Bring back per-change Apply + inline diff review — you’re throwing away your best UX advantage

Describe the request

Body:

I’m a paying Cursor user, and I’m genuinely angry about a recent regression in how Agent applies code changes.

What used to work (and why I chose Cursor):

When the Agent modified code for a specific task, I would see a clear before/after comparison — red/green inline diffs — and a simple Apply (or Accept) control for each change / each location. I could review this feature’s edits, accept what I wanted, and reject what I didn’t — file by file, chunk by chunk. That workflow was Cursor’s killer advantage: great UX + visual diff + granular control. It felt safe to let the Agent work because I was always one click away from approving or discarding a proposed change.

What I get now:

Changes often seem to land in files before I’ve consciously approved them.
The chat shows a session-level “Review +1181 -413” button — that’s a bulk summary of the entire conversation, not a list of “here are the 5 places I changed for this feature — Apply or reject each one.”
Diff View in the editor shows highlighting, but that’s not the same as the old Apply flow. Highlighting without a clear per-change Apply is just “show me damage after the fact.”
I searched settings for “Inline Diffs” — nothing useful. Auto-Run Mode is confusing and doesn’t restore the old mental model.
Ctrl+Shift+J doesn’t even open settings on my machine. The product has become harder to configure, not easier.
Why this matters:

I’m not asking for “no review.” I’m asking for the review model that made Cursor better than alternatives — review at the granularity of the Agent’s proposals, not only at the end of a long session with hundreds of lines in one Review panel.

Without that, I lose trust in every Agent run. I can’t tell whether logic is broken until I’ve already absorbed a huge diff or dig through Git. That’s the opposite of “AI pair programming with guardrails.”

What I want back (minimum):

Per-proposal or per-turn Apply/Reject — when the Agent edits code for a task, list the affected files/hunks and let me Apply or Reject before (or without) silently committing everything.
Clear separation between “preview / pending” and “applied to disk” — Diff View should not be a substitute for explicit acceptance.
Settings that are discoverable — if behavior moved to Auto-Run / Review / something else, name it consistently and document it. Don’t hide the old “always accept” behavior behind a popup and then remove the way to turn it off.
Honest threat (not a bluff):

Cursor’s edge was UX + visual diff + control. If you keep shipping Agent workflows that auto-apply and only offer session-level Review, you’re giving up the reason many of us didn’t stay on plain VS Code or jump to other tools. I’m already looking at Codex and other options. I don’t want to leave — I want the product I paid for back — but I won’t keep paying for an Agent that writes first and asks questions later.

Please treat this as high-priority product feedback, not a niche power-user request. A lot of us build production code; we need incremental, visual, reversible approval — not a single “Review 1000 lines” button at the bottom of a chat.

Thanks for reading. Happy to share version info, screenshots, and repro steps if needed.

— A frustrated long-time user

Operating System (if it applies)

Windows 10/11

Hey, thanks for the detailed feedback. This is a big topic, and you’re not the only one who feels this way. There’s a canonical thread about the same pain point here: Only some diffs are shown whhen agent makes changes 6K views, 386 likes. It’s worth voting there too so the signal stays in one place.

On the actual issue: per-change Accept or Reject didn’t go away, but in the new Agent Window the default flow shifted toward session-level Review. A few things you can tweak to get closer to the old behavior:

  • Auto-Run in the agent settings. If it’s off, the agent should ask for confirmation before applying changes, instead of writing everything to disk and showing a summary at the end.
  • Plan mode Plan Mode | Cursor Docs. The agent first creates a plan without changing files. You review it, then you run it. This matches your review before apply workflow well.
  • Inline diff visibility. In Cursor Settings there’s a toggle for inline diffs. Search for inline diff in Settings, not in App Settings.

About timing for bringing the old flow back as the default: I can’t give an ETA. The team can see there’s a lot of feedback and some bugs around the review flow. If there’s anything concrete to share, I’ll follow up.

If any of the settings above don’t work as described, for example Auto-Run is off but changes still apply without asking, tell me your Cursor version and OS, and ideally the Request ID from one of those sessions top-right chat menu > Copy Request ID. That would look like a specific bug rather than a UX regression, and it can be investigated separately.

I second this. While I understand vibe coding is all the craze which seems to be what the new agent UI is targeted for even Codex has achieved your staple accept/reject UI in their application.

This is literally the only feature holding me back from swapping from Editor to the new Agent UI and I will not make the switch until that returns. It is one of your top features by far and should be a staple for all agent led development. There are so many times when the agent does 90% of the code correct but 1 or 2 changes are wrong and need to be rejected.

Please add it to your new UI - this checks all the boxes on your new direction and will bring your current user base closer to making that swap if you ask me, I know I will.

Hey, thanks for the +1. The strongest signal on this topic is now in the canonical thread: Only some diffs are shown whhen agent makes changes It makes sense to like it there too so the feedback is combined in one place, that’s where the team is looking.

On your request: per-change Accept/Reject didn’t go away, but the default flow in the Agent Window shifted toward session-level Review. If you haven’t tried it yet, in the post above I listed a couple settings Auto-Run off, Plan mode, and the inline diff toggle that make it behave closer to the old flow.

I don’t have a timeline for bringing the old flow back as the default. Feedback noted.