feat: distill oversized plan goals into audit criteria

Plan-goal objectives are capped at 5000 chars for the auditor while the
working agent reads the full plan from its file. Plans over the limit are
now distilled by the small model into completion criteria (end goals +
per-phase verification, no implementation steps), prefixed with a header
pointing back at the plan file so every continuation re-anchors on the
live source of truth. If distillation fails (transient small-model
hiccup), a head+tail excerpt keeps the plan's intent (top) and acceptance
criteria (bottom) with a trim marker between — sacrificing the
implementation middle the agent reads from the file anyway — and a toast
tells the user the objective is degraded.

packages/ui/src/lib/i18n/messages/es.ts

@@ -1415,6 +1415,7 @@ export const dict: Record<I18nKey, string> = {
   "chat.goal.action.save": "Guardar objetivo",
   "chat.goal.action.start": "Iniciar objetivo",
   "chat.goal.toast.actionFailed": "No se pudo actualizar el objetivo",
+  "plans.goal.toast.distillFallback": "No se pudo destilar el plan para el auditor — se usó un extracto recortado",
   "chat.goal.row.aria": "Objetivo de sesión — abrir detalles",
   "chat.goal.button.createAria": "Definir un objetivo de sesión",
   "chat.goal.button.manageAria": "Gestionar el objetivo de sesión",