console: stop printing the customer's words under the AI's name
A contiguous run of WhatsApp turns collapsed into one timeline entry that kept the FIRST turn's speaker and previewed the LAST turn's message. When a run held the customer's question and Engage's answer, the entry carried Engage's chip over a quote the customer had typed — the trail claimed the machine said something a person did, which on an accountability demo is the worst thing it could get wrong. Runs now group per speaker. That still collapses the case grouping exists for (the same sentence resent several times) and can no longer misattribute, because every row in a run is one voice. Customer runs read "the customer / THE CUSTOMER SAID"; Engage runs read as Engage / WE REPLIED. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
3f36ea610b
commit
0df7d12073
@ -346,7 +346,14 @@ export default function Timeline({ rows, onOpenAgent, onOpenChat, onOpenCall })
|
||||
const grouped = []
|
||||
for (const it of items) {
|
||||
const last = grouped[grouped.length - 1]
|
||||
if (it.isChat && last && last.isChat) {
|
||||
// SAME SPEAKER ONLY. Collapsing every contiguous chat turn folded the
|
||||
// customer's question and the AI's answer into one entry that kept the
|
||||
// FIRST turn's name and the LAST turn's words — so the customer's message
|
||||
// printed under Engage's chip, attributing to the machine something a
|
||||
// person had typed. Grouping per speaker still collapses the case this
|
||||
// exists for (the same sentence resent four times) and can never
|
||||
// misattribute, because every row in a run is the same voice.
|
||||
if (it.isChat && last && last.isChat && last.agentKey === it.agentKey) {
|
||||
last.count += 1
|
||||
last.when = it.when
|
||||
// Keep the newest line as the preview — an operator scanning the trail
|
||||
|
||||
Loading…
Reference in New Issue
Block a user