langchain-ai/deepagents · error · ValueError

interpreter_ptc list entries cannot include 'all'; use 'all'

Error message

interpreter_ptc list entries cannot include 'all'; use 'all' as a standalone value or list explicit tool names (optionally with the 'safe' preset).

What it means

When interpreter_ptc is a list, the library rejects any entry that spells 'all'. 'all' is a standalone sentinel for the whole string form only; embedding it in a list is ambiguous (list entries are otherwise literal tool names, plus the optional 'safe' preset), so it fails fast instead of guessing.

Source

Thrown at libs/code/deepagents_code/agent.py:1051

                    write_included,
                )
            return included
        msg = (
            f"Invalid interpreter_ptc string {ptc!r}; expected 'safe', 'all', "
            "or a list of tool names."
        )
        raise ValueError(msg)

    if isinstance(ptc, list):
        from deepagents_code.config import INTERPRETER_PTC_SAFE_PRESET

        if any(name.strip().lower() == "all" for name in ptc):
            msg = (
                "interpreter_ptc list entries cannot include 'all'; use 'all' "
                "as a standalone value or list explicit tool names (optionally "
                "with the 'safe' preset)."
            )
            raise ValueError(msg)

        resolved: list[str] = []
        seen: set[str] = set()

        def _add(name: str) -> None:
            if name not in seen:
                seen.add(name)
                resolved.append(name)

        for name in ptc:
            if name.strip().lower() == "safe":
                for member in sorted(INTERPRETER_PTC_SAFE_PRESET):
                    _add(member)
                continue
            _add(name)

        # Explicit names are passed through unvalidated: the middleware resolves
        # them against the live runtime registry (which includes the SDK

View on GitHub (pinned to a1af029e6e)

Solutions

If you want everything, use the standalone string: interpreter_ptc="all" (plus interpreter_ptc_acknowledge_unsafe=True or auto_approve=True).
If you want the preset plus extras, use "safe" inside the list: ["safe", "execute"].
Otherwise list only explicit tool names and drop the 'all' entry.

Example fix

// before
create_cli_agent(interpreter_ptc=["safe", "all"])
// after
create_cli_agent(interpreter_ptc="all", interpreter_ptc_acknowledge_unsafe=True)
// or preset + explicit extras
create_cli_agent(interpreter_ptc=["safe", "execute"])

Defensive patterns

Strategy: validation

Validate before calling

if isinstance(ptc, list) and any(str(n).strip().lower() == "all" for n in ptc):
    raise ValueError("use interpreter_ptc='all' as a standalone string, not inside a list")

Type guard

def is_ptc_tool_list(v: object) -> TypeGuard[list[str]]:
    return (
        isinstance(v, list)
        and all(isinstance(n, str) and n.strip().lower() != "all" for n in v)
    )

Try / catch

try:
    agent = create_cli_agent(interpreter_ptc=ptc)
except ValueError as exc:
    if "cannot include 'all'" in str(exc):
        agent = create_cli_agent(interpreter_ptc="all", interpreter_ptc_acknowledge_unsafe=True)
    else:
        raise

Prevention

Remember: 'all' is string-form only; 'safe' is the only preset combinable inside a list.
Validate config-driven lists at load time, before agent construction.
Prefer ["safe", ...extras] over ["all"] when you need preset plus extras without full exposure.

When it happens

Trigger: create_cli_agent(interpreter_ptc=["all"]) or interpreter_ptc=["safe", "all"] or ["execute", "ALL"] — any list element whose strip().lower() == 'all' raises this ValueError.

Common situations: Users mixing the sentinel vocabulary, e.g. writing ["safe", "all"] intending 'everything plus the preset'; migrating a config that used the string 'all' into list form without realizing 'all' cannot be combined.

Understand the failure class

Background: Invalid enum value errors: "Unknown type", "Invalid scope", "must be one of" — when a string is not on the library's allowed list — this error's family across 23 libraries.

Related errors

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/23e2de55d02949bf. Report an issue: GitHub.