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.
2026-07-15 08:56:10 +03:00
parent 4eac90ad44
commit e48a9397f1
17 changed files with 106 additions and 6 deletions
@@ -117,6 +117,14 @@ export function SessionGoalDialog({ open, onOpenChange, sessionId, directory }:
              {goal.statusReason && (goal.status === 'blocked' || goal.status === 'budgetLimited') ? (
                <p className="typography-meta text-muted-foreground/70">{goal.statusReason}</p>
              ) : null}
+              {goal.evaluationProviderID || goal.evaluationModelID ? (
+                <div className="flex items-baseline gap-2 typography-meta">
+                  <span className="text-muted-foreground/70">{t('chat.goal.dialog.evaluationModelLabel')}</span>
+                  <span className="min-w-0 break-all text-foreground">
+                    {[goal.evaluationProviderID, goal.evaluationModelID].filter(Boolean).join('/')}
+                  </span>
+                </div>
+              ) : null}
            </div>
          )}

@@ -1416,6 +1416,7 @@ export const dict = {
  'chat.goal.dialog.objectiveLabel': 'Objective',
  'chat.goal.dialog.objectivePlaceholder': 'Describe the end state the agent should reach and verify…',
  'chat.goal.dialog.budgetLabel': 'Token budget',
+  'chat.goal.dialog.evaluationModelLabel': 'Evaluation model',
  'chat.goal.status.active': 'Active',
  'chat.goal.status.evaluating': 'Evaluating…',
  'chat.goal.status.paused': 'Paused',
@@ -1394,6 +1394,7 @@ export const dict: Record<I18nKey, string> = {
  "chat.goal.dialog.objectiveLabel": "Objetivo",
  "chat.goal.dialog.objectivePlaceholder": "Describe el estado final que el agente debe alcanzar y verificar…",
  "chat.goal.dialog.budgetLabel": "Presupuesto de tokens",
+  "chat.goal.dialog.evaluationModelLabel": "Modelo de evaluación",
  "chat.goal.status.active": "Activo",
  "chat.goal.status.evaluating": "Evaluando…",
  "chat.goal.status.paused": "En pausa",
@@ -1236,6 +1236,7 @@ export const dict = {
  'chat.goal.dialog.objectiveLabel': 'Objectif',
  'chat.goal.dialog.objectivePlaceholder': 'Décrivez l\'état final que l\'agent doit atteindre et vérifier…',
  'chat.goal.dialog.budgetLabel': 'Budget de tokens',
+  'chat.goal.dialog.evaluationModelLabel': 'Modèle d’évaluation',
  'chat.goal.status.active': 'Actif',
  'chat.goal.status.evaluating': 'Évaluation…',
  'chat.goal.status.paused': 'En pause',
@@ -1412,6 +1412,7 @@ export const dict: Record<I18nKey, string> = {
  'chat.goal.dialog.objectiveLabel': '目標',
  'chat.goal.dialog.objectivePlaceholder': 'エージェントが到達して検証すべき最終状態を記述してください…',
  'chat.goal.dialog.budgetLabel': 'トークン予算',
+  'chat.goal.dialog.evaluationModelLabel': '評価モデル',
  'chat.goal.status.active': '進行中',
  'chat.goal.status.evaluating': '評価中…',
  'chat.goal.status.paused': '一時停止',
@@ -1418,6 +1418,7 @@ export const dict: Record<I18nKey, string> = {
  'chat.goal.dialog.objectiveLabel': '목표',
  'chat.goal.dialog.objectivePlaceholder': '에이전트가 도달하고 검증해야 할 최종 상태를 설명하세요…',
  'chat.goal.dialog.budgetLabel': '토큰 예산',
+  'chat.goal.dialog.evaluationModelLabel': '평가 모델',
  'chat.goal.status.active': '진행 중',
  'chat.goal.status.evaluating': '평가 중…',
  'chat.goal.status.paused': '일시 중지됨',
@@ -2104,6 +2104,7 @@ export const dict: Record<I18nKey, string> = {
  'chat.goal.dialog.objectiveLabel': 'Cel',
  'chat.goal.dialog.objectivePlaceholder': 'Opisz stan końcowy, który agent ma osiągnąć i zweryfikować…',
  'chat.goal.dialog.budgetLabel': 'Budżet tokenów',
+  'chat.goal.dialog.evaluationModelLabel': 'Model oceniający',
  'chat.goal.status.active': 'Aktywny',
  'chat.goal.status.evaluating': 'Ocenianie…',
  'chat.goal.status.paused': 'Wstrzymany',
@@ -1394,6 +1394,7 @@ export const dict: Record<I18nKey, string> = {
  "chat.goal.dialog.objectiveLabel": "Objetivo",
  "chat.goal.dialog.objectivePlaceholder": "Descreva o estado final que o agente deve alcançar e verificar…",
  "chat.goal.dialog.budgetLabel": "Orçamento de tokens",
+  "chat.goal.dialog.evaluationModelLabel": "Modelo de avaliação",
  "chat.goal.status.active": "Ativo",
  "chat.goal.status.evaluating": "Avaliando…",
  "chat.goal.status.paused": "Pausado",
@@ -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",
@@ -1382,6 +1382,7 @@ export const dict: Record<I18nKey, string> = {
  'chat.goal.dialog.objectiveLabel': '目标',
  'chat.goal.dialog.objectivePlaceholder': '描述代理应达到并验证的最终状态…',
  'chat.goal.dialog.budgetLabel': '令牌预算',
+  'chat.goal.dialog.evaluationModelLabel': '评估模型',
  'chat.goal.status.active': '进行中',
  'chat.goal.status.evaluating': '评估中…',
  'chat.goal.status.paused': '已暂停',
@@ -1386,6 +1386,7 @@ export const dict: Record<I18nKey, string> = {
  'chat.goal.dialog.objectiveLabel': '目標',
  'chat.goal.dialog.objectivePlaceholder': '描述代理應達成並驗證的最終狀態…',
  'chat.goal.dialog.budgetLabel': '權杖預算',
+  'chat.goal.dialog.evaluationModelLabel': '評估模型',
  'chat.goal.status.active': '進行中',
  'chat.goal.status.evaluating': '評估中…',
  'chat.goal.status.paused': '已暫停',
@@ -23,6 +23,8 @@ export interface SessionGoalPayload {
  blockedStreak: number;
  note: string;
  statusReason: string;
+  evaluationProviderID: string;
+  evaluationModelID: string;
  lastAccountedMessageID: string;
  createdAt: number;
  updatedAt: number;
@@ -64,6 +66,8 @@ export function getSessionGoal(session: Session | null | undefined): SessionGoal
    blockedStreak: asCount(goal.blockedStreak),
    note: typeof goal.note === 'string' ? goal.note : '',
    statusReason: typeof goal.statusReason === 'string' ? goal.statusReason : '',
+    evaluationProviderID: typeof goal.evaluationProviderID === 'string' ? goal.evaluationProviderID : '',
+    evaluationModelID: typeof goal.evaluationModelID === 'string' ? goal.evaluationModelID : '',
    lastAccountedMessageID: typeof goal.lastAccountedMessageID === 'string' ? goal.lastAccountedMessageID : '',
    createdAt: typeof goal.createdAt === 'number' ? goal.createdAt : 0,
    updatedAt: typeof goal.updatedAt === 'number' ? goal.updatedAt : 0,