Fix langchain-google-genai integration by stripping 'models/' prefix

Fixes #3702

When using langchain-google-genai with CrewAI, the model name would include
a 'models/' prefix (e.g., 'models/gemini/gemini-pro') which is added by
Google's API internally. However, LiteLLM does not recognize this format,
causing a 'LLM Provider NOT provided' error.

This fix strips the 'models/' prefix from model names when extracting them
from langchain model objects, ensuring compatibility with LiteLLM while
maintaining backward compatibility with models that don't have this prefix.

Changes:
- Modified create_llm() in llm_utils.py to strip 'models/' prefix
- Added comprehensive tests covering various scenarios:
  - Model with 'models/' prefix in model attribute
  - Model with 'models/' prefix in model_name attribute
  - Model without prefix (no change)
  - Case-sensitive prefix handling (only lowercase 'models/' is stripped)

Co-Authored-By: João <joao@crewai.com>

src/crewai/utilities/llm_utils.py

@@ -41,6 +41,10 @@ def create_llm(
             or getattr(llm_value, "deployment_name", None)
             or str(llm_value)
         )
+        
+        if isinstance(model, str) and model.startswith("models/"):
+            model = model[len("models/"):]
+        
         temperature: float | None = getattr(llm_value, "temperature", None)
         max_tokens: int | None = getattr(llm_value, "max_tokens", None)
         logprobs: int | None = getattr(llm_value, "logprobs", None)