CHANGELOG.md

@@ -6,6 +6,17 @@ All notable changes to seismo-relay are documented here.
 
 ## [Unreleased]
 
+### Fixed
+- **Histogram/waveform twin matching is now interval-based** (`find_twins`). A real
+  trigger is recorded twice — as a triggered waveform (stamped at the trigger instant)
+  and inside the scheduled histogram whose interval contains it (stamped at the 7am/7pm
+  interval start) — so the two twins can be **hours apart**. The old ±5-minute window
+  silently missed them, which broke review propagation (flagging one twin didn't flag its
+  twin). Twins are now matched by same serial + identical `peak_vector_sum` + opposite
+  record type + the waveform falling within the histogram's interval (bounded by the next
+  same-serial histogram). `window_seconds` is retained but ignored. Fixes terra-view #102
+  sub-task 2.
+
 ---
 
 ## v0.26.0 — 2026-08-27

sfm/database.py

@@ -603,56 +603,107 @@ class SeismoDb:
             ).fetchall()
         return [dict(r) for r in rows]
 
-    def find_twins(self, event_id: str, *, window_seconds: int = 300) -> list[dict]:
+    def find_twins(self, event_id: str, *, window_seconds: int | None = None) -> list[dict]:
         """
-        Find this event's histogram/waveform twin(s): rows sharing the same
-        serial and an identical peak_vector_sum, whose timestamp falls
-        within ``window_seconds`` of this event's timestamp.  Excludes the
-        event itself.  Returns [] if the event or any required field
-        (serial / peak_vector_sum / timestamp) is missing.
+        Find this event's histogram/waveform twin(s): the SAME physical event
+        recorded both as a scheduled histogram and as a triggered waveform.
 
-        Caveat: identical-PVS matching is a proxy for "same physical event
-        recorded twice," not a guarantee. In the rare case where the device
-        clamps/saturates PVS (clamped to sqrt(3) * geo_range), two distinct
-        saturated events on the same serial within the window can share the
-        same clamped PVS value and be matched as twins even though they are
-        different events. This is harmless in practice — false_trigger/
-        reviewed_real are derived/index columns re-derivable from the
-        sidecar source of truth — but worth knowing if twin counts look
-        surprising on a saturated/clamped run.
+        A real trigger is captured twice — once as a triggered waveform (stamped
+        at the trigger instant) and once inside the scheduled histogram whose
+        interval contains it (stamped at the histogram's interval start, e.g. the
+        7am/7pm call-in). The two can be HOURS apart in time yet report the same
+        serial and identical peak_vector_sum. Twins are therefore matched by:
+
+          * same serial,
+          * identical peak_vector_sum,
+          * OPPOSITE record type (one histogram, one waveform), and
+          * the waveform's timestamp falls within the histogram's interval —
+            from a histogram's timestamp up to the next histogram (same serial).
+
+        This replaces the old ±``window_seconds`` heuristic, which silently
+        missed twins more than a few minutes apart (a histogram's interval-start
+        stamp and the trigger instant routinely differ by hours). ``window_seconds``
+        is still accepted for backward compatibility but is ignored.
+
+        Returns [] if the event or a required field (serial / peak_vector_sum /
+        timestamp) is missing.
+
+        Caveat: identical-PVS matching remains a proxy for "same physical event"
+        — if the device clamps/saturates PVS (to sqrt(3) * geo_range), two
+        distinct saturated events could share a PVS. The added opposite-type and
+        interval constraints make a false pairing far less likely than the old
+        time-window match, and false_trigger/reviewed_real stay re-derivable from
+        the sidecar source of truth.
         """
+        def _parse(ts):
+            if not ts:
+                return None
+            try:
+                return datetime.datetime.fromisoformat(str(ts).replace(" ", "T"))
+            except ValueError:
+                return None
+
+        def _is_hist(rt):
+            return str(rt or "").lower().startswith("hist")
+
         row = self.get_event(event_id)
         if not row:
             return []
-        serial = row.get("serial"); pvs = row.get("peak_vector_sum"); ts = row.get("timestamp")
-        if serial is None or pvs is None or not ts:
+        serial = row.get("serial"); pvs = row.get("peak_vector_sum")
+        t_target = _parse(row.get("timestamp"))
+        if serial is None or pvs is None or t_target is None:
             return []
-        try:
-            t = datetime.datetime.fromisoformat(ts.replace(" ", "T"))
-        except ValueError:
-            return []
-        lo = (t - datetime.timedelta(seconds=window_seconds)).isoformat()
-        hi = (t + datetime.timedelta(seconds=window_seconds)).isoformat()
-        with self._connect() as conn:
-            rows = conn.execute(
-                "SELECT * FROM events WHERE serial=? AND id!=? AND peak_vector_sum=? "
-                "AND timestamp BETWEEN ? AND ?",
-                (serial, event_id, pvs, lo, hi),
-            ).fetchall()
-        return [dict(r) for r in rows]
+        target_hist = _is_hist(row.get("record_type"))
 
-    def propagate_review_to_twins(self, event_id: str, *, window_seconds: int = 300) -> list[str]:
+        with self._connect() as conn:
+            cand_rows = [dict(r) for r in conn.execute(
+                "SELECT * FROM events WHERE serial=? AND id!=? AND peak_vector_sum=?",
+                (serial, event_id, pvs)).fetchall()]
+            hist_ts = [r["timestamp"] for r in conn.execute(
+                "SELECT timestamp FROM events WHERE serial=? AND lower(record_type) LIKE 'hist%'",
+                (serial,)).fetchall()]
+
+        # Histogram interval-start times for this serial, sorted, to bound intervals.
+        starts = sorted(x for x in (_parse(t) for t in hist_ts) if x is not None)
+
+        def _interval_end(h_start):
+            # The next histogram strictly after h_start bounds the interval; else open-ended.
+            for x in starts:
+                if x > h_start:
+                    return x
+            return None
+
+        def _covers(h_start, w_time):
+            end = _interval_end(h_start)
+            return h_start <= w_time and (end is None or w_time < end)
+
+        twins = []
+        for c in cand_rows:
+            if _is_hist(c.get("record_type")) == target_hist:
+                continue  # twins are strictly cross-type (one histogram, one waveform)
+            c_time = _parse(c.get("timestamp"))
+            if c_time is None:
+                continue
+            h_start, w_time = (t_target, c_time) if target_hist else (c_time, t_target)
+            if _covers(h_start, w_time):
+                twins.append(c)
+        return twins
+
+    def propagate_review_to_twins(self, event_id: str, *, window_seconds: int | None = None) -> list[str]:
         """
         Copy this event's `false_trigger`/`reviewed_real` columns onto each
         of its histogram/waveform twins (see `find_twins`), so flagging one
         twin flags both.  Returns the list of twin ids updated.
+
+        ``window_seconds`` is accepted for backward compatibility but ignored;
+        twin matching is now interval-based (see `find_twins`).
         """
         row = self.get_event(event_id)
         if not row:
             return []
         ft = 1 if row.get("false_trigger") else 0
         real = 1 if row.get("reviewed_real") else 0
-        twins = self.find_twins(event_id, window_seconds=window_seconds)
+        twins = self.find_twins(event_id)
         moved = []
         with self._connect() as conn:
             for tw in twins:

tests/test_find_twins.py

@@ -1,33 +1,71 @@
-import datetime
+import sqlite3
 from sfm.database import SeismoDb
 from minimateplus.models import Event, Timestamp
 
 
-def _ins(db, key, serial, pvs, ts):
+def _ins(db, key, serial, pvs, ts, record_type="Waveform"):
     ev = Event(index=0)
     ev._waveform_key = bytes.fromhex(key)
     ev.timestamp = ts
-    # peak_vector_sum comes from peak_values; simplest: insert then UPDATE pvs directly
     db.insert_events([ev], serial=serial)
     row = [r for r in db.query_events(serial=serial) if r["waveform_key"] == key][0]
-    import sqlite3
     with sqlite3.connect(db.db_path) as c:
-        c.execute("UPDATE events SET peak_vector_sum=? WHERE id=?", (pvs, row["id"]))
+        c.execute("UPDATE events SET peak_vector_sum=?, record_type=? WHERE id=?",
+                  (pvs, record_type, row["id"]))
     return row["id"]
 
 
-def test_find_twins_matches_same_serial_pvs_near_time(tmp_path):
+def _ts(hour, minute, second=0, day=25):
+    return Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=day,
+                     hour=hour, minute=minute, second=second)
+
+
+def test_histogram_and_waveform_twin_across_hours(tmp_path):
+    # The real UM12947 case: histogram stamped at its 7pm interval start, the
+    # triggered waveform 75 min later — same serial + identical PVS. The old
+    # ±5-min window missed this; interval matching catches it, both directions.
     db = SeismoDb(tmp_path / "s.db")
-    base = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=5)
-    twin = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=45)
-    far = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=21, minute=0, second=0)
-    # d needs a timestamp distinct from `twin` (UNIQUE(serial, timestamp) would
-    # otherwise collide with b and UPSERT onto its row instead of inserting a
-    # new one) while staying near `base` in time.
-    near = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=44)
-    a = _ins(db, "01110001", "BE1", 0.4763, base)
-    b = _ins(db, "01110002", "BE1", 0.4763, twin)   # twin: same serial+pvs, 40s apart
-    c = _ins(db, "01110003", "BE1", 0.4763, far)    # same pvs but >window away
-    d = _ins(db, "01110004", "BE1", 0.9999, near)   # near time but different pvs
-    ids = {r["id"] for r in db.find_twins(a, window_seconds=300)}
-    assert ids == {b}
+    hist_pm = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 31, 17), "Histogram")
+    wave    = _ins(db, "01110002", "BE1", 0.4763, _ts(20, 46, 44), "Waveform")
+    _ins(db, "01110003", "BE1", 0.0100, _ts(7, 0, 0, day=26), "Histogram")  # bounds the interval
+    assert {r["id"] for r in db.find_twins(hist_pm)} == {wave}
+    assert {r["id"] for r in db.find_twins(wave)} == {hist_pm}
+
+
+def test_same_type_not_twinned(tmp_path):
+    # Two waveforms, same serial + PVS, seconds apart → NOT twins (cross-type only).
+    db = SeismoDb(tmp_path / "s.db")
+    a = _ins(db, "01110001", "BE1", 0.4763, _ts(20, 19, 5), "Waveform")
+    _ins(db, "01110002", "BE1", 0.4763, _ts(20, 19, 45), "Waveform")
+    assert db.find_twins(a) == []
+
+
+def test_waveform_matches_only_the_containing_interval(tmp_path):
+    # Two overnight intervals with the same PVS; a waveform in the SECOND interval
+    # must twin with that histogram, never the first — even though PVS matches both.
+    db = SeismoDb(tmp_path / "s.db")
+    h1 = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0, day=25), "Histogram")
+    h2 = _ins(db, "01110002", "BE1", 0.4763, _ts(7, 0, 0, day=26), "Histogram")
+    w = _ins(db, "01110003", "BE1", 0.4763, _ts(8, 0, 0, day=26), "Waveform")
+    assert {r["id"] for r in db.find_twins(w)} == {h2}
+    assert w not in {r["id"] for r in db.find_twins(h1)}
+
+
+def test_different_pvs_not_twinned(tmp_path):
+    db = SeismoDb(tmp_path / "s.db")
+    h = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0), "Histogram")
+    _ins(db, "01110002", "BE1", 0.9999, _ts(20, 0, 0), "Waveform")  # different PVS
+    assert db.find_twins(h) == []
+
+
+def test_open_ended_latest_interval(tmp_path):
+    # A waveform after the latest histogram (nothing bounds the interval) still twins.
+    db = SeismoDb(tmp_path / "s.db")
+    h = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0), "Histogram")
+    w = _ins(db, "01110002", "BE1", 0.4763, _ts(23, 30, 0), "Waveform")
+    assert {r["id"] for r in db.find_twins(h)} == {w}
+
+
+def test_missing_fields_returns_empty(tmp_path):
+    db = SeismoDb(tmp_path / "s.db")
+    assert db.find_twins("nonexistent-id") == []

tests/test_twin_propagation.py

@@ -3,31 +3,34 @@ from sfm.database import SeismoDb
 from minimateplus.models import Event, Timestamp
 
 
-def _ins(db, key, serial, pvs, ts):
+def _ins(db, key, serial, pvs, ts, record_type="Waveform"):
     ev = Event(index=0)
     ev._waveform_key = bytes.fromhex(key)
     ev.timestamp = ts
-    # peak_vector_sum comes from peak_values; simplest: insert then UPDATE pvs directly
     db.insert_events([ev], serial=serial)
     row = [r for r in db.query_events(serial=serial) if r["waveform_key"] == key][0]
     with sqlite3.connect(db.db_path) as c:
-        c.execute("UPDATE events SET peak_vector_sum=? WHERE id=?", (pvs, row["id"]))
+        c.execute("UPDATE events SET peak_vector_sum=?, record_type=? WHERE id=?",
+                  (pvs, record_type, row["id"]))
     return row["id"]
 
 
-def test_propagate_copies_flags_to_twins(tmp_path):
+def _ts(hour, minute, second=0, day=25):
+    return Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=day,
+                     hour=hour, minute=minute, second=second)
+
+
+def test_propagate_copies_flags_across_hours_apart_twins(tmp_path):
+    # Flagging the waveform FT propagates to its histogram twin 75 min earlier
+    # (the interval matcher pairs them; the old ±5-min window would have missed it).
     db = SeismoDb(tmp_path / "s.db")
-    base = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=5)
-    twin = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=45)
-    other = Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=25, hour=20, minute=19, second=44)
+    hist  = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 31, 17), "Histogram")
+    wave  = _ins(db, "01110002", "BE1", 0.4763, _ts(20, 46, 44), "Waveform")   # twin, 75 min later
+    other = _ins(db, "01110003", "BE1", 0.9999, _ts(20, 20, 0),  "Waveform")   # different pvs
 
-    primary_id = _ins(db, "01110001", "BE1", 0.4763, base)
-    twin_id = _ins(db, "01110002", "BE1", 0.4763, twin)        # twin: same serial+pvs, 40s apart
-    non_twin_id = _ins(db, "01110003", "BE1", 0.9999, other)   # near time but different pvs
+    db.update_event_review(wave, {"false_trigger": True})
+    moved = db.propagate_review_to_twins(wave)
 
-    db.update_event_review(primary_id, {"false_trigger": True})
-    moved = db.propagate_review_to_twins(primary_id)
-
-    assert twin_id in moved
-    assert db.get_event(twin_id)["false_trigger"] == 1
-    assert db.get_event(non_twin_id)["false_trigger"] == 0
+    assert hist in moved
+    assert db.get_event(hist)["false_trigger"] == 1
+    assert db.get_event(other)["false_trigger"] == 0