_validation.py — langchain Source File

Source Code

"""Validation utilities for LangChain serialization.

Provides escape-based protection against injection attacks in serialized objects. The
approach uses an allowlist design: only dicts explicitly produced by
`Serializable.to_json()` are treated as LC objects during deserialization.

## How escaping works

During serialization, plain dicts (user data) that contain an `'lc'` key are wrapped:

```python
{"lc": 1, ...}  # user data that looks like LC object
# becomes:
{"__lc_escaped__": {"lc": 1, ...}}
```

During deserialization, escaped dicts are unwrapped and returned as plain dicts,
NOT instantiated as LC objects.
"""

from typing import Any

from langchain_core.load.serializable import (
    Serializable,
    to_json_not_implemented,
)

_LC_ESCAPED_KEY = "__lc_escaped__"
"""Sentinel key used to mark escaped user dicts during serialization.

When a plain dict contains 'lc' key (which could be confused with LC objects),
we wrap it as {"__lc_escaped__": {...original...}}.
"""


def _needs_escaping(obj: dict[str, Any]) -> bool:
    """Check if a dict needs escaping to prevent confusion with LC objects.

    A dict needs escaping if:

    1. It has an `'lc'` key (could be confused with LC serialization format)
    2. It has only the escape key (would be mistaken for an escaped dict)
    """
    return "lc" in obj or (len(obj) == 1 and _LC_ESCAPED_KEY in obj)


def _escape_dict(obj: dict[str, Any]) -> dict[str, Any]:
    """Wrap a dict in the escape marker.

    Example:
        ```python
        {"key": "value"}  # becomes {"__lc_escaped__": {"key": "value"}}
        ```
    """
    return {_LC_ESCAPED_KEY: obj}


def _is_escaped_dict(obj: dict[str, Any]) -> bool:
    """Check if a dict is an escaped user dict.

// ... (115 more lines)