HKUDS/Vibe-Trading · error · ValueError

valuations may contain at most {_MAX_VALUATIONS} entries

Error message

valuations may contain at most {_MAX_VALUATIONS} entries

What it means

_coerce_valuations caps the array at _MAX_VALUATIONS entries to bound compute and payload size. Exceeding the cap raises this ValueError even if every entry is individually well-formed.

Source

Thrown at agent/src/tools/cashflow_analytics_tool.py:319

def _coerce_valuations(raw: Any) -> list[tuple[date, float]]:
    """Parse the raw valuation array into ``(date, value)`` pairs.

    Args:
        raw: Value supplied for the ``valuations`` parameter.

    Returns:
        Pairs in the order supplied; the library sorts and validates them.

    Raises:
        ValueError: If the array is missing, wrongly shaped, over the size cap,
            or an entry lacks a usable date or value.
    """
    if not isinstance(raw, list) or len(raw) < 2:
        raise ValueError("valuations must be an array of at least two {date, value} objects")
    if len(raw) > _MAX_VALUATIONS:
        raise ValueError(f"valuations may contain at most {_MAX_VALUATIONS} entries")

    pairs: list[tuple[date, float]] = []
    for index, item in enumerate(raw):
        if not isinstance(item, dict):
            raise ValueError(f"valuations[{index}] must be an object with date and value")
        if "date" not in item or "value" not in item:
            raise ValueError(f"valuations[{index}] needs both 'date' and 'value'")
        try:
            value = float(item["value"])
        except (TypeError, ValueError) as exc:
            raise ValueError(f"valuations[{index}].value must be numeric") from exc
        if not math.isfinite(value):
            raise ValueError(f"valuations[{index}].value must be finite")
        pairs.append((item["date"], value))
    return pairs


def _resolve_flows(kwargs: dict[str, Any]) -> CashFlowSeries | None:

View on GitHub (pinned to 80ffdda44c)

Solutions

1. Downsample to at most _MAX_VALUATIONS points (e.g. weekly/monthly sampling or last-N)
2. Check the module constant _MAX_VALUATIONS before building the payload
3. Split the analysis across multiple calls if full resolution is truly needed

Example fix

// before
valuations = daily_nav_history  # 10k entries
// after
valuations = daily_nav_history[::len(daily_nav_history)//_MAX_VALUATIONS + 1]

from src.tools.cashflow_analytics_tool import _MAX_VALUATIONS
if len(valuations) > _MAX_VALUATIONS:
    step = len(valuations) // _MAX_VALUATIONS + 1
    valuations = valuations[::step]

def within_cap(v: list, cap: int) -> bool:
    return len(v) <= cap

try:
    tool.execute(valuations=valuations)
except ValueError as e:
    if 'at most' in str(e):
        valuations = downsample(valuations, _MAX_VALUATIONS); retry

When it happens

Trigger: Passing daily valuation series (thousands of points) where the tool expects a bounded sample; bulk-importing full price history as valuations.

Common situations: Users dumping an entire NAV/price history instead of periodic valuations; LLM pasting large datasets into the tool call; batch jobs that never paginate.

Related errors

• valuations must be an array of at least two {date, value} ob
• valuations[{index}] must be an object with date and value
• legs may contain at most {_MAX_LEGS} entries
• spot_points must be between {_MIN_SPOT_POINTS} and {_MAX_SPO
• scenario_iv_values may contain at most {_MAX_IV_SCENARIOS} e

AI-assisted analysis of HKUDS/Vibe-Trading@80ffdda44c (2026-08-28). Data as JSON: /api/errors/4276737a6e75b968. Report an issue: GitHub.