Evaluation reproducibility check
wever_evaluation-reproducibility-checkAgent Evaluation: submit one reproducibility packet: the agent with its model, exact model version and provider, whether the full prompts are included and their version, the settings (temperature, top_p, output limit, seed and others), the tools with whether they are listed and versioned and how outside calls are handled (none, recorded, mocked or live), the dataset with its version, hash and who can get it, the environment with the code version, pinned dependencies and runtime, the scoring method with the scoring script or the judge model and its version, and when it ran. The signed report says essential by essential what someone else needs to rerun the same evaluation and expect the same result, present or missing with why, and names a missing model, a missing or moving model version (such as latest), prompts left out and no dataset version or hash, then missing settings, no seed above temperature 0, unversioned tools, no code version, unpinned dependencies, a missing scoring script or unpinned judge, live outside calls and a private dataset, with the fix for each. This reads what one evaluation needs to be rerun: whether an implementation’s behavior matches its spec is wever_spec-drift-check and two runs of the same agent compared is wever_evaluation-drift-check. Verdict cannot_rerun, reproducibility_gaps, reproducibility_unverified or rerunnable. POST /api/evaluation-reproducibility-check. Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write. Paid URL: 0.10 USDC per call on Base via x402 exact, with the shared 10 signed-wallet free calls per rolling 30 days. Bind X-Wever-Wallet-Proof to the exact JSON arguments and the tool route. Returns a report with an Ed25519 signed receipt. Contract: /api/agent-evaluation-contract. Human page: https://weverlabs.com/agent-evaluation/.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"agent": "<agent>"
},
"name": "wever_evaluation-reproducibility-check"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent | Yes | ||
| label | No | Optional name recorded in the report. | |
| tools | No | ||
| run_at | No | When it ran. | |
| dataset | No | ||
| prompts | No | ||
| scoring | No | ||
| settings | No | ||
| environment | No |