---
id: QONTO-WP-0002
type: workplan
title: "Phase 1 — policy kernel and read-only REST"
domain: infotech
repo: qonto-assistant
status: finished
owner: codex
topic_slug: the-custodian
created: "2026-07-21"
updated: "2026-07-21"
state_hub_workstream_id: "1540afc2-219e-4d95-96f5-4b45fc6a7aaa"
---

# Phase 1 — policy kernel and read-only REST

Execute **Phase 1** of `specs/ArchitectureBlueprint.md`: a service skeleton
with a protocol-neutral capability core and shared
`decide(request, claims) → Allow|Deny` policy kernel plus a minimal REST
surface for org/accounts/transactions/snapshot. No MCP yet (Phase 2). No
spend or volume-cost tools — default deny. Baseline guardrails ship in this
phase: bounded pagination/timeouts, basic rate limiting, bounded concurrency,
and redaction tests.

**Depends on:** live OpenBao path `tenants/binky/qonto-api` (BINKY-WP-0005 /
CCR-2026-0008) — already provisioned.

## Task: Choose runtime skeleton and layout

```task
id: QONTO-WP-0002-T01
status: done
priority: high
state_hub_task_id: "f9e129f3-5bd4-43e1-b7a0-281e4d3dec2a"
```

Pick implementation stack (recommendation: Python 3.12 + FastAPI unless a
fleet standard dictates otherwise). Scaffold package layout, `pyproject.toml`
(or equivalent), Makefile targets (`test`, `lint`, `run`), and document
commands in `AGENTS.md` / complete QONTO-WP-0001-T02.

Done when: `make test` (or documented equivalent) runs an empty/smoke suite;
layout matches blueprint components (protocol adapters, capability core,
policy, qonto client, api, audit).

## Task: Policy kernel — default-deny no-spend / no-volume-cost

```task
id: QONTO-WP-0002-T02
status: done
priority: high
state_hub_task_id: "552ff651-dc66-4e65-97fe-3ec26652bbdd"
```

Implement declarative policy (YAML or equivalent) + pure decision function:

- default **deny**
- allow only v1 read capability ids (`org_summary`, `list_transactions`,
  `cost_run_rate_hints`, `snapshot_bundle`)
- hard deny classes: `spend`, `volume_cost`, `credential_exfil`
- stable deny reasons for authz, tenant scope, argument constraint, and
  credential exfil cases
- unit tests: allow known reads; deny transfer/card/invoice-shaped tools and
  suspicious args even if somehow invoked

Done when: policy tests pass in CI/local; no network required.

## Task: Qonto REST client (credential inject, no secret log)

```task
id: QONTO-WP-0002-T03
status: done
priority: high
state_hub_task_id: "be3aa7b6-f28c-4436-bd5d-d6940de6c2ce"
```

Implement thirdparty client using `Authorization: login:key` (fields
`API_USER`/`API_KEY` from env or OpenBao fetch helper). Map:

- organization + bank accounts
- paginated transactions with hard caps
- bounded timeouts and conservative retry behavior
- never log Authorization or key material

Support env inject for tests (`QONTO_API_KEY`/`QONTO_ORGANIZATION_ID` or
`API_KEY`/`API_USER`) and document OpenBao fetch for operators. Production
path fetches through a dedicated assistant runtime role only.

Done when: unit tests with mocked HTTP; optional live smoke behind a flag.

## Task: REST API surface

```task
id: QONTO-WP-0002-T04
status: done
priority: high
state_hub_task_id: "678b0b26-15af-4037-849f-d24d320588ac"
```

Expose JSON endpoints that all run through the policy kernel:

| Method | Path | Capability |
| --- | --- | --- |
| GET | `/v1/health` | no bank call |
| GET | `/v1/accounts` | org_summary |
| GET | `/v1/transactions` | list_transactions (capped) |
| GET | `/v1/snapshot` | snapshot_bundle (composed allowed reads) |

Done when: OpenAPI or documented curl examples; integration test with mock
client; deny paths return 403 with stable error code; route-to-capability
mapping is explicit and shared with future MCP.

## Task: Audit metadata (no secrets)

```task
id: QONTO-WP-0002-T05
status: done
priority: medium
state_hub_task_id: "4a42dff1-1281-4cc1-ba6a-24702bce7dc9"
```

Log or emit structured audit events: actor (if present), capability, decision,
deny_reason, latency, upstream HTTP status, and policy version. Never secret
fields. Prefer structured stdout JSON (or equivalent sink) on the hot path;
State Hub progress stays optional roll-up evidence for dogfood runs, not
per-call audit storage.

Done when: tests assert secrets absent from log lines for a sample allow/deny.

## Task: Operator runbook + CostRunRate refresh path

```task
id: QONTO-WP-0002-T06
status: done
priority: medium
state_hub_task_id: "7b7ca0f7-f523-473e-b3f6-fe0564f54ed5"
```

Document how binky-control refreshes `finance/CostRunRate.md` via
`GET /v1/snapshot` (or equivalent) with OpenBao-backed service start. Link from
README. Optional thin script under `scripts/`.

Done when: runbook in `docs/` or README section; dry-run instructions without
pasting keys into chat.

## Task: Closure review

```task
id: QONTO-WP-0002-T07
status: done
priority: low
state_hub_task_id: "9b99ba05-99f2-4624-9044-89bf37055434"
```

**Done 2026-07-21:** Phase 1 landed in `src/qonto_assistant/` with a
FastAPI-based REST service, policy YAML, Qonto client, audit layer, rate
limits, concurrency bounds, and operator runbook. Verified with
`PYTHONPATH=src ../state-hub/.venv/bin/python -m pytest` (`12 passed`) plus
`python3 -m compileall src tests`. Phase 2 seed remains the MCP surface on the
same capability core and policy engine. Run `statehub fix-consistency`.