CI runs nisse-review's live test

scripts/e2e.sh ran only test_end_to_end_loop.py, and the integration step
excludes e2e-marked tests, so test_review_live.py (M7.3) never ran in CI.
The script now runs every e2e-marked test under tests/integration, and the
review test is a smoke test: about a minute on the local model, and the only
check that the review account, its token and its read-only refusal work.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

scripts/e2e.sh

@@ -53,7 +53,8 @@ print(i["spend"], i.get("max_budget"))' 2>/dev/null) || echo "? ?"
 }
 read -r before budget < <(spend)
 status=0
-uv run pytest -m e2e -rs tests/integration/test_end_to_end_loop.py "$@" || status=$?
+# Every e2e-marked test: the agents' loops and nisse-review's live review.
+uv run pytest -m e2e -rs tests/integration "$@" || status=$?
 read -r after _ < <(spend)
 python3 -c "
 b, a, cap = '$before', '$after', '$budget'