Use the new Gemini 2.5 Flash

Updated to support Thinking Tokens as a ratio of the max allowed Updated tests Updated README
2025-06-12 20:46:54 +04:00
parent b34c63d710
commit 3aedb16101
27 changed files with 135 additions and 98 deletions
--- a/tests/test_prompt_regression.py
+++ b/tests/test_prompt_regression.py
@@ -31,7 +31,7 @@ class TestPromptRegression:
            return Mock(
                content=text,
                usage={"input_tokens": 10, "output_tokens": 20, "total_tokens": 30},
-                model_name="gemini-2.0-flash",
+                model_name="gemini-2.5-flash-preview-05-20",
                metadata={"finish_reason": "STOP"},
            )