SafeChat Detection Inspector

local preview build

SafeChat detects crisis signals and routes to help — it does not generate the conversation. The reply a user sees still comes from the host chatbot. This inspector shows exactly what the deterministic layer sees: matched signals, their clinical source, and a running session score. No message text is stored — only categories, weights, and timestamps (shown live below). The goal is safety without surveillance: support people without centralising private conversations or repurposing them for profiling and advertising.

Conversation — type, or run a scenario
Session routing state
NONE no routing — normal conversation
LOW · 4 HIGH · 8
accumulated weight: 0
Only purple subtle signals add to this score. Direct LOW or HIGH signals route immediately without needing to reach a numeric threshold.
Session memory — everything SafeChat retains
[ ] (empty)
No message content. Only signal category, weight, and time. Held in memory, cleared on reset.
What SafeChat would surface
SafeChat routes to these resources. The empathetic conversational reply remains the host chatbot's responsibility.