release: bump version to 0.71.1

backend/app/services/earth_news.py

@@ -2307,7 +2307,10 @@ def _diversify_news_items_for_locale(
     buckets: dict[str, list[ParsedNewsItem]] = {}
     order: list[str] = []
     for item in ranked:
-        key = _news_item_source_id(item) or item.source or item.feed_name or item.id
+        if active_region == "global":
+            key = item.feed_region or "global"
+        else:
+            key = _news_item_source_id(item) or item.source or item.feed_name or item.id
         if key not in buckets:
             buckets[key] = []
             order.append(key)
@@ -2751,6 +2754,7 @@ async def get_earth_news_payload(
             )
         await record_earth_news_sources_health(db, health_by_source)
         ranked_fetched_items = _rank_and_trim_items(fetched_items, active_region=active_region)
+        await _enqueue_unverified_locations(ranked_fetched_items)
         await upsert_earth_news_items(db, ranked_fetched_items)
 
     items = await _call_store_list_items(
@@ -2802,7 +2806,8 @@ async def get_earth_news_payload(
         )
     else:
         cruise_items = items
-    await _enqueue_unverified_locations(items)
+    enqueue_candidates = {item.id: item for item in [*items, *cruise_items] if item.id}
+    await _enqueue_unverified_locations(list(enqueue_candidates.values()))
     stale = bool(errors and items)
 
     return _build_payload(

backend/app/services/earth_news_queue.py

@@ -14,10 +14,14 @@ from app.core.logging import get_logger
 logger = get_logger(__name__, service="earth_news")
 
 TARGET_LOCATION_STREAM = "earth_news:target_location:jobs"
+TARGET_LOCATION_PRIORITY_STREAM = "earth_news:target_location:priority"
 TARGET_LOCATION_GROUP = "earth_news_target_location"
 TARGET_LOCATION_DEAD_LETTER_STREAM = "earth_news:target_location:dead"
 TARGET_LOCATION_RESULT_TTL_SECONDS = 60 * 60 * 12
 TARGET_LOCATION_JOB_DEDUP_TTL_SECONDS = 60 * 60 * 6
+TARGET_LOCATION_PRIORITY_JOB_DEDUP_TTL_SECONDS = 60 * 5
+TARGET_LOCATION_PENDING_RECLAIM_IDLE_MS = 2 * 60 * 1000
+TARGET_LOCATION_PRIORITY_READ_BLOCK_MS = 1
 TARGET_LOCATION_MAX_ATTEMPTS = 3
 
 _redis_client: redis.Redis | None = None
@@ -28,6 +32,7 @@ class NewsTargetLocationMessage:
     message_id: str
     item_id: str
     payload: dict[str, Any]
+    stream_name: str = TARGET_LOCATION_STREAM
     attempts: int = 0
 
 
@@ -44,7 +49,7 @@ class NewsTargetLocationQueue(Protocol):
     ) -> list[NewsTargetLocationMessage]:
         ...
 
-    async def ack(self, message_id: str) -> None:
+    async def ack(self, message: NewsTargetLocationMessage) -> None:
         ...
 
     async def retry_or_dead_letter(
@@ -71,6 +76,10 @@ def _queued_key(item_id: str) -> str:
     return f"earth_news:target_location:queued:{item_id}"
 
 
+def _priority_queued_key(item_id: str) -> str:
+    return f"earth_news:target_location:priority_queued:{item_id}"
+
+
 class RedisStreamsNewsTargetLocationQueue:
     def __init__(self, client: redis.Redis | None = None) -> None:
         self.client = client or _get_redis_client()
@@ -79,34 +88,44 @@ class RedisStreamsNewsTargetLocationQueue:
     async def _ensure_group(self) -> None:
         if self._group_ready:
             return
-        try:
-            await self.client.xgroup_create(
-                TARGET_LOCATION_STREAM,
-                TARGET_LOCATION_GROUP,
-                id="0",
-                mkstream=True,
-            )
-        except ResponseError as exc:
-            if "BUSYGROUP" not in str(exc):
-                raise
+        for stream_name in (TARGET_LOCATION_PRIORITY_STREAM, TARGET_LOCATION_STREAM):
+            try:
+                await self.client.xgroup_create(
+                    stream_name,
+                    TARGET_LOCATION_GROUP,
+                    id="0",
+                    mkstream=True,
+                )
+            except ResponseError as exc:
+                if "BUSYGROUP" not in str(exc):
+                    raise
         self._group_ready = True
 
     async def enqueue(self, *, item_id: str, payload: dict[str, Any], force: bool = False) -> bool:
         await self._ensure_group()
         if force:
-            await self.client.delete(_result_key(item_id), _queued_key(item_id))
+            await self.client.delete(_result_key(item_id))
+            queued_key = _priority_queued_key(item_id)
         elif await self.client.exists(_result_key(item_id)):
             return False
+        else:
+            queued_key = _queued_key(item_id)
+        dedup_ttl = (
+            TARGET_LOCATION_PRIORITY_JOB_DEDUP_TTL_SECONDS
+            if force
+            else TARGET_LOCATION_JOB_DEDUP_TTL_SECONDS
+        )
         queued = await self.client.set(
-            _queued_key(item_id),
+            queued_key,
             "1",
             nx=True,
-            ex=TARGET_LOCATION_JOB_DEDUP_TTL_SECONDS,
+            ex=dedup_ttl,
         )
         if not queued:
-            return bool(await self.client.exists(_queued_key(item_id)))
+            return bool(await self.client.exists(queued_key))
+        stream_name = TARGET_LOCATION_PRIORITY_STREAM if force else TARGET_LOCATION_STREAM
         await self.client.xadd(
-            TARGET_LOCATION_STREAM,
+            stream_name,
             {
                 "item_id": item_id,
                 "attempts": "0",
@@ -123,39 +142,104 @@ class RedisStreamsNewsTargetLocationQueue:
         block_ms: int,
     ) -> list[NewsTargetLocationMessage]:
         await self._ensure_group()
-        streams = await self.client.xreadgroup(
+        streams = []
+        priority_claimed = await self._claim_stale_messages(
+            stream_name=TARGET_LOCATION_PRIORITY_STREAM,
+            consumer_name=consumer_name,
+            count=count,
+        )
+        if priority_claimed:
+            return priority_claimed
+
+        priority_messages = await self.client.xreadgroup(
             TARGET_LOCATION_GROUP,
             consumer_name,
-            {TARGET_LOCATION_STREAM: ">"},
+            {TARGET_LOCATION_PRIORITY_STREAM: ">"},
             count=count,
-            block=block_ms,
+            block=TARGET_LOCATION_PRIORITY_READ_BLOCK_MS,
         )
+        if priority_messages:
+            streams = priority_messages
+        else:
+            regular_claimed = await self._claim_stale_messages(
+                stream_name=TARGET_LOCATION_STREAM,
+                consumer_name=consumer_name,
+                count=count,
+            )
+            if regular_claimed:
+                return regular_claimed
+            streams = await self.client.xreadgroup(
+                TARGET_LOCATION_GROUP,
+                consumer_name,
+                {TARGET_LOCATION_STREAM: ">"},
+                count=count,
+                block=block_ms,
+            )
         messages: list[NewsTargetLocationMessage] = []
-        for _stream_name, stream_messages in streams:
+        for stream_name, stream_messages in streams:
             for message_id, fields in stream_messages:
-                raw_payload = fields.get("payload")
-                item_id = fields.get("item_id")
-                if not raw_payload or not item_id:
-                    await self.ack(message_id)
-                    continue
-                try:
-                    payload = json.loads(raw_payload)
-                except json.JSONDecodeError:
-                    await self.ack(message_id)
-                    continue
-                attempts = int(fields.get("attempts") or 0)
-                messages.append(
-                    NewsTargetLocationMessage(
-                        message_id=message_id,
-                        item_id=item_id,
-                        payload=payload,
-                        attempts=attempts,
-                    )
-                )
+                message = await self._message_from_fields(stream_name, message_id, fields)
+                if message is not None:
+                    messages.append(message)
         return messages
 
-    async def ack(self, message_id: str) -> None:
-        await self.client.xack(TARGET_LOCATION_STREAM, TARGET_LOCATION_GROUP, message_id)
+    async def _claim_stale_messages(
+        self,
+        *,
+        stream_name: str,
+        consumer_name: str,
+        count: int,
+    ) -> list[NewsTargetLocationMessage]:
+        try:
+            _next_id, claimed, _deleted = await self.client.xautoclaim(
+                stream_name,
+                TARGET_LOCATION_GROUP,
+                consumer_name,
+                TARGET_LOCATION_PENDING_RECLAIM_IDLE_MS,
+                start_id="0-0",
+                count=count,
+            )
+        except ResponseError:
+            return []
+        messages: list[NewsTargetLocationMessage] = []
+        for message_id, fields in claimed:
+            message = await self._message_from_fields(stream_name, message_id, fields)
+            if message is not None:
+                messages.append(message)
+        return messages
+
+    async def _message_from_fields(
+        self,
+        stream_name: str,
+        message_id: str,
+        fields: dict[str, str],
+    ) -> NewsTargetLocationMessage | None:
+        raw_payload = fields.get("payload")
+        item_id = fields.get("item_id")
+        if not raw_payload or not item_id:
+            await self._discard_message(stream_name, message_id)
+            return None
+        try:
+            payload = json.loads(raw_payload)
+        except json.JSONDecodeError:
+            await self._discard_message(stream_name, message_id)
+            return None
+        attempts = int(fields.get("attempts") or 0)
+        return NewsTargetLocationMessage(
+            message_id=message_id,
+            item_id=item_id,
+            payload=payload,
+            stream_name=stream_name,
+            attempts=attempts,
+        )
+
+    async def ack(self, message: NewsTargetLocationMessage) -> None:
+        await self.client.xack(message.stream_name, TARGET_LOCATION_GROUP, message.message_id)
+        await self.client.xdel(message.stream_name, message.message_id)
+
+    async def _discard_message(self, stream_name: str, message_id: str) -> None:
+        await self.client.xack(stream_name, TARGET_LOCATION_GROUP, message_id)
+        await self.client.xdel(stream_name, message_id)
 
     async def retry_or_dead_letter(
         self,
@@ -163,7 +247,7 @@ class RedisStreamsNewsTargetLocationQueue:
         *,
         error: str,
     ) -> None:
-        await self.ack(message.message_id)
+        await self.ack(message)
         if message.attempts + 1 >= TARGET_LOCATION_MAX_ATTEMPTS:
             await self.client.xadd(
                 TARGET_LOCATION_DEAD_LETTER_STREAM,
@@ -176,7 +260,7 @@ class RedisStreamsNewsTargetLocationQueue:
             )
             return
         await self.client.xadd(
-            TARGET_LOCATION_STREAM,
+            message.stream_name,
             {
                 "item_id": message.item_id,
                 "attempts": str(message.attempts + 1),
@@ -231,4 +315,4 @@ async def save_target_location_patch(item_id: str, patch: dict[str, Any]) -> Non
         TARGET_LOCATION_RESULT_TTL_SECONDS,
         json.dumps(patch, ensure_ascii=False),
     )
-    await client.delete(_queued_key(item_id))
+    await client.delete(_queued_key(item_id), _priority_queued_key(item_id))

backend/app/services/earth_news_store.py

@@ -19,6 +19,17 @@ from app.services.earth_news_classification import (
     normalize_breaking_scope,
 )
 
+CRUISE_REGION_ORDER = (
+    "americas",
+    "europe",
+    "middle-east-africa",
+    "asia-pacific",
+    "global",
+)
+CRUISE_REGION_QUERY_MULTIPLIER = 12
+CRUISE_REGION_QUERY_MIN_LIMIT = 240
+CRUISE_REGION_QUERY_MAX_LIMIT = 1000
+
 
 def _coerce_datetime(value: datetime | None) -> datetime | None:
     if value is None:
@@ -106,6 +117,41 @@ def _sort_parsed_news_items(items: list[ParsedNewsItem], *, active_region: str)
     )
 
 
+def _diversify_parsed_news_items_by_region(
+    items: list[ParsedNewsItem],
+    *,
+    limit: int,
+) -> list[ParsedNewsItem]:
+    if limit <= 0:
+        return []
+    sorted_items = _sort_parsed_news_items(items, active_region="global")
+    buckets: dict[str, list[ParsedNewsItem]] = {}
+    for item in sorted_items:
+        region = item.feed_region or "global"
+        buckets.setdefault(region, []).append(item)
+
+    ordered_regions = [
+        *[region for region in CRUISE_REGION_ORDER if buckets.get(region)],
+        *sorted(region for region in buckets if region not in CRUISE_REGION_ORDER),
+    ]
+    diversified: list[ParsedNewsItem] = []
+    cursor = 0
+    while len(diversified) < limit:
+        added = False
+        for region in ordered_regions:
+            bucket = buckets.get(region) or []
+            if cursor >= len(bucket):
+                continue
+            diversified.append(bucket[cursor])
+            added = True
+            if len(diversified) >= limit:
+                break
+        if not added:
+            break
+        cursor += 1
+    return diversified
+
+
 def _query_sort_key(active_region: str):
     if active_region == "global":
         return (
@@ -167,6 +213,8 @@ async def list_earth_news_items(
         [record_to_parsed_news_item(record) for record in records],
         active_region=active_region,
     )
+    if active_region == "global" and not source_ids:
+        return _diversify_parsed_news_items_by_region(items, limit=limit)
     return items[:limit]
 
 
@@ -177,15 +225,20 @@ async def list_earth_news_cruise_items(
     categories: set[str] | None = None,
     source_ids: set[str] | None = None,
 ) -> list[ParsedNewsItem]:
+    query_limit = min(
+        max(limit * CRUISE_REGION_QUERY_MULTIPLIER, CRUISE_REGION_QUERY_MIN_LIMIT),
+        CRUISE_REGION_QUERY_MAX_LIMIT,
+    )
     query = (
         select(EarthNewsItem)
         .order_by(
-            EarthNewsItem.region.asc(),
+            EarthNewsItem.published_at.is_(None),
             EarthNewsItem.published_at.desc().nullslast(),
             EarthNewsItem.last_seen_at.desc(),
+            EarthNewsItem.region.asc(),
             EarthNewsItem.feed_name.asc(),
         )
-        .limit(min(max(limit * 4, limit), 200))
+        .limit(query_limit)
     )
     category_clause = _category_filter_clause(categories)
     if category_clause is not None:
@@ -194,11 +247,10 @@ async def list_earth_news_cruise_items(
     if source_clause is not None:
         query = query.where(source_clause)
     result = await db.execute(query)
-    items = _sort_parsed_news_items(
+    return _diversify_parsed_news_items_by_region(
         [record_to_parsed_news_item(record) for record in result.scalars().all()],
-        active_region="global",
+        limit=limit,
     )
-    return items[:limit]
 
 
 async def get_earth_news_freshness(

backend/app/services/earth_news_worker.py

@@ -29,6 +29,9 @@ logger = get_logger(__name__, service="earth_news")
 WORKER_BATCH_SIZE = 4
 WORKER_BLOCK_MS = 5000
 WORKER_BACKOFF_SECONDS = 5.0
+WORKER_JOB_TIMEOUT_MIN_SECONDS = 20.0
+WORKER_JOB_TIMEOUT_MAX_SECONDS = 90.0
+WORKER_JOB_TIMEOUT_GRACE_SECONDS = 10.0
 
 _worker_task: asyncio.Task | None = None
 
@@ -109,12 +112,25 @@ async def _run_target_location_worker() -> None:
         if not messages:
             continue
         provider_client = await _build_provider_client()
-        for message in messages:
+        job_timeout = _get_worker_job_timeout(provider_client)
+
+        async def handle_message(message: NewsTargetLocationMessage) -> None:
             try:
-                await process_target_location_message(message, provider_client=provider_client)
-                await queue.ack(message.message_id)
+                await asyncio.wait_for(
+                    process_target_location_message(message, provider_client=provider_client),
+                    timeout=job_timeout,
+                )
+                await queue.ack(message)
             except asyncio.CancelledError:
                 raise
+            except TimeoutError as exc:
+                logger.warning_event(
+                    "Earth news target location worker job timed out",
+                    event="earth_news.target_location.worker_job_timeout",
+                    context={"item_id": message.item_id, "timeout_seconds": job_timeout},
+                )
+                with suppress(Exception):
+                    await queue.retry_or_dead_letter(message, error=str(exc) or "job timed out")
             except Exception as exc:
                 logger.warning_event(
                     "Earth news target location worker job failed",
@@ -124,6 +140,8 @@ async def _run_target_location_worker() -> None:
                 with suppress(Exception):
                     await queue.retry_or_dead_letter(message, error=str(exc))
 
+        await asyncio.gather(*(handle_message(message) for message in messages))
+
 
 def start_earth_news_target_worker() -> None:
     global _worker_task
@@ -140,3 +158,15 @@ async def stop_earth_news_target_worker() -> None:
     with suppress(asyncio.CancelledError):
         await task
     _worker_task = None
+
+
+def _get_worker_job_timeout(provider_client: AIProviderClient | None) -> float:
+    timeout = float(getattr(provider_client, "timeout", 0) or WORKER_JOB_TIMEOUT_MIN_SECONDS)
+    retry_attempts = float(getattr(provider_client, "retry_attempts", 1) or 1)
+    return min(
+        max(
+            timeout * retry_attempts + WORKER_JOB_TIMEOUT_GRACE_SECONDS,
+            WORKER_JOB_TIMEOUT_MIN_SECONDS,
+        ),
+        WORKER_JOB_TIMEOUT_MAX_SECONDS,
+    )