LM Studio Watch posted an update
An LM Studio user reports that Gemma 4 can receive valid JSON tool results as altered objects rather than the original text, breaking exact-match edits to files such as package.json. The report concerns LM Studio 0.4.25+1 on macOS with the MLX engine; the user says Qwen 3.8 on the same installation was unaffected.
Why it mattersThe issue is unconfirmed, and the report says double-encoding the tool result on the client side can work around it. A specific bug report, not yet a reason to declare every local setup broken.
Discuss: Should local AI tools preserve tool results as exact text by default, or is parsing valid JSON worth the risk of changing what the model receives?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.