Every request through the gateway produces a receipt: a canonical record of what happened — who called, which model, what it cost, and which policy checks ran — cryptographically signed and chained to the receipt before it. The result is an audit trail where tampering with any single record is detectable.
Observability tools can tell you what they observed. Because Wardin sits in the request path and signs what it enforced, a receipt is evidence, not telemetry.
What a receipt contains
| Field | Description |
|---|
request_id | Unique ID of the request |
tenant_id | Your organization |
actor | The user/key the request is attributed to |
provider / model | Who served it and with what |
prompt_tokens / completion_tokens | Token usage |
cost_usd | Actual cost committed for the request |
checks | Ordered list of policy decisions ({name, result}) — budget, allowlist, guardrails, PII |
ts | Timestamp (RFC 3339, UTC, millisecond precision) |
How the chain works
- The receipt’s fields are serialized in a fixed canonical order.
this_hash = sha256(canonical_receipt || prev_hash) — each receipt’s hash incorporates the previous receipt’s hash.this_hash is signed with the gateway’s ED25519 key.
Changing any field of any historical receipt changes its hash, which breaks every subsequent link in the chain. Verification re-derives the hashes from stored fields and checks the signature — nothing is taken on trust.
Chaining and signing happen in an asynchronous writer, off the response path. Receipts
add zero latency to your LLM requests, and the chain only advances after the
receipt is durably stored.
Where to see receipts
- INGRESS — click any request in the live stream to open its receipt drawer (with
RECEIPT | TRACE tabs).
- EVIDENCE — chain statistics, a sample verified receipt, and the compliance-framework view.
Verifying programmatically
# List recent receipts (newest first, cursor pagination)
curl "https://api.wardin.ai/v1/receipts?limit=25" \
-H "Authorization: Bearer wardin_sk_ADMIN_KEY"
# Fetch one receipt and verify its hash + ED25519 signature
curl "https://api.wardin.ai/v1/receipts/RECEIPT_UUID" \
-H "Authorization: Bearer wardin_sk_ADMIN_KEY"
# → { ..., "verified": true }
# Verify a contiguous range of the chain — reports the first broken link, if any
curl "https://api.wardin.ai/v1/receipts/_/verify-chain?from=1&to=100" \
-H "Authorization: Bearer wardin_sk_ADMIN_KEY"
verified: true means the stored hash equals sha256(canonical || prev_hash) and the ED25519 signature over that hash is valid. Receipts are tenant-scoped — you can only read your own.
Why this matters for compliance
Frameworks like the EU AI Act and NIST AI RMF ask for evidence that governance controls actually ran — not a dashboard screenshot. A hash-chained, signed record of every enforcement decision (including blocks: over-budget 429s, allowlist 403s, guardrail rejections) is exactly that artifact, exportable and independently verifiable. 
