fix(llm): sanitize control characters in function call JSON arguments

[ArpitKotecha]

Description

Problem

LLMs sometimes generate function call JSON with literal control characters (e.g., newlines, tabs) inside string values. For example:

{"prompt": "A timeline showing:
- Event 1
- Event 2"}

The literal newline violates the JSON spec, causing pydantic_core.from_json() to fail with:

ValueError: control character (\u0000-\u001F) found while parsing a string

This breaks function tool execution when the LLM outputs multi-line content in tool arguments.

Solution

Add a _sanitize_json_control_chars() helper that escapes control characters within JSON string values before parsing:

• \n → \\n
• \r → \\r
• \t → \\t
• Other control chars → \\uXXXX

The function preserves already-escaped sequences and only modifies content inside JSON string values.

Changes

• Added _sanitize_json_control_chars() helper function in utils.py
• Modified prepare_function_arguments() to sanitize JSON before calling from_json()

Testing

Tested with real-world LLM output containing multi-line prompts that previously caused the error.