fix: SMART overlay shows terminal states + reconciles orphans (1.0.0-49)

The Long SMART column showed "—" while the Burn-In column showed
"FAILED (LONG SMART)" — clear contradiction. Two reasons:

1. The overlay query in _drives_helpers only fetched SMART stage
   data for burn-ins in ('running','queued') state. Failed/passed/
   cancelled jobs got their stage data filtered out, so the SMART
   columns went blank when you most wanted to see them. Removed
   the state filter so all burn-ins overlay.

2. A pre-busy-timeout `database is locked` failure mode (sdj job 5
   from Mar 2026) left long_smart stage rows recorded as state=
   'running' even though the parent job ended in state='failed'.
   The overlay now translates that orphan state at render time:
   if the parent job is failed/cancelled/unknown but the stage is
   still 'running', display the stage as failed (or the parent's
   terminal state) so the column matches the Burn-In column.

The translation is purely display-time; no DB writes. error_text
falls back to the parent job's error_text when the stage's own is
NULL, so the operator sees what actually broke.

app/config.py

@@ -86,7 +86,7 @@ class Settings(BaseSettings):
     ssh_key: str = ""             # PEM private key content (paste full key including headers)
 
     # Application version — used by the /api/v1/updates/check endpoint
-    app_version: str = "1.0.0-48"
+    app_version: str = "1.0.0-49"
 
     # ---- Authentication (1.0.0-22) ----
     # session_secret: HMAC key for signing session cookies. Empty = generate

app/routes/_drives_helpers.py

@@ -147,11 +147,12 @@ async def _fetch_drives_for_template(db: aiosqlite.Connection) -> list[dict]:
 
     # For burn-ins that include SMART stages, fetch those stages so we can
     # mirror their progress/result in the Short/Long SMART columns.
+    # We include burn-ins in ANY state — including failed/passed/cancelled —
+    # so the SMART columns don't go blank when the burn-in finishes. Without
+    # this, "FAILED (LONG SMART)" appears in the Burn-In column while the
+    # Long SMART column shows "—", which contradicts itself.
     bi_smart_stages: dict[int, dict[str, dict]] = {}  # job_id -> {stage_name: row}
-    bi_ids_with_smart = [
+    bi_ids_with_smart = [bi["id"] for bi in burnin_by_drive.values()]
-        bi["id"] for bi in burnin_by_drive.values()
-        if bi["state"] in ("running", "queued")
-    ]
     if bi_ids_with_smart:
         placeholders = ",".join("?" * len(bi_ids_with_smart))
         # placeholders is purely structural ("?,?,?"); IDs themselves are
@@ -163,7 +164,7 @@ async def _fetch_drives_for_template(db: aiosqlite.Connection) -> list[dict]:
             "FROM burnin_stages bs "
             "WHERE bs.burnin_job_id IN (" + placeholders + ") "
             "  AND bs.stage_name IN ('short_smart', 'long_smart') "
-            "  AND bs.state IN ('running', 'passed', 'failed')"
+            "  AND bs.state IN ('running', 'passed', 'failed', 'aborted')"
         )
         cur = await db.execute(sql, bi_ids_with_smart)
         for r in await cur.fetchall():
@@ -185,14 +186,26 @@ async def _fetch_drives_for_template(db: aiosqlite.Connection) -> list[dict]:
                 if existing.get("state") not in (None, "idle"):
                     continue
                 pct = stage["percent"] or 0
+                stage_state = stage["state"]
+                # If the parent burn-in ended in failure but this SMART
+                # stage is still recorded as "running", that's an
+                # orphaned stage row from a hard crash (e.g. the old
+                # `database is locked` failure mode). Surface as failed
+                # so the column matches the Burn-In column.
+                if stage_state == "running" and bi.get("state") in (
+                    "failed", "cancelled", "unknown"
+                ):
+                    stage_state = bi["state"] if bi["state"] != "unknown" else "failed"
                 d[target] = {
-                    "state": stage["state"],
+                    "state": stage_state,
-                    "percent": pct if stage["state"] == "running" else (100 if stage["state"] == "passed" else 0),
+                    "percent": pct if stage_state == "running" else (100 if stage_state == "passed" else 0),
-                    "eta_seconds": _compute_eta_seconds(stage["started_at"], pct) if stage["state"] == "running" else None,
+                    "eta_seconds": _compute_eta_seconds(stage["started_at"], pct) if stage_state == "running" else None,
                     "eta_timestamp": None,
                     "started_at": stage["started_at"],
                     "finished_at": stage["finished_at"],
-                    "error_text": stage["error_text"],
+                    "error_text": stage["error_text"] or (
+                        bi.get("error_text") if stage_state == "failed" else None
+                    ),
                 }
 
         drives.append(d)