feat(v1): relax fall sensitivity for low overhead cameras

Adds configurable event.require_rapid_drop (default off), require_lower_body
(default off) and horizontal_angle_threshold_degrees (default 45). With the
lenient defaults a sustained horizontal pose alone enters SUSPECT and confirms
after the confirm window, which is now the main false-positive guard; missing
knees/ankles no longer reject the pose. Thresholds flow into config_version.
End-to-end smoke confirms a lying pose; 70 tests pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

v1/evidence.py

@@ -7,7 +7,9 @@ from typing import Optional
 from v1.pose import PersonPose
 
 
-_REQUIRED_JOINTS = (5, 6, 11, 12, 13, 14, 15, 16)
+_TORSO_JOINTS = (5, 6, 11, 12)          # shoulders and hips (used by the geometry)
+_LOWER_JOINTS = (13, 14, 15, 16)        # knees and ankles (often occluded in a fall)
+_REQUIRED_JOINTS = _TORSO_JOINTS + _LOWER_JOINTS
 
 
 @dataclass(frozen=True)
@@ -29,7 +31,7 @@ class PoseEvidence:
 
 
 def assess_pose_quality(
-    pose: Optional[PersonPose], threshold: float
+    pose: Optional[PersonPose], threshold: float, require_lower_body: bool = True
 ) -> PoseQuality:
     if not 0.0 <= threshold <= 1.0:
         raise ValueError("threshold must be between 0 and 1")
@@ -40,7 +42,8 @@ def assess_pose_quality(
     visible_count = sum(
         point.confidence >= threshold for point in pose.keypoints
     )
-    if any(pose.keypoints[index].confidence < threshold for index in _REQUIRED_JOINTS):
+    required = _REQUIRED_JOINTS if require_lower_body else _TORSO_JOINTS
+    if any(pose.keypoints[index].confidence < threshold for index in required):
         return PoseQuality(False, "required_joint_low_confidence", visible_count)
     return PoseQuality(True, "accepted", visible_count)