Managing context on the Claude Developer Platform

Post by tortilla » Sun, Oct 05, 2025, 2:05 PM UTC

diggan wrote: post #38

qwertox wrote: post #36

I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…

I kind of do this, semi-manually when using the web chat UIs (which happens less and less). I basically never let the conversations go above two messages in total (one message from me + one reply, since the quality of responses goes down so damn quick), and if anything is wrong, I restart the conversation and fix the initial prompt so it gets it right. And rather than manually writing my prompts in the web UIs, I man…

Post by swader999 » Sun, Oct 05, 2025, 2:31 PM UTC

blixt wrote: post #34

deepdarkforest wrote: post #11

Context editing is interesting because most agents work on the assumption that KV cache is the most important thing to optimise and are very hesitant to remove parts of the context during work. It also sometimes introduces hallucinations, because parts of the context are with the assumption that eg tool results are there, but theyre not. Example Manus [0]. Eg, read file A, make changes on A. Then prompt on some more…

Yes we had the same issue with our coding agent. We found that instead of replacing large tool results in the context it was sometimes better to have two agents, one long lived with smaller tool results produced by another short lived agent that would actually be the one to read and edit large chunks. The downside of this is you always have to manage the balance of which agent gets what context, and you also increase…

Post by hendersoon » Sun, Oct 05, 2025, 2:54 PM UTC

mirsadm wrote: post #44

Jowsey wrote: post #43

Earlier quoted context omitted.

Related, it feels like AI Studio is the only mainstream LLM frontend that treats you like an adult. Choose your own safety boundaries, modify the context & system prompt as you please, clear rate limits and pricing, etc. It's something you come to appreciate a lot, even if we are in the part of the cycle where Google's models aren't particularly SOTA rn

How are they not SOTA? They're all very similar with ChatGPT being the worst (for my use case anyway). Like adding lambdas and random c++ function calls into my vulkan shaders.

Post by brulard » Sun, Oct 05, 2025, 3:13 PM UTC

james_marks wrote: post #49

qwertox wrote: post #36

I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…

I exit and restart CC all the time to get a “Fresh perspective on the universe as it now is”.

Post by brulard » Sun, Oct 05, 2025, 3:29 PM UTC

crvdgc wrote: post #28

EnPissant wrote: post #20

Earlier quoted context omitted.

Claude Code already compacts automatically.

I believe Codex CLI also auto compacts when the context limit is met, but in addition to that, you can manually issue a /compact command at any time.