Add opt-in browser tools for desktop tabs
* Add opt-in browser tools for desktop tabs Adds the daemon opt-in, desktop tab routing, MCP tools, and real browser automation surfaces for Paseo desktop browser tabs. * Fix browser tools CI expectations * Address browser tools review findings * Restrict browser file automation paths * Fix browser upload test on Windows * Harden browser navigation inputs * Make browser tools create usable tabs * Update browser MCP empty-state test * Fail browser tab creation when registration times out * Fix browser screenshots for agents * Hide disabled browser tools from agents * Address browser tools architecture review * Replace browser tools review tests * Wrap browser tab registration errors * Mock Expo Router in app unit tests * Handle invalid browser automation requests * Return browser failure on desktop disconnect * Update browser disconnect websocket test * Relax browser timeout polling test * Handle invalid browser responses * Return browser failure when send fails * Remove local diagnostics and fixture paths * Fix dev service home fallback * Use worktree home for dev services * Use managed daemon in desktop dev * fix(browser): keep agent tabs addressable Track agent-active browser targets separately from human-focused tabs and keep resident webviews alive for automation. Browser tool visibility now comes from registration while the broker reports disabled execution. * refactor(browser): register tools through catalog Move browser tool registration onto the shared Paseo tool catalog so the MCP server remains only the transport adapter. * fix(settings): translate browser tools host error
This commit is contained in:
Mohamed Boudra
@@ -0,0 +1,375 @@
|
||||
import { beforeEach, describe, expect, test, vi } from "vitest";
|
||||
import type { SessionInboundMessage, SessionOutboundMessage } from "@getpaseo/protocol/messages";
|
||||
import { mountBrowserAutomationHandler } from "./handler";
|
||||
import type { DesktopHostBridge } from "@/desktop/host";
|
||||
import { useBrowserStore } from "@/stores/browser-store";
|
||||
import {
|
||||
buildWorkspaceTabPersistenceKey,
|
||||
useWorkspaceLayoutStore,
|
||||
} from "@/stores/workspace-layout-store";
|
||||
|
||||
vi.mock("expo-router", () => ({
|
||||
router: {
|
||||
navigate: vi.fn(),
|
||||
},
|
||||
}));
|
||||
|
||||
vi.mock("@react-native-async-storage/async-storage", () => ({
|
||||
default: {
|
||||
getItem: vi.fn(async () => null),
|
||||
setItem: vi.fn(async () => undefined),
|
||||
removeItem: vi.fn(async () => undefined),
|
||||
},
|
||||
}));
|
||||
|
||||
type BrowserAutomationExecuteRequest = Extract<
|
||||
SessionOutboundMessage,
|
||||
{ type: "browser.automation.execute.request" }
|
||||
>;
|
||||
type BrowserAutomationExecuteResponse = Extract<
|
||||
SessionInboundMessage,
|
||||
{ type: "browser.automation.execute.response" }
|
||||
>;
|
||||
|
||||
class FakeDaemonClient {
|
||||
public sentResponses: BrowserAutomationExecuteResponse[] = [];
|
||||
private handler: ((request: BrowserAutomationExecuteRequest) => void) | null = null;
|
||||
|
||||
public on(
|
||||
type: "browser.automation.execute.request",
|
||||
handler: (request: BrowserAutomationExecuteRequest) => void,
|
||||
): () => void {
|
||||
expect(type).toBe("browser.automation.execute.request");
|
||||
this.handler = handler;
|
||||
return () => {
|
||||
if (this.handler === handler) {
|
||||
this.handler = null;
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
public sendBrowserAutomationExecuteResponse(response: BrowserAutomationExecuteResponse): void {
|
||||
this.sentResponses.push(response);
|
||||
}
|
||||
|
||||
public receive(nextRequest: BrowserAutomationExecuteRequest): void {
|
||||
this.handler?.(nextRequest);
|
||||
}
|
||||
}
|
||||
|
||||
function browserAutomationRequest(): BrowserAutomationExecuteRequest {
|
||||
return {
|
||||
type: "browser.automation.execute.request",
|
||||
requestId: "req-1",
|
||||
command: { command: "list_tabs", args: {} },
|
||||
};
|
||||
}
|
||||
|
||||
function browserNewTabRequest(): BrowserAutomationExecuteRequest {
|
||||
return {
|
||||
type: "browser.automation.execute.request",
|
||||
requestId: "req-new",
|
||||
agentId: "agent-1",
|
||||
workspaceId: "/repo",
|
||||
command: { command: "new_tab", args: { workspaceId: "/repo", url: "https://example.com" } },
|
||||
};
|
||||
}
|
||||
|
||||
function emptyListTabsPayload(requestId = "req-new:list_tabs") {
|
||||
return {
|
||||
requestId,
|
||||
ok: true as const,
|
||||
result: {
|
||||
command: "list_tabs" as const,
|
||||
tabs: [],
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function currentListTabsPayload(requestId = "req-new:list_tabs") {
|
||||
return {
|
||||
requestId,
|
||||
ok: true as const,
|
||||
result: {
|
||||
command: "list_tabs" as const,
|
||||
tabs: currentBrowserTabs(),
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function flushPromises(): Promise<void> {
|
||||
return new Promise((resolve) => setTimeout(resolve, 0));
|
||||
}
|
||||
|
||||
function waitForAsyncWork(): Promise<void> {
|
||||
return new Promise((resolve) => setTimeout(resolve, 20));
|
||||
}
|
||||
|
||||
function currentBrowserTabs() {
|
||||
return Object.values(useBrowserStore.getState().browsersById).map((browser) => ({
|
||||
browserId: browser.browserId,
|
||||
workspaceId: "/repo",
|
||||
url: browser.url,
|
||||
title: browser.title,
|
||||
isActive: true,
|
||||
isLoading: false,
|
||||
}));
|
||||
}
|
||||
|
||||
describe("mountBrowserAutomationHandler", () => {
|
||||
beforeEach(() => {
|
||||
useBrowserStore.setState({ browsersById: {} });
|
||||
useWorkspaceLayoutStore.setState({ layoutByWorkspace: {} });
|
||||
});
|
||||
|
||||
test("creates an unfocused workspace browser tab for browser_new_tab", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
const setWorkspaceActiveBrowser = vi.fn(async () => undefined);
|
||||
const setAgentActiveBrowser = vi.fn(async () => undefined);
|
||||
const registerWorkspaceBrowser = vi.fn(async () => undefined);
|
||||
const ensureResidentBrowserWebview = vi.fn();
|
||||
const executeAutomationCommand = vi.fn(async () => currentListTabsPayload());
|
||||
const workspaceKey = buildWorkspaceTabPersistenceKey({
|
||||
serverId: "server-1",
|
||||
workspaceId: "/repo",
|
||||
});
|
||||
if (!workspaceKey) throw new Error("expected workspace key");
|
||||
const focusedTabId = useWorkspaceLayoutStore
|
||||
.getState()
|
||||
.openTabFocused(workspaceKey, { kind: "draft", draftId: "human-draft" });
|
||||
if (!focusedTabId) throw new Error("expected focused tab");
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
serverId: "server-1",
|
||||
getHost: () =>
|
||||
({
|
||||
browser: {
|
||||
executeAutomationCommand,
|
||||
registerWorkspaceBrowser,
|
||||
setWorkspaceActiveBrowser,
|
||||
setAgentActiveBrowser,
|
||||
},
|
||||
}) satisfies DesktopHostBridge,
|
||||
ensureResidentBrowserWebview,
|
||||
});
|
||||
|
||||
client.receive(browserNewTabRequest());
|
||||
await flushPromises();
|
||||
|
||||
const payload = client.sentResponses[0]?.payload;
|
||||
expect(payload?.ok).toBe(true);
|
||||
if (!payload?.ok) throw new Error("expected success");
|
||||
expect(payload.result.command).toBe("new_tab");
|
||||
if (payload.result.command !== "new_tab") throw new Error("expected new_tab result");
|
||||
expect(payload.result.url).toBe("https://example.com");
|
||||
expect(useWorkspaceLayoutStore.getState().getWorkspaceTabs(workspaceKey)).toContainEqual(
|
||||
expect.objectContaining({ target: { kind: "browser", browserId: payload.result.browserId } }),
|
||||
);
|
||||
const layout = useWorkspaceLayoutStore.getState().layoutByWorkspace[workspaceKey];
|
||||
expect(layout?.root.kind).toBe("pane");
|
||||
if (layout?.root.kind !== "pane") throw new Error("expected root pane");
|
||||
expect(layout.root.pane.focusedTabId).toBe(focusedTabId);
|
||||
expect(registerWorkspaceBrowser).toHaveBeenCalledWith({
|
||||
browserId: payload.result.browserId,
|
||||
workspaceId: "/repo",
|
||||
});
|
||||
expect(setAgentActiveBrowser).toHaveBeenCalledWith({
|
||||
agentId: "agent-1",
|
||||
browserId: payload.result.browserId,
|
||||
});
|
||||
expect(setWorkspaceActiveBrowser).not.toHaveBeenCalled();
|
||||
expect(ensureResidentBrowserWebview).toHaveBeenCalledWith({
|
||||
browserId: payload.result.browserId,
|
||||
url: "https://example.com",
|
||||
});
|
||||
expect(executeAutomationCommand).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
test("returns browser_timeout when the resident webview does not register", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
const ensureResidentBrowserWebview = vi.fn();
|
||||
const executeAutomationCommand = vi.fn(async () => emptyListTabsPayload());
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
serverId: "server-1",
|
||||
getHost: () => ({ browser: { executeAutomationCommand } }) satisfies DesktopHostBridge,
|
||||
ensureResidentBrowserWebview,
|
||||
registrationWaitTimeoutMs: 1,
|
||||
registrationPollIntervalMs: 1,
|
||||
});
|
||||
|
||||
client.receive(browserNewTabRequest());
|
||||
await waitForAsyncWork();
|
||||
|
||||
expect(client.sentResponses[0]?.payload).toMatchObject({
|
||||
requestId: "req-new",
|
||||
ok: false,
|
||||
error: {
|
||||
code: "browser_timeout",
|
||||
retryable: true,
|
||||
},
|
||||
});
|
||||
expect(ensureResidentBrowserWebview).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ url: "https://example.com" }),
|
||||
);
|
||||
expect(client.sentResponses[0]?.payload).not.toMatchObject({
|
||||
ok: true,
|
||||
result: { command: "new_tab" },
|
||||
});
|
||||
});
|
||||
|
||||
test("wraps browser_new_tab registration bridge errors in a response", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
const executeAutomationCommand = vi.fn(async () => {
|
||||
throw new Error("IPC registration check failed");
|
||||
});
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
serverId: "server-1",
|
||||
getHost: () => ({ browser: { executeAutomationCommand } }) satisfies DesktopHostBridge,
|
||||
});
|
||||
|
||||
client.receive(browserNewTabRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(client.sentResponses[0]?.payload).toEqual({
|
||||
requestId: "req-new",
|
||||
ok: false,
|
||||
error: {
|
||||
code: "browser_unknown_error",
|
||||
message: "IPC registration check failed",
|
||||
retryable: false,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
test("sends a success response from the desktop bridge", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
const executeAutomationCommand = vi.fn(async () => ({
|
||||
requestId: "req-1",
|
||||
ok: true as const,
|
||||
result: { command: "list_tabs" as const, tabs: [] },
|
||||
}));
|
||||
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
getHost: () => ({ browser: { executeAutomationCommand } }) satisfies DesktopHostBridge,
|
||||
});
|
||||
|
||||
client.receive(browserAutomationRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(executeAutomationCommand).toHaveBeenCalledWith(browserAutomationRequest());
|
||||
expect(client.sentResponses).toEqual([
|
||||
{
|
||||
type: "browser.automation.execute.response",
|
||||
payload: {
|
||||
requestId: "req-1",
|
||||
ok: true,
|
||||
result: { command: "list_tabs", tabs: [] },
|
||||
},
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
test("missing bridge sends browser_unsupported", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
mountBrowserAutomationHandler({ client, getHost: () => null });
|
||||
|
||||
client.receive(browserAutomationRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(client.sentResponses).toEqual([
|
||||
{
|
||||
type: "browser.automation.execute.response",
|
||||
payload: {
|
||||
requestId: "req-1",
|
||||
ok: false,
|
||||
error: {
|
||||
code: "browser_unsupported",
|
||||
message: "Desktop browser automation is not available in this app runtime.",
|
||||
retryable: false,
|
||||
},
|
||||
},
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
test("typed bridge errors become failure responses", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
getHost: () => ({
|
||||
browser: {
|
||||
executeAutomationCommand: async () => {
|
||||
throw {
|
||||
code: "browser_tab_not_found",
|
||||
message: "Browser tab browser-1 was not found.",
|
||||
retryable: false,
|
||||
};
|
||||
},
|
||||
},
|
||||
}),
|
||||
});
|
||||
|
||||
client.receive(browserAutomationRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(client.sentResponses[0]?.payload).toEqual({
|
||||
requestId: "req-1",
|
||||
ok: false,
|
||||
error: {
|
||||
code: "browser_tab_not_found",
|
||||
message: "Browser tab browser-1 was not found.",
|
||||
retryable: false,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
test("unimplemented preload IPC reports browser_unsupported", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
mountBrowserAutomationHandler({
|
||||
client,
|
||||
getHost: () => ({
|
||||
browser: {
|
||||
executeAutomationCommand: async () => {
|
||||
throw new Error('No handler registered for "paseo:browser:execute-automation-command"');
|
||||
},
|
||||
},
|
||||
}),
|
||||
});
|
||||
|
||||
client.receive(browserAutomationRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(client.sentResponses[0]?.payload).toEqual({
|
||||
requestId: "req-1",
|
||||
ok: false,
|
||||
error: {
|
||||
code: "browser_unsupported",
|
||||
message: "Desktop browser automation is not implemented by this desktop build yet.",
|
||||
retryable: false,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
test("unsubscribe stops handling requests", async () => {
|
||||
const client = new FakeDaemonClient();
|
||||
const executeAutomationCommand = vi.fn(async () => ({
|
||||
requestId: "req-1",
|
||||
ok: true as const,
|
||||
result: { command: "list_tabs" as const, tabs: [] },
|
||||
}));
|
||||
const unsubscribe = mountBrowserAutomationHandler({
|
||||
client,
|
||||
getHost: () => ({ browser: { executeAutomationCommand } }),
|
||||
});
|
||||
|
||||
unsubscribe();
|
||||
client.receive(browserAutomationRequest());
|
||||
await flushPromises();
|
||||
|
||||
expect(executeAutomationCommand).not.toHaveBeenCalled();
|
||||
expect(client.sentResponses).toEqual([]);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user