Run interactive commands in Gemini CLI • Hacker News Board

Re: Run interactive commands in Gemini CLI

#71

Post by iamdamian » Thu, Oct 23, 2025, 4:52 PM UTC

jonfw wrote: post #65

redhale wrote: post #55

I have used Claude Code heavily, and I've been forced to use Gemini CLI heavily (for a particular client project). Of all my issues with Gemini CLI (and there are many), this addresses none of them. This is a fascinating product management prioritization decision. It makes me wonder if the people who build Gemini CLI actually use Gemini CLI for real work. Because I would think that if they did, they would surely have…

This is a very valuable use case for me personally. I frequently have the problem that I change things on the filesystem in a separate tab and the agent context gets out of sync. It fails on subsequent edits, often tries to reverse the changes that I made, and many times I have to copy/paste the command I ran and it's output back into the agent window. Your complaint is likely a product design decision rather than a…

Claude Code has an elegant solution to the problem you mention, without trying to cram everything into a single nested pane (which feels wrong to me).

In Claude Code, when you edit a file independent from the agent, it automatically notices and says something like "I see you've made a change. Let me take a look."

I wish Gemini CLI would've taken a similar approach, since it seems to fit better with a CLI and its associated Unix philosophy.

Re: Run interactive commands in Gemini CLI

#72

Post by guluarte » Thu, Oct 23, 2025, 4:58 PM UTC

Look at me, you are the model now

Re: Run interactive commands in Gemini CLI

#73

Post by zeld4 » Thu, Oct 23, 2025, 5:15 PM UTC

i gave up on gemini cli.

1 in 3 times I used it in past 2 months, it failed for really odd reasons, sometimes the node app just exception quit, sometimes gemini stuck and blame itself and gave up. same task I throw to cc and codex, they nailed without a blink...

Re: Run interactive commands in Gemini CLI

#74

Post by 0x457 » Thu, Oct 23, 2025, 5:24 PM UTC

nacs wrote: post #6

jgoodhcg wrote: post #5

Popping into nvim to check on something really quick seems immediately useful. I think I'll still want a dedicated tab or different terminal app to have my longer lived editor open but this might be nice for validating output with test runners or checking on a database entry in psql or something.

I'm not sure how usable neovim will be in what looks to be a 6 line high window as they show in the demo video.

Pretty sure you can expand it full-screen there.

Re: Run interactive commands in Gemini CLI

#75

Post by aiiizzz » Thu, Oct 23, 2025, 6:27 PM UTC

I'd prefer that the Gemini cli run inside a text file, rather than this way round.

And really, ctrl-f? Do these devs not use the terminal at all?

Re: Run interactive commands in Gemini CLI

#76

Post by breakingcups » Fri, Oct 24, 2025, 8:37 AM UTC

selvan wrote: post #18

From the blog " Gemini CLI spawns a new process within a pseudo-terminal in the background, leveraging the node-pty library...So how does this virtual terminal running in the background show up on your screen? Think of it like a video stream. Our new serializer takes a snapshot of the pseudo terminal at every moment—capturing every piece of text, every color, and even the cursor's position. These snapshots are then s…

That excerpt sounds like it was written by an LLM.

Re: Run interactive commands in Gemini CLI

#77

Post by no-name-here » Fri, Oct 24, 2025, 9:03 AM UTC

redhale wrote: post #55

I have used Claude Code heavily, and I've been forced to use Gemini CLI heavily (for a particular client project). Of all my issues with Gemini CLI (and there are many), this addresses none of them. This is a fascinating product management prioritization decision. It makes me wonder if the people who build Gemini CLI actually use Gemini CLI for real work. Because I would think that if they did, they would surely have…

Worse is that when it hits a 429 and switches models, it will tell you that it switched models for the rest of the session and that you need to enter a new prompt — even if files remain in a partially-changed and non-compilable state. Telling it to “continue” got it to wrap up one sub-item but didn't finish the overall change. At this point I avoid using Gemini for any large changes because it’s likely to hit a 429 and result in such a non-compilable state.

Re: Run interactive commands in Gemini CLI

#78

Post by OJFord » Fri, Oct 24, 2025, 11:19 AM UTC

CaptainOfCoit wrote: post #68

kaycey2022 wrote: post #64

Earlier quoted context omitted.

>most of the times, the tools works best with the models trained with those tools in mind This is a garbage state of affairs though

What do you expect? People building software using other models than they themselves develop? Or people training the models train them for software that isn't the software they develop themselves? It's like saying official car repair shops should repair any type of car, not just their brand. That's just not how the real world works.

Or they just don't even do it? Michelin tyres aren't best fitted by a Michelin shop, those don't exist. You go to KwikFit or whatever you think's best, and get Michelin or Continental or Pirelli or whatever you think's best fitted.

Re: Run interactive commands in Gemini CLI

#79

Post by antonvs » Fri, Oct 24, 2025, 1:40 PM UTC

iamdamian wrote: post #71

jonfw wrote: post #65

Earlier quoted context omitted.

This is a very valuable use case for me personally. I frequently have the problem that I change things on the filesystem in a separate tab and the agent context gets out of sync. It fails on subsequent edits, often tries to reverse the changes that I made, and many times I have to copy/paste the command I ran and it's output back into the agent window. Your complaint is likely a product design decision rather than a…

Claude Code has an elegant solution to the problem you mention, without trying to cram everything into a single nested pane (which feels wrong to me). In Claude Code, when you edit a file independent from the agent, it automatically notices and says something like "I see you've made a change. Let me take a look." I wish Gemini CLI would've taken a similar approach, since it seems to fit better with a CLI and its asso…

Gemini CLI notices changes when it tries to change something and doesn't find what it expects. Then it tells you it's going to reread, and typically handles it fine.

Re: Run interactive commands in Gemini CLI

#80

Post by antonvs » Fri, Oct 24, 2025, 1:44 PM UTC

OJFord wrote: post #78

CaptainOfCoit wrote: post #68

Earlier quoted context omitted.

What do you expect? People building software using other models than they themselves develop? Or people training the models train them for software that isn't the software they develop themselves? It's like saying official car repair shops should repair any type of car, not just their brand. That's just not how the real world works.

Or they just don't even do it? Michelin tyres aren't best fitted by a Michelin shop, those don't exist. You go to KwikFit or whatever you think's best, and get Michelin or Continental or Pirelli or whatever you think's best fitted.

Terrible analogy, because the issues involved in fitting car tires of different brands are in no way comparable to the differences between LLM behavior across models.