langchain-ai/langchain · error · ChevronError

empty tag at line {_CURRENT_LINE}

Error message

empty tag at line {_CURRENT_LINE}

What it means

Raised by the Mustache tokenizer in `langchain_core.utils.mustache` when a tag parses successfully (both delimiters found) but its body is empty or whitespace-only, e.g. `{{ }}` or `{{}}`. An empty tag has no variable name to look up, so it is rejected as malformed. The line number in the message is where the tag appears.

Source

Thrown at libs/core/langchain_core/utils/mustache.py:154

        "^": "inverted section",
        "/": "end",
        ">": "partial",
        "=": "set delimiter?",
        "{": "no escape?",
        "&": "no escape",
    }

    # Get the tag
    try:
        tag, template = template.split(r_del, 1)
    except ValueError as e:
        msg = f"unclosed tag at line {_CURRENT_LINE}"
        raise ChevronError(msg) from e

    # Check for empty tags
    if not tag.strip():
        msg = f"empty tag at line {_CURRENT_LINE}"
        raise ChevronError(msg)

    # Find the type meaning of the first character
    tag_type = tag_types.get(tag[0], "variable")

    # If the type is not a variable
    if tag_type != "variable":
        # Then that first character is not needed
        tag = tag[1:]

    # If we might be a set delimiter tag
    if tag_type == "set delimiter?":
        # Double check to make sure we are
        if tag.endswith("="):
            tag_type = "set delimiter"
            # Remove the equal sign
            tag = tag[:-1]

        # Otherwise we should complain

View on GitHub (pinned to e32fa9a52e)

Solutions

1. Find the empty tag on the reported line and either give it a name (`{{name}}`) or delete it.
2. If the tag was produced by string substitution, guard that the substituted name is non-empty before building the template.
3. Validate templates by tokenizing once at load time so malformed tags fail fast during development.

Example fix

# before
template = "Hello {{ }}!"
MustachePlaceholderFormatter().format(template)  # ChevronError: empty tag

# after
template = "Hello {{name}}!"
MustachePlaceholderFormatter().format(template, name="Ada")

import re

def has_empty_tags(template: str) -> bool:
    return bool(re.search(r"\{\{\s*\}\}", template))

if has_empty_tags(template):
    raise ValueError("template contains an empty tag")

try:
    list(tokenize(template))
except ChevronError as e:
    raise ValueError(f"invalid template: {e}") from e

When it happens

Trigger: Formatting a template with `MustachePlaceholderFormatter` that contains `{{}}`, `{{ }}`, or a tag whose name was removed by an editing mistake; frequently a leftover after deleting a variable name but leaving the braces.

Common situations: Editing prompt templates and deleting the variable name but not the braces; templating pipelines that substitute variable names with empty strings before rendering (`{{%s}} % var` with empty `var`); copy-pasted templates with placeholder braces meant to be filled in later.

Related errors

• unclosed tag at line {_CURRENT_LINE}
• unclosed set delimiter tag\nat line {_CURRENT_LINE}
• Trying to close tag "{tag_key}"\nLooks like it was not opene
• Unexpected EOF\nthe tag "{open_sections[-1]}" was never clos
• Jinja2 templates are not allowed during deserialization for

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/794552bdc41dd0b6. Report an issue: GitHub.