# PR Checklist
- [x] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [x] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [x] Have you added type definitions?
# Description
This PR introduces following:
- Add doNotSummarizeUserMessage option to exclude user messages from
summarization
- Add early return logic to prevent unnecessary similarity checks when
summaries are empty
- Add length check before summarization
- Set to default settings when selecting HypaV3 on OtherBotSettings
- Add localization for HypaV3 settings and modal
- Change HypaV3 modal title
- Add import summary filtering and improve search in HypaV3
# PR Checklist
- [X] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [X] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
# Description
This PR contains modifications to import only the required assets when
talking to Asset Bot.
- refactor parseAdditionalAssets()
- Modified the getClostMatch() to work well with Object<key, value> to
which it is dynamically added.
- Add doNotSummarizeUserChat option to exclude user messages from summarization
- Add early return logic to prevent unnecessary similarity checks when summaries are empty
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
# Description
This PR fixes an issue where a removed module remains active until the
app is restarted if it was enabled at the time of deletion.
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
None of the above apply, as this update only involves UI translations.
# Description
- Updated the missing translations to the latest version
Since I can't perform local testing, I plan to hold off on updating the
Simplified Chinese translation for a while. This will give me time to
check if everything works correctly in Traditional Chinese before making
adjustments to both.
As always, many thanks to kwaroran for the hard work!
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
# Description
This PR introduces fix: add legacy translation support in Auto Translate
Cached Only option
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
# Description
This PR introduces fix: resolve mobile keyboard enter button not working
in HypaV3 modal
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?
# Preview
# Description
This calculation provides users with an approximate maximum memory
tokens ratio, allowing users to choose appropriate maximum context size
or memory tokens ratio based on their specific needs and circumstances.
The maximum memory tokens ratio is calculated based on:
`maxMemoryRatio = (maxContextTokens - requiredTokens) /
maxContextTokens`
- where `requiredTokens = promptTemplateTokens + charTokens +
maxLoreTokens + (maxResponseTokens * 3)`
