FoundationAgents/OpenManus · error · ToolError

No replacement was performed, old_str `{old_str}` did not ap

Error message

No replacement was performed, old_str `{old_str}` did not appear verbatim in {path}.

What it means

Thrown by the str_replace_editor tool when a str_replace operation finds zero occurrences of old_str in the target file. The tool reads the file, expands tabs on both content and arguments, and counts occurrences; an exact verbatim substring match is required before any edit is attempted. A zero count aborts the edit entirely — nothing is written.

Source

Thrown at app/tool/str_replace_editor.py:300

        )

    async def str_replace(
        self,
        path: PathLike,
        old_str: str,
        new_str: Optional[str] = None,
        operator: FileOperator = None,
    ) -> CLIResult:
        """Replace a unique string in a file with a new string."""
        # Read file content and expand tabs
        file_content = (await operator.read_file(path)).expandtabs()
        old_str = old_str.expandtabs()
        new_str = new_str.expandtabs() if new_str is not None else ""

        # Check if old_str is unique in the file
        occurrences = file_content.count(old_str)
        if occurrences == 0:
            raise ToolError(
                f"No replacement was performed, old_str `{old_str}` did not appear verbatim in {path}."
            )
        elif occurrences > 1:
            # Find line numbers of occurrences
            file_content_lines = file_content.split("\n")
            lines = [
                idx + 1
                for idx, line in enumerate(file_content_lines)
                if old_str in line
            ]
            raise ToolError(
                f"No replacement was performed. Multiple occurrences of old_str `{old_str}` "
                f"in lines {lines}. Please ensure it is unique"
            )

        # Replace old_str with new_str
        new_file_content = file_content.replace(old_str, new_str)

View on GitHub (pinned to 52a13f2a57)

Solutions

Re-read the file (view command) at the current path and copy old_str verbatim, including exact leading whitespace and line breaks.
Verify the path is correct — editing a different file than the one displayed is a frequent cause.
Check for line-ending or encoding mismatches; normalize the editor to LF if the file uses LF.
Use a longer, more distinctive snippet as old_str to guarantee an exact match.
If the string may have drifted, fall back to a write/insert operation instead of str_replace.

Example fix

// before
await editor.str_replace('app/main.py', old_str='def run():\n    pass', new_str='def run():\n    return 0')  // indentation mismatch -> error
// after
await editor.view('app/main.py')  // confirm exact text
await editor.str_replace('app/main.py', old_str='def run():\n\t pass', new_str='def run():\n\t return 0')  // copied verbatim from file

Defensive patterns

Strategy: validation

Validate before calling

content = await operator.read_file(path)
if old_str.expandtabs() not in content.expandtabs():
    refreshed = await editor.view(path)  # re-read and re-derive old_str
    # rebuild old_str from refreshed content or abort before calling str_replace

Type guard

def is_exact_snippet(content: str, old_str: str) -> bool:
    return content.expandtabs().count(old_str.expandtabs()) == 1

Try / catch

try:
    await editor.str_replace(path, old_str, new_str)
except ToolError as e:
    if 'did not appear verbatim' in str(e):
        content = await editor.view(path)
        # re-derive old_str from the fresh content and retry once
    else:
        raise

Prevention

Always view/read the file immediately before editing and copy old_str verbatim from that read.
Normalize line endings and tabs in your pipeline before constructing old_str (the tool expands tabs but nothing else).
Never build old_str from memory or a cached snapshot of the file.

When it happens

Trigger: Calling str_replace with an old_str that does not exactly match file content: wrong indentation, tabs vs spaces (note tabs are expanded before matching, so an 8-space vs tab mismatch is normalized but other whitespace differences are not), trailing whitespace, line-ending differences (CRLF vs LF), or the file having changed since it was last read.

Common situations: Agent/tool pipelines that reuse a cached file snapshot then edit after another writer changed the file; copy-pasting old_str from a rendered view that altered whitespace; assuming fuzzy or regex matching when the tool only does literal substring matching.

Related errors

AI-assisted analysis of FoundationAgents/OpenManus@52a13f2a57 (2026-08-15). Data as JSON: /api/errors/ce7c162622c30f05. Report an issue: GitHub.