Skip to main content

disputeguard

Checks whether a chargeback dispute-evidence bundle actually satisfies Visa's reason-code-specific evidence requirements — before you submit it. Representment windows are days, not weeks, and a weak submission auto-loses; this catches the gaps while there's still time to fix them.

No open-source tool does this today — the space is dominated by paid platforms (Stripe Smart Disputes, Chargeflow, Lorikeet).

Quick start — no API key needed

pip install disputeguard
disputeguard check examples/sample_evidence.json --reason-code 10.4 --deadline 2099-01-01

That runs in rules-only mode: it checks that every required piece of evidence is present and the deadline hasn't passed — no LLM, no signup, instant result.

With AI-judged evidence quality

Rules-only mode can tell you a field is empty. It can't tell you whether the content of a customer email actually proves delivery. For that, add a provider:

from disputeguard import check_evidence
from disputeguard.providers.anthropic_provider import AnthropicProvider

report = check_evidence(
    reason_code="10.4",
    deadline="2026-08-25",
    evidence={
        "avs_match": "AVS check returned Y/Y full match.",
        "cvv_match": "CVV verified at time of sale.",
        "customer_history": "3 prior completed orders, same address.",
    },
    provider=AnthropicProvider(),  # or OpenAIProvider(), or OllamaProvider() for a free local model
)

print(report.verdict)        # "ready" | "weak" | "missing-required"
print(report.score)          # 0-100
print(report.action_items)   # ["Strengthen evidence for '...' — ...", ...]

No paid API? Use OllamaProvider() with a local model — same interface, zero cost.

Async

from disputeguard import acheck_evidence
report = await acheck_evidence(reason_code="10.4", deadline="2026-08-25", evidence={...})

v0.1 scope

  • Visa only, 6 reason codes: 10.4, 13.1, 13.3, 13.6, 12.6.1, 13.7.
  • Not in scope yet: Mastercard/Amex/Discover, auto-drafting the rebuttal letter, direct submission to Visa.

See DETAILS.md for the full design, and docs/USAGE.md for the complete API/CLI reference.

Integration examples

See examples/ for FastAPI and Django webhook handlers.

License

MIT

Metadata

Release files for disputeguard 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for disputeguard 0.1.0
File Size Uploaded Provenance
disputeguard-0.1.0.tar.gz 14.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for disputeguard 0.1.0
File Interpreter ABI Platform
disputeguard-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 29.0 kB

Release files / disputeguard-0.1.0.tar.gz

Download URL disputeguard-0.1.0.tar.gz
Size 14.6 kB
Tags Source
SHA-256 checksum
How to use checksums
b01d8d91ff2512d7bac8f4dbf626e60b2f38c6ec93e2c1c4736c4baf0add9e48
BLAKE2b-256 checksum
How to use checksums
2c900ca55731c0e5bfc6c89383405e8abd451700053d091dad91993d9c5183d0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.12

Release files / disputeguard-0.1.0-py3-none-any.whl

Download URL disputeguard-0.1.0-py3-none-any.whl
Size 14.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9baf50aaf6e4bc75ed18b22a7634792c2dd9940cba756a6dc80b8c57b4609730
BLAKE2b-256 checksum
How to use checksums
5bc6e7dd44319ac23aed24b658720586780a5f121227cf1758ee0f14dc9ae3f6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.12

Security for disputeguard 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page