diff --git a/pyproject.toml b/pyproject.toml
index 31a5d2d..8f51fe7 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -13,7 +13,10 @@ dependencies = ["pydantic>=2"]
 hub = ["datasets"]            # HuggingFace-hosted datasets
 parquet = ["pyarrow"]         # parquet sources (ModelScope/HF raw mirrors)
 math = ["sympy", "pylatexenc"]  # symbolic math grading (aime/math family), official PRM800K logic
-exec = ["numpy", "scipy"]     # DROP official aligner (linear_sum_assignment) & code benches
+exec = ["numpy", "scipy"]     # DROP official aligner (linear_sum_assignment)
+bfcl = ["bfcl-eval", "soundfile"]  # OFFICIAL bfcl ast_checker (heavy: pulls 5 cloud SDKs +
+                                   # qwen-agent; native scorer is the dependency-free default)
+all = ["datasets", "pyarrow", "sympy", "pylatexenc", "numpy", "scipy"]  # everything conflict-free
 
 [project.scripts]
 evalharness = "evalharness.cli:main"