Mateo Wang d489c04554 fix(anthropic): drop unknown legacy thinking keys under drop_params when rebuilding adaptive thinking (#46741) ... * fix(anthropic): drop unknown legacy thinking keys under drop_params when rebuilding adaptive thinking * fix(bedrock): drop unknown thinking keys under drop_params on display updates rebuilds Bedrock Invoke copied every caller thinking key when adding display updates, so an unknown key still reached the provider with drop_params on. Filter that copy the same way, and cover each chat call site plus the global litellm.drop_params path in tests * fix(anthropic): drop budget_tokens from rebuilt adaptive thinking under drop_params * test(anthropic): cover drop_params sources for rebuilt adaptive thinking on /v1/messages and Bedrock Invoke		2026-10-15 23:09:30 +00:00
..
chat_bridge	fix(anthropic): emit one tool_use block per call when a /v1/messages stream chunk carries several (#46492)	2026-10-15 04:27:51 +00:00
providers	fix(anthropic): drop unknown legacy thinking keys under drop_params when rebuilding adaptive thinking (#46741)	2026-10-15 23:09:30 +00:00
responses_bridge	fix(anthropic): send detail on input_image parts bridged from /v1/messages to Responses (#46720)	2026-10-15 22:33:09 +00:00
safeguards	feat(anthropic): generate auto mode safeguard_results with a classifier model on the /v1/messages chat bridge (#45600)	2026-10-14 13:09:11 +00:00
test_anthropic_messages_caller_tools_wire.py	fix(anthropic/adapter): stop translate_anthropic_tools_to_openai mutating the caller's input_schema (#34653)	2026-10-15 01:59:24 -07:00