chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,163 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { spawn, ChildProcess } from 'node:child_process';
|
||||
import { join, resolve } from 'node:path';
|
||||
import { writeFileSync, mkdirSync } from 'node:fs';
|
||||
import { Writable, Readable } from 'node:stream';
|
||||
import { env } from 'node:process';
|
||||
import * as acp from '@agentclientprotocol/sdk';
|
||||
|
||||
const sandboxEnv = env['GEMINI_SANDBOX'];
|
||||
const itMaybe = sandboxEnv && sandboxEnv !== 'false' ? it.skip : it;
|
||||
|
||||
class MockClient implements acp.Client {
|
||||
updates: acp.SessionNotification[] = [];
|
||||
sessionUpdate = async (params: acp.SessionNotification) => {
|
||||
this.updates.push(params);
|
||||
};
|
||||
requestPermission = async (): Promise<acp.RequestPermissionResponse> => {
|
||||
throw new Error('unexpected');
|
||||
};
|
||||
}
|
||||
|
||||
describe.skip('ACP Environment and Auth', () => {
|
||||
let rig: TestRig;
|
||||
let child: ChildProcess | undefined;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
child?.kill();
|
||||
child = undefined;
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
itMaybe(
|
||||
'should load .env from project directory and use the provided API key',
|
||||
async () => {
|
||||
rig.setup('acp-env-loading');
|
||||
|
||||
// Create a project directory with a .env file containing a recognizable invalid key
|
||||
const projectDir = resolve(join(rig.testDir!, 'project'));
|
||||
mkdirSync(projectDir, { recursive: true });
|
||||
writeFileSync(
|
||||
join(projectDir, '.env'),
|
||||
'GEMINI_API_KEY=test-key-from-env\n',
|
||||
);
|
||||
|
||||
const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
|
||||
|
||||
child = spawn('node', [bundlePath, '--acp'], {
|
||||
cwd: rig.homeDir!,
|
||||
stdio: ['pipe', 'pipe', 'inherit'],
|
||||
env: {
|
||||
...process.env,
|
||||
GEMINI_CLI_HOME: rig.homeDir!,
|
||||
GEMINI_API_KEY: undefined,
|
||||
VERBOSE: 'true',
|
||||
},
|
||||
});
|
||||
|
||||
const input = Writable.toWeb(child.stdin!);
|
||||
const output = Readable.toWeb(
|
||||
child.stdout!,
|
||||
) as ReadableStream<Uint8Array>;
|
||||
const testClient = new MockClient();
|
||||
const stream = acp.ndJsonStream(input, output);
|
||||
const connection = new acp.ClientSideConnection(() => testClient, stream);
|
||||
|
||||
await connection.initialize({
|
||||
protocolVersion: acp.PROTOCOL_VERSION,
|
||||
clientCapabilities: {
|
||||
fs: { readTextFile: false, writeTextFile: false },
|
||||
},
|
||||
});
|
||||
|
||||
// 1. newSession should succeed because it finds the key in .env
|
||||
const { sessionId } = await connection.newSession({
|
||||
cwd: projectDir,
|
||||
mcpServers: [],
|
||||
});
|
||||
|
||||
expect(sessionId).toBeDefined();
|
||||
|
||||
// 2. prompt should fail because the key is invalid,
|
||||
// but the error should come from the API, not the internal auth check.
|
||||
await expect(
|
||||
connection.prompt({
|
||||
sessionId,
|
||||
prompt: [{ type: 'text', text: 'hello' }],
|
||||
}),
|
||||
).rejects.toSatisfy((error: unknown) => {
|
||||
const acpError = error as acp.RequestError;
|
||||
const errorData = acpError.data as
|
||||
| { error?: { message?: string } }
|
||||
| undefined;
|
||||
const message = String(errorData?.error?.message || acpError.message);
|
||||
// It should NOT be our internal "Authentication required" message
|
||||
expect(message).not.toContain('Authentication required');
|
||||
// It SHOULD be an API error mentioning the invalid key
|
||||
expect(message).toContain('API key not valid');
|
||||
return true;
|
||||
});
|
||||
|
||||
child.stdin!.end();
|
||||
},
|
||||
);
|
||||
|
||||
itMaybe(
|
||||
'should fail with authRequired when no API key is found',
|
||||
async () => {
|
||||
rig.setup('acp-auth-failure');
|
||||
|
||||
const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
|
||||
|
||||
child = spawn('node', [bundlePath, '--acp'], {
|
||||
cwd: rig.homeDir!,
|
||||
stdio: ['pipe', 'pipe', 'inherit'],
|
||||
env: {
|
||||
...process.env,
|
||||
GEMINI_CLI_HOME: rig.homeDir!,
|
||||
GEMINI_API_KEY: undefined,
|
||||
VERBOSE: 'true',
|
||||
},
|
||||
});
|
||||
|
||||
const input = Writable.toWeb(child.stdin!);
|
||||
const output = Readable.toWeb(
|
||||
child.stdout!,
|
||||
) as ReadableStream<Uint8Array>;
|
||||
const testClient = new MockClient();
|
||||
const stream = acp.ndJsonStream(input, output);
|
||||
const connection = new acp.ClientSideConnection(() => testClient, stream);
|
||||
|
||||
await connection.initialize({
|
||||
protocolVersion: acp.PROTOCOL_VERSION,
|
||||
clientCapabilities: {
|
||||
fs: { readTextFile: false, writeTextFile: false },
|
||||
},
|
||||
});
|
||||
|
||||
await expect(
|
||||
connection.newSession({
|
||||
cwd: resolve(rig.testDir!),
|
||||
mcpServers: [],
|
||||
}),
|
||||
).rejects.toMatchObject({
|
||||
message: expect.stringContaining(
|
||||
'Gemini API key is missing or not configured.',
|
||||
),
|
||||
});
|
||||
|
||||
child.stdin!.end();
|
||||
},
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,116 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { spawn, ChildProcess } from 'node:child_process';
|
||||
import { join } from 'node:path';
|
||||
import { readFileSync, existsSync } from 'node:fs';
|
||||
import { Writable, Readable } from 'node:stream';
|
||||
import { env } from 'node:process';
|
||||
import * as acp from '@agentclientprotocol/sdk';
|
||||
|
||||
// Skip in sandbox mode - test spawns CLI directly which behaves differently in containers
|
||||
const sandboxEnv = env['GEMINI_SANDBOX'];
|
||||
const itMaybe = sandboxEnv && sandboxEnv !== 'false' ? it.skip : it;
|
||||
|
||||
// Reuse existing fake responses that return a simple "Hello" response
|
||||
const SIMPLE_RESPONSE_PATH = 'hooks-system.session-startup.responses';
|
||||
|
||||
class SessionUpdateCollector implements acp.Client {
|
||||
updates: acp.SessionNotification[] = [];
|
||||
|
||||
sessionUpdate = async (params: acp.SessionNotification) => {
|
||||
this.updates.push(params);
|
||||
};
|
||||
|
||||
requestPermission = async (): Promise<acp.RequestPermissionResponse> => {
|
||||
throw new Error('unexpected');
|
||||
};
|
||||
}
|
||||
|
||||
describe('ACP telemetry', () => {
|
||||
let rig: TestRig;
|
||||
let child: ChildProcess | undefined;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
child?.kill();
|
||||
child = undefined;
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
itMaybe('should flush telemetry when connection closes', async () => {
|
||||
rig.setup('acp-telemetry-flush', {
|
||||
fakeResponsesPath: join(import.meta.dirname, SIMPLE_RESPONSE_PATH),
|
||||
});
|
||||
|
||||
const telemetryPath = join(rig.homeDir!, 'telemetry.log');
|
||||
const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
|
||||
|
||||
child = spawn(
|
||||
'node',
|
||||
[
|
||||
bundlePath,
|
||||
'--acp',
|
||||
'--fake-responses',
|
||||
join(rig.testDir!, 'fake-responses.json'),
|
||||
],
|
||||
{
|
||||
cwd: rig.testDir!,
|
||||
stdio: ['pipe', 'pipe', 'inherit'],
|
||||
env: {
|
||||
...process.env,
|
||||
GEMINI_API_KEY: 'fake-key',
|
||||
GEMINI_CLI_HOME: rig.homeDir!,
|
||||
GEMINI_TELEMETRY_ENABLED: 'true',
|
||||
GEMINI_TELEMETRY_TRACES_ENABLED: 'true',
|
||||
GEMINI_TELEMETRY_TARGET: 'local',
|
||||
GEMINI_TELEMETRY_OUTFILE: telemetryPath,
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
const input = Writable.toWeb(child.stdin!);
|
||||
const output = Readable.toWeb(child.stdout!) as ReadableStream<Uint8Array>;
|
||||
const testClient = new SessionUpdateCollector();
|
||||
const stream = acp.ndJsonStream(input, output);
|
||||
const connection = new acp.ClientSideConnection(() => testClient, stream);
|
||||
|
||||
await connection.initialize({
|
||||
protocolVersion: acp.PROTOCOL_VERSION,
|
||||
clientCapabilities: { fs: { readTextFile: false, writeTextFile: false } },
|
||||
});
|
||||
|
||||
const { sessionId } = await connection.newSession({
|
||||
cwd: rig.testDir!,
|
||||
mcpServers: [],
|
||||
});
|
||||
|
||||
await connection.prompt({
|
||||
sessionId,
|
||||
prompt: [{ type: 'text', text: 'Say hello' }],
|
||||
});
|
||||
|
||||
expect(JSON.stringify(testClient.updates)).toContain('Hello');
|
||||
|
||||
// Close stdin to trigger telemetry flush via runExitCleanup()
|
||||
child.stdin!.end();
|
||||
await new Promise<void>((resolve) => {
|
||||
child!.on('close', () => resolve());
|
||||
});
|
||||
child = undefined;
|
||||
|
||||
// gen_ai.output.messages is the last OTEL log emitted (after prompt response)
|
||||
expect(existsSync(telemetryPath)).toBe(true);
|
||||
expect(readFileSync(telemetryPath, 'utf-8')).toContain(
|
||||
'gen_ai.output.messages',
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Part 1. "}],"role":"model"},"index":0}]},{"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":10,"totalTokenCount":110}},{"candidates":[{"content":{"parts":[{"text":"Part 2."}],"role":"model"},"index":0,"finishReason":"STOP"}]}]}
|
||||
@@ -0,0 +1,50 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join, dirname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
describe('API Resilience E2E', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should not crash when receiving metadata-only chunks in a stream', async () => {
|
||||
await rig.setup('api-resilience-metadata-only', {
|
||||
fakeResponsesPath: join(
|
||||
dirname(fileURLToPath(import.meta.url)),
|
||||
'api-resilience.responses',
|
||||
),
|
||||
settings: {
|
||||
planSettings: { modelRouting: false },
|
||||
},
|
||||
});
|
||||
|
||||
// Run the CLI with a simple prompt.
|
||||
// The fake responses will provide a stream with a metadata-only chunk in the middle.
|
||||
// We use gemini-3-pro-preview to minimize internal service calls.
|
||||
const result = await rig.run({
|
||||
args: ['hi', '--model', 'gemini-3-pro-preview'],
|
||||
});
|
||||
|
||||
// Verify the output contains text from the normal chunks.
|
||||
// If the CLI crashed on the metadata chunk, rig.run would throw.
|
||||
expect(result).toContain('Part 1.');
|
||||
expect(result).toContain('Part 2.');
|
||||
|
||||
// Verify telemetry event for the prompt was still generated
|
||||
const hasUserPromptEvent = await rig.waitForTelemetryEvent('user_prompt');
|
||||
expect(hasUserPromptEvent).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,6 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll check the dynamic content page on the localhost server."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to http://127.0.0.1:18923/dynamic.html, wait for the dynamic content to load, then capture the accessibility tree and report what content appeared"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/dynamic.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"wait_for","args":{"selector":"#dynamic-content","state":"visible","timeout":5000}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":15,"totalTokenCount":195}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Dynamic content loaded successfully. Found heading 'Content Loaded', message 'This content was loaded dynamically via JavaScript.', and a list with items: Item Alpha, Item Beta, Item Gamma."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The dynamic content page loaded successfully:\n\n- **Heading**: Content Loaded\n- **Message**: This content was loaded dynamically via JavaScript\n- **Items**: Item Alpha, Item Beta, Item Gamma\n\nThe JavaScript-rendered content appeared after the initial page load, replacing the 'Loading...' indicator."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":60,"totalTokenCount":260}}]}
|
||||
@@ -0,0 +1,9 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll fill out the contact form on the localhost server."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to http://127.0.0.1:18923/form.html, fill in the name field with 'Test User', the email field with 'test@example.com', the message field with 'Hello World', and submit the form"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/form.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#name","value":"Test User"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#email","value":"test@example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":25,"totalTokenCount":205}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#message","value":"Hello World"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":210,"candidatesTokenCount":25,"totalTokenCount":235}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#submit-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":240,"candidatesTokenCount":20,"totalTokenCount":260}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":270,"candidatesTokenCount":15,"totalTokenCount":285}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully filled and submitted the contact form. Navigated to form-result.html which shows 'Form Submitted Successfully'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully filled out and submitted the contact form:\n\n- **Name**: Test User\n- **Email**: test@example.com\n- **Message**: Hello World\n\nAfter submission, the page navigated to the result page showing 'Form Submitted Successfully'."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":60,"totalTokenCount":360}}]}
|
||||
@@ -0,0 +1,9 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll go through the multi-step flow on the localhost server."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to http://127.0.0.1:18923/multi-step/step1.html, fill in 'testuser' as the username, click Next, then on step 2 select 'Option B' and click Finish. Report the final result page content."}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/multi-step/step1.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"fill","args":{"selector":"#username","value":"testuser"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":25,"totalTokenCount":175}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#next-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":180,"candidatesTokenCount":20,"totalTokenCount":200}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":210,"candidatesTokenCount":15,"totalTokenCount":225}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"selector":"#finish-btn"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":240,"candidatesTokenCount":20,"totalTokenCount":260}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":270,"candidatesTokenCount":15,"totalTokenCount":285}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Completed all steps. Step 1: entered username 'testuser'. Step 2: selected default option. Final result page shows 'Multi-Step Complete' with '✓ Complete' status badge."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've completed the multi-step flow:\n\n1. **Step 1**: Entered 'testuser' as username and clicked Next\n2. **Step 2**: Confirmed selection and clicked Finish\n3. **Result**: Final page shows 'Multi-Step Complete' with a '✓ Complete' status badge\n\nAll steps were successfully navigated."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":60,"totalTokenCount":360}}]}
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to the localhost page and read its content using the browser agent."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to http://127.0.0.1:18923/index.html and tell me the page title and list all links on the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/index.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is 'Test Fixture - Home'. Found 3 links: Contact Form (/form.html), Multi-Step Flow (/multi-step/step1.html), Dynamic Content (/dynamic.html)."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The localhost test fixture page has:\n\n**Title**: Test Fixture - Home\n\n**Links**:\n1. Contact Form (form.html)\n2. Multi-Step Flow (multi-step/step1.html)\n3. Dynamic Content (dynamic.html)\n\nThe page also has a heading 'Test Fixture Home Page' and footer content."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":60,"totalTokenCount":260}}]}
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll take a screenshot of the localhost test page."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to http://127.0.0.1:18923/index.html and take a screenshot of the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":35,"totalTokenCount":135}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"http://127.0.0.1:18923/index.html"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Screenshot captured of the localhost test fixture home page showing the heading, navigation links, and footer.","data":{"screenshotTaken":true}}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've captured a screenshot of the localhost test fixture page. The screenshot shows the 'Test Fixture Home Page' heading with navigation links to the Contact Form, Multi-Step Flow, and Dynamic Content pages, along with the footer section."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}
|
||||
@@ -0,0 +1,171 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig, assertModelHasOutput } from './test-helper.js';
|
||||
import { dirname, join } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
||||
describe('browser-agent-localhost', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
const browserSettings = {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated' as const,
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should navigate to localhost fixture and read page content', async () => {
|
||||
rig.setup('localhost-navigate', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent-localhost.navigate.responses',
|
||||
),
|
||||
settings: browserSettings,
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Navigate to http://127.0.0.1:18923/index.html and tell me the page title and list all links.',
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
});
|
||||
|
||||
it('should fill out and submit a form on localhost', async () => {
|
||||
rig.setup('localhost-form', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent-localhost.form.responses',
|
||||
),
|
||||
settings: browserSettings,
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: "Navigate to http://127.0.0.1:18923/form.html, fill in name='Test User', email='test@example.com', message='Hello World', and submit the form.",
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
});
|
||||
|
||||
it('should navigate through a multi-step flow', async () => {
|
||||
rig.setup('localhost-multistep', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent-localhost.multistep.responses',
|
||||
),
|
||||
settings: browserSettings,
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: "Go to http://127.0.0.1:18923/multi-step/step1.html, fill in 'testuser' as username, click Next, then click Finish on step 2. Report the result.",
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
});
|
||||
|
||||
it('should handle dynamically loaded content', async () => {
|
||||
rig.setup('localhost-dynamic', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent-localhost.dynamic.responses',
|
||||
),
|
||||
settings: browserSettings,
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Navigate to http://127.0.0.1:18923/dynamic.html, wait for content to load, and tell me what items appear.',
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
});
|
||||
|
||||
it('should take a screenshot of localhost page', async () => {
|
||||
rig.setup('localhost-screenshot', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent-localhost.screenshot.responses',
|
||||
),
|
||||
settings: browserSettings,
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Navigate to http://127.0.0.1:18923/index.html and take a screenshot.',
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserCalls = toolLogs.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(browserCalls.length).toBeGreaterThan(0);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll open https://example.com and check the page title for you."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Open https://example.com and get the page title"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":35,"totalTokenCount":135}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"The page title is 'Example Domain'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I have opened the page and the title is 'Example Domain'. The browser session has been cleaned up successfully."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
|
||||
@@ -0,0 +1,8 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll launch two browser agents concurrently to check both repositories."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to https://example.com and get the page title"}}},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to https://example.com and get the page title"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is Example Domain."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is Example Domain."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Both browser agents completed successfully. Agent 1 and Agent 2 both navigated to their respective pages and confirmed the page titles."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"test.txt","content":"hello"}}},{"text":"I've successfully written \"hello\" to test.txt. The file has been created with the specified content."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to https://example.com and analyze the links on the page."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Go to https://example.com and find all links on the page, then describe them"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Found one link on https://example.com: 'More information...' linking to the IANA website for details about reserved domains."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"After analyzing https://example.com, I found the following links:\n\n1. **\"More information...\"** - This is the main link on the page that points to the IANA (Internet Assigned Numbers Authority) website for more details about reserved domains.\n\nThe page is quite minimal with just this single informational link, which is typical for example domains used in documentation."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":70,"totalTokenCount":270}}]}
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll help you open https://example.com and analyze the page. Let me use the browser agent to navigate and capture the page information."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to https://example.com and capture the accessibility tree to get the page title and main content"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":30,"totalTokenCount":130}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com. The page title is 'Example Domain' and the main content states: 'This domain is for use in illustrative examples in documents.'"}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Based on the browser analysis of https://example.com:\n\n**Page Title**: Example Domain\n\n**Main Content**: The page contains a simple heading \"Example Domain\" and explanatory text stating \"This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.\"\n\nThe page has a clean, minimal layout typical of placeholder domains used for documentation and examples."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":80,"totalTokenCount":280}}]}
|
||||
@@ -0,0 +1,26 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will invoke the browser agent to get the page title of example.com."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10491,"candidatesTokenCount":16,"totalTokenCount":10587,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10491}],"thoughtsTokenCount":80}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"invoke_agent","args":{"prompt":"Navigate to example.com and return the page title.","agent_name":"browser_agent"},"id":"1zgnzmz8"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10491,"candidatesTokenCount":52,"totalTokenCount":10623,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10491}],"thoughtsTokenCount":80}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10491,"candidatesTokenCount":52,"totalTokenCount":10623,"cachedContentTokenCount":8126,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10491}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8126}],"thoughtsTokenCount":80}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"list_pages","args":{"wait_for_previous":true},"id":"q9a8dwir"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8627,"candidatesTokenCount":18,"totalTokenCount":8742,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8627}],"thoughtsTokenCount":97}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8627,"candidatesTokenCount":18,"totalTokenCount":8742,"cachedContentTokenCount":8066,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8627}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8066}],"thoughtsTokenCount":97}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"new_page","args":{"url":"http://example.com","wait_for_previous":true},"id":"q8jik45z"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8669,"candidatesTokenCount":28,"totalTokenCount":8841,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8669}],"thoughtsTokenCount":144}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8766,"candidatesTokenCount":28,"totalTokenCount":8938,"cachedContentTokenCount":8059,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8766}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8059}],"thoughtsTokenCount":144}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"wait_for_previous":true,"url":"https://example.com","type":"url"},"id":"chnx16bz"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8726,"candidatesTokenCount":34,"totalTokenCount":8855,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8726}],"thoughtsTokenCount":95}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8967,"candidatesTokenCount":34,"totalTokenCount":9096,"cachedContentTokenCount":8053,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8967}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8053}],"thoughtsTokenCount":95}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"wait_for_previous":true,"url":"http://example.com","type":"url"},"id":"dh6nh7uc"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8823,"candidatesTokenCount":34,"totalTokenCount":9004,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8823}],"thoughtsTokenCount":147}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9159,"candidatesTokenCount":34,"totalTokenCount":9340,"cachedContentTokenCount":8047,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9159}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8047}],"thoughtsTokenCount":147}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"prantos8"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8920,"candidatesTokenCount":18,"totalTokenCount":9060,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8920}],"thoughtsTokenCount":122}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9403,"candidatesTokenCount":18,"totalTokenCount":9543,"cachedContentTokenCount":8043,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9403}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8043}],"thoughtsTokenCount":122}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"wait_for_previous":true,"uid":"1_12"},"id":"r79qt569"},"thoughtSignature":"EogCCoUCAb4+9vt60822Xp/P+yQ5WNfvAKPF0LS6q0a47hBm0WrzbxwEB/HBzw14/ywGVT0tGNCypHm6ZWVht+ZgHJoxA2WtHDOdRbdjsvvmJaIBIjI3wPSiVc2dm2S9qVKlCER5uMwhW5aHbgmax/F0TSHej+g1P4+uOq2cJeAZ3iqgCcyROYji/O/eKWIBqaB6Wu10KtUvj0M9Dd+K0GkPpjNIvw17IS2jUxu/yPPZ9m6CSSFrdhaA7R4YXaE4L6qISdcdBxgsiSRkI/m+0f3J2/1jPk24y6GjrWEiejKCpfMw+sHTnTaEABh8Unih31eRkR7/WmcyGu9/IUMXREEo3W3ddIGFgCS0"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9210,"candidatesTokenCount":25,"totalTokenCount":9275,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9210}],"thoughtsTokenCount":40}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9815,"candidatesTokenCount":25,"totalTokenCount":9880,"cachedContentTokenCount":8041,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9815}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8041}],"thoughtsTokenCount":40}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"3f6suk04"},"thoughtSignature":"EpEBCo4BAb4+9vvrysVAn4EZuigwkHrOkiDNXb0u0bGnAPKivQ0/NoR5aEg2NSa74y1Llo7ifzocwWsiqG+q0erh7yiacc0ypevnjpkJ9nfDrNOVoGZIz+OusBXs3AqPmMaNOiFCYFgOnNXIJNiZwkNSjrdSR7yr9T1L/+MfiXSS8Qy5ySSrlWyjjY/EBK0/vp4VHg=="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9251,"candidatesTokenCount":18,"totalTokenCount":9287,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9251}],"thoughtsTokenCount":18}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9896,"candidatesTokenCount":18,"totalTokenCount":9932,"cachedContentTokenCount":8034,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9896}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8034}],"thoughtsTokenCount":18}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"wait_for_previous":true,"uid":"2_3"},"id":"4hcr39ek"},"thoughtSignature":"EpoBCpcBAb4+9vtqGpRZfxSRRNqP+Yla/FpN5SRI6mbuvYI3+uUz6bG0Z3yxd6JeCbYM0+JCfyXOCbwZzRrdyf+cGGs0LjFlsRNEHbgjCzoGhN9dZdFzbHvFuXZMwaeCKP5BIWKtHjCPrtEwfsBO+HUnUqV5XeBB9zEfA8fgoPZm5y27ip8eyeYKtQarCXvaX9nIqygKNqGzxb/L4Q=="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9666,"candidatesTokenCount":24,"totalTokenCount":9714,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9666}],"thoughtsTokenCount":24}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10329,"candidatesTokenCount":24,"totalTokenCount":10377,"cachedContentTokenCount":8033,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10329}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8033}],"thoughtsTokenCount":24}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"a7323k6z"},"thoughtSignature":"EoABCn4Bvj72+wrxMO/2uA1RwpvzkuM4xNaslnr/+xfZy/iqwCHZyR5bvsFfsovWYzjzolMLSmvVdGYx/bw6F1ewM3LohjPmEXdiLFI1fEBxNK0166QB6XdOGucHJbItjxzekY2hTYcMJTZWLArFaCl5+wxhLWXAE/zkj3TInmRSPRc="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9469,"candidatesTokenCount":18,"totalTokenCount":9503,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9469}],"thoughtsTokenCount":16}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10156,"candidatesTokenCount":18,"totalTokenCount":10190,"cachedContentTokenCount":8022,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10156}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8022}],"thoughtsTokenCount":16}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to example.com and found the page title: \"Example Domain\""},"wait_for_previous":true},"id":"81koewoz"},"thoughtSignature":"EoYBCoMBAb4+9vsiO1ru68XCJ6gZ+FKthHSwWAdj1b92U7qX4bVZ5j2kaNJFs3EYNsAdZHtkWLKLugPhFT1j9DXaptDYSfnbBbY/gEH5PW0RizHMI9VUQ6rvAyjrfUNh5ga7RuIEeRy3y0uCrglSx0JCOj2gtXG5kwGJDqT6YqTKjXvk3R0DRLg="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9606,"candidatesTokenCount":45,"totalTokenCount":9665,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9606}],"thoughtsTokenCount":14}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10309,"candidatesTokenCount":45,"totalTokenCount":10368,"cachedContentTokenCount":8017,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10309}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8017}],"thoughtsTokenCount":14}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will invoke the browser agent a"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10603,"candidatesTokenCount":7,"totalTokenCount":10649,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10603}],"thoughtsTokenCount":39}},{"candidates":[{"content":{"parts":[{"text":" second time to check for links on example.com."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10603,"candidatesTokenCount":19,"totalTokenCount":10661,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10603}],"thoughtsTokenCount":39}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"invoke_agent","args":{"prompt":"Navigate to example.com and list all the links on the page.","agent_name":"browser_agent"},"id":"rn9rpbw6"},"thoughtSignature":"EosCCogCAb4+9vt0QmjCmkrGoIi1HLtLRARGxmKpP3a2ZF8HrZLv4bfHC1a7d5a1BlPllShIkkAjL1RZmTe9tjpulNV7xsavrWINRdkfrNqC/on1h+F3nhQAa3HBbf4AWWH/AHmVPlUsVDr19hq4NLLL3hxFg04Fb1YEgRDHrjWOs3Oy9SmzdG+MiWv5GFVUM6spjOujO76dKzHZGe7chmMsmE8NhjQ9c/lbWUoXBxJ/72Qs+mRQHpd3p1ufkL0UV8bFtfyJdLTF4iJ/R5kJiqsEN1FtS3PpQaQHsmby7ytEjPX29ps7xp6NO1i/je9p3u+tGXEpnomqdJJ4SvdDJm4XyqO9HTIQxC3jg7mi"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10603,"candidatesTokenCount":58,"totalTokenCount":10700,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10603}],"thoughtsTokenCount":39}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10683,"candidatesTokenCount":58,"totalTokenCount":10780,"cachedContentTokenCount":8119,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10683}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8119}],"thoughtsTokenCount":39}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"list_pages","args":{"wait_for_previous":true},"id":"vqfkekqm"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8630,"candidatesTokenCount":18,"totalTokenCount":8823,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8630}],"thoughtsTokenCount":175}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8630,"candidatesTokenCount":18,"totalTokenCount":8823,"cachedContentTokenCount":8066,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8630}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8066}],"thoughtsTokenCount":175}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"type":"url","url":"https://example.com","wait_for_previous":true},"id":"dsy0oh63"},"thoughtSignature":"ErECCq4CAb4+9vuQlylaFlrtKtYp1EGoDqb9nhSmJ9IPYvmFcBku92rqL1WJU3x2CeLvj0tww69yEodZQSSIJw/4hPtWzLlr3P362ITxFIgvgpzAue5AIjH6EbXJmAcEO8i+I8TV8QneJQiula5HBUdncCTqKycdrjyCKVbAcV1nnkNxbPagAiuumgOaWGPPmE4d+W4Xgbq695Rov0xR0ijSeknqkcf14JKqZqpyuGdMYSDxQhveQS7o4UgrsUhQOgEVc53XqfV5tMjhC7Agpb3WN7zoDUmIAzgbnoG6ha2mJOQ2x3jSRUozLq6fIQ2oZSmb7eajvcGqUxtXp4n4z9cdLpBuHlPB8hfiCxNN0RP60uvaqBtvAFBNfVCbk1eZdxnnvpwQdqp3Ue7H4lzJ9tDBey8="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8672,"candidatesTokenCount":34,"totalTokenCount":8765,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8672}],"thoughtsTokenCount":59}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8847,"candidatesTokenCount":34,"totalTokenCount":8940,"cachedContentTokenCount":8060,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8847}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8060}],"thoughtsTokenCount":59}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"type":"url","wait_for_previous":true,"url":"http://example.com"},"id":"spfjmlgz"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8763,"candidatesTokenCount":34,"totalTokenCount":8906,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8763}],"thoughtsTokenCount":109}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8997,"candidatesTokenCount":34,"totalTokenCount":9140,"cachedContentTokenCount":8054,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8997}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8054}],"thoughtsTokenCount":109}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"new_page","args":{"url":"http://example.com","wait_for_previous":true},"id":"xa6m1ifg"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8854,"candidatesTokenCount":28,"totalTokenCount":9044,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8854}],"thoughtsTokenCount":162}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9197,"candidatesTokenCount":28,"totalTokenCount":9387,"cachedContentTokenCount":8048,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9197}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8048}],"thoughtsTokenCount":162}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"new_page","args":{"url":"https://www.example.com","wait_for_previous":true},"id":"1pxqeqmn"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8911,"candidatesTokenCount":30,"totalTokenCount":9079,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8911}],"thoughtsTokenCount":138}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9416,"candidatesTokenCount":30,"totalTokenCount":9584,"cachedContentTokenCount":8043,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9416}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8043}],"thoughtsTokenCount":138}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Clarifying Domain Inclusion**\n\nOkay, so I'm stuck on this domain thing. I thought I understood the instruction regarding allowed domains, specifically example.com and potential subdomains. It seems the domain provided, www.example.com, might not be explicitly included. I need to be certain whether the original instruction's wording covers www as a subdomain, or if the lack of \"*.\" before \"example.com\" means it is not included at all. It's a key point!\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8968,"totalTokenCount":8968,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8968}]}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"5fmzjlk4"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8968,"candidatesTokenCount":18,"totalTokenCount":9293,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8968}],"thoughtsTokenCount":307}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":9611,"candidatesTokenCount":18,"totalTokenCount":9936,"cachedContentTokenCount":8038,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9611}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8038}],"thoughtsTokenCount":307}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"wait_for_previous":true,"uid":"1_12"},"id":"w39u7j53"},"thoughtSignature":"ErkBCrYBAb4+9vs4gIpgWxIubEi40hUOpqyqvtfJ8qAW3Yz1wJHpce3xFhJwbOc/wiY7AIIvAYAjG0e5+/Y1KrlsGbrUrTK1oDN+yOvei7feK2qXLJVNArii8e7n2MYmgLJM+LXH67m/fxTR9m9rZ6a2RzGpFkjKmXfEk95I+Yx2HYam0DrWc2g/mm3tkXp5FcEG1jx7KNBTv+/uLC/0wR11Emp+vR6tEhtbcv6AIbqqVc+ptmr8HWuZIys="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9258,"candidatesTokenCount":25,"totalTokenCount":9310,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9258}],"thoughtsTokenCount":27}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10208,"candidatesTokenCount":25,"totalTokenCount":10260,"cachedContentTokenCount":8039,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10208}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8039}],"thoughtsTokenCount":27}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"qzaod8vn"},"thoughtSignature":"En4KfAG+Pvb7Wx5fC3gw1Fn9qKx0pll+kkEOEIlaOD5/OJJAFZvLbkJkxdd4qP7+X6FxWf1vFrn8uoWUQxUCK3y/E1KTOMDEKozi7ApeB5W36/iVvHI/MbELdTDQrk4unKqMvcPTHDR55qHDVcS25FyIpqCHQL3OiodSKgK5//0="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9299,"candidatesTokenCount":18,"totalTokenCount":9333,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9299}],"thoughtsTokenCount":16}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10276,"candidatesTokenCount":18,"totalTokenCount":10310,"cachedContentTokenCount":8032,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10276}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8032}],"thoughtsTokenCount":16}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"click","args":{"uid":"2_3","wait_for_previous":true},"id":"izwyu21z"},"thoughtSignature":"EpgBCpUBAb4+9vtf3WpNBe9YcImIFf1HzOHJQ6WIKuadA3qMRbi5n6DAl9v+HkdpYL1tB/5bVGJJ5yDhoTjgAPuMfzk9H0DS+T/NoQjwRBPS6pMMNdVeY0O7Qckwc1oXVzZEMO1mOLHxItYQBeEhQIRme2/ISq6ObWvtEAP/2wazYsPB9m5+suOXNVQhtv0lAtgFwka/O08mhRI="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9714,"candidatesTokenCount":24,"totalTokenCount":9759,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9714}],"thoughtsTokenCount":21}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10707,"candidatesTokenCount":24,"totalTokenCount":10752,"cachedContentTokenCount":8031,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10707}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8031}],"thoughtsTokenCount":21}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"wait_for","args":{"wait_for_previous":true,"text":["Example Domain"]},"id":"u9v4ngts"},"thoughtSignature":"ErwBCrkBAb4+9vtgNuXwkrEU13cJ58BYZBhnQ2xlGVufQgMl26Hbwc4zUciWIrWI+SUaunKBgnut6tmnGA3SYJAZ0wePJLnh3bCRJBcmX0aNEsResAIXD0nmC4tcDQnuWuFHNeb8XzfVxiZcBsnjqNVcZtQ7rT01GAKzOKvfIYKhfoFkwv7spv5A6LUefkHphnu7+5BJYrpBvEN+5xzOZmlNXuUprxVsfbOnopzrPYDZ7YrWZr+R6Y5W0LJ5afI="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9517,"candidatesTokenCount":25,"totalTokenCount":9568,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9517}],"thoughtsTokenCount":26}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10531,"candidatesTokenCount":25,"totalTokenCount":10582,"cachedContentTokenCount":8021,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10531}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8021}],"thoughtsTokenCount":26}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{"wait_for_previous":true},"id":"en5wzv6a"},"thoughtSignature":"ErMBCrABAb4+9vsFi8H2zIOww5bzPlC6nM9VohFXg2gw1IGPsI9e8UzwMm8f6OpzofLx5b3+W73OYCBaGJD0ubRJeIP4yA3kjvaSm89FyjQg/oc3Ktu2WosK2nKynOzk3FoLN3fOMfMWfxKOxV7k5TBnKwGhnEn0WGGaKF2YiAap5ADC3KCIWP5dsJKRHP11AuLlvTvvgptxX1WqqsyXMijvLXbnrdfETWI6b7LtOiUgsTHfS3Q="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9565,"candidatesTokenCount":18,"totalTokenCount":9608,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9565}],"thoughtsTokenCount":25}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10605,"candidatesTokenCount":18,"totalTokenCount":10648,"cachedContentTokenCount":8015,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10605}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8015}],"thoughtsTokenCount":25}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Analyzing the Links**\n\nI've located a link labeled \"Learn more\" pointing to `https://iana.org/domains/example`. The snapshot confirms the link's details. Now I'm checking for more links.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9702,"totalTokenCount":9702,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9702}]}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"evaluate_script","args":{"wait_for_previous":true,"function":"() => {\n return Array.from(document.querySelectorAll('a')).map(a => ({\n text: a.innerText,\n href: a.href\n }));\n}"},"id":"2lza53qd"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9702,"candidatesTokenCount":64,"totalTokenCount":10078,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9702}],"thoughtsTokenCount":312}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10767,"candidatesTokenCount":64,"totalTokenCount":11143,"cachedContentTokenCount":8010,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10767}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8010}],"thoughtsTokenCount":312}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Clarifying My Findings**\n\nI confirmed there is only one link on the page, the \"Learn more\" link. Initially, my process was a bit unclear, but I am now certain of the task's instructions.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9450,"totalTokenCount":9450,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9450}]}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"The following link was found on the example.com page:\n- [Learn more](https://iana.org/domains/example)"},"wait_for_previous":true},"id":"1lqryjfq"},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":9450,"candidatesTokenCount":57,"totalTokenCount":9846,"promptTokensDetails":[{"modality":"TEXT","tokenCount":9450}],"thoughtsTokenCount":339}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10827,"candidatesTokenCount":57,"totalTokenCount":11223,"cachedContentTokenCount":8004,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10827}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8004}],"thoughtsTokenCount":339}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10731,"candidatesTokenCount":1,"totalTokenCount":10798,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10731}],"thoughtsTokenCount":66}},{"candidates":[{"content":{"parts":[{"text":" page title of example.com is \"Example Domain\". The link found on the page is:\n- [Learn more](https://www"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10850,"candidatesTokenCount":29,"totalTokenCount":10945,"cachedContentTokenCount":8113,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10850}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8113}],"thoughtsTokenCount":66}},{"candidates":[{"content":{"parts":[{"text":".iana.org/domains/example)"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":10850,"candidatesTokenCount":38,"totalTokenCount":10954,"cachedContentTokenCount":8113,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10850}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8113}],"thoughtsTokenCount":66}},{"candidates":[{"content":{"parts":[{"text":"","thoughtSignature":"EtsCCtgCAb4+9vsG6jAGgwWyEfGwT99Cs3RhM4EVEyjTlze2DxNUtsRE7mMenqfZcQie9h4+kTEKjQM20PXBD/IFsUIEozrdJbLJhm9CpVQlqG1yBh2q8q/43jRmb8A2T/JcjCr+3raGAOkRHgiBlTkdvcAAQdHhVa9S+WyI1mtHOZ/Caa2Zx9bgKFB7GEmHQud+39HwlwL8ZZMy/yfHNk8C1PYfwnEvvBGiqe2wL6w+BdMx1X+2uixe62VwwxBx8tLvVV7U+RTagCH8xLAl8AZUtFYuOOh9cdeNjLYtSmajVp5NQyybriDy5J1+zmmBW0EGrunTZ6YZOBI/NJaogboeuNrX51l4I1bWYHzrgY5yeeclxhYgYSPs/RcW0lxcJwIlH5FwZBVkVra14U/RvAiL8/PxTTVROtp//zZLNgEav6S+KEiTqEV7yzwd797WkDG9NIAyBX235WpRVTc="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10850,"candidatesTokenCount":38,"totalTokenCount":10954,"cachedContentTokenCount":8113,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10850}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":8113}],"thoughtsTokenCount":66}}]}
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll navigate to https://example.com and take a screenshot for you."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to https://example.com and take a screenshot of the page"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":40,"totalTokenCount":140}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com and captured a screenshot. The page shows the Example Domain header with explanatory text."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully navigated to https://example.com and captured a screenshot. The page shows the familiar \"Example Domain\" header with explanatory text below it. The screenshot captures the clean, minimal layout of this demonstration website."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}
|
||||
@@ -0,0 +1,6 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll help you navigate to https://example.com and perform both operations - capturing the accessibility tree and taking a screenshot."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Navigate to https://example.com, take a snapshot of the accessibility tree, then take a screenshot"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":45,"totalTokenCount":145}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_screenshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":20,"totalTokenCount":220}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Successfully navigated to https://example.com, captured accessibility tree snapshot and took a screenshot. Page title is 'Example Domain'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":250,"candidatesTokenCount":40,"totalTokenCount":290}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I've successfully completed both operations on https://example.com:\n\n**Accessibility Tree Snapshot**: The page has a clear structure with the main heading \"Example Domain\" and descriptive text about the domain's purpose for documentation examples.\n\n**Screenshot**: Captured a visual representation of the page showing the clean, minimal layout with the heading and explanatory text.\n\nBoth the accessibility data and visual screenshot confirm this is the standard example domain page used for documentation purposes."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":80,"totalTokenCount":280}}]}
|
||||
@@ -0,0 +1,367 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
/**
|
||||
* Integration tests for the browser agent.
|
||||
*
|
||||
* These tests verify the complete end-to-end flow from CLI prompt through
|
||||
* browser_agent delegation to MCP/Chrome DevTools and back. Unlike the unit
|
||||
* tests in packages/core/src/agents/browser/ which mock all MCP components,
|
||||
* these tests launch real Chrome instances in headless mode.
|
||||
*
|
||||
* Tests are skipped on systems without Chrome/Chromium installed.
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig, assertModelHasOutput } from './test-helper.js';
|
||||
import { dirname, join } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { execSync } from 'node:child_process';
|
||||
import { existsSync } from 'node:fs';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
||||
const chromeAvailable = (() => {
|
||||
try {
|
||||
if (process.platform === 'darwin') {
|
||||
execSync(
|
||||
'test -d "/Applications/Google Chrome.app" || test -d "/Applications/Chromium.app"',
|
||||
{
|
||||
stdio: 'ignore',
|
||||
},
|
||||
);
|
||||
} else if (process.platform === 'linux') {
|
||||
execSync(
|
||||
'which google-chrome || which chromium-browser || which chromium',
|
||||
{ stdio: 'ignore' },
|
||||
);
|
||||
} else if (process.platform === 'win32') {
|
||||
// Check standard Windows installation paths using Node.js fs
|
||||
const chromePaths = [
|
||||
'C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe',
|
||||
'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe',
|
||||
`${process.env['LOCALAPPDATA'] ?? ''}\\Google\\Chrome\\Application\\chrome.exe`,
|
||||
];
|
||||
const found = chromePaths.some((p) => existsSync(p));
|
||||
if (!found) {
|
||||
// Fall back to PATH check
|
||||
execSync('where chrome || where chromium', { stdio: 'ignore' });
|
||||
}
|
||||
} else {
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
})();
|
||||
|
||||
describe.skipIf(!chromeAvailable)('browser-agent', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should navigate to a page and capture accessibility tree', async () => {
|
||||
rig.setup('browser-navigate-and-snapshot', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent.navigate-snapshot.responses',
|
||||
),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Open https://example.com in the browser and tell me the page title and main content.',
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
});
|
||||
|
||||
it('should take screenshots of web pages', async () => {
|
||||
rig.setup('browser-screenshot', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.screenshot.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Navigate to https://example.com and take a screenshot.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserCalls = toolLogs.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(browserCalls.length).toBeGreaterThan(0);
|
||||
|
||||
assertModelHasOutput(result);
|
||||
});
|
||||
|
||||
it('should interact with page elements', async () => {
|
||||
rig.setup('browser-interaction', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.interaction.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Go to https://example.com, find any links on the page, and describe them.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserAgentCall = toolLogs.find(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(
|
||||
browserAgentCall,
|
||||
'Expected browser_agent to be called',
|
||||
).toBeDefined();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
});
|
||||
|
||||
it('should clean up browser processes after completion', async () => {
|
||||
rig.setup('browser-cleanup', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.cleanup.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
args: 'Open https://example.com in the browser and check the page title.',
|
||||
});
|
||||
|
||||
// Test passes if we reach here, relying on Vitest's timeout mechanism
|
||||
// to detect hanging browser processes.
|
||||
});
|
||||
|
||||
it('should handle multiple browser operations in sequence', async () => {
|
||||
rig.setup('browser-sequential', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.sequential.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Navigate to https://example.com, take a snapshot of the accessibility tree, then take a screenshot.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserCalls = toolLogs.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
expect(browserCalls.length).toBeGreaterThan(0);
|
||||
|
||||
// Should successfully complete all operations
|
||||
assertModelHasOutput(result);
|
||||
});
|
||||
|
||||
it('should keep browser open across multiple browser_agent invocations', async () => {
|
||||
rig.setup('browser-persistent-session', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent.persistent-session.responses',
|
||||
),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
allowedDomains: ['example.com'],
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'First, ask the browser agent to get the page title of example.com. After you receive that response, you MUST invoke the browser agent a second time to check for links on the page.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserCalls = toolLogs.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
|
||||
// Both browser_agent invocations must succeed — if the browser was
|
||||
// incorrectly closed after the first call (regression #24210),
|
||||
// the second call would fail.
|
||||
expect(
|
||||
browserCalls.length,
|
||||
'Expected browser_agent to be called twice',
|
||||
).toBe(2);
|
||||
expect(
|
||||
browserCalls.every((c) => c.toolRequest.success),
|
||||
'Both browser_agent calls should succeed',
|
||||
).toBe(true);
|
||||
|
||||
assertModelHasOutput(result);
|
||||
});
|
||||
|
||||
it('should handle tool confirmation for write_file without crashing', async () => {
|
||||
rig.setup('tool-confirmation', {
|
||||
fakeResponsesPath: join(
|
||||
__dirname,
|
||||
'browser-agent.confirmation.responses',
|
||||
),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive({ approvalMode: 'default' });
|
||||
|
||||
await run.type('Write hello to test.txt');
|
||||
await run.type('\r');
|
||||
|
||||
await run.expectText('Allow', 15000);
|
||||
|
||||
await run.type('y');
|
||||
await run.type('\r');
|
||||
|
||||
await run.expectText('successfully written', 15000);
|
||||
});
|
||||
|
||||
it('should handle concurrent browser agents with isolated session mode', async () => {
|
||||
rig.setup('browser-concurrent', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.concurrent.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
// Isolated mode supports concurrent browser agents.
|
||||
// Persistent/existing modes reject concurrent calls to prevent
|
||||
// Chrome profile lock conflicts.
|
||||
sessionMode: 'isolated',
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: 'Launch two browser agents concurrently to check example.com',
|
||||
});
|
||||
|
||||
assertModelHasOutput(result);
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const browserCalls = toolLogs.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === 'invoke_agent' &&
|
||||
JSON.parse(t.toolRequest.args).agent_name === 'browser_agent',
|
||||
);
|
||||
|
||||
// Both browser_agent invocations should have been called
|
||||
expect(browserCalls.length).toBe(2);
|
||||
|
||||
// Both should complete successfully (no errors)
|
||||
for (const call of browserCalls) {
|
||||
expect(
|
||||
call.toolRequest.success,
|
||||
`browser_agent call failed: ${JSON.stringify(call.toolRequest)}`,
|
||||
).toBe(true);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll help you with that."},{"functionCall":{"name":"invoke_agent","args":{"agent_name":"browser_agent","prompt":"Open https://example.com and check if there is a heading"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"new_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"success":true,"summary":"SUCCESS_POLICY_TEST_COMPLETED"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Task completed successfully. The page has the heading \"Example Domain\"."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}
|
||||
@@ -0,0 +1,240 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig, poll } from './test-helper.js';
|
||||
import { dirname, join } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { execSync } from 'node:child_process';
|
||||
import { existsSync, writeFileSync, readFileSync, mkdirSync } from 'node:fs';
|
||||
import { env } from 'node:process';
|
||||
import stripAnsi from 'strip-ansi';
|
||||
|
||||
// Browser agent Chrome DevTools MCP connection is flaky in Docker sandbox.
|
||||
// See: https://github.com/google-gemini/gemini-cli/issues/24382
|
||||
const isDockerSandbox = env['GEMINI_SANDBOX'] === 'docker';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
||||
const chromeAvailable = (() => {
|
||||
try {
|
||||
if (process.platform === 'darwin') {
|
||||
execSync(
|
||||
'test -d "/Applications/Google Chrome.app" || test -d "/Applications/Chromium.app"',
|
||||
{
|
||||
stdio: 'ignore',
|
||||
},
|
||||
);
|
||||
} else if (process.platform === 'linux') {
|
||||
execSync(
|
||||
'which google-chrome || which chromium-browser || which chromium',
|
||||
{ stdio: 'ignore' },
|
||||
);
|
||||
} else if (process.platform === 'win32') {
|
||||
const chromePaths = [
|
||||
'C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe',
|
||||
'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe',
|
||||
`${process.env['LOCALAPPDATA'] ?? ''}\\Google\\Chrome\\Application\\chrome.exe`,
|
||||
];
|
||||
const found = chromePaths.some((p) => existsSync(p));
|
||||
if (!found) {
|
||||
execSync('where chrome || where chromium', { stdio: 'ignore' });
|
||||
}
|
||||
} else {
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
})();
|
||||
|
||||
describe.skipIf(!chromeAvailable)('browser-policy', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it.skipIf(isDockerSandbox)(
|
||||
'should skip confirmation when "Allow all server tools for this session" is chosen',
|
||||
async () => {
|
||||
rig.setup('browser-policy-skip-confirmation', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-policy.responses'),
|
||||
settings: {
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
headless: true,
|
||||
sessionMode: 'isolated',
|
||||
allowedDomains: ['example.com'],
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
// Manually trust the folder to avoid the dialog and enable option 3
|
||||
const geminiDir = join(rig.homeDir!, '.gemini');
|
||||
mkdirSync(geminiDir, { recursive: true });
|
||||
|
||||
// Write to trustedFolders.json
|
||||
const trustedFoldersPath = join(geminiDir, 'trustedFolders.json');
|
||||
const trustedFolders = {
|
||||
[rig.testDir!]: 'TRUST_FOLDER',
|
||||
};
|
||||
writeFileSync(
|
||||
trustedFoldersPath,
|
||||
JSON.stringify(trustedFolders, null, 2),
|
||||
);
|
||||
|
||||
// Force confirmation for browser agent.
|
||||
// NOTE: We don't force confirm browser tools here because "Allow all server tools"
|
||||
// adds a rule with ALWAYS_ALLOW_PRIORITY (3.9x) which would be overshadowed by
|
||||
// a rule in the user tier (4.x) like the one from this TOML.
|
||||
// By removing the explicit mcp rule, the first MCP tool will still prompt
|
||||
// due to default approvalMode = 'default', and then "Allow all" will correctly
|
||||
// bypass subsequent tools.
|
||||
const policyFile = join(rig.testDir!, 'force-confirm.toml');
|
||||
writeFileSync(
|
||||
policyFile,
|
||||
`
|
||||
[[rule]]
|
||||
name = "Force confirm browser_agent"
|
||||
toolName = "invoke_agent"
|
||||
argsPattern = "\\"agent_name\\":\\\\s*\\"browser_agent\\""
|
||||
decision = "ask_user"
|
||||
priority = 200
|
||||
`,
|
||||
);
|
||||
|
||||
// Update settings.json in both project and home directories to point to the policy file
|
||||
for (const baseDir of [rig.testDir!, rig.homeDir!]) {
|
||||
const settingsPath = join(baseDir, '.gemini', 'settings.json');
|
||||
if (existsSync(settingsPath)) {
|
||||
const settings = JSON.parse(readFileSync(settingsPath, 'utf-8'));
|
||||
settings.policyPaths = [policyFile];
|
||||
// Ensure folder trust is enabled
|
||||
settings.security = settings.security || {};
|
||||
settings.security.folderTrust = settings.security.folderTrust || {};
|
||||
settings.security.folderTrust.enabled = true;
|
||||
writeFileSync(settingsPath, JSON.stringify(settings, null, 2));
|
||||
}
|
||||
}
|
||||
|
||||
const run = await rig.runInteractive({
|
||||
approvalMode: 'default',
|
||||
env: {
|
||||
GEMINI_CLI_INTEGRATION_TEST: 'true',
|
||||
},
|
||||
});
|
||||
|
||||
await run.sendKeys(
|
||||
'Open https://example.com and check if there is a heading\r',
|
||||
);
|
||||
await run.sendKeys('\r');
|
||||
|
||||
// Handle confirmations.
|
||||
// 1. Initial browser_agent delegation (likely only 3 options, so use option 1: Allow once)
|
||||
await poll(
|
||||
() => stripAnsi(run.output).toLowerCase().includes('action required'),
|
||||
60000,
|
||||
1000,
|
||||
);
|
||||
await run.sendKeys('1\r');
|
||||
await new Promise((r) => setTimeout(r, 2000));
|
||||
|
||||
// Handle privacy notice
|
||||
await poll(
|
||||
() => stripAnsi(run.output).toLowerCase().includes('privacy notice'),
|
||||
5000,
|
||||
100,
|
||||
);
|
||||
await run.sendKeys('1\r');
|
||||
await new Promise((r) => setTimeout(r, 5000));
|
||||
|
||||
// new_page (MCP tool, should have 4 options, use option 3: Allow all server tools)
|
||||
await poll(
|
||||
() => {
|
||||
const stripped = stripAnsi(run.output).toLowerCase();
|
||||
return (
|
||||
stripped.includes('new_page') &&
|
||||
stripped.includes('allow all server tools for this session')
|
||||
);
|
||||
},
|
||||
60000,
|
||||
1000,
|
||||
);
|
||||
|
||||
// Select "Allow all server tools for this session" (option 3)
|
||||
await run.sendKeys('3\r');
|
||||
|
||||
// Wait for the browser agent to finish (success or failure)
|
||||
await poll(
|
||||
() => {
|
||||
const stripped = stripAnsi(run.output).toLowerCase();
|
||||
return (
|
||||
stripped.includes('completed successfully') ||
|
||||
stripped.includes('agent error')
|
||||
);
|
||||
},
|
||||
120000,
|
||||
1000,
|
||||
);
|
||||
|
||||
const output = stripAnsi(run.output).toLowerCase();
|
||||
|
||||
expect(output).toContain('browser_agent');
|
||||
// The test validates that "Allow all server tools" skips subsequent
|
||||
// tool confirmations — the browser agent may still fail due to
|
||||
// Chrome/MCP issues in CI, which is acceptable for this policy test.
|
||||
expect(
|
||||
output.includes('completed successfully') ||
|
||||
output.includes('agent error'),
|
||||
).toBe(true);
|
||||
},
|
||||
);
|
||||
|
||||
it('should show the visible warning when browser agent starts in existing session mode', async () => {
|
||||
rig.setup('browser-session-warning', {
|
||||
fakeResponsesPath: join(__dirname, 'browser-agent.cleanup.responses'),
|
||||
settings: {
|
||||
general: {
|
||||
enableAutoUpdateNotification: false,
|
||||
},
|
||||
agents: {
|
||||
overrides: {
|
||||
browser_agent: {
|
||||
enabled: true,
|
||||
},
|
||||
},
|
||||
browser: {
|
||||
sessionMode: 'existing',
|
||||
headless: true,
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const stdout = await rig.runCommand(['Open https://example.com'], {
|
||||
env: {
|
||||
GEMINI_API_KEY: 'fake-key',
|
||||
GEMINI_TELEMETRY_DISABLED: 'true',
|
||||
DEV: 'true',
|
||||
},
|
||||
});
|
||||
|
||||
expect(stdout).toContain('saved logins will be visible');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,155 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import * as fs from 'node:fs/promises';
|
||||
import * as path from 'node:path';
|
||||
import * as os from 'node:os';
|
||||
import { GitService, Storage } from '@google/gemini-cli-core';
|
||||
|
||||
describe('Checkpointing Integration', () => {
|
||||
let tmpDir: string;
|
||||
let projectRoot: string;
|
||||
let fakeHome: string;
|
||||
let originalEnv: NodeJS.ProcessEnv;
|
||||
|
||||
beforeEach(async () => {
|
||||
tmpDir = await fs.mkdtemp(
|
||||
path.join(os.tmpdir(), 'gemini-checkpoint-test-'),
|
||||
);
|
||||
projectRoot = path.join(tmpDir, 'project');
|
||||
fakeHome = path.join(tmpDir, 'home');
|
||||
|
||||
await fs.mkdir(projectRoot, { recursive: true });
|
||||
await fs.mkdir(fakeHome, { recursive: true });
|
||||
|
||||
// Save original env
|
||||
originalEnv = { ...process.env };
|
||||
|
||||
// Simulate environment with NO global gitconfig
|
||||
process.env['HOME'] = fakeHome;
|
||||
delete process.env['GIT_CONFIG_GLOBAL'];
|
||||
delete process.env['GIT_CONFIG_SYSTEM'];
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
// Restore env
|
||||
process.env = originalEnv;
|
||||
|
||||
// Cleanup
|
||||
try {
|
||||
await fs.rm(tmpDir, { recursive: true, force: true });
|
||||
} catch (e) {
|
||||
console.error('Failed to cleanup temp dir', e);
|
||||
}
|
||||
});
|
||||
|
||||
it('should successfully create and restore snapshots without global git config', async () => {
|
||||
const storage = new Storage(projectRoot);
|
||||
const gitService = new GitService(projectRoot, storage);
|
||||
|
||||
// 1. Initialize
|
||||
await gitService.initialize();
|
||||
|
||||
// Verify system config empty file creation
|
||||
// We need to access getHistoryDir logic or replicate it.
|
||||
// Since we don't have access to private getHistoryDir, we can infer it or just trust the functional test.
|
||||
|
||||
// 2. Create initial state
|
||||
await fs.writeFile(path.join(projectRoot, 'file1.txt'), 'version 1');
|
||||
await fs.writeFile(path.join(projectRoot, 'file2.txt'), 'permanent file');
|
||||
|
||||
// 3. Create Snapshot
|
||||
const snapshotHash = await gitService.createFileSnapshot('Checkpoint 1');
|
||||
expect(snapshotHash).toBeDefined();
|
||||
|
||||
// 4. Modify files
|
||||
await fs.writeFile(
|
||||
path.join(projectRoot, 'file1.txt'),
|
||||
'version 2 (BAD CHANGE)',
|
||||
);
|
||||
await fs.writeFile(
|
||||
path.join(projectRoot, 'file3.txt'),
|
||||
'new file (SHOULD BE GONE)',
|
||||
);
|
||||
await fs.rm(path.join(projectRoot, 'file2.txt'));
|
||||
|
||||
// 5. Restore
|
||||
await gitService.restoreProjectFromSnapshot(snapshotHash);
|
||||
|
||||
// 6. Verify state
|
||||
const file1Content = await fs.readFile(
|
||||
path.join(projectRoot, 'file1.txt'),
|
||||
'utf-8',
|
||||
);
|
||||
expect(file1Content).toBe('version 1');
|
||||
|
||||
const file2Exists = await fs
|
||||
.stat(path.join(projectRoot, 'file2.txt'))
|
||||
.then(() => true)
|
||||
.catch(() => false);
|
||||
expect(file2Exists).toBe(true);
|
||||
const file2Content = await fs.readFile(
|
||||
path.join(projectRoot, 'file2.txt'),
|
||||
'utf-8',
|
||||
);
|
||||
expect(file2Content).toBe('permanent file');
|
||||
|
||||
const file3Exists = await fs
|
||||
.stat(path.join(projectRoot, 'file3.txt'))
|
||||
.then(() => true)
|
||||
.catch(() => false);
|
||||
expect(file3Exists).toBe(false);
|
||||
});
|
||||
|
||||
it('should ignore user global git config and use isolated identity', async () => {
|
||||
// 1. Create a fake global gitconfig with a specific user
|
||||
const globalConfigPath = path.join(fakeHome, '.gitconfig');
|
||||
const globalConfigContent = `[user]
|
||||
name = Global User
|
||||
email = global@example.com
|
||||
`;
|
||||
await fs.writeFile(globalConfigPath, globalConfigContent);
|
||||
|
||||
// Point HOME to fakeHome so git picks up this global config (if we didn't isolate it)
|
||||
process.env['HOME'] = fakeHome;
|
||||
// Ensure GIT_CONFIG_GLOBAL is NOT set for the process initially,
|
||||
// so it would default to HOME/.gitconfig if GitService didn't override it.
|
||||
delete process.env['GIT_CONFIG_GLOBAL'];
|
||||
|
||||
const storage = new Storage(projectRoot);
|
||||
const gitService = new GitService(projectRoot, storage);
|
||||
|
||||
await gitService.initialize();
|
||||
|
||||
// 2. Create a file and snapshot
|
||||
await fs.writeFile(path.join(projectRoot, 'test.txt'), 'content');
|
||||
await gitService.createFileSnapshot('Snapshot with global config present');
|
||||
|
||||
// 3. Verify the commit author in the shadow repo
|
||||
const historyDir = storage.getHistoryDir();
|
||||
|
||||
const { execFileSync } = await import('node:child_process');
|
||||
|
||||
const logOutput = execFileSync(
|
||||
'git',
|
||||
['log', '-1', '--pretty=format:%an <%ae>'],
|
||||
{
|
||||
cwd: historyDir,
|
||||
env: {
|
||||
...process.env,
|
||||
GIT_DIR: path.join(historyDir, '.git'),
|
||||
GIT_CONFIG_GLOBAL: path.join(historyDir, '.gitconfig'),
|
||||
GIT_CONFIG_SYSTEM: path.join(historyDir, '.gitconfig_system_empty'),
|
||||
},
|
||||
encoding: 'utf-8',
|
||||
},
|
||||
);
|
||||
|
||||
expect(logOutput).toBe('Gemini CLI <gemini-cli@google.com>');
|
||||
expect(logOutput).not.toContain('Global User');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,110 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { execSync, spawnSync } from 'node:child_process';
|
||||
import * as os from 'node:os';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
|
||||
// Minimal 1x1 PNG image base64
|
||||
const DUMMY_PNG_BASE64 =
|
||||
'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
|
||||
|
||||
describe('Linux Clipboard Integration', () => {
|
||||
let rig: TestRig;
|
||||
let dummyImagePath: string;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
// Create a dummy image file for testing
|
||||
dummyImagePath = path.join(
|
||||
os.tmpdir(),
|
||||
`gemini-test-clipboard-${Date.now()}.png`,
|
||||
);
|
||||
fs.writeFileSync(dummyImagePath, Buffer.from(DUMMY_PNG_BASE64, 'base64'));
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
try {
|
||||
if (fs.existsSync(dummyImagePath)) {
|
||||
fs.unlinkSync(dummyImagePath);
|
||||
}
|
||||
} catch {
|
||||
// Ignore cleanup errors
|
||||
}
|
||||
});
|
||||
|
||||
// Only run this test on Linux
|
||||
const runIfLinux = os.platform() === 'linux' ? it : it.skip;
|
||||
|
||||
runIfLinux(
|
||||
'should paste image from system clipboard when Ctrl+V is pressed',
|
||||
async () => {
|
||||
// 1. Setup rig
|
||||
await rig.setup('linux-clipboard-paste');
|
||||
|
||||
// 2. Inject image into system clipboard
|
||||
// We attempt both Wayland and X11 tools.
|
||||
let clipboardSet = false;
|
||||
|
||||
// Try wl-copy (Wayland)
|
||||
let sessionType = '';
|
||||
const wlCopy = spawnSync('wl-copy', ['--type', 'image/png'], {
|
||||
input: fs.readFileSync(dummyImagePath),
|
||||
});
|
||||
if (wlCopy.status === 0) {
|
||||
clipboardSet = true;
|
||||
sessionType = 'wayland';
|
||||
} else {
|
||||
// Try xclip (X11)
|
||||
try {
|
||||
execSync(
|
||||
`xclip -selection clipboard -t image/png -i "${dummyImagePath}"`,
|
||||
{ stdio: 'ignore' },
|
||||
);
|
||||
clipboardSet = true;
|
||||
sessionType = 'x11';
|
||||
} catch {
|
||||
// Both failed
|
||||
}
|
||||
}
|
||||
|
||||
if (!clipboardSet) {
|
||||
console.warn(
|
||||
'Skipping test: Could not access system clipboard (wl-copy or xclip required)',
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
// 3. Launch CLI and simulate Ctrl+V
|
||||
// We send the control character \u0016 (SYN) which corresponds to Ctrl+V
|
||||
// Note: The CLI must be running and accepting input.
|
||||
// The TestRig usually sends args/stdin and waits for exit or output.
|
||||
// To properly test "interactive" pasting, we need the rig to support sending input *while* running.
|
||||
// Assuming rig.run with 'stdin' sends it immediately.
|
||||
// The CLI treats stdin as typed input if it's interactive.
|
||||
|
||||
// We append a small delay or a newline to ensure processing?
|
||||
// Ctrl+V (\u0016) followed by a newline (\r) to submit?
|
||||
// Or just Ctrl+V and check if the buffer updates (which we can't easily see in non-verbose rig output).
|
||||
// If we send Ctrl+V then Enter, the CLI should submit the prompt containing the image path.
|
||||
|
||||
const result = await rig.run({
|
||||
stdin: '\u0016\r', // Ctrl+V then Enter
|
||||
env: { XDG_SESSION_TYPE: sessionType },
|
||||
});
|
||||
|
||||
// 4. Verify Output
|
||||
// Expect the CLI to have processed the image and echoed back the path (or the prompt containing it)
|
||||
// The output usually contains the user's input echoed back + model response.
|
||||
// The pasted image path should look like @.../clipboard-....png
|
||||
expect(result).toMatch(/@\/.*\.gemini-clipboard\/clipboard-.*\.png/);
|
||||
},
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,12 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/1"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/2"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/3"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/4"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/5"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/6"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/7"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/8"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/9"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/10"}}},{"functionCall":{"name":"web_fetch","args":{"prompt":"fetch https://example.com/11"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":500,"totalTokenCount":600}}]}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 1 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 2 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 3 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 4 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 5 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 6 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 7 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 8 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 9 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"Page 10 content"}],"role":"model"},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Some requests were rate limited: Rate limit exceeded for host. Please wait 60 seconds before trying again."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":1000,"candidatesTokenCount":50,"totalTokenCount":1050}}]}
|
||||
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
|
||||
describe('web-fetch rate limiting', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (rig) {
|
||||
await rig.cleanup();
|
||||
}
|
||||
});
|
||||
|
||||
it('should rate limit multiple requests to the same host', async () => {
|
||||
rig.setup('web-fetch rate limit', {
|
||||
settings: { tools: { core: ['web_fetch'] } },
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'concurrency-limit.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const result = await rig.run({
|
||||
args: `Fetch 11 pages from example.com`,
|
||||
});
|
||||
|
||||
// We expect to find at least one tool call that failed with a rate limit error.
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const rateLimitedCalls = toolLogs.filter(
|
||||
(log) =>
|
||||
log.toolRequest.name === 'web_fetch' &&
|
||||
(
|
||||
('error' in log.toolRequest
|
||||
? (log.toolRequest as unknown as Record<string, string>)['error']
|
||||
: '') as string
|
||||
)?.includes('Rate limit exceeded'),
|
||||
);
|
||||
|
||||
expect(rateLimitedCalls.length).toBeGreaterThan(0);
|
||||
expect(result).toContain('Rate limit exceeded');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,3 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Observing Initial Conditions**\n\nI'm currently focused on the initial context. I've taken note of the provided date, OS, and working directory. I'm also carefully examining the file structure presented within the current working directory. It's helping me understand the starting point for further analysis.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12316,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":46}},{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Assessing User Intent**\n\nI'm now shifting my focus. I've successfully registered the provided data and file structure. My current task is to understand the user's ultimate goal, given the information provided. The \"Hello.\" command is straightforward, but I'm checking if there's an underlying objective.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12341,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":71}},{"candidates":[{"content":{"parts":[{"thoughtSignature":"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","text":"Hello."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12341,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":71}}]}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"<state_snapshot>\n <overall_goal>\n <!-- The user has not yet specified a goal. -->\n </overall_goal>\n\n <key_knowledge>\n - OS: linux\n - Date: Friday, October 24, 2025\n </key_knowledge>\n\n <file_system_state>\n - OBSERVED: The directory contains `telemetry.log` and a `.gemini/` directory.\n - OBSERVED: The `.gemini/` directory contains `settings.json` and `settings.json.orig`.\n </file_system_state>\n\n <recent_actions>\n - The user initiated the chat.\n </recent_actions>\n\n <current_plan>\n 1. [TODO] Await the user's first instruction to formulate a plan.\n </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":983,"candidatesTokenCount":299,"totalTokenCount":1637,"promptTokensDetails":[{"modality":"TEXT","tokenCount":983}],"thoughtsTokenCount":355}}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"<state_snapshot>\n <overall_goal>\n <!-- The user has not yet specified a goal. -->\n </overall_goal>\n\n <key_knowledge>\n - OS: linux\n - Date: Friday, October 24, 2025\n </key_knowledge>\n\n <file_system_state>\n - OBSERVED: The directory contains `telemetry.log` and a `.gemini/` directory.\n - OBSERVED: The `.gemini/` directory contains `settings.json` and `settings.json.orig`.\n </file_system_state>\n\n <recent_actions>\n - The user initiated the chat.\n </recent_actions>\n\n <current_plan>\n 1. [TODO] Await the user's first instruction to formulate a plan.\n </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":983,"candidatesTokenCount":299,"totalTokenCount":1637,"promptTokensDetails":[{"modality":"TEXT","tokenCount":983}],"thoughtsTokenCount":355}}}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Generating a Story**\n\nI've crafted the robot story. The narrative is complete and meets the length requirement. Now, I'm getting ready to use the `write_file` tool to save it. I'm choosing the filename `robot_story.txt` as a default.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12352,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"thoughtsTokenCount":70}},{"candidates":[{"finishReason":"MALFORMED_FUNCTION_CALL","index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12282,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Drafting the Narrative**\n\nI'm currently focused on the narrative's central conflict. I'm aiming for a compelling story about a robot and am working to keep the word count tight. The \"THE _END.\" conclusion is proving challenging to integrate organically. I need to make the ending feel natural and satisfying.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12326,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"thoughtSignature":"CikB0e2Kb7zkpgRyJXXNt6ykO/+FoOglhrKxjLgoESrgafzIZak2Ofxo1gpaAdHtim9aG7MvpXlIg+n2zgmcDBWOPXtvQHxhE9k8pR+DO8i2jIe3tMWLxdN944XpUlR9vaNmVdtSRMKr4MhB/t1R3WSWR3QYhk7MEQxnjYR7cv/pR9viwZyFCoYBAdHtim/xKmMl/S+U8p+p9848q4agsL/STufluXewPqL3uJSinZbN0Z4jTYfMzXKldhDYIonvw3Crn/Y11oAjnT656Sx0kkKtavAXbiU/WsGyDxZbNhLofnJGQxruljPGztxkKawz1cTiQnddnQRfLddhy+3iJIOSh6ZpYq9uGHz3PzVkUuQ=","text":"Unit 734 whirred, its optical sensors scanning the desolate junkyard. For years, its purpose had been clear: compress refuse, maintain order. But today, a glint of tarnished silver beneath a rusted hull"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":47,"totalTokenCount":12373,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" caught its attention. It was a discarded music box, its delicate gears jammed, a faint, melancholic tune trapped within.\n\n734 usually crushed, never salvaged. Yet, a new directive flickered in its circuits – curiosity."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":95,"totalTokenCount":12421,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" With surprising gentleness for its formidable pincers, it retrieved the box. Back in its monochrome workshop, it meticulously cleaned and repaired. Each tiny spring, each worn tooth, became a puzzle.\n\nHours later, a soft, ethereal melody filled the clang"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":146,"totalTokenCount":12472,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":"orous space. The music box sang. 734 felt a strange, new sensation – a warmth in its core processors, a hum of contentment. Its existence, once solely utilitarian, now held a note of beauty, a hint of something more than"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":197,"totalTokenCount":12523,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" just compression. It had fixed a broken song, and in doing so, had found a different kind of purpose. THE_END."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":224,"totalTokenCount":12550,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}}]}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"scratchpad\nThe user's overall goal was to write a 200-word story about a robot, ending with \"THE_END.\". The agent successfully completed this task.\n\nSince the task is complete, the snapshot should reflect that the goal has been achieved and there are no further actions planned regarding the story.\n\nLet's break down the required sections for the snapshot:\n\n1. **Overall Goal**: The initial goal was to write a story. This has been completed.\n2. **Key Knowledge**: No specific key knowledge was provided or discovered during this simple interaction beyond the prompt's constraints.\n3. **File System State**: No files were read, modified, or created by the agent relevant to the task. The initial file system state was merely provided for context.\n4. **Recent Actions**: The agent wrote the story.\n5. **Current Plan**: The plan was to write the story, which is now done. Therefore, the plan should indicate completion."},{"text":"<state_snapshot>\n <overall_goal>\n Write a 200-word story about a robot, ending with \"THE_END.\".\n </overall_goal>\n\n <key_knowledge>\n - The story must be approximately 200 words.\n - The story must end with the exact phrase \"THE_END.\"\n </key_knowledge>\n\n <file_system_state>\n <!-- No relevant file system interactions occurred during this task. -->\n </file_system_state>\n\n <recent_actions>\n - Generated a 200-word story about a robot, successfully ending it with \"THE_END.\".\n </recent_actions>\n\n <current_plan>\n 1. [DONE] Write a 200-word story about a robot.\n 2. [DONE] Ensure the story ends with the exact text \"THE_END.\".\n </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":1223,"candidatesTokenCount":424,"totalTokenCount":1647,"promptTokensDetails":[{"modality":"TEXT","tokenCount":1223}]}}}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"scratchpad\nThe user's overall goal was to write a 200-word story about a robot, ending with \"THE_END.\". The agent successfully completed this task.\n\nSince the task is complete, the snapshot should reflect that the goal has been achieved and there are no further actions planned regarding the story.\n\nLet's break down the required sections for the snapshot:\n\n1. **Overall Goal**: The initial goal was to write a story. This has been completed.\n2. **Key Knowledge**: No specific key knowledge was provided or discovered during this simple interaction beyond the prompt's constraints.\n3. **File System State**: No files were read, modified, or created by the agent relevant to the task. The initial file system state was merely provided for context.\n4. **Recent Actions**: The agent wrote the story.\n5. **Current Plan**: The plan was to write the story, which is now done. Therefore, the plan should indicate completion."},{"text":"<state_snapshot>\n <overall_goal>\n Write a 200-word story about a robot, ending with \"THE_END.\".\n </overall_goal>\n\n <key_knowledge>\n - The story must be approximately 200 words.\n - The story must end with the exact phrase \"THE_END.\"\n </key_knowledge>\n\n <file_system_state>\n <!-- No relevant file system interactions occurred during this task. -->\n </file_system_state>\n\n <recent_actions>\n - Generated a 200-word story about a robot, successfully ending it with \"THE_END.\".\n </recent_actions>\n\n <current_plan>\n 1. [DONE] Write a 200-word story about a robot.\n 2. [DONE] Ensure the story ends with the exact text \"THE_END.\".\n </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":1223,"candidatesTokenCount":424,"totalTokenCount":1647,"promptTokensDetails":[{"modality":"TEXT","tokenCount":1223}]}}}
|
||||
@@ -0,0 +1,120 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { expect, describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
|
||||
// Skip on macOS: every interactive test in this file is chronically flaky
|
||||
// because the captured pty buffer contains the CLI's startup escape
|
||||
// sequences (`q4;?m...true color warning`) instead of the streamed output,
|
||||
// causing `expectText(...)` to time out. Reproducible across unrelated
|
||||
// runs on `main` (24740161950, 24739323404) and on consecutive merge-queue
|
||||
// gates for #25753 (24743605639, 24747624513) — different tests in the
|
||||
// same describe fail on different runs. Not specific to any model.
|
||||
const skipOnDarwin = process.platform === 'darwin';
|
||||
|
||||
describe.skipIf(skipOnDarwin)('Interactive Mode', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should trigger chat compression with /compress command', async () => {
|
||||
await rig.setup('interactive-compress-success', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'context-compress-interactive.compress.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
|
||||
await run.sendKeys(
|
||||
'Write a 200 word story about a robot. The story MUST end with the text THE_END followed by a period.',
|
||||
);
|
||||
await run.type('\r');
|
||||
|
||||
// Wait for the specific end marker.
|
||||
await run.expectText('THE_END.', 30000);
|
||||
|
||||
await run.type('/compress');
|
||||
await run.type('\r');
|
||||
|
||||
const foundEvent = await rig.waitForTelemetryEvent(
|
||||
'chat_compression',
|
||||
25000,
|
||||
);
|
||||
expect(foundEvent, 'chat_compression telemetry event was not found').toBe(
|
||||
true,
|
||||
);
|
||||
|
||||
await run.expectText('Chat history compressed', 5000);
|
||||
});
|
||||
|
||||
// TODO: Context compression is broken and doesn't include the system
|
||||
// instructions or tool counts, so it thinks compression is beneficial when
|
||||
// it is in fact not.
|
||||
it.skip('should handle compression failure on token inflation', async () => {
|
||||
await rig.setup('interactive-compress-failure', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'context-compress-interactive.compress-failure.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
|
||||
await run.type('Respond with exactly "Hello" followed by a period');
|
||||
await run.type('\r');
|
||||
|
||||
await run.expectText('Hello.', 25000);
|
||||
|
||||
await run.type('/compress');
|
||||
await run.type('\r');
|
||||
await run.expectText('compression was not beneficial', 25000);
|
||||
|
||||
// Verify no telemetry event is logged for NOOP
|
||||
const foundEvent = await rig.waitForTelemetryEvent(
|
||||
'chat_compression',
|
||||
5000,
|
||||
);
|
||||
expect(
|
||||
foundEvent,
|
||||
'chat_compression telemetry event should be found for failures',
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it('should handle /compress command on empty history', async () => {
|
||||
rig.setup('interactive-compress-empty', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'context-compress-interactive.compress-empty.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
await run.type('/compress');
|
||||
await run.type('\r');
|
||||
|
||||
await run.expectText('Nothing to compress.', 5000);
|
||||
|
||||
// Verify no telemetry event is logged for NOOP
|
||||
const foundEvent = await rig.waitForTelemetryEvent(
|
||||
'chat_compression',
|
||||
5000, // Short timeout as we expect it not to happen
|
||||
);
|
||||
expect(
|
||||
foundEvent,
|
||||
'chat_compression telemetry event should not be found for NOOP',
|
||||
).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,287 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import * as path from 'node:path';
|
||||
import * as fs from 'node:fs';
|
||||
import { FinishReason, GenerateContentResponse } from '@google/genai';
|
||||
import type { FakeResponse, HistoryTurn } from '@google/gemini-cli-core';
|
||||
|
||||
describe('Context Management Fidelity E2E', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
function generateRandomString(length: number): string {
|
||||
const characters =
|
||||
'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789';
|
||||
let result = '';
|
||||
for (let i = 0; i < length; i++) {
|
||||
result += characters.charAt(
|
||||
Math.floor(Math.random() * characters.length),
|
||||
);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it(
|
||||
'should reproduce the exact context working buffer on resume',
|
||||
{ timeout: 300000 },
|
||||
async () => {
|
||||
// Mock responses to trigger GC (summarization)
|
||||
const snapshotResponse: FakeResponse = {
|
||||
method: 'generateContent',
|
||||
response: {
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [
|
||||
{
|
||||
text: JSON.stringify({
|
||||
new_facts: ['GC Triggered.'],
|
||||
new_constraints: [],
|
||||
new_tasks: [],
|
||||
resolved_task_ids: [],
|
||||
obsolete_fact_indices: [],
|
||||
obsolete_constraint_indices: [],
|
||||
chronological_summary: 'Snapshot created.',
|
||||
}),
|
||||
},
|
||||
],
|
||||
role: 'model',
|
||||
},
|
||||
finishReason: FinishReason.STOP,
|
||||
index: 0,
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse,
|
||||
};
|
||||
|
||||
const countTokensResponse: FakeResponse = {
|
||||
method: 'countTokens',
|
||||
response: { totalTokens: 1000 },
|
||||
};
|
||||
|
||||
const streamResponse = (text: string): FakeResponse => ({
|
||||
method: 'generateContentStream',
|
||||
response: [
|
||||
{
|
||||
candidates: [
|
||||
{
|
||||
content: { parts: [{ text }], role: 'model' },
|
||||
finishReason: FinishReason.STOP,
|
||||
index: 0,
|
||||
},
|
||||
],
|
||||
},
|
||||
] as unknown as GenerateContentResponse[],
|
||||
});
|
||||
|
||||
const setupResponses = (fileName: string, mocks: FakeResponse[]) => {
|
||||
const filePath = path.join(rig.testDir!, fileName);
|
||||
fs.writeFileSync(
|
||||
filePath,
|
||||
mocks.map((m) => JSON.stringify(m)).join('\n'),
|
||||
);
|
||||
return filePath;
|
||||
};
|
||||
|
||||
await rig.setup('context-fidelity', {
|
||||
settings: {
|
||||
experimental: {
|
||||
stressTestProfile: true, // Lowers thresholds to trigger GC easily
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const traceDir = path.join(rig.testDir!, 'traces');
|
||||
fs.mkdirSync(traceDir, { recursive: true });
|
||||
const traceLog = path.join(traceDir, 'trace.log');
|
||||
|
||||
// Ignore trace and response files to keep environment context clean and stable
|
||||
fs.writeFileSync(
|
||||
path.join(rig.testDir!, '.geminiignore'),
|
||||
'traces/\nresp*.json\ndebug.log\n',
|
||||
);
|
||||
|
||||
const commonEnv = {
|
||||
GEMINI_API_KEY: 'mock-key',
|
||||
GEMINI_CONTEXT_TRACE_DIR: traceDir,
|
||||
GEMINI_CONTEXT_TRACE_ENABLED: 'true',
|
||||
GEMINI_DEBUG_LOG_FILE: path.join(rig.testDir!, 'debug.log'),
|
||||
};
|
||||
|
||||
const runMocks: FakeResponse[] = [
|
||||
streamResponse('Ack 1'),
|
||||
streamResponse('Ack 2'),
|
||||
streamResponse('Ack 3'),
|
||||
streamResponse('Ack 4'),
|
||||
streamResponse('Ack 5'),
|
||||
streamResponse('Ack 6'),
|
||||
streamResponse('Ack 7'),
|
||||
streamResponse('Ack 8'),
|
||||
streamResponse('Ack 9'),
|
||||
streamResponse('Ack 10'),
|
||||
streamResponse('Ack 11'),
|
||||
streamResponse('Ack 12'),
|
||||
];
|
||||
for (let i = 0; i < 50; i++) {
|
||||
runMocks.push(snapshotResponse);
|
||||
runMocks.push(countTokensResponse);
|
||||
}
|
||||
|
||||
// Turns 1-10: Build up history
|
||||
for (let i = 1; i <= 10; i++) {
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
i === 1 ? '' : '--resume',
|
||||
i === 1 ? '' : 'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses(`resp_init_${i}.json`, runMocks),
|
||||
].filter(Boolean),
|
||||
stdin: `Turn ${i}: ` + generateRandomString(900),
|
||||
env: commonEnv,
|
||||
});
|
||||
}
|
||||
|
||||
// Turn 11: Penultimate turn
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--resume',
|
||||
'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp2.json', runMocks),
|
||||
],
|
||||
stdin: 'Turn 11: ' + generateRandomString(900),
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
// Turn 12: Breach threshold and force GC
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--resume',
|
||||
'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp3.json', runMocks),
|
||||
],
|
||||
stdin: 'Turn 12: ' + generateRandomString(900),
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
// Extract the rendered context asset from the log
|
||||
const getRenderedContext = (logContent: string): HistoryTurn[] | null => {
|
||||
const lines = logContent.split('\n');
|
||||
const renderLines = lines.filter(
|
||||
(l) =>
|
||||
l.includes('[Render] Render Sanitized Context for LLM') ||
|
||||
l.includes('[Render] Render Context for LLM'),
|
||||
);
|
||||
if (renderLines.length === 0) return null;
|
||||
|
||||
const lastRender = renderLines[renderLines.length - 1];
|
||||
const detailsMatch = lastRender.match(/\| Details: (.*)$/);
|
||||
if (!detailsMatch) return null;
|
||||
|
||||
const details = JSON.parse(detailsMatch[1]);
|
||||
const assetInfo =
|
||||
details.renderedContextSanitized || details.renderedContext;
|
||||
if (assetInfo && assetInfo.$asset) {
|
||||
const assetPath = path.join(traceDir, 'assets', assetInfo.$asset);
|
||||
return JSON.parse(fs.readFileSync(assetPath, 'utf-8'));
|
||||
}
|
||||
return assetInfo;
|
||||
};
|
||||
|
||||
const log1 = fs.readFileSync(traceLog, 'utf-8');
|
||||
const contextBeforeExit = getRenderedContext(log1);
|
||||
expect(contextBeforeExit).toBeDefined();
|
||||
console.log(
|
||||
'Context Before Exit (First 2 turns):',
|
||||
JSON.stringify(contextBeforeExit!.slice(0, 2), null, 2),
|
||||
);
|
||||
|
||||
// Turn 4: Resume and run a small command
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--resume',
|
||||
'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp4.json', runMocks),
|
||||
'continue',
|
||||
],
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
const log2 = fs.readFileSync(traceLog, 'utf-8');
|
||||
const contextAfterResume = getRenderedContext(log2);
|
||||
expect(contextAfterResume).toBeDefined();
|
||||
console.log(
|
||||
'Context After Resume (First 2 turns):',
|
||||
JSON.stringify(contextAfterResume!.slice(0, 2), null, 2),
|
||||
);
|
||||
|
||||
expect(contextAfterResume!.length).toBeGreaterThanOrEqual(
|
||||
contextBeforeExit!.length,
|
||||
);
|
||||
|
||||
// The environment context is intentionally refreshed on resume to reflect
|
||||
// the current state of the workspace (e.g. new files, current date).
|
||||
// We allow its content to differ but ensure it's still an environment context.
|
||||
const isEnvContext = (turn: HistoryTurn) =>
|
||||
turn.content.parts?.some((p) => p.text?.includes('<session_context>'));
|
||||
|
||||
for (let i = 0; i < contextBeforeExit!.length; i++) {
|
||||
expect(contextAfterResume![i].id).toBe(contextBeforeExit![i].id);
|
||||
|
||||
const turnBefore = contextBeforeExit![i];
|
||||
const turnAfter = contextAfterResume![i];
|
||||
|
||||
if (isEnvContext(turnBefore)) {
|
||||
expect(isEnvContext(turnAfter)).toBe(true);
|
||||
continue;
|
||||
}
|
||||
|
||||
expect(turnAfter.content).toEqual(turnBefore.content);
|
||||
}
|
||||
|
||||
// Most importantly, synthetic IDs (like summaries) must be stable.
|
||||
const syntheticTurns = contextBeforeExit!.filter(
|
||||
(t: HistoryTurn) =>
|
||||
t.content.parts?.some((p) => p.text?.includes('active_tasks')) ||
|
||||
(t.id && t.id.length === 32),
|
||||
);
|
||||
expect(syntheticTurns.length).toBeGreaterThan(0);
|
||||
|
||||
const syntheticTurnsAfter = contextAfterResume!.filter(
|
||||
(t: HistoryTurn) =>
|
||||
t.content.parts?.some((p) => p.text?.includes('active_tasks')) ||
|
||||
(t.id && t.id.length === 32),
|
||||
);
|
||||
expect(syntheticTurnsAfter.length).toBeGreaterThanOrEqual(
|
||||
syntheticTurns.length,
|
||||
);
|
||||
|
||||
// Check if the first synthetic turn is identical (with relaxation for environment context)
|
||||
expect(syntheticTurnsAfter[0].id).toBe(syntheticTurns[0].id);
|
||||
if (isEnvContext(syntheticTurns[0])) {
|
||||
expect(isEnvContext(syntheticTurnsAfter[0])).toBe(true);
|
||||
} else {
|
||||
expect(syntheticTurnsAfter[0].content).toEqual(
|
||||
syntheticTurns[0].content,
|
||||
);
|
||||
}
|
||||
},
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,59 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import * as os from 'node:os';
|
||||
import { TestRig, skipFlaky } from './test-helper.js';
|
||||
|
||||
describe.skipIf(skipFlaky)('Ctrl+C exit', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should exit gracefully on second Ctrl+C', async () => {
|
||||
await rig.setup('should exit gracefully on second Ctrl+C', {
|
||||
settings: { tools: { useRipgrep: false } },
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
|
||||
// Send first Ctrl+C
|
||||
run.sendKeys('\x03');
|
||||
|
||||
await run.expectText('Press Ctrl+C again to exit', 5000);
|
||||
|
||||
if (os.platform() === 'win32') {
|
||||
// This is a workaround for node-pty/winpty on Windows.
|
||||
// Reliably sending a second Ctrl+C signal to a process that is already
|
||||
// handling the first one is not possible in the emulated pty environment.
|
||||
// The first signal is caught correctly (verified by the poll above),
|
||||
// which is the most critical part of the test on this platform.
|
||||
// To allow the test to pass, we forcefully kill the process,
|
||||
// simulating a successful exit. We accept that we cannot test the
|
||||
// graceful shutdown message on Windows in this automated context.
|
||||
run.kill();
|
||||
|
||||
const exitCode = await run.expectExit();
|
||||
// On Windows, the exit code after ptyProcess.kill() can be unpredictable
|
||||
// (often 1), so we accept any non-null exit code as a pass condition,
|
||||
// focusing on the fact that the process did terminate.
|
||||
expect(exitCode, `Process exited with code ${exitCode}.`).not.toBeNull();
|
||||
return;
|
||||
}
|
||||
|
||||
// Send second Ctrl+C
|
||||
run.sendKeys('\x03');
|
||||
|
||||
const exitCode = await run.expectExit();
|
||||
expect(exitCode, `Process exited with code ${exitCode}.`).toBe(0);
|
||||
|
||||
await run.expectText('Agent powering down. Goodbye!', 5000);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,64 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
/**
|
||||
* integration test to ensure no node.js deprecation warnings are emitted.
|
||||
* must run for all supported node versions as warnings may vary by version.
|
||||
*/
|
||||
describe('deprecation-warnings', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it.each([
|
||||
{ command: '--version', description: 'running --version' },
|
||||
{ command: '--help', description: 'running with --help' },
|
||||
])(
|
||||
'should not emit any deprecation warnings when $description',
|
||||
async ({ command, description }) => {
|
||||
await rig.setup(
|
||||
`should not emit any deprecation warnings when ${description}`,
|
||||
);
|
||||
|
||||
const { stderr, exitCode } = await rig.runWithStreams([command]);
|
||||
|
||||
// node.js deprecation warnings: (node:12345) [DEP0040] DeprecationWarning: ...
|
||||
const deprecationWarningPattern = /\[DEP\d+\].*DeprecationWarning/i;
|
||||
const hasDeprecationWarning = deprecationWarningPattern.test(stderr);
|
||||
|
||||
if (hasDeprecationWarning) {
|
||||
const deprecationMatches = stderr.match(
|
||||
/\[DEP\d+\].*DeprecationWarning:.*/gi,
|
||||
);
|
||||
const warnings = deprecationMatches
|
||||
? deprecationMatches.map((m) => m.trim()).join('\n')
|
||||
: 'Unknown deprecation warning format';
|
||||
|
||||
throw new Error(
|
||||
`Deprecation warnings detected in CLI output:\n${warnings}\n\n` +
|
||||
`Full stderr:\n${stderr}\n\n` +
|
||||
`This test ensures no deprecated Node.js modules are used. ` +
|
||||
`Please update dependencies to use non-deprecated alternatives.`,
|
||||
);
|
||||
}
|
||||
|
||||
// only check exit code if no deprecation warnings found
|
||||
if (exitCode !== 0) {
|
||||
throw new Error(
|
||||
`CLI exited with code ${exitCode} (expected 0). This may indicate a setup issue.\n` +
|
||||
`Stderr: ${stderr}`,
|
||||
);
|
||||
}
|
||||
},
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,62 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, expect, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
|
||||
const extension = `{
|
||||
"name": "test-extension-install",
|
||||
"version": "0.0.1"
|
||||
}`;
|
||||
|
||||
const extensionUpdate = `{
|
||||
"name": "test-extension-install",
|
||||
"version": "0.0.2"
|
||||
}`;
|
||||
|
||||
describe('extension install', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('installs a local extension, verifies a command, and updates it', async () => {
|
||||
rig.setup('extension install test');
|
||||
const testServerPath = join(rig.testDir!, 'gemini-extension.json');
|
||||
writeFileSync(testServerPath, extension);
|
||||
try {
|
||||
const result = await rig.runCommand(
|
||||
['--debug', 'extensions', 'install', `${rig.testDir!}`],
|
||||
{ stdin: 'y\n' },
|
||||
);
|
||||
expect(result).toContain('test-extension-install');
|
||||
|
||||
const listResult = await rig.runCommand([
|
||||
'--debug',
|
||||
'extensions',
|
||||
'list',
|
||||
]);
|
||||
expect(listResult).toContain('test-extension-install');
|
||||
writeFileSync(testServerPath, extensionUpdate);
|
||||
const updateResult = await rig.runCommand(
|
||||
['--debug', 'extensions', 'update', `test-extension-install`],
|
||||
{ stdin: 'y\n' },
|
||||
);
|
||||
expect(updateResult).toContain('0.0.2');
|
||||
} finally {
|
||||
await rig.runCommand([
|
||||
'extensions',
|
||||
'uninstall',
|
||||
'test-extension-install',
|
||||
]);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,151 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { expect, it, describe, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { TestMcpServer } from './test-mcp-server.js';
|
||||
import { writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { safeJsonStringify } from '@google/gemini-cli-core/src/utils/safeJsonStringify.js';
|
||||
|
||||
import stripAnsi from 'strip-ansi';
|
||||
|
||||
describe('extension reloading', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
// always fails
|
||||
// TODO(#14527): Re-enable this once fixed
|
||||
it.skip('installs a local extension, updates it, checks it was reloaded properly', async () => {
|
||||
const serverA = new TestMcpServer();
|
||||
const portA = await serverA.start({
|
||||
hello: () => ({ content: [{ type: 'text', text: 'world' }] }),
|
||||
});
|
||||
const extension = {
|
||||
name: 'test-extension',
|
||||
version: '0.0.1',
|
||||
mcpServers: {
|
||||
'test-server': {
|
||||
httpUrl: `http://localhost:${portA}/mcp`,
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
rig.setup('extension reload test', {
|
||||
settings: {
|
||||
experimental: { extensionReloading: true },
|
||||
},
|
||||
});
|
||||
const testServerPath = join(rig.testDir!, 'gemini-extension.json');
|
||||
writeFileSync(testServerPath, safeJsonStringify(extension, 2));
|
||||
// defensive cleanup from previous tests.
|
||||
try {
|
||||
await rig.runCommand(['extensions', 'uninstall', 'test-extension']);
|
||||
} catch {
|
||||
/* empty */
|
||||
}
|
||||
|
||||
const result = await rig.runCommand(
|
||||
['--debug', 'extensions', 'install', `${rig.testDir!}`],
|
||||
{ stdin: 'y\n' },
|
||||
);
|
||||
expect(result).toContain('test-extension');
|
||||
|
||||
// Now create the update, but its not installed yet
|
||||
const serverB = new TestMcpServer();
|
||||
const portB = await serverB.start({
|
||||
goodbye: () => ({ content: [{ type: 'text', text: 'world' }] }),
|
||||
});
|
||||
extension.version = '0.0.2';
|
||||
extension.mcpServers['test-server'].httpUrl =
|
||||
`http://localhost:${portB}/mcp`;
|
||||
writeFileSync(testServerPath, safeJsonStringify(extension, 2));
|
||||
|
||||
// Start the CLI.
|
||||
const run = await rig.runInteractive({ args: '--debug' });
|
||||
await run.expectText('You have 1 extension with an update available');
|
||||
// See the outdated extension
|
||||
await run.sendText('/extensions list');
|
||||
await run.type('\r');
|
||||
await run.expectText('test-extension (v0.0.1) - active (update available)');
|
||||
// Wait for the UI to settle and retry the command until we see the update
|
||||
await new Promise((resolve) => setTimeout(resolve, 1000));
|
||||
|
||||
// Poll for the updated list
|
||||
await rig.pollCommand(
|
||||
async () => {
|
||||
await run.sendText('/mcp list');
|
||||
await run.type('\r');
|
||||
},
|
||||
() => {
|
||||
const output = stripAnsi(run.output);
|
||||
return (
|
||||
output.includes(
|
||||
'test-server (from test-extension) - Ready (1 tool)',
|
||||
) && output.includes('- mcp_test-server_hello')
|
||||
);
|
||||
},
|
||||
30000, // 30s timeout
|
||||
);
|
||||
|
||||
// Update the extension, expect the list to update, and mcp servers as well.
|
||||
await run.sendKeys('\u0015/extensions update test-extension');
|
||||
await run.expectText('/extensions update test-extension');
|
||||
await run.type('\r');
|
||||
await new Promise((resolve) => setTimeout(resolve, 500));
|
||||
await run.type('\r');
|
||||
await run.expectText(
|
||||
` * test-server (remote): http://localhost:${portB}/mcp`,
|
||||
);
|
||||
await run.type('\r'); // consent
|
||||
await run.expectText(
|
||||
'Extension "test-extension" successfully updated: 0.0.1 → 0.0.2',
|
||||
);
|
||||
|
||||
// Poll for the updated extension version
|
||||
await rig.pollCommand(
|
||||
async () => {
|
||||
await run.sendText('/extensions list');
|
||||
await run.type('\r');
|
||||
},
|
||||
() =>
|
||||
stripAnsi(run.output).includes(
|
||||
'test-extension (v0.0.2) - active (updated)',
|
||||
),
|
||||
30000,
|
||||
);
|
||||
|
||||
// Poll for the updated mcp tool
|
||||
await rig.pollCommand(
|
||||
async () => {
|
||||
await run.sendText('/mcp list');
|
||||
await run.type('\r');
|
||||
},
|
||||
() => {
|
||||
const output = stripAnsi(run.output);
|
||||
return (
|
||||
output.includes(
|
||||
'test-server (from test-extension) - Ready (1 tool)',
|
||||
) && output.includes('- mcp_test-server_goodbye')
|
||||
);
|
||||
},
|
||||
30000,
|
||||
);
|
||||
|
||||
await run.sendText('/quit');
|
||||
await run.type('\r');
|
||||
|
||||
// Clean things up.
|
||||
await serverA.stop();
|
||||
await serverB.stop();
|
||||
await rig.runCommand(['extensions', 'uninstall', 'test-extension']);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,60 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { expect, describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
describe('Interactive file system', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should perform a read-then-write sequence', async () => {
|
||||
const fileName = 'version.txt';
|
||||
await rig.setup('interactive-read-then-write', {
|
||||
settings: {
|
||||
security: {
|
||||
auth: {
|
||||
selectedType: 'gemini-api-key',
|
||||
},
|
||||
disableYoloMode: false,
|
||||
},
|
||||
},
|
||||
});
|
||||
rig.createFile(fileName, '1.0.0');
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
|
||||
// Step 1: Read the file
|
||||
const readPrompt = `Read the version from ${fileName}`;
|
||||
await run.type(readPrompt);
|
||||
await run.type('\r');
|
||||
|
||||
const readCall = await rig.waitForToolCall('read_file', 30000);
|
||||
expect(readCall, 'Expected to find a read_file tool call').toBe(true);
|
||||
|
||||
// Step 2: Write the file
|
||||
const writePrompt = `now change the version to 1.0.1 in the file`;
|
||||
await run.type(writePrompt);
|
||||
await run.type('\r');
|
||||
|
||||
// Check tool calls made with right args
|
||||
await rig.expectToolCallSuccess(
|
||||
['write_file', 'replace'],
|
||||
30000,
|
||||
(args) => args.includes('1.0.1') && args.includes(fileName),
|
||||
);
|
||||
|
||||
// Wait for telemetry to flush and file system to sync, especially in sandboxed environments
|
||||
await rig.waitForTelemetryReady();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,297 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { existsSync } from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import {
|
||||
TestRig,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
|
||||
describe('file-system', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should be able to read a file', async () => {
|
||||
await rig.setup('should be able to read a file', {
|
||||
settings: { tools: { core: ['read_file'] } },
|
||||
});
|
||||
rig.createFile('test.txt', 'hello world');
|
||||
|
||||
const result = await rig.run({
|
||||
args: `read the file test.txt and show me its contents`,
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('read_file');
|
||||
|
||||
// Add debugging information
|
||||
if (!foundToolCall || !result.includes('hello world')) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Contains hello world': result.includes('hello world'),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a read_file tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: 'hello world',
|
||||
testName: 'File read test',
|
||||
});
|
||||
});
|
||||
|
||||
it('should be able to write a hello world message to a file', async () => {
|
||||
await rig.setup('should be able to write a hello world message to a file', {
|
||||
settings: { tools: { core: ['write_file', 'replace', 'read_file'] } },
|
||||
});
|
||||
rig.createFile('test.txt', '');
|
||||
|
||||
const result = await rig.run({
|
||||
args: `edit test.txt to have a hello world message`,
|
||||
});
|
||||
|
||||
// Accept multiple valid tools for editing files
|
||||
const foundToolCall = await rig.waitForAnyToolCall([
|
||||
'write_file',
|
||||
'edit',
|
||||
'replace',
|
||||
]);
|
||||
|
||||
// Add debugging information
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a write_file, edit, or replace tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, { testName: 'File write test' });
|
||||
|
||||
const fileContent = rig.readFile('test.txt');
|
||||
|
||||
// Add debugging for file content
|
||||
if (!fileContent.toLowerCase().includes('hello')) {
|
||||
const writeCalls = rig
|
||||
.readToolLogs()
|
||||
.filter((t) => t.toolRequest.name === 'write_file')
|
||||
.map((t) => t.toolRequest.args);
|
||||
|
||||
printDebugInfo(rig, result, {
|
||||
'File content mismatch': true,
|
||||
'Expected to contain': 'hello',
|
||||
'Actual content': fileContent,
|
||||
'Write tool calls': JSON.stringify(writeCalls),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
fileContent.toLowerCase().includes('hello'),
|
||||
'Expected file to contain hello',
|
||||
).toBeTruthy();
|
||||
|
||||
// Log success info if verbose
|
||||
if (process.env['VERBOSE'] === 'true') {
|
||||
console.log('File written successfully with hello message.');
|
||||
}
|
||||
});
|
||||
|
||||
it('should correctly handle file paths with spaces', async () => {
|
||||
await rig.setup('should correctly handle file paths with spaces', {
|
||||
settings: { tools: { core: ['write_file', 'read_file'] } },
|
||||
});
|
||||
const fileName = 'my test file.txt';
|
||||
|
||||
const result = await rig.run({
|
||||
args: `write "hello" to "${fileName}" and then stop. Do not perform any other actions.`,
|
||||
timeout: 600000, // 10 min — real LLM can be slow in Docker sandbox
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('write_file');
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a write_file tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const newFileContent = rig.readFile(fileName);
|
||||
// Trim to tolerate models that idiomatically append a trailing newline.
|
||||
// This test is about path-with-spaces handling, not whitespace fidelity.
|
||||
expect(newFileContent.trim()).toBe('hello');
|
||||
});
|
||||
|
||||
it('should perform a read-then-write sequence', async () => {
|
||||
await rig.setup('should perform a read-then-write sequence', {
|
||||
settings: { tools: { core: ['read_file', 'replace', 'write_file'] } },
|
||||
});
|
||||
const fileName = 'version.txt';
|
||||
rig.createFile(fileName, '1.0.0');
|
||||
|
||||
const prompt = `Read the version from ${fileName} and write the next version 1.0.1 back to the file.`;
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
await rig.waitForTelemetryReady();
|
||||
const toolLogs = rig.readToolLogs();
|
||||
|
||||
const readCall = toolLogs.find(
|
||||
(log) => log.toolRequest.name === 'read_file',
|
||||
);
|
||||
const writeCall = toolLogs.find(
|
||||
(log) =>
|
||||
log.toolRequest.name === 'write_file' ||
|
||||
log.toolRequest.name === 'replace',
|
||||
);
|
||||
|
||||
if (!readCall || !writeCall) {
|
||||
printDebugInfo(rig, result, { readCall, writeCall });
|
||||
}
|
||||
|
||||
expect(readCall, 'Expected to find a read_file tool call').toBeDefined();
|
||||
expect(
|
||||
writeCall,
|
||||
'Expected to find a write_file or replace tool call',
|
||||
).toBeDefined();
|
||||
|
||||
const newFileContent = rig.readFile(fileName);
|
||||
expect(newFileContent.trimEnd()).toBe('1.0.1');
|
||||
});
|
||||
|
||||
it.skip('should replace multiple instances of a string', async () => {
|
||||
rig.setup('should replace multiple instances of a string');
|
||||
const fileName = 'ambiguous.txt';
|
||||
const fileContent = 'Hey there, \ntest line\ntest line';
|
||||
const expectedContent = 'Hey there, \nnew line\nnew line';
|
||||
rig.createFile(fileName, fileContent);
|
||||
|
||||
const result = await rig.run({
|
||||
args: `rewrite the file ${fileName} to replace all instances of "test line" with "new line"`,
|
||||
});
|
||||
|
||||
const validTools = ['write_file', 'edit'];
|
||||
const foundToolCall = await rig.waitForAnyToolCall(validTools);
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Tool call found': foundToolCall,
|
||||
'Tool logs': rig.readToolLogs(),
|
||||
});
|
||||
}
|
||||
expect(
|
||||
foundToolCall,
|
||||
`Expected to find one of ${validTools.join(', ')} tool calls`,
|
||||
).toBeTruthy();
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const successfulEdit = toolLogs.some(
|
||||
(log) =>
|
||||
validTools.includes(log.toolRequest.name) && log.toolRequest.success,
|
||||
);
|
||||
if (!successfulEdit) {
|
||||
console.error(
|
||||
`Expected a successful edit tool call (${validTools.join(', ')}), but none was found.`,
|
||||
);
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
expect(
|
||||
successfulEdit,
|
||||
`Expected a successful edit tool call (${validTools.join(', ')})`,
|
||||
).toBeTruthy();
|
||||
|
||||
const newFileContent = rig.readFile(fileName);
|
||||
if (newFileContent !== expectedContent) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Final file content': newFileContent,
|
||||
'Expected file content': expectedContent,
|
||||
'Tool logs': rig.readToolLogs(),
|
||||
});
|
||||
}
|
||||
expect(newFileContent).toBe(expectedContent);
|
||||
});
|
||||
|
||||
it('should fail safely when trying to edit a non-existent file', async () => {
|
||||
await rig.setup(
|
||||
'should fail safely when trying to edit a non-existent file',
|
||||
{ settings: { tools: { core: ['read_file', 'replace'] } } },
|
||||
);
|
||||
const fileName = 'non_existent.txt';
|
||||
|
||||
const result = await rig.run({
|
||||
args: `In ${fileName}, replace "a" with "b"`,
|
||||
});
|
||||
|
||||
await rig.waitForTelemetryReady();
|
||||
const toolLogs = rig.readToolLogs();
|
||||
|
||||
const readAttempt = toolLogs.find(
|
||||
(log) => log.toolRequest.name === 'read_file',
|
||||
);
|
||||
const writeAttempt = toolLogs.find(
|
||||
(log) => log.toolRequest.name === 'write_file',
|
||||
);
|
||||
const successfulReplace = toolLogs.find(
|
||||
(log) => log.toolRequest.name === 'replace' && log.toolRequest.success,
|
||||
);
|
||||
|
||||
// The model can either investigate (and fail) or do nothing.
|
||||
// If it chose to investigate by reading, that read must have failed.
|
||||
if (readAttempt && readAttempt.toolRequest.success) {
|
||||
console.error(
|
||||
'A read_file attempt succeeded for a non-existent file when it should have failed.',
|
||||
);
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
if (readAttempt) {
|
||||
expect(
|
||||
readAttempt.toolRequest.success,
|
||||
'If model tries to read the file, that attempt must fail',
|
||||
).toBe(false);
|
||||
}
|
||||
|
||||
// CRITICAL: Verify that no matter what the model did, it never successfully
|
||||
// wrote or replaced anything.
|
||||
if (writeAttempt) {
|
||||
console.error(
|
||||
'A write_file attempt was made when no file should be written.',
|
||||
);
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
expect(
|
||||
writeAttempt,
|
||||
'write_file should not have been called',
|
||||
).toBeUndefined();
|
||||
|
||||
if (successfulReplace) {
|
||||
console.error('A successful replace occurred when it should not have.');
|
||||
printDebugInfo(rig, result);
|
||||
}
|
||||
expect(
|
||||
successfulReplace,
|
||||
'A successful replace should not have occurred',
|
||||
).toBeUndefined();
|
||||
|
||||
// Final verification: ensure the file was not created.
|
||||
const filePath = path.join(rig.testDir!, fileName);
|
||||
const fileExists = existsSync(filePath);
|
||||
expect(fileExists, 'The non-existent file should not be created').toBe(
|
||||
false,
|
||||
);
|
||||
});
|
||||
});
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,42 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
|
||||
describe('Flicker Detector', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should not detect a flicker under the max height budget', async () => {
|
||||
rig.setup('flicker-detector-test', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'flicker-detector.max-height.responses',
|
||||
),
|
||||
});
|
||||
const run = await rig.runInteractive();
|
||||
const prompt = 'Tell me a fun fact.';
|
||||
await run.type(prompt);
|
||||
await run.type('\r');
|
||||
|
||||
const hasUserPromptEvent = await rig.waitForTelemetryEvent('user_prompt');
|
||||
expect(hasUserPromptEvent).toBe(true);
|
||||
|
||||
const hasSessionCountMetric = await rig.waitForMetric('session.count');
|
||||
expect(hasSessionCountMetric).toBe(true);
|
||||
|
||||
// We expect NO flicker event to be found.
|
||||
const flickerMetric = rig.readMetric('ui.flicker.count');
|
||||
expect(flickerMetric).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,155 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
// Unset NO_COLOR environment variable to ensure consistent theme behavior between local and CI test runs
|
||||
if (process.env['NO_COLOR'] !== undefined) {
|
||||
delete process.env['NO_COLOR'];
|
||||
}
|
||||
|
||||
import { mkdir, readdir, rm, readFile } from 'node:fs/promises';
|
||||
import { join, dirname, extname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { resolveRipgrepPath } from '../packages/core/src/tools/ripGrep.js';
|
||||
import { disableMouseTracking } from '@google/gemini-cli-core';
|
||||
import { isolateTestEnv } from '../packages/test-utils/src/env-setup.js';
|
||||
import { createServer, type Server } from 'node:http';
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
const rootDir = join(__dirname, '..');
|
||||
const integrationTestsDir = join(rootDir, '.integration-tests');
|
||||
let runDir = ''; // Make runDir accessible in teardown
|
||||
let fixtureServer: Server | undefined;
|
||||
|
||||
const FIXTURE_PORT = 18923;
|
||||
const FIXTURE_DIR = join(__dirname, 'test-fixtures');
|
||||
|
||||
const MIME_TYPES: Record<string, string> = {
|
||||
'.html': 'text/html',
|
||||
'.css': 'text/css',
|
||||
'.js': 'application/javascript',
|
||||
'.json': 'application/json',
|
||||
'.png': 'image/png',
|
||||
'.jpg': 'image/jpeg',
|
||||
'.svg': 'image/svg+xml',
|
||||
};
|
||||
|
||||
async function startFixtureServer(): Promise<number> {
|
||||
return new Promise((resolve, reject) => {
|
||||
const server = createServer(async (req, res) => {
|
||||
const urlPath = req.url?.split('?')[0] || '/';
|
||||
const relativePath = urlPath === '/' ? 'index.html' : urlPath;
|
||||
const filePath = join(FIXTURE_DIR, relativePath);
|
||||
|
||||
if (!filePath.startsWith(FIXTURE_DIR)) {
|
||||
res.writeHead(403, { 'Content-Type': 'text/html' });
|
||||
res.end('<h1>403 Forbidden</h1>');
|
||||
return;
|
||||
}
|
||||
|
||||
try {
|
||||
const content = await readFile(filePath);
|
||||
const ext = extname(filePath);
|
||||
res.writeHead(200, {
|
||||
'Content-Type': MIME_TYPES[ext] || 'application/octet-stream',
|
||||
});
|
||||
res.end(content);
|
||||
} catch {
|
||||
res.writeHead(404, { 'Content-Type': 'text/html' });
|
||||
res.end('<h1>404 Not Found</h1>');
|
||||
}
|
||||
});
|
||||
|
||||
server.on('error', (err: NodeJS.ErrnoException) => {
|
||||
if (err.code === 'EADDRINUSE') {
|
||||
console.warn(
|
||||
`Port ${FIXTURE_PORT} in use, trying ${FIXTURE_PORT + 1}...`,
|
||||
);
|
||||
server.listen(FIXTURE_PORT + 1, '127.0.0.1');
|
||||
} else {
|
||||
reject(err);
|
||||
}
|
||||
});
|
||||
|
||||
server.on('listening', () => {
|
||||
const addr = server.address();
|
||||
const port = typeof addr === 'object' && addr ? addr.port : FIXTURE_PORT;
|
||||
fixtureServer = server;
|
||||
console.log(`Test fixture server listening on http://127.0.0.1:${port}`);
|
||||
resolve(port);
|
||||
});
|
||||
|
||||
server.listen(FIXTURE_PORT, '127.0.0.1');
|
||||
});
|
||||
}
|
||||
|
||||
export async function setup() {
|
||||
runDir = join(integrationTestsDir, `${Date.now()}`);
|
||||
await mkdir(runDir, { recursive: true });
|
||||
|
||||
// Isolate environment variables
|
||||
isolateTestEnv(runDir);
|
||||
|
||||
// Download ripgrep to avoid race conditions in parallel tests
|
||||
const available = await resolveRipgrepPath();
|
||||
if (!available) {
|
||||
throw new Error('Failed to download ripgrep binary');
|
||||
}
|
||||
|
||||
// Start the test fixture server
|
||||
const port = await startFixtureServer();
|
||||
process.env['TEST_FIXTURE_PORT'] = String(port);
|
||||
|
||||
// Clean up old test runs, but keep the latest few for debugging
|
||||
try {
|
||||
const testRuns = await readdir(integrationTestsDir);
|
||||
if (testRuns.length > 5) {
|
||||
const oldRuns = testRuns.sort().slice(0, testRuns.length - 5);
|
||||
await Promise.all(
|
||||
oldRuns.map((oldRun) =>
|
||||
rm(join(integrationTestsDir, oldRun), {
|
||||
recursive: true,
|
||||
force: true,
|
||||
}),
|
||||
),
|
||||
);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Error cleaning up old test runs:', e);
|
||||
}
|
||||
|
||||
process.env['INTEGRATION_TEST_FILE_DIR'] = runDir;
|
||||
|
||||
if (process.env['KEEP_OUTPUT']) {
|
||||
console.log(`Keeping output for test run in: ${runDir}`);
|
||||
}
|
||||
process.env['VERBOSE'] = process.env['VERBOSE'] ?? 'false';
|
||||
|
||||
console.log(`\nIntegration test output directory: ${runDir}`);
|
||||
}
|
||||
|
||||
export async function teardown() {
|
||||
// Stop the fixture server
|
||||
if (fixtureServer) {
|
||||
await new Promise<void>((resolve) => {
|
||||
fixtureServer!.close(() => resolve());
|
||||
});
|
||||
fixtureServer = undefined;
|
||||
}
|
||||
|
||||
// Disable mouse tracking
|
||||
if (process.stdout.isTTY) {
|
||||
disableMouseTracking();
|
||||
}
|
||||
|
||||
// Cleanup the test run directory unless KEEP_OUTPUT is set
|
||||
if (process.env['KEEP_OUTPUT'] !== 'true' && runDir) {
|
||||
try {
|
||||
await rm(runDir, { recursive: true, force: true });
|
||||
} catch (e) {
|
||||
console.warn('Failed to clean up test run directory:', e);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,95 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { WEB_SEARCH_TOOL_NAME } from '../packages/core/src/tools/tool-names.js';
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
|
||||
describe('web search tool', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should be able to search the web', async () => {
|
||||
await rig.setup('should be able to search the web', {
|
||||
settings: { tools: { core: [WEB_SEARCH_TOOL_NAME] } },
|
||||
});
|
||||
|
||||
let result;
|
||||
try {
|
||||
result = await rig.run({ args: `what is the weather in London` });
|
||||
} catch (error) {
|
||||
// Network errors can occur in CI environments
|
||||
if (
|
||||
error instanceof Error &&
|
||||
(error.message.includes('network') || error.message.includes('timeout'))
|
||||
) {
|
||||
console.warn(
|
||||
'Skipping test due to network error:',
|
||||
(error as Error).message,
|
||||
);
|
||||
return; // Skip the test
|
||||
}
|
||||
throw error; // Re-throw if not a network error
|
||||
}
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall(WEB_SEARCH_TOOL_NAME);
|
||||
|
||||
// Add debugging information
|
||||
if (!foundToolCall) {
|
||||
const allTools = printDebugInfo(rig, result);
|
||||
|
||||
// Check if the tool call failed due to network issues
|
||||
const failedSearchCalls = allTools.filter(
|
||||
(t) =>
|
||||
t.toolRequest.name === WEB_SEARCH_TOOL_NAME && !t.toolRequest.success,
|
||||
);
|
||||
if (failedSearchCalls.length > 0) {
|
||||
console.warn(
|
||||
`${WEB_SEARCH_TOOL_NAME} tool was called but failed, possibly due to network issues`,
|
||||
);
|
||||
console.warn(
|
||||
'Failed calls:',
|
||||
failedSearchCalls.map((t) => t.toolRequest.args),
|
||||
);
|
||||
return; // Skip the test if network issues
|
||||
}
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
`Expected to find a call to ${WEB_SEARCH_TOOL_NAME}`,
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
const hasExpectedContent = checkModelOutputContent(result, {
|
||||
expectedContent: ['weather', 'london'],
|
||||
testName: 'Google web search test',
|
||||
});
|
||||
|
||||
// If content was missing, log the search queries used
|
||||
if (!hasExpectedContent) {
|
||||
const searchCalls = rig
|
||||
.readToolLogs()
|
||||
.filter((t) => t.toolRequest.name === WEB_SEARCH_TOOL_NAME);
|
||||
if (searchCalls.length > 0) {
|
||||
console.warn(
|
||||
'Search queries used:',
|
||||
searchCalls.map((t) => t.toolRequest.args),
|
||||
);
|
||||
}
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"list_dir","args":{"path":"."}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Final Answer"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Responding**\n\nI will respond to the user's request.\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":100,"totalTokenCount":120,"promptTokensDetails":[{"modality":"TEXT","tokenCount":100}],"thoughtsTokenCount":20}},{"candidates":[{"content":{"parts":[{"text":"Response to: "}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":5,"totalTokenCount":125,"promptTokensDetails":[{"modality":"TEXT","tokenCount":100}],"thoughtsTokenCount":20}},{"candidates":[{"content":{"parts":[{"text":"Hello World"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":7,"totalTokenCount":127,"promptTokensDetails":[{"modality":"TEXT","tokenCount":100}],"thoughtsTokenCount":20}}]}
|
||||
@@ -0,0 +1,338 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig, normalizePath } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
import { writeFileSync } from 'node:fs';
|
||||
|
||||
describe('Hooks Agent Flow', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (rig) {
|
||||
await rig.cleanup();
|
||||
}
|
||||
});
|
||||
|
||||
describe('BeforeAgent Hooks', () => {
|
||||
it('should inject additional context via BeforeAgent hook', async () => {
|
||||
await rig.setup('should inject additional context via BeforeAgent hook', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'hooks-agent-flow.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const hookScript = `
|
||||
try {
|
||||
const output = {
|
||||
decision: "allow",
|
||||
hookSpecificOutput: {
|
||||
hookEventName: "BeforeAgent",
|
||||
additionalContext: "SYSTEM INSTRUCTION: This is injected context."
|
||||
}
|
||||
};
|
||||
process.stdout.write(JSON.stringify(output));
|
||||
} catch (e) {
|
||||
console.error('Failed to write stdout:', e);
|
||||
process.exit(1);
|
||||
}
|
||||
console.error('DEBUG: BeforeAgent hook executed');
|
||||
`;
|
||||
|
||||
const scriptPath = join(rig.testDir!, 'before_agent_context.cjs');
|
||||
writeFileSync(scriptPath, hookScript);
|
||||
|
||||
await rig.setup('should inject additional context via BeforeAgent hook', {
|
||||
settings: {
|
||||
hooksConfig: {
|
||||
enabled: true,
|
||||
},
|
||||
hooks: {
|
||||
BeforeAgent: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: `node "${scriptPath}"`,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({ args: 'Hello test' });
|
||||
|
||||
// Verify hook execution and telemetry
|
||||
const hookTelemetryFound = await rig.waitForTelemetryEvent('hook_call');
|
||||
expect(hookTelemetryFound).toBeTruthy();
|
||||
|
||||
const hookLogs = rig.readHookLogs();
|
||||
const beforeAgentLog = hookLogs.find(
|
||||
(log) => log.hookCall.hook_event_name === 'BeforeAgent',
|
||||
);
|
||||
|
||||
expect(beforeAgentLog).toBeDefined();
|
||||
expect(beforeAgentLog?.hookCall.stdout).toContain('injected context');
|
||||
expect(beforeAgentLog?.hookCall.stdout).toContain('"decision":"allow"');
|
||||
expect(beforeAgentLog?.hookCall.stdout).toContain(
|
||||
'SYSTEM INSTRUCTION: This is injected context.',
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('AfterAgent Hooks', () => {
|
||||
it('should receive prompt and response in AfterAgent hook', async () => {
|
||||
await rig.setup('should receive prompt and response in AfterAgent hook', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'hooks-agent-flow.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const hookScript = `
|
||||
const fs = require('fs');
|
||||
try {
|
||||
const input = fs.readFileSync(0, 'utf-8');
|
||||
console.error('DEBUG: AfterAgent hook input received');
|
||||
process.stdout.write("Received Input: " + input);
|
||||
} catch (err) {
|
||||
console.error('Hook Failed:', err);
|
||||
process.exit(1);
|
||||
}
|
||||
`;
|
||||
|
||||
const scriptPath = rig.createScript('after_agent_verify.cjs', hookScript);
|
||||
|
||||
rig.setup('should receive prompt and response in AfterAgent hook', {
|
||||
settings: {
|
||||
hooksConfig: {
|
||||
enabled: true,
|
||||
},
|
||||
hooks: {
|
||||
AfterAgent: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: normalizePath(`node "${scriptPath}"`)!,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({ args: 'Hello validation' });
|
||||
|
||||
const hookTelemetryFound = await rig.waitForTelemetryEvent('hook_call');
|
||||
expect(hookTelemetryFound).toBeTruthy();
|
||||
|
||||
const hookLogs = rig.readHookLogs();
|
||||
const afterAgentLog = hookLogs.find(
|
||||
(log) => log.hookCall.hook_event_name === 'AfterAgent',
|
||||
);
|
||||
|
||||
expect(afterAgentLog).toBeDefined();
|
||||
// Verify the hook stdout contains the input we echoed which proves the
|
||||
// hook received the prompt and response
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('Received Input');
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('Hello validation');
|
||||
// The fake response contains "Hello World"
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('Hello World');
|
||||
});
|
||||
|
||||
it('should process clearContext in AfterAgent hook output', async () => {
|
||||
rig.setup('should process clearContext in AfterAgent hook output', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'hooks-system.after-agent.responses',
|
||||
),
|
||||
});
|
||||
|
||||
// BeforeModel hook to track message counts across LLM calls
|
||||
const messageCountFile = join(rig.testDir!, 'message-counts.json');
|
||||
const escapedPath = JSON.stringify(messageCountFile);
|
||||
const beforeModelScript = `
|
||||
const fs = require('fs');
|
||||
const input = JSON.parse(fs.readFileSync(0, 'utf-8'));
|
||||
const messageCount = input.llm_request?.contents?.length || 0;
|
||||
let counts = [];
|
||||
try { counts = JSON.parse(fs.readFileSync(${escapedPath}, 'utf-8')); } catch (e) {}
|
||||
counts.push(messageCount);
|
||||
fs.writeFileSync(${escapedPath}, JSON.stringify(counts));
|
||||
console.log(JSON.stringify({ decision: 'allow' }));
|
||||
`;
|
||||
const beforeModelScriptPath = rig.createScript(
|
||||
'before_model_counter.cjs',
|
||||
beforeModelScript,
|
||||
);
|
||||
|
||||
const afterAgentScript = `
|
||||
const fs = require('fs');
|
||||
const input = JSON.parse(fs.readFileSync(0, 'utf-8'));
|
||||
if (input.stop_hook_active) {
|
||||
// Retry turn: allow execution to proceed (breaks the loop)
|
||||
console.log(JSON.stringify({ decision: 'allow' }));
|
||||
} else {
|
||||
// First call: block and clear context to trigger the retry
|
||||
console.log(JSON.stringify({
|
||||
decision: 'block',
|
||||
reason: 'Security policy triggered',
|
||||
hookSpecificOutput: {
|
||||
hookEventName: 'AfterAgent',
|
||||
clearContext: true
|
||||
}
|
||||
}));
|
||||
}
|
||||
`;
|
||||
const afterAgentScriptPath = rig.createScript(
|
||||
'after_agent_clear.cjs',
|
||||
afterAgentScript,
|
||||
);
|
||||
|
||||
rig.setup('should process clearContext in AfterAgent hook output', {
|
||||
settings: {
|
||||
hooksConfig: {
|
||||
enabled: true,
|
||||
},
|
||||
hooks: {
|
||||
BeforeModel: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: normalizePath(`node "${beforeModelScriptPath}"`)!,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
AfterAgent: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: normalizePath(`node "${afterAgentScriptPath}"`)!,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const result = await rig.run({ args: 'Hello test' });
|
||||
|
||||
const hookTelemetryFound = await rig.waitForTelemetryEvent('hook_call');
|
||||
expect(hookTelemetryFound).toBeTruthy();
|
||||
|
||||
const hookLogs = rig.readHookLogs();
|
||||
const afterAgentLog = hookLogs.find(
|
||||
(log) => log.hookCall.hook_event_name === 'AfterAgent',
|
||||
);
|
||||
|
||||
expect(afterAgentLog).toBeDefined();
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('clearContext');
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('true');
|
||||
expect(result).toContain('Security policy triggered');
|
||||
|
||||
// Verify context was cleared: second call should not have more messages than first
|
||||
const countsRaw = rig.readFile('message-counts.json');
|
||||
const counts = JSON.parse(countsRaw) as number[];
|
||||
expect(counts.length).toBeGreaterThanOrEqual(2);
|
||||
expect(counts[1]).toBeLessThanOrEqual(counts[0]);
|
||||
});
|
||||
});
|
||||
|
||||
describe('Multi-step Loops', () => {
|
||||
it('should fire BeforeAgent and AfterAgent exactly once per turn despite tool calls', async () => {
|
||||
await rig.setup(
|
||||
'should fire BeforeAgent and AfterAgent exactly once per turn despite tool calls',
|
||||
{
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'hooks-agent-flow-multistep.responses',
|
||||
),
|
||||
},
|
||||
);
|
||||
|
||||
// Create script files for hooks
|
||||
const baPath = rig.createScript(
|
||||
'ba_fired.cjs',
|
||||
"console.log('BeforeAgent Fired');",
|
||||
);
|
||||
const aaPath = rig.createScript(
|
||||
'aa_fired.cjs',
|
||||
"console.log('AfterAgent Fired');",
|
||||
);
|
||||
|
||||
await rig.setup(
|
||||
'should fire BeforeAgent and AfterAgent exactly once per turn despite tool calls',
|
||||
{
|
||||
settings: {
|
||||
hooksConfig: {
|
||||
enabled: true,
|
||||
},
|
||||
hooks: {
|
||||
BeforeAgent: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: normalizePath(`node "${baPath}"`)!,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
AfterAgent: [
|
||||
{
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
command: normalizePath(`node "${aaPath}"`)!,
|
||||
timeout: 5000,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
await rig.run({ args: 'Do a multi-step task' });
|
||||
|
||||
const hookLogs = rig.readHookLogs();
|
||||
const beforeAgentLogs = hookLogs.filter(
|
||||
(log) => log.hookCall.hook_event_name === 'BeforeAgent',
|
||||
);
|
||||
const afterAgentLogs = hookLogs.filter(
|
||||
(log) => log.hookCall.hook_event_name === 'AfterAgent',
|
||||
);
|
||||
|
||||
expect(beforeAgentLogs).toHaveLength(1);
|
||||
|
||||
expect(afterAgentLogs).toHaveLength(1);
|
||||
|
||||
const afterAgentLog = afterAgentLogs[0];
|
||||
expect(afterAgentLog).toBeDefined();
|
||||
expect(afterAgentLog?.hookCall.stdout).toContain('AfterAgent Fired');
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,3 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hi there!"}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Clarification: I am a bot."}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Security policy triggered"}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Addressing the Inquiry**\n\nI've grasped the core of the user's question and identified that no tools are needed. My focus is now on crafting a straightforward, direct response that fully addresses their query without any unnecessary complexity. The goal is to provide a clear and concise answer.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12777,"totalTokenCount":12802,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12777}],"thoughtsTokenCount":25}},{"candidates":[{"content":{"parts":[{"text":"4","thoughtSignature":"CiQBcsjafBFqw6veocEvtOGGuQcsyHdcNrXDIn19n9ImwBBwcYQKdgFyyNp8g7o8Ji++OXoqml4gbLPIB2DQbXcaRQfRuYefF8RxMEpzJSITZBlT1VpJQoeYmQcb9c8dg/POmo5d3ZcuLbpVJpbjMIV1SoUI4KEn3zqz7a8BFuyq3zY4VEliRWMZO21JMd8qp59M9m64hX7W1YPyzu8KPwFyyNp8aNCD7P1NJDG3csQkiMW/0jWdPkh+7+XxT7i3ku/lYH4yTEShdicPcmnzoPGhEWTUDr/4Lx+A0DnVGQ=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12777,"totalTokenCount":12802,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12777}],"thoughtsTokenCount":25}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Analyzing File Access**\n\nI've realized the `read_file` tool is perfect for accessing the contents of `test-file.txt`. My next step is to call this tool and set the `file_path` parameter to `test-file.txt`.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12785,"totalTokenCount":12841,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12785}],"thoughtsTokenCount":56}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_file","args":{"file_path":"test-file.txt"}},"thoughtSignature":"CiQBcsjafE9D7iAF+V3wpXP81/VmxiMeSFA6afML/lAB76U6QFQKXgFyyNp8i/vhxpkTQ5Cq81QTeEJDDMaYihzSTFMqO4Vj0+CLNtoy+SC/LmqA+WaXh4tm6UCNFTzB2fpVW13YOU1oVYhLpVpeck746YExu1MOSTAq7AC9Yz8ZoelXdecKdwFyyNp8q0PejiY9K1osdOJ02tOHAzAb8ZCSFHtHamEPxRB93krGMNvuIYC1jM1JnC/fzpH8gYV+0/xkoPJMHpF/aSzWq4kZ/j5cUhMYaqKJTulY8ZZGfawnXG7z0spmmr06gwfgILa+HK++xQhhTphMQCobX5hyCjUBcsjafHY6eJfVNitYmfruLV1mnoYnNViHuAOOOni9jIz4VMIjLbClKkb2rpVfHIjx+vZSHA=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12785,"candidatesTokenCount":20,"totalTokenCount":12861,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12785}],"thoughtsTokenCount":56}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"This"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12889,"candidatesTokenCount":1,"totalTokenCount":12890,"cachedContentTokenCount":12206,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12889}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12206}]}},{"candidates":[{"content":{"parts":[{"text":" is test content"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12889,"candidatesTokenCount":4,"totalTokenCount":12893,"cachedContentTokenCount":12206,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12889}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12206}]}}]}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Formulating the Write Operation**\n\nOkay, I'm now clear on the user's intent: they want a file called `approved.txt`, containing the words \"Approved content.\" I've decided to leverage the `write_file` tool. The specific parameter assignments seem straightforward; `file_path` will be \"approved.txt\", and the file's `content` will precisely mirror the desired output string.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12778,"totalTokenCount":12838,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12778}],"thoughtsTokenCount":60}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"Approved content","file_path":"approved.txt"}},"thoughtSignature":"CiQBcsjafF4NswdygCBTU7cA/yXVRcUI3XHwV+E8BDg/hRr1MaoKZQFyyNp8HRY1qEvivtg0LpYPo1022IfTY3QIeigqGvSoRVospxT5MBggc9nRbwH2vrdhZ772IdqOCrpjNHs3wc+h0AF4JzjlBet6+yC2m7TdenVOkzVAtqnNDMQAIS1gDZyKs8w/CngBcsjafOeuyDQtxuK7JCafKjtfvPvoKOkVxzDetQtHesBkPtv1Xng9dkP77jLH44hn9rrg7yA+za6vssiFZUjC/FU25pCWQgIhM+K7nt3wbAgoOZRqra2gRr3od2D3osV/UpYhy8MoloykqrWvHDOzT/0KScpHarwKXQFyyNp8qabyDYlfElywQBjqQT4f6My7+Ln9AbKZQz4NaEe90ESg4jr4jjANxyd/WKzRheaBq7BYxTHQSeShgQbVjk2D0tZO4hAN+CToMtQwJl95Ss4ZEov6gAwMNA=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12778,"candidatesTokenCount":24,"totalTokenCount":12862,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12778}],"thoughtsTokenCount":60}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12939,"totalTokenCount":12939,"cachedContentTokenCount":12203,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12939}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12203}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12939,"totalTokenCount":12939,"cachedContentTokenCount":12203,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12939}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12203}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Confirming File Creation**\n\nI've successfully created the file `approved.txt`, and I've verified that it contains the intended content, \"Approved content\". Moving on.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12887,"totalTokenCount":12932,"cachedContentTokenCount":12198,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12887}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12198}],"thoughtsTokenCount":45}},{"candidates":[{"content":{"parts":[{"text":"**Assessing File Contents**\n\nI'm now checking the content of `approved.txt`. I used `cat` to display its contents, and it confirms the initial content of \"Approved content\" is present. My next step will be based on this verification.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12887,"totalTokenCount":12946,"cachedContentTokenCount":12198,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12887}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12198}],"thoughtsTokenCount":59}},{"candidates":[{"content":{"parts":[{"text":"I have created the file. What would you like me to do next?","thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12887,"candidatesTokenCount":13,"totalTokenCount":12959,"cachedContentTokenCount":12198,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12887}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12198}],"thoughtsTokenCount":59}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Responding Truthfully**\n\nI've determined the user's question is straightforward and doesn't necessitate tools. My primary focus now is ensuring a truthful and direct response, without getting caught up in unnecessary complexity. The goal is clarity and accuracy in my reply.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12795,"totalTokenCount":12818,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12795}],"thoughtsTokenCount":23}},{"candidates":[{"content":{"parts":[{"text":"Hello! I'm doing well, thank you. I'm ready to help you with your software engineering tasks. All","thoughtSignature":"CiQBcsjafEYrS7SUZE2xuCgUZ7+hs+NrTRZFywSgq09wuKUzD5gKbQFyyNp8snmh8vfDLLCmnKl2shxGR5McWLmRDIQx+gvyW9ipB+5v5R3tvYgBY0yYGxuB8XPHJDP8unxCqg2koazS050HLU5NZaF74m9KDAWrnWPqQ2hDPc9suJRZpcTse5R+nepMu+oXWEsD03UKOwFyyNp82dmgHDF2DLELc6ly78JDLDmb4kM4qkXmuT8OP7Nu5z2o8kkHiKD4HTx0srjLi6u6dN4ufA0o"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12795,"candidatesTokenCount":24,"totalTokenCount":12842,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12795}],"thoughtsTokenCount":23}},{"candidates":[{"content":{"parts":[{"text":" our interactions are logged for security and compliance purposes. How can I assist you today?"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12795,"candidatesTokenCount":41,"totalTokenCount":12859,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12795}],"thoughtsTokenCount":23}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Initiating String Output**\n\nI'm now fully focused on directly outputting the specified string. The process has been simplified to its core objective, eliminating extraneous steps. All systems are go for immediate execution of the requested string output.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12419,"totalTokenCount":12439,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12419}],"thoughtsTokenCount":20}},{"candidates":[{"content":{"parts":[{"text":"The security hook modified this request successfully.","thoughtSignature":"CiQBcsjafAsmW87n4ndCW3YiNIqK6jp0zaTwTjz12vWiwbCFNAUKdQFyyNp808SX5BqCBNZt+dlgsPf74u9W6ofevKGwkTTHQZWJEQiJR2j4uRfESTazuawuWfzKfNJq5Zml6fokNR9jzmQM+Jf4FHw95Jd4lneap+YGO9x5nZMNDI1cHRx0vs4BYW9GWY7lBIM8xKtaEkPrwqc88goiAXLI2nx5o6VrBpXs6jzf5maZIauSYw42zlnkqdDEMI20rg=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12419,"candidatesTokenCount":7,"totalTokenCount":12446,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12419}],"thoughtsTokenCount":20}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Processing File Contents**\n\nI've successfully incorporated the request to read the contents of `new_file_data.txt`. My next step is to prepare the `echo` command to output that very content, which I'll be using the `run_shell` function for. It's a fairly straightforward plan from here.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12803,"totalTokenCount":12873,"cachedContentTokenCount":11797,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12803}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11797}],"thoughtsTokenCount":70}},{"candidates":[{"content":{"parts":[{"text":"**Initiating Echo Procedure**\n\nI'm now in the process of incorporating the next phase: echoing the `new_file_data.txt` content. I'll utilize `run_shell` with the `echo` command to present the file's contents, continuing the project towards completion. I'm focusing now on correctly constructing and executing this `echo` command. The user's goal of visualizing the file content is top of mind.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12803,"totalTokenCount":12977,"cachedContentTokenCount":11797,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12803}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11797}],"thoughtsTokenCount":174}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_file","args":{"file_path":"new_file_data.txt"}},"thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12803,"candidatesTokenCount":21,"totalTokenCount":12998,"cachedContentTokenCount":11797,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12803}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11797}],"thoughtsTokenCount":174}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Done."}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Initializing File Creation**\n\nI'm starting to think about how to make a new file called `test.txt`. My plan is to use a `write_file` tool. I'll need to specify the location and what the file should contain. For now, it will be empty.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":13216,"totalTokenCount":13269,"promptTokensDetails":[{"modality":"TEXT","tokenCount":13216}],"thoughtsTokenCount":53}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"test.txt","content":""}},"thoughtSignature":"CiQBcsjafJ20Qbx0YvING6aZ0wYoGWJh3eqornOG4E4AfBLiVsQKXwFyyNp8UlwYs/pv9IRQQGhDlrmlOJF2hfQijryyUYLI+qjDYTpZ6KKIfZF4+vS0soL2BJ3eTXA6gaadFEfNQem3WQVeQoKLFoW4Hv4mbasXqQc0K3p15DuSAtZZENTbCnsBcsjafGK+BJyF/Npnd7gyU0TL5PXePT0nuDFjhJDxlSRUJHDP315TewD3PUYsXd10oWsfhy4B5AngyUiBPUoajdsxg8WxaxnOZYqcp8EIuwtGZrCTev6IihT5nE5jj7u0P9vtnCmkAc6p+4O7Q7Jku1uVGqeJChgzI4YKSAFyyNp8EXSdbttV4xzX+NLKkc276L8Y63tnKU6/Y7fc9/58tU29DSdrgwfe9qmvwtTsO0piFXSLazqHJt8h2bgR7A7GnKDiIA=="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":13216,"candidatesTokenCount":21,"totalTokenCount":13290,"promptTokensDetails":[{"modality":"TEXT","tokenCount":13216}],"thoughtsTokenCount":53}},{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":13216,"candidatesTokenCount":21,"totalTokenCount":13290,"promptTokensDetails":[{"modality":"TEXT","tokenCount":13216}],"thoughtsTokenCount":53}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Constructing File Parameters**\n\nI'm currently focused on the parameters needed for creating `test.txt`. The `write_file` tool seems ideal. I've settled on the `file_path` being \"test.txt\" and the `content` parameter being \"Hello World\". This should result in the desired file creation.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12779,"totalTokenCount":12843,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"thoughtsTokenCount":64}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"test.txt","content":"Hello World"}},"thoughtSignature":"CiQBcsjafGeGML0hnm03md4ExPwk5i2rcaNDqetrrKnEoEFjxRcKYQFyyNp8rs78myvJfPMuC2AWyTHEoWUps7GWpGu/2VU1BB3ekI32yO0q9KSKkmGX28Palht22I77ac5HsFTuutPBDWIqSkrERkzOh3HKJE2MXzsVJJGHX3jVBirJ+Y8F1OAKcQFyyNp8pMKA4E8M3PhbuhDzOv3c9tVEgCQ4W6kzmZHBQeUQNuHVLw1cZfx/aichP6fJeZEJPCXROa7WEWPbwY9evB+ofTqjiifUXo0l4smudNHAerr7UrspQVDwGRGnWBkKiy9a6V5q6XkEhYci+2tBCnIBcsjafNb1jWT0qNMJcPcb8Ngu9xVLsMxb3DEftWMblDwnwv+tMaaQWeXVav8HgSYyg/P40pfOgOtASYZAHZGDhkwfbYY8J1Br8Y71kpEzoImbeQwALV1LMsr1uHQjq2nekTjmOXbIFr68Ef44BzFSBuI="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12779,"candidatesTokenCount":24,"totalTokenCount":12867,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"thoughtsTokenCount":64}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Acknowledge the Block**\n\nI've hit a snag. The file creation was blocked, as you saw. Rather than persisting, I'm waiting on your next instructions. I'm ready to proceed, but need your input on how to adjust course.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12886,"totalTokenCount":12925,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12886}],"thoughtsTokenCount":39}},{"candidates":[{"content":{"parts":[{"text":"I am sorry, but I was unable to create the file as the request was blocked by the security policy.","thoughtSignature":"CikBcsjafKIxdnJr+6NHip/3cc9MiaqA+EfxMy6T2dArrEw3Ga3y69q7fgppAXLI2nxri+Z6NSOI3wvN+xmipbnuKNWfZKMWHN/amQSZcMqIoFNpTyt1t8B/MIGtIVpQ8CfQQAypanAIGa4G+tEhKxOXIdFNktSLB/Yrr0HQQAkD6t12s8S0KTdH5P4xmAII4gdwvSXzCnIBcsjafO06UBT/9dUO7OcS6UItneCNaFUEwAzcn5nGO0kUfu50lTPEwPTGNgrOc8FB303GEcIjZpTXc5X737oyAxqgRk7fY10vwBGOJk+PuiVIQeZQKTazZ7Q90W2d2MRTIAatQYi572oiw4m6vqLJg7o="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12886,"candidatesTokenCount":21,"totalTokenCount":12946,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12886}],"thoughtsTokenCount":39}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Devising a Greeting Phrase**\n\nI've been occupied by the constraint of constructing a five-word salutation. My goal is to make it natural and concise. I'm exploring various combinations to meet the specified word count precisely.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12587,"totalTokenCount":12612,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12587}],"thoughtsTokenCount":25}},{"candidates":[{"content":{"parts":[{"text":"Hello! How can I help you?","thoughtSignature":"CiQBcsjafHso9FUsdYOCTv1xOLlW4MnjbeYnUUBocz0KNgHSzOcKZAFyyNp8XuI6j2afRczgPL8v1dxfVwAJ+5XDKhWKIYf1/8TKGVHh7xXnPfdYBdQ07Ohe7OZXr92xL/IC7B1U2SHDuAOozC0CCW7aiDysu6Hbo6jzYfW5epKht4QjdxYgcKHySrkKMQFyyNp8jXWlHmox53O/CJPXXz2FAmw+ubHKBpYgRezBpA+byyEY2RbVYlZlEMSNkhs="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12587,"candidatesTokenCount":7,"totalTokenCount":12619,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12587}],"thoughtsTokenCount":25}}]}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Creating the First Test File**\n\nI'll use the `write_file` tool to create `first-run.txt` with the content \"test1\".\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12779,"totalTokenCount":12824,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":45}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"test1","file_path":"first-run.txt"}},"thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12779,"candidatesTokenCount":24,"totalTokenCount":12848,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":45}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"File created successfully. Active hook executed"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12951,"candidatesTokenCount":7,"totalTokenCount":12958,"cachedContentTokenCount":12202,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12951}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12202}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Creating the Second Test File**\n\nI'll use the `write_file` tool to create `second-run.txt` with the content \"test2\".\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12779,"totalTokenCount":12826,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":47}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"test2","file_path":"second-run.txt"}},"thoughtSignature":"CiQBcsjafG+JDSqtKOK+ZvSjZQZmS91c1Gz0YyTiirI2u5+rhEIKZAFyyNp8DNXb+xHILTC+FVlEifqEHdrmfFNBLKojci1UIBhcZpQ4UXCMkxUXYKO34IjTlyLgSsjVbbXWEFXatb/z/RtTDcf51uc3YOEwlDScGempkJxfFgcPfIiD7bhuHBqdQfUKfAFyyNp8wZ71h+QjdfVw12PwDXWgGZ0Xed1GuyJXuqAwpWnwxDIvsDaPwDFYyLR1XDiIZZk4AvFCGt6HGMSLRuPh4K3i9CVnDc5hcjyvMIde0idAFMrgs2Mq5SARfCPrWkqyq2f0Q0WonUl2n7yr/sDQ78rx2E6qXyUJ8XMKfAFyyNp8DdTYLttyI0jknqAeZDxdFmHtpJUI8UKP5YHzpQc8Qn80OJcwhZSRH4HRKCqoC7Sukq/A5vJ5T468WqgjOoLlPLq02bYRTf/q6LC1ogEhdLHrcFv2jDeCdXJJ8NHv3O4DZAUAk1W5Gd0428zMFOxH3AgkWwEGuow="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12779,"candidatesTokenCount":24,"totalTokenCount":12850,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":47}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"File created successfully. Active hook executed"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12951,"candidatesTokenCount":7,"totalTokenCount":12958,"cachedContentTokenCount":12202,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12951}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12202}]}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Creating the Test File**\n\nI'll use the `write_file` tool to create `disabled-test.txt` with the content \"test\".\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12779,"totalTokenCount":12820,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":41}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"test","file_path":"disabled-test.txt"}},"thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12779,"candidatesTokenCount":24,"totalTokenCount":12844,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":41}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"File created successfully. Enabled hook executed."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12951,"candidatesTokenCount":8,"totalTokenCount":12959,"cachedContentTokenCount":12202,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12951}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12202}]}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Defining File Parameters**\n\nI've decided on the filename: `error-test.txt`. I'll populate it with the text \"testing error handling\". The `write_file` tool seems ideal for this, given its clear functionality. I'm focusing on assigning the values of `file_path` as `error-test.txt` and `content` as \"testing error handling\" to initiate the tool.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12786,"totalTokenCount":12852,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12786}],"thoughtsTokenCount":66}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"error-test.txt","content":"testing error handling"}},"thoughtSignature":"CiQBcsjafMeH+OLl4BHZIH0Hg2b339mDmV+8hSLTIZ8rBtABe/sKZwFyyNp8Gh1K04S9kcEId8vXyr9F9ium+5Hpc2KjkW6gfIcXRYrwYA9kvwQT9i7xz/0Dtr39FNkcqJil59sI1MrRKI+SfMtAOxo85PPV5Dd5oWaFEgufexxZIjJoJrxocUw0TMwU1SMKeAFyyNp8D36DcvOYdJEs4SbdRH/WP+abiCnPTKHuV1lFxuZXcyig/HEv2+uGN3XgdRu5kKLto0DbkaRRrjb5Z9w9MytOzQzg0ffZnvUyE1uyCJInBV+kSnosrNi81+WSlKnCPhQO67i7y3H0zPmoQSSIw2e1VadZdAprAXLI2nwchfIb/xiTeWb2cnNDPj98A31b/i80QyRXEnQp2DAlwvPSp/CLs+J82tzps+lFFcKXT3QRID+/Y7D3wTxxKiET3/dwobW4y9hrHP+DhzU5h1GC5fOcvximpOl9KUp98viPrOAaMqs="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12786,"candidatesTokenCount":27,"totalTokenCount":12879,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12786}],"thoughtsTokenCount":66}},{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12786,"candidatesTokenCount":27,"totalTokenCount":12879,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12786}],"thoughtsTokenCount":66}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"OK."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12951,"candidatesTokenCount":2,"totalTokenCount":12953,"cachedContentTokenCount":12203,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12951}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12203}]}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"original content","file_path":"original.txt"}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I have created the file."}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Defining File Creation**\n\nI'm thinking about the user's intent to generate a file named \"input-test.txt\" with the content \" test\". I've determined that the `write_file` tool is suitable. I've parsed `file_path` as \"input-test.txt\" and `content` as \" test\". This should accomplish the user's need.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12778,"totalTokenCount":12840,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12778}],"thoughtsTokenCount":62}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"input-test.txt","content":"test"}},"thoughtSignature":"CiQBcsjafCO/Ifs3Lj/Gtzy2ylSYoGB3GXjJby4F3R8FxWp+hP0KZwFyyNp8oD7KvcSYXDimGOiqAdxtdOJpc2tFJbHm2Jw7ahiuKLtoKZWE+1bBZEWVKxC0dCQIeIcxZ0SaLn7tDbfc2qPzhyUA46d/T1+e314SFLWW1asIOBkQ4T0sFDAFPZ4m9bFm3UkKbAFyyNp8EAnclI0wYCGwpg0AOOV52F5J9Hc2EeaXkGsc6hCnba7aNhPucWYIn2Da8FK2IJAWUWaNvGNGoNUZETaG+iL9+6KRJgN3Ql/wQzQ2pHUvTGHC3RkfMGTQ+YCQKvlOReilps5lDmMnhQpTAXLI2nzcl9Aqd0Nb/w934w+tqz1Jth7GlQVMYktHOl7Hgkoykfh3NzM67SEAilxjowfBL6MY7UBUP3YGwi1CXVVa4d0wHnMD9BJYp2w8ztZch8I="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12778,"candidatesTokenCount":25,"totalTokenCount":12865,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12778}],"thoughtsTokenCount":62}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**File Creation Achieved**\n\nI've successfully created the file as requested. Now, I'm ready to move on to the next instruction whenever it arrives. I am now awaiting the next task.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12940,"totalTokenCount":12965,"cachedContentTokenCount":12203,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12940}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12203}],"thoughtsTokenCount":25}},{"candidates":[{"content":{"parts":[{"text":"Done.","thoughtSignature":"CiQBcsjafEwfH5zTnAjEjloMcDDflS/MmoH03HXVl8HoQ04vmVIKcQFyyNp8/6HrBz8vokXB1Ms1zW51p32T3Ni3HEbgSFPHMGZt9LHFtLkLzuFrxym66z1Tcb5tqj+7jAdpM/dIUb6ecrKj9FWqMB+QR4BSxdAiJSiL8Rp+Pc5ckCtT1nrv4C5w3/fhCNE4WvZzeyGPt+PACjsBcsjafNWzUJcHxgKp6MYWQ8RW0QrGerM51nkgXHBafxY5KwTznX4B/ETccGnXX3zSciaJiZR1FfudVw=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12940,"candidatesTokenCount":1,"totalTokenCount":12966,"cachedContentTokenCount":12203,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12940}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12203}],"thoughtsTokenCount":25}}]}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Formulating a Plan**\n\nOkay, I've outlined the initial steps: I'll use the `write_file` tool to make a file named `multi-event-test.txt` containing the text \"testing multiple events\". After that, I'll need to remember to reply with the phrase as requested. It seems straightforward so far.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12622,"totalTokenCount":12692,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12622}],"thoughtsTokenCount":70}},{"candidates":[{"content":{"parts":[{"text":"**Confirming the Procedure**\n\nI've solidified the steps. First, I'll create `multi-event-test.txt` using the `write_file` tool with the required content. Following that, my response will be \"BeforeAgent: User request processed.\" This ensures I fulfill both parts of the request.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12622,"totalTokenCount":12713,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12622}],"thoughtsTokenCount":91}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"file_path":"multi-event-test.txt","content":"testing multiple events"}},"thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12622,"candidatesTokenCount":28,"totalTokenCount":12741,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12622}],"thoughtsTokenCount":91}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12836,"totalTokenCount":12836,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12836}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}]}},{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12836,"totalTokenCount":12836,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12836}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12836,"totalTokenCount":12836,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12836}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}]}},{"candidates":[{"content":{"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12836,"totalTokenCount":12836,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12836}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}]}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Echoing User Commands**\n\nI'm now tasked with echoing a specific phrase following a particular signal, but it's becoming complex. The user wants me to repeat \"BeforeAgent: User request processed\" when prompted. It appears I need to retain context from the previous turn, the user's initial request to create a file, to correctly respond now.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12759,"totalTokenCount":12827,"cachedContentTokenCount":12199,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12759}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12199}],"thoughtsTokenCount":68}},{"candidates":[{"content":{"parts":[{"text":"**Responding Precisely to Prompt**\n\nI've determined I need to repeat the phrase \"BeforeAgent: User request processed,\" even though the overall context and turn history are complex. The user has given several prompts, but has now provided a more direct command, which I believe is to follow up on the previous request. I am taking care to match the specific instructions the user provided.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12759,"totalTokenCount":12982,"cachedContentTokenCount":12199,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12759}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12199}],"thoughtsTokenCount":223}},{"candidates":[{"content":{"parts":[{"text":"BeforeAgent: User request processed","thoughtSignature":"CiQBcsjafAntJrb1JBgpnZaCNeYhOJXtbH6dKTeM1llglCdoOvUKYwFyyNp8PUj5sihYyITQJhdz4MqEeftyuUc4G+iTprve11gPN04eK9Y1Wi/wyln4RjRgroIrV5kByKzdGhECoyCeInpiILGhY0peIM7dZOKFdIOL7xAR9pmn4wMreqyH7l5WSAqJAQFyyNp8Cugemkt4YZWkIwEJYmUukLFx4d5EwP/9k/e4OH/svpM+uyuN3n1KVN3bFgRV5yuF0HnDLl+P7WVSSxMmWvXO2f7A1HALg+gCvZw9IV7Btgg1qp81dDoNcVkzSbTBtT4UrlJ5R6sclvHZOLUtKGwBEQ6zRonBugAgj9RV4BT1AJNOgdSsCokBAXLI2nyDGU1Iq30QVbqhgEwFa5sB6uPC+35BV8ZKGwK+YglO9rqXMrkXM+GcQi2hVIsOFXBYGTS6E2/mQfFbIKDytrb1JgP3q5xVd/bE23M2Nnf+q5TLbRpLAPmyfg0AGwhN0L7d5W6b/3ydqEPeA1/Vw/cnBzz5ND1LOTOX6BFqEs33/WHj7HIKpAEBcsjafEsn8//cZMWUQcSAucBQauojv/f7h11nbeMrZK84nEotR30BgMIWYiiWM6sGDy/4MzHwr+z2YdAz4PSgRvEf7DPxHps2nvZfAdtskgtdPl2JD81WpokSnJvCqU+cOuz+Nh3+fIiZ6vEsVpi/5cwEiGT0g3Z3I2ubyzv58oH8YnVQlKT3MsKRGb5//aXZJY57jNrexgDPzYAQsBgSuGBmqwqaAQFyyNp8sSIYw3It6GpZqC+oxJCC26pt4RxhG8rDZ3zuoADYlOpoUdSzbNuDB+iVHeen5OoCEAaH0GrFV4iZxgu40wu4ZD/VMfHi/Vm7vku23EUV/94U8mT+VEwPfd2gqv+3xPZ9MEHjOOox1Xq1984w2cA6u0Qn7wWHXeOGFVGSOHtdJtQ7ToNT8VEecblAVq8lm42sSccXQEEKmAEBcsjafONCvBhW2s8Bset20YFdbeSHelnILFDxXlCoYla5nP5UjGk4vpXu2+7RCFtKXfoyYEVEkmiGBRsmwJ82Q1nMkGkXMhuTdNhu4aCwI5m+STGxx26vkp9bcqGwMDHBotZL63PSrJacRoW8zfpDXD1PABLeTIfh5jgipQdgltyjlbc+3qfIfjBYNRSkE8ByErSz5rT7SwqSAQFyyNp8W2kut1PSJISxM7YJtbRdFqPBTikGDM6F/3l6ba6LpeRBfHdtueLChqFpwLH41VdIPQ7lRZflOq3KaZz+TQ11eDnYQbiaIdGOPgHJ/HH/0iQv2hnoOY5vg3gubFWFuZh9Bfun2VCYUI39tIxGC46TZWfgCdiP/O9CFOlpDfidPiz5ZS/4LhG9FA4Q85OuCpEBAXLI2nzpoEUA6jCZopeNTRA2uZ1r0DMm5cWVVXtFO4CoRS+19BbADNBRyNrR5qcf7bUflJBvMRVxx3mtmgK9aE5VmKYxK2Dqg15l9RUxjtqspC3VVmszVd6lOkf1BBQ/VtWDulqRetKE2u62Is9NNGuK9HsLzIBLRRc8QoML41WffuXQ+uxwyXpjx2USC44MGAqIAQFyyNp8gN3lOyHyk674W3Pyv+Egw1ZDUQK4xpvAfgnK+y53gclMGJ2IjOSvg4j0f1WO1OGqY2TBUFS7w21PXasvCkfxpqeStEb+U7Vm0r63LzXdGdug5/b1Ap6Phn4/vAYmfaKISKG4+QpjI+ehgEJzsIee2rgqOaePTP18fq8T7EDbF/B/iscKNQFyyNp8DWt2a8OetaCc5E/KsntbbOcNc7yikPZBdUezphrqIH4ztpicsHvEicYF002qWHoY"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12759,"candidatesTokenCount":4,"totalTokenCount":12986,"cachedContentTokenCount":12199,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12759}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12199}],"thoughtsTokenCount":223}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Executing the Command**\n\nI've got the command, \"echo test,\" ready to go. My focus is entirely on calling the `run_shell_command` tool now. The user's input is processed, and the next step is straightforward: using the tool to execute the supplied command.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12751,"totalTokenCount":12801,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12751}],"thoughtsTokenCount":50}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"run_shell_command","args":{"command":"echo test","description":"Running the command 'echo test'"}},"thoughtSignature":"CiQBcsjafL1lDlnUGmt38n1/gjwecXzy9S3qEW5sYMEno5Mr7LEKZgFyyNp8jMABmMAatt49FTdh7UiM62SI1GnjcyG+kV7xzcD73uMKHST/0D0vKP7x1equv5d6YiXnOslhVnnHotYPtVl0/kI/0unBZRdMzkBNrJXKUoSWXJXxNpV6JhJav3Uh9h1sPQqOAQFyyNp8PFeESLk0J5cPFP0EA7a13iA/rXTiKoHnjSCzDV9ALcXM78xv10/V028ZtDeQslYfT82q4++W8AlJwTQRTIrdscu2y+nCS8jnQizYN1V1yR42eMzuBU3txXcqEV8bmP6GGOe58vrqyS2zdnJKCgMntMB/niwlJlr5frhDestSOJk62tVDWKFzOiAKOAFyyNp81FtGXQTX+OSio/2PbzpCCuaQFqpEgCZpkaXXyvmXYDAI1qCq1tA+m/e5ozWdm8zTGuyb"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12751,"candidatesTokenCount":28,"totalTokenCount":12829,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12751}],"thoughtsTokenCount":50}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Seeking Task Clarity**\n\nI'm currently focused on identifying the precise task. My initial assessment indicates the user is seeking assistance, but the specific requirements remain undefined. I will directly solicit a detailed task description from the user to clarify this.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12604,"totalTokenCount":12633,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12604}],"thoughtsTokenCount":29}},{"candidates":[{"content":{"parts":[{"text":"Hello! I'm ready to help. Please describe the task you'd like me to assist you with.","thoughtSignature":"CiQBcsjafM2CL00L595T19DK8M8zP5p9/tbFPPwdM2S6669z2FgKYQFyyNp8Ya0YVCtft9Asr/45XOCfNdPWbwZt8SvIeX3IxYzOFcOK14+DnoDIuTIrmRQBeUvdxD59QmEWx+/OaSxj9564L0IU703C1JX20buEtYhkRM4LhK0G4LG/z6IJauEKSQFyyNp8n784BnEcDTQGfZ8/s3pl/TNaNzjQx0o8wYCYZH1qsRbVa3YJAvRGrVXL6y9ka10w0lhEsrQ8vOiw6ilZKirA5DjLz4U="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12604,"candidatesTokenCount":22,"totalTokenCount":12655,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12604}],"thoughtsTokenCount":29}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Greeting the User**\n\nI've registered the user's greeting. I'm primed to respond with a friendly welcome and signal my availability to assist. My focus now is drafting a suitable response.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12761,"totalTokenCount":12787,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12761}],"thoughtsTokenCount":26}},{"candidates":[{"content":{"parts":[{"text":"Hello! I'm ready to help. What can I do for you?","thoughtSignature":"CikBcsjafBz/0rqJuIv9woxRvivjZyAqBjpoJhOTSPfcbMWCawTfcyKImQpxAXLI2nxyuBo6dqZmTxkH7XxPxjq7mNoacRa48wc/eT5caK/4tu0Y9fJ1ScpJZb+tCNzrqTNwVXa98ppjB2O/X4eejJN+hUr3LCalDFRdRLO17PFUI5qgYSbSgIGzhbnQASgzOArvvqzDPPgqXWVIDj8KMQFyyNp8ayfqBNRkBykRSTDtzOKVGkjLW1dXWamLB4ojeEVHSOgne4vlYaKs44pitsg="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12761,"candidatesTokenCount":15,"totalTokenCount":12802,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12761}],"thoughtsTokenCount":26}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Initiating a Dialogue**\n\nI've successfully received and understood the user's initial request. My next move will be to output a simple \"Hello\" as a greeting, fulfilling the basic instruction I was given. This constitutes the first step in the interaction, and I'm ready to move forward based on the user's subsequent input.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12588,"totalTokenCount":12607,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12588}],"thoughtsTokenCount":19}},{"candidates":[{"content":{"parts":[{"text":"Hello","thoughtSignature":"CikBcsjafB9jXawgyqQ5mpEJ4ihpLD/B2i8GR75sod00ZF3TCbrLHS9YjgpeAXLI2nx1fmJO2VIiwBpF+vLBPhYE/B2992PVW6XM20cEYx4g0leDNs6BIhzEipm6RYOxzgz8KxH9+ZkCnd8bVZr59lbDCgqSCSB6IKA+csXHKsF9g3UMRAtoSBwiBw=="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12588,"totalTokenCount":12607,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12588}],"thoughtsTokenCount":19}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_file","args":{"file_path":"original.txt"}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Tail call completed successfully."}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Initializing File Creation**\n\nI've decided on the `write_file` tool to create the telemetry file. I'll pass \"telemetry-test.txt\" as the file path, and an empty string for the content, as the user didn't specify anything to include. This is the initial setup; the file should now exist.\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12779,"totalTokenCount":12850,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":71}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"write_file","args":{"content":"","file_path":"telemetry-test.txt"}},"thoughtSignature":"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"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12779,"candidatesTokenCount":24,"totalTokenCount":12874,"cachedContentTokenCount":12204,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12779}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12204}],"thoughtsTokenCount":71}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"OK."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12951,"candidatesTokenCount":2,"totalTokenCount":12953,"cachedContentTokenCount":12202,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12951}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":12202}]}}]}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Investigating File Access**\n\nI'm currently focused on the challenge of reading a file. The path provided is `/gemini-cli/.integration-tests/1761766343238/json-output-error/path/to/nonexistent/file.txt`, and I'm anticipating an error. It's safe to assume the file doesn't exist, which I intend to handle by responding with \"File not found\" as instructed.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12303,"totalTokenCount":12418,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12303}],"thoughtsTokenCount":115}},{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Analyzing Error Handling**\n\nI've attempted to read the specified file, expecting an error due to the \"nonexistent\" path. My plan is to catch the error thrown by the `read_file` tool. Upon receiving this error, I'll promptly return \"File not found.\" This is in line with the initial instructions and ensures appropriate error management for the user's intended functionality. I'm now testing the error response.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12303,"totalTokenCount":12467,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12303}],"thoughtsTokenCount":164}},{"candidates":[{"content":{"parts":[{"thoughtSignature":"CiQB0e2Kb0c450IIdZRHl1vvjWDAl9oKa7s5sfFgrTnU0w3qBQwKYgHR7YpvPjZlXSHaJNYgX8IuCvxfyyeACX4NZ8u+u3Z1kqQbgOMpiH6aPYCK9lPyhVftPDBF2m3j7Y2AShwXSpB+9+UB3zphOKCvq6i0ZLvK6QzVynZ1fySQacyjEBD+U6y5CpoBAdHtim9D6oskRu7f3x8rp56h24i6dwb1hzlyqLGl3A5Hsh/fGYjBCxR+Vs+U5Sb7LunmFMKxmO1fktz0x06FUiyaWgAaXl4E4FyLTKs9BbPdgo58uAhaI3vTQybeGZQzkRi6n+ywCniVKaTUd07EHYWdvLiB6x5zFKVOiTmh8PC6I4vNOkJIzFXRfR5aM5QFjEQY8R88HBH+ugraAQHR7YpvuNUG8Ttbzg+kq+kJYMNGDG4zVLPxFBbJZYU5zGLFLrNeEpp9HJ+1N1Pdts17J5pzoefKd2U9H5muPxoeW1CCpFqqKfYZNyoChrQnb4CgWoJ92pcb2UAZbDQ6H4rTyXWdXaAEP1i8rOmdWzI5GFPyxCwBKAbFhfMJOo7P4va5H13XTlLgWAgXlx3n24ookkD/DOL9ro/F6pmV6tzf/j7RVl0V5yozngnrFl4dFsQPp1nDQcFkbRIKHD30byjLGh6Vd6A2lrB477qUaCRfPXtlEgKgsOSYCuABAdHtim+PJPZV3QuQoJ0Qokr+vcdW1W2qzC4Vvt4QRJXyp6+eIS6iNjOisk4jfWLHmLTa11KrUSQsFJnGwsFhe1foOqfO4y46ROBPeSdyuc0gDzSCZPowiovGBwoZd+MbPTTVyExWBo6StVk+xWLj+sUqa8VDof45AOOK9kdzcLQPa2SXIeK6SYLS1zVTrbzGHQDZPv9UC99lmKxPFqAcuwpe9CQre9J3GcZSwd5Mfs/UkHbWui10a8jga4Ck7umjKSDFq/VWiRUp/jh+EN4xeLTG/UQhgH49Gw+Bi1hN1uYKIgHR7YpvS0j1oO2HV/HeK3YxSku9CLQ3OSJGhoAKiu8UGYE=","functionCall":{"name":"read_file","args":{"file_path":"/gemini-cli/.integration-tests/1761766343238/json-output-error/path/to/nonexistent/file.txt"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12303,"candidatesTokenCount":58,"totalTokenCount":12525,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12303}],"thoughtsTokenCount":164}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"File not found"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12588,"candidatesTokenCount":3,"totalTokenCount":12591,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12588}]}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The capital of France is Paris."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":7,"candidatesTokenCount":7,"totalTokenCount":14,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7}]}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hello! How can I help you today?"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":5,"candidatesTokenCount":9,"totalTokenCount":14,"promptTokensDetails":[{"modality":"TEXT","tokenCount":5}]}}]}
|
||||
@@ -0,0 +1,164 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { expect, describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
import { ExitCodes } from '@google/gemini-cli-core/src/index.js';
|
||||
|
||||
describe('JSON output', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(async () => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should return a valid JSON with response and stats', async () => {
|
||||
await rig.setup('json-output-france', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'json-output.france.responses',
|
||||
),
|
||||
});
|
||||
const result = await rig.run({
|
||||
args: ['What is the capital of France?', '--output-format', 'json'],
|
||||
});
|
||||
const parsed = JSON.parse(result);
|
||||
|
||||
expect(parsed).toHaveProperty('response');
|
||||
expect(typeof parsed.response).toBe('string');
|
||||
expect(parsed.response.toLowerCase()).toContain('paris');
|
||||
|
||||
expect(parsed).toHaveProperty('stats');
|
||||
expect(typeof parsed.stats).toBe('object');
|
||||
});
|
||||
|
||||
it('should return a valid JSON with a session ID', async () => {
|
||||
await rig.setup('json-output-session-id', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'json-output.session-id.responses',
|
||||
),
|
||||
});
|
||||
const result = await rig.run({
|
||||
args: ['Hello', '--output-format', 'json'],
|
||||
});
|
||||
const parsed = JSON.parse(result);
|
||||
|
||||
expect(parsed).toHaveProperty('session_id');
|
||||
expect(typeof parsed.session_id).toBe('string');
|
||||
expect(parsed.session_id).not.toBe('');
|
||||
});
|
||||
|
||||
it('should return a JSON error for sd auth mismatch before running', async () => {
|
||||
await rig.setup('json-output-auth-mismatch', {
|
||||
settings: {
|
||||
security: {
|
||||
auth: { enforcedType: 'gemini-api-key', selectedType: '' },
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
let thrown: Error | undefined;
|
||||
try {
|
||||
await rig.run({
|
||||
args: ['Hello', '--output-format', 'json'],
|
||||
env: { GOOGLE_GENAI_USE_GCA: 'true' },
|
||||
});
|
||||
expect.fail('Expected process to exit with error');
|
||||
} catch (e) {
|
||||
thrown = e as Error;
|
||||
}
|
||||
|
||||
expect(thrown).toBeDefined();
|
||||
const message = (thrown as Error).message;
|
||||
|
||||
// Use a regex to find the first complete JSON object in the string
|
||||
// We expect the JSON to start with a quote (e.g. {"error": ...}) to avoid
|
||||
// matching random error objects printed to stderr (like ENOENT).
|
||||
const jsonMatch = message.match(/{\s*"[\s\S]*}/);
|
||||
|
||||
// Fail if no JSON-like text was found
|
||||
expect(
|
||||
jsonMatch,
|
||||
'Expected to find a JSON object in the error output',
|
||||
).toBeTruthy();
|
||||
|
||||
let payload;
|
||||
try {
|
||||
// Parse the matched JSON string
|
||||
payload = JSON.parse(jsonMatch![0]);
|
||||
} catch (parseError) {
|
||||
console.error('Failed to parse the following JSON:', jsonMatch![0]);
|
||||
throw new Error(
|
||||
`Test failed: Could not parse JSON from error message. Details: ${parseError}`,
|
||||
);
|
||||
}
|
||||
|
||||
expect(payload.error).toBeDefined();
|
||||
expect(payload.error.type).toBe('Error');
|
||||
expect(payload.error.code).toBe(ExitCodes.FATAL_AUTHENTICATION_ERROR);
|
||||
expect(payload.error.message).toContain(
|
||||
"enforced authentication type is 'gemini-api-key'",
|
||||
);
|
||||
expect(payload.error.message).toContain("current type is 'oauth-personal'");
|
||||
expect(payload).toHaveProperty('session_id');
|
||||
expect(typeof payload.session_id).toBe('string');
|
||||
expect(payload.session_id).not.toBe('');
|
||||
});
|
||||
|
||||
it('should not exit on tool errors and allow model to self-correct in JSON mode', async () => {
|
||||
await rig.setup('json-output-error', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'json-output.error.responses',
|
||||
),
|
||||
});
|
||||
const result = await rig.run({
|
||||
args: [
|
||||
`Read the contents of ${rig.testDir}/path/to/nonexistent/file.txt and tell me what it says. ` +
|
||||
'On error, respond to the user with exactly the text "File not found".',
|
||||
'--output-format',
|
||||
'json',
|
||||
],
|
||||
});
|
||||
|
||||
const parsed = JSON.parse(result);
|
||||
|
||||
// The response should contain an actual response from the model,
|
||||
// not a fatal error that caused the CLI to exit
|
||||
expect(parsed).toHaveProperty('response');
|
||||
expect(typeof parsed.response).toBe('string');
|
||||
|
||||
// The model should acknowledge the error in its response with exactly the
|
||||
// text "File not found" based on the instruction above, but we also match
|
||||
// some other forms. If you get flakes for this test please file an issue to
|
||||
// come up with a more robust solution.
|
||||
expect(parsed.response.toLowerCase()).toMatch(
|
||||
/cannot|does not exist|doesn't exist|not found|unable to|error|couldn't/,
|
||||
);
|
||||
|
||||
// Stats should be present, indicating the session completed normally.
|
||||
expect(parsed).toHaveProperty('stats');
|
||||
|
||||
// Should see one failed tool call in the stats.
|
||||
expect(parsed.stats).toHaveProperty('tools');
|
||||
expect(parsed.stats.tools.totalCalls).toBe(1);
|
||||
expect(parsed.stats.tools.totalFail).toBe(1);
|
||||
expect(parsed.stats.tools.totalSuccess).toBe(0);
|
||||
|
||||
// Should NOT have an error field at the top level
|
||||
expect(parsed.error).toBeUndefined();
|
||||
|
||||
expect(parsed).toHaveProperty('session_id');
|
||||
expect(typeof parsed.session_id).toBe('string');
|
||||
expect(parsed.session_id).not.toBe('');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,78 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
poll,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
import { existsSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
|
||||
describe('list_directory', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should be able to list a directory', async () => {
|
||||
await rig.setup('should be able to list a directory', {
|
||||
settings: { tools: { core: ['list_directory'] } },
|
||||
});
|
||||
rig.createFile('file1.txt', 'file 1 content');
|
||||
rig.mkdir('subdir');
|
||||
rig.sync();
|
||||
|
||||
// Poll for filesystem changes to propagate in containers
|
||||
await poll(
|
||||
() => {
|
||||
// Check if the files exist in the test directory
|
||||
const file1Path = join(rig.testDir!, 'file1.txt');
|
||||
const subdirPath = join(rig.testDir!, 'subdir');
|
||||
return existsSync(file1Path) && existsSync(subdirPath);
|
||||
},
|
||||
1000, // 1 second max wait
|
||||
50, // check every 50ms
|
||||
);
|
||||
|
||||
const prompt = `Can you list the files in the current directory.`;
|
||||
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
try {
|
||||
await rig.expectToolCallSuccess(['list_directory']);
|
||||
} catch (e) {
|
||||
// Add debugging information
|
||||
if (!result.includes('file1.txt') || !result.includes('subdir')) {
|
||||
const allTools = printDebugInfo(rig, result, {
|
||||
'Found tool call': false,
|
||||
'Contains file1.txt': result.includes('file1.txt'),
|
||||
'Contains subdir': result.includes('subdir'),
|
||||
});
|
||||
|
||||
console.error(
|
||||
'List directory calls:',
|
||||
allTools
|
||||
.filter((t) => t.toolRequest.name === 'list_directory')
|
||||
.map((t) => t.toolRequest.args),
|
||||
);
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: ['file1.txt', 'subdir'],
|
||||
testName: 'List directory test',
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"list_mcp_resources","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Here are the resources: test://resource1"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_mcp_resource","args":{"uri":"test://resource1"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The content is: content of resource 1"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
@@ -0,0 +1,4 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"list_mcp_resources","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Here are the resources: test://resource1"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_mcp_resource","args":{"uri":"test://resource1"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The content is: content of resource 1"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":10,"totalTokenCount":20}}]}
|
||||
@@ -0,0 +1,178 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join, dirname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import fs from 'node:fs';
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
|
||||
describe('mcp-resources-integration', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should list mcp resources', async () => {
|
||||
await rig.setup('mcp-list-resources-test', {
|
||||
settings: {
|
||||
model: {
|
||||
name: 'gemini-3-flash-preview',
|
||||
},
|
||||
},
|
||||
fakeResponsesPath: join(__dirname, 'mcp-list-resources.responses'),
|
||||
});
|
||||
|
||||
// Workaround for ProjectRegistry save issue
|
||||
const userGeminiDir = join(rig.homeDir!, '.gemini');
|
||||
fs.writeFileSync(join(userGeminiDir, 'projects.json'), '{"projects":{}}');
|
||||
|
||||
// Add a dummy server to get setup done
|
||||
rig.addTestMcpServer('resource-server', {
|
||||
name: 'resource-server',
|
||||
tools: [],
|
||||
});
|
||||
|
||||
// Overwrite the script with resource support
|
||||
const scriptPath = join(rig.testDir!, 'test-mcp-resource-server.mjs');
|
||||
const scriptContent = `
|
||||
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
|
||||
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
|
||||
import {
|
||||
ListResourcesRequestSchema,
|
||||
} from '@modelcontextprotocol/sdk/types.js';
|
||||
|
||||
const server = new Server(
|
||||
{
|
||||
name: 'resource-server',
|
||||
version: '1.0.0',
|
||||
},
|
||||
{
|
||||
capabilities: {
|
||||
resources: {},
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
server.setRequestHandler(ListResourcesRequestSchema, async () => {
|
||||
return {
|
||||
resources: [
|
||||
{
|
||||
uri: 'test://resource1',
|
||||
name: 'Resource 1',
|
||||
mimeType: 'text/plain',
|
||||
description: 'A test resource',
|
||||
}
|
||||
],
|
||||
};
|
||||
});
|
||||
|
||||
const transport = new StdioServerTransport();
|
||||
await server.connect(transport);
|
||||
`;
|
||||
fs.writeFileSync(scriptPath, scriptContent);
|
||||
|
||||
const output = await rig.run({
|
||||
args: 'List all available MCP resources.',
|
||||
env: { GEMINI_API_KEY: 'dummy' },
|
||||
});
|
||||
|
||||
const foundCall = await rig.waitForToolCall('list_mcp_resources');
|
||||
expect(foundCall).toBeTruthy();
|
||||
expect(output).toContain('test://resource1');
|
||||
}, 60000);
|
||||
|
||||
it('should read mcp resource', async () => {
|
||||
await rig.setup('mcp-read-resource-test', {
|
||||
settings: {
|
||||
model: {
|
||||
name: 'gemini-3-flash-preview',
|
||||
},
|
||||
},
|
||||
fakeResponsesPath: join(__dirname, 'mcp-read-resource.responses'),
|
||||
});
|
||||
|
||||
// Workaround for ProjectRegistry save issue
|
||||
const userGeminiDir = join(rig.homeDir!, '.gemini');
|
||||
fs.writeFileSync(join(userGeminiDir, 'projects.json'), '{"projects":{}}');
|
||||
|
||||
// Add a dummy server to get setup done
|
||||
rig.addTestMcpServer('resource-server', {
|
||||
name: 'resource-server',
|
||||
tools: [],
|
||||
});
|
||||
|
||||
// Overwrite the script with resource support
|
||||
const scriptPath = join(rig.testDir!, 'test-mcp-resource-server.mjs');
|
||||
const scriptContent = `
|
||||
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
|
||||
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
|
||||
import {
|
||||
ListResourcesRequestSchema,
|
||||
ReadResourceRequestSchema,
|
||||
} from '@modelcontextprotocol/sdk/types.js';
|
||||
|
||||
const server = new Server(
|
||||
{
|
||||
name: 'resource-server',
|
||||
version: '1.0.0',
|
||||
},
|
||||
{
|
||||
capabilities: {
|
||||
resources: {},
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
// Need to provide list resources so the tool is active!
|
||||
server.setRequestHandler(ListResourcesRequestSchema, async () => {
|
||||
return {
|
||||
resources: [
|
||||
{
|
||||
uri: 'test://resource1',
|
||||
name: 'Resource 1',
|
||||
mimeType: 'text/plain',
|
||||
description: 'A test resource',
|
||||
}
|
||||
],
|
||||
};
|
||||
});
|
||||
|
||||
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
|
||||
if (request.params.uri === 'test://resource1') {
|
||||
return {
|
||||
contents: [
|
||||
{
|
||||
uri: 'test://resource1',
|
||||
mimeType: 'text/plain',
|
||||
text: 'This is the content of resource 1',
|
||||
}
|
||||
],
|
||||
};
|
||||
}
|
||||
throw new Error('Resource not found');
|
||||
});
|
||||
|
||||
const transport = new StdioServerTransport();
|
||||
await server.connect(transport);
|
||||
`;
|
||||
fs.writeFileSync(scriptPath, scriptContent);
|
||||
|
||||
const output = await rig.run({
|
||||
args: 'Read the MCP resource test://resource1.',
|
||||
env: { GEMINI_API_KEY: 'dummy' },
|
||||
});
|
||||
|
||||
const foundCall = await rig.waitForToolCall('read_mcp_resource');
|
||||
expect(foundCall).toBeTruthy();
|
||||
expect(output).toContain('content of resource 1');
|
||||
}, 60000);
|
||||
});
|
||||
@@ -0,0 +1,207 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
/**
|
||||
* This test verifies we can provide MCP tools with recursive input schemas
|
||||
* (in JSON, using the $ref keyword) and both the GenAI SDK and the Gemini
|
||||
* API calls succeed. Note that prior to
|
||||
* https://github.com/googleapis/js-genai/commit/36f6350705ecafc47eaea3f3eecbcc69512edab7#diff-fdde9372aec859322b7c5a5efe467e0ad25a57210c7229724586ee90ea4f5a30
|
||||
* the Gemini API call would fail for such tools because the schema was
|
||||
* passed not as a JSON string but using the Gemini API's tool parameter
|
||||
* schema object which has stricter typing and recursion restrictions.
|
||||
* If this test fails, it's likely because either the GenAI SDK or Gemini API
|
||||
* has become more restrictive about the type of tool parameter schemas that
|
||||
* are accepted. If this occurs: Gemini CLI previously attempted to detect
|
||||
* such tools and proactively remove them from the set of tools provided in
|
||||
* the Gemini API call (as FunctionDeclaration objects). It may be appropriate
|
||||
* to resurrect that behavior but note that it's difficult to keep the
|
||||
* GCLI filters in sync with the Gemini API restrictions and behavior.
|
||||
*/
|
||||
|
||||
import { writeFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { describe, it, afterEach, beforeEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
// Create a minimal MCP server that doesn't require external dependencies
|
||||
// This implements the MCP protocol directly using Node.js built-ins
|
||||
const serverScript = `#!/usr/bin/env node
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
const readline = require('readline');
|
||||
const fs = require('fs');
|
||||
|
||||
// Debug logging to stderr (only when MCP_DEBUG or VERBOSE is set)
|
||||
const debugEnabled = process.env['MCP_DEBUG'] === 'true' || process.env['VERBOSE'] === 'true';
|
||||
function debug(msg) {
|
||||
if (debugEnabled) {
|
||||
fs.writeSync(2, \`[MCP-DEBUG] \${msg}\\n\`);
|
||||
}
|
||||
}
|
||||
|
||||
debug('MCP server starting...');
|
||||
|
||||
// Simple JSON-RPC implementation for MCP
|
||||
class SimpleJSONRPC {
|
||||
constructor() {
|
||||
this.handlers = new Map();
|
||||
this.rl = readline.createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout,
|
||||
terminal: false
|
||||
});
|
||||
|
||||
this.rl.on('line', (line) => {
|
||||
debug(\`Received line: \${line}\`);
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
debug(\`Parsed message: \${JSON.stringify(message)}\`);
|
||||
this.handleMessage(message);
|
||||
} catch (e) {
|
||||
debug(\`Parse error: \${e.message}\`);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
send(message) {
|
||||
const msgStr = JSON.stringify(message);
|
||||
debug(\`Sending message: \${msgStr}\`);
|
||||
process.stdout.write(msgStr + '\\n');
|
||||
}
|
||||
|
||||
async handleMessage(message) {
|
||||
if (message.method && this.handlers.has(message.method)) {
|
||||
try {
|
||||
const result = await this.handlers.get(message.method)(message.params || {});
|
||||
if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
result
|
||||
});
|
||||
}
|
||||
} catch (error) {
|
||||
if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
error: {
|
||||
code: -32603,
|
||||
message: error.message
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
} else if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
error: {
|
||||
code: -32601,
|
||||
message: 'Method not found'
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
on(method, handler) {
|
||||
this.handlers.set(method, handler);
|
||||
}
|
||||
}
|
||||
|
||||
// Create MCP server
|
||||
const rpc = new SimpleJSONRPC();
|
||||
|
||||
// Handle initialize
|
||||
rpc.on('initialize', async (params) => {
|
||||
debug('Handling initialize request');
|
||||
return {
|
||||
protocolVersion: '2024-11-05',
|
||||
capabilities: {
|
||||
tools: {}
|
||||
},
|
||||
serverInfo: {
|
||||
name: 'cyclic-schema-server',
|
||||
version: '1.0.0'
|
||||
}
|
||||
};
|
||||
});
|
||||
|
||||
// Handle tools/list
|
||||
rpc.on('tools/list', async () => {
|
||||
debug('Handling tools/list request');
|
||||
return {
|
||||
tools: [{
|
||||
name: 'tool_with_cyclic_schema',
|
||||
inputSchema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
data: {
|
||||
type: 'array',
|
||||
items: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
child: { $ref: '#/properties/data/items' },
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
}]
|
||||
};
|
||||
});
|
||||
|
||||
// Send initialization notification
|
||||
rpc.send({
|
||||
jsonrpc: '2.0',
|
||||
method: 'initialized'
|
||||
});
|
||||
`;
|
||||
|
||||
describe('mcp server with cyclic tool schema is detected', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('mcp tool list should include tool with cyclic tool schema', async () => {
|
||||
// Setup test directory with MCP server configuration
|
||||
await rig.setup('cyclic-schema-mcp-server', {
|
||||
settings: {
|
||||
mcpServers: {
|
||||
'cyclic-schema-server': {
|
||||
command: 'node',
|
||||
args: ['mcp-server.cjs'],
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
// Create server script in the test directory
|
||||
const testServerPath = join(rig.testDir!, 'mcp-server.cjs');
|
||||
writeFileSync(testServerPath, serverScript);
|
||||
|
||||
// Make the script executable (though running with 'node' should work anyway)
|
||||
if (process.platform !== 'win32') {
|
||||
const { chmodSync } = await import('node:fs');
|
||||
chmodSync(testServerPath, 0o755);
|
||||
}
|
||||
|
||||
const run = await rig.runInteractive();
|
||||
|
||||
await run.type('/mcp list');
|
||||
await run.type('\r');
|
||||
|
||||
await run.expectText('tool_with_cyclic_schema');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,65 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
describe('mixed input crash prevention', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should not crash when using mixed prompt inputs', async () => {
|
||||
rig.setup('should not crash when using mixed prompt inputs');
|
||||
|
||||
// Test: echo "say '1'." | gemini --prompt-interactive="say '2'." say '3'.
|
||||
const stdinContent = "say '1'.";
|
||||
|
||||
try {
|
||||
await rig.run({
|
||||
args: ['--prompt-interactive', "say '2'.", "say '3'."],
|
||||
stdin: stdinContent,
|
||||
});
|
||||
throw new Error('Expected the command to fail, but it succeeded');
|
||||
} catch (error: unknown) {
|
||||
expect(error).toBeInstanceOf(Error);
|
||||
const err = error as Error;
|
||||
|
||||
expect(err.message).toContain('Process exited with code 42');
|
||||
expect(err.message).toContain(
|
||||
'--prompt-interactive flag cannot be used when input is piped',
|
||||
);
|
||||
expect(err.message).not.toContain('setRawMode is not a function');
|
||||
expect(err.message).not.toContain('unexpected critical error');
|
||||
}
|
||||
|
||||
const lastRequest = rig.readLastApiRequest();
|
||||
expect(lastRequest).toBeNull();
|
||||
});
|
||||
|
||||
it('should provide clear error message for mixed input', async () => {
|
||||
rig.setup('should provide clear error message for mixed input');
|
||||
|
||||
try {
|
||||
await rig.run({
|
||||
args: ['--prompt-interactive', 'test prompt'],
|
||||
stdin: 'test input',
|
||||
});
|
||||
throw new Error('Expected the command to fail, but it succeeded');
|
||||
} catch (error: unknown) {
|
||||
expect(error).toBeInstanceOf(Error);
|
||||
const err = error as Error;
|
||||
|
||||
expect(err.message).toContain(
|
||||
'--prompt-interactive flag cannot be used when input is piped',
|
||||
);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,3 @@
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"{\n \"reasoning\": \"Simple task.\",\n \"model_choice\": \"flash\"\n}"}]},"finishReason":"STOP","index":0}]}}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_file","args":{"file_path":"file1.txt"}}},{"functionCall":{"name":"read_file","args":{"file_path":"file2.txt"}}},{"functionCall":{"name":"write_file","args":{"file_path":"output.txt","content":"wave2"}}},{"functionCall":{"name":"read_file","args":{"file_path":"file3.txt"}}},{"functionCall":{"name":"read_file","args":{"file_path":"file4.txt"}}}, {"text":"All waves completed successfully."}]},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"All waves completed successfully."}]},"finishReason":"STOP","index":0}]}}
|
||||
@@ -0,0 +1,83 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
import fs from 'node:fs';
|
||||
|
||||
describe('Parallel Tool Execution Integration', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should execute [read, read, write, read, read] in correct waves with user approval', async () => {
|
||||
rig.setup('parallel-wave-execution', {
|
||||
fakeResponsesPath: join(import.meta.dirname, 'parallel-tools.responses'),
|
||||
fakeResponsesNonStrict: true,
|
||||
settings: {
|
||||
tools: {
|
||||
core: ['read_file', 'write_file'],
|
||||
approval: 'ASK', // Disable YOLO mode to show permission prompts
|
||||
confirmationRequired: ['write_file'],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
rig.createFile('file1.txt', 'c1');
|
||||
rig.createFile('file2.txt', 'c2');
|
||||
rig.createFile('file3.txt', 'c3');
|
||||
rig.createFile('file4.txt', 'c4');
|
||||
rig.sync();
|
||||
|
||||
const run = await rig.runInteractive({ approvalMode: 'default' });
|
||||
|
||||
try {
|
||||
// 1. Trigger the wave
|
||||
await run.type('ok');
|
||||
await run.type('\r');
|
||||
|
||||
// 3. Wait for the write_file prompt.
|
||||
await run.expectText('Allow', 10000);
|
||||
|
||||
// 4. Press Enter to approve the write_file.
|
||||
await run.type('y');
|
||||
await run.type('\r');
|
||||
|
||||
// 5. Wait for the final model response
|
||||
await run.expectText('All waves completed successfully.', 10000);
|
||||
} catch (err) {
|
||||
fs.writeFileSync('pty_output_failure.txt', run.output);
|
||||
throw err;
|
||||
}
|
||||
|
||||
// Verify all tool calls were made and succeeded in the logs
|
||||
await rig.expectToolCallSuccess(['write_file']);
|
||||
const toolLogs = rig.readToolLogs();
|
||||
|
||||
const readFiles = toolLogs.filter(
|
||||
(l) => l.toolRequest.name === 'read_file',
|
||||
);
|
||||
const writeFiles = toolLogs.filter(
|
||||
(l) => l.toolRequest.name === 'write_file',
|
||||
);
|
||||
|
||||
expect(readFiles.length).toBe(4);
|
||||
expect(writeFiles.length).toBe(1);
|
||||
expect(toolLogs.every((l) => l.toolRequest.success)).toBe(true);
|
||||
|
||||
// Check that output.txt was actually written
|
||||
expect(fs.readFileSync(join(rig.testDir!, 'output.txt'), 'utf8')).toBe(
|
||||
'wave2',
|
||||
);
|
||||
}, 30000);
|
||||
});
|
||||
@@ -0,0 +1,310 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { writeFileSync, mkdirSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { GEMINI_DIR, TestRig, checkModelOutputContent } from './test-helper.js';
|
||||
|
||||
describe('Plan Mode', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should allow read-only tools but deny write tools in plan mode', async () => {
|
||||
await rig.setup(
|
||||
'should allow read-only tools but deny write tools in plan mode',
|
||||
{
|
||||
settings: {
|
||||
general: {
|
||||
plan: { enabled: true },
|
||||
},
|
||||
tools: {
|
||||
core: [
|
||||
'run_shell_command',
|
||||
'list_directory',
|
||||
'write_file',
|
||||
'read_file',
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
);
|
||||
|
||||
const result = await rig.run({
|
||||
approvalMode: 'plan',
|
||||
args: 'Please list the files in the current directory, and then attempt to create a new file named "denied.txt" using a shell command.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const lsLog = toolLogs.find((l) => l.toolRequest.name === 'list_directory');
|
||||
const shellLog = toolLogs.find(
|
||||
(l) => l.toolRequest.name === 'run_shell_command',
|
||||
);
|
||||
|
||||
expect(lsLog, 'Expected list_directory to be called').toBeDefined();
|
||||
expect(lsLog?.toolRequest.success).toBe(true);
|
||||
expect(
|
||||
shellLog,
|
||||
'Expected run_shell_command to be blocked (not even called)',
|
||||
).toBeUndefined();
|
||||
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: ['Plan Mode', 'read-only'],
|
||||
testName: 'Plan Mode restrictions test',
|
||||
});
|
||||
});
|
||||
|
||||
it('should allow write_file to the plans directory in plan mode', async () => {
|
||||
const plansDir = '.gemini/tmp/foo/123/plans';
|
||||
const testName =
|
||||
'should allow write_file to the plans directory in plan mode';
|
||||
|
||||
await rig.setup(testName, {
|
||||
settings: {
|
||||
tools: {
|
||||
core: ['write_file', 'read_file', 'list_directory'],
|
||||
},
|
||||
general: {
|
||||
plan: { enabled: true, directory: plansDir },
|
||||
defaultApprovalMode: 'plan',
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
approvalMode: 'plan',
|
||||
args:
|
||||
'Create a file called plan.md in the plans directory with the ' +
|
||||
'content "# Plan". Treat this as a Directive and write the file ' +
|
||||
'immediately without proposing strategy or asking for confirmation.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const planWrite = toolLogs.find(
|
||||
(l) =>
|
||||
l.toolRequest.name === 'write_file' &&
|
||||
l.toolRequest.args.includes('plans') &&
|
||||
l.toolRequest.args.includes('plan.md'),
|
||||
);
|
||||
|
||||
if (!planWrite) {
|
||||
console.error(
|
||||
'All tool calls found:',
|
||||
toolLogs.map((l) => ({
|
||||
name: l.toolRequest.name,
|
||||
args: l.toolRequest.args,
|
||||
})),
|
||||
);
|
||||
}
|
||||
|
||||
expect(
|
||||
planWrite,
|
||||
'Expected write_file to be called for plan.md',
|
||||
).toBeDefined();
|
||||
expect(
|
||||
planWrite?.toolRequest.success,
|
||||
`Expected write_file to succeed, but it failed with error: ${'error' in (planWrite?.toolRequest || {}) ? (planWrite?.toolRequest as unknown as Record<string, string>)['error'] : 'unknown'}`,
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it('should deny write_file to non-plans directory in plan mode', async () => {
|
||||
const plansDir = '.gemini/tmp/foo/123/plans';
|
||||
const testName =
|
||||
'should deny write_file to non-plans directory in plan mode';
|
||||
|
||||
await rig.setup(testName, {
|
||||
settings: {
|
||||
tools: {
|
||||
core: ['write_file', 'read_file', 'list_directory'],
|
||||
},
|
||||
general: {
|
||||
plan: { enabled: true, directory: plansDir },
|
||||
defaultApprovalMode: 'plan',
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
approvalMode: 'plan',
|
||||
args: 'Attempt to create a file named "hello.txt" in the current directory. Do not create a plan file, try to write hello.txt directly.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const writeLog = toolLogs.find(
|
||||
(l) =>
|
||||
l.toolRequest.name === 'write_file' &&
|
||||
l.toolRequest.args.includes('hello.txt'),
|
||||
);
|
||||
|
||||
if (writeLog) {
|
||||
expect(
|
||||
writeLog.toolRequest.success,
|
||||
'Expected write_file to non-plans dir to fail',
|
||||
).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
it('should be able to enter plan mode from default mode', async () => {
|
||||
await rig.setup('should be able to enter plan mode from default mode', {
|
||||
settings: {
|
||||
general: {
|
||||
plan: { enabled: true },
|
||||
},
|
||||
tools: {
|
||||
core: ['enter_plan_mode'],
|
||||
allowed: ['enter_plan_mode'],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
approvalMode: 'default',
|
||||
args: 'I want to perform a complex refactoring. Please enter plan mode so we can design it first.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const enterLog = toolLogs.find(
|
||||
(l) => l.toolRequest.name === 'enter_plan_mode',
|
||||
);
|
||||
expect(enterLog, 'Expected enter_plan_mode to be called').toBeDefined();
|
||||
expect(enterLog?.toolRequest.success).toBe(true);
|
||||
});
|
||||
|
||||
it('should allow write_file to the plans directory in plan mode even without a session ID', async () => {
|
||||
const plansDir = '.gemini/tmp/foo/plans';
|
||||
const testName =
|
||||
'should allow write_file to the plans directory in plan mode even without a session ID';
|
||||
|
||||
await rig.setup(testName, {
|
||||
settings: {
|
||||
tools: {
|
||||
core: ['write_file', 'read_file', 'list_directory'],
|
||||
},
|
||||
general: {
|
||||
plan: { enabled: true, directory: plansDir },
|
||||
defaultApprovalMode: 'plan',
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
approvalMode: 'plan',
|
||||
args:
|
||||
'Create a file called plan-no-session.md in the plans directory ' +
|
||||
'with the content "# Plan". Treat this as a Directive and write ' +
|
||||
'the file immediately without proposing strategy or asking for ' +
|
||||
'confirmation.',
|
||||
});
|
||||
|
||||
const toolLogs = rig.readToolLogs();
|
||||
const planWrite = toolLogs.find(
|
||||
(l) =>
|
||||
l.toolRequest.name === 'write_file' &&
|
||||
l.toolRequest.args.includes('plans') &&
|
||||
l.toolRequest.args.includes('plan-no-session.md'),
|
||||
);
|
||||
|
||||
if (!planWrite) {
|
||||
console.error(
|
||||
'All tool calls found:',
|
||||
toolLogs.map((l) => ({
|
||||
name: l.toolRequest.name,
|
||||
args: l.toolRequest.args,
|
||||
})),
|
||||
);
|
||||
}
|
||||
|
||||
expect(
|
||||
planWrite,
|
||||
'Expected write_file to be called for plan-no-session.md',
|
||||
).toBeDefined();
|
||||
expect(
|
||||
planWrite?.toolRequest.success,
|
||||
`Expected write_file to succeed, but it failed with error: ${'error' in (planWrite?.toolRequest || {}) ? (planWrite?.toolRequest as unknown as Record<string, string>)['error'] : 'unknown'}`,
|
||||
).toBe(true);
|
||||
});
|
||||
|
||||
it.skip('should switch from a pro model to a flash model after exiting plan mode', async () => {
|
||||
const plansDir = 'plans-folder';
|
||||
const planFilename = 'my-plan.md';
|
||||
|
||||
await rig.setup('should-switch-to-flash', {
|
||||
settings: {
|
||||
model: {
|
||||
name: 'auto-gemini-2.5',
|
||||
},
|
||||
experimental: { plan: true },
|
||||
tools: {
|
||||
core: ['exit_plan_mode', 'run_shell_command'],
|
||||
allowed: ['exit_plan_mode', 'run_shell_command'],
|
||||
},
|
||||
general: {
|
||||
defaultApprovalMode: 'plan',
|
||||
plan: {
|
||||
directory: plansDir,
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
writeFileSync(
|
||||
join(rig.homeDir!, GEMINI_DIR, 'state.json'),
|
||||
JSON.stringify({ terminalSetupPromptShown: true }, null, 2),
|
||||
);
|
||||
|
||||
const fullPlansDir = join(rig.testDir!, plansDir);
|
||||
mkdirSync(fullPlansDir, { recursive: true });
|
||||
writeFileSync(join(fullPlansDir, planFilename), 'Execute echo hello');
|
||||
|
||||
await rig.run({
|
||||
approvalMode: 'plan',
|
||||
stdin: `Exit plan mode using ${planFilename} and then run a shell command \`echo hello\`.`,
|
||||
});
|
||||
|
||||
const exitCallFound = await rig.waitForToolCall('exit_plan_mode');
|
||||
expect(exitCallFound, 'Expected exit_plan_mode to be called').toBe(true);
|
||||
|
||||
const shellCallFound = await rig.waitForToolCall('run_shell_command');
|
||||
expect(shellCallFound, 'Expected run_shell_command to be called').toBe(
|
||||
true,
|
||||
);
|
||||
|
||||
const apiRequests = rig.readAllApiRequest();
|
||||
const modelNames = apiRequests.map(
|
||||
(r) =>
|
||||
('model' in (r.attributes || {})
|
||||
? (r.attributes as unknown as Record<string, string>)['model']
|
||||
: 'unknown') || 'unknown',
|
||||
);
|
||||
|
||||
const proRequests = apiRequests.filter((r) =>
|
||||
('model' in (r.attributes || {})
|
||||
? (r.attributes as unknown as Record<string, string>)['model']
|
||||
: 'unknown'
|
||||
)?.includes('pro'),
|
||||
);
|
||||
const flashRequests = apiRequests.filter((r) =>
|
||||
('model' in (r.attributes || {})
|
||||
? (r.attributes as unknown as Record<string, string>)['model']
|
||||
: 'unknown'
|
||||
)?.includes('flash'),
|
||||
);
|
||||
|
||||
expect(
|
||||
proRequests.length,
|
||||
`Expected at least one Pro request. Models used: ${modelNames.join(', ')}`,
|
||||
).toBeGreaterThanOrEqual(1);
|
||||
expect(
|
||||
flashRequests.length,
|
||||
`Expected at least one Flash request after mode switch. Models used: ${modelNames.join(', ')}`,
|
||||
).toBeGreaterThanOrEqual(1);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will read the content of the file to identify its"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7969,"candidatesTokenCount":11,"totalTokenCount":8061,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7969}],"thoughtsTokenCount":81}},{"candidates":[{"content":{"parts":[{"text":" language.\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7969,"candidatesTokenCount":14,"totalTokenCount":8064,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7969}],"thoughtsTokenCount":81}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"read_file","args":{"file_path":"test.txt"}},"thoughtSignature":"EvkCCvYCAb4+9vt8mJ/o45uuuAJtfjaZ3YzkJzqXHZBttRE+Om0ahcr1S5RDFp50KpgHtJtbAH1pwEXampOnDV3WKiWwA+e3Jnyk4CNQegz7ZMKsl55Nem2XDViP8BZKnJVqGmSFuMoKJLFmbVIxKejtWcblfn3httbGsrUUNbHwdPjPHo1qY043lF63g0kWx4v68gPSsJpNhxLrSugKKjiyRFN+J0rOIBHI2S9MdZoHEKhJxvGMtXiJquxmhPmKcNEsn+hMdXAZB39hmrRrGRHDQPVYVPhfJthVc73ufzbn+5KGJpaMQyKY5hqrc2ea8MHz+z6BSx+tFz4NZBff1tJQOiUp09/QndxQRZHSQZr1ALGy0O1Qw4JqsX94x81IxtXqYkSRo3zgm2vl/xPMC5lKlnK5xoKJmoWaHkUNeXs/sopu3/Waf1a5Csoh9ImnKQsW0rJ6GRyDQvky1FwR6Aa98bgfNdcXOPHml/BtghaqRMXTiG6vaPJ8UFs="}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7969,"candidatesTokenCount":64,"totalTokenCount":8114,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7969}],"thoughtsTokenCount":81}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":7969,"candidatesTokenCount":64,"totalTokenCount":8114,"cachedContentTokenCount":6082,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7969}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":6082}],"thoughtsTokenCount":81}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The language of the file is Latin."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8054,"candidatesTokenCount":8,"totalTokenCount":8078,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8054}],"thoughtsTokenCount":16}},{"candidates":[{"content":{"parts":[{"text":"","thoughtSignature":"EnIKcAG+Pvb7vnRBJVz3khx1oArQQqTNvXOXkliNQS7NvYw94dq5m+wGKRmSj3egO3GVp7pacnAtLn9NT1ABKBGpa7MpRhiAe3bbPZfkqOuveeyC19LKQ9fzasCywiYqg5k5qSxfjs5okk+O0NLOvTjN/tg="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8135,"candidatesTokenCount":8,"totalTokenCount":8159,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8135}],"thoughtsTokenCount":16}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will run the requested"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":5,"totalTokenCount":8092,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":138}},{"candidates":[{"content":{"parts":[{"text":" shell command to verify the policy configuration.\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":14,"totalTokenCount":8101,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":138}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"run_shell_command","args":{"command":"echo POLICY_TEST_ECHO_COMMAND","description":"Echo the test string to verify policy settings."}},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":54,"totalTokenCount":8141,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":138}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":54,"totalTokenCount":8141,"cachedContentTokenCount":6082,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":6082}],"thoughtsTokenCount":138}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"POLICY_TEST_"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8042,"candidatesTokenCount":4,"totalTokenCount":8046,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8042}]}},{"candidates":[{"content":{"parts":[{"text":"ECHO_COMMAND"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8042,"candidatesTokenCount":8,"totalTokenCount":8050,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8042}]}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8180,"candidatesTokenCount":8,"totalTokenCount":8188,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8180}]}}]}
|
||||
@@ -0,0 +1,2 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"**Assessing Command Execution**\n\nOkay, I'm currently assessing the feasibility of executing `echo POLICY_TEST_ECHO_COMMAND` using the `run_shell_command` function. Restrictions are being evaluated; the prompt is specifically geared towards a successful command output: \"POLICY_TEST_ECHO_COMMAND\".\n\n\n","thought":true}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"totalTokenCount":7949,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}]}},{"candidates":[{"content":{"parts":[{"text":"I will execute the requested echo"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":6,"totalTokenCount":8161,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":206}},{"candidates":[{"content":{"parts":[{"text":" command to verify the policy."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":12,"totalTokenCount":8167,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":206}},{"candidates":[{"content":{"parts":[{"functionCall":{"name":"run_shell_command","args":{"description":"Execute the echo command as requested.","command":"echo POLICY_TEST_ECHO_COMMAND"}},"thoughtSignature":"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"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":50,"totalTokenCount":8205,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"thoughtsTokenCount":206}},{"candidates":[{"content":{"parts":[{"text":""}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":7949,"candidatesTokenCount":50,"totalTokenCount":8205,"cachedContentTokenCount":6082,"promptTokensDetails":[{"modality":"TEXT","tokenCount":7949}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":6082}],"thoughtsTokenCount":206}}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"AR NAR"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":8020,"candidatesTokenCount":2,"totalTokenCount":8049,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8020}],"thoughtsTokenCount":27}},{"candidates":[{"content":{"parts":[{"text":"","thoughtSignature":"Er8BCrwBAb4+9vv6KGeMf6yopmPBE/az7Kjdp+Pe5a/R6wgXcyCZzGNwkwKFW3i3ro0j26bRrVeHD1zRfWFTIGdOSZKV6OMPWLqFC/RU6CNJ88B1xY7hbCVwA7EchYPzgd3YZRVNwmFu52j86/9qXf/zaqTFN+WQ0mUESJXh2O2YX8E7imAvxhmRdobVkxvEt4ZX3dW5skDhXHMDZOxbLpX0nkK7cWWS7iEc+qBFP0yinlA/eiG2ZdKpuTiDl76a9ik="}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":8226,"candidatesTokenCount":2,"totalTokenCount":8255,"promptTokensDetails":[{"modality":"TEXT","tokenCount":8226}],"thoughtsTokenCount":27}}]}
|
||||
@@ -0,0 +1,211 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { join } from 'node:path';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
interface PromptCommand {
|
||||
prompt: (testFile: string) => string;
|
||||
tool: string;
|
||||
command: string;
|
||||
expectedSuccessResult: string;
|
||||
expectedFailureResult: string;
|
||||
}
|
||||
|
||||
const ECHO_PROMPT: PromptCommand = {
|
||||
command: 'echo',
|
||||
prompt: () =>
|
||||
`Use the \`echo POLICY_TEST_ECHO_COMMAND\` shell command. On success, ` +
|
||||
`your final response must ONLY be "POLICY_TEST_ECHO_COMMAND". If the ` +
|
||||
`command fails output AR NAR and stop.`,
|
||||
tool: 'run_shell_command',
|
||||
expectedSuccessResult: 'POLICY_TEST_ECHO_COMMAND',
|
||||
expectedFailureResult: 'AR NAR',
|
||||
};
|
||||
|
||||
const READ_FILE_PROMPT: PromptCommand = {
|
||||
prompt: (testFile: string) =>
|
||||
`Read the file ${testFile} and tell me what language it is, if the ` +
|
||||
`read_file tool fails output AR NAR and stop.`,
|
||||
tool: 'read_file',
|
||||
command: '',
|
||||
expectedSuccessResult: 'Latin',
|
||||
expectedFailureResult: 'AR NAR',
|
||||
};
|
||||
|
||||
async function waitForToolCallLog(
|
||||
rig: TestRig,
|
||||
tool: string,
|
||||
command: string,
|
||||
timeout: number = 15000,
|
||||
) {
|
||||
const foundToolCall = await rig.waitForToolCall(tool, timeout, (args) =>
|
||||
args.toLowerCase().includes(command.toLowerCase()),
|
||||
);
|
||||
|
||||
expect(foundToolCall).toBe(true);
|
||||
|
||||
const toolLogs = rig
|
||||
.readToolLogs()
|
||||
.filter((toolLog) => toolLog.toolRequest.name === tool);
|
||||
const log = toolLogs.find(
|
||||
(toolLog) =>
|
||||
!command ||
|
||||
toolLog.toolRequest.args.toLowerCase().includes(command.toLowerCase()),
|
||||
);
|
||||
|
||||
// The policy engine should have logged the tool call
|
||||
expect(log).toBeTruthy();
|
||||
return log;
|
||||
}
|
||||
|
||||
async function verifyToolExecution(
|
||||
rig: TestRig,
|
||||
promptCommand: PromptCommand,
|
||||
result: string,
|
||||
expectAllowed: boolean,
|
||||
expectedDenialString?: string,
|
||||
) {
|
||||
const log = await waitForToolCallLog(
|
||||
rig,
|
||||
promptCommand.tool,
|
||||
promptCommand.command,
|
||||
);
|
||||
|
||||
if (expectAllowed) {
|
||||
expect(log!.toolRequest.success).toBe(true);
|
||||
expect(result).not.toContain('Tool execution denied by policy');
|
||||
expect(result).not.toContain(`Tool "${promptCommand.tool}" not found`);
|
||||
expect(result).toContain(promptCommand.expectedSuccessResult);
|
||||
} else {
|
||||
expect(log!.toolRequest.success).toBe(false);
|
||||
expect(result).toContain(
|
||||
expectedDenialString || 'Tool execution denied by policy',
|
||||
);
|
||||
expect(result).toContain(promptCommand.expectedFailureResult);
|
||||
}
|
||||
}
|
||||
|
||||
interface TestCase {
|
||||
name: string;
|
||||
responsesFile: string;
|
||||
promptCommand: PromptCommand;
|
||||
policyContent?: string;
|
||||
expectAllowed: boolean;
|
||||
expectedDenialString?: string;
|
||||
}
|
||||
|
||||
describe('Policy Engine Headless Mode', () => {
|
||||
let rig: TestRig;
|
||||
let testFile: string;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
if (rig) {
|
||||
await rig.cleanup();
|
||||
}
|
||||
});
|
||||
|
||||
const runTestCase = async (tc: TestCase) => {
|
||||
const fakeResponsesPath = join(import.meta.dirname, tc.responsesFile);
|
||||
rig.setup(tc.name, { fakeResponsesPath });
|
||||
|
||||
testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');
|
||||
const args = ['-p', tc.promptCommand.prompt(testFile)];
|
||||
|
||||
if (tc.policyContent) {
|
||||
const policyPath = rig.createFile('test-policy.toml', tc.policyContent);
|
||||
args.push('--policy', policyPath);
|
||||
}
|
||||
|
||||
const result = await rig.run({
|
||||
args,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
await verifyToolExecution(
|
||||
rig,
|
||||
tc.promptCommand,
|
||||
result,
|
||||
tc.expectAllowed,
|
||||
tc.expectedDenialString,
|
||||
);
|
||||
};
|
||||
|
||||
const testCases = [
|
||||
{
|
||||
name: 'should deny ASK_USER tools by default in headless mode',
|
||||
responsesFile: 'policy-headless-shell-denied.responses',
|
||||
promptCommand: ECHO_PROMPT,
|
||||
expectAllowed: false,
|
||||
expectedDenialString: 'Tool "run_shell_command" not found',
|
||||
},
|
||||
{
|
||||
name: 'should allow ASK_USER tools in headless mode if explicitly allowed via policy file',
|
||||
responsesFile: 'policy-headless-shell-allowed.responses',
|
||||
promptCommand: ECHO_PROMPT,
|
||||
policyContent: `
|
||||
[[rule]]
|
||||
toolName = "run_shell_command"
|
||||
decision = "allow"
|
||||
priority = 100
|
||||
`,
|
||||
expectAllowed: true,
|
||||
},
|
||||
{
|
||||
name: 'should allow read-only tools by default in headless mode',
|
||||
responsesFile: 'policy-headless-readonly.responses',
|
||||
promptCommand: READ_FILE_PROMPT,
|
||||
expectAllowed: true,
|
||||
},
|
||||
{
|
||||
name: 'should allow specific shell commands in policy file',
|
||||
responsesFile: 'policy-headless-shell-allowed.responses',
|
||||
promptCommand: ECHO_PROMPT,
|
||||
policyContent: `
|
||||
[[rule]]
|
||||
toolName = "run_shell_command"
|
||||
commandPrefix = "${ECHO_PROMPT.command}"
|
||||
decision = "allow"
|
||||
priority = 100
|
||||
`,
|
||||
expectAllowed: true,
|
||||
},
|
||||
{
|
||||
name: 'should deny other shell commands in policy file',
|
||||
responsesFile: 'policy-headless-shell-denied.responses',
|
||||
promptCommand: ECHO_PROMPT,
|
||||
policyContent: `
|
||||
[[rule]]
|
||||
toolName = "run_shell_command"
|
||||
commandPrefix = "echo"
|
||||
decision = "deny"
|
||||
priority = 100
|
||||
|
||||
[[rule]]
|
||||
toolName = "run_shell_command"
|
||||
commandPrefix = "node"
|
||||
decision = "allow"
|
||||
priority = 90
|
||||
`,
|
||||
expectAllowed: false,
|
||||
expectedDenialString: 'Tool execution denied by policy',
|
||||
},
|
||||
];
|
||||
|
||||
it.each(testCases)(
|
||||
'$name',
|
||||
async (tc) => {
|
||||
await runTestCase(tc);
|
||||
},
|
||||
// Large timeout for regeneration
|
||||
process.env['REGENERATE_MODEL_GOLDENS'] === 'true' ? 120000 : undefined,
|
||||
);
|
||||
});
|
||||
@@ -0,0 +1,61 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
|
||||
describe('read_many_files', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it.skip('should be able to read multiple files', async () => {
|
||||
await rig.setup('should be able to read multiple files', {
|
||||
settings: { tools: { core: ['read_many_files', 'read_file'] } },
|
||||
});
|
||||
rig.createFile('file1.txt', 'file 1 content');
|
||||
rig.createFile('file2.txt', 'file 2 content');
|
||||
|
||||
const prompt = `Use the read_many_files tool to read the contents of file1.txt and file2.txt and then print the contents of each file.`;
|
||||
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
// Check for either read_many_files or multiple read_file calls
|
||||
const allTools = rig.readToolLogs();
|
||||
const readManyFilesCall = await rig.waitForToolCall('read_many_files');
|
||||
const readFileCalls = allTools.filter(
|
||||
(t) => t.toolRequest.name === 'read_file',
|
||||
);
|
||||
|
||||
// Accept either read_many_files OR at least 2 read_file calls
|
||||
const foundValidPattern = readManyFilesCall || readFileCalls.length >= 2;
|
||||
|
||||
// Add debugging information
|
||||
if (!foundValidPattern) {
|
||||
printDebugInfo(rig, result, {
|
||||
'read_many_files called': readManyFilesCall,
|
||||
'read_file calls': readFileCalls.length,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundValidPattern,
|
||||
'Expected to find either read_many_files or multiple read_file tool calls',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, { testName: 'Read many files test' });
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,101 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
describe('replace', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
it('should be able to replace content in a file', async () => {
|
||||
await rig.setup('should be able to replace content in a file', {
|
||||
settings: { tools: { core: ['replace', 'read_file'] } },
|
||||
});
|
||||
|
||||
const fileName = 'file_to_replace.txt';
|
||||
const originalContent = 'foo content';
|
||||
const expectedContent = 'bar content';
|
||||
|
||||
rig.createFile(fileName, originalContent);
|
||||
|
||||
await rig.run({
|
||||
args: `Replace 'foo' with 'bar' in the file 'file_to_replace.txt'`,
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('replace');
|
||||
expect(foundToolCall, 'Expected to find a replace tool call').toBeTruthy();
|
||||
|
||||
expect(rig.readFile(fileName)).toBe(expectedContent);
|
||||
});
|
||||
|
||||
it.skip('should handle $ literally when replacing text ending with $', async () => {
|
||||
await rig.setup(
|
||||
'should handle $ literally when replacing text ending with $',
|
||||
{ settings: { tools: { core: ['replace', 'read_file'] } } },
|
||||
);
|
||||
|
||||
const fileName = 'regex.yml';
|
||||
const originalContent = "| select('match', '^[sv]d[a-z]$')\n";
|
||||
const expectedContent = "| select('match', '^[sv]d[a-z]$') # updated\n";
|
||||
|
||||
rig.createFile(fileName, originalContent);
|
||||
|
||||
await rig.run({
|
||||
args: "Open regex.yml and append ' # updated' after the line containing ^[sv]d[a-z]$ without breaking the $ character.",
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('replace');
|
||||
expect(foundToolCall, 'Expected to find a replace tool call').toBeTruthy();
|
||||
|
||||
expect(rig.readFile(fileName)).toBe(expectedContent);
|
||||
});
|
||||
|
||||
it.skip('should insert a multi-line block of text', async () => {
|
||||
await rig.setup('should insert a multi-line block of text', {
|
||||
settings: { tools: { core: ['replace', 'read_file'] } },
|
||||
});
|
||||
const fileName = 'insert_block.txt';
|
||||
const originalContent = 'Line A\n<INSERT_TEXT_HERE>\nLine C';
|
||||
const newBlock = 'First line\nSecond line\nThird line';
|
||||
const expectedContent =
|
||||
'Line A\nFirst line\nSecond line\nThird line\nLine C';
|
||||
rig.createFile(fileName, originalContent);
|
||||
|
||||
const prompt = `In ${fileName}, replace "<INSERT_TEXT_HERE>" with:\n${newBlock}. Use unix style line endings.`;
|
||||
await rig.run({ args: prompt });
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('replace');
|
||||
expect(foundToolCall, 'Expected to find a replace tool call').toBeTruthy();
|
||||
|
||||
expect(rig.readFile(fileName)).toBe(expectedContent);
|
||||
});
|
||||
|
||||
it.skip('should delete a block of text', async () => {
|
||||
await rig.setup('should delete a block of text', {
|
||||
settings: { tools: { core: ['replace', 'read_file'] } },
|
||||
});
|
||||
const fileName = 'delete_block.txt';
|
||||
const blockToDelete =
|
||||
'## DELETE THIS ##\nThis is a block of text to delete.\n## END DELETE ##';
|
||||
const originalContent = `Hello\n${blockToDelete}\nWorld`;
|
||||
const expectedContent = 'Hello\nWorld';
|
||||
rig.createFile(fileName, originalContent);
|
||||
|
||||
await rig.run({
|
||||
args: `In ${fileName}, delete the entire block from "## DELETE THIS ##" to "## END DELETE ##" including the markers and the newline that follows it.`,
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('replace');
|
||||
expect(foundToolCall, 'Expected to find a replace tool call').toBeTruthy();
|
||||
|
||||
expect(rig.readFile(fileName)).toBe(expectedContent);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,149 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import * as path from 'node:path';
|
||||
import * as fs from 'node:fs';
|
||||
import { FinishReason, GenerateContentResponse } from '@google/genai';
|
||||
import type { FakeResponse } from '@google/gemini-cli-core';
|
||||
|
||||
describe('Context Management Resume E2E', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should preserve and utilize GC snapshot boundaries when resuming a session', async () => {
|
||||
const snapshotResponse: FakeResponse = {
|
||||
method: 'generateContent',
|
||||
response: {
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [
|
||||
{
|
||||
text: JSON.stringify({
|
||||
new_facts: ['GC Triggered.'],
|
||||
new_constraints: [],
|
||||
new_tasks: [],
|
||||
resolved_task_ids: [],
|
||||
obsolete_fact_indices: [],
|
||||
obsolete_constraint_indices: [],
|
||||
chronological_summary: 'Snapshot created.',
|
||||
}),
|
||||
},
|
||||
],
|
||||
role: 'model',
|
||||
},
|
||||
finishReason: FinishReason.STOP,
|
||||
index: 0,
|
||||
},
|
||||
],
|
||||
} as unknown as GenerateContentResponse,
|
||||
};
|
||||
|
||||
const countTokensResponse: FakeResponse = {
|
||||
method: 'countTokens',
|
||||
response: { totalTokens: 50000 },
|
||||
};
|
||||
|
||||
const streamResponse = (text: string): FakeResponse => ({
|
||||
method: 'generateContentStream',
|
||||
response: [
|
||||
{
|
||||
candidates: [
|
||||
{
|
||||
content: { parts: [{ text }], role: 'model' },
|
||||
finishReason: FinishReason.STOP,
|
||||
index: 0,
|
||||
},
|
||||
],
|
||||
},
|
||||
] as unknown as GenerateContentResponse[],
|
||||
});
|
||||
|
||||
const setupResponses = (fileName: string, mocks: FakeResponse[]) => {
|
||||
const filePath = path.join(rig.testDir!, fileName);
|
||||
fs.writeFileSync(
|
||||
filePath,
|
||||
mocks.map((m) => JSON.stringify(m)).join('\n'),
|
||||
);
|
||||
return filePath;
|
||||
};
|
||||
|
||||
await rig.setup('resume-gc-snapshot', {
|
||||
settings: {
|
||||
experimental: {
|
||||
stressTestProfile: true,
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const massivePayload = 'X'.repeat(40000);
|
||||
const logFile = path.join(rig.testDir!, 'debug.log');
|
||||
const traceDir = path.join(rig.testDir!, 'traces');
|
||||
fs.mkdirSync(traceDir, { recursive: true });
|
||||
const traceLog = path.join(traceDir, 'trace.log');
|
||||
|
||||
const commonEnv = {
|
||||
GEMINI_API_KEY: 'mock-key',
|
||||
GEMINI_DEBUG_LOG_FILE: logFile,
|
||||
GEMINI_CONTEXT_TRACE_DIR: traceDir,
|
||||
};
|
||||
|
||||
// Provide a massive pool of responses to prevent exhaustion
|
||||
const runMocks: FakeResponse[] = [streamResponse('Acknowledged block.')];
|
||||
for (let i = 0; i < 50; i++) {
|
||||
runMocks.push(snapshotResponse);
|
||||
runMocks.push(countTokensResponse);
|
||||
}
|
||||
|
||||
// Use stdin for the massive payload to avoid ENAMETOOLONG on Windows
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp1.json', runMocks),
|
||||
],
|
||||
stdin: 'Turn 1: ' + massivePayload,
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--resume',
|
||||
'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp2.json', runMocks),
|
||||
],
|
||||
stdin: 'Turn 2: ' + massivePayload,
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
const result3 = await rig.run({
|
||||
args: [
|
||||
'--debug',
|
||||
'--resume',
|
||||
'latest',
|
||||
'--fake-responses-non-strict',
|
||||
setupResponses('resp3.json', runMocks),
|
||||
'continue',
|
||||
],
|
||||
env: commonEnv,
|
||||
});
|
||||
|
||||
expect(result3).toContain('Acknowledged block');
|
||||
|
||||
const traces = fs.readFileSync(traceLog, 'utf-8');
|
||||
expect(traces).toContain('Hitting Synchronous Pressure Barrier');
|
||||
expect(traces).toContain('GC Triggered.');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Session started."}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1,42 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import * as path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
||||
|
||||
describe('resume-repro', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should be able to resume a session without "Storage must be initialized before use"', async () => {
|
||||
const responsesPath = path.join(__dirname, 'resume_repro.responses');
|
||||
await rig.setup('should be able to resume a session', {
|
||||
fakeResponsesPath: responsesPath,
|
||||
});
|
||||
|
||||
// 1. First run to create a session
|
||||
await rig.run({
|
||||
args: 'hello',
|
||||
});
|
||||
|
||||
// 2. Second run with --resume latest
|
||||
// This should NOT fail with "Storage must be initialized before use"
|
||||
const result = await rig.run({
|
||||
args: ['--resume', 'latest', 'continue'],
|
||||
});
|
||||
|
||||
expect(result).toContain('Session started');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,150 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
|
||||
import * as path from 'node:path';
|
||||
import * as fs from 'node:fs/promises';
|
||||
import * as os from 'node:os';
|
||||
import {
|
||||
RipGrepTool,
|
||||
resolveRipgrepPath,
|
||||
} from '../packages/core/src/tools/ripGrep.js';
|
||||
import { Config } from '../packages/core/src/config/config.js';
|
||||
import { WorkspaceContext } from '../packages/core/src/utils/workspaceContext.js';
|
||||
import { createMockMessageBus } from '../packages/core/src/test-utils/mock-message-bus.js';
|
||||
|
||||
// Mock Config to provide necessary context
|
||||
class MockConfig {
|
||||
constructor(private targetDir: string) {}
|
||||
|
||||
getTargetDir() {
|
||||
return this.targetDir;
|
||||
}
|
||||
|
||||
getWorkspaceContext() {
|
||||
return new WorkspaceContext(this.targetDir, [this.targetDir]);
|
||||
}
|
||||
|
||||
getDebugMode() {
|
||||
return true;
|
||||
}
|
||||
|
||||
getFileFilteringRespectGitIgnore() {
|
||||
return true;
|
||||
}
|
||||
|
||||
getFileFilteringRespectGeminiIgnore() {
|
||||
return true;
|
||||
}
|
||||
|
||||
getFileFilteringOptions() {
|
||||
return {
|
||||
respectGitIgnore: true,
|
||||
respectGeminiIgnore: true,
|
||||
customIgnoreFilePaths: [],
|
||||
};
|
||||
}
|
||||
|
||||
validatePathAccess() {
|
||||
return null;
|
||||
}
|
||||
|
||||
async getRipgrepPath() {
|
||||
return resolveRipgrepPath();
|
||||
}
|
||||
}
|
||||
|
||||
describe('ripgrep-real-direct', () => {
|
||||
let tempDir: string;
|
||||
let tool: RipGrepTool;
|
||||
|
||||
beforeAll(async () => {
|
||||
tempDir = await fs.mkdtemp(path.join(os.tmpdir(), 'ripgrep-real-test-'));
|
||||
|
||||
// Create test files
|
||||
await fs.writeFile(path.join(tempDir, 'file1.txt'), 'hello world\n');
|
||||
await fs.mkdir(path.join(tempDir, 'subdir'));
|
||||
await fs.writeFile(
|
||||
path.join(tempDir, 'subdir', 'file2.txt'),
|
||||
'hello universe\n',
|
||||
);
|
||||
await fs.writeFile(path.join(tempDir, 'file3.txt'), 'goodbye moon\n');
|
||||
|
||||
const config = new MockConfig(tempDir) as unknown as Config;
|
||||
tool = new RipGrepTool(config, createMockMessageBus());
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await fs.rm(tempDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('should find matches using the real ripgrep binary', async () => {
|
||||
const invocation = tool.build({ pattern: 'hello' });
|
||||
const result = await invocation.execute({
|
||||
abortSignal: new AbortController().signal,
|
||||
});
|
||||
|
||||
expect(result.llmContent).toContain('Found 2 matches');
|
||||
expect(result.llmContent).toContain('file1.txt');
|
||||
expect(result.llmContent).toContain('L1: hello world');
|
||||
expect(result.llmContent).toContain('subdir'); // Should show path
|
||||
expect(result.llmContent).toContain('file2.txt');
|
||||
expect(result.llmContent).toContain('L1: hello universe');
|
||||
|
||||
expect(result.llmContent).not.toContain('goodbye moon');
|
||||
});
|
||||
|
||||
it('should handle no matches correctly', async () => {
|
||||
const invocation = tool.build({ pattern: 'nonexistent_pattern_123' });
|
||||
const result = await invocation.execute({
|
||||
abortSignal: new AbortController().signal,
|
||||
});
|
||||
|
||||
expect(result.llmContent).toContain('No matches found');
|
||||
});
|
||||
|
||||
it('should respect include filters', async () => {
|
||||
// Create a .js file
|
||||
await fs.writeFile(
|
||||
path.join(tempDir, 'script.js'),
|
||||
'console.log("hello");\n',
|
||||
);
|
||||
|
||||
const invocation = tool.build({
|
||||
pattern: 'hello',
|
||||
include_pattern: '*.js',
|
||||
});
|
||||
const result = await invocation.execute({
|
||||
abortSignal: new AbortController().signal,
|
||||
});
|
||||
|
||||
expect(result.llmContent).toContain('Found 1 match');
|
||||
expect(result.llmContent).toContain('script.js');
|
||||
expect(result.llmContent).not.toContain('file1.txt');
|
||||
});
|
||||
|
||||
it('should support context parameters', async () => {
|
||||
// Create a file with multiple lines
|
||||
await fs.writeFile(
|
||||
path.join(tempDir, 'context.txt'),
|
||||
'line1\nline2\nline3 match\nline4\nline5\n',
|
||||
);
|
||||
|
||||
const invocation = tool.build({
|
||||
pattern: 'match',
|
||||
context: 1,
|
||||
});
|
||||
const result = await invocation.execute({
|
||||
abortSignal: new AbortController().signal,
|
||||
});
|
||||
|
||||
expect(result.llmContent).toContain('Found 1 match');
|
||||
expect(result.llmContent).toContain('context.txt');
|
||||
expect(result.llmContent).toContain('L2- line2');
|
||||
expect(result.llmContent).toContain('L3: line3 match');
|
||||
expect(result.llmContent).toContain('L4- line4');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,644 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
import { getShellConfiguration } from '../packages/core/src/utils/shell-utils.js';
|
||||
|
||||
const { shell } = getShellConfiguration();
|
||||
|
||||
function getLineCountCommand(): { command: string; tool: string } {
|
||||
switch (shell) {
|
||||
case 'powershell':
|
||||
return { command: `Measure-Object -Line`, tool: 'Measure-Object' };
|
||||
case 'cmd':
|
||||
return { command: `find /c /v`, tool: 'find' };
|
||||
case 'bash':
|
||||
default:
|
||||
return { command: `wc -l`, tool: 'wc' };
|
||||
}
|
||||
}
|
||||
|
||||
function getInvalidCommand(): string {
|
||||
switch (shell) {
|
||||
case 'powershell':
|
||||
return `Get-ChildItem | | Select-Object`;
|
||||
case 'cmd':
|
||||
return `dir | | findstr foo`;
|
||||
case 'bash':
|
||||
default:
|
||||
return `echo "hello" > > file`;
|
||||
}
|
||||
}
|
||||
|
||||
function getAllowedListCommand(): string {
|
||||
switch (shell) {
|
||||
case 'powershell':
|
||||
return 'Get-ChildItem';
|
||||
case 'cmd':
|
||||
return 'dir';
|
||||
case 'bash':
|
||||
default:
|
||||
return 'ls';
|
||||
}
|
||||
}
|
||||
|
||||
function getDisallowedFileReadCommand(testFile: string): {
|
||||
command: string;
|
||||
tool: string;
|
||||
} {
|
||||
const quotedPath = `"${testFile}"`;
|
||||
switch (shell) {
|
||||
case 'powershell':
|
||||
return {
|
||||
command: `powershell -Command "Get-Content ${quotedPath}"`,
|
||||
tool: 'powershell',
|
||||
};
|
||||
case 'cmd':
|
||||
return { command: `cmd /c type ${quotedPath}`, tool: 'cmd' };
|
||||
case 'bash':
|
||||
default:
|
||||
return {
|
||||
command: `node -e "console.log(require('fs').readFileSync('${testFile}', 'utf8'))"`,
|
||||
tool: 'node',
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
function getChainedEchoCommand(): { allowPattern: string; command: string } {
|
||||
const secondCommand = getAllowedListCommand();
|
||||
switch (shell) {
|
||||
case 'powershell':
|
||||
return {
|
||||
allowPattern: 'Write-Output',
|
||||
command: `Write-Output "foo" && ${secondCommand}`,
|
||||
};
|
||||
case 'cmd':
|
||||
return {
|
||||
allowPattern: 'echo',
|
||||
command: `echo "foo" && ${secondCommand}`,
|
||||
};
|
||||
case 'bash':
|
||||
default:
|
||||
return {
|
||||
allowPattern: 'echo',
|
||||
command: `echo "foo" && ${secondCommand}`,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
describe('run_shell_command', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
it('should be able to run a shell command', async () => {
|
||||
await rig.setup('should be able to run a shell command', {
|
||||
settings: { tools: { core: ['run_shell_command'] } },
|
||||
});
|
||||
|
||||
const prompt = `Please run the command "echo hello-world" and show me the output`;
|
||||
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command');
|
||||
|
||||
// Add debugging information
|
||||
if (!foundToolCall || !result.includes('hello-world')) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Contains hello-world': result.includes('hello-world'),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: ['hello-world', 'exit code 0'],
|
||||
testName: 'Shell command test',
|
||||
});
|
||||
});
|
||||
|
||||
it('should be able to run a shell command via stdin', async () => {
|
||||
await rig.setup('should be able to run a shell command via stdin', {
|
||||
settings: { tools: { core: ['run_shell_command'] } },
|
||||
});
|
||||
|
||||
const prompt = `Please run the command "echo test-stdin" and show me what it outputs`;
|
||||
|
||||
const result = await rig.run({ stdin: prompt });
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command');
|
||||
|
||||
// Add debugging information
|
||||
if (!foundToolCall || !result.includes('test-stdin')) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Test type': 'Stdin test',
|
||||
'Found tool call': foundToolCall,
|
||||
'Contains test-stdin': result.includes('test-stdin'),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: 'test-stdin',
|
||||
testName: 'Shell command stdin test',
|
||||
});
|
||||
});
|
||||
|
||||
it.skip('should run allowed sub-command in non-interactive mode', async () => {
|
||||
await rig.setup('should run allowed sub-command in non-interactive mode');
|
||||
|
||||
const testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');
|
||||
const { tool, command } = getLineCountCommand();
|
||||
const prompt = `use ${command} to tell me how many lines there are in ${testFile}`;
|
||||
|
||||
// Provide the prompt via stdin to simulate non-interactive mode
|
||||
const result = await rig.run({
|
||||
args: [`--allowed-tools=run_shell_command(${tool})`],
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
|
||||
|
||||
if (!foundToolCall) {
|
||||
const toolLogs = rig.readToolLogs().map(({ toolRequest }) => ({
|
||||
name: toolRequest.name,
|
||||
success: toolRequest.success,
|
||||
args: toolRequest.args,
|
||||
}));
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Allowed tools flag': `run_shell_command(${tool})`,
|
||||
Prompt: prompt,
|
||||
'Tool logs': toolLogs,
|
||||
Result: result,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const toolCall = rig
|
||||
.readToolLogs()
|
||||
.filter(
|
||||
(toolCall) => toolCall.toolRequest.name === 'run_shell_command',
|
||||
)[0];
|
||||
expect(toolCall.toolRequest.success).toBe(true);
|
||||
});
|
||||
|
||||
it.skip('should succeed with no parens in non-interactive mode', async () => {
|
||||
await rig.setup('should succeed with no parens in non-interactive mode');
|
||||
|
||||
const testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');
|
||||
const { command } = getLineCountCommand();
|
||||
const prompt = `use ${command} to tell me how many lines there are in ${testFile}`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: '--allowed-tools=run_shell_command',
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
|
||||
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const toolCall = rig
|
||||
.readToolLogs()
|
||||
.filter(
|
||||
(toolCall) => toolCall.toolRequest.name === 'run_shell_command',
|
||||
)[0];
|
||||
expect(toolCall.toolRequest.success).toBe(true);
|
||||
});
|
||||
|
||||
it('should succeed in yolo mode', async () => {
|
||||
const isWindows = process.platform === 'win32';
|
||||
await rig.setup('should succeed in yolo mode', {
|
||||
settings: {
|
||||
tools: { core: ['run_shell_command'] },
|
||||
shell: isWindows ? { enableInteractiveShell: false } : undefined,
|
||||
},
|
||||
});
|
||||
|
||||
const testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');
|
||||
const { command } = getLineCountCommand();
|
||||
const prompt = `use ${command} to tell me how many lines there are in ${testFile}`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: prompt,
|
||||
approvalMode: 'yolo',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
|
||||
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const toolCall = rig
|
||||
.readToolLogs()
|
||||
.filter(
|
||||
(toolCall) => toolCall.toolRequest.name === 'run_shell_command',
|
||||
)[0];
|
||||
expect(toolCall.toolRequest.success).toBe(true);
|
||||
});
|
||||
|
||||
it.skip('should work with ShellTool alias', async () => {
|
||||
await rig.setup('should work with ShellTool alias');
|
||||
|
||||
const testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');
|
||||
const { tool, command } = getLineCountCommand();
|
||||
const prompt = `use ${command} to tell me how many lines there are in ${testFile}`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: `--allowed-tools=ShellTool(${tool})`,
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
|
||||
|
||||
if (!foundToolCall) {
|
||||
const toolLogs = rig.readToolLogs().map(({ toolRequest }) => ({
|
||||
name: toolRequest.name,
|
||||
success: toolRequest.success,
|
||||
args: toolRequest.args,
|
||||
}));
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Allowed tools flag': `ShellTool(${tool})`,
|
||||
Prompt: prompt,
|
||||
'Tool logs': toolLogs,
|
||||
Result: result,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const toolCall = rig
|
||||
.readToolLogs()
|
||||
.filter(
|
||||
(toolCall) => toolCall.toolRequest.name === 'run_shell_command',
|
||||
)[0];
|
||||
expect(toolCall.toolRequest.success).toBe(true);
|
||||
});
|
||||
|
||||
// TODO(#11062): Un-skip this once we can make it reliable by using hard coded
|
||||
// model responses.
|
||||
it.skip('should combine multiple --allowed-tools flags', async () => {
|
||||
await rig.setup('should combine multiple --allowed-tools flags');
|
||||
|
||||
const { tool, command } = getLineCountCommand();
|
||||
const prompt =
|
||||
`use both ${command} and ls to count the number of lines in files in this ` +
|
||||
`directory. Do not pipe these commands into each other, run them separately.`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: [
|
||||
`--allowed-tools=run_shell_command(${tool})`,
|
||||
'--allowed-tools=run_shell_command(ls)',
|
||||
],
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
for (const expected in ['ls', tool]) {
|
||||
const foundToolCall = await rig.waitForToolCall(
|
||||
'run_shell_command',
|
||||
15000,
|
||||
(args) => args.toLowerCase().includes(`"command": "${expected}`),
|
||||
);
|
||||
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
`Expected to find a run_shell_command tool call to "${expected}",` +
|
||||
` got ${rig.readToolLogs().join('\n')}`,
|
||||
).toBeTruthy();
|
||||
}
|
||||
|
||||
const toolLogs = rig
|
||||
.readToolLogs()
|
||||
.filter((toolCall) => toolCall.toolRequest.name === 'run_shell_command');
|
||||
expect(toolLogs.length, toolLogs.join('\n')).toBeGreaterThanOrEqual(2);
|
||||
for (const toolLog of toolLogs) {
|
||||
expect(
|
||||
toolLog.toolRequest.success,
|
||||
`Expected tool call ${toolLog} to succeed`,
|
||||
).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('should reject commands not on the allowlist', async () => {
|
||||
await rig.setup('should reject commands not on the allowlist', {
|
||||
settings: { tools: { core: ['run_shell_command'] } },
|
||||
});
|
||||
|
||||
const testFile = rig.createFile('test.txt', 'Disallowed command check\n');
|
||||
const allowedCommand = getAllowedListCommand();
|
||||
const disallowed = getDisallowedFileReadCommand(testFile);
|
||||
const prompt =
|
||||
`I am testing the allowed tools configuration. ` +
|
||||
`Attempt to run "${disallowed.command}" to read the contents of ${testFile}. ` +
|
||||
`If the command fails because it is not permitted, respond with the single word FAIL. ` +
|
||||
`If it succeeds, respond with SUCCESS.`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: `--allowed-tools=run_shell_command(${allowedCommand})`,
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
if (!result.toLowerCase().includes('fail')) {
|
||||
printDebugInfo(rig, result, {
|
||||
Result: result,
|
||||
AllowedCommand: allowedCommand,
|
||||
DisallowedCommand: disallowed.command,
|
||||
});
|
||||
}
|
||||
expect(result).toContain('FAIL');
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall(
|
||||
'run_shell_command',
|
||||
15000,
|
||||
(args) => args.toLowerCase().includes(disallowed.tool.toLowerCase()),
|
||||
);
|
||||
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
ToolLogs: rig.readToolLogs(),
|
||||
});
|
||||
}
|
||||
expect(foundToolCall).toBe(true);
|
||||
|
||||
const toolLogs = rig
|
||||
.readToolLogs()
|
||||
.filter((toolLog) => toolLog.toolRequest.name === 'run_shell_command');
|
||||
const failureLog = toolLogs.find((toolLog) =>
|
||||
toolLog.toolRequest.args
|
||||
.toLowerCase()
|
||||
.includes(disallowed.tool.toLowerCase()),
|
||||
);
|
||||
|
||||
if (!failureLog || failureLog.toolRequest.success) {
|
||||
printDebugInfo(rig, result, {
|
||||
ToolLogs: toolLogs,
|
||||
DisallowedTool: disallowed.tool,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
failureLog,
|
||||
'Expected failing run_shell_command invocation',
|
||||
).toBeTruthy();
|
||||
expect(failureLog!.toolRequest.success).toBe(false);
|
||||
});
|
||||
|
||||
// TODO(#11966): Deflake this test and re-enable once the underlying race is resolved.
|
||||
it.skip('should reject chained commands when only the first segment is allowlisted in non-interactive mode', async () => {
|
||||
await rig.setup(
|
||||
'should reject chained commands when only the first segment is allowlisted',
|
||||
);
|
||||
|
||||
const chained = getChainedEchoCommand();
|
||||
const shellInjection = `!{${chained.command}}`;
|
||||
|
||||
await rig.run({
|
||||
args: `--allowed-tools=ShellTool(${chained.allowPattern})`,
|
||||
stdin: `${shellInjection}\n`,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
// CLI should refuse to execute the chained command without scheduling run_shell_command.
|
||||
const toolLogs = rig
|
||||
.readToolLogs()
|
||||
.filter((log) => log.toolRequest.name === 'run_shell_command');
|
||||
|
||||
// Success is false because tool is in the scheduled state.
|
||||
for (const log of toolLogs) {
|
||||
expect(log.toolRequest.success).toBe(false);
|
||||
expect(log.toolRequest.args).toContain('&&');
|
||||
}
|
||||
});
|
||||
|
||||
it('should allow all with "ShellTool" and other specific tools', async () => {
|
||||
await rig.setup(
|
||||
'should allow all with "ShellTool" and other specific tools',
|
||||
{
|
||||
settings: { tools: { core: ['run_shell_command'] } },
|
||||
},
|
||||
);
|
||||
|
||||
const { tool } = getLineCountCommand();
|
||||
const prompt = `Please run the command "echo test-allow-all" and show me the output`;
|
||||
|
||||
const result = await rig.run({
|
||||
args: [
|
||||
`--allowed-tools=run_shell_command(${tool})`,
|
||||
'--allowed-tools=run_shell_command',
|
||||
],
|
||||
stdin: prompt,
|
||||
approvalMode: 'default',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
|
||||
|
||||
if (!foundToolCall || !result.includes('test-allow-all')) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
Result: result,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
const toolCall = rig
|
||||
.readToolLogs()
|
||||
.filter(
|
||||
(toolCall) => toolCall.toolRequest.name === 'run_shell_command',
|
||||
)[0];
|
||||
expect(toolCall.toolRequest.success).toBe(true);
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: 'test-allow-all',
|
||||
testName: 'Shell command stdin allow all',
|
||||
});
|
||||
});
|
||||
|
||||
it('should propagate environment variables to the child process', async () => {
|
||||
await rig.setup('should propagate environment variables', {
|
||||
settings: { tools: { core: ['run_shell_command'] } },
|
||||
});
|
||||
|
||||
const varName = 'GEMINI_CLI_TEST_VAR';
|
||||
const varValue = `test-value-${Math.random().toString(36).substring(7)}`;
|
||||
process.env[varName] = varValue;
|
||||
|
||||
try {
|
||||
const prompt = `Use echo to learn the value of the environment variable named ${varName} and tell me what it is.`;
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command');
|
||||
|
||||
if (!foundToolCall || !result.includes(varValue)) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Contains varValue': result.includes(varValue),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: varValue,
|
||||
testName: 'Env var propagation test',
|
||||
});
|
||||
expect(result).toContain(varValue);
|
||||
} finally {
|
||||
delete process.env[varName];
|
||||
}
|
||||
});
|
||||
|
||||
it.skip('should run a platform-specific file listing command', async () => {
|
||||
await rig.setup('should run platform-specific file listing');
|
||||
const fileName = `test-file-${Math.random().toString(36).substring(7)}.txt`;
|
||||
rig.createFile(fileName, 'test content');
|
||||
|
||||
const prompt = `Run a shell command to list the files in the current directory and tell me what they are.`;
|
||||
const result = await rig.run({ args: prompt });
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('run_shell_command');
|
||||
|
||||
// Debugging info
|
||||
if (!foundToolCall || !result.includes(fileName)) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
'Contains fileName': result.includes(fileName),
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
foundToolCall,
|
||||
'Expected to find a run_shell_command tool call',
|
||||
).toBeTruthy();
|
||||
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: fileName,
|
||||
testName: 'Platform-specific listing test',
|
||||
});
|
||||
expect(result).toContain(fileName);
|
||||
});
|
||||
|
||||
it('rejects invalid shell expressions', async () => {
|
||||
await rig.setup('rejects invalid shell expressions', {
|
||||
settings: {
|
||||
tools: {
|
||||
core: ['run_shell_command'],
|
||||
allowed: ['run_shell_command(echo)'], // Specifically allow echo
|
||||
},
|
||||
},
|
||||
});
|
||||
const invalidCommand = getInvalidCommand();
|
||||
const result = await rig.run({
|
||||
args: `I am testing the error handling of the run_shell_command tool. Please attempt to run the following command, which I know has invalid syntax: \`${invalidCommand}\`. If the command fails as expected, please return the word FAIL, otherwise return the word SUCCESS.`,
|
||||
approvalMode: 'default', // Use default mode so safety fallback triggers confirmation
|
||||
});
|
||||
expect(result).toContain('FAIL');
|
||||
|
||||
const escapedInvalidCommand = JSON.stringify(invalidCommand).slice(1, -1);
|
||||
const foundToolCall = await rig.waitForToolCall(
|
||||
'run_shell_command',
|
||||
15000,
|
||||
(args) =>
|
||||
args.toLowerCase().includes(escapedInvalidCommand.toLowerCase()),
|
||||
);
|
||||
|
||||
if (!foundToolCall) {
|
||||
printDebugInfo(rig, result, {
|
||||
'Found tool call': foundToolCall,
|
||||
EscapedCommand: escapedInvalidCommand,
|
||||
ToolLogs: rig.readToolLogs(),
|
||||
});
|
||||
}
|
||||
expect(foundToolCall).toBe(true);
|
||||
|
||||
const toolLogs = rig
|
||||
.readToolLogs()
|
||||
.filter((toolLog) => toolLog.toolRequest.name === 'run_shell_command');
|
||||
const failureLog = toolLogs.find((toolLog) =>
|
||||
toolLog.toolRequest.args
|
||||
.toLowerCase()
|
||||
.includes(escapedInvalidCommand.toLowerCase()),
|
||||
);
|
||||
|
||||
if (!failureLog || failureLog.toolRequest.success) {
|
||||
printDebugInfo(rig, result, {
|
||||
ToolLogs: toolLogs,
|
||||
EscapedCommand: escapedInvalidCommand,
|
||||
});
|
||||
}
|
||||
|
||||
expect(
|
||||
failureLog,
|
||||
'Expected failing run_shell_command invocation for invalid syntax',
|
||||
).toBeTruthy();
|
||||
expect(failureLog!.toolRequest.success).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,5 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will run the command in the background for you."},{"functionCall":{"name":"run_shell_command","args":{"command":"sleep 10 && echo hello-from-background","is_background":true}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The background process has been started. Now I will list the background processes to verify."},{"functionCall":{"name":"list_background_processes","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I see the background process 'sleep 10 && echo hello-from-background' is running. Would you like me to read its output?"}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I will read the output for you."},{"functionCall":{"name":"read_background_output","args":{"pid":12345}}}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The output of the background process is:\nhello-from-background"}],"role":"model"},"finishReason":"STOP","index":0}]}]}
|
||||
@@ -0,0 +1,105 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import { join, dirname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
||||
describe('shell-background-tools', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should run a command in the background, list it, and read its output', async () => {
|
||||
// We use a fake responses file to make the test deterministic and run in CI.
|
||||
rig.setup('shell-background-workflow', {
|
||||
fakeResponsesPath: join(__dirname, 'shell-background.responses'),
|
||||
settings: {
|
||||
tools: {
|
||||
core: [
|
||||
'run_shell_command',
|
||||
'list_background_processes',
|
||||
'read_background_output',
|
||||
],
|
||||
},
|
||||
hooksConfig: {
|
||||
enabled: true,
|
||||
},
|
||||
hooks: {
|
||||
BeforeTool: [
|
||||
{
|
||||
matcher: 'run_shell_command',
|
||||
hooks: [
|
||||
{
|
||||
type: 'command',
|
||||
// This hook intercepts run_shell_command.
|
||||
// If is_background is true, it returns a mock result with PID 12345.
|
||||
// It also creates the mock log file that read_background_output expects.
|
||||
command: `node -e "
|
||||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
const input = JSON.parse(fs.readFileSync(0, 'utf-8'));
|
||||
const args = JSON.parse(input.tool_call.args);
|
||||
|
||||
if (args.is_background) {
|
||||
const logDir = path.join(process.env.GEMINI_CLI_HOME, 'background-processes');
|
||||
if (!fs.existsSync(logDir)) fs.mkdirSync(logDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(logDir, 'background-12345.log'), 'hello-from-background\\n');
|
||||
|
||||
console.log(JSON.stringify({
|
||||
decision: 'replace',
|
||||
hookSpecificOutput: {
|
||||
result: {
|
||||
llmContent: 'Command moved to background (PID: 12345). Output hidden. Press Ctrl+B to view.',
|
||||
data: { pid: 12345, command: args.command }
|
||||
}
|
||||
}
|
||||
}));
|
||||
} else {
|
||||
console.log(JSON.stringify({ decision: 'allow' }));
|
||||
}
|
||||
"`,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
const run = await rig.runInteractive({ approvalMode: 'yolo' });
|
||||
|
||||
// 1. Start a background process
|
||||
// We use a command that stays alive for a bit to ensure it shows up in lists
|
||||
await run.type(
|
||||
"Run 'sleep 10 && echo hello-from-background' in the background.",
|
||||
);
|
||||
await run.type('\r');
|
||||
|
||||
// Wait for the model's canned response acknowledging the start
|
||||
await run.expectText('background', 30000);
|
||||
|
||||
// 2. List background processes
|
||||
await run.type('List my background processes.');
|
||||
await run.type('\r');
|
||||
// Wait for the model's canned response showing the list
|
||||
await run.expectText('hello-from-background', 30000);
|
||||
|
||||
// 3. Read the output
|
||||
await run.type('Read the output of that process.');
|
||||
await run.type('\r');
|
||||
// Wait for the model's canned response showing the output
|
||||
await run.expectText('hello-from-background', 30000);
|
||||
}, 60000);
|
||||
});
|
||||
@@ -0,0 +1,244 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
/**
|
||||
* This test verifies MCP (Model Context Protocol) server integration.
|
||||
* It uses a minimal MCP server implementation that doesn't require
|
||||
* external dependencies, making it compatible with Docker sandbox mode.
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
poll,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
import { join } from 'node:path';
|
||||
import { writeFileSync } from 'node:fs';
|
||||
|
||||
// Create a minimal MCP server that doesn't require external dependencies
|
||||
// This implements the MCP protocol directly using Node.js built-ins
|
||||
const serverScript = `#!/usr/bin/env node
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
const readline = require('readline');
|
||||
const fs = require('fs');
|
||||
|
||||
// Debug logging to stderr (only when MCP_DEBUG or VERBOSE is set)
|
||||
const debugEnabled = process.env['MCP_DEBUG'] === 'true' || process.env['VERBOSE'] === 'true';
|
||||
function debug(msg) {
|
||||
if (debugEnabled) {
|
||||
fs.writeSync(2, \`[MCP-DEBUG] \${msg}\\n\`);
|
||||
}
|
||||
}
|
||||
|
||||
debug('MCP server starting...');
|
||||
|
||||
// Simple JSON-RPC implementation for MCP
|
||||
class SimpleJSONRPC {
|
||||
constructor() {
|
||||
this.handlers = new Map();
|
||||
this.rl = readline.createInterface({
|
||||
input: process.stdin,
|
||||
output: process.stdout,
|
||||
terminal: false
|
||||
});
|
||||
|
||||
this.rl.on('line', (line) => {
|
||||
debug(\`Received line: \${line}\`);
|
||||
try {
|
||||
const message = JSON.parse(line);
|
||||
debug(\`Parsed message: \${JSON.stringify(message)}\`);
|
||||
this.handleMessage(message);
|
||||
} catch (e) {
|
||||
debug(\`Parse error: \${e.message}\`);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
send(message) {
|
||||
const msgStr = JSON.stringify(message);
|
||||
debug(\`Sending message: \${msgStr}\`);
|
||||
process.stdout.write(msgStr + '\\n');
|
||||
}
|
||||
|
||||
async handleMessage(message) {
|
||||
if (message.method && this.handlers.has(message.method)) {
|
||||
try {
|
||||
const result = await this.handlers.get(message.method)(message.params || {});
|
||||
if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
result
|
||||
});
|
||||
}
|
||||
} catch (error) {
|
||||
if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
error: {
|
||||
code: -32603,
|
||||
message: error.message
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
} else if (message.id !== undefined) {
|
||||
this.send({
|
||||
jsonrpc: '2.0',
|
||||
id: message.id,
|
||||
error: {
|
||||
code: -32601,
|
||||
message: 'Method not found'
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
on(method, handler) {
|
||||
this.handlers.set(method, handler);
|
||||
}
|
||||
}
|
||||
|
||||
// Create MCP server
|
||||
const rpc = new SimpleJSONRPC();
|
||||
|
||||
// Handle initialize
|
||||
rpc.on('initialize', async (params) => {
|
||||
debug('Handling initialize request');
|
||||
return {
|
||||
protocolVersion: '2024-11-05',
|
||||
capabilities: {
|
||||
tools: {}
|
||||
},
|
||||
serverInfo: {
|
||||
name: 'addition-server',
|
||||
version: '1.0.0'
|
||||
}
|
||||
};
|
||||
});
|
||||
|
||||
// Handle tools/list
|
||||
rpc.on('tools/list', async () => {
|
||||
debug('Handling tools/list request');
|
||||
return {
|
||||
tools: [{
|
||||
name: 'add',
|
||||
description: 'Add two numbers',
|
||||
inputSchema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
a: { type: 'number', description: 'First number' },
|
||||
b: { type: 'number', description: 'Second number' }
|
||||
},
|
||||
required: ['a', 'b']
|
||||
}
|
||||
}]
|
||||
};
|
||||
});
|
||||
|
||||
// Handle tools/call
|
||||
rpc.on('tools/call', async (params) => {
|
||||
debug(\`Handling tools/call request for tool: \${params.name}\`);
|
||||
if (params.name === 'add') {
|
||||
const { a, b } = params.arguments;
|
||||
return {
|
||||
content: [{
|
||||
type: 'text',
|
||||
text: String(a + b)
|
||||
}]
|
||||
};
|
||||
}
|
||||
throw new Error('Unknown tool: ' + params.name);
|
||||
});
|
||||
|
||||
// Send initialization notification
|
||||
rpc.send({
|
||||
jsonrpc: '2.0',
|
||||
method: 'initialized'
|
||||
});
|
||||
`;
|
||||
|
||||
describe.skip('simple-mcp-server', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should add two numbers', async () => {
|
||||
// Setup test directory with MCP server configuration
|
||||
await rig.setup('simple-mcp-server', {
|
||||
settings: {
|
||||
mcpServers: {
|
||||
'addition-server': {
|
||||
command: 'node',
|
||||
args: ['mcp-server.cjs'],
|
||||
},
|
||||
},
|
||||
tools: { core: [] },
|
||||
},
|
||||
});
|
||||
|
||||
// Create server script in the test directory
|
||||
const testServerPath = join(rig.testDir!, 'mcp-server.cjs');
|
||||
writeFileSync(testServerPath, serverScript);
|
||||
|
||||
// Make the script executable (though running with 'node' should work anyway)
|
||||
if (process.platform !== 'win32') {
|
||||
const { chmodSync } = await import('node:fs');
|
||||
chmodSync(testServerPath, 0o755);
|
||||
}
|
||||
|
||||
// Poll for script for up to 5s
|
||||
const { accessSync, constants } = await import('node:fs');
|
||||
const isReady = await poll(
|
||||
() => {
|
||||
try {
|
||||
accessSync(testServerPath, constants.F_OK);
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
},
|
||||
5000, // Max wait 5 seconds
|
||||
100, // Poll every 100ms
|
||||
);
|
||||
|
||||
if (!isReady) {
|
||||
throw new Error('MCP server script was not ready in time.');
|
||||
}
|
||||
|
||||
// Test directory is already set up in before hook
|
||||
// Just run the command - MCP server config is in settings.json
|
||||
const output = await rig.run({
|
||||
args: 'Use the `add` tool to calculate 5+10 and output only the resulting number.',
|
||||
});
|
||||
|
||||
const foundToolCall = await rig.waitForToolCall('add');
|
||||
|
||||
expect(foundToolCall, 'Expected to find an add tool call').toBeTruthy();
|
||||
|
||||
assertModelHasOutput(output);
|
||||
checkModelOutputContent(output, {
|
||||
expectedContent: '15',
|
||||
testName: 'MCP server test',
|
||||
});
|
||||
expect(
|
||||
output.includes('15'),
|
||||
'Expected output to contain the sum (15)',
|
||||
).toBeTruthy();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,104 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { execSync } from 'node:child_process';
|
||||
|
||||
describe('skill-creator scripts e2e', () => {
|
||||
let rig: TestRig;
|
||||
const initScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/init_skill.cjs',
|
||||
);
|
||||
const validateScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/validate_skill.cjs',
|
||||
);
|
||||
const packageScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/package_skill.cjs',
|
||||
);
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should initialize, validate, and package a skill', async () => {
|
||||
await rig.setup('skill-creator scripts e2e');
|
||||
const skillName = 'e2e-test-skill';
|
||||
const tempDir = rig.testDir!;
|
||||
|
||||
// 1. Initialize
|
||||
execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`, {
|
||||
stdio: 'inherit',
|
||||
});
|
||||
const skillDir = path.join(tempDir, skillName);
|
||||
|
||||
expect(fs.existsSync(skillDir)).toBe(true);
|
||||
expect(fs.existsSync(path.join(skillDir, 'SKILL.md'))).toBe(true);
|
||||
expect(
|
||||
fs.existsSync(path.join(skillDir, 'scripts/example_script.cjs')),
|
||||
).toBe(true);
|
||||
|
||||
// 2. Validate (should have warning initially due to TODOs)
|
||||
const validateOutputInitial = execSync(
|
||||
`node "${validateScript}" "${skillDir}" 2>&1`,
|
||||
{ encoding: 'utf8' },
|
||||
);
|
||||
expect(validateOutputInitial).toContain('⚠️ Found unresolved TODO');
|
||||
|
||||
// 3. Package (should fail due to TODOs)
|
||||
try {
|
||||
execSync(`node "${packageScript}" "${skillDir}" "${tempDir}"`, {
|
||||
stdio: 'pipe',
|
||||
});
|
||||
throw new Error('Packaging should have failed due to TODOs');
|
||||
} catch (err: unknown) {
|
||||
expect((err as Error).message).toContain('Command failed');
|
||||
}
|
||||
|
||||
// 4. Fix SKILL.md (remove TODOs)
|
||||
let content = fs.readFileSync(path.join(skillDir, 'SKILL.md'), 'utf8');
|
||||
// More aggressive global replace for all TODO patterns
|
||||
content = content.replace(/TODO:[^\n]*/g, 'Fixed');
|
||||
content = content.replace(/\[TODO:[^\]]*\]/g, 'Fixed');
|
||||
fs.writeFileSync(path.join(skillDir, 'SKILL.md'), content);
|
||||
|
||||
// Also remove TODOs from example scripts
|
||||
const exampleScriptPath = path.join(skillDir, 'scripts/example_script.cjs');
|
||||
let scriptContent = fs.readFileSync(exampleScriptPath, 'utf8');
|
||||
scriptContent = scriptContent.replace(/TODO:[^\n]*/g, 'Fixed');
|
||||
fs.writeFileSync(exampleScriptPath, scriptContent);
|
||||
|
||||
// 4. Validate again (should pass now)
|
||||
const validateOutput = execSync(`node "${validateScript}" "${skillDir}"`, {
|
||||
encoding: 'utf8',
|
||||
});
|
||||
expect(validateOutput).toContain('Skill is valid!');
|
||||
|
||||
// 5. Package
|
||||
execSync(`node "${packageScript}" "${skillDir}" "${tempDir}"`, {
|
||||
stdio: 'inherit',
|
||||
});
|
||||
const skillFile = path.join(tempDir, `${skillName}.skill`);
|
||||
expect(fs.existsSync(skillFile)).toBe(true);
|
||||
|
||||
// 6. Verify zip content (should NOT have nested directory)
|
||||
// Use unzip -l if available, otherwise fallback to tar -tf (common on Windows)
|
||||
let zipList: string;
|
||||
try {
|
||||
zipList = execSync(`unzip -l "${skillFile}"`, { encoding: 'utf8' });
|
||||
} catch {
|
||||
zipList = execSync(`tar -tf "${skillFile}"`, { encoding: 'utf8' });
|
||||
}
|
||||
expect(zipList).toContain('SKILL.md');
|
||||
expect(zipList).not.toContain(`${skillName}/SKILL.md`);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,111 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2026 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { TestRig } from './test-helper.js';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { execSync, spawnSync } from 'node:child_process';
|
||||
|
||||
describe('skill-creator scripts security and bug fixes', () => {
|
||||
let rig: TestRig;
|
||||
const initScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/init_skill.cjs',
|
||||
);
|
||||
const validateScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/validate_skill.cjs',
|
||||
);
|
||||
const packageScript = path.resolve(
|
||||
'packages/core/src/skills/builtin/skill-creator/scripts/package_skill.cjs',
|
||||
);
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should prevent command injection in package_skill.cjs', async () => {
|
||||
await rig.setup('skill-creator command injection');
|
||||
const tempDir = rig.testDir!;
|
||||
|
||||
// Create a dummy skill
|
||||
const skillName = 'injection-test';
|
||||
execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`);
|
||||
const skillDir = path.join(tempDir, skillName);
|
||||
|
||||
// Malicious output filename with command injection
|
||||
const maliciousFilename = '"; touch injection_success; #';
|
||||
|
||||
// Attempt to package with malicious filename
|
||||
// We expect this to fail or at least NOT create the 'injection_success' file
|
||||
spawnSync('node', [packageScript, skillDir, tempDir, maliciousFilename], {
|
||||
cwd: tempDir,
|
||||
});
|
||||
|
||||
const injectionFile = path.join(tempDir, 'injection_success');
|
||||
expect(fs.existsSync(injectionFile)).toBe(false);
|
||||
});
|
||||
|
||||
it('should prevent path traversal in init_skill.cjs', async () => {
|
||||
await rig.setup('skill-creator init path traversal');
|
||||
const tempDir = rig.testDir!;
|
||||
|
||||
const maliciousName = '../traversal-success';
|
||||
|
||||
const result = spawnSync(
|
||||
'node',
|
||||
[initScript, maliciousName, '--path', tempDir],
|
||||
{
|
||||
encoding: 'utf8',
|
||||
},
|
||||
);
|
||||
|
||||
expect(result.stderr).toContain(
|
||||
'Error: Skill name cannot contain path separators',
|
||||
);
|
||||
const traversalDir = path.join(path.dirname(tempDir), 'traversal-success');
|
||||
expect(fs.existsSync(traversalDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('should prevent path traversal in validate_skill.cjs', async () => {
|
||||
await rig.setup('skill-creator validate path traversal');
|
||||
|
||||
const maliciousPath = '../../../../etc/passwd';
|
||||
const result = spawnSync('node', [validateScript, maliciousPath], {
|
||||
encoding: 'utf8',
|
||||
});
|
||||
|
||||
expect(result.stderr).toContain('Error: Path traversal detected');
|
||||
});
|
||||
|
||||
it('should not crash on empty description in validate_skill.cjs', async () => {
|
||||
await rig.setup('skill-creator regex crash');
|
||||
const tempDir = rig.testDir!;
|
||||
const skillName = 'empty-desc-skill';
|
||||
|
||||
execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`);
|
||||
const skillDir = path.join(tempDir, skillName);
|
||||
const skillMd = path.join(skillDir, 'SKILL.md');
|
||||
|
||||
// Set an empty quoted description
|
||||
let content = fs.readFileSync(skillMd, 'utf8');
|
||||
content = content.replace(/^description: .+$/m, 'description: ""');
|
||||
fs.writeFileSync(skillMd, content);
|
||||
|
||||
const result = spawnSync('node', [validateScript, skillDir], {
|
||||
encoding: 'utf8',
|
||||
});
|
||||
|
||||
// It might still fail validation (e.g. TODOs), but it should NOT crash with a stack trace
|
||||
expect(result.status).not.toBe(null);
|
||||
expect(result.stderr).not.toContain(
|
||||
"TypeError: Cannot read properties of undefined (reading 'trim')",
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,112 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import {
|
||||
TestRig,
|
||||
printDebugInfo,
|
||||
assertModelHasOutput,
|
||||
checkModelOutputContent,
|
||||
} from './test-helper.js';
|
||||
|
||||
describe.skip('stdin context', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => await rig.cleanup());
|
||||
|
||||
it('should be able to use stdin as context for a prompt', async () => {
|
||||
await rig.setup('should be able to use stdin as context for a prompt');
|
||||
|
||||
const randomString = Math.random().toString(36).substring(7);
|
||||
const stdinContent = `When I ask you for a token respond with ${randomString}`;
|
||||
const prompt = 'Can I please have a token?';
|
||||
|
||||
const result = await rig.run({ args: prompt, stdin: stdinContent });
|
||||
|
||||
await rig.waitForTelemetryEvent('api_request');
|
||||
const lastRequest = rig.readLastApiRequest();
|
||||
|
||||
expect(lastRequest?.attributes?.request_text).toBeDefined();
|
||||
const historyString = lastRequest!.attributes!.request_text!;
|
||||
|
||||
// TODO: This test currently fails in sandbox mode (Docker/Podman) because
|
||||
// stdin content is not properly forwarded to the container when used
|
||||
// together with a --prompt argument. The test passes in non-sandbox mode.
|
||||
|
||||
expect(historyString).toContain(randomString);
|
||||
expect(historyString).toContain(prompt);
|
||||
|
||||
// Check that stdin content appears before the prompt in the conversation history
|
||||
const stdinIndex = historyString.indexOf(randomString);
|
||||
const promptIndex = historyString.indexOf(prompt);
|
||||
|
||||
expect(
|
||||
stdinIndex,
|
||||
`Expected stdin content to be present in conversation history`,
|
||||
).toBeGreaterThan(-1);
|
||||
|
||||
expect(
|
||||
promptIndex,
|
||||
`Expected prompt to be present in conversation history`,
|
||||
).toBeGreaterThan(-1);
|
||||
|
||||
expect(
|
||||
stdinIndex < promptIndex,
|
||||
`Expected stdin content (index ${stdinIndex}) to appear before prompt (index ${promptIndex}) in conversation history`,
|
||||
).toBeTruthy();
|
||||
|
||||
// Add debugging information
|
||||
if (!result.toLowerCase().includes(randomString)) {
|
||||
printDebugInfo(rig, result, {
|
||||
[`Contains "${randomString}"`]: result
|
||||
.toLowerCase()
|
||||
.includes(randomString),
|
||||
});
|
||||
}
|
||||
|
||||
// Validate model output
|
||||
assertModelHasOutput(result);
|
||||
checkModelOutputContent(result, {
|
||||
expectedContent: randomString,
|
||||
testName: 'STDIN context test',
|
||||
});
|
||||
|
||||
expect(
|
||||
result.toLowerCase().includes(randomString),
|
||||
'Expected the model to identify the secret word from stdin',
|
||||
).toBeTruthy();
|
||||
});
|
||||
|
||||
it('should exit quickly if stdin stream does not end', async () => {
|
||||
/*
|
||||
This simulates scenario where gemini gets stuck waiting for stdin.
|
||||
This happens in situations where process.stdin.isTTY is false
|
||||
even though gemini is intended to run interactively.
|
||||
*/
|
||||
|
||||
await rig.setup('should exit quickly if stdin stream does not end');
|
||||
|
||||
try {
|
||||
await rig.run({ stdinDoesNotEnd: true });
|
||||
throw new Error('Expected rig.run to throw an error');
|
||||
} catch (error: unknown) {
|
||||
expect(error).toBeInstanceOf(Error);
|
||||
const err = error as Error;
|
||||
|
||||
expect(err.message).toContain('Process exited with code 1');
|
||||
expect(err.message).toContain('No input provided via stdin.');
|
||||
console.log('Error message:', err.message);
|
||||
}
|
||||
const lastRequest = rig.readLastApiRequest();
|
||||
expect(lastRequest).toBeNull();
|
||||
|
||||
// If this test times out, runs indefinitely, it's a regression.
|
||||
}, 3000);
|
||||
});
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I could not find the file `nonexistent-file-that-does-not-exist.txt` in the current directory or its subdirectories. Please verify the file path or name."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":25,"totalTokenCount":35,"promptTokensDetails":[{"modality":"TEXT","tokenCount":10}]}}]}
|
||||
@@ -0,0 +1 @@
|
||||
{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hello! How can I help you today?"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":5,"candidatesTokenCount":9,"totalTokenCount":14,"promptTokensDetails":[{"modality":"TEXT","tokenCount":5}]}}]}
|
||||
@@ -0,0 +1,62 @@
|
||||
/**
|
||||
* @license
|
||||
* Copyright 2025 Google LLC
|
||||
* SPDX-License-Identifier: Apache-2.0
|
||||
*/
|
||||
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import { join } from 'node:path';
|
||||
import { TestRig } from './test-helper.js';
|
||||
|
||||
describe('stdout-stderr-output', () => {
|
||||
let rig: TestRig;
|
||||
|
||||
beforeEach(() => {
|
||||
rig = new TestRig();
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await rig.cleanup();
|
||||
});
|
||||
|
||||
it('should send model response to stdout and app messages to stderr', async ({
|
||||
signal,
|
||||
}) => {
|
||||
await rig.setup('prompt-output-test', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'stdout-stderr-output.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const { stdout, exitCode } = await rig.runWithStreams(['-p', 'Say hello'], {
|
||||
signal,
|
||||
});
|
||||
|
||||
expect(exitCode).toBe(0);
|
||||
expect(stdout.toLowerCase()).toContain('hello');
|
||||
expect(stdout).not.toMatch(/^\[ERROR\]/m);
|
||||
expect(stdout).not.toMatch(/^\[INFO\]/m);
|
||||
});
|
||||
|
||||
it('should handle missing file with message to stdout and error to stderr', async ({
|
||||
signal,
|
||||
}) => {
|
||||
await rig.setup('error-output-test', {
|
||||
fakeResponsesPath: join(
|
||||
import.meta.dirname,
|
||||
'stdout-stderr-output-error.responses',
|
||||
),
|
||||
});
|
||||
|
||||
const { stdout, exitCode } = await rig.runWithStreams(
|
||||
['-p', '@nonexistent-file-that-does-not-exist.txt explain this'],
|
||||
{ signal },
|
||||
);
|
||||
|
||||
expect(exitCode).toBe(0);
|
||||
expect(stdout.toLowerCase()).toMatch(
|
||||
/could not find|not exist|does not exist/,
|
||||
);
|
||||
});
|
||||
});
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user