Repository navigation
Expand file tree
/
Copy pathtest-helper.ts
More file actions
208 lines (186 loc) · 7.27 KB
/
Copy pathtest-helper.ts
File metadata and controls
208 lines (186 loc) · 7.27 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
/**
* @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,
} from '@google/gemini-cli-core';
export * from '@google/gemini-cli-test-utils';
// 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';
export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
const fn = 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 {
rig.setup(evalCase.name, evalCase.params);
// Symlink node modules to reduce the amount of time needed to
// bootstrap test projects.
symlinkNodeModules(rig.testDir || '');
if (evalCase.files) {
const acknowledgedAgents: Record<string, Record<string, string>> = {};
const projectRoot = fs.realpathSync(rig.testDir!);
for (const [filePath, content] of Object.entries(evalCase.files)) {
const fullPath = path.join(rig.testDir!, filePath);
fs.mkdirSync(path.dirname(fullPath), { recursive: true });
fs.writeFileSync(fullPath, content);
// If it's an agent file, calculate hash for acknowledgement
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: ${filePath}`,
error,
);
}
}
}
// Write acknowledged_agents.json to the home directory
if (Object.keys(acknowledgedAgents).length > 0) {
const ackPath = path.join(
rig.homeDir!,
'.gemini',
'acknowledgments',
'agents.json',
);
fs.mkdirSync(path.dirname(ackPath), { recursive: true });
fs.writeFileSync(
ackPath,
JSON.stringify(acknowledgedAgents, null, 2),
);
}
const execOptions = { cwd: rig.testDir!, stdio: 'inherit' as const };
execSync('git init', execOptions);
execSync('git config user.email "test@example.com"', execOptions);
execSync('git config user.name "Test User"', execOptions);
// Temporarily disable the interactive editor and git pager
// to avoid hanging the tests. It seems the the agent isn't
// consistently honoring the instructions to avoid interactive
// commands.
execSync('git config core.editor "true"', execOptions);
execSync('git config core.pager "cat"', execOptions);
execSync('git config commit.gpgsign false', execOptions);
execSync('git add .', execOptions);
execSync('git commit --allow-empty -m "Initial commit"', execOptions);
}
const result = await rig.run({
args: evalCase.prompt,
approvalMode: evalCase.approvalMode ?? 'yolo',
timeout: evalCase.timeout,
env: {
GEMINI_CLI_ACTIVITY_LOG_TARGET: activityLogFile,
},
});
const unauthorizedErrorPrefix =
createUnauthorizedToolError('').split("'")[0];
if (result.includes(unauthorizedErrorPrefix)) {
throw new Error(
'Test failed due to unauthorized tool call in output: ' + result,
);
}
await evalCase.assert(rig, result);
isSuccess = true;
} finally {
if (isSuccess) {
await fs.promises.unlink(activityLogFile).catch((err) => {
if (err.code !== 'ENOENT') throw err;
});
}
if (rig._lastRunStderr) {
const stderrFile = path.join(logDir, `${sanitizedName}.stderr.log`);
await fs.promises.writeFile(stderrFile, rig._lastRunStderr);
}
await fs.promises.writeFile(
logFile,
JSON.stringify(rig.readToolLogs(), null, 2),
);
await rig.cleanup();
}
};
runEval(policy, evalCase.name, fn, evalCase.timeout);
}
/**
* Wraps a test function with the appropriate Vitest 'it' or 'it.skip' based on policy.
*/
export function runEval(
policy: EvalPolicy,
name: string,
fn: () => Promise<void>,
timeout?: number,
) {
if (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) {
it.skip(name, fn);
} else {
it(name, fn, timeout);
}
}
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');
}
}
export interface EvalCase {
name: string;
params?: Record<string, any>;
prompt: string;
timeout?: number;
files?: Record<string, string>;
approvalMode?: 'default' | 'auto_edit' | 'yolo' | 'plan';
assert: (rig: TestRig, result: string) => Promise<void>;
}