Getting started with Graphite (Team subscription), but haven't been able to get the AI code reviewer to identify glaring issues in my PRs. As a test, I created a mock PR to one of my projects with secrets from a local env file and a whole bunch of generated code (2 things that absolutely should not be checked in). The AI review just said that it had identified no issues and gave it a green tick... Also, I wish there was more context about the agent's thinking. So far I haven't been able to get it to output anything other than green ticks. GitHub Copilot is much more interactive in this regard. This is, in our mind, half the selling point of Graphite - so if it can't spot basic mistakes, we may have to reconsider.

(If applicable) To help us repro, please send the following if you haven't already: - PR links, screenshots, and/or debug output if applicable - Repro steps - Does this happen consistently? Just to you or others on your team also? - Is this a regression? Is the problem new? - If you're having an issue with the CLI, please send us debug logs using

gt feedback --with-debug-context <any message>

OK - will do!