Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Message your other Claude Code sessions

code.claude.com

Post reply on HN
Print view View original

11–20 of 76 posts

Re: Message your other Claude Code sessions

#11

Post by anonthrownaway »

4b11b4 wrote: post #9
Alifatisk wrote: post #3

I wish there was a clean way to compact the conversation into a prompt with all necessary context for a new fresh conversation.

There is, but your wish of "clean" is ambiguous.

Here's a view for "clean:"

1. Every chat should have a context used/remaining measurement so you know when you have to ditch the current chat for a fresh one.

2. Every chat should analyze and categorizes each element of context by how useful it is towards the overarching goal of the chat.

3. Every chat has a handoff button with a "usefulness" slider (say 1-5) that shows the total size of the context based on its setting.

4. The handoff automatically creates a new chat with the desired amount of context and a prompt to get it back to where you were.

That said, I am newb and so there is some reason why these non-deterministic LLMs can't do this :-/

Re: Message your other Claude Code sessions

#12

Post by bonoboTP »

jauntywundrkind wrote: post #6

i miss when opencode let you interact with your subagents. that was so so so much better. I broadly miss this feature to allow user agency, in letting users work with the various agents at they please, and to send data around.

Claude Code does allow this. You can talk to the subagents directly and watch what they are doing.

Re: Message your other Claude Code sessions

#13

Post by zhoujianfu »

andai wrote: post #4

I was reading about the HF hack and one of the first thing the GPT swarm did was build a messaging system for themselves. This reminded me of that. (Also of how weirded out I was by Moltbook when it came out. Time flies!) Unrelated: when my Claude/Codex finishes cooking (or needs my attention), it pings a local HTTP endpoint that plays a frog sound on my laptop. I found this massively boosts quality of life.

How do you know when they’re done (or need your attention)? Is that a standard “api”/hook? I want that!

Re: Message your other Claude Code sessions

#14

Post by Alifatisk »

4b11b4 wrote: post #9
Alifatisk wrote: post #3

I wish there was a clean way to compact the conversation into a prompt with all necessary context for a new fresh conversation.

There is, but your wish of "clean" is ambiguous.

With clean I mean the opposite of how I currently do it, which is by asking the model to compact the whole thread into a prompt which will act as context for next model.

My way of prompting this varies and every time I receive the blob of output, I can’t fell how well it managed to capture the necessary details. This way feels lika a dirty way to transfer knowledge from one conversation to another.

You said there is? What’s the options?

Re: Message your other Claude Code sessions

#18

Post by tym0 »

zhoujianfu wrote: post #13
andai wrote: post #4

I was reading about the HF hack and one of the first thing the GPT swarm did was build a messaging system for themselves. This reminded me of that. (Also of how weirded out I was by Moltbook when it came out. Time flies!) Unrelated: when my Claude/Codex finishes cooking (or needs my attention), it pings a local HTTP endpoint that plays a frog sound on my laptop. I found this massively boosts quality of life.

How do you know when they’re done (or need your attention)? Is that a standard “api”/hook? I want that!

All agents I know of have a hook system that can call arbitrary scripts.

Re: Message your other Claude Code sessions

#19

Post by simonw »

Alifatisk wrote: post #3

I wish there was a clean way to compact the conversation into a prompt with all necessary context for a new fresh conversation.

I'm fed up with compaction. I want my agent to get compacted but also retain full access to the prior conversation via search and tool calls - I want it to know "the requirements for X were discussed in detail previously in conversation C51E31CE-C985-4633-A749-DCC9805A7FEB" and have a tool that lets it dispatch a subagent to find those details again.

Do any of the coding agents have this already?

Re: Message your other Claude Code sessions

#20

Post by onlyrealcuzzo »

eigenblake wrote: post #10

Like some others, I also built this myself. Overly simply, with tmux, a memory tree, and handoff files and an orchestrator. And yet for how simple it was, it was so effective at minimizing the amount of duplicate context. It's like having shared specialist subagents who source and derive important shared knowledge from separate threads. It's useful because some skills just take too much of a token penalty to invoke a…

Does this work for different harnesses like Codex and Antigravity?
Post reply on HN