Files
MobilityOps/backend/app/services/demo_manifest.py
T
NuklearRabbit 81e3fd63bd
MobilityOps acceptance / backend (push) Failing after 19s
MobilityOps acceptance / frontend (push) Successful in 25s
MobilityOps acceptance / e2e (push) Skipped
M54: harden operations and demo resilience
2026-08-24 03:31:03 +02:00

221 lines
8.5 KiB
Python

from __future__ import annotations
from datetime import datetime
from sqlalchemy import select
from sqlalchemy.orm import Session
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, 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 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)
.where(AuditEvent.action == "demo_data_seeded")
.order_by(AuditEvent.occurred_at.desc())
)
if marker is None:
return None, None
metadata = marker.metadata_json or {}
return marker.occurred_at, metadata.get("anchor_date")
def _scenarios(db: Session) -> list[DemoScenarioOut]:
booking = db.scalar(select(Booking).where(Booking.public_ref == "BK-DEMO-RETURN"))
duplicate_issue = db.scalar(
select(DataQualityIssue).where(DataQualityIssue.public_ref == "DQ-DEMO-DUPLICATE")
)
overlap_issue = db.scalar(
select(DataQualityIssue).where(DataQualityIssue.public_ref == "DQ-DEMO-OVERLAP")
)
failed_run = db.scalar(select(OutboxEvent).where(OutboxEvent.event_id == _FAILED_DEMO_EVENT_ID))
knowledge_health = get_knowledge_provider().health()
# Human copy (title, problem statement, "demonstrates" summary) lives entirely in the
# frontend's demo.json (scenarios.items.<id>.*) so it's available in all three UI
# languages. This service only emits stable identifiers and message codes -- never
# display prose -- per the message_code + params architecture used across the app.
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 is_demo_scenario_failure(failed_run))
knowledge_ready = _knowledge_scenario_ready(knowledge_health)
return [
DemoScenarioOut(
id="return-anomaly",
estimated_minutes=3,
required_roles=["rental_employee", "operations_manager"],
start_path=f"/bookings/{booking.public_ref}" if booking else "/bookings",
ready=return_ready,
blocked_reason_code=(
None
if return_ready
else "bookingNotFound"
if booking is None
else "bookingAlreadyProcessed"
),
),
DemoScenarioOut(
id="duplicate-customer",
estimated_minutes=3,
required_roles=["operations_manager"],
start_path=(
f"/data-quality/{duplicate_issue.public_ref}"
if duplicate_issue
else "/data-quality"
),
ready=duplicate_ready,
blocked_reason_code=(
None
if duplicate_ready
else "duplicateIssueNotFound"
if duplicate_issue is None
else "issueAlreadyResolved"
),
),
DemoScenarioOut(
id="booking-overlap",
estimated_minutes=2,
required_roles=["operations_manager"],
start_path=(
f"/data-quality/{overlap_issue.public_ref}" if overlap_issue else "/data-quality"
),
ready=overlap_ready,
blocked_reason_code=(
None
if overlap_ready
else "overlapIssueNotFound"
if overlap_issue is None
else "issueAlreadyResolved"
),
),
DemoScenarioOut(
id="automation-retry",
estimated_minutes=2,
required_roles=["operations_manager"],
start_path="/automation",
ready=automation_ready,
blocked_reason_code=(
None
if automation_ready
else "failedEventNotFound"
if failed_run is None
else "eventAlreadyRecovered"
),
),
DemoScenarioOut(
id="knowledge-question",
estimated_minutes=2,
required_roles=["rental_employee", "operations_manager"],
start_path="/knowledge",
ready=knowledge_ready,
blocked_reason_code=None if knowledge_ready else "knowledgeUnavailable",
),
]
def _integrations(db: Session) -> list[DemoIntegrationSummaryOut]:
n8n = derive_n8n_status(db)
knowledge_health = get_knowledge_provider().health()
mcp_hub = derive_mcp_hub_status(db)
return [
DemoIntegrationSummaryOut(
key="n8n",
status_code=n8n.state,
detail_code="n8nDetail",
detail_params={
"succeeded": n8n.succeeded,
"failed": n8n.failed,
"pending": n8n.pending,
},
),
DemoIntegrationSummaryOut(
key="ragcore",
status_code=(
"operational"
if knowledge_health.provider == "ragcore"
and _knowledge_scenario_ready(knowledge_health)
else "demoMode"
if knowledge_health.provider == "demo"
and _knowledge_scenario_ready(knowledge_health)
else "unavailable"
),
detail_code=(
"ragcoreDetail"
if knowledge_health.document_count is not None
else "ragcoreSourceDetail"
),
detail_params={
"count": knowledge_health.document_count or 0,
"source_count": knowledge_health.source_document_count,
"collection": knowledge_health.collection,
},
),
DemoIntegrationSummaryOut(
key="mcp_hub",
# `MCP_HUB_REGISTRATION_ENABLED` on its own proves nothing: registration is
# catalog-driven on the Hub's side, so the flag only says Fleet Ops expects
# to be called. Only real recorded `mcp_tool_request` calls make this
# "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"
),
detail_params={},
),
]
def scenario_integrity_report(db: Session) -> dict:
"""Server-side scenario-integrity check run after every reset (section 15): confirms
each of the 5 named scenarios is actually present and ready, rather than trusting the
seed loader silently. Reuses the same readiness derivation the manifest/scenario
overview already use, so this can never drift from what a visitor actually sees."""
scenarios = _scenarios(db)
not_ready = [
{"id": s.id, "reason_code": s.blocked_reason_code} for s in scenarios if not s.ready
]
return {"all_ready": len(not_ready) == 0, "not_ready": not_ready}
def build_demo_manifest(db: Session) -> DemoManifestOut:
last_reset_at, anchor_date = _last_reset(db)
return DemoManifestOut(
demo_mode=settings.mobilityops_demo_mode,
organization_name=settings.demo_organization_name,
timezone=settings.demo_timezone,
synthetic_data=True,
allow_reset=settings.demo_allow_reset,
last_reset_at=last_reset_at,
anchor_date=anchor_date,
guide_available=True,
required_roles=["operations_manager", "rental_employee"],
scenarios=_scenarios(db),
integrations=_integrations(db),
)