tengu_v3_intel_macro_snapshot

shallow

io.github.Hlobo-dev/tengu-firm · Verify this server

NOW WITH a `credit` block: CDX IG/HY on-the-run 5Y composite spreads + 1-session delta (T-2 by source, cadence-aware staleness; full series at /api/v3/credit/indices). Cross-asset macro composite returning REAL underlying values, all real-time where the data source permits. Fields: `vix` (real-time spot), `ten_year_yield_pct` (FRED DGS10, %), `usd_index_narrow_dxy` (computed from FRED 6-pair basket via the standard geometric weighted formula — the institutional standard ~99), `usd_index_trade_weighted_broad` (FRED DTWEXBGS — Fed's broader policy measure ~118), `wti_oil_usd_bbl` (FRED DCOILWTICO, $/bbl), `gold_usd_oz` (real-time forex spot, $/oz), `sp500` (real-time index; SPY×10 emergency fallback), `nasdaq100` (real-time index; QQQ×41 emergency fallback), `djia` (real-time index; null when unavailable — no ETF proxy emitted), `russell2000` (real-time index; IWM×10 emergency fallback). Every numeric field is gated by a plausibility guard — out-of-band values are nulled with an `error.implausible_value` field rather than served, so the chat Brain never cites a wrong number with the [macro_snapshot] tag. Includes `vol_regime` (low_vol/normal/elevated/stress per VIX bucket), `data_freshness` timestamp, and a `sources` block with the series reference for each indicator. 60s cache.

100.0/100

1 trials · measured 8 days ago

tengu_v3_intel_macro_snapshot scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.Hlobo-dev/tengu-firm, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.

Component breakdown

ComponentWeightValue
Reliability35%not applicable
Schema integrity25%100.0
Failure behaviour15%not applicable
Latency15%not applicable
Concurrency10%not applicable

Tool details

Transport
remote
Credential class
unreachable
Category
Finance & compliance
Input schema
not declared
Output schema
not declared
Side-effect classification
unclassified

Score history

DayScoreTierMethodology
2026-08-25100.0shallowv0.2.0

Probe evidence

ProbeOutcomes
schema_integritypass: 1

Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.

Embed this score

Available for every tool, scored or not — not a verification perk. Always links back to this page.

Vouch score: tengu_v3_intel_macro_snapshot
[![Vouch score](https://vouch.tools/api/tools/8e3df38e-c2d8-4a3b-be8f-d4b9b16b162e/badge.svg)](https://vouch.tools/tools/8e3df38e-c2d8-4a3b-be8f-d4b9b16b162e)
tengu_v3_intel_macro_snapshot — Vouch