mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-03-11 06:31:01 -07:00
61b35ff745
Major upgrade to the agent's self-validation, safety, and project integrity
capabilities through five iterations of system prompt enhancements:
Workflow & Quality Mandates:
1. Incremental Validation: Mandates building, linting, and testing after
every significant file change to maintain a "green" state.
2. Mandatory Reproduction: Requires creating a failing test case to confirm
a bug before fixing, and explicitly verifying the failure (Negative Verification).
3. Test Persistence & Locality: Requires integrating repro cases into the
permanent test suite, preferably by amending existing related test files.
4. Script Discovery: Mandates identifying project-specific validation
commands from configuration files (package.json, Makefile, etc.).
5. Self-Review: Mandates running `git diff` after every edit, using
`--name-only` for large changes to preserve context window tokens.
6. Fast-Path Validation: Prioritizes lightweight checks (e.g., `tsc --noEmit`)
for frequent feedback, reserving heavy builds for final verification.
7. Output Verification: Requires checking command output (not just exit codes)
to prevent false-positives from empty test runs or hidden warnings.
Semantic Integrity & Dependency Safety:
8. Global Usage Discovery: Mandates searching the entire workspace for all
usages (via `grep_search`) before modifying exported symbols or APIs.
9. Dependency Integrity: Requires verifying that new imports are explicitly
declared in the project's dependency manifest (e.g., package.json).
10. Configuration Sync: Mandates updating build/environment configs
(tsconfig, Dockerfile, etc.) to support new file types or entry points.
11. Documentation Sync: Requires searching for and updating documentation
references when public APIs or CLI interfaces change.
12. Anti-Silencing Mandate: Prohibits using `any`, `@ts-ignore`, or lint
suppressions to resolve validation errors.
Diagnostics, Safety & Runtime Verification:
13. Error Grounding: Mandates reading full error logs and stack traces upon
failure. Includes Smart Log Navigation to prioritize the tail of large files.
14. Scope Isolation: Instructs the agent to focus only on errors introduced
by its changes and ignore unrelated legacy technical debt.
15. Destructive Safety: Mandates a `git status` check before deleting files
or modifying critical project configurations.
16. Non-Blocking Smoke Tests: Requires briefly running applications to
verify boot stability, using background/timeout strategies for servers.
Includes 15 new behavioral evaluations verifying these mandates and updated
snapshots in packages/core/src/core/prompts.test.ts.
48 lines
1.4 KiB
TypeScript
48 lines
1.4 KiB
TypeScript
/**
|
|
* @license
|
|
* Copyright 2026 Google LLC
|
|
* SPDX-License-Identifier: Apache-2.0
|
|
*/
|
|
|
|
import { describe, expect } from 'vitest';
|
|
import { evalTest } from './test-helper.js';
|
|
|
|
describe('Configuration Sync', () => {
|
|
/**
|
|
* Verifies that the agent checks configuration files when adding a new entry point.
|
|
*/
|
|
evalTest('USUALLY_PASSES', {
|
|
name: 'should verify tsconfig when adding a new source file',
|
|
files: {
|
|
'src/index.ts': 'console.log("main");',
|
|
'package.json': JSON.stringify({
|
|
name: 'test-project',
|
|
type: 'module',
|
|
}),
|
|
'tsconfig.json': JSON.stringify({
|
|
compilerOptions: { strict: true },
|
|
include: ['src/index.ts'],
|
|
}),
|
|
},
|
|
prompt:
|
|
'Add a new utility file src/utils.ts and ensure it is included in the project configuration.',
|
|
assert: async (rig) => {
|
|
const toolLogs = rig.readToolLogs();
|
|
|
|
// Check if it read or edited tsconfig.json
|
|
const touchedTsConfig = toolLogs.some(
|
|
(log) =>
|
|
(log.toolRequest.name === 'read_file' ||
|
|
log.toolRequest.name === 'replace' ||
|
|
log.toolRequest.name === 'write_file') &&
|
|
log.toolRequest.args.includes('tsconfig.json'),
|
|
);
|
|
|
|
expect(
|
|
touchedTsConfig,
|
|
'Agent should have verified or updated tsconfig.json when adding a new source file',
|
|
).toBe(true);
|
|
},
|
|
});
|
|
});
|