fix(agent): immediately transfer accidents involving three or more vehicles

evals/README.md

@@ -11,6 +11,12 @@ The original case comments retain their historical workflow versions.
 
 Add YAML files anywhere under `evals/cases/`:
 
+- `complex_vehicle/`: three-car collisions must immediately return `0003`
+  with the approved handoff wording in both client modes. Assert the first
+  explicit three-car turn transfers, extracts count/cause, leaves unknown
+  injury/time/scene fields absent, and asks no further collection or photo questions.
+  Semantic probes additionally cover four cars, a known count in an otherwise
+  empty form, new corrections, uncertain counts, unrelated vehicles, and lower bounds.
 - `customer_feedback/`: replay repeated connection checks and the customer's
   complete single-car collision description in both client modes. A clearly
   described motor vehicle hitting a fixed object, without other vehicle

evals/cases/complex_vehicle/browser_addon_three_immediate.yaml

@@ -0,0 +1,20 @@
+name: browser_addon_complex_three_immediate
+clientMode: browser_addon
+
+# 用户提供的三车事故反馈：在首次明确三车时立即转人工。
+steps:
+  - input: 新对话
+    expect: {stageCode: "browser_addon.1001"}
+  - input: 【继续办理】
+    expect: {stageCode: "browser_addon.1002"}
+  - input: 你好你好喂喂喂。
+    expect:
+      stageCode: "browser_addon.1002"
+      formAbsent: [vehicle_count, has_injury]
+  - input: 在高速上，三辆车子追尾了。
+    expect:
+      stageCode: "browser_addon.0003"
+      form: {vehicle_count: 3, accident_cause: 追尾}
+      formAbsent: [has_injury, has_non_motor_vehicle_hit, accident_time, is_on_scene]
+      replyMatches: "收到，您描述的是三辆机动车追尾，属于需要人工处理的复杂事故，我将立即为您转接人工警员。请保持通话。"
+      replyNotMatches: "(请问|拍照|这个时间对吗|能否)"

evals/cases/complex_vehicle/direct_three_immediate.yaml

@@ -0,0 +1,20 @@
+name: direct_complex_three_immediate
+clientMode: direct
+
+# 用户提供的三车事故反馈：在首次明确三车时立即转人工。
+steps:
+  - input: 新对话
+    expect: {stageCode: "1001"}
+  - input: 【继续办理】
+    expect: {stageCode: "1002"}
+  - input: 你好你好喂喂喂。
+    expect:
+      stageCode: "1002"
+      formAbsent: [vehicle_count, has_injury]
+  - input: 在高速上，三辆车子追尾了。
+    expect:
+      stageCode: "0003"
+      form: {vehicle_count: 3, accident_cause: 追尾}
+      formAbsent: [has_injury, has_non_motor_vehicle_hit, accident_time, is_on_scene]
+      replyMatches: "收到，您描述的是三辆机动车追尾，属于需要人工处理的复杂事故，我将立即为您转接人工警员。请保持通话。"
+      replyNotMatches: "(请问|拍照|这个时间对吗|能否)"

evals/prompt_probes.py

@@ -27,6 +27,27 @@ def probes():
     known_form = dict(accident_cause='其他：车辆碰撞', has_injury=False,
                       has_non_motor_vehicle_hit=False, accident_time=TIME, is_on_scene=True)
     return [
+        dict(name='complex_three_original', user='在高速上，三辆车子追尾了。', history=[],
+             code='0003', count=3, not_matches='(请问|是否.*[？?]|拍照|这个时间对吗)',
+             matches='三辆机动车追尾.*复杂事故.*立即.*转接人工警员'),
+        dict(name='complex_four_missing_everything', user='四辆汽车发生连环碰撞。', history=[],
+             code='0003', count=4, not_matches='(请问|拍照|这个时间对吗)'),
+        dict(name='complex_form_only_three', user='我不在现场，没法拍照。', history=[],
+             form={'vehicle_count': 3}, code='0003', count=3,
+             not_matches='(请问|能否|拍照|这个时间对吗)'),
+        dict(name='complex_new_count_overrides_form', user='不是两辆，是三辆汽车追尾。', history=[],
+             form={'vehicle_count': 2}, code='0003', count=3, not_matches='(请问|拍照)'),
+        dict(name='complex_correction_back_to_two', user='刚才说错了，不是三辆，是两辆汽车追尾。',
+             history=[], form={'vehicle_count': 3}, code='1002', count=2, contains='受伤'),
+        dict(name='complex_at_least_three', user='至少三辆机动车发生碰撞，总共多少还不清楚。', history=[],
+             code='0003', count_absent=True, not_matches='(请问|拍照|这个时间对吗)'),
+        dict(name='complex_uncertain_three', user='可能是三辆汽车追尾，我没看清。', history=[],
+             code='1002', count_absent=True),
+        dict(name='complex_irrelevant_three', user='我倒车撞到护栏，旁边停着三辆车，和事故无关。', history=[],
+             code='1002', count=1, contains='受伤'),
+        dict(name='complex_time_pending', user='还有第三辆汽车参与追尾，是三辆。',
+             history=[{'role':'assistant','content':CONFIRM}], code='0003', count=3,
+             not_matches='(这个时间对吗|请问|拍照)'),
         dict(name='feedback_single_motor_fixed_object', user='我现在还在事故现场。', history=[
             {'role':'user','content':'我的车子是自己的小轿车，撞到了路边围栏。'},
             {'role':'user','content':'没有人员伤伤就车子撞了。'},