Google Team Member d0b33a0569 fix: cache read write token counts in LiteLLM and Anthropic models ...

Extract cache creation (write) tokens from LiteLLM and Anthropic model
usage metadata and map them to the GenerateContentResponseUsageMetadata
object. This ensures they are recorded in telemetry, allowing correct cost
calculations for prompt caching with providers like Bedrock.

Close #5835

PiperOrigin-RevId: 967259812

2026-08-19 09:44:47 -07:00

..

benchmarks

perf: avoid deepcopy of session contents when building LLM requests

2026-06-30 14:36:32 -07:00

integration

feat(eval): support custom metrics in AgentEvaluator

2026-08-18 00:17:15 -07:00

remote/triggers

chore: migrate from gemini-1.* and gemini-2.0* to gemini-2.5-*

2026-04-29 10:34:22 -07:00

unittests

fix: cache read write token counts in LiteLLM and Anthropic models

2026-08-19 09:44:47 -07:00

__init__.py

chore: Upgrade to headers to 2026

2026-01-20 14:50:09 -08:00