# 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?
- [x] Did you added a type def?
# Description
This PR fixes the image input functionality for the Gemini model.
### Issue with Existing Code
The previous implementation attempted to process images in the following
way:
1. In the `OpenAIChat` type, if the `memo` field started with
`inlayImage`, the `content` field's value was copied into a variable
called `pendingImage`.
2. Later, if the `chat` role was `'user'` and `pendingImage` was not an
empty string, the code processed the image.
However, it does not seem to work as expected in the current state.
### Update
I updated the image input handling to align with the method used in
RisuAI for handling GPT’s image input. Specifically, the changes
include:
1. In `image.ts`, I explicitly specified the `gemini-exp` model.
2. If the `chat` object has a `multimodals` field and the `role` is
`user`:
- I created an array called `geminiParts` to store `GeminiPart` objects.
- The `chat.content` value is set as the `text` field of the
`GeminiPart` object in the array.
- I then iterated over `chat.multimodals` and created an object for each
`image` type, formatting it to match the Gemini structure, and added it
to the `geminiParts` array.
- After the iteration, the `geminiParts` array is assigned to the
`parts` field of `reformatedChat`.
### Notes
- I removed the previous non-functional code entirely. If this causes
any inconvenience or violates any conventions, I sincerely apologize.
- As the final name of the next-generation Gemini model is currently
unknown, I restricted the functionality to the **gemini-exp** model in
the `image.ts` file for now. This can be updated later when the official
name is confirmed.
The Gemini model is currently very widely used, so I kindly request you
to review the updated code. If you have any feedback or if the changes
are not acceptable, I completely understand if this PR is rejected.
Thank you for your time and consideration! Let me know if there's
anything I can improve or clarify.
# 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
There was an issue where the autoTranslateCachedOnly option was being
ignored when sending messages. This occurred due to the way the
translated variable was initialized with let translated =
$state(DBState.db.autoTranslate).
# 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.
# 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 an issue where cache misses occur when
translateBeforeHTMLFormatting is disabled. Previously, the 'Auto
Translate Cached Only' feature only worked when
translateBeforeHTMLFormatting was enabled. This update ensures that
cached translations are used properly even when
translateBeforeHTMLFormatting is disabled.
Thank you for taking the time. This is not an urgent matter, but I would
appreciate it if you could incorporate this PR along with other changes
in the next update.
