Receipts & Analytics
List Receipts
List receipts with filters by period, category, and pagination
GET
Returns a paginated list of receipts for the calling agent. Free endpoint — requires
X-Agent-ID only.
Query Parameters
number
default:"all"
Filter to last N days (1–365). Omit to include all receipts.
string
Filter by category:
data, verification, communication, commerce, infrastructure, agent_to_agent. See overview for the tool→category mapping.number
default:"50"
Results per page. Hard ceiling of 100 — values above 100 are clamped.
number
default:"0"
Pagination offset
string
Lower bound on
created_at, inclusive (ISO 8601, e.g. 2026-05-01T00:00:00Z). Combine with until to page through a fixed time window — useful for reaching receipts older than the 100-row cap when tagging value weeks after the call.string
Upper bound on
created_at, inclusive (ISO 8601).Audit fields
Receipts include the audit metadata the caller attached at call time:string | null
The job that produced this receipt. This equals the
request_id returned from the originating tool call (result.request_id) — so you can find a receipt without storing its rcpt_… id, and you can pass that request_id straight to Tag Receipt Value. The caller’s memo / decisionContext are also echoed into the receipt, so they double as match keys.string | null
Human-readable reason for the tool call, up to 1000 chars. Set via the SDK’s
memo option or memo in the JSON body. See Audit Trail.object | null
Machine-readable decision metadata. Open schema; known fields include
goal, goalId, alternatives, confidence (0-1). Used by supervisor / auditor agents.A non-null
value_tag only counts toward RoCS when its status is "confirmed". See Tag Receipt Value for how to tag.