chain-receipt-sdk 0.1.1

Chain-Receipt SDK — emit, verify, replay, and chain Receipts (v1.0.0) from LangChain runnables, agent loops, or any Python callable.

chain-receipt-sdk

Emit, verify, replay, and chain Chain-Receipts (v1.0.0) from any Python LLM-agent loop. Drop-in callback for LangChain, plus a framework-agnostic ReceiptBuilder for raw API loops.

This is the methodology dependency for the Calibrated Chain-Determinism paper. Reviewers reproduce any cited Receipt with:

pip install chain-receipt-sdk
chain-receipt verify sha256:<hash>
chain-receipt replay sha256:<hash> --n 10

60-second demo

from chain_receipt_sdk import ReceiptBuilder, ClientInfo, Interaction
from chain_receipt_core import compute_text_hash, compute_tool_calls_hash, generate_keypair

sk, pub = generate_keypair()
client = ClientInfo(
    name="my-agent",
    version="0.1.0",
    platform="python-3.12",
    emitter_pubkey=f"ed25519:{pub}",
)
b = ReceiptBuilder(client=client, private_key=sk, chain_seed=pub.encode())

inter = Interaction(
    vendor="anthropic",
    model="claude-sonnet-4-5",
    temperature=0.0,
    system_prompt_hash=compute_text_hash("you are helpful"),
    prompt_hash=compute_text_hash("hello"),
    response_hash=compute_text_hash("hi"),
    tool_calls_hash=compute_tool_calls_hash([]),
    n_tool_calls=0,
    latency_ms=120,
)
r = b.build(interaction=inter)
print(r.receipt_id, r.chain.sequence_number)

LangChain callback

from langchain_core.runnables import RunnableLambda
from chain_receipt_sdk.callback import ReceiptCallback

cb = ReceiptCallback(
    client_name="my-langchain-agent",
    vendor="anthropic",
    model="claude-sonnet-4-5",
)
chain = RunnableLambda(lambda x: f"echo: {x}")
chain.invoke("hello", config={"callbacks": [cb]})

receipts = cb.receipts
print(f"emitted {len(receipts)} Receipts")

CLI

chain-receipt status                       # local chain head + count
chain-receipt verify sha256:<hash>         # validate signature + chain link
chain-receipt replay sha256:<hash> --n 10  # re-run captured prompt N times
chain-receipt chain --since 2026-04-25     # list Receipts since timestamp
chain-receipt publish sha256:<hash>        # push to chain-determinism.org

Local chain storage

Receipts are written to ~/.chain-receipt/chain.jsonl (one JSON per line) when emitted via ReceiptCallback or ReceiptBuilder.build(persist=True). The chain_receipt_sdk.chain.LocalChain reader/writer is the public API for that file.

Replay determinism

chain_receipt_sdk.replay re-runs the captured prompt against the same vendor + model + temperature N times and reports final_answer_consistent, tool_seq_identical, tool_args_identical, and a Wilson 95% CI for the divergence rate. The hash logic is byte-identical to scripts/paper5_multivendor_replay.py — that is the integration test gate in tests/test_replay.py.

Citation

@misc{calibrated_chain_determinism_2026,
  title  = {Calibrated Chain-Determinism for Production LLM Agent Loops},
  author = {Ausili, Mars},
  year   = {2026},
  note   = {Methodology: \texttt{chain-receipt-sdk} 0.1.0},
}

License

MIT — see LICENSE.