feat: surface session goal evaluation model and add diagnostics

Shows the evaluation provider/model used for the latest successful goal audit in the UI.
Persists evaluation model metadata on session goals and covers it in tests.
Adds diagnostic logging for small-model calls and session-goal audit parsing.
This commit is contained in:
Bohdan Triapitsyn
2026-07-15 08:56:10 +03:00
parent 4eac90ad44
commit e48a9397f1
17 changed files with 106 additions and 6 deletions
+1
View File
@@ -1394,6 +1394,7 @@ export const dict: Record<I18nKey, string> = {
"chat.goal.dialog.objectiveLabel": "Ціль",
"chat.goal.dialog.objectivePlaceholder": "Опишіть кінцевий стан, якого агент має досягти та перевірити…",
"chat.goal.dialog.budgetLabel": "Бюджет токенів",
"chat.goal.dialog.evaluationModelLabel": "Модель оцінювання",
"chat.goal.status.active": "Активна",
"chat.goal.status.evaluating": "Оцінювання…",
"chat.goal.status.paused": "Призупинена",