SillyTavern 1.13.3

News

Most built-in formatting templates for Text Completion (instruct and context) have been updated to support proper Story String wrapping. To use the at-depth position and get a correctly formatted prompt:

1. If you are using system-provided templates, restore your context and instruct templates to their default state.
2. If you are using custom templates, update them manually by moving the wrapping to the Story String sequence settings.

See the documentation for more details.

Backends

• Chat Completion: Removed the 01.AI source. Added Moonshot, Fireworks, and CometAPI sources.
• Synchronized model lists for OpenAI, Claude, Cohere, and MistralAI.
• Synchronized the providers list for OpenRouter.

Improvements

• Instruct Mode: Removed System Prompt wrapping sequences. Added Story String wrapping sequences.
• Context Template: Added {{anchorBefore}} and {{anchorAfter}} Story String placeholders.
• Advanced Formatting: Added the ability to place the Story String in-chat at depth.
• Advanced Formatting: Added OpenAI Harmony (gpt-oss) formatting templates.
• Welcome Screen: The hint about setting an assistant will not be displayed for customized assistant greetings.
• Chat Completion: Added an indication of model support for Image Inlining and Tool Calling options.
• Tokenizers: Downloadable tokenizer files now support GZIP compression.
• World Info: Added a per-entry toggle to ignore budget constraints.
• World Info: Updated the World Info editor toolbar layout and file selection dropdown.
• Tags: Added an option to prune unused tags in the Tags Management dialog.
• Tags: All tri-state tag filters now persist their state on reload.
• UI: The Alternate Greeting editor textarea can be maximized.
• UX: Auto-scrolling behavior can be deactivated and snapped back more reliably.
• Reasoning: Added a button to close all currently open reasoning blocks.

Extensions

• Extension manifests can now specify a minimal SillyTavern client version.
• Regex: Added support for named capture groups in "Replace With".
• Quick Replies: QR sets can be bound to characters (non-exportable).
• Quick Replies: Added a "Before message generation" auto-execute option.
• TTS: Added an option to split voice maps for quotes, asterisks, and other text.
• TTS: Added the MiniMax provider. Added the gpt-4o-mini-tts model for the OpenAI provider.
• Image Generation: Added a Variety Boost option for NovelAI image generation.
• Image Captioning: Always load the external models list for OpenRouter, Pollinations, and AI/ML.

STscript

• Added the trim argument to the /gen and /sysgen commands to trim the output by sentence boundary.
• The name argument of the /gen command will now activate group members if used in groups.

Bug fixes

• Fixed a server crash when trying to back up the settings of a deleted user.
• Fixed the pre-allocation of injections in chat history for Text Completion.
• Fixed an issue where the server would try to DNS resolve the localhost domain.
• Fixed an auto-load issue when opening recent chats from the Welcome Screen.
• Fixed the syntax of YAML placeholders in the Additional Parameters dialog.
• Fixed model reasoning extraction for the MistralAI source.
• Fixed the duplication of multi-line example message separators in Instruct Mode.
• Fixed the initialization of UI elements in the QR set duplication logic.
• Fixed an issue with Character Filters after World Info entry duplication.
• Fixed the removal of a name prefix from the prompt upon continuation in Text Completion.
• Fixed MovingUI behavior when the resized element overlaps with the top bar.
• Fixed the activation of group members on quiet generation when the last message is hidden.
• Fixed chat metadata cloning compatibility for some third-party extensions.
• Fixed highlighting for quoted run shorthand syntax when used with QR names containing a space.

Community updates

• Fix convert to persona with unusual names by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4319
• AI Studio/Vertex AI: add seed param by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4314
• feat: add tts provider MiniMax by @MindsMaster in https://github.com/SillyTavern/SillyTavern/pull/4309
• Deprecate 01.ai chat completion source by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4327
• fixes #4324: injectedIndices becomes invalidated with a off-by-one in… by @alekslt in https://github.com/SillyTavern/SillyTavern/pull/4325
• Feat/moonshot api by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4330
• Add command-a-vision support by @equal-l2 in https://github.com/SillyTavern/SillyTavern/pull/4340
• Add copy option to move WI entry by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4335
• Support gzip compression for tokenizer downloads by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4348
• Fix duplication of multi-line example message separators in instruct mode by @crimeragames in https://github.com/SillyTavern/SillyTavern/pull/4347
• Allow extensions to specify minimum ST client version by @qvink in https://github.com/SillyTavern/SillyTavern/pull/4350
• feature: ignore budget switch by @kallewoof in https://github.com/SillyTavern/SillyTavern/pull/4354
• Add gpt-4o-mini-tts model with character voice instructions #3879 by @Ni-co-la-s in https://github.com/SillyTavern/SillyTavern/pull/4352
• Instruct: Add Sequences as Stop Strings control by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4355
• Text Completion: Inject Story String @ depth by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4362
• feat(client): desktop version uses select2 to search, filter, and select by @pAnhTri in https://github.com/SillyTavern/SillyTavern/pull/4359
• Add multiple voice per character in TTS extension by @Ni-co-la-s in https://github.com/SillyTavern/SillyTavern/pull/4367
• feat: Add close all reasonings button by @andrempiva in https://github.com/SillyTavern/SillyTavern/pull/4375
• Fix Soulkyn import by @buzz in https://github.com/SillyTavern/SillyTavern/pull/4372
• Persist actionable tag states on reload by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/4368
• Add Fireworks AI Provider Support by @ershang-fireworks in https://github.com/SillyTavern/SillyTavern/pull/4374
• Fix overly sticky auto-scroll behavior by @Christoph-D in https://github.com/SillyTavern/SillyTavern/pull/4382
• Added saveMetadataDebounced to context, fixed 0 values for custom-req… by @bmen25124 in https://github.com/SillyTavern/SillyTavern/pull/4386
• bug-fix: adhere to chat template hash bound settings when a new model appears using the same hash as a bound one by @kallewoof in https://github.com/SillyTavern/SillyTavern/pull/4393

New Contributors

• @MindsMaster made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4309
• @alekslt made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4325
• @crimeragames made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4347
• @Ni-co-la-s made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4352
• @pAnhTri made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4359
• @andrempiva made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4375
• @ershang-fireworks made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4374
• @Christoph-D made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4382
• @zeroDtree made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4397
• @TensorNull made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4402
• @dfaker made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/4425

Full Changelog: https://github.com/SillyTavern/SillyTavern/compare/1.13.2...1.13.3