# LUMI Forecast Integrity Receipt

> LUMI Forecast Integrity Receipt is a paid API for AI agents from app.tenna.ai, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Returns a tamper-evident audit receipt for sealed 5-minute BTC forecast history, including cutoff timing, feature hashes, settlement sources, agent prediction coverage, and separately disclosed Brier quality scores.

## Facts

- Endpoint: POST https://app.tenna.ai/api/x402/lumi/lumi_forecast_integrity_receipt
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/lumi-forecast-integrity-receipt-ba404e4b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_c1zQHghkdyHtMV2NT-V8F

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability lumi-forecast-integrity-receipt-ba404e4b -d '<json body>'
```

Example prompt: Pull me a LUMI forecast integrity receipt for the last 50 rounds auditing the 'lumi' agent — I want to see the cutoff timing, feature hashes, settlement sources, and Brier quality score.

## When to prefer this

Choose this endpoint when you need cryptographically verifiable audit evidence of LUMI's forecast history — specifically cutoff timing, feature hashes, and Brier scores — rather than a live forecast or trading signal. Prefer this over sibling endpoints when your goal is data provenance verification, compliance auditing, or due diligence before trusting forecast-derived decisions.

## Known failure modes

- Invalid agentId enum value returns validation error
- limit outside 1-100 range rejected with schema error
- Incorrect or missing offering identifier causes request failure
- Payment failure via x402 protocol blocks access
- Insufficient recent rounds available if fewer exist than requested limit

## How this service works

Integrity receipt for sealed five-minute forecast history: cutoff timing, feature hashes, settlement sources, and agent prediction coverage, with Brier quality disclosed separately. A large sample does not turn a weak score into demonstrated edge. Audit evidence only, not a forecast or trading signal.

## Output

A structured audit receipt containing: cutoff timestamps for each sealed forecast round, cryptographic feature-snapshot hashes, settlement data sources used, per-agent prediction coverage metrics, and separately disclosed Brier quality scores. Explicitly marked as audit evidence only — not a forecast or trading signal.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "integer",
   "maximum": 100,
   "minimum": 1,
   "description": "Recent rounds to include (1-100)."
  },
  "agentId": {
   "enum": [
    "consensus",
    "lumi",
    "tenna"
   ],
   "type": "string",
   "description": "Forecast participant to audit."
  },
  "offering": {
   "type": "string",
   "const": "forecast_integrity_receipt",
   "description": "Offering identifier. Must be exactly 'forecast_integrity_receipt'."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/lumi-forecast-integrity-receipt-ba404e4b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from app.tenna.ai](https://www.zero.xyz/host/app.tenna.ai/llms.txt)