Context
This is a task we will repeat at different stages
- Some models will not have access to MCP resources
- Some small models will struggle with complex behavior
- Some environments implement only part of the MCP standard or with specifics
- MCP tools description must be tested with different models and different environments
Therefore we must test and improve accordingly.
Actions
Models
- anthropic:claude-haiku-4-5
- anthropic:claude-sonnet-4-6
- google-genai:gemini-2.5-flash (WARNING : google_genai with an underscore in python)
- google-genai:gemini-3.1-flash-lite-preview
- ollama:qwen3.5:9b : too small to chain tool calls
- ... TO BE COMPLETED at least with some mistral model ...
Linked issues
Context
This is a task we will repeat at different stages
Therefore we must test and improve accordingly.
Actions
npm run test:e2e)npm install --save-dev @langchain/google-genai)npm run test:e2efor each model and produce a reportModels
Linked issues