The Boring Controls Every AI IDE Eventually Needs

AI IDEs feel impressive at first.

Then the boring stuff shows up. Quota gets fuzzy. A chat panel drags after a long session. The language server starts acting weird, and you waste twenty minutes blaming TypeScript when the editor just needed a kick.

That is the gap Antigravity Panel tries to cover.

It is a sidebar toolkit for Google Antigravity IDE users. It focuses less on novelty and more on operational controls.

The Problem Is Not Code

When an AI coding session goes sideways, the first instinct is to inspect the repo.

Bad assumption.

Sometimes the problem lives in the tool around the repo. Maybe a model quota is almost gone. Maybe the conversation cache grew into a brick. Maybe an internal service is stale after the IDE has been open since breakfast.

I have lost time to this exact shape of bug. The terminal looked clean. The app built. The editor still behaved like it had sand in the gears.

You need operational controls close to the work. Not buried three panels deep.

Quota Should Be Visible

Quota problems are annoying because they rarely announce themselves clearly.

One minute the agent is fast. Then the model changes tone, latency creeps up, or a workflow refuses to continue. You end up asking a bad question: "Did I break something?"

Antigravity Panel tracks model usage where the local environment exposes it, including Gemini, Claude, and GPT status data. It also includes threshold-style quota visualization and usage history.

That matters during heavy AI work.

If you are halfway through a refactor and the assistant starts limping, you should know whether the bottleneck is your code, the model, or the IDE session itself.

Cache Cleanup Is Not Cosmetic

Conversation cache sounds like housekeeping.

It is not.

Long AI sessions create drag. The IDE can feel sticky after a pile of prompts, edits, tool calls, and cached context. Restarting the whole environment works, but it is a blunt instrument. You lose flow.

Antigravity Panel exposes cache size checks and cleanup commands from the IDE.

The useful part is speed. You can inspect cache pressure, clean it, and keep moving without turning a small cleanup into a full ceremony.

Antigravity Panel: Show Cache Size
Antigravity Panel: Clean Cache

That is the kind of command you do not care about until the day it saves your afternoon.

Diagnostics Before Panic

The extension also exposes diagnostics and recovery commands:

Antigravity Panel: Run Diagnostics
Antigravity Panel: Restart Language Server
Antigravity Panel: Reload Window
Antigravity Panel: Reset User Status

None of this sounds glamorous.

Good.

Developer tools should make the next move obvious. If the language server is stale, restart it. If the window is in a bad state, reload it. If the user status is stuck, reset it.

That beats randomly deleting folders and hoping the IDE forgives you.

Auto-Accept Needs Respect

Antigravity Panel includes an Auto-Accept toggle.

That can be useful. It is also the feature you should treat with a little suspicion.

Auto-approval can be useful in a trusted repo when the agent is doing boring edits you have already constrained. It is a bad idea in a workspace you do not understand, or when commands touch files outside the project boundary.

This is why the project ships a disclaimer and keeps the feature visible as a deliberate toggle. Automation should feel like a switch you consciously flip, not a trapdoor.

Read the rules. Check your allowlist. Then decide.

Commit Messages Are Part Of The Loop

The panel also supports AI commit-message generation. You can wire it to Claude with an Anthropic API key, or use a local model setup when that fits your workflow.

This is a small thing with a real payoff.

When you are doing AI-assisted edits, the final diff can be oddly shaped: one component fix, one config change, a test adjustment, and a tiny docs patch. A commit message written from the diff helps you catch what actually happened.

It is not about pretty wording. It is about review hygiene.

A Toolkit For The Unsexy Layer

AI IDEs keep adding bigger features.

That is fine. But daily work usually breaks in smaller places: quota, cache, stale services, unclear status, hidden settings.

Antigravity Panel sits in that unsexy layer. It gives you knobs for the stuff that interrupts real coding sessions.

The stance is simple: if an IDE becomes an agent runtime, it needs operations tooling inside the IDE. Not as an afterthought.

Start there.