simplify Athena runtime and centralize MCP management

dev/test_local.sh

@@ -183,6 +183,34 @@ echo "$RESP"
 echo "$RESP" | grep -q "data: " && echo "$RESP" | grep -q "\[DONE\]" \
   && ok "SSE-Stream mit [DONE] erhalten" || bad "Streaming"
 
+echo "== Test 4b: Client-Abbruch gibt den Router-Slot frei"
+command curl -H "Authorization: Bearer $TEST_ROUTER_KEY" -sfN \
+  "$BASE/v1/chat/completions" -H "Content-Type: application/json" \
+  -d '{"model":"qwen-fast","stream":true,"mock_stream_delay":2,"messages":[{"role":"user","content":"Abbruch"}]}' \
+  >/tmp/aborted-stream.txt 2>/dev/null &
+ABORT_PID=$!
+sleep 0.4
+kill "$ABORT_PID" 2>/dev/null || true
+wait "$ABORT_PID" 2>/dev/null || true
+for _ in $(seq 1 30); do
+  ACTIVE=$(curl -sf "$BASE/status" | python3 -c 'import json,sys; print(json.load(sys.stdin)["qwen"]["active_chats"])')
+  [[ $ACTIVE == 0 ]] && break
+  sleep 0.1
+done
+CODE=$(curl -s -o /tmp/after-abort.json -w "%{http_code}" "$BASE/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"qwen-fast","messages":[{"role":"user","content":"noch frei?"}]}')
+[[ ${ACTIVE:-1} == 0 && $CODE == 200 ]] \
+  && ok "abgebrochener Stream gibt Lease frei; Folgerequest erfolgreich" \
+  || bad "Stream-Abbruch hinterließ active_chats=${ACTIVE:-?}, HTTP $CODE"
+
+if [[ ${ROUTER_TEST_QUICK:-0} == 1 ]]; then
+  echo
+  echo "== Schnellergebnis: $PASS bestanden, $FAIL fehlgeschlagen =="
+  [[ $FAIL -eq 0 ]]
+  exit
+fi
+
 # --- 5. Tool Calls -----------------------------------------------------------------
 echo "== Test 5: Tool Calls"
 RESP=$(curl -sf "$BASE/v1/chat/completions" -H "Content-Type: application/json" \