verbose live UI + tool-level SSE events + Groq default + regression tests

api/evals/run_evals.py

@@ -0,0 +1,11 @@
+"""BIRD `financial` golden-set runner.
+
+Stub — the eval harness lands once the Plan + Analyses + Tools are in place.
+"""
+
+def main() -> None:
+    raise SystemExit("api/evals/run_evals.py is a stub; agent stack not yet built")
+
+
+if __name__ == "__main__":
+    main()