feat(redrock_group_manager): LLM 审查谐音/emoji 变体识别与软色情擦边判定,豁免自动解禁修复 - #16
Merged
3 commits merged intoAug 8, 2026
Merged
Conversation
- 提示词新增变体识别章节:谐音/同音/形近/英文缩写/emoji 替代/符号拆分, 明确映射仅为示例、按方法泛化还原,先剥离防屏蔽符号再判断意图 - 敏感标准扩充软色情/擦边细则:性暗示与性挑逗、疑似未成年语境 (校服/课堂/新生+性化,最高优先级)、擦边平台账号引流 - 灰色词库追加变体触发词(板卡/加裙/薇信/裙号等 28 词)与软色情 触发词(骚/主人/校服/撩/扭/单身哥哥等 17 词),保证谐音与擦边 消息进入 LLM 审查而非漏检
部分 OneBot 实现(如 NapCat 群成员缓存)的 shut_up_timestamp 可能缺失 或失效,导致 until_ts 判断不成立、豁免时跳过解禁(日志 解除禁言 false)。 改为直接调用 ban_group_member(duration=0)(OneBot11 规范 0=取消禁言, 对未禁言成员为无害 no-op),并检查返回值,失败时记录 warn 日志
This pull request was closed.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
变更
feat: LLM 审查识别谐音/emoji 变体与软色情擦边内容
fix: 豁免自动解禁不再依赖 shut_up_timestamp 判断
shut_up_timestamp可能缺失/失效,导致豁免时跳过解禁(日志解除禁言 false)ban_group_member(duration=0)(OneBot11 规范 0=取消禁言,对未禁言成员为无害 no-op),并检查返回值、失败记 warn 日志验证
go test ./internal/pluggin/ -run TestRedrockPASS(含豁免自动解禁断言)