langchain-ai/deepagents · error · ValueError

RewarmEstimate costs must be non-negative, got cold={self.co

Error message

RewarmEstimate costs must be non-negative, got cold={self.cold_cost_usd!r}, incremental={self.incremental_cost_usd!r}

What it means

RewarmEstimate.__post_init__ rejects negative cold_cost_usd or incremental_cost_usd. Costs in USD cannot be negative, so a negative value indicates a sign error, a refund misapplied as a cost, or corrupted data. The library raises immediately to keep cost accounting sane.

Source

Thrown at libs/code/deepagents_code/cold_cache.py:213

        # below (`nan < 0` and `nan > nan` are both `False`), so it would slide
        # past both guards and reach `format_cost_estimate`, where the
        # magnitude arithmetic raises far from the value's real origin.
        if not math.isfinite(self.cold_cost_usd) or not math.isfinite(
            self.incremental_cost_usd
        ):
            msg = (
                f"RewarmEstimate costs must be finite, got "
                f"cold={self.cold_cost_usd!r}, "
                f"incremental={self.incremental_cost_usd!r}"
            )
            raise ValueError(msg)
        if self.cold_cost_usd < 0 or self.incremental_cost_usd < 0:
            msg = (
                f"RewarmEstimate costs must be non-negative, got "
                f"cold={self.cold_cost_usd!r}, "
                f"incremental={self.incremental_cost_usd!r}"
            )
            raise ValueError(msg)
        if self.incremental_cost_usd > self.cold_cost_usd:
            msg = (
                f"RewarmEstimate incremental cost {self.incremental_cost_usd!r} "
                f"cannot exceed the cold cost {self.cold_cost_usd!r}"
            )
            raise ValueError(msg)


@dataclass(frozen=True, slots=True)
class ColdCacheWarning:
    """Validated data needed to render one advisory warning.

    Constructed only after every gate has passed -- a policy resolved, the
    prefix cleared the provider's cache minimum, and the priced delta reached
    the configured threshold -- so the modal renders it without re-deciding
    anything.
    """

View on GitHub (pinned to a1af029e6e)

Solutions

1. Compute costs with abs() or verify the subtraction order so both values are >= 0 before constructing RewarmEstimate.
2. If a negative number signals 'savings', model that separately (e.g. a savings field) instead of passing it as a cost.
3. Validate values at the data-ingestion boundary and log/skip corrupted records instead of feeding them into estimates.

Example fix

// before
inc = old_total - new_total  # negative when new is cheaper
est = RewarmEstimate(cold_cost_usd=cold, incremental_cost_usd=inc)
// after
inc = max(0.0, new_total - old_total)
est = RewarmEstimate(cold_cost_usd=cold, incremental_cost_usd=inc)

if cold < 0 or inc < 0:
    raise ValueError(f"costs cannot be negative: cold={cold!r}, inc={inc!r}")
est = RewarmEstimate(cold_cost_usd=cold, incremental_cost_usd=inc)

def is_non_negative_number(v: object) -> bool:
    return isinstance(v, (int, float)) and not isinstance(v, bool) and v >= 0

try:
    est = RewarmEstimate(cold_cost_usd=cold, incremental_cost_usd=inc)
except ValueError:
    est = RewarmEstimate(cold_cost_usd=abs(cold), incremental_cost_usd=abs(inc))

When it happens

Trigger: Calling RewarmEstimate(cold_cost_usd=-0.5, ...) or passing a negative incremental_cost_usd, typically from subtracting in the wrong order or negating a delta.

Common situations: Computing incremental cost as (new_total - old_total) when values were swapped, parsing cost columns from a CSV with currency signs, or reusing a signed 'savings' value as a cost.

Related errors

• RewarmEstimate costs must be finite, got cold={self.cold_cos
• RewarmEstimate incremental cost {self.incremental_cost_usd!r
• modes can only be provided when agent is a factory
• models can only be provided when agent is a factory
• -32602

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/085448e963c91a98. Report an issue: GitHub.