diff --git a/evalharness/cli.py b/evalharness/cli.py
index 000ede1..a5df6ae 100644
--- a/evalharness/cli.py
+++ b/evalharness/cli.py
@@ -788,8 +788,12 @@ def _cmd_eval_run(args) -> int:
             # YAML config: per-bench generation params, AUTO-LOADED
             # (single .yaml in config/ = the default; --config overrides)
             bench_cfg = _load_bench_cfg(args, name)
+            # env: per-bench from YAML, CLI --env as fallback/default
+            _env_cfg = bench_cfg.pop('env', '') or ''
+            if _env_cfg:
+                args.env = _env_cfg
             # strip non-generation keys (they go to run_eval kwargs)
-            for k in ('judge', 'judge_url', 'env', 'max_turns',
+            for k in ('judge', 'judge_url', 'max_turns',
                       'limit', 'limit_per_task', 'concurrency'):
                 bench_cfg.pop(k, None)
 
diff --git a/evalharness/config/default.yaml b/evalharness/config/default.yaml
index 219a3f4..3ce0253 100644
--- a/evalharness/config/default.yaml
+++ b/evalharness/config/default.yaml
@@ -54,7 +54,9 @@ openai_mrcr:
   max_input_tokens: 128000
 bfcl_v3:
   max_tokens: 4096
+  env: bfcl_mock          # agent 模式：工具调用轨迹 + 官方 AST 判分
 general_fc:
   max_tokens: 4096
 tau2_bench:
   max_tokens: 16384
+  env: tau2_official      # agent 模式：官方引擎