Major Features
- API key encryption at rest using Fernet (OS keyring with file fallback)
- Prompt Manager: unified UI with template groups, priority ordering, override tracking, response extractors
- Scene context history review panel with token budgets and best-fit mode
- Multiple concurrent director chats with auto-generated titles
- Granular scene state reset dialog
- Time passage insert/edit/delete in scene view
- Image analysis via OpenAI-compatible and Talemate Client backends
- Volatile context placement after scene history for improved prompt caching
Improvements
- Configurable narrator generation length per narration type
- AI Aware conversation mode
- Summarizer: custom instructions, writing style inclusion, short line filtering
- Anthropic: adaptive thinking support, updated model list (opus-4-5/4-6, haiku-4-5)
- Google: gemini-3.1 support
- World editor: generate from topic, quick create state reinforcement, reorganized menus
- Node editor: promote scene modules to global
- Frontend: version mismatch detection, hideable bracket content, required scene name
- TTS: improved pause handling, audio tag support for vocal markers (ElevenLabs v3)
- Writing style template for AI-generated instructions
- Added Kimi.jinja2 LLM prompt template
- Option to disable character names in stopping strings
- Client response length enforcement options
- Graduated token count sliders
- Increased summarizer token threshold max
Bugfixes
- Fix bracket/paren/brace terminators stripped from message ends
- Fix colon in conversation causing content loss
- Fix "Use as reference" navigating to blank page
- Fix avatar regeneration and manual regenerate
- Fix conversation agent ignoring generation length
- Fix duplicate length instructions with reasoning enabled
- Fix trailing newline on message edits
- Fix summarize dialogue sending too much context with layered history
- Fix layered history inspection and construction issues
- Fix empty response handling in summarization
- Fix context ID dot notation with dotted character names
- Fix recursive retry in focal agent
- Fix leading whitespace causing duplicate prepared responses
- Fix summarization not stripping ANALYSIS OF lines
- Fix template group selection/removal in prompt manager
- Fix multiline text in parentheses/brackets parser
- Fix determine_character_name resolution
- Fix character activate/deactivate desyncing creative menu
- Fix character image generation missing context
- Fix LMStudio client not sending token limits
- Fix Recent Scene images on newer Chromium
- Fix sequential reinforcement messages cut off at first linebreak
- Fix reinforcement removal not clearing state
- Fixes#252, #256, #258
Deprecations
- Removed context investigations (replaced by AI-assisted RAG mixin)
- Removed deprecated prompt templates (fix-continuity-errors, fix-exposition, etc.)
- Removed conversation/edit.jinja2, auto break repetition, CLI reset layered history
---------
Co-authored-by: theDTV2 <47825738+theDTV2@users.noreply.github.com>
* cleanup
* refactor clean_dialogue
* prompt fixes
* prompt fixes
* conversation format types - movie script and chat (legacy)
* stopping strings updated
* mistral.ai client
* prompt tweaks
* mistral client return token counts
* anthropic client
* archive history emits whole object so we can inspectr time stamps
* show timestamp in history dialog
* openai compat fixes to stop trying to coerce openai url path schema and to never attempt to retrieve the model name automatically, hopefully improving compatibility with the various openai api implementations across the board
* openai compat client let api control prompt template via config option
* fix custom client configs and implement max backscroll
* fix backscroll limit
* remove debug message
* prep 0.21.0
* include model name in prompt template selection label
* use tabs for side nav in app config modal
* readme / docs
* fix issue where "No API key set" could be persisted as the selected model name to the config
* deepinfra example
* linting
* fix issue where recent save cover images would sometimes not load
* paraphrase prompt tweaks
* action_to_narration regenerate compatibility fixes
* sim suite add asnwer question instruction
* more sim suite tweaks
* refactor agent details display in agent bar
* visual agent progres (a1111 support)
* visual gen prompt tweaks
* openai compat client pass max_tokens
* world state sequential reinforcement max tokens tightened
* improve item names
* Improve item names
* attempt to remove "changed from.." notes when altering an existing character sheet
* prompt improvements for single character portraits
* visual agent progress
* fix issue where character.update wouldn't update long-term memory
* remove experimental flag for now
* add better instructions for updating existing character sheet
* background processing for agents, visual and tts
* fix selected voice not saving between restarts for elevenlabs
* lessen timeout
* clean up agent status logic
* conditional agent configs
* comfyui support
* visualization queue
* refactor visual styles, comfyui progress
* regen images
auto cover image assign
websocket handler plugin abstraction
agent websocket handler
* automatic1111 fixes
agent status and ready checks
* tweaks to character portrait prompt
* system prompt for visualize
* textgenwebui use temp smoothing on yi models
* comment out api key for now
* fixes issues with openai compat client for retaining api key and auto fixing urls
* update_reinforcment tweaks
* agent status emit from one place
* emit agent status as asyncio task
* remove debug output
* tts add openai support
* openai img gen support
* fix issue with confyui checkbox list not loading
* tts model selection for openai
* narrate_query include character sheet if character is referenced in query
improve visual character portrit generation prompt
* client implementation extra field support and runpod vllm client example
* relock
* fix issue where changing context length would cause next generation to error
* visual agent tweaks and auto gen character cover image in sim suite
* fix issue with readyness lock when there werent any clients defined
* load scene readiness fixes
* linting
* docs
* notes for the runpod vllm example
