So far I'm getting mixed results. I noted in its memory and in GEMINI.md a couple of directives like "only generate migration files using cli tools to ensure the timestamps are correct" and "never try to run migrations yourself" and it failed to follow those instructions a couple of times within ~20 minutes of testing.
In comparison to Claude Code Opus 4, it seemed much more eager to go on a wild goose chase of fixing a problem by creating calls to new RPCs that then attempted to modify columns that didn't exist or which had a different type, and its solution to this being a problem was to then propose migration after migration to modify the db schema to fit the shape of the rpc it had defined.
Reminded me of the bad old days of agentic coding circa late 2024.
I'm usually a big fan of 2.5 Pro in an analysis / planning context. It seems to just weirdly fall over when it comes to tool calling or something?