TauricResearch/TradingAgents · error · ValueError

llm_max_retries must be an integer, got {value!r}

Error message

llm_max_retries must be an integer, got {value!r}

What it means

ValueError raised by _coerce_max_retries when the llm_max_retries value cannot be converted to int at all — e.g. None, a non-numeric string like 'many', or a list. The conversion int(value) raises TypeError/ValueError and is re-raised with a clear message so the misconfiguration surfaces at graph construction, not as a mysterious crash mid-run.

Source

Thrown at tradingagents/graph/trading_graph.py:59

from .setup import GraphSetup
from .signal_processing import SignalProcessor

logger = logging.getLogger(__name__)


def _coerce_max_retries(value):
    """Validate an ``llm_max_retries`` value to a non-negative int.

    Accepts an int or a numeric string (env vars arrive as strings). Rejects
    booleans and negatives loudly so a misconfiguration fails at startup rather
    than silently disabling retries.
    """
    if isinstance(value, bool):
        raise ValueError(f"llm_max_retries must be an integer, not a boolean: {value!r}")
    try:
        n = int(value)
    except (TypeError, ValueError) as exc:
        raise ValueError(f"llm_max_retries must be an integer, got {value!r}") from exc
    if n < 0:
        raise ValueError(f"llm_max_retries must be >= 0, got {n}")
    return n


class TradingAgentsGraph:
    """Main class that orchestrates the trading agents framework."""

    def __init__(
        self,
        selected_analysts=("market", "social", "news", "fundamentals"),
        debug=False,
        config: dict[str, Any] = None,
        callbacks: list | None = None,
    ):
        """Initialize the trading agents graph and components.

        Args:

View on GitHub (pinned to a33fd4c0f1)

Solutions

1. Set the value to a concrete non-negative integer or numeric string.
2. Ensure config resolution never passes None — give it a default (e.g. 3) when the key is absent.
3. Check for unresolved placeholder strings like '${RETRIES}' in your deployment.

Example fix

# before
TradingAgentsGraph(config={**DEFAULT_CONFIG, 'llm_max_retries': None})

# after
TradingAgentsGraph(config={**DEFAULT_CONFIG, 'llm_max_retries': 3})

def resolve_max_retries(cfg: dict, default: int = 3) -> int:
    value = cfg.get('llm_max_retries', default)
    if value is None:
        return default
    if isinstance(value, bool):
        raise ValueError('llm_max_retries must be an int, not bool')
    return int(value)

try:
    graph = TradingAgentsGraph(config=config)
except ValueError as e:
    if 'llm_max_retries' in str(e):
        config['llm_max_retries'] = 3  # sensible default; log the original bad value
        graph = TradingAgentsGraph(config=config)
    else:
        raise

When it happens

Trigger: Passing llm_max_retries=None, 'unlimited', '' (empty string from an env var that slipped past empty-checks elsewhere), or any non-numeric object to TradingAgentsGraph.

Common situations: Missing config key resolved to None; env var set to a word instead of a number; templating bugs that leave placeholders like '${RETRIES}' unresolved.

Related errors

• llm_max_retries must be an integer, not a boolean: {value!r}
• llm_max_retries must be >= 0, got {n}
• expected a boolean ({'/'.join(_BOOL_TRUE + _BOOL_FALSE)}), g
• Invalid value for {env_var}: {exc}
• unknown analyst key: {analyst_key}

AI-assisted analysis of TauricResearch/TradingAgents@a33fd4c0f1 (2026-08-14). Data as JSON: /api/errors/36d7a02e1648cd13. Report an issue: GitHub.