Changelog ChatAcademia

Stay up to date with all the latest updates, improvements, and new features we ship to help you do better research. We’re constantly improving ChatAcademia for academics and researchers.

Home

© 2026 ChatAcademia

More Reliable Onboarding and Long-Running Tools

More Reliable Onboarding and Long-Running Tools

ChatAcademia now keeps onboarding conversations and long-running research tools stable across slower AI responses.

Improvements

  • Let long-running research tools use the full chat time budget when needed
  • Keep onboarding conversations reliable when OpenAI responses are replayed across steps
  • Refresh app and workspace dependencies for current runtime fixes

Longer Academic Tools Without Interruption

Longer Academic Tools Without Interruption

Academic Chat now gives longer searches and document tools enough time to finish while keeping safeguards for stalled requests.

Improvements

  • Let longer database searches and document tools finish within their intended time limits
  • Keep Fast, Pro, and Max chats protected by total, step, and tool-specific safeguards
  • Improve recovery details when an agent tool genuinely times out

More Reliable Chat and Website Recovery

More Reliable Chat and Website Recovery

ChatAcademia now recovers more cleanly from slow AI steps and browser tools that unexpectedly modify the page.

Improvements

  • Keep handled Fast chat timeouts from surfacing as unexpected app errors
  • Prevent external browser translation tools from breaking website navigation
  • Improve stability when Android in-app browsers close or navigate away

More Reliable Chat Navigation

More Reliable Chat Navigation

Academic Chat now recovers more cleanly from rare browser navigation and connection interruptions.

Improvements

  • Keep the Academic Chat landing page available during rare background-tab navigation races
  • Preserve clear connection recovery when mobile browsers briefly interrupt chat requests
  • Refresh app, API, website, and workspace dependencies for current runtime fixes

GPT-5.6 Across Every Chat Tier

GPT-5.6 Across Every Chat Tier

Fast, Pro, and Max chats now use the GPT-5.6 family, matching each tier to the right balance of speed, capability, and depth.

Improvements

  • Use GPT-5.6 Luna for faster, more affordable everyday research questions
  • Use GPT-5.6 Terra for balanced Pro chats with stronger reasoning
  • Use GPT-5.6 Sol for demanding academic work with a balanced reasoning budget
  • Keep every tier within a 272,000-token context window and retain provider-diverse fallbacks