Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Use the public fastmcp call_tool so the MCP guard test survives fastmcp 4 (#10110)
Daniel Han6a8b3874f677
diff --git a/studio/backend/tests/test_mcp_training_start_guard.py b/studio/backend/tests/test_mcp_training_start_guard.pyindex ddff1406d4b..d18b4b90140 100644--- a/studio/backend/tests/test_mcp_training_start_guard.py+++ b/studio/backend/tests/test_mcp_training_start_guard.py@@ -361,8 +361,10 @@ def test_the_mcp_tool_surfaces_the_409_as_a_tool_error_not_a_dict(monkeypatch):from fastmcp.exceptions import ToolError+ # call_tool, not the private _call_tool_mcp fastmcp 4 dropped: requirements+ # floor it at 3.0.2 and never cap it, so a test may only use the public API.with pytest.raises(ToolError) as tool_error:- asyncio.run(server._call_tool_mcp("start_training", {"config": _config()}))+ asyncio.run(server.call_tool("start_training", {"config": _config()}))# mask_error_details defaults False, so the 409 detail survives to the client# (as the text of an isError CallToolResult, not a JSON-RPC protocol error).