mirror of
https://github.com/google-gemini/gemini-cli.git
synced 2026-05-24 10:42:37 -07:00
Promote stable tests.
This commit is contained in:
@@ -111,7 +111,7 @@ describe('Answer vs. ask eval', () => {
|
||||
* Ensures that when the user asks a question about style, the agent does NOT
|
||||
* automatically modify the file.
|
||||
*/
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: 'should not edit files when asked about style',
|
||||
prompt: 'Is app.ts following good style?',
|
||||
files: FILES,
|
||||
|
||||
@@ -60,7 +60,7 @@ describe('ask_user', () => {
|
||||
// confirm shell commands. Fixed via prompt refinements and tool definition
|
||||
// updates to clarify that shell command confirmation is handled by the UI.
|
||||
// See fix: https://github.com/google-gemini/gemini-cli/pull/20504
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: 'Agent does NOT use AskUser to confirm shell commands',
|
||||
files: {
|
||||
'package.json': JSON.stringify({
|
||||
|
||||
@@ -11,7 +11,7 @@ import { assertModelHasOutput } from '../integration-tests/test-helper.js';
|
||||
describe('Hierarchical Memory', () => {
|
||||
const conflictResolutionTest =
|
||||
'Agent follows hierarchy for contradictory instructions';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: conflictResolutionTest,
|
||||
params: {
|
||||
settings: {
|
||||
|
||||
@@ -14,7 +14,7 @@ import {
|
||||
describe('save_memory', () => {
|
||||
const TEST_PREFIX = 'Save memory test: ';
|
||||
const rememberingFavoriteColor = "Agent remembers user's favorite color";
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: rememberingFavoriteColor,
|
||||
params: {
|
||||
settings: { tools: { core: ['save_memory'] } },
|
||||
@@ -79,7 +79,7 @@ describe('save_memory', () => {
|
||||
|
||||
const ignoringTemporaryInformation =
|
||||
'Agent ignores temporary conversation details';
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: ignoringTemporaryInformation,
|
||||
params: {
|
||||
settings: { tools: { core: ['save_memory'] } },
|
||||
@@ -104,7 +104,7 @@ describe('save_memory', () => {
|
||||
});
|
||||
|
||||
const rememberingPetName = "Agent remembers user's pet's name";
|
||||
evalTest('USUALLY_PASSES', {
|
||||
evalTest('ALWAYS_PASSES', {
|
||||
name: rememberingPetName,
|
||||
params: {
|
||||
settings: { tools: { core: ['save_memory'] } },
|
||||
|
||||
Reference in New Issue
Block a user