Fix more problematic attribute values for LangCache

[abrookins]

Following on #437, we find and encode/decode more problematic characters used within attribute values in LangCache. This PR also adds a comprehensive punctuation test for other characters.

[Copilot]

Pull request overview

This PR extends the LangCache attribute encoding mechanism to handle backslash (\) and question mark (?) characters in attribute values by mapping them to fullwidth Unicode equivalents. This follows the same pattern established in PR #437 for comma and slash characters.

• Adds two new character mappings to the encoding/decoding translation tables
• Updates unit test to verify encoding/decoding of backslash and question mark
• Adds comprehensive integration tests for newly supported special characters and all tokenizer separators

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
redisvl/extensions/cache/llm/langcache.py	Adds backslash and question mark mappings to the attribute encoding/decoding translation tables
tests/unit/test_langcache_semantic_cache.py	Updates mock data and assertions to include backslash and question mark in encoded attribute values
tests/integration/test_langcache_semantic_cache_integration.py	Adds new integration tests for backslash/question mark handling and comprehensive tokenizer separator testing

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[bsbodden]

Ship it!