release: bump version to 0.66.0

backend/app/api/v1/datasources.py

@@ -1,4 +1,3 @@
-import asyncio
 from datetime import datetime, timedelta, timezone
 from typing import Optional
 
@@ -7,7 +6,7 @@ from pydantic import BaseModel, Field
 from sqlalchemy import func, or_, select, text
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.core.cache import cache
+from app.core.logging import get_logger
 from app.core.time import to_iso8601_utc
 from app.core.security import get_current_user
 from app.core.data_sources import get_data_sources_config
@@ -22,16 +21,26 @@ 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 (
-    cancel_running_collector_now,
-    get_latest_task_id_for_datasource,
-    run_collector_now,
     sync_datasource_job,
 )
-from app.services.earth_layer_cache import invalidate_earth_layer_cache_for_source
+from app.services.data_jobs import (
+    JOB_STATUS_CANCELLING,
+    JOB_STATUS_QUEUED,
+    JOB_STATUS_RUNNING,
+    JOB_TYPE_CLEAR_CACHE,
+    JOB_TYPE_CLEAR_DATA,
+    JOB_TYPE_COLLECT,
+    enqueue_datasource_job,
+    get_active_datasource_job,
+    request_cancel_datasource_task,
+)
+from app.services.business_logs import emit_business_log
 
 router = APIRouter()
+logger = get_logger(__name__, service="api")
 STALE_RUNNING_TASK_TIMEOUT_MINUTES = 90
 
+
 PRODUCT_SOURCE_KEYWORDS: tuple[tuple[str, tuple[str, ...]], ...] = (
     ("vessels", ("vessel", "ais")),
     ("cables", ("cable", "landing", "telegeography", "arcgis", "fao")),
@@ -115,7 +124,7 @@ async def _load_latest_running_tasks(
             _task_rank_column(CollectionTask.started_at),
         )
         .where(CollectionTask.datasource_id.in_(datasource_ids))
-        .where(CollectionTask.status == "running")
+        .where(CollectionTask.status.in_((JOB_STATUS_QUEUED, JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING)))
         .subquery()
     )
     result = await db.execute(
@@ -126,32 +135,6 @@ async def _load_latest_running_tasks(
     return {task.datasource_id: task for task in result.scalars().all()}
 
 
-async def _load_latest_task_ids(
-    db: AsyncSession,
-    datasource_ids: list[int],
-) -> dict[int, int]:
-    if not datasource_ids:
-        return {}
-
-    ranked_tasks = (
-        select(
-            CollectionTask.id.label("task_id"),
-            CollectionTask.datasource_id.label("datasource_id"),
-            func.row_number().over(
-                partition_by=CollectionTask.datasource_id,
-                order_by=CollectionTask.id.desc(),
-            ).label("row_num"),
-        )
-        .where(CollectionTask.datasource_id.in_(datasource_ids))
-        .subquery()
-    )
-    result = await db.execute(
-        select(ranked_tasks.c.datasource_id, ranked_tasks.c.task_id)
-        .where(ranked_tasks.c.row_num == 1)
-    )
-    return {datasource_id: task_id for datasource_id, task_id in result.all()}
-
-
 async def _load_latest_tasks(
     db: AsyncSession,
     datasource_ids: list[int],
@@ -303,8 +286,11 @@ def serialize_datasource_row(
         "last_run": to_iso8601_utc(last_run_at),
         "last_run_at": to_iso8601_utc(last_run_at),
         "last_status": last_status,
-        "is_running": running_task is not None,
+        "is_running": running_task is not None and running_task.task_type == JOB_TYPE_COLLECT,
+        "is_task_active": running_task is not None,
+        "task_status": running_task.status if running_task else None,
         "task_id": display_task.id if display_task else None,
+        "task_type": display_task.task_type if display_task else None,
         "progress": display_task.progress if display_task else None,
         "phase": display_task.phase if display_task else None,
         "phase_progress": display_task.phase_progress if display_task else None,
@@ -400,9 +386,25 @@ async def _trigger_datasource_batch(
     datasources: list[DataSource],
     *,
     force: bool,
+    actor_id: int | None = None,
+    trigger_kind: str = "batch",
 ) -> dict:
+    await emit_business_log(
+        logger,
+        event=f"collector.trigger.{trigger_kind}.start",
+        message="Datasource batch trigger started",
+        category="collector",
+        service="api",
+        module=__name__,
+        user_id=actor_id,
+        context={
+            "trigger_kind": trigger_kind,
+            "force": force,
+            "requested_count": len(datasources),
+        },
+    )
     if not datasources:
-        return {
+        result = {
             "status": "noop",
             "message": "No matching data sources to trigger",
             "force": force,
@@ -410,8 +412,18 @@ async def _trigger_datasource_batch(
             "skipped": [],
             "failed": [],
         }
+        await emit_business_log(
+            logger,
+            event=f"collector.trigger.{trigger_kind}.completed",
+            message="Datasource batch trigger completed with no matching sources",
+            category="collector",
+            service="api",
+            module=__name__,
+            user_id=actor_id,
+            context={"trigger_kind": trigger_kind, "force": force, "status": "noop", "triggered_count": 0},
+        )
+        return result
 
-    previous_task_ids: dict[int, Optional[int]] = {}
     triggered_sources: list[dict] = []
     skipped_sources: list[dict] = []
     failed_sources: list[dict] = []
@@ -446,9 +458,11 @@ async def _trigger_datasource_batch(
                     }
                 )
                 continue
-            cancelled = await cancel_running_collector_now(datasource.source)
-            if not cancelled:
-                await rollback_orphaned_running_task(db, datasource, running_task)
+            await request_cancel_datasource_task(
+                db,
+                running_task,
+                reason="superseded_by_forced_collection",
+            )
 
         if not force and not is_due_for_collection(datasource, now):
             skipped_sources.append(
@@ -465,57 +479,51 @@ async def _trigger_datasource_batch(
             )
             continue
 
-        previous_task_ids[datasource.id] = None
-        success = run_collector_now(datasource.source)
-        if not success:
-            failed_sources.append(
-                {
-                    "id": datasource.id,
-                    "source": datasource.source,
-                    "name": datasource.name,
-                    "reason": "trigger_failed",
-                }
-            )
-            continue
+        task = await enqueue_datasource_job(
+            db,
+            datasource,
+            JOB_TYPE_COLLECT,
+            payload={"force": force, "trigger": "batch"},
+        )
 
         triggered_sources.append(
             {
                 "id": datasource.id,
                 "source": datasource.source,
                 "name": datasource.name,
-                "task_id": None,
+                "task_id": task.id,
             }
         )
 
-    latest_task_ids = await _load_latest_task_ids(
-        db,
-        [datasource.id for datasource in datasources],
-    )
-    for datasource_id in previous_task_ids:
-        previous_task_ids[datasource_id] = latest_task_ids.get(datasource_id)
-
-    for _ in range(20):
-        await asyncio.sleep(0.1)
-        pending = [item for item in triggered_sources if item["task_id"] is None]
-        if not pending:
-            break
-        latest_task_ids = await _load_latest_task_ids(
-            db,
-            [item["id"] for item in pending],
-        )
-        for item in pending:
-            task_id = latest_task_ids.get(item["id"])
-            if task_id is not None and task_id != previous_task_ids.get(item["id"]):
-                item["task_id"] = task_id
-
-    return {
-        "status": "triggered" if triggered_sources else "partial",
-        "message": f"Triggered {len(triggered_sources)} data sources",
+    result = {
+        "status": "queued" if triggered_sources else "partial",
+        "message": f"Queued {len(triggered_sources)} data source jobs",
         "force": force,
         "triggered": triggered_sources,
         "skipped": skipped_sources,
         "failed": failed_sources,
     }
+    await emit_business_log(
+        logger,
+        event=f"collector.trigger.{trigger_kind}.completed",
+        message="Datasource batch trigger completed",
+        category="collector",
+        service="api",
+        module=__name__,
+        user_id=actor_id,
+        context={
+            "trigger_kind": trigger_kind,
+            "force": force,
+            "status": result["status"],
+            "requested_count": len(datasources),
+            "triggered_count": len(triggered_sources),
+            "skipped_count": len(skipped_sources),
+            "failed_count": len(failed_sources),
+            "triggered_sources": [item["source"] for item in triggered_sources],
+            "skipped_reasons": [item["reason"] for item in skipped_sources],
+        },
+    )
+    return result
 
 
 async def get_datasource_record(db: AsyncSession, source_id: str) -> Optional[DataSource]:
@@ -780,7 +788,13 @@ async def trigger_all_datasources(
         .order_by(DataSource.module, DataSource.id)
     )
     datasources = result.scalars().all()
-    return await _trigger_datasource_batch(db, datasources, force=force)
+    return await _trigger_datasource_batch(
+        db,
+        datasources,
+        force=force,
+        actor_id=current_user.id,
+        trigger_kind="all",
+    )
 
 
 @router.post("/trigger-batch")
@@ -816,7 +830,13 @@ async def trigger_datasource_batch(
         collected=None if payload.source_ids else payload.collected,
         credential_status=None if payload.source_ids else payload.credential_status,
     )
-    return await _trigger_datasource_batch(db, datasources, force=payload.force)
+    return await _trigger_datasource_batch(
+        db,
+        datasources,
+        force=payload.force,
+        actor_id=current_user.id,
+        trigger_kind="batch",
+    )
 
 
 @router.get("/snapshots")
@@ -992,8 +1012,24 @@ async def trigger_datasource(
     if not datasource.is_active:
         raise HTTPException(status_code=400, detail="Data source is disabled")
 
-    running_task = await get_running_task(db, datasource.id)
+    running_task = await get_active_datasource_job(db, datasource.id, task_types=(JOB_TYPE_COLLECT,))
     if running_task is not None and not force:
+        await emit_business_log(
+            logger,
+            event="collector.trigger.single.skipped_already_running",
+            message="Datasource trigger skipped because a task is already running",
+            category="collector",
+            level="warning",
+            service="api",
+            module=__name__,
+            user_id=current_user.id,
+            context={
+                "collector_name": datasource.source,
+                "datasource_id": datasource.id,
+                "task_id": running_task.id,
+                "status": "skipped",
+            },
+        )
         raise HTTPException(
             status_code=409,
             detail={
@@ -1013,31 +1049,42 @@ async def trigger_datasource(
         )
 
     if running_task is not None and force:
-        cancelled = await cancel_running_collector_now(datasource.source)
-        if not cancelled:
-            await rollback_orphaned_running_task(db, datasource, running_task)
+        await request_cancel_datasource_task(
+            db,
+            running_task,
+            reason="superseded_by_forced_collection",
+        )
 
-    previous_task_id = await get_latest_task_id_for_datasource(datasource.id)
-    success = run_collector_now(datasource.source)
-    if not success:
-        raise HTTPException(status_code=500, detail=f"Failed to trigger collector '{datasource.source}'")
-
-    task_id = None
-    for _ in range(20):
-        await asyncio.sleep(0.1)
-        task_id = await get_latest_task_id_for_datasource(datasource.id)
-        if task_id is not None and task_id != previous_task_id:
-            break
-    if task_id == previous_task_id:
-        task_id = None
+    task = await enqueue_datasource_job(
+        db,
+        datasource,
+        JOB_TYPE_COLLECT,
+        payload={"force": force, "trigger": "single"},
+    )
+    await emit_business_log(
+        logger,
+        event="collector.trigger.single.completed",
+        message="Datasource trigger queued",
+        category="collector",
+        service="api",
+        module=__name__,
+        user_id=current_user.id,
+        context={
+            "collector_name": datasource.source,
+            "datasource_id": datasource.id,
+            "task_id": task.id,
+            "force": force,
+            "status": "queued",
+        },
+    )
 
     return {
-        "status": "triggered",
+        "status": "queued",
         "source_id": datasource.id,
-        "task_id": task_id,
+        "task_id": task.id,
         "collector_name": datasource.source,
         "force": force,
-        "message": f"Collector '{datasource.source}' has been triggered",
+        "message": f"Collector '{datasource.source}' has been queued",
     }
 
 
@@ -1051,22 +1098,30 @@ async def clear_datasource_data(
     if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    result = await db.execute(
-        select(func.count(CollectedData.id)).where(CollectedData.source == datasource.source)
+    active_task = await get_active_datasource_job(db, datasource.id)
+    if active_task is not None:
+        raise HTTPException(
+            status_code=409,
+            detail={
+                "reason": "datasource_job_in_progress",
+                "message": "当前数据源已有任务在执行，请等待完成或先取消任务。",
+                "task_id": active_task.id,
+                "task_type": active_task.task_type,
+                "status": active_task.status,
+            },
+        )
+    task = await enqueue_datasource_job(
+        db,
+        datasource,
+        JOB_TYPE_CLEAR_DATA,
+        payload={"source": datasource.source},
     )
-    count = result.scalar() or 0
-
-    if count == 0:
-        return {"status": "success", "message": "No data to clear", "deleted_count": 0}
-
-    delete_query = CollectedData.__table__.delete().where(CollectedData.source == datasource.source)
-    await db.execute(delete_query)
-    await db.commit()
 
     return {
-        "status": "success",
-        "message": f"Cleared {count} records for data source '{datasource.name}'",
-        "deleted_count": count,
+        "status": "queued",
+        "message": f"Queued data clearing for data source '{datasource.name}'",
+        "task_id": task.id,
+        "deleted_count": None,
     }
 
 
@@ -1080,16 +1135,44 @@ async def clear_datasource_cache(
     if not datasource:
         raise HTTPException(status_code=404, detail="Data source not found")
 
-    earth_deleted_count = invalidate_earth_layer_cache_for_source(datasource.source)
-    dashboard_deleted_count = int(cache.delete("dashboard:stats")) + int(cache.delete("dashboard:summary"))
-    deleted_count = earth_deleted_count + dashboard_deleted_count
+    task = await enqueue_datasource_job(
+        db,
+        datasource,
+        JOB_TYPE_CLEAR_CACHE,
+        payload={"source": datasource.source},
+        dedupe_key=f"clear_cache:{datasource.source}",
+    )
 
     return {
-        "status": "success",
-        "message": f"Cleared {deleted_count} cache keys for data source '{datasource.name}'",
-        "deleted_count": deleted_count,
-        "earth_layer_deleted_count": earth_deleted_count,
-        "dashboard_deleted_count": dashboard_deleted_count,
+        "status": "queued",
+        "message": f"Queued cache clearing for data source '{datasource.name}'",
+        "task_id": task.id,
+        "deleted_count": None,
+    }
+
+
+@router.post("/{source_id}/tasks/{task_id}/cancel")
+async def cancel_datasource_task(
+    source_id: str,
+    task_id: int,
+    current_user: User = Depends(get_current_user),
+    db: AsyncSession = Depends(get_db),
+):
+    datasource = await get_datasource_record(db, source_id)
+    if not datasource:
+        raise HTTPException(status_code=404, detail="Data source not found")
+
+    task = await db.get(CollectionTask, task_id)
+    if not task or task.datasource_id != datasource.id:
+        raise HTTPException(status_code=404, detail="Task not found")
+
+    task = await request_cancel_datasource_task(db, task)
+    return {
+        "status": "cancelled" if task.completed_at else "cancelling",
+        "task_id": task.id,
+        "task_type": task.task_type,
+        "phase": task.phase,
+        "requested_cancel_at": to_iso8601_utc(task.requested_cancel_at),
     }
 
 
@@ -1109,7 +1192,7 @@ async def get_task_status(
         if not task or task.datasource_id != datasource.id:
             raise HTTPException(status_code=404, detail="Task not found")
     else:
-        task = await get_running_task(db, datasource.id)
+        task = await get_active_datasource_job(db, datasource.id)
         if task is None:
             result = await db.execute(
                 select(CollectionTask)
@@ -1134,8 +1217,12 @@ async def get_task_status(
         }
 
     return {
-        "is_running": task.status == "running",
+        "is_running": task.status in {JOB_STATUS_QUEUED, JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING}
+        and task.task_type == JOB_TYPE_COLLECT,
+        "is_task_active": task.status in {JOB_STATUS_QUEUED, JOB_STATUS_RUNNING, JOB_STATUS_CANCELLING},
         "task_id": task.id,
+        "task_type": task.task_type,
+        "task_status": task.status,
         "progress": task.progress,
         "phase": task.phase,
         "phase_progress": task.phase_progress,
@@ -1146,5 +1233,6 @@ async def get_task_status(
         "records_processed": task.records_processed,
         "total_records": task.total_records,
         "status": task.status,
+        "requested_cancel_at": to_iso8601_utc(task.requested_cancel_at),
         "error_message": task.error_message,
     }