* [feat]: Add a new semantic_search_client crate that provides vector embedding and
    semantic search capabilities for the Amazon Q CLI. This implementation:

    - Supports text embedding generation using Candle and ONNX runtimes
    - Provides hardware acceleration via Metal on macOS
    - Implements efficient vector indexing for semantic search
    - Includes file processing utilities for various file types
    - Supports persistent storage of semantic contexts
    - Includes comprehensive test coverage

    This crate will enable memory bank functionality for Amazon Q, allowing
    users to create, manage, and search through semantic memory contexts.

    🤖 Assisted by [Amazon Q Developer](https://aws.amazon.com/q/developer)

* Update semantic_search_client dependencies in Cargo.toml

* Refactor embedder implementation for Linux platforms to use trait objects

This change modifies the semantic search client to use Box<dyn TextEmbedderTrait>
on Linux platforms instead of directly using CandleTextEmbedder. This provides
more flexibility and consistency with the implementation on macOS and Windows,
allowing for better extensibility and polymorphic behavior across all platforms.

* Update Cargo.lock file

* Remove redundant CandleTextEmbedder import for non-macOS/Windows platforms

* fix(semantic_search): Update conditional compilation flags for embedders

Update conditional compilation flags to match the new embedding model selection logic:
- Replace target_env="musl" conditions with target_os conditions
- Update TextEmbedder trait implementation to use macOS/Windows condition
- Ensure consistent conditions across all files

🤖 Assisted by [Amazon Q Developer](https://aws.amazon.com/q/developer)

---------

Co-authored-by: Kenneth Sanchez V <[email protected]>

Implement comprehensive batch operations for fs_read and fs_write tools:

- Add operations-based structure to fs_read with multiple operation types
- Implement batch processing for fs_write to handle multiple files and edits
- Add BatchReadResult and BatchWriteResult for consistent response formats
- Standardize tool summary display with improved parameter handling
- Add comprehensive test coverage for all new functionality
- Optimize performance by reducing separate tool calls for multiple files
- Improve error handling and reporting for batch operations

This feature significantly improves performance and usability when working with
multiple files by reducing the number of separate tool calls needed.

🤖 Assisted by [Amazon Q Developer](https://aws.amazon.com/q/developer)

Implement improved edit ordering approach for fs_write tool:
- Sort operations by type priority (Create/Rewrite first, line-based operations, string operations, append last)
- Give ReplaceLines, DeleteLines, and Insert operations the same priority
- Apply line-based operations from bottom to top to avoid line number shifting
- Eliminate redundant line number adjustment logic

Enhance UI formatting:
- Use green ticks for successful operations
- Use red exclamation marks for errors
- Use neutral bullets for summary lines
- Only color the symbols, not the text that follows them

Update tool_index.json documentation to clearly explain the edit ordering approach
and explicitly state that LLMs should not attempt to adjust line numbers.

Document the approach in code-roast.md for future reference.

🤖 Assisted by [Amazon Q Developer](https://aws.amazon.com/q/developer)

Removes an unused backup file (fs_write.rs.bak) and updates the tool descriptions in tool_index.json to improve guidance for fs_read and fs_write tools. Also updates the batch file operations RFC to reflect current implementation status.

- Removed: Deleted obsolete fs_write.rs.bak file
- Updated: Enhanced tool descriptions with better batching guidance
- Updated: RFC documentation to accurately reflect implementation status
- Added: Implementation status section to RFC with next steps

🤖 Assisted by [Amazon Q Developer](https://aws.amazon.com/q/developer)