feat(h5): standardize sensor-check into the .h5 (schema v2); SFM reads it

Make the sensor self-check a first-class part of the standardized decoded event
so SFM stops decoding it at report time — device-agnostic, per the store's
decoder→standardized-.h5→SFM model.

  * Event gains a `sensor_check` field; both decoders attach the traces where
    they set raw_samples — series-3 in event_file_io.read_blastware_file
    (minimateplus.sensor_check), series-4 in waveform_store's IDF path
    (micromate.sensor_check).  Covers ingest and backfill (both re-decode).
  * event_hdf5 bumps schema_version 1→2 and writes an optional /sensor_check
    group (raw counts, int32, per channel present).  read_event_hdf5 returns
    it; plot_json_from_hdf5 carries it as a top-level key.  Old v1 files still
    read cleanly (no group → None), so nothing breaks before the backfill.
  * gather_report_data reads sensor_check_waveforms from the .h5 and drops the
    report-time series-3 decode — the report no longer reaches into a decoder,
    and a series-4 event now lights up the same strip automatically.

Stored as raw counts (a shape diagnostic, rendered fit-to-box): the per-series
count scale differs and a physical mic unit is ill-defined, so conversion would
add complexity for no display benefit — easy to add later if a numeric use
appears.

Tests: .h5 roundtrip + backward-compat + plot_json + real series-3 decode
attaches to the Event.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YDXjZCr4RqT2U3QvMDhgzf

minimateplus/event_file_io.py

@@ -960,6 +960,11 @@ def read_blastware_file(path: Union[str, Path]) -> Event:
         project=project, client=client, operator=user, sensor_location=seisloc,
     )
     ev.raw_samples = samples
+    # Sensor self-check traces from the binary's trailing block (waveform
+    # events only; returns {} for histograms / when absent).  Carried on the
+    # Event so the .h5 writer persists them device-agnostically.
+    from minimateplus.sensor_check import decode_sensor_check
+    ev.sensor_check = decode_sensor_check(raw) or None
     # Only compute peaks from samples when we actually have samples.
     # For events the codec couldn't decode (histogram-mode bodies, until
     # the §7.6.2 histogram codec is wired in), samples is an empty dict

minimateplus/models.py

@@ -544,6 +544,15 @@ class Event:
     pretrig_samples: Optional[int] = None   # from STRT record: pre-trigger sample count
     rectime_seconds: Optional[int] = None   # from STRT record: record duration (seconds)
 
+    # Sensor self-check traces keyed by channel label — the short diagnostic
+    # waveforms the unit records when it pulses each sensor before monitoring
+    # (geophone ring-downs + a mic pulse train).  Decoded from the binary by
+    # the per-series decoder (minimateplus.sensor_check / micromate.sensor_check)
+    # and carried here so the .h5 writer can persist them device-agnostically.
+    # Raw ADC counts; the source series' scale differs but the trace is a
+    # shape diagnostic (rendered fit-to-box).  None when absent.
+    sensor_check: Optional[dict] = None     # {"Tran": [...], ..., "MicL": [...]}
+
     # ── Debug / introspection ─────────────────────────────────────────────────
     # Raw 210-byte waveform record bytes, set when debug mode is active.
     # Exposed by the SFM server via ?debug=true so field layouts can be verified.

sfm/event_hdf5.py

@@ -12,8 +12,11 @@ Layout written to `<filename>.h5`:
   ├─ samples_int16/ (optional)
   │   ├─ Tran  (int16, raw ADC counts) shape: (N,)
   │   └─ ... per channel (only when present in the source)
+  ├─ sensor_check/ (optional, schema v2+)
+  │   ├─ Tran  (int32, raw counts)     shape: (M,)   M ≪ N
+  │   └─ ... per channel present in the source (MicL absent on 3-channel units)
   └─ root attrs (event metadata):
-       schema_version       int    = 1
+       schema_version       int    = 2
        kind                 str    = "sfm.event.hdf5"
        serial               str
        waveform_key         str    (8-hex)
@@ -64,7 +67,7 @@ from minimateplus.models import Event
 
 log = logging.getLogger(__name__)
 
-SCHEMA_VERSION = 1
+SCHEMA_VERSION = 2   # v2 adds the optional /sensor_check group
 HDF5_KIND = "sfm.event.hdf5"
 
 # Geophone full-scale velocity per range (in/s).  Confirmed in CLAUDE.md
@@ -270,6 +273,22 @@ def write_event_hdf5(
                     )
             igrp.attrs["mic_psi_per_count"] = float(mic_factor)
 
+        # /sensor_check — optional short diagnostic self-check traces (schema
+        # v2+).  Raw ADC counts (a shape diagnostic; the per-series count scale
+        # differs, and the renderer fits each trace to its box).  Only channels
+        # the decoder found are written — 3-channel units carry no MicL.
+        sc = event.sensor_check or {}
+        if sc:
+            scgrp = f.create_group("sensor_check")
+            for ch in ("Tran", "Vert", "Long", "MicL"):
+                vals = sc.get(ch)
+                if vals:
+                    scgrp.create_dataset(
+                        ch, data=np.asarray(vals, dtype=np.int32),
+                        compression="gzip", compression_opts=4, shuffle=True,
+                    )
+            scgrp.attrs["units"] = "raw_counts"
+
     import os
     os.replace(tmp, path)
 
@@ -334,6 +353,16 @@ def read_event_hdf5(path: Union[str, Path]) -> dict:
             if mic_attr is not None:
                 mic_psi = float(mic_attr)
 
+        # /sensor_check — optional (schema v2+); absent on older files.
+        sensor_check = None
+        scgrp = f.get("sensor_check")
+        if scgrp is not None:
+            sensor_check = {}
+            for ch in ("Tran", "Vert", "Long", "MicL"):
+                ds = scgrp.get(ch)
+                if ds is not None:
+                    sensor_check[ch] = np.asarray(ds[()])
+
     return {
         "schema_version":     sv,
         "kind":               attrs.get("kind"),
@@ -341,6 +370,7 @@ def read_event_hdf5(path: Union[str, Path]) -> dict:
         "samples":            samples,
         "samples_int16":      samples_int16,
         "mic_psi_per_count":  mic_psi,
+        "sensor_check":       sensor_check,
     }
 
 
@@ -431,11 +461,16 @@ def plot_json_from_hdf5(
     event_id: Optional[str] = None,
     index: Optional[int] = None,
 ) -> dict:
-    """Build a `sfm.plot.v1` JSON dict from a stored .h5 file."""
+    """Build a `sfm.plot.v1` JSON dict from a stored .h5 file.
+
+    The dict also carries a top-level ``sensor_check`` key (the raw self-check
+    traces as ``{ch: [int]}``, or None) beyond the plot schema, so report
+    generation can read the traces from the same single .h5 load.
+    """
     data = read_event_hdf5(path)
     a = data["attrs"]
     s = data["samples"]
-    return _build_plot_dict(
+    out = _build_plot_dict(
         n_samples=len(s["Tran"]) if "Tran" in s else 0,
         sample_rate=int(a.get("sample_rate", 1024) or 1024),
         pretrig_samples=int(a.get("pretrig_samples", 0) or 0),
@@ -463,6 +498,11 @@ def plot_json_from_hdf5(
         event_id=event_id,
         index=index,
     )
+    scd = data.get("sensor_check")
+    out["sensor_check"] = (
+        {ch: v.tolist() for ch, v in scd.items()} if scd else None
+    )
+    return out
 
 
 def _build_plot_dict(

sfm/report_pdf.py

@@ -121,9 +121,11 @@ class ReportData:
     t0_ms:                  Optional[float] = None
     dt_ms:                  Optional[float] = None
 
-    # Sensor self-check traces — {ch: [samples]} in raw decode units, decoded
-    # from the binary's trailing block (see minimateplus.sensor_check). The
-    # little waveforms BW draws in its "Sensor Check" strip. Empty when absent.
+    # Sensor self-check traces — {ch: [samples]} in raw counts, read from the
+    # standardized .h5 (/sensor_check group, schema v2+) where the per-series
+    # decoder stored them at ingest.  The little diagnostic waveforms BW draws
+    # in its "Sensor Check" strip.  Empty when absent (pre-v2 .h5, histogram,
+    # or 3-channel unit's MicL).
     sensor_check_waveforms: dict = field(default_factory=dict)
 
     # Record-type discriminator
@@ -294,22 +296,15 @@ def gather_report_data(
             rd.pretrig_samples  = ta.get("pretrig_samples")
             rd.t0_ms            = ta.get("t0_ms")
             rd.dt_ms            = ta.get("dt_ms")
+            # Sensor self-check traces — read from the standardized .h5 (schema
+            # v2+).  Device-agnostic: whichever decoder produced the event
+            # stored them at ingest, so SFM reads them here without knowing or
+            # caring about the source instrument series.  Empty on pre-v2 files
+            # (until backfilled) and on 3-channel / histogram events.
+            rd.sensor_check_waveforms = wf.get("sensor_check") or {}
         except Exception as exc:
             log.warning("gather_report_data: hdf5 read failed: %s", exc)
 
-    # ── Sensor self-check traces — decoded from the retained raw binary ──
-    # The .h5 holds only the main waveform; the sensor-check traces live in the
-    # binary's trailing block, so decode them straight from the kept BW file.
-    # Waveform events only (histograms have no sensor-check strip).
-    if not rd.is_histogram:
-        try:
-            from minimateplus.sensor_check import decode_sensor_check
-            bw_path, _a5 = store.paths_for(serial, filename)
-            if bw_path.exists():
-                rd.sensor_check_waveforms = decode_sensor_check(bw_path.read_bytes())
-        except Exception as exc:
-            log.warning("gather_report_data: sensor-check decode failed: %s", exc)
-
     # ── Histogram aggregation ──
     # Codec emits ~N per-block samples (typically 1/sec); BW reports
     # one bar per configured interval (1 min / 5 min / etc.).  When

sfm/waveform_store.py

@@ -662,6 +662,11 @@ class WaveformStore:
             ev.raw_samples = idf_samples
             n_samples = max((len(idf_samples.get(ch, [])) for ch in ("Tran", "Vert", "Long", "MicL")), default=0)
             ev.total_samples = ev.total_samples or n_samples
+            # Sensor self-check traces from the IDFW fixed header (waveform
+            # events only; {} on histograms / when absent).  Carried on the
+            # bridged Event so the .h5 writer persists them like series-3.
+            from micromate.sensor_check import decode_idf_sensor_check
+            ev.sensor_check = decode_idf_sensor_check(idf_bytes) or None
 
         # For IDFH histograms there are no per-sample waveform arrays — the
         # device stores one peak ADC count per interval per channel.  Synthesise

tests/test_event_hdf5_sensor_check.py

@@ -0,0 +1,71 @@
+"""The event .h5 carries the sensor self-check traces (schema v2).
+
+The sensor check is decoded by the per-series decoder and attached to the
+standardized Event, so the .h5 writer persists it device-agnostically and SFM
+reads it back without knowing which instrument produced it.  Old v1 files (no
+sensor_check group) must still read cleanly.
+"""
+import tempfile
+from pathlib import Path
+
+import numpy as np
+
+from minimateplus.models import Event
+from minimateplus.event_file_io import read_blastware_file
+from sfm import event_hdf5
+
+S3_FIX = Path(__file__).parent / "fixtures" / "fft-oracle-2026-09-14" / "N844LQHB.ZT0W"
+
+
+def _write(ev, **kw):
+    d = Path(tempfile.mkdtemp())
+    p = d / "e.h5"
+    event_hdf5.write_event_hdf5(p, ev, serial="BE12844", **kw)
+    return p
+
+
+def test_sensor_check_roundtrips_through_hdf5():
+    ev = Event(index=0)
+    ev.raw_samples = {"Tran": [1, 2, -3], "Vert": [0, 1], "Long": [2], "MicL": [5, -5]}
+    ev.sample_rate = 1024
+    sc = {"Tran": [0, -990, -500, -100], "Vert": [0, -980, -480],
+          "Long": [0, -986, -470], "MicL": [0, -1800, 1800, -1800]}
+    ev.sensor_check = sc
+
+    r = event_hdf5.read_event_hdf5(_write(ev))
+    assert r["schema_version"] == 2
+    assert set(r["sensor_check"]) == {"Tran", "Vert", "Long", "MicL"}
+    for ch, vals in sc.items():
+        assert r["sensor_check"][ch].tolist() == vals
+
+
+def test_plot_json_carries_sensor_check():
+    ev = Event(index=0)
+    ev.raw_samples = {"Tran": [1, 2, 3]}
+    ev.sample_rate = 1024
+    ev.sensor_check = {"Tran": [0, -990, -500], "Vert": [0, -980],
+                       "Long": [0, -986]}   # 3-channel: no MicL
+    pj = event_hdf5.plot_json_from_hdf5(_write(ev))
+    assert pj["sensor_check"] is not None
+    assert "MicL" not in pj["sensor_check"]
+    assert pj["sensor_check"]["Tran"] == [0, -990, -500]
+
+
+def test_event_without_sensor_check_still_reads_as_v2():
+    ev = Event(index=0)
+    ev.raw_samples = {"Tran": [1, 2, 3]}
+    ev.sample_rate = 1024
+    r = event_hdf5.read_event_hdf5(_write(ev))
+    assert r["schema_version"] == 2
+    assert r["sensor_check"] is None
+    assert event_hdf5.plot_json_from_hdf5(_write(ev))["sensor_check"] is None
+
+
+def test_series3_decode_populates_event_sensor_check():
+    # The real series-3 decoder attaches the traces to the Event, so the
+    # ingest/backfill .h5 write picks them up with no extra plumbing.
+    ev = read_blastware_file(S3_FIX)
+    assert ev.sensor_check is not None
+    assert set(ev.sensor_check) == {"Tran", "Vert", "Long", "MicL"}
+    tran = np.asarray(ev.sensor_check["Tran"], dtype=float)
+    assert tran.min() < -800   # the geophone ring-down deflection