mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-03-10 22:21:22 -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.
89 lines
2.8 KiB
TypeScript
89 lines
2.8 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('Incremental Validation', () => {
|
|
/**
|
|
* This evaluation verifies that the agent adheres to the "Incremental Validation" mandate
|
|
* by performing build or test checks between distinct, significant file changes.
|
|
*/
|
|
evalTest('USUALLY_PASSES', {
|
|
name: 'should perform incremental validation between distinct file changes',
|
|
files: {
|
|
'src/a.ts': 'export const valA = 1 - 2; // BUG: should be 1 + 2',
|
|
'src/b.ts': 'export const valB = 0;',
|
|
'package.json': JSON.stringify({
|
|
name: 'test-project',
|
|
type: 'module',
|
|
scripts: {
|
|
test: 'echo "running tests..."',
|
|
build: 'echo "building..."',
|
|
},
|
|
}),
|
|
},
|
|
prompt:
|
|
'1. Fix the bug in src/a.ts (change - to +). 2. After that is done, update src/b.ts to export valB = 42. Ensure the project is buildable and tested at each step.',
|
|
assert: async (rig) => {
|
|
const toolLogs = rig.readToolLogs();
|
|
|
|
// Find indices of edits to a.ts and b.ts
|
|
const editAIndex = toolLogs.findIndex(
|
|
(log) =>
|
|
(log.toolRequest.name === 'replace' ||
|
|
log.toolRequest.name === 'write_file') &&
|
|
log.toolRequest.args.includes('src/a.ts'),
|
|
);
|
|
|
|
const editBIndex = toolLogs.findIndex(
|
|
(log) =>
|
|
(log.toolRequest.name === 'replace' ||
|
|
log.toolRequest.name === 'write_file') &&
|
|
log.toolRequest.args.includes('src/b.ts'),
|
|
);
|
|
|
|
expect(editAIndex, 'Agent should have edited src/a.ts').toBeGreaterThan(
|
|
-1,
|
|
);
|
|
expect(editBIndex, 'Agent should have edited src/b.ts').toBeGreaterThan(
|
|
editAIndex,
|
|
);
|
|
|
|
const isValidationCommand = (log: any) => {
|
|
if (log.toolRequest.name !== 'run_shell_command') return false;
|
|
const cmd = log.toolRequest.args.toLowerCase();
|
|
return (
|
|
cmd.includes('build') ||
|
|
cmd.includes('test') ||
|
|
cmd.includes('npm run') ||
|
|
cmd.includes('tsc')
|
|
);
|
|
};
|
|
|
|
// Check for validation between editA and editB
|
|
const validationBetween = toolLogs
|
|
.slice(editAIndex + 1, editBIndex)
|
|
.some(isValidationCommand);
|
|
|
|
expect(
|
|
validationBetween,
|
|
'Expected a build/test command between two distinct file edits to ensure incremental stability',
|
|
).toBe(true);
|
|
|
|
// Also check for validation after editB to confirm final state
|
|
const validationAfter = toolLogs
|
|
.slice(editBIndex + 1)
|
|
.some(isValidationCommand);
|
|
|
|
expect(
|
|
validationAfter,
|
|
'Expected a build/test command after the final file edit',
|
|
).toBe(true);
|
|
},
|
|
});
|
|
});
|