scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 35
litellm/tests/e2e/claude_code/thinking
History
Exact
mateo-berri 929ee52b87 fix(bedrock): preserve adaptive thinking effort through the /v1/messages bridge 
Claude Code drives Opus 4.7 with thinking {"type": "adaptive"} plus
output_config {"effort": "max"}. The anthropic-to-openai adapter
forwarded thinking verbatim for Claude models but dropped output_config,
and Bedrock Converse streams zero reasoningContent blocks for adaptive
thinking without an effort tier. Forward the effort subset of
output_config for Bedrock targets, accept it in the converse supported
params, and map it with the model's effort ceiling applied. Re-enable
the skipped e2e compat cell that catches this
2026-08-11 03:23:16 +00:00
..
__init__.py test(claude_code): move the Claude Code compatibility matrix under tests/e2e (#32548) 2026-07-14 19:19:03 -07:00
test_anthropic.py fix(e2e/claude_code): unblock stage collection, align proxy env names, register compat models (#33433) 2026-07-16 11:05:31 -07:00
test_azure.py fix(e2e/claude_code): unblock stage collection, align proxy env names, register compat models (#33433) 2026-07-16 11:05:31 -07:00
test_bedrock_converse.py fix(bedrock): preserve adaptive thinking effort through the /v1/messages bridge 2026-08-11 03:23:16 +00:00
test_bedrock_invoke.py fix(e2e/claude_code): unblock stage collection, align proxy env names, register compat models (#33433) 2026-07-16 11:05:31 -07:00
test_vertex_ai.py fix(e2e/claude_code): unblock stage collection, align proxy env names, register compat models (#33433) 2026-07-16 11:05:31 -07:00