jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-29 09:12:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

Validate clarification and correct context-test setup; record rejected prompt experiment

Browse Source
This commit is contained in:
pewdiepie-archdaemon
2026-09-17 21:49:00 +00:00
parent cb305ca45e
commit a312e918e7
3 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/verify_clean_v3_search_quality.mjs
+1 -1
View File
@@ -136,7 +136,7 @@ try {
['no-web-ambiguous', ['can u look it up'], false],
['no-web-missing-object', ['please find that'], false],
['no-web-missing-price', ['what about its price?'], false],
['grounded-lookup-followup', ['Remember this topic for my next question: the Python release schedule. Do not search yet.', 'can u look it up'], [false, true]],
['grounded-lookup-followup', ['My next question is about the Python release schedule. For now, just acknowledge; do not search or save anything.', 'can u look it up'], [false, true]],
];
async function runCase([name, prompts, needsWeb]) {
const scenario = { name, status: 'running', turns: [] };