ryan-crabbe-berri 05de300ed6 fix(anthropic): keep signed empty thinking blocks and honor thinking.block_binding (#46342) ... * fix(anthropic): treat adaptive thinking as enabled when mapping response_format is_thinking_enabled only recognised thinking.type=enabled, so a request that paired thinking.type=adaptive with response_format took the synthetic JSON tool path with a forced tool_choice, which Anthropic rejects alongside thinking. The same check also gates the Bedrock Converse and Databricks forced tool_choice downgrades, so they now see adaptive thinking too. * fix(anthropic): keep signed thinking blocks with empty text on chat completions Models that default to display: omitted return signed thinking blocks whose text is empty, and Anthropic rejects the next turn when they are not replayed unchanged. is_unsignable_thinking_block dropped them along with unsigned blocks, and the inline content path required non-empty text, so a tool-use turn on Opus 4.7+ or the 5 families lost its thinking blocks and 400ed on the tool-result turn. Only a missing signature now drops a block, and the mid-conversation system placement mirrors that rule. The /v1/messages strip helper is left to #41362. * fix(anthropic): skip the thinking-strip retry when block_binding asks for an error The /v1/messages retry loop strips thinking blocks and resends on any invalid-thinking 400, including the binding mismatch a caller opted into with thinking.block_binding.prefix_mismatch_behavior: error. The retry decision now sees the request body and surfaces that 400 instead of overriding the caller's choice. #42888 covers the litellm_params side. * fix(bedrock): carry thinking.block_binding through the Invoke thinking rebuilds Bedrock Invoke rebuilt the thinking param from scratch when display: updates was requested, on both the /v1/messages and chat completions paths, and the legacy enabled-to-adaptive translation plus the clear_thinking injection did the same, so thinking.block_binding never reached Bedrock. Every rebuild now spreads the caller's thinking and only overrides the keys it owns, and AnthropicThinkingParam types block_binding. The thinking-binding-controls beta was already on the Bedrock allowlist. * fix(anthropic): keep forcing the response_format tool under adaptive thinking This reverts ad9e861ae7. Anthropic, Bedrock Invoke and Vertex all accept a forced tool_choice next to thinking.type=adaptive and only reject it with type=enabled, so counting adaptive as enabled fixed no live failure. It did drop the forced JSON tool, so Claude answered response_format requests in prose, and it downgraded a required tool_choice to auto on Bedrock Converse * test(e2e): drop the adaptive thinking tool round trip case With adaptive thinking the model often skips thinking on the weather prompt, so turn 1 carries no signed empty block and the case fails before the replay it is meant to cover. Anthropic also answers the replay with a 200 whether or not the block is forwarded, so the case could not tell the fix from main. The factory unit tests pin the outgoing shape instead * fix(anthropic): only skip the thinking-strip retry for a binding mismatch 400 prefix_mismatch_behavior: error asks Anthropic to reject a block bound to another conversation. It says nothing about unrelated bad blocks such as a null signature, so those still get the strip-and-retry self-heal. Also trims the empty-thinking docstrings to what the code guarantees and types the new test parameters * refactor(anthropic): narrow thinking fields with the mapping validator instead of typing.cast typing.cast is banned by the strict ruff gate (TID251), so the three new casts pushed that rule one over its merge-base count. The existing pydantic mapping validator gives the same typed view without an unchecked cast, and it now has a generic name since it is no longer only used for Claude Code payloads * refactor(anthropic): read thinking settings through the validated mapping so basedpyright stays at its merge-base count The Bedrock clear_thinking rewrite still narrowed with a cast and an untyped dict fallback, which added two reportUnknownVariableType errors. It now uses the same pydantic mapping validator, made public for that reuse, and the retry hook validates the request body itself so the handler passes a typed dict instead of an untyped one --------- Co-authored-by: yuneng-jiang <yuneng@berri.ai> (cherry picked from commit f470e418ea)		2026-10-20 01:06:24 -07:00
..
__init__.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_aiohttp_cleanup_closed.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_aiohttp_handler.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_aiohttp_so_keepalive.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_aiohttp_transport.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_asgi_handler.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_async_client_cleanup.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_container_handler.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_credential_leak_prevention.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_gemini_session_leak.py	test(unit): stop test modules from putting their own directory on sys.path (#43421)	2026-09-28 12:20:20 -07:00
test_http_handler.py	test(ci): repair stale tests and flaky CI infrastructure (#43983)	2026-10-01 17:46:43 +00:00
test_llm_http_handler.py	fix(anthropic): keep signed empty thinking blocks and honor thinking.block_binding (#46342)	2026-10-20 01:06:24 -07:00
test_mock_transport.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00