rawctx

Tamper-proof receipts for your AI's answers.

When an AI answer is challenged, rawctx records what it said, which sources it used, and a verifiable receipt. It keeps answer evidence and proof review separate from the agent and observability stack you already run.

Install

pip install rawctx
rawctx login

You can also mint a no-signup, hash-only browser receipt from the rawctx Hub. The browser path sends cryptographic fingerprints instead of the question and answer text.

Log an answer

import rawctx

receipt = rawctx.log_answer(
    "What is the refund policy?",
    "Customers can request a refund within 30 days.",
)

print(receipt)

Hash-centered storage is the default. Workspace settings can enable raw question and answer text storage, while hashes remain available when text storage is off.

Queue EZKL verification

Set the workspace endpoint and a UI-issued deployment token in the process environment:

RAWCTX_REGISTRY=https://<workspace-api-host>
RAWCTX_TOKEN=<workspace-api-token>

After EZKL has generated the proof artifacts, one SDK call creates the answer log and queues server-side verification:

import rawctx

with rawctx.RawctxClient() as client:
    result = client.create_ezkl_answer_log(
        application_key="ezkl_test",
        input_text="2",
        output_text="2",
        model_path="identity.onnx",
        proof_path="proof.json",
        settings_path="settings.json",
        verification_key_path="vk.key",
        srs_path="kzg.srs",
        idempotency_key="ezkl:identity:run-001",
        backend_version="23.0.5",
    )

print(result["log_id"])
print(result["job_id"], result["proof_job"]["status"])

The helper validates the first rescaled public input and output and hashes the artifacts locally. It queues verification rather than running it locally; the proof is verified only when the worker reports adapter_verified. srs_path is hashed but not uploaded. Use a stable idempotency_key for retries because answer-log and job creation are separate writes.

What rawctx records

• Answer record: application, environment, question and answer text or hashes, idempotency key, policy flags, and status.
• Source evidence: source_refs for documents, registered audio or video evidence, answer segments, and purpose-bound retrieval events.
• Model-run lineage: model metadata, input and output hashes, configuration hashes, trace IDs, and inference commitments.
• Lifecycle and proof: correction, void, and redaction events plus Merkle inclusion, signed tree-head binding, external anchors, witness receipts, and explicit proof status.

rawctx does not generate answers, orchestrate workflows, or replace LangSmith, Langfuse, or another OpenTelemetry runtime. It records the evidence object that connects an answer to the sources and trace information needed for review.

Connect OpenTelemetry evidence

rawctx.ingest_otel_trace_bundle() wraps public-safe fields from an existing OpenTelemetry trace into an answer-audit record. Keep trace ownership in your current observability system and submit only the identifiers, hashes, and references needed for answer review.

Do not send observability API keys, private trace URLs, raw tool outputs, or other secrets to rawctx.

Check answer-log completeness

Independent reconciliation compares a short-period external reference set with rawctx answer-audit logs. It detects missing, unexpected, late, duplicate, and unanchored records without becoming an inline decision gate.

rawctx reconcile run reconciliation.json --json
rawctx reconcile findings RUN_ID --json
rawctx reconcile proof RUN_ID --output reconciliation-proof.json
rawctx trust verify reconciliation-proof.json --online

Use a business-system export, provider usage export, or auditor-controlled extract that cannot be rewritten in lockstep with the answer logs. Persisted findings and proofs are commitment-oriented; do not place secrets, raw customer exports, raw PII, or private system URLs in payload metadata.

Review proof state

Proof status distinguishes externally anchored records from pending or local-only evidence. It describes the receipt's verification state; it does not claim that the submitted answer or upstream trace content is true.

rawctx trust proof answer ANSWER_LOG_ID --output proof.json
rawctx trust verify proof.json --online --json

Public documentation

• rawctx Hub
• Answer Audit
• Independent Reconciliation
• OpenTelemetry integrations