diff --git a/maintenance_service_http_monitoring/README.md b/maintenance_service_http_monitoring/README.md index eeee667..3b9bbc7 100644 --- a/maintenance_service_http_monitoring/README.md +++ b/maintenance_service_http_monitoring/README.md @@ -107,6 +107,12 @@ When a service fails HTTP checks: after 2 seconds. A maintenance request is only created if the service fails **both** checks, reducing noise from transient HTTP errors +When a service recovers (returns HTTP 200 after having an open request): +- The open maintenance request is automatically moved to the first **done** stage +- A chatter note is posted on the request by OdooBot to record the automatic closure +- The link between the service and the request is cleared, allowing a new request to + be created if the service fails again in the future + ## Webhook notifications When a new maintenance request is created (HTTP check failure), the module can diff --git a/maintenance_service_http_monitoring/models/service_instance.py b/maintenance_service_http_monitoring/models/service_instance.py index 2360a1f..3c7cc66 100644 --- a/maintenance_service_http_monitoring/models/service_instance.py +++ b/maintenance_service_http_monitoring/models/service_instance.py @@ -74,13 +74,43 @@ class ServiceInstance(models.Model): ko_records |= rec return ko_records + def _close_http_maintenance_request(self): + """ + Close the open maintenance.request for each recovered service. + + Moves the request to the first done stage, posts a chatter note as OdooBot, and + clears http_maintenance_request on the service instance. + """ + done_stage = self.env["maintenance.stage"].search( + [("done", "=", True)], limit=1 + ) + if not done_stage: + return + odoobot = self.env.ref("base.partner_root") + for rec in self: + request = rec.http_maintenance_request + if not request or request.stage_id.done: + continue + request.sudo().write({"stage_id": done_stage.id}) + request.sudo().message_post( + body=( + f"Service {rec.service_url} is back online. " + "This request has been automatically closed by the monitoring cron." + ), + author_id=odoobot.id, + message_type="comment", + subtype_xmlid="mail.mt_note", + ) + rec.http_maintenance_request = False + @api.model def cron_check_http_services(self): """ Check all active services with a URL, with one retry on failure. Pass 1: test every eligible service. - If any fail, wait HTTP_RETRY_DELAY seconds then retest only the KO ones. + - Services that had an open request and are now OK are auto-resolved. + - Services still KO after pass 1 are retested after HTTP_RETRY_DELAY seconds. maintenance.request is created only for services that fail both passes, reducing noise from transient HTTP errors. """ @@ -93,8 +123,19 @@ class ServiceInstance(models.Model): lambda s: not s.equipment_id.maintenance_mode ) + # Snapshot services that currently have an open request before pass 1 + services_with_open_request = services.filtered( + lambda s: s.http_maintenance_request + and not s.http_maintenance_request.stage_id.done + ) + ko_after_pass1 = services.check_http_status() + # Auto-resolve services that recovered during pass 1 + recovered = services_with_open_request.filtered(lambda s: s.http_status_ok) + if recovered: + recovered._close_http_maintenance_request() + if not ko_after_pass1: return diff --git a/maintenance_service_http_monitoring/tests/test_http_monitoring.py b/maintenance_service_http_monitoring/tests/test_http_monitoring.py index e74500c..7de03d8 100644 --- a/maintenance_service_http_monitoring/tests/test_http_monitoring.py +++ b/maintenance_service_http_monitoring/tests/test_http_monitoring.py @@ -312,3 +312,49 @@ class TestHttpMonitoring(TransactionCase): ), 2, ) + + # ------------------------------------------------------------------ + # Test 15 -- Service recovery closes the open request and posts a note + # ------------------------------------------------------------------ + def test_service_recovery_closes_request(self): + # First cron run: service is KO -> request created + with ( + patch(SERVICE_INSTANCE_REQUESTS) as mock_requests, + patch(SERVICE_INSTANCE_SLEEP), + ): + mock_requests.get.return_value = _mock_response(500) + mock_requests.exceptions.RequestException = Exception + self.env["service.instance"].cron_check_http_services() + + request = self.service_instance.http_maintenance_request + self.assertTrue(request) + self.assertFalse(request.stage_id.done) + + # Second cron run: service is back OK -> request auto-closed + with ( + patch(SERVICE_INSTANCE_REQUESTS) as mock_requests, + patch(SERVICE_INSTANCE_SLEEP), + ): + mock_requests.get.return_value = _mock_response(200) + mock_requests.exceptions.RequestException = Exception + self.env["service.instance"].cron_check_http_services() + + # Request must be in a done stage + self.assertTrue(request.stage_id.done) + # http_maintenance_request must be cleared on the service instance + self.assertFalse(self.service_instance.http_maintenance_request) + # A chatter note must have been posted mentioning the service URL + notes = request.message_ids.filtered( + lambda m: self.service_instance.service_url in (m.body or "") + ) + self.assertTrue(notes) + + # ------------------------------------------------------------------ + # Test 16 -- No open request -> _close_http_maintenance_request is a no-op + # ------------------------------------------------------------------ + def test_no_close_when_no_open_request(self): + # Service is OK from the start, no request exists + self.assertFalse(self.service_instance.http_maintenance_request) + # Calling close directly must not raise + self.service_instance._close_http_maintenance_request() + self.assertFalse(self.service_instance.http_maintenance_request)