release: bump version to 0.68.0

backend/app/api/v1/datasources.py

@@ -19,7 +19,6 @@ from app.models.datasource_config import DataSourceConfig
 from app.models.task import CollectionTask
 from app.models.user import User
 from app.models.vessel import AISRawObservation
-from app.services.vessel_ais_aggregation import VESSEL_AIS_SCHEMA
 from app.services.scheduler import (
     sync_datasource_job,
 )
@@ -165,6 +164,8 @@ async def _load_latest_tasks(
 async def _load_collected_record_counts(
     db: AsyncSession,
     sources: list[str],
+    *,
+    exact_vessel_counts: bool = False,
 ) -> dict[str, int]:
     if not sources:
         return {}
@@ -185,14 +186,46 @@ async def _load_collected_record_counts(
         or "ais" in source
     ]
     if vessel_sources:
-        raw_result = await db.execute(
-            select(AISRawObservation.source, func.count(AISRawObservation.id))
-            .where(AISRawObservation.target_schema == VESSEL_AIS_SCHEMA)
-            .where(AISRawObservation.source.in_(vessel_sources))
-            .group_by(AISRawObservation.source)
+        if exact_vessel_counts:
+            exact_result = await db.execute(
+                select(AISRawObservation.source, func.count(AISRawObservation.id))
+                .where(AISRawObservation.source.in_(vessel_sources))
+                .group_by(AISRawObservation.source)
+            )
+            for source, count in exact_result.all():
+                counts[source] = max(counts.get(source, 0), int(count or 0))
+            return counts
+
+        # AIS raw observations can be tens of millions of rows. Use planner
+        # statistics for the datasource list instead of blocking page load on
+        # source-level count(*) scans.
+        stats_result = await db.execute(
+            text(
+                """
+                SELECT
+                    COALESCE(pg_class.reltuples, 0)::bigint AS total_rows,
+                    pg_stats.most_common_vals::text AS source_values,
+                    pg_stats.most_common_freqs::text AS source_freqs
+                FROM pg_class
+                LEFT JOIN pg_stats
+                  ON pg_stats.schemaname = 'public'
+                 AND pg_stats.tablename = 'ais_raw_observations'
+                 AND pg_stats.attname = 'source'
+                WHERE pg_class.relname = 'ais_raw_observations'
+                LIMIT 1
+                """
+            )
         )
-        for source, count in raw_result.all():
-            counts[source] = max(counts.get(source, 0), int(count or 0))
+        stats = stats_result.mappings().first()
+        if stats:
+            total_rows = int(stats["total_rows"] or 0)
+            values = str(stats["source_values"] or "").strip("{}")
+            freqs = str(stats["source_freqs"] or "").strip("{}")
+            source_values = [value.strip('"') for value in values.split(",") if value]
+            source_freqs = [float(value) for value in freqs.split(",") if value]
+            for source, freq in zip(source_values, source_freqs):
+                if source in vessel_sources:
+                    counts[source] = max(counts.get(source, 0), int(round(total_rows * freq)))
 
     return counts
 
@@ -929,7 +962,7 @@ async def get_datasource_row(
         [datasource],
         include_endpoint=include_endpoint,
     )
-    record_counts = await _load_collected_record_counts(db, [datasource.source])
+    record_counts = await _load_collected_record_counts(db, [datasource.source], exact_vessel_counts=True)
     return {
         "data": serialize_datasource_row(
             datasource,

backend/app/api/v1/tasks.py

@@ -29,7 +29,8 @@ async def list_tasks(
         SELECT ct.id, ct.datasource_id, ds.name as datasource_name, ct.status,
                ct.started_at, ct.completed_at, ct.records_processed, ct.error_message,
                ct.phase, ct.phase_progress, ct.phase_message, ct.phase_current,
-               ct.phase_total, ct.phase_unit, ct.total_records, ct.progress
+               ct.phase_total, ct.phase_unit, ct.total_records, ct.progress,
+               ct.task_type, ct.source, ds.source as datasource_source
         FROM collection_tasks ct
         JOIN data_sources ds ON ct.datasource_id = ds.id
         WHERE 1=1
@@ -39,12 +40,19 @@ async def list_tasks(
 
     if datasource_id:
         query += " AND ct.datasource_id = :datasource_id"
-        count_query += " WHERE ct.datasource_id = :datasource_id"
+        count_query += " AND ct.datasource_id = :datasource_id"
         params["datasource_id"] = datasource_id
     if status:
-        query += " AND ct.status = :status"
-        count_query += " AND ct.status = :status"
-        params["status"] = status
+        statuses = [item.strip() for item in status.split(",") if item.strip()]
+        if len(statuses) > 1:
+            placeholders = ", ".join(f":status_{index}" for index, _item in enumerate(statuses))
+            query += f" AND ct.status IN ({placeholders})"
+            count_query += f" AND ct.status IN ({placeholders})"
+            params.update({f"status_{index}": item for index, item in enumerate(statuses)})
+        else:
+            query += " AND ct.status = :status"
+            count_query += " AND ct.status = :status"
+            params["status"] = statuses[0] if statuses else status
 
     query += f" ORDER BY ct.created_at DESC LIMIT {page_size} OFFSET {offset}"
 
@@ -76,6 +84,9 @@ async def list_tasks(
                 "phase_unit": t[13],
                 "total_records": t[14],
                 "progress": t[15],
+                "task_type": t[16],
+                "source": t[17] or t[18],
+                "datasource_source": t[18],
             }
             for t in tasks
         ],