# PR Checklist
- [x] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [x] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [ ] Did you added a type def?
# Description
This PR fixes hypav2 issue where the "search_document: " string is not
truncated correctly.
If the "search_document: " string is not truncated correctly, it will
cause "t: " to remain within the <Past Events Details></Past Events
Details> tag.
Edit: This PR also add memo "supaPrompt" to detect supaMemory model
requests in the plugin
Resolved bug when entire chat context is deleted and hypaV2Data becomes empty, throwing a undefined index error. Also changed it to typescript index.
Hopefully resolved issue where same chat is summarized over and over again by adding another field to mainChunks.
# Changelist:
## 1. Types
### MainChunks
Added id(int), and chatMemos(Set<string>)
Id: incremental int starting from 0
chatMemos: A set of UUID, containing which chat has been summarized in it.
### Chunks
mainChunkID: A connection of which mainChunk it has been split from
text: the split text data
## 2. Features
### CleanInvalidChunks
Called every time when chat is updated and Hypamemory is used.
Gets all the memo(UUID)s of current chats, and creates a set.
Then checks if each mainChunk's chatMemos set is subset of the enitre memo set. If not, the summarized part's chat is deleted/edited. The mainChunk is filtered out.
Concurrently, the chunks that are split from that mainChunk is also deleted.
# PR Checklist
- [ ] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [x] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [ ] Did you added a type def?
# Description
This PR fixes an issue where indentation and whitespace inside the
{{#if_pure}} syntax were being trimmed.
I made an effort to minimize the impact on the parser's existing
behavior.
Also revoked potentially problematic feature(add hypav2data chunk)
TODO:
1. On mid-context editing, currently that is not considered as deletion. Do have optional editedChatIndex to latter dive in more.
2. re-roll mainChunks(re-summarization) functionalities added, but not able to access it.
# PR Checklist
- [x] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [x] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [ ] Did you added a type def?
# Description
This PR introduces a fix for the issue where the input auto-translation
field ("Enter Message for Translate to English" text displayed when
nothing is entered) was not correctly translating the original text into
English in the LLM-based translation.
Additionally, this update ensures that "Curly Braced Syntaxes {{slot}}"
are translated into the user's native language when the translation
button is pressed, and into English during the input translation,
facilitating more effective translation.
