chore: Pin litellm dependency to versions below 1.80.17

This is a stopgap before the actual fix is added for 1.80.17+.

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 859351463

Author: wuliang229

pyproject.toml

@@ -123,7 +123,7 @@ test = [
   "kubernetes>=29.0.0",                           # For GkeCodeExecutor
   "langchain-community>=0.3.17",
   "langgraph>=0.2.60, <0.4.8",                    # For LangGraphAgent
-  "litellm>=1.75.5, <1.81.0",                     # For LiteLLM tests
+  "litellm>=1.75.5, <1.80.17",                    # For LiteLLM tests
   "llama-index-readers-file>=0.4.0",              # For retrieval tests
   "openai>=1.100.2",                              # For LiteLLM
   "pytest-asyncio>=0.25.0",
@@ -153,7 +153,7 @@ extensions = [
   "docker>=7.0.0",                              # For ContainerCodeExecutor
   "kubernetes>=29.0.0",                         # For GkeCodeExecutor
   "langgraph>=0.2.60, <0.4.8",                  # For LangGraphAgent
-  "litellm>=1.75.5, <1.81.0",                   # For LiteLlm class. Currently has OpenAI limitations. TODO: once LiteLlm fix it
+  "litellm>=1.75.5, <1.80.17",                  # For LiteLlm class. Currently has OpenAI limitations. TODO: once LiteLlm fix it
   "llama-index-readers-file>=0.4.0",            # For retrieval using LlamaIndex.
   "llama-index-embeddings-google-genai>=0.3.0", # For files retrieval using LlamaIndex.
   "lxml>=5.3.0",                                # For load_web_page tool.