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

DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

esengine.github.io

Post reply on HN
Print view View original

251–260 of 325 posts

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#251

Post by arthurcolle »

awoimbee wrote: post #242
dathery wrote: post #87

Earlier quoted context omitted.

The OpenCode devs talk about this on Twitter a lot, e.g. https://xcancel.com/thdxr/status/2048268697790300343 > tool call pruning breaks cache and people will tell you this is horrible and expensive > except i looked at some anthropic data and real user behavior ends up with better cache hits and 30% less spend > even this is needs to be analyzed further, it's just not simple > for openai data it's inverted! cache hi…

You didn't quote the interesting part: > our implementation is it only prunes calls from > 3 user messages ago, if context is > 40K, and only if there's at least 20K tokens to be removed Seems reasonable to me and explains why I can have long sessions (way longer than with zed agents) while still hitting cache. Opencode is just missing per-provider TTL.

I found that keeping current context utilization at 18% of total context length was best for minimizing spend, across all models with 400k context length or more

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#255

Post by subscribed »

jijji wrote: post #83
Den_VR wrote: post #36

Earlier quoted context omitted.

I’m feeling more a novice every day, but how isn’t this just handing over your code to team deepseek for whatever they might want

there's laws on the books in China that says that every company operating in China must aid and abet the Chinese government in espionage against the rest of the world. given those facts, I find it deeply troubling to be using anything coming out of China, especially a program that runs in the context of a Linux terminal on a machine that might have something important on it. I'd argue it's a back door waiting to happ…

I forbidden from working on the company code with DS, but if I have a private something that looks pretty much like one of the thousands repositories put there, it doesn't matter that much.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#256

Post by embedding-shape »

kiproping wrote: post #104
embedding-shape wrote: post #2

I'm not sure you need a "DeepSeek native coding agent" to take advantage of DeepSeeks cache, yesterday as the Codex quota usage issue still wasn't solved for me, I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex, and seems most of everything I did was basically cached as far as I can tell: https://i.imgur.com/7eKn6wN.png (2026-05-23 Input (Cache hit): 39,123,200 tokens, Input (Cache miss) 1,692,28…

This would be a better page to link to https://github.com/esengine/DeepSeek-Reasonix/blob/main/docs... They explain some of the the reasons why they have a better solution and why they are very opinionated >Automatic prefix caching activates only when the exact byte prefix of the previous request matches. Most agent loops reorder, rewrite, or inject fresh timestamps each turn — cache hit rate in practice: So they opt…

> Most agent loops reorder, rewrite, or inject fresh timestamps each turn

I haven't seen that, it'd be crazy slow if they did this. What "agent loops" are they talking about here specifically? The vagueness makes it sound potentially made up.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#257

Post by phrotoma »

jbellis wrote: post #156

As someone who has been writing harnesses for a year: the people at opencode etc aren't stupid, when they decide to break the prefix cache [usually partially] it's always because they've tested it and it gives better results overall. If you think that dsv4 behaves differently enough from the aggregate of other models, submit a PR with a patch to special case that to your harness of choice with evidence. Just blindly…

Is "harness" in this context ~= "agent"?

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#258

Post by Akamant »

HDBaseT wrote: post #199
chillfox wrote: post #41

Earlier quoted context omitted.

Deepseek v4 pro is definitely my preferred cheap model, it's very good, and I use it all the time for my personal projects (opencode go plan), but I also use Claude Opus all the time at work and Deepseek is not as good as that, but it does compete with Sonnet for capability, and beats it on price.

Deepseek V4 Pro is an amazing model, even without the unreal cost factored in. It is my default model at the moment. I'm not doing anything too complex though. I honestly found more expensive models like Qwen 3.6 to fail in tasks Deepseek nails. I'm interested in knowing what people are using for tasks which require a bit more thinking. Kimi 2.6? Qwen 3.7? GLM 5.1?

17 GoLang microservices for a serious project were written perfectly using the latest version of QWEN(3.6). The only areas where we really had to work hard were documentation and a very serious task breakdown. All of this was tested, and yes, a review was required, but everything was within reason. The deadline was 10 days of 24/7 work, including the review. When attempting to submit the same task, Opus 4.7/4.6 had to be stopped after three hours. If you have significant resources for experimentation, you can certainly try. For us, the choice is absolutely clear at this point.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#260

Post by 3uler »

embedding-shape wrote: post #48
3uler wrote: post #31

Earlier quoted context omitted.

Opencode has really bad cache stability issues that they seem uninterested in fixing at the moment.

That'd be really easy to spot and also fix, most likely. Any open issue you could point us to, must surely been reported already?

https://github.com/anomalyco/opencode/pull/14743
Post reply on HN