names are exposed to the model so observe() returns
@ -1829,7 +1801,7 @@ components:
description: Model configuration object or model name string (e.g.,
'openai/gpt-5-nano')
anyOf:
- $ref: "#/components/schemas/ModelConfig"
- $ref: "#/components/schemas/ModelConfigOutput"
- type: string
systemPrompt:
description: Custom system prompt for the agent
@ -1853,7 +1825,7 @@ components:
agent tools). If not specified, inherits from the main model
configuration.
anyOf:
- $ref: "#/components/schemas/ModelConfig"
- $ref: "#/components/schemas/ModelConfigOutput"
- type: string
additionalProperties: false
AgentUsageOutput:

View File

@ -12,7 +12,7 @@
* SEA_INCLUDE_SOURCEMAPS.
* Example: pnpm run build:sea:cjs -- --target-platform=linux --target-arch=arm64
*/
import { execFileSync, spawnSync } from "node:child_process";
import { spawnSync } from "node:child_process";
import { createHash } from "node:crypto";
import fs from "node:fs";
import os from "node:os";
@ -87,17 +87,6 @@ const includeSourcemaps = parseBoolean(
false,
);
const gitOutput = (args: string[]) =>
execFileSync("git", args, { cwd: repoDir, encoding: "utf8" }).trim();
const buildCommit = gitOutput(["rev-parse", "HEAD"]);
const seaVersion = [
`commit: ${buildCommit}`,
`timestamp: ${gitOutput(["show", "-s", "--format=%cI", buildCommit])}`,
].join("\n");
const seaBuildDefine = {
__STAGEHAND_SERVER_VERSION__: JSON.stringify(seaVersion),
};
const run = (cmd: string, args: string[], opts: { cwd?: string } = {}) => {
const result = spawnSync(cmd, args, { stdio: "inherit", ...opts });
if (result.error) {
@ -284,7 +273,6 @@ const buildCjsBundle = () => {
platform: "node",
format: "cjs",
outfile: bundlePath,
define: seaBuildDefine,
logLevel: "warning",
absWorkingDir: repoDir,
});
@ -307,7 +295,6 @@ const buildEsmBundle = () => {
format: "esm",
treeShaking: false,
outfile: appBundlePath,
define: seaBuildDefine,
alias: {
"@browserbasehq/stagehand": `${repoDir}/packages/core/dist/esm/index.js`,
},
@ -425,15 +412,6 @@ const { pathToFileURL } = require("node:url");
const bundleBase64 = ${JSON.stringify(appBytes.toString("base64"))};
const bundleLength = ${appBytes.length};
const bundleHash = ${JSON.stringify(bundleHash)};
const versionOutput = ${JSON.stringify(seaVersion)};
const argv = process.argv.slice(1);
const normalizedArgv = argv[0]?.startsWith("--") ? argv : argv.slice(1);
if (normalizedArgv.includes("--version")) {
console.log(versionOutput);
process.exit(0);
}
const cacheRoot =
process.env.STAGEHAND_SEA_CACHE_DIR ||

View File

@ -44,12 +44,7 @@ async function main() {
LocalBrowserLaunchOptions: Api.LocalBrowserLaunchOptionsSchema,
GoogleServiceAccountCredentials:
Api.GoogleServiceAccountCredentialsSchema,
GoogleServiceAccountAuth: Api.GoogleServiceAccountAuthSchema,
ModelAuth: Api.ModelAuthSchema,
VertexProviderOptions: Api.VertexProviderOptionsSchema,
ModelProviderOptions: Api.ModelProviderOptionsSchema,
GenericModelConfigObject: Api.GenericModelConfigObjectSchema,
VertexModelConfigObject: Api.VertexModelConfigObjectSchema,
GoogleAuthOptions: Api.GoogleAuthOptionsSchema,
ModelConfigObject: Api.ModelConfigObjectSchema,
ModelConfig: Api.ModelConfigSchema,
Action: Api.ActionSchema,

View File

@ -208,17 +208,10 @@ export class InMemorySessionStore implements SessionStore {
const options: V3Options = {
env: isBrowserbase ? "BROWSERBASE" : "LOCAL",
model: ctx.requestModelConfig
? {
...ctx.requestModelConfig,
...(ctx.requestModelConfig.apiKey
? {}
: { apiKey: ctx.modelApiKey }),
}
: {
modelName: params.modelName,
apiKey: ctx.modelApiKey,
},
model: {
modelName: params.modelName,
apiKey: ctx.modelApiKey,
},
verbose: params.verbose,
systemPrompt: params.systemPrompt,
selfHeal: params.selfHeal,

View File

@ -67,8 +67,6 @@ export interface CreateSessionParams {
export interface RequestContext {
/** Model API key (from x-model-api-key header) */
modelApiKey?: string;
/** Structured model config from the current request body */
requestModelConfig?: Api.ModelConfig;
/** Logger function for this request */
logger?: (message: LogLine) => void;
}

View File

@ -1,6 +1,4 @@
import type { FastifyRequest } from "fastify";
import { Api } from "@browserbasehq/stagehand";
import { z } from "zod/v4";
import { MissingHeaderError } from "../types/error.js";
@ -41,134 +39,41 @@ export const getOptionalHeader = (
return headerValue;
};
const emptyStringSchema = z.literal("").transform((): undefined => undefined);
const requiredStringSchema = z.string().min(1);
const optionalStringSchema = z
.union([emptyStringSchema, z.string()])
.optional();
const requestModelInputSchema = z
.union([
emptyStringSchema,
requiredStringSchema.transform(
(modelName): Api.ModelConfig => ({ modelName }),
),
Api.ModelConfigSchema,
])
.optional();
const requestModelCarrierSchema = z
.object({
model: requestModelInputSchema,
})
.passthrough();
const unparsedModelCarrierSchema = z
.object({
model: z.unknown().optional(),
})
.passthrough();
const requestModelEnvelopeSchema = z
.object({
options: requestModelCarrierSchema.optional(),
agentConfig: unparsedModelCarrierSchema.optional(),
modelName: optionalStringSchema,
})
.passthrough();
const stagehandInitModelEnvelopeSchema = z
.object({
options: requestModelCarrierSchema.optional(),
agentConfig: requestModelCarrierSchema.optional(),
modelName: optionalStringSchema,
})
.passthrough();
const requestModelConfigSchema = z
.object({
model: Api.ModelConfigSchema.optional(),
modelName: optionalStringSchema,
apiKey: optionalStringSchema,
})
.strict();
export type RequestModelConfig = z.infer<typeof requestModelConfigSchema>;
type RequestModelConfigResult =
| { success: true; data: RequestModelConfig }
| { success: false; error: z.ZodError };
/**
* Extracts request-level model config with precedence.
*
* Model name:
* 1. body.options.model.modelName or body.options.model string
* 2. Legacy body.modelName fallback
*
* API key:
* 1. body.options.model.apiKey
* 2. x-model-api-key header
*
* agentConfig.model is parsed separately for Stagehand initialization. Its
* credentials are scoped to the agent main model and must not become the
* request-level API key fallback used by action/execution models.
* Extracts model name from request body, supporting V3 structure.
* - V3: body.options.model.modelName
*/
export function getRequestModelConfig(
request: FastifyRequest,
): RequestModelConfigResult {
const bodyResult = requestModelEnvelopeSchema.safeParse(request.body ?? {});
if (!bodyResult.success) {
return bodyResult;
export function getModelName(request: FastifyRequest): string | undefined {
const body = request.body as Record<string, unknown> | undefined;
const options = body?.options as Record<string, unknown> | undefined;
const model = options?.model as Record<string, unknown> | undefined;
if (typeof model?.modelName === "string" && model.modelName) {
return model.modelName;
}
const body = bodyResult.data;
const model = body.options?.model;
const configResult = requestModelConfigSchema.safeParse({
model,
modelName: model?.modelName ?? body.modelName,
apiKey: model?.apiKey ?? getOptionalHeader(request, "x-model-api-key"),
});
if (!configResult.success) {
return configResult;
if (typeof body?.modelName === "string" && body.modelName) {
return body.modelName;
}
return configResult;
return undefined;
}
/**
* Extracts the structured model config used when creating a Stagehand instance
* for this request. This can read agentConfig.model for agentExecute startup,
* but it does not promote agent model credentials to the request-level API key.
* Extracts the model API key with precedence:
* 1. Per-request body apiKey (V3: body.options.model.apiKey)
* 2. Per-request header x-model-api-key
*/
export function getStagehandInitModelConfig(
request: FastifyRequest,
requestModelConfig?: RequestModelConfig,
): RequestModelConfigResult {
const baseConfigResult = requestModelConfig
? requestModelConfigSchema.safeParse(requestModelConfig)
: getRequestModelConfig(request);
if (!baseConfigResult.success) {
return baseConfigResult;
export function getModelApiKey(request: FastifyRequest): string | undefined {
const body = request.body as Record<string, unknown> | undefined;
const options = body?.options as Record<string, unknown> | undefined;
const model = options?.model as Record<string, unknown> | undefined;
if (typeof model?.apiKey === "string" && model.apiKey) {
return model.apiKey;
}
const baseConfig = baseConfigResult.data;
if (baseConfig.model) {
return baseConfigResult;
}
const bodyResult = stagehandInitModelEnvelopeSchema.safeParse(
request.body ?? {},
);
if (!bodyResult.success) {
return bodyResult;
}
const agentModel = bodyResult.data.agentConfig?.model;
const configResult = requestModelConfigSchema.safeParse({
model: agentModel,
modelName: agentModel?.modelName ?? baseConfig.modelName,
apiKey: baseConfig.apiKey,
});
if (!configResult.success) {
return configResult;
}
return configResult;
return getOptionalHeader(request, "x-model-api-key");
}
/**

View File

@ -6,11 +6,10 @@ import { z } from "zod/v4";
import { AppError } from "./errorHandler.js";
import {
getModelApiKey,
getModelName,
getOptionalHeader,
getRequestModelConfig,
getStagehandInitModelConfig,
shouldRespondWithSSE,
type RequestModelConfig,
} from "./header.js";
import { error, success } from "./response.js";
import { getSessionStore } from "./sessionStoreManager.js";
@ -36,13 +35,6 @@ type StreamEventName =
| "error";
type StreamPayloadType = "system" | "log";
function formatZodIssues(err: z.ZodError) {
return err.issues.map((issue) => ({
path: issue.path[0] ?? "unknown",
message: issue.message,
}));
}
export async function createStreamingResponse<TV3>({
sessionId,
request,
@ -52,6 +44,7 @@ export async function createStreamingResponse<TV3>({
operation,
}: StreamingResponseOptions<TV3>) {
const shouldStreamResponse = shouldRespondWithSSE(request);
const modelApiKey = getModelApiKey(request);
const sessionStore = getSessionStore();
const sessionConfig = await sessionStore.getSessionConfig(sessionId);
@ -134,45 +127,9 @@ export async function createStreamingResponse<TV3>({
const actionId = v4();
sendData("starting", "system", { status: "starting" });
const sendZodValidationError = (err: z.ZodError) => {
const validationIssues = formatZodIssues(err);
if (shouldStreamResponse) {
sendData("error", "system", {
status: "error",
error: validationIssues,
});
reply.raw.end();
return reply;
}
return reply.status(StatusCodes.BAD_REQUEST).send({
error: validationIssues,
});
};
const requestModelConfigResult = getRequestModelConfig(request);
if (requestModelConfigResult.success === false) {
return sendZodValidationError(requestModelConfigResult.error);
}
const requestModelConfig: RequestModelConfig = requestModelConfigResult.data;
const stagehandInitModelConfigResult = getStagehandInitModelConfig(
request,
requestModelConfig,
);
if (stagehandInitModelConfigResult.success === false) {
return sendZodValidationError(stagehandInitModelConfigResult.error);
}
const stagehandInitModelConfig = stagehandInitModelConfigResult.data;
const modelApiKey = requestModelConfig.apiKey;
const parsedRequestModelConfig = stagehandInitModelConfig.model?.modelName
? stagehandInitModelConfig.model
: undefined;
const requestContext: RequestContext = {
modelApiKey,
requestModelConfig: parsedRequestModelConfig,
logger: shouldStreamResponse
? (message) => {
sendData("running", "log", { status: "running", message });
@ -220,7 +177,7 @@ export async function createStreamingResponse<TV3>({
operation: operation ?? "operation",
sessionId,
browserType,
modelName: requestModelConfig.modelName,
modelName: getModelName(request),
hasModelApiKey: Boolean(modelApiKey),
hasBrowserbaseApiKey: Boolean(browserbaseApiKey),
hasBrowserbaseProjectId: Boolean(browserbaseProjectId),

View File

@ -8,10 +8,7 @@ import { z } from "zod/v4";
import { authMiddleware } from "../../../lib/auth.js";
import { withErrorHandling } from "../../../lib/errorHandler.js";
import {
getOptionalHeader,
getRequestModelConfig,
} from "../../../lib/header.js";
import { getModelApiKey, getOptionalHeader } from "../../../lib/header.js";
import { error, success } from "../../../lib/response.js";
import { getSessionStore } from "../../../lib/sessionStoreManager.js";
import { AISDK_PROVIDERS } from "../../../types/model.js";
@ -113,30 +110,11 @@ const startRouteHandler: RouteHandler = withErrorHandling(
}
const browserType = browser?.type ?? "browserbase";
const localBrowserLaunchOptions =
browserType === "local" && browser?.launchOptions && !browser?.cdpUrl
? browser.launchOptions
: undefined;
let bbApiKey: string | undefined;
let browserbaseProjectId: string | undefined;
let browserbaseSessionId: string | undefined;
let connectUrl: string | undefined;
let localBrowserModelApiKey: string | undefined;
if (localBrowserLaunchOptions) {
const requestModelConfigResult = getRequestModelConfig(request);
if (requestModelConfigResult.success === false) {
return reply.status(StatusCodes.BAD_REQUEST).send({
error: requestModelConfigResult.error.issues.map((issue) => ({
path: issue.path[0] ?? "unknown",
message: issue.message,
})),
});
}
localBrowserModelApiKey = requestModelConfigResult.data.apiKey;
}
if (browserType === "browserbase") {
bbApiKey = getOptionalHeader(request, "x-bb-api-key");
@ -232,11 +210,12 @@ const startRouteHandler: RouteHandler = withErrorHandling(
// For local browsers with launchOptions (no explicit cdpUrl), eagerly
// initialize the browser so we can return the actual CDP URL
let finalCdpUrl = connectUrl ?? session.cdpUrl ?? "";
if (localBrowserLaunchOptions) {
if (browserType === "local" && browser?.launchOptions && !browser?.cdpUrl) {
const modelApiKey = getModelApiKey(request);
try {
const stagehand = await sessionStore.getOrCreateStagehand(
session.sessionId,
{ modelApiKey: localBrowserModelApiKey },
{ modelApiKey },
);
finalCdpUrl = stagehand.connectURL();
} catch (err) {
@ -247,12 +226,12 @@ const startRouteHandler: RouteHandler = withErrorHandling(
browserType,
chromePathEnv: process.env.CHROME_PATH,
launchOptions: {
executablePath: localBrowserLaunchOptions.executablePath,
argsCount: localBrowserLaunchOptions.args?.length ?? 0,
headless: localBrowserLaunchOptions.headless,
hasUserDataDir: Boolean(localBrowserLaunchOptions.userDataDir),
port: localBrowserLaunchOptions.port,
connectTimeoutMs: localBrowserLaunchOptions.connectTimeoutMs,
executablePath: browser.launchOptions.executablePath,
argsCount: browser.launchOptions.args?.length ?? 0,
headless: browser.launchOptions.headless,
hasUserDataDir: Boolean(browser.launchOptions.userDataDir),
port: browser.launchOptions.port,
connectTimeoutMs: browser.launchOptions.connectTimeoutMs,
},
},
"Failed to initialize local browser session in /v1/sessions/start",

View File

@ -1,23 +1,15 @@
declare const __STAGEHAND_SERVER_VERSION__: string;
import { __internalMaybeRunShutdownSupervisorFromArgv } from "@browserbasehq/stagehand";
// if SEA binary is launched with --supervisor, it will run the shutdown supervisor only
const argv = process.argv.slice(1);
const normalizedArgv = argv[0]?.startsWith("--") ? argv : argv.slice(1);
if (normalizedArgv.includes("--version")) {
console.log(__STAGEHAND_SERVER_VERSION__);
process.exit(0);
}
void import("@browserbasehq/stagehand")
.then(async ({ __internalMaybeRunShutdownSupervisorFromArgv }) => {
if (__internalMaybeRunShutdownSupervisorFromArgv(normalizedArgv)) {
return;
}
process.env.BROWSERBASE_FLOW_LOGS = "1";
await import("./server.js");
})
.catch((err) => {
// otherwise, start the stagehand/server
if (!__internalMaybeRunShutdownSupervisorFromArgv(normalizedArgv)) {
// Force flow logs on before the server module loads Stagehand core.
process.env.BROWSERBASE_FLOW_LOGS = "1";
void import("./server.js").catch((err) => {
console.error("Failed to start server:", err);
process.exit(1);
});
}

View File

@ -1,120 +0,0 @@
import assert from "node:assert/strict";
import { describe, it } from "node:test";
import type { FastifyRequest } from "fastify";
import {
getRequestModelConfig,
getStagehandInitModelConfig,
type RequestModelConfig,
} from "../../src/lib/header.js";
function createRequest({
body,
headers = {},
}: {
body?: Record<string, unknown>;
headers?: Record<string, string>;
}): FastifyRequest {
return {
body,
headers,
} as FastifyRequest;
}
function assertSuccess(
result: ReturnType<typeof getRequestModelConfig>,
): RequestModelConfig {
if (result.success === false) {
throw result.error;
}
assert.equal(result.success, true);
return result.data;
}
describe("getRequestModelConfig", () => {
it("preserves a Vertex model config from an action request so auth fields reach session initialization", () => {
const model = {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
auth: {
type: "googleServiceAccount",
credentials: {
client_email: "vertex@example.iam.gserviceaccount.com",
private_key:
"-----BEGIN PRIVATE KEY-----\\ntest\\n-----END PRIVATE KEY-----",
},
},
providerOptions: {
vertex: {
project: "test-gcp-project",
location: "us-central1",
},
},
};
const request = createRequest({
body: {
options: { model },
},
headers: {
"x-model-api-key": "sk-header",
},
});
const config = assertSuccess(getRequestModelConfig(request));
assert.equal(config.modelName, "vertex/gemini-2.5-flash");
assert.equal(config.apiKey, "sk-header");
assert.deepEqual(config.model, model);
});
it("does not read agentConfig.model as a request-level model config", () => {
const request = createRequest({
body: {
agentConfig: { model: "google/gemini-2.5-flash" },
},
});
assert.deepEqual(assertSuccess(getRequestModelConfig(request)), {
model: undefined,
modelName: undefined,
apiKey: undefined,
});
});
it("normalizes an agent string model into the session bootstrap model config", () => {
const request = createRequest({
body: {
agentConfig: { model: "google/gemini-2.5-flash" },
},
});
assert.deepEqual(assertSuccess(getStagehandInitModelConfig(request)), {
model: { modelName: "google/gemini-2.5-flash" },
modelName: "google/gemini-2.5-flash",
apiKey: undefined,
});
});
it("returns a validation result instead of throwing when agent bootstrap model config is invalid", () => {
const request = createRequest({
body: {
agentConfig: {
model: {
provider: "vertex",
modelName: "vertex/gemini-2.5-flash",
},
},
},
});
assert.deepEqual(assertSuccess(getRequestModelConfig(request)), {
model: undefined,
modelName: undefined,
apiKey: undefined,
});
const result = getStagehandInitModelConfig(request);
assert.equal(result.success, false);
});
});