Skip to main content

xero-ai-review-gateway

tests Python 3.10+ License: MIT Zero-Network Safe

A fixed-policy, zero-network ledger-review boundary for AI, not an AI that operates Xero.

The repository name is the public project identity; the elizabeth-anne-alexander distribution, import package and command remain compatibility identifiers.

xero-ai-review-gateway consumes validated Xero-shaped trial-balance exports and produces a bounded, redacted variance-review result alongside separate local human-reviewer evidence. It deliberately features no network calls, no cloud telemetry, no LLM API clients, and zero accounting-system write operations.


Zero-Network Architecture

%%{init: {"themeVariables": {"lineColor": "#B1AFAD"}}}%%
flowchart TD
    subgraph ClientPerimeter ["Local Client Perimeter (Zero-Network)"]
        Raw["Validated Xero Trial Balance Export"] --> Validate["Context & Hash Integrity Gate"]
        Validate --> Engine["Decimal Variance Review Engine<br/><i>(Fixed Policy v1)</i>"]
    end

    subgraph ArtifactSplit ["Deterministic Artifact Generation"]
        Engine --> Split{"Split Boundary"}
        Split --> Model["model-result.json<br/><i>(Redacted Bounded Values for AI)</i>"]
        Split --> Evidence["reviewer-evidence.json<br/><i>(Local Human Display Evidence)</i>"]
        Split --> Receipt["receipt.json<br/><i>(Cryptographic SHA-256 Sealing)</i>"]
    end

    subgraph Governance ["Human-in-the-Loop Signoff"]
        Model --> LLM["AI Advisory Assessment"]
        Evidence & Receipt & LLM --> Reviewer["Human Accountant Signoff Gate"]
        Reviewer --> Decision{"Decision Status"}
        Decision -->|ACKNOWLEDGED| Done["Signed Working Paper"]
        Decision -->|NEEDS_EVIDENCE / ESCALATED| Action["Further Investigation"]
    end

    style ClientPerimeter fill:#140E24,stroke:#4F485E,stroke-width:2px,color:#FFFFFF
    style ArtifactSplit fill:#1E1236,stroke:#5C2D91,stroke-width:2px,color:#FFFFFF
    style Governance fill:#2D184E,stroke:#8A4AC7,stroke-width:2px,color:#FFFFFF

Quick Demo

# Install package in editable development mode
pip install -e ".[dev]"

# Run deterministic evaluation
elizabeth-anne-alexander evaluate \
  --context samples/contexts/sample-monthly-variance.context.json \
  --request samples/requests/sample-revenue-variance.request.json \
  --policy policy/demo-policy-v1.json \
  --out build/demo

Validate Human Review Signoff

elizabeth-anne-alexander validate-review \
  --evidence build/demo/reviewer-evidence.json \
  --receipt build/demo/receipt.json \
  --decision samples/decisions/sample-review-decision.json

Control boundary

  • The canonical source contract has exactly ten columns: ReportDate,Tenant,Section,AccountID,AccountName,AccountCode,Debit,Credit,YTDDebit,YTDCredit.
  • CSV schema, duplicate account IDs, reporting dates, balance pairs, source hashes, entity, basis, currency, tracking filters, and draft setting are all checked before review.
  • Monetary values use Decimal, never binary floating point.
  • percent_change in the model result is expressed in percent and quantized to four decimal places ("18.3333" means 18.3333%). It is null when there is no prior balance to compare against.
  • The model result states its own currency and sign_convention. Amounts are debit-positive (ytd_net = YTDDebit - YTDCredit), so a revenue, liability, or equity balance is negative and a revenue increase shows as a negative delta.
  • Current and prior reports must sit in the same Australian financial year, or be the same day and month in different years. YTD columns reset on 1 July, so a comparison across the reset would report a whole prior-year balance as a movement.
  • Current/prior trial balances are joined by stable AccountID, not account display name or code.
  • An account changing section between periods fails closed instead of disappearing from, or being silently reclassified within, a section-scoped comparison.
  • The model result never contains a tenant name, account name, account code, source file path, token, raw error, or free text copied from source data.
  • Artefact timestamps (export.generated_at, reviewed_at) are accepted as YYYY-MM-DD, then T, t, or a space, then HH:MM with optional :SS and optional . plus one to six fractional digits, then Z, z, or +/-HH:MM with optional :SS. The gateway fixes that grammar itself rather than inheriting datetime.fromisoformat, whose accepted forms widened in Python 3.11: a bare +10 offset, a week date, a basic-format 20260809T000000+0000, and a fraction longer than six digits are refused on every interpreter, as is a separator character other than T, t, or a space.
  • The three run artefacts are staged beside their destinations and moved into place only once all three are written, receipt last. The moves are not one atomic step, so an interrupted run can still leave one new file beside two old ones; validate-review refuses that pack, because the receipt seals both the reviewer evidence and the model result sitting beside it.
  • The package contains no network imports or mutation adapter. A future live connection must remain an authorised, read-only export handoff rather than an AI-controlled broad Xero tool set.

Scope and limitation

Every source manifest, review context, model result, reviewer evidence, and receipt is marked mode: synthetic. The policy, request, and human-decision files carry no mode key: each is validated against an exact key set, so adding one is rejected. The validate-review output carries no mode key either; it reports the decision status for a run whose artefacts were already checked. It is a local design demonstration, not a client-data processor, production security system, accounting service, or professional opinion. The reviewer evidence/model-result file split demonstrates disclosure minimisation only; it is not an access-control mechanism by itself.

Documentation & Governance

  • DATA-FLOW.md – Formal data-flow and zero-network security specification.
  • CITATION.cff – Academic and industry citation metadata.
  • LICENSE – MIT License.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

elizabeth_anne_alexander-0.2.1.tar.gz (45.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

elizabeth_anne_alexander-0.2.1-py3-none-any.whl (25.8 kB view details)

Uploaded Python 3

File details

Details for the file elizabeth_anne_alexander-0.2.1.tar.gz.

File metadata

  • Download URL: elizabeth_anne_alexander-0.2.1.tar.gz
  • Upload date:
  • Size: 45.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for elizabeth_anne_alexander-0.2.1.tar.gz
Algorithm Hash digest
SHA256 ff514722753759750a4c8ae2bb621cebb68ec563d9495f5e0797484a8771c141
MD5 6403e63be64156064783c278cba6f940
BLAKE2b-256 17e5129202cda9957a37ea22d9c7a1550572c39918c244bd9144a6849bc152c2

See more details on using hashes here.

Provenance

The following attestation bundles were made for elizabeth_anne_alexander-0.2.1.tar.gz:

Publisher: release.yml on ryanduguid/xero-ai-review-gateway

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file elizabeth_anne_alexander-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for elizabeth_anne_alexander-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f5d3fe7910f7d23d510b2a2fb4b7f3dd1a6f84e3e16cdaa94f6507997d0074d9
MD5 051a35c549ef541a6238fdf67fea08e7
BLAKE2b-256 51ef674602f37db8c59e97d8dfc12e231c58ce924d6d0ecf236778eb45c6762a

See more details on using hashes here.

Provenance

The following attestation bundles were made for elizabeth_anne_alexander-0.2.1-py3-none-any.whl:

Publisher: release.yml on ryanduguid/xero-ai-review-gateway

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.2.1 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page