release: archivebox 0.9.32rc10

archivebox/core/views.py

@@ -1521,7 +1521,13 @@ def live_progress_view(request):
             "created_by_id",
             "modified_at",
             "urls",
+            "config",
             "max_depth",
+            "max_urls",
+            "crawl_max_size",
+            "snapshot_max_size",
+            "tags_str",
+            "persona_id",
             "status",
             "retry_at",
             "label",
@@ -1541,6 +1547,14 @@ def live_progress_view(request):
             key=lambda crawl: crawl.modified_at,
             reverse=True,
         )[:10]
+        persona_names_by_id: dict[str, str] = {}
+        persona_ids = {crawl.persona_id for crawl in active_crawls_list if crawl.persona_id}
+        if persona_ids:
+            from archivebox.personas.models import Persona
+
+            persona_names_by_id = {
+                str(persona_id): name for persona_id, name in Persona.objects.filter(id__in=persona_ids).values_list("id", "name")
+            }
         active_crawl_ids = [crawl.id for crawl in active_crawls_list]
         snapshot_counts_by_crawl: dict[str, dict[str, int]] = {str(crawl_id): {} for crawl_id in active_crawl_ids}
         cancelled_snapshot_counts_by_crawl: dict[str, int] = {str(crawl_id): 0 for crawl_id in active_crawl_ids}
@@ -1926,6 +1940,9 @@ def live_progress_view(request):
             # Check if crawl can start (for debugging stuck crawls)
             can_start = bool(crawl.urls)
             urls_preview = crawl.urls[:60] if crawl.urls else None
+            crawl_tags = [tag.strip() for tag in (crawl.tags_str or "").replace("\n", ",").split(",") if tag.strip()]
+            persona_name = persona_names_by_id.get(str(crawl.persona_id)) if crawl.persona_id else None
+            persona_name = persona_name or str((crawl.config or {}).get("DEFAULT_PERSONA") or "Default")
 
             # Check if retry_at is in the future (would prevent worker from claiming)
             retry_at_future = crawl.retry_at > now if crawl.retry_at else False
@@ -1949,7 +1966,15 @@ def live_progress_view(request):
                     "status": crawl.status,
                     "started": crawl.created_at.isoformat() if crawl.created_at else None,
                     "progress": crawl_progress,
+                    "created_by": crawl.created_by.username,
+                    "persona": persona_name,
                     "max_depth": crawl.max_depth,
+                    "max_urls": crawl.max_urls,
+                    "max_crawl_size": crawl.crawl_max_size,
+                    "max_snapshot_size": crawl.snapshot_max_size,
+                    "max_crawl_size_display": printable_filesize(crawl.crawl_max_size) if crawl.crawl_max_size else "unlimited",
+                    "max_snapshot_size_display": printable_filesize(crawl.snapshot_max_size) if crawl.snapshot_max_size else "unlimited",
+                    "tags": crawl_tags,
                     "urls_count": urls_count,
                     "total_snapshots": total_snapshots,
                     "completed_snapshots": completed_snapshots,

archivebox/services/runner.py

@@ -1122,18 +1122,25 @@ def recover_orphaned_snapshots() -> int:
     from archivebox.crawls.models import Crawl
     from archivebox.core.models import ArchiveResult, Snapshot
     from archivebox.machine.models import Process
-    from django.db.models import Q
 
     active_snapshot_ids: set[str] = set()
     orphaned_snapshots = list(
-        Snapshot.objects.filter(
-            Q(status=Snapshot.StatusChoices.STARTED, retry_at__isnull=True)
-            | Q(status=Snapshot.StatusChoices.SEALED, archiveresult__status=ArchiveResult.StatusChoices.QUEUED),
-        )
+        Snapshot.objects.filter(status=Snapshot.StatusChoices.STARTED, retry_at__isnull=True)
         .select_related("crawl")
-        .prefetch_related("archiveresult_set")
-        .distinct(),
+        .prefetch_related("archiveresult_set"),
     )
+
+    queued_result_snapshot_ids = list(
+        ArchiveResult.objects.filter(status=ArchiveResult.StatusChoices.QUEUED).values_list("snapshot_id", flat=True).distinct(),
+    )
+    if queued_result_snapshot_ids:
+        orphaned_snapshots.extend(
+            snapshot
+            for snapshot in Snapshot.objects.filter(id__in=queued_result_snapshot_ids)
+            .select_related("crawl")
+            .prefetch_related("archiveresult_set")
+            if snapshot.status == Snapshot.StatusChoices.SEALED
+        )
     running_processes = Process.objects.filter(
         status=Process.StatusChoices.RUNNING,
         process_type__in=[

archivebox/templates/admin/progress_monitor.html

@@ -222,6 +222,27 @@
         color: #8b949e;
         margin-top: 2px;
     }
+    #progress-monitor .crawl-tags {
+        display: flex;
+        flex-wrap: wrap;
+        gap: 4px;
+        margin-top: 5px;
+    }
+    #progress-monitor .crawl-tag {
+        display: inline-flex;
+        align-items: center;
+        max-width: 120px;
+        padding: 1px 6px;
+        border: 1px solid #30363d;
+        border-radius: 10px;
+        color: #c9d1d9;
+        background: rgba(139, 148, 158, 0.12);
+        font-size: 10px;
+        line-height: 16px;
+        white-space: nowrap;
+        overflow: hidden;
+        text-overflow: ellipsis;
+    }
     #progress-monitor .crawl-stats {
         display: flex;
         gap: 12px;
@@ -944,7 +965,10 @@
         }
 
         // Show snapshot info or URL count if no snapshots yet
-        let metaText = `depth: ${crawl.max_depth || 0}`;
+        const maxUrlsText = (crawl.max_urls || 0) > 0 ? `${crawl.max_urls} max URLs` : 'all URLs';
+        const crawlSizeText = crawl.max_crawl_size_display || 'unlimited';
+        const snapshotSizeText = crawl.max_snapshot_size_display || 'unlimited';
+        let metaText = `by ${escapeHtml(crawl.created_by || 'unknown')} | persona: ${escapeHtml(crawl.persona || 'Default')} | depth: ${crawl.max_depth || 0} | ${maxUrlsText} | crawl: ${escapeHtml(crawlSizeText)} | snapshot: ${escapeHtml(snapshotSizeText)}`;
         if ((crawl.total_snapshots || 0) > 0) {
             metaText += ` | ${crawl.total_snapshots} snapshots`;
         } else if ((crawl.urls_count || 0) > 0) {
@@ -952,6 +976,9 @@
         } else if (crawl.urls_preview) {
             metaText += ` | ${escapeHtml(crawl.urls_preview.substring(0, 40))}${crawl.urls_preview.length > 40 ? '...' : ''}`;
         }
+        const tagsHtml = (crawl.tags || []).length
+            ? `<div class="crawl-tags">${crawl.tags.map(tag => `<span class="crawl-tag" title="${escapeAttr(tag)}">${escapeHtml(tag)}</span>`).join('')}</div>`
+            : '';
 
         return `
             <div class="crawl-item" data-crawl-id="${crawl.id || 'unknown'}">
@@ -961,6 +988,7 @@
                             <div class="crawl-info">
                             <div class="crawl-label">Crawl: ${escapeHtml(crawl.label || '(no label)')}</div>
                             <div class="crawl-meta">${metaText}</div>
+                            ${tagsHtml}
                         </div>
                         <div class="crawl-stats">
                             <span style="color:#3fb950">${crawl.completed_snapshots || 0} done</span>

etc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "archivebox",
-  "version": "0.9.32rc9",
+  "version": "0.9.32rc10",
   "repository": "github:ArchiveBox/ArchiveBox",
   "license": "MIT",
   "dependencies": {

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "archivebox"
-version = "0.9.32rc9"
+version = "0.9.32rc10"
 requires-python = ">=3.13"
 description = "Self-hosted internet archiving solution."
 authors = [{name = "Nick Sweeting", email = "pyproject.toml@archivebox.io"}]