- 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?
# Description
This PR allows custom toggles to be added in the module as well. Below
is a screenshot of the updated module editing UI. Please feel free to
let me know if any further adjustments are needed or if you prefer not
to proceed with these changes.
# 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 pull request reintroduces charJS style button event previously
deprecated and removed, using luaEngine. This implementation diverges
from current style by passing attribute data as parameters rather than
function names.
# 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)`
