release: bump version to 0.66.0

backend/app/services/scheduler.py

@@ -13,6 +13,7 @@ from app.db.session import async_session_factory
 from app.core.time import to_iso8601_utc
 from app.models.datasource import DataSource
 from app.models.task import CollectionTask
+from app.services.business_logs import emit_business_log, emit_business_log_background, exception_context
 from app.services.collectors.registry import collector_registry
 from app.services.datasource_connectivity import (
     build_builtin_connectivity_checksum,
@@ -124,6 +125,15 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.skipped_disabled",
                 context={"collector_name": collector_name},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.skipped_disabled",
+                message="Skipping disabled collector",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource.id, "status": "skipped"},
+            )
             return
 
         running_result = await db.execute(
@@ -152,6 +162,21 @@ async def run_collector_task(collector_name: str):
                     event="collector.run.skipped_already_running",
                     context={"collector_name": collector_name, "task_id": existing_running.id},
                 )
+                await emit_business_log(
+                    logger,
+                    event="collector.run.skipped_already_running",
+                    message="Skipping collector trigger because task is already running",
+                    category="collector",
+                    level="warning",
+                    service="scheduler",
+                    module=__name__,
+                    context={
+                        "collector_name": collector_name,
+                        "datasource_id": datasource.id,
+                        "task_id": existing_running.id,
+                        "status": "skipped",
+                    },
+                )
                 return
 
             existing_error = (existing_running.error_message or "").strip()
@@ -173,6 +198,21 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.stale_task_failed",
                 context={"collector_name": collector_name, "task_id": existing_running.id},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.stale_task_failed",
+                message="Marked stale running task as failed before rerun",
+                category="collector",
+                level="warning",
+                service="scheduler",
+                module=__name__,
+                context={
+                    "collector_name": collector_name,
+                    "datasource_id": datasource.id,
+                    "task_id": existing_running.id,
+                    "status": "failed",
+                },
+            )
 
         try:
             datasource_id = datasource.id
@@ -183,6 +223,15 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.started",
                 context={"collector_name": collector_name, "datasource_id": datasource_id},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.scheduled_started",
+                message="Scheduler started collector run",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource_id, "status": "running"},
+            )
             task_result = await collector.run(db)
             datasource = await db.get(DataSource, datasource_id)
             if datasource is None:
@@ -217,6 +266,20 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.completed",
                 context={"collector_name": collector_name, "datasource_id": datasource_id, "result": task_result},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.scheduled_completed",
+                message="Scheduler completed collector run",
+                category="collector",
+                service="scheduler",
+                module=__name__,
+                context={
+                    "collector_name": collector_name,
+                    "datasource_id": datasource_id,
+                    "status": task_result.get("status"),
+                    "result": task_result,
+                },
+            )
         except asyncio.CancelledError:
             await db.rollback()
             datasource = await db.get(DataSource, datasource_id)
@@ -228,6 +291,16 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.cancelled",
                 context={"collector_name": collector_name, "datasource_id": datasource.id},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.cancelled",
+                message="Collector cancelled by operator",
+                category="collector",
+                level="warning",
+                service="scheduler",
+                module=__name__,
+                context={"collector_name": collector_name, "datasource_id": datasource.id, "status": "cancelled"},
+            )
             raise
         except Exception as exc:
             await db.rollback()
@@ -240,6 +313,19 @@ async def run_collector_task(collector_name: str):
                 event="collector.run.failed",
                 context={"collector_name": collector_name, "datasource_id": datasource.id, "error": str(exc)},
             )
+            await emit_business_log(
+                logger,
+                event="collector.run.failed",
+                message="Collector failed",
+                category="collector",
+                level="error",
+                service="scheduler",
+                module=__name__,
+                context=exception_context(
+                    exc,
+                    {"collector_name": collector_name, "datasource_id": datasource.id, "status": "failed"},
+                ),
+            )
 
 
 async def cleanup_stale_running_tasks(max_age_hours: int = 2) -> int:
@@ -361,6 +447,16 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.skipped_already_running",
             context={"collector_name": collector_name},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.skipped_already_running",
+            message="Collector is already running in-memory; skipping duplicate trigger",
+            category="collector",
+            level="warning",
+            service="scheduler",
+            module=__name__,
+            context={"collector_name": collector_name, "status": "skipped"},
+        )
         return False
 
     try:
@@ -378,6 +474,15 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.started",
             context={"collector_name": collector_name},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.started",
+            message="Triggered collector",
+            category="collector",
+            service="scheduler",
+            module=__name__,
+            context={"collector_name": collector_name, "status": "queued"},
+        )
         return True
     except Exception as exc:
         logger.error_event(
@@ -385,6 +490,16 @@ def run_collector_now(collector_name: str) -> bool:
             event="collector.trigger.failed",
             context={"collector_name": collector_name, "error": str(exc)},
         )
+        emit_business_log_background(
+            logger,
+            event="collector.trigger.failed",
+            message="Failed to trigger collector",
+            category="collector",
+            level="error",
+            service="scheduler",
+            module=__name__,
+            context=exception_context(exc, {"collector_name": collector_name, "status": "failed"}),
+        )
         return False