OpenChainGraph Suite · CONTRACT A3 · arch #5

Agent Session Receipt

Note (dated 2026-08-04): a chain composes independent computations performed in an analytical order. No step's output is carried into the next step by the execution model; each step computes from its own declared inputs. This is true of every chain on this site, including chains whose per-step copy below reads as a data handoff.

Aggregate N execution_hashes from an agent session into one SHA-256 Merkle-root session receipt (CRY-05) > regulator-framed prompt (PTG-01). One tamper-evident audit object for EU AI Act Art. 12 / DORA.

OpenChainGraph · 2 Steps prompt template Hash-Anchored §4 chain_depth:2 Client-Side · Zero PII
Chain Topology — Agent-Action Audit-Trail Aggregator → AP2 Prompt Template Generator
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 2 Steps
1 ROOT · D0 node
Agent-Action Audit-Trail Aggregator cry-05-agent-action-audit-trail-aggregator
session_receipt_root (Merkle root over all session execution_hashes) feeds Stage 2 prompt generation
MCP Call · aggregate_execution_receipts
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "aggregate_execution_receipts",
    "arguments": {}
  },
  "id": 1
}
↓
2 TERMINAL · D2 node
AP2 Prompt Template Generator ptg-01-ap2-prompt-template-generator
Generates a regulator-framed prompt citing the full session receipt, final stage
MCP Call · compose_ap2_prompt
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "compose_ap2_prompt",
    "arguments": {}
  },
  "id": 1
}
Export Artifacts
Download the §4 chain definition artifact (hash-anchored composite JSON) or the §13.11 W3C Verifiable Credentials view. Both derive from the chain definition — no new hash is minted. Available after hash computation.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.

Question: This session's receipts need a summary for a new audience. What prompt does the template generator produce for it?
Run the AINumbers MCP tool `run_chain` with {"chain":"agent-session-receipt"} and read `ptg-01-ap2-prompt-template-generator.generated_prompt`.
Re-run with `inputs` for `ptg-01-ap2-prompt-template-generator`, reusing the values that result echoed, with `audience` set to "regulator". Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/agent-session-receipt.html