langchain-ai/deepagents · error · TypeError

`{field_name}` must be a list/set of strings, got {type(valu

Error message

`{field_name}` must be a list/set of strings, got {type(value).__name__}

What it means

_coerce_frozen_strset validates set-typed fields (excluded_tools, excluded_middleware) loaded from dicts. If the value is not a list, tuple, set, or frozenset (and not None), a TypeError is raised naming the field and its actual type. The result is normalized to a frozenset of strings.

Source

Thrown at libs/deepagents/deepagents/profiles/harness/harness_profiles.py:849

    if not isinstance(value, Mapping):
        msg = f"`{field_name}` must be a mapping, got {type(value).__name__}"
        raise TypeError(msg)
    out: dict[str, str] = {}
    for key, val in value.items():
        if not isinstance(key, str) or not isinstance(val, str):
            msg = f"`{field_name}` keys and values must be strings"
            raise TypeError(msg)
        out[key] = val
    return out


def _coerce_frozen_strset(value: object, field_name: str) -> frozenset[str]:
    """Validate that `value` is an iterable of strings (or `None`)."""
    if value is None:
        return frozenset()
    if not isinstance(value, (list, tuple, set, frozenset)):
        msg = f"`{field_name}` must be a list/set of strings, got {type(value).__name__}"
        raise TypeError(msg)
    entries: list[str] = []
    for entry in value:
        if not isinstance(entry, str):
            msg = f"`{field_name}` entries must be strings, got {type(entry).__name__} ({entry!r})"
            raise TypeError(msg)
        entries.append(entry)
    return frozenset(entries)


def _coerce_general_purpose_subagent(value: object) -> GeneralPurposeSubagentProfile | None:
    """Validate and construct a `GeneralPurposeSubagentProfile` from a dict value."""
    if value is None:
        return None
    if isinstance(value, Mapping):
        return GeneralPurposeSubagentProfile.from_dict(cast("Mapping[str, Any]", value))
    msg = f"`general_purpose_subagent` must be a mapping, got {type(value).__name__}"
    raise TypeError(msg)

View on GitHub (pinned to a1af029e6e)

Solutions

1. Wrap the value in a list: ["bash"] instead of "bash".
2. Split comma-joined strings before passing: value.split(",").
3. Use a set/frozenset directly if building programmatically.

Example fix

// before
config = HarnessProfileConfig.from_dict({"excluded_tools": "bash"})
// after
config = HarnessProfileConfig.from_dict({"excluded_tools": ["bash"]})

tools = data.get("excluded_tools")
if isinstance(tools, str):
    data["excluded_tools"] = tools.split(",") if "," in tools else [tools]

def is_str_iterable(value: object) -> TypeGuard[list[str] | set[str] | tuple[str, ...] | frozenset[str]]:
    return isinstance(value, (list, tuple, set, frozenset)) and all(isinstance(e, str) for e in value)

try:
    config = HarnessProfileConfig.from_dict(data)
except TypeError as e:
    if "must be a list/set of strings" in str(e):
        field = str(e).split('`')[1]
        data[field] = [data[field]]
        config = HarnessProfileConfig.from_dict(data)
    else:
        raise

When it happens

Trigger: Calling HarnessProfileConfig.from_dict with e.g. {"excluded_tools": "bash"} (bare string instead of a list) or {"excluded_tools": {"bash": true}} (dict).

Common situations: YAML/JSON configs where a single excluded tool was written as a plain string instead of a one-element list; string-joined values like "bash,git"; config builders assigning dict membership maps.

Related errors

• `{field_name}` entries must be strings, got {type(entry).__n
• interpreter_ptc must be False, 'safe', 'all', or a list of t
• max_retries must be an int, got {type(max_retries).__name__}
• stream_output_is_visible must be a bool, got {type(stream_ou
• context.{key} must be a string or null, got {type(value).__n

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/4f4da239aff0e3bc. Report an issue: GitHub.