Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

test(llms): Claude 3.5 Sonnet v2 on Bedrock has a 200k window in the refreshed catalog (#8151)

João Mouraacd4b33a177e
diff --git a/lib/crewai/tests/llms/test_context_window.py b/lib/crewai/tests/llms/test_context_window.py
index ebeb8680e..6adb0cb8a 100644
--- a/lib/crewai/tests/llms/test_context_window.py
+++ b/lib/crewai/tests/llms/test_context_window.py
@@ -130,10 +130,12 @@ def test_affected_model_ids_use_their_specific_context_windows(
("gemma-4-31b-it", GEMINI_CONTEXT_WINDOWS, 262_144),
("amazon.nova-2-lite-v1:0", BEDROCK_CONTEXT_WINDOWS, 1_000_000),
("global.moonshotai.kimi-k3", BEDROCK_CONTEXT_WINDOWS, 1_000_000),
+ # 200k: LiteLLM's catalog had 1M here until its refresh for 1.15.28
+ # corrected it to the model's documented window.
(
"anthropic.claude-3-5-sonnet-20241022-v2:0",
BEDROCK_CONTEXT_WINDOWS,
- 1_000_000,
+ 200_000,
),
("us.anthropic.claude-opus-4-1-20250805-v1:0", BEDROCK_CONTEXT_WINDOWS, 200_000),
(