0.6.13: Fix watermark maintenance jobs, honest buy-link write reporting, Qobuz 403 diagnosis

scrub-watermark-text.py crashed on every run (missing import os). strip-watermark-art.py
was starved every Sunday by lock contention from strip-mb-tags' growing runtime -- moved
it to 01:00 so the rest of the weekly chain has room. enrich-buy-url.py's summary line
counted matches found, not successful writes, so a run where every metaflac write failed
(root-owned files) still reported "N tagged". pipeline-status.sh now tells a 403 from
Qobuz (Akamai/CDN block) apart from a 401 (actually expired token) -- re-exporting the
token does nothing for the former. Also fixes the dedup review table's "Caught by" badge
overflowing into the Keep column's format pill.

README.md

@@ -73,10 +73,10 @@ Optional, add these later if you want them:
 Pull the prebuilt image onto your Docker host:
 
 ```bash
-docker pull git.kretzer.club/andrew/alembic:0.6.8
+docker pull git.kretzer.club/andrew/alembic:0.6.13
 ```
 
-That is the whole install. You do not need to download the source or build anything. The `0.6.8` is the version; you can pin to it so nothing changes under you, or use `latest` to always get the newest.
+That is the whole install. You do not need to download the source or build anything. The `0.6.13` is the version; you can pin to it so nothing changes under you, or use `latest` to always get the newest.
 
 (If you would rather build it yourself from source, you can, but you do not need to.)
 
@@ -136,7 +136,7 @@ Create a file called `docker-compose.yml` on your server (put it wherever you ke
 ```yaml
 services:
   alembic:
-    image: git.kretzer.club/andrew/alembic:0.6.8
+    image: git.kretzer.club/andrew/alembic:0.6.13
     container_name: alembic
     ports:
       - "8420:8420"

app/routers/dedup.py

@@ -1,3 +1,6 @@
+import os
+import re
+
 from fastapi import APIRouter, BackgroundTasks, Depends, Request
 from fastapi.responses import RedirectResponse
 from fastapi.templating import Jinja2Templates
@@ -30,16 +33,76 @@ def _display_path(path: str) -> str:
     return path[len(_LIBRARY_PREFIX):] if path.startswith(_LIBRARY_PREFIX) else path
 
 
+# Compilation-style import paths carry a "$track " prefix on the filename
+# (see pipeline/configs/beets config.yaml paths: comp/albumtype_soundtrack);
+# singleton paths (the vast majority of this library) don't. Strip it either
+# way so the title reads clean.
+_TRACK_PREFIX_RE = re.compile(r"^\d{1,3}[\s.\-]+")
+
+# rank_file() in dedup-library.sh always ranks FLAC above every other format
+# and WAV below MP3 (a download glitch, never desirable) -- mirror that
+# judgment in the format pill's color so it reads as "this one's the keeper"
+# at a glance, not just a bare extension string.
+_FORMAT_BADGE = {"flac": "badge-success", "wav": "badge-warning"}
+
+
+def _split_display(path: str) -> dict:
+    """Break a library display path into (artist, album, title, ext).
+
+    Beets' singleton path template is always
+    %the{$albumartist}/$album/$title (pipeline/configs/beets config.yaml,
+    paths:) -- every track in this library lands at exactly that shape, so
+    the last two segments are reliably album/filename. A path that doesn't
+    fit (an unexpected root-level file) degrades to showing the raw display
+    path as the title instead of guessing at structure that isn't there.
+    """
+    display = _display_path(path)
+    parts = display.split("/")
+    if len(parts) >= 2:
+        artist, album, filename = parts[0], parts[-2], parts[-1]
+        title, ext = os.path.splitext(filename)
+        title = _TRACK_PREFIX_RE.sub("", title)
+    else:
+        artist, album = "", ""
+        title, ext = os.path.splitext(display)
+    return {
+        "path": path,
+        "display": display,
+        "artist": artist,
+        "album": album,
+        "title": title,
+        "ext": ext.lstrip(".").lower(),
+    }
+
+
+def _file_size(path: str) -> int | None:
+    try:
+        return os.path.getsize(path)
+    except OSError:
+        return None
+
+
 def _to_row(c) -> dict:
+    keep = _split_display(c.keep_path)
+    delete = _split_display(c.delete_path)
+    keep["size_bytes"] = _file_size(c.keep_path)
+    keep["badge"] = _FORMAT_BADGE.get(keep["ext"], "badge-muted")
+    delete["size_bytes"] = c.delete_size_bytes if c.delete_size_bytes is not None else _file_size(c.delete_path)
+    delete["badge"] = _FORMAT_BADGE.get(delete["ext"], "badge-muted")
     return {
         "id": c.id,
         "pass_name": c.pass_name,
         "pass_label": _pass_label(c.pass_name),
-        "keep_path": c.keep_path,
+        "keep": keep,
-        "delete_path": c.delete_path,
+        "delete": delete,
-        "keep_display": _display_path(c.keep_path),
+        # Same-tag passes (numbered_sibling/case_insensitive/normalized) share
-        "delete_display": _display_path(c.delete_path),
+        # artist/title almost always; cross_album_fuzzy and fuzzy_audio can
-        "delete_size_bytes": c.delete_size_bytes,
+        # legitimately differ (different credit, different album entirely) --
+        # the template only collapses shared context onto one line when it's
+        # actually shared, otherwise shows both sides in full.
+        "same_title": keep["title"].lower() == delete["title"].lower(),
+        "same_artist": keep["artist"].lower() == delete["artist"].lower(),
+        "same_album": keep["album"].lower() == delete["album"].lower(),
     }
 
 

app/services/dedup_review_service.py

@@ -27,6 +27,38 @@ def _script_for_pass(pass_name: str) -> str:
     return _FUZZY_SCRIPT if pass_name == _FUZZY_PASS else _SCRIPT
 
 
+def _prune_stale_pending(db) -> int:
+    """Mark pending candidates whose delete_path or keep_path no longer
+    exists as resolved, instead of leaving them to surface forever.
+
+    A pending row can go stale without ever being confirmed through the UI --
+    e.g. a later scan's numbered-twin/format-upgrade auto-apply already
+    removed one side, or upgrade-mp3-to-flac replaced it, or someone deleted
+    it by hand. confirm_and_apply() already does this "already_gone" check
+    for candidates a user explicitly acts on; this generalizes it to run at
+    the start of every scan, so the pending list reflects current reality
+    instead of stale groups that something else already resolved."""
+    now = time.time()
+    rows = db.execute(
+        select(DedupCandidate).where(
+            DedupCandidate.applied == False,  # noqa: E712
+            DedupCandidate.confirmed == False,  # noqa: E712
+            DedupCandidate.ignored == False,  # noqa: E712
+        )
+    ).scalars().all()
+    pruned = 0
+    for c in rows:
+        if not Path(c.delete_path).exists() or not Path(c.keep_path).exists():
+            c.confirmed = True
+            c.confirmed_by = "auto:stale"
+            c.confirmed_at = now
+            c.applied = True
+            pruned += 1
+    if pruned:
+        db.commit()
+    return pruned
+
+
 def _is_pair_ignored(db, path_a: str, path_b: str) -> bool:
     """True if this path pair was ever marked 'keep both', regardless of
     which path was on the keep/delete side that time -- a later scan can
@@ -58,7 +90,9 @@ def _is_pair_already_pending(db, keep_path: str, delete_path: str) -> bool:
     return db.execute(query).first() is not None
 
 
-async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupRun | None:
+async def _run_scan(
+    job_key: str, script_name: str, triggered_by: str, extra_args: tuple[str, ...] = ()
+) -> DedupRun | None:
     """Returns None (persisting nothing) if the job never actually ran --
     e.g. skipped_lock because something else was using the pipeline lock
     at that moment. Same lesson as genre_review_service.run(): recording a
@@ -67,7 +101,7 @@ async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupR
     pending-candidates list isn't scoped to "latest run only"."""
     script = str(settings.pipeline_dir / "lib" / script_name)
     job_run, output = await pipeline_runner.run_job_capture(
-        job_key, [script, "--json"], triggered_by=triggered_by, timeout=_JOB_TIMEOUT_SECONDS
+        job_key, [script, "--json", *extra_args], triggered_by=triggered_by, timeout=_JOB_TIMEOUT_SECONDS
     )
     if job_run.status != "success":
         return None
@@ -76,6 +110,8 @@ async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupR
 
     db = SessionLocal()
     try:
+        _prune_stale_pending(db)
+        now = time.time()
         dedup_run = DedupRun(
             started_at=job_run.started_at,
             finished_at=job_run.finished_at,
@@ -91,7 +127,30 @@ async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupR
 
         skipped_ignored = 0
         skipped_duplicate = 0
+        auto_applied = 0
         for c in candidates:
+            if c.get("auto_applied"):
+                # dedup-library.sh already deleted this pair unconditionally
+                # (identical numbered-sibling twin: same dir/name/ext, no
+                # tag/fuzzy ambiguity involved) -- record it pre-applied for
+                # audit history; it never shows up as a pending review item.
+                db.add(
+                    DedupCandidate(
+                        dedup_run_id=dedup_run.id,
+                        pass_name=c.get("pass", "unknown"),
+                        keep_path=c["keep_path"],
+                        delete_path=c["delete_path"],
+                        delete_id=c.get("delete_id"),
+                        delete_size_bytes=c.get("delete_size_bytes"),
+                        confirmed=True,
+                        confirmed_by="auto:numbered_twin",
+                        confirmed_at=now,
+                        applied=True,
+                    )
+                )
+                auto_applied += 1
+                db.flush()
+                continue
             if _is_pair_ignored(db, c["keep_path"], c["delete_path"]):
                 skipped_ignored += 1
                 continue
@@ -116,8 +175,11 @@ async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupR
         db.commit()
         db.refresh(dedup_run)
         skipped_total = skipped_ignored + skipped_duplicate
-        if skipped_total:
+        if skipped_total or auto_applied:
-            dedup_run.kept = (dedup_run.kept or 0) + skipped_total
+            if skipped_total:
+                dedup_run.kept = (dedup_run.kept or 0) + skipped_total
+            if auto_applied:
+                dedup_run.deleted = auto_applied
             db.commit()
             db.refresh(dedup_run)
         return dedup_run
@@ -126,12 +188,23 @@ async def _run_scan(job_key: str, script_name: str, triggered_by: str) -> DedupR
 
 
 async def scan(triggered_by: str = "manual") -> DedupRun | None:
-    """Dry-run dedup-library.sh --json, persist every candidate deletion
+    """Dry-run dedup-library.sh --json (plus --auto-apply-numbered), persist
-    into a fresh dedup_runs/dedup_candidates pair. Never deletes anything
+    every candidate deletion into a fresh dedup_runs/dedup_candidates pair.
-    -- the scheduled maintenance:dedup job also only ever calls this (no
+
-    --apply), matching the false-negative-biased dedup preference; actual
+    Two kinds of match need no human judgment and get deleted unconditionally
-    deletion only ever happens through confirm_and_apply() below."""
+    by dedup-library.sh itself (see is_numbered_twin/is_format_upgrade there):
-    return await _run_scan("dedup:scan", _SCRIPT, triggered_by)
+    identical numbered-sibling twins (same dir, same name, same extension,
+    differing only by the ".N" collision suffix), and format upgrades within
+    an EXACT tag match from Pass 2/3 (case-insensitive/normalized already
+    proved same song via identical tags, so a differing extension there is
+    just "better format vs. worse"). Everything else -- including Pass 4's
+    cross-album fuzzy matches, where a wrong auto-delete could take out a
+    genuinely different version (a different album pressing, a DJ-mix edit,
+    etc.) -- stays a dry-run candidate awaiting manual confirm_and_apply()
+    below; that's the false-negative-biased preference for anything with real
+    ambiguity. Auto-applied deletions are reported here already applied,
+    purely for audit visibility."""
+    return await _run_scan("dedup:scan", _SCRIPT, triggered_by, extra_args=("--auto-apply-numbered",))
 
 
 async def scan_fuzzy(triggered_by: str = "manual") -> DedupRun | None:

app/services/scheduler_service.py

@@ -155,8 +155,19 @@ MAINTENANCE_JOBS: dict[str, tuple[dict, callable]] = {
         _log_rotation,
     ),
     # ==== Weekly (Sunday) ====
+    # strip_mb_tags runs first here at 01:00 -- not 08:30 like the rest of
+    # this chain -- because its runtime isn't stable: 10m19s on 2026-07-12,
+    # 39.6min on 2026-07-19 (MusicBrainz lookup latency scales with library
+    # size and isn't under our control). At 08:30 that variance repeatedly
+    # starved every job behind it: strip_watermark_art waited the full
+    # SCHEDULED_LOCK_WAIT_SECONDS and gave up every week from 07-12 onward,
+    # and on 07-19 the starvation cascaded all the way through genre:run,
+    # normalize_casing, beets_update_sync, dedup:scan, and both gen_*_playlist
+    # jobs. 01:00 sits in the dead zone before the first playlist sync (05:00)
+    # and well after log_rotation (00:00), so even a run several times slower
+    # than 07-19's is guaranteed to release the lock long before 08:30.
     "maintenance:strip_mb_tags": (
-        dict(minute=30, hour=8, day_of_week="sun"),
+        dict(minute=0, hour=1, day_of_week="sun"),
         _lib("maintenance:strip_mb_tags", "strip-mb-tags.sh"),
     ),
     "maintenance:strip_watermark_art": (

app/static/style.css

@@ -475,11 +475,60 @@ tbody tr:hover { background: rgba(167, 139, 250, 0.055); }
 tbody td.actions-cell { display: flex; gap: 0.5rem; flex-wrap: wrap; }
 
 .dedup-table { table-layout: fixed; }
-.dedup-table .path-cell {
+
-  overflow: hidden;
+/* Each candidate is its own <tbody> (title row + detail row) so the pair
-  text-overflow: ellipsis;
+   highlights together on hover, and so :hover can bubble from either row
-  white-space: nowrap;
+   up to the shared group without JS. That means every detail row is now
-  max-width: 0; /* forces the cell to respect the colgroup width instead of the content's natural width */
+   a tbody's last-child, which would otherwise strip the separator between
+   one candidate and the next (the generic `tbody tr:last-child` rule above
+   assumed one shared tbody) -- restore it here, and only drop it for the
+   actual last group in the table. */
+.dedup-table .dedup-row-group:hover td { background: rgba(167, 139, 250, 0.06); }
+.dedup-table .dedup-detail-row td { border-bottom: 1px solid var(--border); }
+.dedup-table .dedup-row-group:last-of-type .dedup-detail-row td { border-bottom: none; }
+
+.dedup-title-row td { padding: 0.75rem 1.1rem 0.2rem; border-bottom: none; }
+.dedup-detail-row td { padding-top: 0.15rem; }
+
+.dedup-title {
+  font-family: var(--font-display);
+  font-size: 1.02rem;
+  font-weight: 700;
+  color: var(--fg);
+  line-height: 1.35;
+  overflow-wrap: anywhere;
+}
+.dedup-title-alt { font-weight: 400; color: var(--muted); }
+
+.dedup-context { font-size: 0.8rem; margin-top: 0.15rem; }
+
+/* A thin colored rail on each side echoes the keep/delete verdict itself --
+   green for the copy that survives, muted-pink for the one on the chopping
+   block -- so which side is which reads before you've even read the words. */
+.dedup-side {
+  display: flex;
+  align-items: center;
+  gap: 0.55rem;
+  padding-left: 0.65rem;
+  border-left: 2px solid transparent;
+  min-height: 1.6rem;
+}
+.dedup-side-keep { border-left-color: var(--status-success); }
+.dedup-side-delete { border-left-color: var(--status-danger); }
+
+.dedup-side-size { font-size: 0.78rem; white-space: nowrap; flex-shrink: 0; }
+
+/* The actual filename/path -- always visible, never truncated. Tags can be
+   wrong; this is the ground truth for judging whether two files are really
+   the same recording, so it can't be hover-only the way it was in the first
+   pass of this redesign. */
+.dedup-side-path {
+  padding-left: 0.65rem;
+  margin-top: 0.2rem;
+  font-size: 0.78rem;
+  color: var(--muted-2);
+  overflow-wrap: anywhere;
+  line-height: 1.4;
 }
 
 .empty-row td { padding: 2.5rem 1rem; text-align: center; }
@@ -509,6 +558,13 @@ tbody td.actions-cell { display: flex; gap: 0.5rem; flex-wrap: wrap; }
 .badge-pulse::before { animation: pulse-dot 1.4s ease-in-out infinite; }
 @keyframes pulse-dot { 0%, 100% { opacity: 1; } 50% { opacity: 0.35; } }
 
+/* The dedup "Caught by" column is only 10.75rem wide -- "Acoustically
+   Similar" at the default badge size overflowed past it and rendered on
+   top of the keep-side format pill. Smaller size/padding/tracking keeps it
+   inside the column instead of shrinking the column itself, which would
+   just crowd the Keep/Delete path columns next to it. */
+.badge-caughtby { font-size: 0.6rem; padding: 0.24rem 0.55rem; letter-spacing: 0.02em; }
+
 /* ---- stacked status bar (playlist track reconciliation) ---- */
 
 .status-bar {

app/templates/dedup/index.html

@@ -1,5 +1,65 @@
 {% extends "base.html" %}
 {% block title %}Dedup — alembic{% endblock %}
+
+{% macro candidate_rows(c, mode) %}
+<tbody class="dedup-row-group">
+  <tr class="dedup-title-row">
+    <td colspan="{{ 5 if mode == 'pending' else 4 }}">
+      {% if c.same_title %}
+      <div class="dedup-title">{{ c.keep.title }}</div>
+      {% else %}
+      <div class="dedup-title">{{ c.keep.title }} <span class="dedup-title-alt">/ {{ c.delete.title }}</span></div>
+      {% endif %}
+      {% if c.same_artist and c.same_album and c.keep.album %}
+      <div class="dedup-context muted">{{ c.keep.artist }} · {{ c.keep.album }}</div>
+      {% elif c.same_artist %}
+      <div class="dedup-context muted">{{ c.keep.artist }}</div>
+      {% else %}
+      <div class="dedup-context muted">{{ c.keep.artist }} / {{ c.delete.artist }}</div>
+      {% endif %}
+    </td>
+  </tr>
+  <tr class="dedup-detail-row">
+    {% if mode == 'pending' %}
+    <td><input type="checkbox" name="candidate_id" value="{{ c.id }}" form="bulk-delete-form"></td>
+    {% endif %}
+    <td><span class="badge badge-caughtby {{ 'badge-warning' if c.pass_label == 'Acoustically Similar' else 'badge-info' }}" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
+    <td>
+      <div class="dedup-side dedup-side-keep">
+        <span class="badge {{ c.keep.badge }}">{{ c.keep.ext or '?' }}</span>
+        {% if c.keep.size_bytes %}<span class="muted dedup-side-size">{{ (c.keep.size_bytes / 1024 / 1024) | round(1) }} MB</span>{% endif %}
+      </div>
+      <div class="dedup-side-path mono muted">{{ c.keep.display }}</div>
+    </td>
+    <td>
+      <div class="dedup-side dedup-side-delete">
+        <span class="badge {{ c.delete.badge }}">{{ c.delete.ext or '?' }}</span>
+        {% if c.delete.size_bytes %}<span class="muted dedup-side-size">{{ (c.delete.size_bytes / 1024 / 1024) | round(1) }} MB</span>{% endif %}
+      </div>
+      <div class="dedup-side-path mono muted">{{ c.delete.display }}</div>
+    </td>
+    <td class="actions-cell">
+      {% if mode == 'pending' %}
+      <form method="post" action="/dedup/confirm" class="inline"
+            onsubmit="return confirm('Permanently delete this file from disk?\n{{ c.delete.display }}')">
+        <input type="hidden" name="candidate_id" value="{{ c.id }}">
+        <button type="submit" class="btn btn-sm btn-danger">Delete</button>
+      </form>
+      <form method="post" action="/dedup/ignore" class="inline">
+        <input type="hidden" name="candidate_id" value="{{ c.id }}">
+        <button type="submit" class="btn btn-sm btn-ghost" title="Keep both copies and never flag this pair again">Keep both</button>
+      </form>
+      {% else %}
+      <form method="post" action="/dedup/unignore" class="inline">
+        <input type="hidden" name="candidate_id" value="{{ c.id }}">
+        <button type="submit" class="btn btn-sm btn-ghost">Un-ignore</button>
+      </form>
+      {% endif %}
+    </td>
+  </tr>
+</tbody>
+{% endmacro %}
+
 {% block content %}
 <div class="page-header">
   <div>
@@ -18,48 +78,30 @@
 {% endif %}
 
 <h2>Pending candidates</h2>
-<p class="muted" style="margin-top:-0.5rem;">Paths are relative to the library root. Hover a name for the full path.</p>
+<p class="muted" style="margin-top:-0.5rem;">Song title up top so you can scan straight down the list; the actual file path is always shown underneath each side so you can check they're really the same file before confirming.</p>
 <form id="bulk-delete-form" method="post" action="/dedup/confirm"
       onsubmit="return confirm('Permanently delete every selected file from disk? This cannot be undone.')"></form>
 <div class="table-wrap scroll">
   <table class="dedup-table">
     <colgroup>
-      <col style="width:2.2rem"><col style="width:9.5rem"><col style="width:28%">
+      <col style="width:2.2rem"><col style="width:10.75rem"><col style="width:37.5%">
-      <col style="width:28%"><col style="width:5rem"><col style="width:9rem">
+      <col style="width:37.5%"><col style="width:10rem">
     </colgroup>
     <thead>
-      <tr><th></th><th>Caught by</th><th>Keep</th><th>Delete</th><th>Size</th><th>Action</th></tr>
+      <tr><th></th><th>Caught by</th><th>Keep</th><th>Delete</th><th>Action</th></tr>
     </thead>
+    {% for c in candidates %}
+    {{ candidate_rows(c, 'pending') }}
+    {% else %}
     <tbody>
-      {% set pass_badge = {"File Naming": "badge-info", "Acoustically Similar": "badge-warning"} %}
+      <tr class="empty-row"><td colspan="5">
-      {% for c in candidates %}
-      <tr>
-        <td><input type="checkbox" name="candidate_id" value="{{ c.id }}" form="bulk-delete-form"></td>
-        <td><span class="badge {{ pass_badge.get(c.pass_label, 'badge-info') }}" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
-        <td class="muted mono path-cell" title="{{ c.keep_path }}">{{ c.keep_display }}</td>
-        <td class="mono path-cell" title="{{ c.delete_path }}">{{ c.delete_display }}</td>
-        <td class="muted">{{ (c.delete_size_bytes / 1024 / 1024) | round(1) if c.delete_size_bytes else '?' }} MB</td>
-        <td class="actions-cell">
-          <form method="post" action="/dedup/confirm" class="inline"
-                onsubmit="return confirm('Permanently delete this file from disk?\n{{ c.delete_display }}')">
-            <input type="hidden" name="candidate_id" value="{{ c.id }}">
-            <button type="submit" class="btn btn-sm btn-danger">Delete</button>
-          </form>
-          <form method="post" action="/dedup/ignore" class="inline">
-            <input type="hidden" name="candidate_id" value="{{ c.id }}">
-            <button type="submit" class="btn btn-sm btn-ghost" title="Keep both copies and never flag this pair again">Keep both</button>
-          </form>
-        </td>
-      </tr>
-      {% else %}
-      <tr class="empty-row"><td colspan="6">
         <div class="empty-state">
           <span class="sparkle" style="position:relative; display:inline-block; margin-bottom:0.5rem;"></span>
           <p class="muted" style="margin:0;">No pending candidates. Run a scan.</p>
         </div>
       </td></tr>
-      {% endfor %}
     </tbody>
+    {% endfor %}
   </table>
 </div>
 {% if candidates %}
@@ -72,28 +114,15 @@
 <div class="table-wrap scroll">
   <table class="dedup-table">
     <colgroup>
-      <col style="width:9.5rem"><col style="width:33%">
+      <col style="width:10.75rem"><col style="width:39.25%">
-      <col style="width:33%"><col style="width:5rem"><col style="width:7rem">
+      <col style="width:39.25%"><col style="width:7rem">
     </colgroup>
     <thead>
-      <tr><th>Caught by</th><th>Keep</th><th>Delete</th><th>Size</th><th></th></tr>
+      <tr><th>Caught by</th><th>Keep</th><th>Delete</th><th></th></tr>
     </thead>
-    <tbody>
+    {% for c in ignored %}
-      {% for c in ignored %}
+    {{ candidate_rows(c, 'ignored') }}
-      <tr>
+    {% endfor %}
-        <td><span class="badge badge-muted" title="{{ c.pass_name }}">{{ c.pass_label }}</span></td>
-        <td class="muted mono path-cell" title="{{ c.keep_path }}">{{ c.keep_display }}</td>
-        <td class="muted mono path-cell" title="{{ c.delete_path }}">{{ c.delete_display }}</td>
-        <td class="muted">{{ (c.delete_size_bytes / 1024 / 1024) | round(1) if c.delete_size_bytes else '?' }} MB</td>
-        <td>
-          <form method="post" action="/dedup/unignore" class="inline">
-            <input type="hidden" name="candidate_id" value="{{ c.id }}">
-            <button type="submit" class="btn btn-sm btn-ghost">Un-ignore</button>
-          </form>
-        </td>
-      </tr>
-      {% endfor %}
-    </tbody>
   </table>
 </div>
 {% endif %}

pipeline/lib/dedup-library.sh

@@ -34,11 +34,26 @@ set -euo pipefail
 APPLY=0
 JSON_MODE=0
 ONLY_PATHS_FILE=""
+AUTO_APPLY_NUMBERED=0
 while [[ $# -gt 0 ]]; do
   case "$1" in
     --apply) APPLY=1; shift ;;
     --json) JSON_MODE=1; shift ;;
     --only-paths) ONLY_PATHS_FILE="$2"; shift 2 ;;
+    # Delete two kinds of match unconditionally, independent of
+    # --apply/--only-paths, while everything else stays dry-run/log-only:
+    #   - numbered-sibling twins (see is_numbered_twin): same dir, same name,
+    #     same extension, just the ".N" collision suffix -- the same download
+    #     landing twice.
+    #   - format upgrades within an exact tag match (see is_format_upgrade):
+    #     Pass 2/3 already proved same song via identical tags; a different
+    #     extension there just means "better format vs. worse", never a
+    #     different version.
+    # Excludes Pass 4 (cross-album fuzzy) entirely -- matching across
+    # different albums/directories is exactly where a different master or
+    # DJ-mix edit can share tags without being interchangeable, so it always
+    # needs a human. See dedup_review_service.scan().
+    --auto-apply-numbered) AUTO_APPLY_NUMBERED=1; shift ;;
     *) shift ;;
   esac
 done
@@ -97,6 +112,44 @@ host_path() {
 
 SEP=$'\x1c'  # ASCII file separator — safe with any music metadata
 
+# True if two paths are the SAME directory, SAME extension, and identical
+# basenames except for a numeric ".N" infix sldl/beets inserts on a filename
+# collision (e.g. "Title.flac" vs "Title.1.flac"). This is deliberately
+# narrower than any tag-based pass: no fuzzy matching, no cross-album
+# ambiguity, just the literal same download landing twice. Used to
+# auto-delete regardless of which pass found the pair -- Pass 1 only fires
+# when the canonical name is a beets ghost; the very common case where BOTH
+# copies are already tracked in beets (so Pass 1 defers) surfaces instead via
+# Pass 2/3's tag-based grouping, and still deserves the same free pass.
+is_numbered_twin() {
+  local a="$1" b="$2"
+  [[ "${a%/*}" == "${b%/*}" ]] || return 1
+  local ba="${a##*/}" bb="${b##*/}"
+  local ext="${ba##*.}"
+  [[ "${ext,,}" == "${bb##*.}" ]] || return 1
+  [[ "$(echo "$ba" | sed -E "s/\.[0-9]+\.${ext}\$/.${ext}/")" \
+     == "$(echo "$bb" | sed -E "s/\.[0-9]+\.${ext}\$/.${ext}/")" ]]
+}
+
+# True if this pair is a same-song format upgrade found by an EXACT tag match
+# (Pass 2 case-insensitive or Pass 3 normalized -- both require identical
+# albumartist+album+title after case/punctuation folding, so "same song" is
+# already proven by the pass itself) where the two files simply have
+# different extensions. rank_file() always ranks FLAC ahead of any other
+# format regardless of size/dirty-name/etc, so within a tag-exact group a
+# cross-extension pair unconditionally means "the format-preferred copy vs.
+# a lesser one" -- no judgment call. Deliberately excludes Pass 4
+# (cross_album_fuzzy): that pass matches by artist+title-base ACROSS
+# different albums/directories, which is exactly where a different master,
+# DJ-mix edit, or reissue can share tags without being an interchangeable
+# copy -- those still need a human to look at album/context before deleting
+# either side.
+is_format_upgrade() {
+  local pass="$1" keep="$2" delete="$3"
+  [[ "$pass" == "case_insensitive" || "$pass" == "normalized" ]] || return 1
+  [[ "${keep##*.}" != "${delete##*.}" ]]
+}
+
 # Rank a file: lower = better. FLAC > MP3 > other (WAV/etc.); clean filename
 # > sync-conflict artifact (-DESKTOP-, (1), .1.); extended/club mix > radio
 # edit at same format; then larger wins.
@@ -177,7 +230,7 @@ process_group() {
   esac
 
   local first=1
-  local keep_path=""
+  local keep_path="" keep_id="" any_auto=0
   while IFS="$SEP" read -r _sk id hp; do
     [[ -z "$hp" ]] && continue
     local size_bytes; size_bytes=$(stat -c '%s' "$hp" 2>/dev/null || echo 0)
@@ -185,14 +238,31 @@ process_group() {
     if [[ $first -eq 1 ]]; then
       log "  KEEP   ($size_h) $hp"
       keep_path="$hp"
+      keep_id="$id"
       first=0
     else
       log "  DELETE ($size_h) $hp"
-      json_emit "{\"pass\":\"${pass_name}\",\"keep_path\":\"$(json_escape "$keep_path")\",\"delete_path\":\"$(json_escape "$hp")\",\"delete_size_bytes\":${size_bytes}}"
+
+      # Auto-apply-numbered deletes numbered_sibling matches unconditionally,
+      # bypassing --only-paths (that gate exists only for the manual confirm
+      # flow, which never runs alongside this flag). All other passes stay
+      # dry-run/log-only here regardless.
+      local do_delete=0 auto_applied=0
       if [[ $APPLY -eq 1 ]]; then
+        do_delete=1
+      elif [[ $AUTO_APPLY_NUMBERED -eq 1 ]] \
+        && { is_numbered_twin "$keep_path" "$hp" || is_format_upgrade "$pass_name" "$keep_path" "$hp"; }; then
+        do_delete=1
+        auto_applied=1
+        any_auto=1
+      fi
+      local auto_json="false"; [[ $auto_applied -eq 1 ]] && auto_json="true"
+      json_emit "{\"pass\":\"${pass_name}\",\"keep_path\":\"$(json_escape "$keep_path")\",\"delete_path\":\"$(json_escape "$hp")\",\"delete_size_bytes\":${size_bytes},\"auto_applied\":${auto_json}}"
+
+      if [[ $do_delete -eq 1 ]]; then
         # With --only-paths given, only delete entries the caller explicitly
         # confirmed; without it, delete everything (original behavior).
-        if [[ -n "$ONLY_PATHS_FILE" && -z "${ONLY_PATHS[$hp]:-}" ]]; then
+        if [[ $auto_applied -eq 0 && -n "$ONLY_PATHS_FILE" && -z "${ONLY_PATHS[$hp]:-}" ]]; then
           log "    (skipped — not in --only-paths confirm list)"
         elif [[ -n "$id" ]]; then
           # In beets — beet remove -d removes from DB + disk. Best-effort: a
@@ -206,6 +276,18 @@ process_group() {
       fi
     fi
   done < <(echo "$ranked" | grep -v '^$' | sort -n)
+
+  # An auto-applied numbered-twin deletion can leave the numbered-named file
+  # as the sole survivor (it won on size despite the dirty-filename penalty).
+  # Rename it back to the canonical name so the library doesn't accumulate
+  # ".1."/".2." filenames for tracks that no longer have a duplicate. Only
+  # auto_applied triggers this (never a manual --only-paths confirm, which
+  # may leave the sibling undeleted if the user didn't confirm it -- renaming
+  # then would collide); only when it's actually in beets (a ghost survivor
+  # has nothing to move); only when the name still has the dirty infix.
+  if [[ $any_auto -eq 1 && -n "$keep_id" && "$keep_path" =~ \.[0-9]+\.[A-Za-z0-9]+$ ]]; then
+    beet move "id:${keep_id}" >> "$LOG" 2>&1 || log "    WARN: beet move id:${keep_id} failed (rename survivor)"
+  fi
   return 0  # explicit: the loop's last command status must not leak out under set -e
 }
 
@@ -248,16 +330,20 @@ while IFS="$SEP" read -r numbered_id numbered_cp; do
     # Canonical wins: delete numbered (in beets), keep canonical (ghost)
     process_group "P1 numbered-sibling: ${numbered_cp##*/Library/}" \
       "$host_canonical" "${numbered_id}${SEP}${numbered_cp}"
-    if [[ $APPLY -eq 1 ]]; then
+    if [[ $APPLY -eq 1 || $AUTO_APPLY_NUMBERED -eq 1 ]]; then
       # canonical is now a ghost file; import it into beets
       beet import -q -s "${canonical_cp}" >> "$LOG" 2>&1 || log "  WARN: beet import failed for ${canonical_cp}"
     fi
   else
     # Numbered wins (canonical is ghost): rm the ghost, then beet move to rename
     # the numbered file to the canonical path (id query — see process_group).
+    # Safe to reach with just AUTO_APPLY_NUMBERED: this loop only ever builds
+    # genuine numbered-sibling pairs (see is_numbered_twin), and process_group
+    # above already deleted the ghost canonical before this runs, so the move
+    # target is guaranteed clear -- no rename collision.
     process_group "P1 numbered-sibling: ${numbered_cp##*/Library/}" \
       "${numbered_id}${SEP}${numbered_cp}" "$host_canonical"
-    if [[ $APPLY -eq 1 ]]; then
+    if [[ $APPLY -eq 1 || $AUTO_APPLY_NUMBERED -eq 1 ]]; then
       beet move "id:${numbered_id}" >> "$LOG" 2>&1 || log "  WARN: beet move id:${numbered_id} failed"
     fi
   fi

pipeline/lib/enrich-buy-url.py

@@ -458,7 +458,7 @@ def main():
           + (f"  upgrade-from={sorted(upgrade_from)}" if upgrade_from else ""))
     print(f"[enrich] {len(flacs)} FLAC files in library\n")
 
-    looked = found = upgraded = 0
+    looked = found = upgraded = write_failed = 0
     by_source = {s: 0 for s in cascade}
     touched = []
     for p in flacs:
@@ -519,17 +519,25 @@ def main():
             if set_flac_tag(sp, BUY_URL_TAG, url):
                 touched.append(sp)
             else:
-                print("      ! metaflac write failed")
+                write_failed += 1
+                print("      ! metaflac write failed (permissions? disk full?) -- NOT tagged")
         else:
             touched.append(sp)
 
         if found % 50 == 0:
             print(f"  ...{found} links from {looked} lookups so far", flush=True)
 
-    print(f"\n[enrich] {looked} lookups, {found} {'tagged' if args.apply else 'would-tag'}"
+    # touched is only appended to on an actual successful write (apply mode)
+    # or a would-tag match (dry run) -- len(touched) is what really landed on
+    # disk. `found` counts matches regardless of write outcome, so reporting
+    # `found` here as "tagged" lied about full success on 2026-07-22, when
+    # every write in the run failed (root-owned files under explo/) but the
+    # summary line still read "51 tagged".
+    print(f"\n[enrich] {looked} lookups, {len(touched)} {'tagged' if args.apply else 'would-tag'}"
           f"  ({', '.join(f'{s}={by_source[s]}' for s in cascade)})"
           f"  no-match={looked - found}"
-          + (f"  upgraded={upgraded}" if upgrade_from else ""))
+          + (f"  upgraded={upgraded}" if upgrade_from else "")
+          + (f"  WRITE-FAILED={write_failed}" if write_failed else ""))
 
     if args.apply and touched and az_key and args.azuracast_base:
         print("[enrich] telling AzuraCast to reprocess touched files...")

pipeline/lib/export-laptop-playlists.py

@@ -57,11 +57,12 @@ OUT_DIR = f"{_MUSIC_DATA_DIR}/playlists-laptop"
 # Absolute Windows path to the laptop's library root.
 LIBRARY_LAPTOP_ROOT = r"C:\Music\Library"
 
-# Beets stores paths with this prefix (the container-side mount of the
+# Prefixes beets may display library paths under, tried in order: the real
-# library); strip it to get the path relative to the library root. This is
+# library dir (everything since the 2026-07-08 path rewrite) and the legacy
-# still "/music/" through the migration's Stage 0-3 transitional mount;
+# transitional mount (any stale pre-rewrite entry). Strip whichever matches
-# revisit at Stage 4 once beets' directory: becomes MUSIC_DATA_DIR/Library.
+# to get the path relative to the library root; when neither matches the
-BEETS_LIBRARY_PREFIX = "/music/"
+# track is outside the library and is skipped.
+BEETS_LIBRARY_PREFIXES = (f"{_MUSIC_DATA_DIR}/Library/", "/music/")
 
 M3U_EXT = ".m3u"
 # Older formats from earlier iterations of this script — swept by reconcile.
@@ -157,9 +158,12 @@ def build_beets_index() -> dict[tuple[str, str], list[tuple[str, str, str, str]]
         if len(parts) != 4:
             continue
         aa, alb, ti, path = parts
-        if not path.startswith(BEETS_LIBRARY_PREFIX):
+        rel = next(
+            (path[len(p):] for p in BEETS_LIBRARY_PREFIXES if path.startswith(p)),
+            None,
+        )
+        if rel is None:
             continue
-        rel = path[len(BEETS_LIBRARY_PREFIX):]
         idx.setdefault((_normkey(alb), _normkey(ti)), []).append((aa, alb, ti, rel))
     return idx
 

pipeline/lib/fix-track-metadata.py

@@ -49,8 +49,10 @@ _ALEMBIC_CONFIG_DIR = os.environ.get("ALEMBIC_CONFIG_DIR", "/config")
 _MUSIC_DATA_DIR = os.environ.get("MUSIC_DATA_DIR", "/data/music")
 
 LIBRARY = f"{_MUSIC_DATA_DIR}/Library"
-# Still "/music" through the migration's Stage 0-3 transitional beets mount;
+# Legacy prefix from the migration's transitional beets mount. Since the
-# revisit at Stage 4 once beets' directory: becomes MUSIC_DATA_DIR/Library.
+# 2026-07-08 path rewrite beets displays real LIBRARY paths, so this only
+# matters for accepting pasted /music/... paths as input and as a fallback
+# beets query form for any stale pre-rewrite DB entry.
 CONTAINER_PREFIX = "/music"
 SPOTIFY_ENV = f"{_ALEMBIC_CONFIG_DIR}/pipeline/_spotify.env"
 SPOTIFY_GENRE = f"{os.environ.get('PIPELINE_DIR', '/app/pipeline')}/lib/spotify-genre.py"
@@ -316,15 +318,19 @@ def resolve_input_path(arg):
 
 
 def beets_id_for(host_path):
-    cp = host_to_container(host_path)
+    # Real path first (how beets displays everything since the 2026-07-08
-    r = subprocess.run(
+    # path rewrite), legacy /music/... form second for any stale entry.
-        ["beet", "ls", "-f", "$id|||$path", f"path:{cp}"],
+    # Querying only the legacy form (the old behavior) matched nothing after
-        capture_output=True, text=True, check=True)
+    # the rewrite, so retag-from-url silently skipped beet update/move.
-    for line in r.stdout.splitlines():
+    for cp in (host_path, host_to_container(host_path)):
-        if "|||" in line:
+        r = subprocess.run(
-            id_str, p = line.split("|||", 1)
+            ["beet", "ls", "-f", "$id|||$path", f"path:{cp}"],
-            if p == cp:
+            capture_output=True, text=True, check=True)
-                return int(id_str)
+        for line in r.stdout.splitlines():
+            if "|||" in line:
+                id_str, p = line.split("|||", 1)
+                if p == cp:
+                    return int(id_str)
     return None
 
 

pipeline/lib/pipeline-status.sh

@@ -425,6 +425,14 @@ PYEOF
     case "$q_code" in
       200) mark_ok   "Qobuz token" "valid (buy-link lookup live)" ;;
       401) mark_warn "Qobuz token" "EXPIRED — re-export X-User-Auth-Token to ${ALEMBIC_CONFIG_DIR:-/config}/pipeline/qobuz/token" ;;
+      # A genuinely expired/bad token gets a JSON 401 from Qobuz's own API.
+      # 403 instead means the request never reached that code at all -- Qobuz's
+      # Akamai edge is rejecting the request outright (seen 2026-07-22: the
+      # exact same request got this "Access Denied"/edgesuite.net block from
+      # alembic's VPN egress IP, but a clean 401 from a non-VPN IP). Re-
+      # exporting the token does nothing for that -- it's the egress IP's
+      # reputation, not the credential. Say so, so it isn't mistaken for 401.
+      403) mark_warn "Qobuz token" "blocked (HTTP 403, likely Akamai/CDN, not the token) — VPN egress IP may be flagged; re-exporting the token won't fix this" ;;
       *)   mark_warn "Qobuz token" "check failed (HTTP ${q_code:-none})" ;;
     esac
   else

pipeline/lib/replace-with-better.sh

@@ -195,7 +195,18 @@ while IFS= read -r -d '' new_file; do
   existing_id="${match%%$'\x1f'*}"
   existing_container="${match#*$'\x1f'}"
 
-  existing="${MUSIC_DATA_DIR:-/data/music}/Library${existing_container#/music}"
+  # beets displays real ${MUSIC_DATA_DIR}/Library/... paths since the
+  # 2026-07-08 path rewrite -- use them as-is; only a legacy /music/...
+  # display path still needs the prefix swap. Blindly prepending (the old
+  # behavior) doubled the prefix, so every match logged [stale-db], the MP3
+  # never got replaced, and the leftover-import step at the bottom imported
+  # the staged FLAC as a NEW track -- producing exactly the flac+mp3 twins
+  # this script exists to prevent.
+  if [[ "$existing_container" == /music/* ]]; then
+    existing="${MUSIC_DATA_DIR:-/data/music}/Library${existing_container#/music}"
+  else
+    existing="$existing_container"
+  fi
   if [[ ! -f "$existing" ]]; then
     echo "[stale-db]       beets has $existing_container but file missing" | tee -a "$LOG"
     continue

pipeline/lib/scrub-watermark-text.py

@@ -29,7 +29,7 @@ Usage:
   scrub-watermark-text.py                # dry run
   scrub-watermark-text.py --apply        # actually strip
 """
-import sys, re, argparse
+import os, sys, re, argparse
 from pathlib import Path
 from mutagen import File as MFile
 from mutagen.id3 import ID3, ID3NoHeaderError