Summary

closes #10239

This PR introduces a smarter way for Roo to read your code files. Instead of just grabbing arbitrary line ranges, Roo can now intelligently extract complete functions, classes, and code blocks based on their structure.

What's New

Indentation Mode for Smart Code Extraction

When Roo needs to read code around a specific line (like when investigating an error or following a search result), it can now use indentation mode to automatically extract the complete containing function or class—not just a fixed number of lines that might cut off mid-block.

Example: If Roo finds an error on line 42 inside a function, indentation mode will return the entire function definition with proper context, instead of an arbitrary range like "lines 40-60" that might miss important context or include unrelated code.

Simplified File Reading

The read_file tool now has two clear modes:

• Slice mode (default): Read a specific portion of a file using offset and limit
• Indentation mode: Extract semantically meaningful code blocks

Breaking Changes

Settings Removed

The following settings have been removed from the UI:

• Max Read File Lines - No longer needed; agents now control read limits per-request
• Max Concurrent File Reads - Batch file reading has been replaced with single-file reads

If you previously relied on maxReadFileLine to limit file reads, this behavior is now handled automatically by the agent's per-request parameters.

API Changes (for Custom Modes/Prompts)

The line_ranges parameter has been replaced with a simpler offset/limit approach:

Before:

{ "files": [{ "path": "app.ts", "line_ranges": [[1, 50]] }] }

After:

{ "path": "app.ts", "mode": "slice", "offset": 1, "limit": 50 }

For semantic code extraction, use the new indentation mode:

{ "path": "app.ts", "mode": "indentation", "indentation": { "anchor_line": 42 } }

Backward Compatibility

Legacy Format Support

To ensure smooth mid-chat updates, the parser maintains full backward compatibility with the old read_file format. If a model uses the legacy format (based on chat history from before the update), it will still work correctly.

Supported legacy formats:

• { files: [{ path: "...", line_ranges: [[start, end]] }] } - Array format
• { files: "[{...}]" } - Double-stringified JSON (model quirk)
• line_ranges as tuples, objects, or strings

How it works:

1. NativeToolCallParser detects the presence of a files parameter
2. If found, it converts the legacy format to the new internal format
3. ReadFileTool.executeLegacy() handles multi-file batch processing
4. A telemetry event (READ_FILE_LEGACY_FORMAT_USED) is captured for monitoring adoption

Testing indicator: A console.warn("[read_file] Legacy format detected") message appears when the fallback path is used (temporary, for validation).

Benefits

• Better code context: Roo now understands code structure and can extract complete functions/classes
• Simpler configuration: Fewer settings to worry about
• Cleaner agent prompts: The simplified API reduces confusion and improves reliability
• Works across languages: Indentation-based extraction works for Python, TypeScript, JavaScript, and other indentation-structured code
• Seamless updates: Users can update Roo mid-chat without breaking ongoing conversations