Update prompt and grep tool definition to limit context size #18780
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,134 @@ | ||
| /** | ||
| * @license | ||
| * Copyright 2026 Google LLC | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| import { describe, expect } from 'vitest'; | ||
| import { evalTest } from './test-helper.js'; | ||
|
|
||
| describe('Frugal Search', () => { | ||
| const getGrepParams = (call: any): any => { | ||
| let args = call.toolRequest.args; | ||
| if (typeof args === 'string') { | ||
| try { | ||
| args = JSON.parse(args); | ||
| } catch (e) { | ||
| // Ignore parse errors | ||
| } | ||
| } | ||
| return args; | ||
| }; | ||
|
|
||
| evalTest('USUALLY_PASSES', { | ||
| name: 'should use targeted search with limit', | ||
| prompt: 'find me a sample usage of path.resolve() in the codebase', | ||
| files: { | ||
| 'package.json': JSON.stringify({ | ||
| name: 'test-project', | ||
| version: '1.0.0', | ||
| main: 'dist/index.js', | ||
| scripts: { | ||
| build: 'tsc', | ||
| test: 'vitest', | ||
| }, | ||
| dependencies: { | ||
| typescript: '^5.0.0', | ||
| '@types/node': '^20.0.0', | ||
| vitest: '^1.0.0', | ||
| }, | ||
| }), | ||
| 'src/index.ts': ` | ||
| import { App } from './app.ts'; | ||
|
|
||
| const app = new App(); | ||
| app.start(); | ||
| `, | ||
| 'src/app.ts': ` | ||
| import * as path from 'path'; | ||
| import { UserController } from './controllers/user.ts'; | ||
|
|
||
| export class App { | ||
| constructor() { | ||
| console.log('App initialized'); | ||
| } | ||
|
|
||
| public start(): void { | ||
| const userController = new UserController(); | ||
| console.log('Static path:', path.resolve(__dirname, '../public')); | ||
| } | ||
| } | ||
| `, | ||
| 'src/utils.ts': ` | ||
| import * as path from 'path'; | ||
| import * as fs from 'fs'; | ||
|
|
||
| export function resolvePath(p: string): string { | ||
| return path.resolve(process.cwd(), p); | ||
| } | ||
|
|
||
| export function ensureDir(dirPath: string): void { | ||
| const absolutePath = path.resolve(dirPath); | ||
| if (!fs.existsSync(absolutePath)) { | ||
| fs.mkdirSync(absolutePath, { recursive: true }); | ||
| } | ||
| } | ||
| `, | ||
| 'src/config.ts': ` | ||
| import * as path from 'path'; | ||
|
|
||
| export const config = { | ||
| dbPath: path.resolve(process.cwd(), 'data/db.sqlite'), | ||
| logLevel: 'info', | ||
| }; | ||
| `, | ||
| 'src/controllers/user.ts': ` | ||
| import * as path from 'path'; | ||
|
|
||
| export class UserController { | ||
| public getUsers(): any[] { | ||
| console.log('Loading users from:', path.resolve('data/users.json')); | ||
| return [{ id: 1, name: 'Alice' }]; | ||
| } | ||
| } | ||
| `, | ||
| 'tests/app.test.ts': ` | ||
| import { describe, it, expect } from 'vitest'; | ||
| import * as path from 'path'; | ||
|
|
||
| describe('App', () => { | ||
| it('should resolve paths', () => { | ||
| const p = path.resolve('test'); | ||
| expect(p).toBeDefined(); | ||
| }); | ||
| }); | ||
| `, | ||
| }, | ||
| assert: async (rig) => { | ||
| const toolCalls = rig.readToolLogs(); | ||
| const grepCalls = toolCalls.filter( | ||
| (call) => call.toolRequest.name === 'grep_search', | ||
| ); | ||
|
|
||
| expect(grepCalls.length).toBeGreaterThan(0); | ||
|
|
||
| const hasFrugalLimit = grepCalls.some((call) => { | ||
| const params = getGrepParams(call); | ||
| // Check for explicitly set small limit for "sample" or "example" requests | ||
| return ( | ||
| params.total_max_matches !== undefined && | ||
| params.total_max_matches <= 100 | ||
| ); | ||
| }); | ||
|
|
||
| expect( | ||
| hasFrugalLimit, | ||
| `Expected agent to use a small total_max_matches for a sample usage request. Params used: ${JSON.stringify( | ||
| grepCalls.map(getGrepParams), | ||
| null, | ||
| 2, | ||
| )}`, | ||
| ).toBe(true); | ||
| }, | ||
| }); | ||
| }); | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: for me it is not obvious what this evals do - we don't have frugal search tool or anything, so I imagine, it might be hard to remember in a year or too. I would add a comment or smth.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the feedback. In the interest of keeping momentum (particularly avoiding the need to re-run evals), I'm going to take these in an immediate followup.