SillyTavern 1.13.4
Backends
- Google: Added support for the gemini-2.5-flash-image (Nano Banana) model.
- DeepSeek: Sampling parameters can be passed to the reasoner model.
- NanoGPT: Enabled prompt cache setting for Claude models.
- OpenRouter: Added image output parsing for models that support it.
- Chat Completion: Added Azure OpenAI and Electron Hub as sources.
Improvements
- Server: Added validation of hostnames in requests for improved security (opt-in).
- Server: Added support for SSL certificates with a passphrase when using HTTPS.
- Chat Completion: Requests that fail with code 429 will no longer be silently retried.
- Chat Completion: Inline Image Quality control is now available for all compatible sources.
- Reasoning: Auto-parsed reasoning blocks are now automatically removed from impersonation results.
- UI: Updated the layout of the background image settings menu.
- UX: Ctrl+Enter will send a user message if the text input is not empty.
- Added Thai locale and made various improvements to existing locales.
Extensions
- Image Captioning: Added custom model input for Ollama, updated the list of Groq models, and added NanoGPT as a source.
- Regex: Added a debug mode for regex visualization and the ability to save regex order and state as presets.
- TTS: Improved handling of nested quotes when using the "Narrate quotes" option.
Bug Fixes
- Fixed request streaming for the Vertex AI backend in Express mode.
- Fixed erroneous replacement of newlines with
<br>tags inside HTML code blocks. - Fixed custom toast positions not being applied to popups.
- Fixed the depth of in-chat prompt injections when using the continue function with the Chat Completion API.
What's Changed
- feat: Advanced Regex Chain Debugger and Testing Panel by @MAX-TAB in #4418
- Update dependencies by @Cohee1207 in #4447
- fix: Slash command descriptions and argument help text are not translated by @MAX-TAB in #4434
- Update ru-ru locale by @Yokayo in #4449
- Fix JannyAI error handling in #4460
- Chat Completion: Adjust depth of 0-depth injects on continue with prefill by @Cohee1207 in #4452
- Header change by @Vibecoder9000 in #4465
- Update zh-CN translations by @Tosd0 in #4466
- Fix compiler errors in public/global.d.ts by @epyllia in #4464
- fix: Resolve streaming output for Vertex AI Express Mode by @AliceRabbit in #4474
- a11y: Setup observers for element roles by @Cohee1207 in #4469
- More modern backgrounds buttons and filename by @Vibecoder9000 in #4484
- Server: Support passphrase for SSL private key by @Cohee1207 in #4488
- Server: Add host whitelisting by @Cohee1207 in #4476
- Add Electron Hub as Chat Completions Provider by @snowby666 in #4458
- Backgrounds Border Conflicts by @Vibecoder9000 in #4491
- Add: id="PersonaManagement" to Persona Management div by @RivelleDays in #4495
- Reasoning: Support auto-parse for impersonation results by @Cohee1207 in #4489
- feat: Regex Presets by @Tosd0 in #4468
- Fix: Do not replace newlines inside of pre blocks by @Cohee1207 in #4498
- Improvement: Add Upload Button to Image Gallery by @RivelleDays in #4500
- Fix/cleanup and background interactability (keyboard navigation, focus/hover) by @Wolfsblvt in #4503
- Change Ctrl+Enter handling for non-empty text input to send, instead of regenerate by @Wolfsblvt in #4504
- Fix toast positioning inside popups to align with the "Notifications" positioning option by @Wolfsblvt in #4506
- Implement robust quote extraction for TTS narration with support for nested quotes by @Wolfsblvt in #4502
- Improvement: Enhanced UI Consistency by @RivelleDays in #4499
- feat: Add Azure OpenAI chat completions provider by @nfuller286 in #4456
- Sync OpenRouter providers list by @cloak1505 in #4509
- Add Thai Translation by @Rawi1005 in #4513
- Staging by @Cohee1207 in #4516
New Contributors
- @epyllia made their first contribution in #4464
- @snowby666 made their first contribution in #4458
- @nfuller286 made their first contribution in #4456
- @Rawi1005 made their first contribution in #4513
Full Changelog: 1.13.3...1.13.4