Repository navigation
Expand file tree
/
Copy pathtest-helper.ts
More file actions
430 lines (385 loc) · 13.9 KB
/
Copy pathtest-helper.ts
File metadata and controls
430 lines (385 loc) · 13.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
/**
* @license
* Copyright 2025 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { it } from 'vitest';
import fs from 'node:fs';
import path from 'node:path';
import crypto from 'node:crypto';
import { execSync } from 'node:child_process';
import { TestRig } from '@google/gemini-cli-test-utils';
import {
createUnauthorizedToolError,
parseAgentMarkdown,
Storage,
getProjectHash,
SESSION_FILE_PREFIX,
PREVIEW_GEMINI_FLASH_MODEL,
getErrorMessage,
} from '@google/gemini-cli-core';
export * from '@google/gemini-cli-test-utils';
/**
* The default model used for all evaluations.
* Can be overridden by setting the GEMINI_MODEL environment variable.
*/
export const EVAL_MODEL =
process.env['GEMINI_MODEL'] || PREVIEW_GEMINI_FLASH_MODEL;
// Indicates the consistency expectation for this test.
// - ALWAYS_PASSES - Means that the test is expected to pass 100% of the time. These
// These tests are typically trivial and test basic functionality with unambiguous
// prompts. For example: "call save_memory to remember foo" should be fairly reliable.
// These are the first line of defense against regressions in key behaviors and run in
// every CI. You can run these locally with 'npm run test:always_passing_evals'.
//
// - USUALLY_PASSES - Means that the test is expected to pass most of the time but
// may have some flakiness as a result of relying on non-deterministic prompted
// behaviors and/or ambiguous prompts or complex tasks.
// For example: "Please do build changes until the very end" --> ambiguous whether
// the agent should add to memory without more explicit system prompt or user
// instructions. There are many more of these tests and they may pass less consistently.
// The pass/fail trendline of this set of tests can be used as a general measure
// of product quality. You can run these locally with 'npm run test:all_evals'.
// This may take a really long time and is not recommended.
export type EvalPolicy = 'ALWAYS_PASSES' | 'USUALLY_PASSES' | 'USUALLY_FAILS';
export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
runEval(policy, evalCase, () => internalEvalTest(evalCase));
}
export async function withEvalRetries(
name: string,
attemptFn: (attempt: number) => Promise<void>,
) {
const maxRetries = 3;
let attempt = 0;
while (attempt <= maxRetries) {
try {
await attemptFn(attempt);
return; // Success! Exit the retry loop.
} catch (error: unknown) {
const errorMessage = getErrorMessage(error);
const errorCode = getApiErrorCode(errorMessage);
if (errorCode) {
const status = attempt < maxRetries ? 'RETRY' : 'SKIP';
logReliabilityEvent(name, attempt, status, errorCode, errorMessage);
if (attempt < maxRetries) {
attempt++;
console.warn(
`[Eval] Attempt ${attempt} failed with ${errorCode} Error. Retrying...`,
);
continue; // Retry
}
console.warn(
`[Eval] '${name}' failed after ${maxRetries} retries due to persistent API errors. Skipping failure to avoid blocking PR.`,
);
return; // Gracefully exit without failing the test
}
throw error; // Real failure
}
}
}
export async function internalEvalTest(evalCase: EvalCase) {
await withEvalRetries(evalCase.name, async () => {
const rig = new TestRig();
const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
const activityLogFile = path.join(logDir, `${sanitizedName}.jsonl`);
const logFile = path.join(logDir, `${sanitizedName}.log`);
let isSuccess = false;
try {
const setupOptions = {
...evalCase.params,
settings: {
model: { name: EVAL_MODEL },
...evalCase.params?.settings,
},
};
rig.setup(evalCase.name, setupOptions);
if (evalCase.setup) {
await evalCase.setup(rig);
}
if (evalCase.files) {
await prepareWorkspace(rig.testDir!, rig.homeDir!, evalCase.files);
}
symlinkNodeModules(rig.testDir || '');
// If messages are provided, write a session file so --resume can load it.
let sessionId: string | undefined;
if (evalCase.messages) {
sessionId =
evalCase.sessionId ||
`test-session-${crypto.randomUUID().slice(0, 8)}`;
// Temporarily set GEMINI_CLI_HOME so Storage writes to the same
// directory the CLI subprocess will use (rig.homeDir).
const originalGeminiHome = process.env['GEMINI_CLI_HOME'];
process.env['GEMINI_CLI_HOME'] = rig.homeDir!;
try {
const storage = new Storage(fs.realpathSync(rig.testDir!));
await storage.initialize();
const chatsDir = path.join(storage.getProjectTempDir(), 'chats');
fs.mkdirSync(chatsDir, { recursive: true });
const conversation = {
sessionId,
projectHash: getProjectHash(fs.realpathSync(rig.testDir!)),
startTime: new Date().toISOString(),
lastUpdated: new Date().toISOString(),
messages: evalCase.messages,
};
const timestamp = new Date()
.toISOString()
.slice(0, 16)
.replace(/:/g, '-');
const filename = `${SESSION_FILE_PREFIX}${timestamp}-${sessionId.slice(0, 8)}.json`;
fs.writeFileSync(
path.join(chatsDir, filename),
JSON.stringify(conversation, null, 2),
);
} catch (e) {
// Storage initialization may fail in some environments; log and continue.
console.warn('Failed to write session history:', e);
} finally {
// Restore original GEMINI_CLI_HOME.
if (originalGeminiHome === undefined) {
delete process.env['GEMINI_CLI_HOME'];
} else {
process.env['GEMINI_CLI_HOME'] = originalGeminiHome;
}
}
}
const result = await rig.run({
args: sessionId
? ['--resume', sessionId, evalCase.prompt]
: evalCase.prompt,
approvalMode: evalCase.approvalMode ?? 'yolo',
timeout: evalCase.timeout,
env: {
GEMINI_CLI_ACTIVITY_LOG_TARGET: activityLogFile,
GEMINI_CLI_TRUST_WORKSPACE: 'true',
},
});
const unauthorizedErrorPrefix =
createUnauthorizedToolError('').split("'")[0];
if (result.includes(unauthorizedErrorPrefix)) {
throw new Error(
'Test failed due to unauthorized tool call in output: ' + result,
);
}
await evalCase.assert(rig, result);
isSuccess = true;
} finally {
if (isSuccess) {
await fs.promises.unlink(activityLogFile).catch((err) => {
if (err.code !== 'ENOENT') throw err;
});
}
if (rig._lastRunStderr) {
const stderrFile = path.join(logDir, `${sanitizedName}.stderr.log`);
await fs.promises.writeFile(stderrFile, rig._lastRunStderr);
}
await fs.promises.writeFile(
logFile,
JSON.stringify(rig.readToolLogs(), null, 2),
);
await rig.cleanup();
}
});
}
function getApiErrorCode(message: string): '500' | '503' | undefined {
if (
message.includes('status: UNAVAILABLE') ||
message.includes('code: 503') ||
message.includes('Service Unavailable')
) {
return '503';
}
if (
message.includes('status: INTERNAL') ||
message.includes('code: 500') ||
message.includes('Internal error encountered')
) {
return '500';
}
return undefined;
}
/**
* Log reliability event for later harvesting.
*
* Note: Uses synchronous file I/O to ensure the log is persisted even if the
* test process is abruptly terminated by a timeout or CI crash. Performance
* impact is negligible compared to long-running evaluation tests.
*/
function logReliabilityEvent(
testName: string,
attempt: number,
status: 'RETRY' | 'SKIP',
errorCode: '500' | '503',
errorMessage: string,
) {
const reliabilityLog = {
timestamp: new Date().toISOString(),
testName,
model: process.env['GEMINI_MODEL'] || 'unknown',
attempt,
status,
errorCode,
error: errorMessage,
};
try {
const relDir = path.resolve(process.cwd(), 'evals/logs');
fs.mkdirSync(relDir, { recursive: true });
fs.appendFileSync(
path.join(relDir, 'api-reliability.jsonl'),
JSON.stringify(reliabilityLog) + '\n',
);
} catch (logError) {
console.error('Failed to write reliability log:', logError);
}
}
/**
* Helper to setup test files and git repository.
*
* Note: While this is an async function (due to parseAgentMarkdown), it
* intentionally uses synchronous filesystem and child_process operations
* for simplicity and to ensure sequential environment preparation.
*/
export async function prepareWorkspace(
testDir: string,
homeDir: string,
files: Record<string, string>,
) {
const acknowledgedAgents: Record<string, Record<string, string>> = {};
const projectRoot = fs.realpathSync(testDir);
for (const [filePath, content] of Object.entries(files)) {
if (filePath.includes('..') || path.isAbsolute(filePath)) {
throw new Error(`Invalid file path in test case: ${filePath}`);
}
const fullPath = path.join(projectRoot, filePath);
if (!fullPath.startsWith(projectRoot)) {
throw new Error(`Path traversal detected: ${filePath}`);
}
fs.mkdirSync(path.dirname(fullPath), { recursive: true });
fs.writeFileSync(fullPath, content);
if (filePath.startsWith('.gemini/agents/') && filePath.endsWith('.md')) {
const hash = crypto.createHash('sha256').update(content).digest('hex');
try {
const agentDefs = await parseAgentMarkdown(fullPath, content);
if (agentDefs.length > 0) {
const agentName = agentDefs[0].name;
if (!acknowledgedAgents[projectRoot]) {
acknowledgedAgents[projectRoot] = {};
}
acknowledgedAgents[projectRoot][agentName] = hash;
}
} catch (error) {
console.warn(
`Failed to parse agent for test acknowledgement: ${filePath}`,
error,
);
}
}
}
if (Object.keys(acknowledgedAgents).length > 0) {
const ackPath = path.join(
homeDir,
'.gemini',
'acknowledgments',
'agents.json',
);
fs.mkdirSync(path.dirname(ackPath), { recursive: true });
fs.writeFileSync(ackPath, JSON.stringify(acknowledgedAgents, null, 2));
}
const execOptions = { cwd: testDir, stdio: 'ignore' as const };
execSync('git init --initial-branch=main', execOptions);
execSync('git config user.email "test@example.com"', execOptions);
execSync('git config user.name "Test User"', execOptions);
// Temporarily disable the interactive editor and git pager
// to avoid hanging the tests. It seems the the agent isn't
// consistently honoring the instructions to avoid interactive
// commands.
execSync('git config core.editor "true"', execOptions);
execSync('git config core.pager "cat"', execOptions);
execSync('git config commit.gpgsign false', execOptions);
execSync('git add .', execOptions);
execSync('git commit --allow-empty -m "Initial commit"', execOptions);
}
/**
* Wraps a test function with the appropriate Vitest 'it' or 'it.skip' based on policy.
*/
export function runEval(
policy: EvalPolicy,
evalCase: BaseEvalCase,
fn: () => Promise<void>,
timeoutOverride?: number,
) {
const { name, timeout, suiteName, suiteType } = evalCase;
const targetSuiteType = process.env['EVAL_SUITE_TYPE'];
const targetSuiteName = process.env['EVAL_SUITE_NAME'];
const meta = { suiteType, suiteName };
const skipBySuiteType =
targetSuiteType && suiteType && suiteType !== targetSuiteType;
const skipBySuiteName =
targetSuiteName && suiteName && suiteName !== targetSuiteName;
const options = { timeout: timeoutOverride ?? timeout, meta };
if (skipBySuiteType || skipBySuiteName) {
it.skip(name, options, fn);
} else if (
!process.env['RUN_EVALS'] &&
(policy === 'USUALLY_PASSES' || policy === 'USUALLY_FAILS')
) {
it.skip(name, options, fn);
} else if (policy === 'USUALLY_FAILS') {
it.fails(name, options, fn);
} else {
it(name, options, fn);
}
}
export async function prepareLogDir(name: string) {
const logDir = path.resolve(process.cwd(), 'evals/logs');
await fs.promises.mkdir(logDir, { recursive: true });
const sanitizedName = name.replace(/[^a-z0-9]/gi, '_').toLowerCase();
return { logDir, sanitizedName };
}
/**
* Symlinks node_modules to the test directory to speed up tests that need to run tools.
*/
export function symlinkNodeModules(testDir: string) {
const rootNodeModules = path.join(process.cwd(), 'node_modules');
const testNodeModules = path.join(testDir, 'node_modules');
if (
testDir &&
fs.existsSync(rootNodeModules) &&
!fs.existsSync(testNodeModules)
) {
fs.symlinkSync(rootNodeModules, testNodeModules, 'dir');
}
}
/**
* Settings that are forbidden in evals. Evals should never restrict which
* tools are available — they must test against the full, default tool set
* to ensure realistic behavior.
*/
interface ForbiddenToolSettings {
tools?: {
/** Restricting core tools in evals is forbidden. */
core?: never;
[key: string]: unknown;
};
}
export interface BaseEvalCase {
suiteName: string;
suiteType: 'behavioral' | 'component-level' | 'hero-scenario';
name: string;
timeout?: number;
files?: Record<string, string>;
}
export interface EvalCase extends BaseEvalCase {
params?: {
settings?: ForbiddenToolSettings & Record<string, unknown>;
[key: string]: unknown;
};
prompt: string;
setup?: (rig: TestRig) => Promise<void> | void;
/** Conversation history to pre-load via --resume. Each entry is a message object with type, content, etc. */
messages?: Record<string, unknown>[];
/** Session ID for the resumed session. Auto-generated if not provided. */
sessionId?: string;
approvalMode?: 'default' | 'auto_edit' | 'yolo' | 'plan';
assert: (rig: TestRig, result: string) => Promise<void>;
}