v2.15.0

Added

• Message Thinking Properties - Added thinking and cleaned_content properties to Message class
  • thinking: Extracts content inside <think> tags (reasoning trace from models like Qwen3, DeepSeek R1)
  • cleaned_content: Returns content with <think> tags removed (actual response)
  • Multiple <think> blocks are concatenated
  • Returns None for thinking if no tags present

Usage

response = model.chat_complete(messages)
msg = response.choices[0].message

msg.content          # "<think>reasoning...</think>\n\n42"
msg.thinking         # "reasoning..."
msg.cleaned_content  # "42"

Full Changelog: v2.14.1...v2.15.0