Language filter: correct the confidence semantics, announce the release - #106
Merged
Conversation
The page described the old behaviour, where a detection the bot could not make confidently counted as a violation. That has been flipped: a low-confidence reading is now skipped, and Minimum detection confidence is the bar the detector must clear before the filter may act. Default is 40. Adds how a message is checked, step by step, and the measured confidence values behind the default, so picking a value is not guesswork. Setting names now match the dashboard: Minimum detection confidence and Ignored words, not Minimum percentage and Excluded characters. Also adds a changelog entry, since the filter has only now become reachable for creators.
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ✅ Deployment successful! View logs |
docs | 688567a | Aug 17 2026, 10:03 AM |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Language filter page described behaviour that no longer exists, and the filter has only now become reachable for creators, so it also gets a changelog entry.
The correction
The page said a message is flagged "when the detection isn't confident enough to tell", and described Minimum percentage as the bar below which messages get flagged. StreamElements/chatbot#716 flipped that: a low-confidence reading is now skipped, and the setting is the confidence the detector must reach before the filter may act.
That matters because confidence spreads across 75 languages, so short messages misdetect badly. Under the old reading, an English-only channel timed out anyone typing
ok(Zulu, 6.4%) orgg(Indonesian, 14.4%), at any threshold.What else changed on the page
Changelog
New entry at
changelog/chatbot/2026-08-17-language-filter.mdxannouncing the filter.Verified against
bot/filters/language.goat chatbotv2.31.0and theminPercentagedefault in caipirinha'sbotFiltersmodel. Dashboard side is StreamElements/frontend#682.pnpm buildclean, all internal links valid.