fix high priority issues

bincio/extract/metrics.py

@@ -112,10 +112,11 @@ def compute_mmp(pts: list[DataPoint], started_at: datetime) -> Optional[list[lis
     [duration_s, avg_watts] pairs (integers), or None when the activity has no
     power data.  Only durations shorter than the total activity are included.
     """
-    # 1 Hz downsample: at most one sample per second, skip sub-second duplicates.
-    # Seconds without a recorded sample are omitted (not zero-filled) so that
-    # paused-recording gaps don't silently lower power averages.
-    power_1hz: list[int] = []
+    # Build a dense 1 Hz power array with gaps zero-filled.
+    # Zero-filling is the standard approach (matches GoldenCheetah / WKO):
+    # a recording gap counts as 0 W so windows cannot silently span pauses
+    # and inflate MMP values.
+    sparse: dict[int, int] = {}
     last_t = -1
     for p in pts:
         t = int((p.timestamp - started_at).total_seconds())
@@ -123,11 +124,15 @@ def compute_mmp(pts: list[DataPoint], started_at: datetime) -> Optional[list[lis
             continue
         last_t = t
         if p.power_w is not None:
-            power_1hz.append(p.power_w)
+            sparse[t] = p.power_w
 
-    if len(power_1hz) < 2:
+    if len(sparse) < 2:
         return None
 
+    t_min = min(sparse)
+    t_max = max(sparse)
+    power_1hz: list[int] = [sparse.get(t, 0) for t in range(t_min, t_max + 1)]
+
     n = len(power_1hz)
     results: list[list[int]] = []
 
@@ -166,17 +171,27 @@ def compute_best_efforts(
     """
     targets = BEST_EFFORT_DISTANCES.get(sport, [])
 
-    # Build 1 Hz speed (km/h) and elevation (m) arrays — same downsampling as timeseries.py
-    speed_1hz: list[float] = []
-    ele_1hz: list[Optional[float]] = []
+    # Build dense 1 Hz speed (km/h) and elevation (m) arrays with gap zero-filling.
+    # Zero-filling speed gaps (0 km/h) prevents best-effort windows from spanning
+    # recording pauses and producing artificially fast times.
+    sparse_speed: dict[int, float] = {}
+    sparse_ele: dict[int, Optional[float]] = {}
     last_t = -1
     for p in pts:
         t = int((p.timestamp - started_at).total_seconds())
         if t < 0 or t == last_t:
             continue
         last_t = t
-        speed_1hz.append(p.speed_kmh if p.speed_kmh is not None else 0.0)
-        ele_1hz.append(p.elevation_m)
+        sparse_speed[t] = p.speed_kmh if p.speed_kmh is not None else 0.0
+        sparse_ele[t] = p.elevation_m
+
+    if not sparse_speed:
+        return None, None
+
+    t_min = min(sparse_speed)
+    t_max = max(sparse_speed)
+    speed_1hz: list[float] = [sparse_speed.get(t, 0.0) for t in range(t_min, t_max + 1)]
+    ele_1hz: list[Optional[float]] = [sparse_ele.get(t) for t in range(t_min, t_max + 1)]
 
     best_efforts: Optional[list[list[float]]] = None
     if targets and speed_1hz:

bincio/extract/writer.py

@@ -83,6 +83,13 @@ def write_activity(
     }
 
     json_path = acts_dir / f"{activity_id}.json"
+    # Collision guard: if a *different* activity already has this ID, append a
+    # short hash suffix to disambiguate (same hash = idempotent re-extract).
+    if json_path.exists():
+        existing = json.loads(json_path.read_text(encoding="utf-8"))
+        if existing.get("source_hash") != activity.source_hash:
+            activity_id = f"{activity_id}-{activity.source_hash[-6:]}"
+            json_path = acts_dir / f"{activity_id}.json"
     json_path.write_text(json.dumps(detail, indent=2, ensure_ascii=False))
 
     # ── GeoJSON track ────────────────────────────────────────────────────────