What's new in Novelcrafter

Chat Extractions

• Added a button to toggle “keeping” all extractions (previously each entry had to be toggled individually)
• Added support for lots more edge cases

Other stuff

• Added support for advanced model parameters (minP, topK, repetition Penalty,…). These are only available for some OpenRouter models right now.
• The system defaults now includes the scene POV in text rewrite prompts
• You can now export single codex categories
• When editing a custom scene POV it now shows a list of existing POVs to choose from
• The codex now sorts names using numerical sort (so 1,10,60 instead of 1,10,60)

Nothing user-facing, just internal updates to reduce error rates in certain cases (e.g. leaving novelcrafter running in the background with an expired session/login).

• Chat messages containing code blocks now get properly interpreted as prose (That means you can now extract data from chat messages that previously had code blocks)
• Your codex list can now be sorted by color as well (still by name within that color)
• Added support for context.nextScene custom prompting functions
• Original error message is now being included in OpenRouter errors.

Blockquotes are here!

You can now select paragraphs to be styled as block quotes (this will also export properly to markdown as well as .docx/word files).

Custom Prompting

• Add context.codex.all function
• Add support for context.wordsAfter
• Add context.wordsBeforeAcrossScenes function
• Show per-message word counts in prompt preview/debugger

Other

• You can now see the word count of collapsible sections in their action menu
• Fix incorrect word counting of editor selection (for text that contained highlighted words)
• Make global codex entries clickable in beat validation (for those with no or short description)
• Improve loading of matrix view with lots of entries, as well as larger manuscripts
• Various other improvements and fixes

• Added support for Claude 3 Haiku
• Updated system prompts to include other Claude 3 models too, where missing
• Various other bug fixes and improvements (NC should be a bit faster to load now)

• Allow selecting from existing author / pen names when creating a new novel
• Added “Atkinson Hyperlegible” as 3rd sans-serif font
• Added prompt preview to default scene summarization (in case you don’t have a custom prompt for those)
• Return markdown when calling scene.content (this also now excludes “AI excluded” sections for both, summarization and chat)
• Fixed text replacement prompts not getting proper selection context (some codex entries would not be pulled into the AI prompt)
• Fixed word export not supporting collapsible sections
• Fixed markdown export not supporting collapsible sections

• You can now easily copy all text within a section to your clipboard!
• Improve chat message extraction (certain edge cases with bold names separating content)
• Fixes series meta data not being editable after creation
• Fixes some save issues with label editing
• Various visual tweaks/fixes
• Various other bug fixes and improvements

Updated System prompts

By popular demand the system prompt for prose generation has been tweaked based on your feedback:

1. If the previous scene matches the same POV, it will now fall back to the last words of the previous scene to give the AI a head start for prose
2. Less words by default: The previous 900 words was too much and tended to cause the writing to drift too much. This has now been reduced to just 400 words (Again, these are just guidelines for the model. Actual word counts might differ).
3. Toppy has been switched to use the OpenRouter free model instead. This makes it easier on newcomers to try out a few functions without having to pay.

Model Updates

New Claude 3 Model Support

Claude 3 Opus and Sonnet have been just released and are now available inside of Novelcrafter as well (via OpenRouter).

Unmoderated Claude endpoints

All Claude models have now also been switched over to their unmoderated endpoints. This should result in less strict responses.

While Opus is a good model for writing, it is also very expensive! Please make sure you have the funds to use it.

Mistral Medium + Large have been added to system prompts

Mistral recently released their “Large” model and you can now use both, medium and large for various actions (chat, summarization, …) as well.

New /section Command

Instead of having to type text, select it and then put it in a section, you can now easily create a new section by using the /section command in your manuscript.

Other changes

• Fixed issues with commas in your chapters when creating an outline from text
• Highlights in the timeline will now be hidden for collapsed sections as well
• Various other bugfixes and improvements

Improvements

• Prose sections can now be colorized! 🌈

• Act/chapter/scene texts/headings in matrix view as well as the selected scene in chats are now links to the manuscript

• Add codex.getAliases("Entry name") to get a comma-separated list of aliases for the given entry.

• Add context.codex.getAllByType and codex.getAllByType to get all entries for character, location, object, lore, subplot and other

• Make code blocks in chat messages more readable

• Improvements to chat message extraction

• When calling moderation, you now see a little message about its status

Fixes

• Chat Codex Entry Tracker shows entries again
• Codex additions in sections are now also being detected
• Hide word counts in chat message when AI is idling
• You can now use {codex.get("Entry name")} on entries that have the “do not track” flag enabled as well

A small one today, mostly just internal bugfixes and improvements. In addition:

• Codex Entries with quotes in their name should now be detected properly in prose as well
• You can now “add from archive” in outline plan mode, too