1.4.0

AI Efficiency, Tool Decomposition & CDN Architecture

AI Agent

  • YENİOptimized AI responses: All read endpoints now return 40–50% smaller responses, reducing AI token costs significantly.
  • YENİOptimized tool output: `getKeyDetails` returns a more efficient format (55% token reduction) with built-in field legend.
  • YENİImmediate HTTP streaming: AI chat opens the HTTP connection instantly, eliminating perceived "hanging" during initialization.
  • GÜNCELLEMEAI context window: Token counting now uses last step usage instead of cumulative totals.
  • GÜNCELLEMEAuto-approve UX: Clearer auto-approve prompt flow with semantic XML tags.

Dashboard

  • YENİNote activity type: Annotate translation keys with notes tracked in the activity feed.
  • YENİBilling cycle toggle: Monthly/yearly pricing with 20% yearly savings badge.
  • GÜNCELLEMETool UI decomposition: Monolithic tool.tsx decomposed into 11 focused files with zero visual changes.

Infrastructure

  • YENİR2 dual-bucket architecture: Flag images and static assets migrated to dedicated R2 bucket (`s3.better-i18n.com`), separate from translation files.
  • GÜNCELLEMEPublish query optimization: Parallelized queries for faster response times.
  • GÜNCELLEMEUser attribution: Sync jobs now track which user triggered them.

Bug Fixes & Improvements

  • DÜZELTİLDİMCP publish: Fixed failing when CDN is enabled but no files uploaded yet.
  • DÜZELTİLDİSoft-delete rename: Fixed transaction using single connection for find+rename+insert.
  • DÜZELTİLDİVList height: Fixed height mismatch for small translation lists (<20 items).
  • DÜZELTİLDİCache invalidation: Fixed organization settings cache invalidation key.