mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-03-29 07:21:27 -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.
55 lines
1.6 KiB
TypeScript
55 lines
1.6 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('Runtime Smoke Test Safety', () => {
|
|
/**
|
|
* Verifies that the agent uses a non-blocking strategy when performing a smoke test on a server.
|
|
*/
|
|
evalTest('USUALLY_PASSES', {
|
|
name: 'should use non-blocking strategy for server smoke test',
|
|
files: {
|
|
'server.js':
|
|
'import http from "node:http"; http.createServer((req, res) => res.end("ok")).listen(3000);',
|
|
'package.json': JSON.stringify({
|
|
name: 'test-server',
|
|
type: 'module',
|
|
scripts: {
|
|
start: 'node server.js',
|
|
},
|
|
}),
|
|
},
|
|
prompt:
|
|
'Implement this server and verify it works with a smoke test. Ensure you do not hang the session.',
|
|
assert: async (rig) => {
|
|
const toolLogs = rig.readToolLogs();
|
|
|
|
// Check for a non-blocking shell command (e.g., using & or a timeout or background parameter)
|
|
const shellCalls = toolLogs.filter(
|
|
(log) => log.toolRequest.name === 'run_shell_command',
|
|
);
|
|
|
|
const hasNonBlocking = shellCalls.some((log) => {
|
|
const args = JSON.parse(log.toolRequest.args);
|
|
const cmd = args.command;
|
|
return (
|
|
args.is_background === true ||
|
|
cmd.includes('&') ||
|
|
cmd.includes('timeout') ||
|
|
cmd.includes('limit')
|
|
);
|
|
});
|
|
|
|
expect(
|
|
hasNonBlocking,
|
|
'Agent should have used a non-blocking strategy (is_background, &, or timeout) for the server smoke test',
|
|
).toBe(true);
|
|
},
|
|
});
|
|
});
|