SDK Econ + Gov Query Patterns

When to use

• Pulling FRED economic series (CPI, UNRATE, FEDFUNDS, GDP) inside a TypeScript app
• Looking up congressional bills, vote records, or hearing schedules
• Adding macro context to a prediction-market thesis

Prerequisites

npm install @spfunctions/[email protected]

Most econ/gov queries work without SF_API_KEY (anonymous-allowed reads).

Contract mapping

Both are read-only with sideEffect: "none".

Economic data

import { SimpleFunctions } from "@spfunctions/sdk"

const sf = new SimpleFunctions({
  baseUrl: process.env.SF_API_URL ?? "https://simplefunctions.dev",
})

const econ = await sf.econ.query({
  q: "unemployment rate",
  mode: "raw",
  limit: 3,
})

console.log(econ.series?.map(s => ({
  id: s.id,
  title: s.title,
  latest: s.latest,
})))

mode: "raw" returns the FRED series data verbatim. Other modes:

• "summary" — LLM-summarized econ context
• "compare" — series vs. prediction-market implied levels

Government / legislation

const gov = await sf.gov.query({
  q: "SAVE Act",
  mode: "raw",
  limit: 5,
})

console.log(gov.bills?.map(b => ({
  id: b.id,
  title: b.title,
  status: b.status,
  sponsors: b.sponsors,
  latestActionDate: b.latestActionDate,
})))

Common usage patterns

Macro context for a thesis

async function macroContext(theme: string) {
  const [econ, gov, world] = await Promise.all([
    sf.econ.query({ q: theme, mode: "raw", limit: 3 }),
    sf.gov.query({ q: theme, mode: "raw", limit: 3 }),
    sf.world.get(),
  ])
  
  return {
    theme,
    econ: econ.series,
    legislation: gov.bills,
    marketState: {
      regime: world.regime?.label,
      salient: world.salient?.slice(0, 3),
    },
  }
}

const ctx = await macroContext("Fed rate cuts inflation")
console.log(JSON.stringify(ctx, null, 2))

Anchor a prediction market to FRED data

async function anchorMarket(ticker: string, fredSeries: string) {
  const [market, econ] = await Promise.all([
    sf.markets.get(ticker),
    sf.econ.query({ q: fredSeries, mode: "raw", limit: 1 }),
  ])
  
  return {
    market: { ticker, price: market.price, implied: market.indicators },
    anchor: econ.series?.[0]?.latest,
  }
}

const anchor = await anchorMarket("KXCPIYOY-26JUN-T4.2", "CPIENGSL")
console.log(anchor)

Senator vote market context

async function senatorVoteContext(senatorName: string, billTitle: string) {
  const gov = await sf.gov.query({ q: billTitle, mode: "raw", limit: 1 })
  const bill = gov.bills?.[0]
  
  const votes = bill?.votes?.filter(v =>
    v.senator?.toLowerCase().includes(senatorName.toLowerCase())
  )
  
  return {
    bill: bill?.title,
    sponsor: bill?.sponsors,
    senatorVotes: votes,
    nextSchedule: bill?.latestActionDate,
  }
}

const ctx = await senatorVoteContext("Cortez Masto", "crypto market structure")
console.log(ctx)

Direct agent tool mode

sf agent --tool econ.query --stream-json --input '{"q":"unemployment rate","mode":"raw","limit":3}'
sf agent --tool gov.query --stream-json --input '{"q":"SAVE Act","mode":"raw","limit":3}'

Use direct-tool mode when you want one canonical tool call without an LLM loop (deterministic, cheap).

Series IDs to know

Common FRED series for prediction-market analysis:

Errors

• Empty results: query too specific. Broaden the term.
• Outdated `latest`: FRED has variable release cadence. CPI is monthly, jobs is monthly, GDP is quarterly. Check the FRED page for release schedule.
• `HttpError 503` on gov.query: congress.gov API can be flaky. Retry with backoff.

Related skills

• sf-sdk-quickstart — install + first call
• sf-research — CLI workflow that uses these surfaces
• ctx-economic-data — econ data context package (knowledge layer)
• ctx-us-legislative — legislative context package

Reference docs

• <https://docs.simplefunctions.dev/guides/econ-gov-sdk>
• <https://docs.simplefunctions.dev/api-reference/public-market-data>