feat(group-chat): add @all mention routing (#857)

Add modular group-chat mention routing helpers for the reserved @all token, route it to every non-sender agent, and strip routing tokens before model input.

Expose @all in mention autocomplete, highlight it in group messages, reserve literal all agent names, and cover boundary/partial-match regressions with tests.
This commit is contained in:
Zhicheng Han
2026-05-20 04:21:57 +02:00
committed by GitHub
parent 210b0ee6c2
commit 904ca8c648
10 changed files with 386 additions and 42 deletions
@@ -56,7 +56,7 @@ const avatarSvg = computed(() => {
return multiavatar(props.message.senderName || props.message.senderId)
})
const mentionNames = computed(() => props.agents.map(a => a.name).filter(Boolean))
const mentionNames = computed(() => ['all', ...props.agents.map(a => a.name).filter(Boolean)])
const parsedThinking = computed(() => parseThinking(props.message.content || '', { streaming: !!props.message.isStreaming }))
const hasReasoningField = computed(() => !!(props.message.reasoning && props.message.reasoning.length > 0))
const hasThinking = computed(() => hasReasoningField.value || parsedThinking.value.hasThinking)