Shxiao 7fe8317fc4 fix(llm): correct gpt-4o-mini context window 200000 -> 128000 (#7294) ...

gpt-4o-mini's official context window is 128,000 tokens (OpenAI
announcement and API docs; litellm's model database agrees), but the
shared LLM_CONTEXT_WINDOW_SIZES table and the OpenAI/Azure provider-local
tables listed 200000 - apparently copied from the neighboring o3-mini /
o4-mini entries. With CONTEXT_WINDOW_USAGE_RATIO = 0.85, crews resolved
the usable window to 170000 instead of 108800, letting history grow past
the model's real 128k limit and failing with API 400s on long runs.

Fixes #7293

2026-09-07 11:11:57 +05:30

..

cli

feat: bump versions to 1.15.20 (#7270)

2026-09-04 09:40:31 -03:00

crewai

fix(llm): correct gpt-4o-mini context window 200000 -> 128000 (#7294)

2026-09-07 11:11:57 +05:30

crewai-core

feat: bump versions to 1.15.20 (#7270)

2026-09-04 09:40:31 -03:00

crewai-files

feat: bump versions to 1.15.20 (#7270)

2026-09-04 09:40:31 -03:00

crewai-tools

feat: bump versions to 1.15.20 (#7270)

2026-09-04 09:40:31 -03:00

devtools

feat: bump versions to 1.15.20 (#7270)

2026-09-04 09:40:31 -03:00