An attach-mode partial failure persists successes then records the failure 🟩

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

applications/modelling_e2e/handler.py

@@ -65,7 +65,7 @@ from domain.modelling.plan import Plan
 from domain.property.property import Property, PropertyIdentity
 from domain.property_baseline.calculator_rebaseliner import CalculatorRebaseliner
 from domain.sap10_calculator.calculator import Sap10Calculator
-from domain.tasks.subtasks import SubTask
+from domain.tasks.subtasks import SubTask, SubTaskFailure
 from domain.tasks.tasks import Source
 from harness.console import run_modelling
 from orchestration.task_orchestrator import TaskOrchestrator
@@ -687,12 +687,21 @@ def handler(
             )
             logger.info(f"property={pid} queued for write")
 
+        failed_properties: list[dict[str, Any]] = []
         if trigger.subtask_id is not None:
             # Attach mode (ADR-0055): the whole batch runs under the
             # distributor's pre-created sub_task — the @task_handler wrapper is
             # already inside it — so no per-property children are created.
+            # Failures stay isolated per property (siblings continue) and are
+            # recorded on the sub_task after the surviving writes flush.
             for pid in property_ids:
-                _model_property(pid)
+                try:
+                    _model_property(pid)
+                except Exception as exc:  # noqa: BLE001 — recorded below
+                    logger.exception(f"property={pid} failed")
+                    failed_properties.append(
+                        {"property_id": pid, "error": str(exc)}
+                    )
         else:
             # Fan the batch out into one child SubTask per property and run
             # them in a single batched pass: create all children, model each
@@ -732,5 +741,18 @@ def handler(
                 f"{[s['certificate_number'] for s in skipped_certs]}"
             )
 
+        # Raised only after the surviving writes flushed: the failure is a
+        # record on the sub_task, never an SQS retry (ADR-0055). Recovery is a
+        # deliberate re-send of the sub_task's own inputs.
+        if failed_properties:
+            raise SubTaskFailure(
+                f"{len(failed_properties)} of {len(property_ids)} "
+                "properties failed",
+                details={
+                    "succeeded": len(property_ids) - len(failed_properties),
+                    "failed": failed_properties,
+                },
+            )
+
     finally:
         read_session.close()