feat(channels): real LLM compaction for web UI compact endpoint

Extract CompactGroup() from runCompaction() for shared use by both
auto-compact and HTTP compact endpoint. Wire provider registry into
PendingMessagesHandler so /v1/pending-messages/compact performs actual
LLM summarization (keep 15 recent + summary) instead of hard delete.

Add rows-affected guard in Compact() to prevent duplicate summaries
when concurrent compactions race on the same key.

cmd/gateway_http_handlers.go

@@ -71,7 +71,7 @@ func wireHTTP(stores *store.Stores, token string, msgBus *bus.MessageBus, toolsR
 	}
 
 	if stores != nil && stores.PendingMessages != nil {
-		pendingMessagesH = httpapi.NewPendingMessagesHandler(stores.PendingMessages, token)
+		pendingMessagesH = httpapi.NewPendingMessagesHandler(stores.PendingMessages, token, providerReg)
 	}
 
 	return agentsH, skillsH, tracesH, mcpH, customToolsH, channelInstancesH, providersH, delegationsH, builtinToolsH, pendingMessagesH