From f844775f1ea7ee72371f8b4942f3607fac903fdb Mon Sep 17 00:00:00 2001
From: sora <2075279110@qq.com>
Date: Thu, 17 Sep 2026 09:24:54 +0000
Subject: [PATCH] tau2 scorer: read the composite 'reward' field

tau2's current reward_info carries 'reward' (composite) + db_check /
action_checks; the scorer read the old environment_reward /
communication_reward split that no longer exists -- simulations scored
1.0 came out 0.0. Fallback to the old split kept for older engines.

Co-Authored-By: Claude <noreply@anthropic.com>
---
 evalharness/eval/recipes/agent.py | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/evalharness/eval/recipes/agent.py b/evalharness/eval/recipes/agent.py
index 73e1d7d..6a90ba3 100644
--- a/evalharness/eval/recipes/agent.py
+++ b/evalharness/eval/recipes/agent.py
@@ -262,16 +262,23 @@ def swe_bench_verified():
 
 
 def _tau2_reward(pred, target, sample, ctx):
-    """Score from the official engine's reward_info (env_state)."""
+    """Score from the official engine's reward_info (env_state).
+
+    Current tau2 reward_info carries the COMPOSITE 'reward' plus detail
+    fields (db_check / action_checks / communicate_checks); the old
+    environment_reward/communication_reward split no longer exists."""
     env_state = ctx.params.get('env_state') or {}
     rewards = env_state.get('tau2_rewards') or {}
-    env_r = rewards.get('environment_reward')
-    comm_r = rewards.get('communication_reward')
-    vals = [r for r in (env_r, comm_r) if isinstance(r, (int, float))]
-    score = float(sum(vals) / len(vals)) if vals else 0.0
-    return ({'acc': score}, {'acc': {'mode': 'official_tau2',
-                                     'env_reward': env_r,
-                                     'comm_reward': comm_r}})
+    r = rewards.get('reward')
+    if not isinstance(r, (int, float)):
+        vals = [v for v in (rewards.get('environment_reward'),
+                            rewards.get('communication_reward'))
+                if isinstance(v, (int, float))]
+        r = sum(vals) / len(vals) if vals else 0.0
+    return ({'acc': float(r)}, {'acc': {'mode': 'official_tau2',
+                                        'reward': r,
+                                        'db_check': rewards.get('db_check'),
+                                        'note': str((rewards.get('info') or {}).get('note', ''))[:120]}})
 
 
 @register_eval('tau2_bench')