TauricResearch/TradingAgents · error · ValueError

'{indicator}' is not a known macro alias or a valid FRED ser

Error message

'{indicator}' is not a known macro alias or a valid FRED series ID. Use an alias (e.g. 'cpi', 'unemployment', '10y_treasury') or a raw FRED series ID (e.g. 'CPIAUCSL').

What it means

Raised by _resolve_series_id() in tradingagents/dataflows/fred.py when the indicator argument is neither a known macro alias (keys of MACRO_SERIES like 'cpi', 'unemployment', '10y_treasury') nor a plausible raw FRED series ID: FRED IDs are uppercase, short (<= 30 chars), and contain no whitespace. It is a ValueError that fails fast with guidance instead of letting a malformed query 400 at the API.

Source

Thrown at tradingagents/dataflows/fred.py:110

    return api_key


def _resolve_series_id(indicator: str) -> str:
    """Map a friendly alias to a FRED series ID, or pass a raw ID through.

    Raises ``ValueError`` when the input is neither a known alias nor a plausible
    series ID — typically a descriptive phrase the LLM passed instead (e.g.
    "bank of japan rate"). FRED IDs are short and alphanumeric, so this rejects
    it up front with guidance rather than letting it 400 the API.
    """
    key = indicator.strip().lower().replace(" ", "_").replace("-", "_")
    if key in MACRO_SERIES:
        return MACRO_SERIES[key]
    candidate = indicator.strip().upper()
    # FRED series IDs never contain whitespace and are short; reject anything
    # else (a descriptive phrase the LLM passed) rather than 400ing the API.
    if not candidate or len(candidate) > 30 or any(c.isspace() for c in candidate):
        raise ValueError(
            f"'{indicator}' is not a known macro alias or a valid FRED series ID. "
            f"Use an alias (e.g. 'cpi', 'unemployment', '10y_treasury') or a raw "
            f"FRED series ID (e.g. 'CPIAUCSL')."
        )
    return candidate


def _request(path: str, params: dict) -> dict:
    """GET a FRED endpoint, surfacing FRED's JSON error body on a bad request."""
    api_params = {**params, "api_key": get_api_key(), "file_type": "json"}
    response = requests.get(
        f"{FRED_API_BASE}/{path}", params=api_params, timeout=REQUEST_TIMEOUT
    )
    # FRED returns 400 with a JSON {"error_message": ...} for unknown series IDs
    # or malformed params; turn that into a clear, actionable error.
    if response.status_code == 400:
        try:
            message = response.json().get("error_message", response.text)

View on GitHub (pinned to a33fd4c0f1)

Solutions

  1. Use a documented alias from MACRO_SERIES ('cpi', 'unemployment', '10y_treasury', etc.) — check fred.py's MACRO_SERIES dict for the exact set
  2. Or pass a real FRED series ID (uppercase, no spaces, <= 30 chars), e.g. 'CPIAUCSL', 'FEDFUNDS', 'DGS10'
  3. Extend MACRO_SERIES with a new alias -> series ID mapping for phrases you use often
  4. In LLM tool descriptions, enumerate the accepted aliases so the model stops emitting prose

Example fix

# before
get_macro_data("bank of japan rate", "2025-06-10")
# -> ValueError: 'bank of japan rate' is not a known macro alias or a valid FRED series ID. ...

# after
get_macro_data("interest_rate", "2025-06-10")     # alias in MACRO_SERIES
get_macro_data("IRSTCB01JPM156N", "2025-06-10")    # raw FRED series ID (no spaces)
Defensive patterns

Strategy: validation

Validate before calling

import re
from tradingagents.dataflows.fred import MACRO_SERIES

def valid_fred_indicator(name: str) -> bool:
    if not isinstance(name, str):
        return False
    key = name.strip().lower().replace(" ", "_").replace("-", "_")
    if key in MACRO_SERIES:
        return True
    c = name.strip().upper()
    return bool(c) and len(c) <= 30 and not any(ch.isspace() for ch in c)

Type guard

def is_fred_series_id(s: str) -> bool:
    return bool(re.fullmatch(r"[A-Z0-9]{1,30}", s or ""))

Try / catch

try:
    get_macro_data(indicator, curr_date)
except ValueError as e:
    if "not a known macro alias" in str(e):
        indicator = "cpi"  # or re-prompt the LLM with aliases + example IDs
    else:
        raise

Prevention

When it happens

Trigger: Passing natural-language phrases such as 'bank of japan rate', 'fed funds', or 'GDP growth rate'; passing lowercase raw IDs without uppercase normalization won't error (upper-cased), but spaces, >30-char strings, or empty strings do; passing a question sentence from an LLM tool call.

Common situations: LLM macro analyst emitting descriptive phrases instead of the documented aliases; users guessing series names; prompts not listing the accepted aliases; multi-word queries not yet mapped in MACRO_SERIES.

Related errors

AI-assisted analysis of TauricResearch/TradingAgents@a33fd4c0f1 (2026-08-14). Data as JSON: /api/errors/0b7fcd77d4729135. Report an issue: GitHub.