Cursor Agent 4b4195e8da fix: make Azure Responses OpenAICompletion mock reliable under xdist ...

Patch AzureCompletion._openai_completion_class instead of the dynamic
import target so Responses delegate tests do not intermittently use the
real OpenAICompletion and fail under pytest-xdist.

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

2026-08-05 11:08:32 +00:00

..

anthropic

fix: detect Anthropic preview tool-use blocks (#6629)

2026-07-24 15:32:38 -03:00

azure

fix: make Azure Responses OpenAICompletion mock reliable under xdist

2026-08-05 11:08:32 +00:00

bedrock

JSON first crews (#6131)

2026-06-14 04:19:48 -03:00

google

feat(otel): surface real finish_reason + sampling params + response.id on LLM events (#5945)

2026-06-05 07:23:38 -04:00

hooks

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

litellm

chore: drop tiktoken from anthropic async max_tokens test

2026-04-11 03:20:20 +08:00

openai

fix(openai): recover from the GPT-5.6 tools + reasoning_effort 400 (#6660)

2026-07-26 12:48:17 -03:00

openai_compatible

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

snowflake

Handle Snowflake Claude stringified tool calls (#6008)

2026-06-02 19:37:18 -03:00

__init__.py

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_multimodal_integration.py

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

test_multimodal.py

Lorenze/fix/file input not working reliably (#6020)

2026-06-02 17:14:51 -07:00

test_prompt_cache.py

chore(crewai): drop self-explanatory comments

2026-05-26 10:23:33 -07:00

test_tool_call_streaming.py

fix: clear CodeQL incomplete URL substring sanitization alerts (#6804)

2026-08-05 13:28:47 +08:00