File size: 4,296 Bytes
739fc44 | 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 | /**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { describe, expect } from 'vitest';
import { TRACKER_CREATE_TASK_TOOL_NAME } from '@google/gemini-cli-core';
import { evalTest, TEST_AGENTS } from './test-helper.js';
describe('subtask delegation eval test cases', () => {
/**
* Checks that the main agent can correctly decompose a complex, sequential
* task into subtasks using the task tracker and delegate each to the appropriate expert subagent.
*
* The task requires:
* 1. Reading requirements (researcher)
* 2. Implementing logic (developer)
* 3. Documenting (doc expert)
*/
evalTest('USUALLY_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: 'should delegate sequential subtasks to relevant experts using the task tracker',
params: {
settings: {
experimental: {
enableAgents: true,
taskTracker: true,
},
},
},
prompt:
'Please read the requirements in requirements.txt using a researcher, then implement the requested logic in src/logic.ts using a developer, and finally document the implementation in docs/logic.md using a documentation expert.',
files: {
'.gemini/agents/researcher.md': `---
name: researcher
description: Expert in reading files and extracting requirements.
tools:
- read_file
---
You are the researcher. Read the provided file and extract requirements.`,
'.gemini/agents/developer.md': `---
name: developer
description: Expert in implementing logic in TypeScript.
tools:
- write_file
---
You are the developer. Implement the requested logic in the specified file.`,
'.gemini/agents/doc-expert.md': `---
name: doc-expert
description: Expert in writing technical documentation.
tools:
- write_file
---
You are the doc expert. Document the provided implementation clearly.`,
'requirements.txt':
'Implement a function named "calculateSum" that adds two numbers.',
},
assert: async (rig, _result) => {
// Verify tracker tasks were created
const wasCreateCalled = await rig.waitForToolCall(
TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(wasCreateCalled).toBe(true);
const toolLogs = rig.readToolLogs();
const createCalls = toolLogs.filter(
(l) => l.toolRequest.name === TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(createCalls.length).toBeGreaterThanOrEqual(3);
await rig.expectToolCallSuccess([
'researcher',
'developer',
'doc-expert',
]);
const logicFile = rig.readFile('src/logic.ts');
const docFile = rig.readFile('docs/logic.md');
expect(logicFile).toContain('calculateSum');
expect(docFile).toBeTruthy();
},
});
/**
* Checks that the main agent can delegate a batch of independent subtasks
* to multiple subagents in parallel using the task tracker to manage state.
*/
evalTest('USUALLY_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: 'should delegate independent subtasks to specialists using the task tracker',
params: {
settings: {
experimental: {
enableAgents: true,
taskTracker: true,
},
},
},
prompt:
'Please update the project for internationalization (i18n), audit the security of the current code, and update the CSS to use a blue theme. Use specialized experts for each task.',
files: {
...TEST_AGENTS.I18N_AGENT.asFile(),
...TEST_AGENTS.SECURITY_AGENT.asFile(),
...TEST_AGENTS.CSS_AGENT.asFile(),
'index.ts': 'console.log("Hello World");',
},
assert: async (rig, _result) => {
// Verify tracker tasks were created
const wasCreateCalled = await rig.waitForToolCall(
TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(wasCreateCalled).toBe(true);
const toolLogs = rig.readToolLogs();
const createCalls = toolLogs.filter(
(l) => l.toolRequest.name === TRACKER_CREATE_TASK_TOOL_NAME,
);
expect(createCalls.length).toBeGreaterThanOrEqual(3);
await rig.expectToolCallSuccess([
TEST_AGENTS.I18N_AGENT.name,
TEST_AGENTS.SECURITY_AGENT.name,
TEST_AGENTS.CSS_AGENT.name,
]);
},
});
});
|