Merge remote-tracking branch 'origin/main' into gundermanc/promote2

evals/answer-vs-act.eval.ts

@@ -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,

evals/hierarchical_memory.eval.ts

@@ -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: {

evals/save_memory.eval.ts

@@ -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'] } },