feat(collector): capture additional smartctl diagnostics

Record host read and write commands, controller busy time, error log
entries, warning and critical temperature time, and thermal management
transitions from the existing smartctl -a -j acquisition. Schema 7 adds
nullable columns to samples so legacy rows read as unknown, and the
Diagnostics panel shows each counter with its change.

src/fenris/activity_readout.py

@@ -51,8 +51,25 @@ DIAGNOSTIC_COUNTERS = (
     ("unsafe_shutdowns", "Unsafe shutdowns", ""),
     ("media_errors", "Media errors", ""),
     ("available_spare", "Available spare", "%"),
+    ("host_reads", "Host reads", ""),
+    ("host_writes", "Host writes", ""),
+    ("controller_busy_time", "Controller busy time", " min"),
+    ("num_err_log_entries", "Error log entries", ""),
+    ("warning_temp_time", "Warning temperature time", " min"),
+    ("critical_comp_time", "Critical temperature time", " min"),
+    ("thm_temp1_trans_count", "Thermal management 1 transitions", ""),
+    ("thm_temp1_total_time", "Thermal management 1 time", " s"),
+    ("thm_temp2_trans_count", "Thermal management 2 transitions", ""),
+    ("thm_temp2_total_time", "Thermal management 2 time", " s"),
 )
 
+# Reported only by drives that implement thermal management; with no value the
+# panel omits them instead of listing four permanent n/a rows.
+_OPTIONAL_DIAGNOSTICS = frozenset((
+    "thm_temp1_trans_count", "thm_temp1_total_time",
+    "thm_temp2_trans_count", "thm_temp2_total_time",
+))
+
 LOCAL_ACTIVITY_STATE_LABELS = {
     "so_far": "totals so far",
     "incomplete": "incomplete",
@@ -689,7 +706,10 @@ def _counter_deltas(
     inside the window; with fewer than two distinct samples, or across a
     controller-segment change, there is no delta.
     """
-    columns = ", ".join(key for key, _, _ in DIAGNOSTIC_COUNTERS)
+    # A store not yet migrated lacks the newer counter columns: read them as unknown.
+    present = {row[1] for row in conn.execute("PRAGMA table_info(samples)")}
+    columns = ", ".join(
+        key if key in present else "NULL" for key, _, _ in DIAGNOSTIC_COUNTERS)
     columns += ", segment_id"
     last = conn.execute(
         "SELECT id, %s FROM samples WHERE ts <= ? ORDER BY ts DESC, id DESC "
@@ -1016,6 +1036,8 @@ def diagnostics_text(activity: ActivityReadout) -> str:
     for key, label, unit in DIAGNOSTIC_COUNTERS:
         counter = diag["counters"][key]
         if counter["value"] is None:
+            if key in _OPTIONAL_DIAGNOSTICS:
+                continue
             lines.append("%s n/a" % label)
             continue
         delta = "Δ n/a" if counter["delta"] is None else "Δ " + _signed(counter["delta"])

src/fenris/collector.py

@@ -19,7 +19,7 @@ from typing import Any, Dict, Optional
 
 from .derive import derive_hours_from_interval, find_previous_sample
 from .monitoring_periods import ensure_period_open
-from .store import init_store, get_store_path
+from .store import DIAGNOSTIC_SAMPLE_COLUMNS, init_store, get_store_path
 
 
 class AcquisitionError(Exception):
@@ -103,6 +103,8 @@ def acquire_from_smartctl(smartctl_data: Dict[str, Any]) -> Dict[str, Any]:
         "bytes_written": log["data_units_written"] * 512000,
         "bytes_read": log["data_units_read"] * 512000,
         "critical_warning": log.get("critical_warning", 0),
+        # Diagnostic counters (issue #111); absent keys stay None, never zero.
+        **{column: log.get(column) for column in DIAGNOSTIC_SAMPLE_COLUMNS},
     }
 
 
@@ -259,9 +261,10 @@ def write_sample(
             percentage_used, available_spare, media_errors, power_on_hours,
             power_cycles, unsafe_shutdowns, temperature_c,
             data_units_written, data_units_read, bytes_written, bytes_read,
-            critical_warning, segment_id, local_tz
-        ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-        """,
+            critical_warning, segment_id, local_tz, %s
+        ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, %s)
+        """ % (", ".join(DIAGNOSTIC_SAMPLE_COLUMNS),
+               ", ".join("?" * len(DIAGNOSTIC_SAMPLE_COLUMNS))),
         (
             sample["ts"],
             sample["device"],
@@ -284,6 +287,8 @@ def write_sample(
             sample["critical_warning"],
             segment_id,
             sample.get("local_tz"),
+            # Samples staged by an earlier version lack these keys.
+            *(sample.get(column) for column in DIAGNOSTIC_SAMPLE_COLUMNS),
         ),
     )
     

src/fenris/store.py

@@ -11,7 +11,23 @@ from typing import Optional
 
 
 # Schema version - increment on each migration
-SCHEMA_VERSION = 6
+SCHEMA_VERSION = 7
+
+# Diagnostic counters added in schema 7 (issue #111), named after the
+# NVMe health-log keys they come from. All nullable: legacy rows and drives that
+# do not report a counter stay unknown rather than zero.
+DIAGNOSTIC_SAMPLE_COLUMNS = (
+    "host_reads",
+    "host_writes",
+    "controller_busy_time",
+    "num_err_log_entries",
+    "warning_temp_time",
+    "critical_comp_time",
+    "thm_temp1_trans_count",
+    "thm_temp1_total_time",
+    "thm_temp2_trans_count",
+    "thm_temp2_total_time",
+)
 
 
 # Packaged default placement (spec §8.3). The config may override it, but a
@@ -109,7 +125,17 @@ def _create_schema(conn: sqlite3.Connection):
             bytes_read INTEGER,
             critical_warning INTEGER,
             segment_id INTEGER,
-            local_tz TEXT
+            local_tz TEXT,
+            host_reads INTEGER,
+            host_writes INTEGER,
+            controller_busy_time INTEGER,
+            num_err_log_entries INTEGER,
+            warning_temp_time INTEGER,
+            critical_comp_time INTEGER,
+            thm_temp1_trans_count INTEGER,
+            thm_temp1_total_time INTEGER,
+            thm_temp2_trans_count INTEGER,
+            thm_temp2_total_time INTEGER
         )
     """)
     
@@ -303,6 +329,7 @@ def _apply_migrations(conn: sqlite3.Connection, current_version: int):
         4: _migrate_3_to_4,
         5: _migrate_4_to_5,
         6: _migrate_5_to_6,
+        7: _migrate_6_to_7,
     }
     while current_version < SCHEMA_VERSION:
         target_version = current_version + 1
@@ -408,6 +435,22 @@ def _migrate_5_to_6(conn: sqlite3.Connection) -> None:
     repair_legacy_local_day_evidence(conn)
 
 
+def _migrate_6_to_7(conn: sqlite3.Connection) -> None:
+    """Add nullable diagnostic counters to samples (issue #111).
+
+    Additive only: existing rows are untouched and read NULL (unknown).
+    Rollback (SQLite 3.35+, with the collector stopped): for each column in
+    DIAGNOSTIC_SAMPLE_COLUMNS run ``ALTER TABLE samples DROP COLUMN <name>``,
+    then ``PRAGMA user_version=6``. Dropping loses only the new counters.
+    """
+    cols = {row[1] for row in conn.execute("PRAGMA table_info(samples)").fetchall()}
+    if not cols:
+        return
+    for column in DIAGNOSTIC_SAMPLE_COLUMNS:
+        if column not in cols:
+            conn.execute(f"ALTER TABLE samples ADD COLUMN {column} INTEGER")
+
+
 def migrate_to_latest(store_path: Path) -> int:
     """Apply forward-only migrations to bring the store to SCHEMA_VERSION.