extract_json silently drops memories when an LLM wraps JSON in prose containing braces #5998

What happened

mem0.memory.utils.extract_json is the last-resort parser for LLM responses with no code fence. It returns the span from the first { to the last }. When a chatty LLM (common with local Ollama / LM Studio models) wraps its JSON in prose that itself contains braces, that span begins inside the prose and is not valid JSON. json.loads raises, the outer except in _add_to_vector_store swallows it, and the extracted memories are silently dropped with no error surfaced to the caller.

This is the same silent-memory-loss class as #5245 and #5509, and it falls in the scope tests/test_chatty_llm_parsing.py already targets, but the existing tests only cover prose without braces.

Steps to reproduce (offline, no API key)

import json
from mem0.memory.utils import extract_json, remove_code_blocks

response = 'Based on the conversation {about travel}, here is the update: {"memory": [{"id": "0", "text": "likes travel", "event": "ADD"}]}'

# Mirrors the fallback chain in _add_to_vector_store
text = remove_code_blocks(response)
try:
    parsed = json.loads(text, strict=False)
except json.JSONDecodeError:
    parsed = json.loads(extract_json(text), strict=False)  # raises -> caught upstream -> memories dropped

extract_json returns '{about travel}, here is the update: {"memory": [...]}', which fails to parse, so the memory is lost with no error.

Expected behavior

The JSON object ({"memory": [...]}) should be extracted and stored, regardless of brace-containing prose around it.

Environment

mem0 main (reproduced on 2.0.10), Python 3.11, any LLM that returns conversational text around the JSON.