langchain-ai/deepagents · error · TypeError

`{field_name}` entries must be strings, got {type(entry).__n

Error message

`{field_name}` entries must be strings, got {type(entry).__name__} ({entry!r})

What it means

After confirming the container type, _coerce_frozen_strset checks each entry is a str. A non-string element raises a TypeError naming the field, the element's type, and its repr. This keeps excluded tool/middleware sets strictly string-based.

Source

Thrown at libs/deepagents/deepagents/profiles/harness/harness_profiles.py:854

        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)


def _validate_config_middleware_string(entry: object, field_name: str) -> None:
    """Validate grammar of a string `excluded_middleware` entry.

    Runs at `HarnessProfile` / `HarnessProfileConfig` construction so malformed

View on GitHub (pinned to a1af029e6e)

Solutions

1. Cast each entry to str (or map enum members to their string names) before calling from_dict.
2. Quote entries in YAML that could parse as non-strings (e.g. 'no', 'on', numeric-looking names).
3. Filter or repair the list upstream so it contains only strings.

Example fix

// before
config = HarnessProfileConfig.from_dict({"excluded_tools": ["bash", 42]})
// after
config = HarnessProfileConfig.from_dict({"excluded_tools": [str(t) for t in ["bash", 42]]})

tools = data.get("excluded_tools") or []
if not all(isinstance(e, str) for e in tools):
    data["excluded_tools"] = [str(e) for e in tools]

def is_str_list(value: object) -> TypeGuard[list[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 "entries must be strings" in str(e):
        field = str(e).split('`')[1]
        data[field] = [str(e2) for e2 in data[field]]
        config = HarnessProfileConfig.from_dict(data)
    else:
        raise

When it happens

Trigger: from_dict receiving excluded_tools/excluded_middleware containing non-str items, e.g. {"excluded_tools": ["bash", 42]} or enums/None mixed into the list.

Common situations: Configs generated by scripts appending raw IDs or enum members instead of tool-name strings; YAML lists where an entry parsed as a number or boolean (e.g. a tool literally named `no` becoming False in YAML).

Related errors

• `{field_name}` must be a list/set of strings, got {type(valu
• 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/d821b822ca81148b. Report an issue: GitHub.