fix: address temperature typo in LLMConfig class

[mvdmakesthings]

Summary

Simply fixing a typo ("temprature" vs "temperature") found in the LLMConfig class. These changes seek to align the spelling with what is generally expected in LiteLLM's documentation.

This would be a breaking API change because existing implementations would need to adopt the new spelling.

List of files changed and why

• crawl4ai/async_configs.py - To update the LLMConfig "temperature" constructor initializer and instance member spelling.
• crawl4ai/extraction_strategy.py - Updating "temperature" spelling in the LLMExtractionStrategy docstring.
• deploy/docker/c4ai-code-context.md - Updating the docker code-context file with the correct spelling. I was unsure if this was necessary as it seems this file is generated but was unable to find where/how it was generated. I am happy to remove this code change, just wanted to be thorough.

How Has This Been Tested?

• Locally ran test_llm_filter.py

• Locally ran test_serialization.py

I was unable to get the other tests to run due to environmental issues, unrelated to the above code changes.

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added/updated unit tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes