feat(adapter): implement segment quality filters

ai_mouse/data_adapters/balabit.py

@@ -124,9 +124,72 @@ def filter_segments(
     min_dist: int,
     max_span_ms: int,
     max_gap_ms: int,
+    coord_max: int = 5000,
 ) -> list[Segment]:
-    """Stub — implemented in Task 5."""
-    raise NotImplementedError
+    """Drop segments that fail any quality check.
+
+    A segment is dropped if any of these are true:
+    - len(events) < min_events
+    - Euclidean dist(events[0], (click_x, click_y)) < min_dist
+    - events[-1].t_ms - events[0].t_ms > max_span_ms
+    - any adjacent Move pair has dt > max_gap_ms (sampling drop-out)
+    - any coord (start/end/click) outside [0, coord_max]
+    - total arc length < min_dist (high-frequency jitter only)
+
+    Args:
+        segments: Candidate segments.
+        min_events: Minimum number of Move events.
+        min_dist: Minimum start→click pixel distance AND minimum total arc length.
+        max_span_ms: Maximum time span of the segment (events[-1] - events[0]).
+        max_gap_ms: Maximum allowed gap between adjacent Move events.
+        coord_max: Maximum allowed pixel coordinate value (5000 catches multi-monitor anomalies).
+
+    Returns:
+        Filtered list, original order preserved.
+    """
+    import math
+
+    keep: list[Segment] = []
+    for seg in segments:
+        if len(seg.events) < min_events:
+            continue
+
+        sx, sy = seg.events[0].x, seg.events[0].y
+        ex, ey = seg.click_x, seg.click_y
+
+        # Coord range check
+        if any(c < 0 or c > coord_max for c in (sx, sy, ex, ey)):
+            continue
+
+        # Endpoint distance
+        dist = math.hypot(ex - sx, ey - sy)
+        if dist < min_dist:
+            continue
+
+        # Time span
+        span = seg.events[-1].t_ms - seg.events[0].t_ms
+        if span > max_span_ms:
+            continue
+
+        # Gap check + total arc length
+        total_arc = 0.0
+        bad_gap = False
+        for i in range(1, len(seg.events)):
+            dt = seg.events[i].t_ms - seg.events[i - 1].t_ms
+            if dt > max_gap_ms:
+                bad_gap = True
+                break
+            dx = seg.events[i].x - seg.events[i - 1].x
+            dy = seg.events[i].y - seg.events[i - 1].y
+            total_arc += math.hypot(dx, dy)
+        if bad_gap:
+            continue
+        if total_arc < min_dist:
+            continue
+
+        keep.append(seg)
+
+    return keep
 
 
 def process_session(

tests/test_balabit_adapter.py

@@ -185,3 +185,79 @@ class TestSegmentByClicks:
         # Drag event should not appear in seg.events
         assert all(e.state == "Move" for e in segments[0].events)
         assert len(segments[0].events) == 2
+
+
+class TestFilterSegments:
+    def _seg(self, events_data: list[tuple[int, int, int]], click=(500, 500), session="s"):
+        """events_data: list of (t_ms, x, y) tuples."""
+        from ai_mouse.data_adapters.balabit import MouseEvent, Segment
+        events = [MouseEvent(t_ms=t, button="NoButton", state="Move", x=x, y=y)
+                  for (t, x, y) in events_data]
+        click_t = events[-1].t_ms + 50 if events else 100
+        return Segment(events=events, click_x=click[0], click_y=click[1],
+                       click_t_ms=click_t, session_id=session)
+
+    def test_drops_segment_with_too_few_events(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        seg = self._seg([(0, 100, 100), (50, 105, 105)])  # 2 events, min=5
+        result = filter_segments([seg], min_events=5, min_dist=10,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert result == []
+
+    def test_drops_segment_with_short_distance(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # Start (100,100), end click=(105,100) → dist=5, min_dist=50
+        events = [(i*10, 100+i, 100) for i in range(10)]
+        seg = self._seg(events, click=(105, 100))
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert result == []
+
+    def test_drops_segment_with_too_long_span(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # Span 6000ms, max_span=5000
+        events = [(0, 100, 100), (2000, 200, 200), (4000, 300, 300), (6000, 400, 400),
+                  (6010, 410, 400), (6020, 420, 400)]
+        seg = self._seg(events, click=(500, 500))
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=10000)
+        assert result == []
+
+    def test_drops_segment_with_gap(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # Gap of 500ms between events 2 and 3, max_gap=200
+        events = [(0, 100, 100), (50, 110, 110), (100, 120, 120),
+                  (600, 200, 200), (650, 210, 210), (700, 220, 220)]
+        seg = self._seg(events, click=(300, 300))
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert result == []
+
+    def test_drops_segment_with_out_of_range_coords(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # x=10000 out of range
+        events = [(i*10, 10000, 100) for i in range(6)]
+        seg = self._seg(events, click=(10100, 100))
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert result == []
+
+    def test_drops_segment_with_short_arc_length(self):
+        """Total arc < 50 even though endpoints are far → high-frequency jitter only."""
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # Tiny back-and-forth with click 100px away — unrealistic, drop it
+        events = [(i*10, 100 + (i % 2), 100) for i in range(10)]
+        seg = self._seg(events, click=(200, 100))
+        # arc length = sum of |Δp| ≈ 9 (alternating ±1) which is < 50
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert result == []
+
+    def test_keeps_valid_segment(self):
+        from ai_mouse.data_adapters.balabit import filter_segments
+        # Smooth 100→500 px straight line, 10 events, span 500ms
+        events = [(i*50, 100 + i*40, 100) for i in range(10)]
+        seg = self._seg(events, click=(500, 100))
+        result = filter_segments([seg], min_events=5, min_dist=50,
+                                  max_span_ms=5000, max_gap_ms=200)
+        assert len(result) == 1