Files
MobilityOps/README.md
T
NuklearRabbitandClaude Sonnet 5 34df66d28c M8: GUI polish, n8n workflow-3 fixes, RAGcore retrieval root-cause and fix
GUI: dashboard Attention Queue presents a curated severity mix instead of pure
severity-sort (grouped Now/Today/Later headers); Today's Movements seed data
curated so a fresh reset shows a credible day (2+ departures, 2+ returns), with
a new seed-integrity test; About Demo restructured into a compact grid with
progressive disclosure for technical sections; Duplicate Merge shows match/conflict
counts, hides matching fields by default, and previews the final merged record
before confirmation.

Repo hygiene: removed a stray empty `backend;C` directory and an untracked 31MB
zip export; `.gitignore` now excludes future archive exports.

n8n: fixed invalid JSON (a missing `},` between two node objects) in the committed
`fleet-ops-vehicle-return.json` -- the file could not be parsed. Live-validated
workflow 3 (RAGcore Procedure Sync): found and fixed a real defect (three body
parameters had a stray trailing `}}`) and a missing Error Workflow wiring, both
via the safe `n8n import:workflow` CLI path; exported the corrected, still-
inactive workflow as the new source of truth and updated MANIFEST.md/check_drift.py.
Publishing it (starts real daily unattended runs) remains a separate decision.

RAGcore: root-caused and fixed (live, approved) the "zero retrieval candidates"
bug -- a filesystem permission bug (`embedding_profiles.json` unreadable by the
app's own runtime user) that broke every retrieval call before it reached Qdrant.
Every other suspect (grants, scope resolution, Qdrant filters, embeddings) was
verified healthy first. Found a second, deeper gap: the reranker adapter calls
an Ollama HTTP route that does not exist on the deployed Ollama version, so
`/v1/answers` still returns `not_answerable`. `KNOWLEDGE_PROVIDER` stays `demo`
until that is resolved on the RAGcore side. Evidence-based MCP Hub integration
status (real tool-call audit history, not just a boolean flag) replaces the old
`configured`/`not_configured` guess. Full findings in
`docs/final-integrations/current-state-audit.md`.

Backend: 172 tests passing, ruff clean, mypy clean (50 files). Frontend: tsc
clean, production build clean.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-05 13:05:02 +02:00

139 lines
7.5 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Fleet Ops
**Connected operations for vehicle rental and service teams.**
Fleet Ops is a working proof of concept for a fictitious mobility company. It combines vehicle and booking operations, a controlled vehicle-return workflow, data-quality review, RAGcore-backed internal knowledge, n8n orchestration and read-only tools published through ITWorx MCP Hub.
**Naming:** "Fleet Ops" is the product's visible name everywhere in the UI, the demo
knowledge base, and this documentation. "MobilityOps" remains the technical
identifier only — the repository name, local directory, package/module names, Docker
Compose project, deployment directory, and database names. The UI is fully trilingual
(nl-BE default, en-GB, fr-BE); see `docs/fleet-ops-correction/` for the localization
architecture, the vehicle-status decision table, and the correction evidence, and
`docs/fleet-ops-final-localization/` for the follow-up correction round (remaining
NL/FR translation gaps, centralized API-error localization, the time-dependent
Europe/Brussels dashboard greeting).
The web application uses the premium responsive **Control Rail** interface: a compact
operations-first workspace with persisted readiness metrics, evidence-led exceptions,
review-before-commit return handling and mobile navigation designed down to 390 px. See
`docs/design/design-directions.md` and `docs/design/implementation-validation.md` for the
design decision and visual evidence.
All people, companies, vehicles, bookings and documents are synthetic. The workflows, validation, integrations, audit logging and access boundaries are intended to be real.
## Demo
The demo presents itself as **Northstar Mobility**, a fictitious Belgian camper/van
rental company — the login screen, a permanent "Synthetische demo" indicator, an in-app
guided tour (Demo Guide), a curated `/scenarios` overview, and an "Over deze demo" page
all make the fictional context, synthetic-data status, and real-vs-simulated boundaries
explicit without any verbal explanation. See `docs/demo-release/` for the full demo
concept, the five named scenarios, the seed/date-anchoring strategy, the guided-tour
design, and the operational runbook (5-minute and 10-minute demo flows, reset, redeploy,
rollback).
## Scope
The PoC implements:
- operations dashboard with a truthful aggregate n8n/MCP integration-status card;
- vehicle and booking views with working search, filters and pagination;
- server-backed session lifecycle (refresh-safe, central 401 handling);
- a role matrix enforced server-side and mirrored in the UI (see
`docs/12-security-and-audit.md`);
- vehicle return capture → authoritative server-evaluated review → commit → result;
- five deterministic data-quality checks, each with a bounded resolution flow, plus a
manual scan action;
- human review and customer merge;
- audit trail with human-readable before/after evidence and safe entity links;
- role-aware global search across vehicles, bookings and (Operations Manager) issues;
- safe, confirmed demo reset;
- RAGcore-backed knowledge assistant with citations;
- two n8n workflows: return processing, and a scheduled data-quality scan with
crash-recoverable outbox delivery leases;
- four read-only MCP tools through ITWorx MCP Hub;
- deterministic demo reset and five-minute showcase.
It is not an ERP, CRM, accounting package, public booking site, payment system or autonomous agent.
## Integration status
- **n8n**: fully implemented and verified against a real n8n instance, including
degraded mode (n8n stopped mid-flow → return still commits, event stays `pending`
with backoff, self-heals once n8n returns), the failed-delivery manual-retry path,
stale-delivery-lease recovery after a simulated crash, and a second (scheduled
quality-scan) workflow live-verified end to end against a real n8n instance.
`GET /api/v1/integrations/status` reports a truthful aggregate state from outbox
delivery counts, not just the most recent event.
- **RAGcore**: the demo `KnowledgeProvider` (deterministic TF-IDF extractive retrieval
over the local procedure documents) is what satisfies the knowledge-assistant
acceptance criteria and is what's active in production (`KNOWLEDGE_PROVIDER=demo`). A
`RAGcoreKnowledgeProvider` HTTP adapter is implemented, unit-tested, and has been
exercised live against the deployed RAGcore instance: a real filesystem-permission bug
that caused every live retrieval to return zero candidates was found and fixed
(`docs/final-integrations/current-state-audit.md`), but a second, deeper gap — RAGcore's
reranker adapter calls an Ollama HTTP route (`/api/rerank`) that does not exist on the
deployed Ollama version — still blocks real grounded answers. `KNOWLEDGE_PROVIDER` stays
`demo` until that is resolved on the RAGcore side.
- **ITWorx MCP Hub**: the four read-only provider endpoints are implemented, tested, and
directly `curl`-verified with correct auth enforcement and audit logging.
`MCP_HUB_REGISTRATION_ENABLED` is actually wired into `Settings` and reported honestly
by the integration-status endpoint (evidence-based: real tool-call audit history, not
just the flag). The Fleet Ops connector is confirmed live in the ITWorx MCP Hub's own
production deployment (Tower), with a real contract fix already applied there
(`vehicle.get`'s wire parameter normalized to `vehicleRef`).
See `artifacts/functional-completion/final-summary.md` for the functional-completion
audit evidence (supersedes the design-validation summary below for integration status),
and `artifacts/final-acceptance/summary.md` for the original M0M7 acceptance evidence.
## Repository map
- `CLAUDE.md` — binding implementation rules.
- `MASTER_BUILD_PROMPT.md` — prompt to start an autonomous Claude run.
- `PROJECT_STATE.md` — short persistent project memory.
- `docs/` — product, architecture, UX and acceptance specification.
- `contracts/` — OpenAPI, event and MCP contracts.
- `knowledge/` — fictitious source documents for the MobilityOps RAGcore workspace.
- `seed/` — deterministic synthetic dataset and generator.
- `n8n/` — importable workflow definitions.
- `backend/` — FastAPI/SQLAlchemy/Alembic API.
- `frontend/` — React/TypeScript/Vite web app, including the Playwright end-to-end suite (`frontend/e2e/`).
- `artifacts/evidence/` — final acceptance evidence (screenshots, architecture, `final-summary.md`).
- `artifacts/design-validation/` — baseline audit, Stitch direction references and implemented responsive captures.
- `docs/functional-completion/` — the functional-completion audit and pre-work server baseline.
- `artifacts/functional-completion/` — functional-completion acceptance evidence.
- `docs/demo-release/` — demo concept, scenarios, seed/date-anchoring strategy, guided
tour, and runbook.
- `artifacts/demo-release/` — demo-productization acceptance evidence.
## Quickstart
```bash
cp .env.example .env
make demo
```
This builds and starts the full stack (migrations run automatically) and loads the
deterministic demo dataset. See `docs/17-runbook.md` for the one-time n8n workflow setup
required for the automation demo, and the full operational runbook.
Endpoints:
- Web: `http://localhost:1228`
- API health: `http://localhost:8128/health`
- n8n: `http://localhost:5678`
All defaults are configurable via `.env` (see `.env.example`).
## Quality gates
```bash
make test # backend: pytest (151 tests)
make lint # backend: ruff + mypy (strict, zero errors)
make e2e # frontend: Playwright end-to-end (138 tests, live stack required)
```
Frontend build/typecheck: `cd frontend && npm run build` (`tsc -b && vite build`).