v1.5.7-alpha.9

Add detailed debug logs to OpenAIBrain (actual Brain in use)

v1.5.7-alpha.8

Add detailed debug logs to OpenAIBrain (actual Brain in use)

v1.5.7-alpha.11

Fix: add System.Linq using for Metadata serialization

v1.5.7-alpha.10

Fix OpenAIBrain: extract token usage from Metadata instead of InnerCo…

v1.5.7-alpha.7

Add CachedTokens extraction to AzureAIInferenceBrain using reflection

v1.5.7-alpha.6

Pass TokenUsageStatistics to AIChatHandleStreamAsync for monitoring

v1.5.7-alpha.5

Add layered logging to trace brain creation and GetStreamingTokenUsag…

v1.5.7-alpha.4

Upgrade Semantic Kernel to 1.66.0 for cache support

v1.5.7-alpha.3

Move cache monitoring to AzureOpenAIBrain

v1.5.7-alpha.2

Add prompt cache monitoring logs

- Extract cached token count from OpenAI API response
- Log cache hit/miss status with detailed metrics
- Display cache hit rate percentage for monitoring
- Support both normal and streaming chat modes
- Use string interpolation for log messages