M54: harden operations and demo resilience

backend/app/services/demo_manifest.py

@@ -9,16 +9,28 @@ from app.core.config import get_settings
 from app.models.audit import AuditEvent
 from app.models.booking import Booking
 from app.models.data_quality import DataQualityIssue
-from app.models.outbox import OutboxEvent
+from app.models.outbox import OutboxEvent, is_demo_scenario_failure
 from app.schemas import DemoIntegrationSummaryOut, DemoManifestOut, DemoScenarioOut
 from app.services.integration_status import derive_mcp_hub_status, derive_n8n_status
-from app.services.knowledge import get_knowledge_provider
+from app.services.knowledge import KnowledgeHealth, get_knowledge_provider
 
 settings = get_settings()
 
 _FAILED_DEMO_EVENT_ID = "00000000-0000-4000-8000-000000000020"
 
 
+def _knowledge_scenario_ready(health: KnowledgeHealth) -> bool:
+    """Require a reachable provider and independently verified indexed documents.
+
+    ``source_document_count`` describes local Markdown files, while a sync report only
+    describes an upload attempt. Neither proves that the active provider can retrieve a
+    corpus, so an unavailable verification count remains honestly not ready.
+    """
+    return bool(
+        health.available and health.document_count is not None and health.document_count > 0
+    )
+
+
 def _last_reset(db: Session) -> tuple[datetime | None, str | None]:
     marker = db.scalar(
         select(AuditEvent)
@@ -49,7 +61,8 @@ def _scenarios(db: Session) -> list[DemoScenarioOut]:
     return_ready = bool(booking and booking.status == "active" and booking.end_odometer_km is None)
     duplicate_ready = bool(duplicate_issue and duplicate_issue.status == "open")
     overlap_ready = bool(overlap_issue and overlap_issue.status == "open")
-    automation_ready = bool(failed_run and failed_run.delivery_status == "failed")
+    automation_ready = bool(failed_run and is_demo_scenario_failure(failed_run))
+    knowledge_ready = _knowledge_scenario_ready(knowledge_health)
 
     return [
         DemoScenarioOut(
@@ -119,8 +132,8 @@ def _scenarios(db: Session) -> list[DemoScenarioOut]:
             estimated_minutes=2,
             required_roles=["rental_employee", "operations_manager"],
             start_path="/knowledge",
-            ready=knowledge_health.available,
-            blocked_reason_code=None if knowledge_health.available else "knowledgeUnavailable",
+            ready=knowledge_ready,
+            blocked_reason_code=None if knowledge_ready else "knowledgeUnavailable",
         ),
     ]
 
@@ -145,9 +158,11 @@ def _integrations(db: Session) -> list[DemoIntegrationSummaryOut]:
             key="ragcore",
             status_code=(
                 "operational"
-                if knowledge_health.provider == "ragcore" and knowledge_health.available
+                if knowledge_health.provider == "ragcore"
+                and _knowledge_scenario_ready(knowledge_health)
                 else "demoMode"
-                if knowledge_health.provider == "demo" and knowledge_health.available
+                if knowledge_health.provider == "demo"
+                and _knowledge_scenario_ready(knowledge_health)
                 else "unavailable"
             ),
             detail_code=(
@@ -169,9 +184,7 @@ def _integrations(db: Session) -> list[DemoIntegrationSummaryOut]:
             # "operational" -- same evidence rule the integration status page uses.
             status_code="operational" if mcp_hub.state == "operational" else "notConnected",
             detail_code=(
-                "mcpDetailOperational"
-                if mcp_hub.state == "operational"
-                else "mcpDetailPrepared"
+                "mcpDetailOperational" if mcp_hub.state == "operational" else "mcpDetailPrepared"
             ),
             detail_params={},
         ),