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

241–250 of 325 posts

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

#241

Post by vidarh »

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…

I've never seen an agent loop "reorder, rewrite, or inject fresh timestamps" each turn other than mostly towards the end of the messages. Messing with a large part of the context every turn would be a fairly crazy thing to do.

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

#242

Post by awoimbee »

dathery wrote: post #87
3uler wrote: post #31

Earlier quoted context omitted.

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

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.

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

#243

Post by vidarh »

gopher_space wrote: post #143
franknord23 wrote: post #111

Earlier quoted context omitted.

That sounds like the experience of writing Containerfiles; since steps are cached you want to pull the thing you are iterating on as far down as possible.

All of this work has been done before in different contexts. Memory management with bigger blocks and weaker definitions that change whenever some grad student gets a bright idea.

100%. Since you mention memory management: Generational GC is pretty much the same idea: Keep the stuff that's least likely to change an important property (liveness) together.

Conceptually the underlying general idea is to sort things based on stability if you can avoid recomputing properties of the stable part.

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

#244

Post by jbellis »

anon373839 wrote: post #222
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…

Are there any learning resources you'd recommend on writing harnesses? I'm interested in doing a non-coding one, but not really sure where to start.

Generically, I would say, just start building it and ask your favorite coding agent for advice when you get stuck. This is the first technology that can teach you how to use it! (But do ask a model with a recent knowledge cutoff, i.e. not gemini.)

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

#245

Post by watwut »

jijji wrote: post #207
goobatrooba wrote: post #128

Earlier quoted context omitted.

As a European I have to admit I am these days more worried about the US than China. See yesterday's article about the US government forcing Microsoft to give them lists of Dutch government officials. Utter madness. At least the Chinese mainly care about the money and power levers, the US about strange worlds of revenge and manipulation, trying to change or influence your government. E.g. which of the two countries ha…

The situation you reference is related to a specific investigation by US congress requesting documents about potentially illegal censorship actions by EU officials from a specific company (microsoft). The difference is that the laws in china are broadly defined to include giving all intellectual property of anyone back to the government with no oversight, for the purposes of espionage. The former relates to a specifi…

> If they did, no one would use cloud providers.

EU has literal directive about location of data which has to be located in the EU and not in the USA, because the data are in danger otherwise.

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

#247

Post by mordae »

ctxc wrote: post #215
estebarb wrote: post #196

Earlier quoted context omitted.

I'm not sure that is really the case, or relevant in practice. I have been using OpenCode with DeepSeek lately (regular coding). For instance, today I got 120 million input tokens hitting cache, vs just 2.59million missing cache.

Reads like a LOT of tokens to me. What does your usage /workflow look like? I'm v curious because although I do use Claude code, my token counts aren't nearly as much I want to know if I'm missing something cool!

Not OP, but I routinely load 150k tokens into context. A full sub-package to work on, select other files in the monorepo, e.g. front-end visualization and back-end data loader. Then work some 150k tokens, then start again.

At the end, cache hit rate is like 99.5% if Novita is not having issues.

For official DeepSeek API, 99.9% or something.

Custom harness that never compacts or otherwise doctors the history.

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

#248

Post by sparkleMing »

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…

The last time I heard about something like this, it was Claude Code intentionally injecting random strings to break caching when you're not using a Claude model. Aside from that kind of intentional sabotage, I don't think any coding agent would just ignore prefix caching.

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

#249

Post by MASNeo »

jijji wrote: post #207
goobatrooba wrote: post #128

Earlier quoted context omitted.

As a European I have to admit I am these days more worried about the US than China. See yesterday's article about the US government forcing Microsoft to give them lists of Dutch government officials. Utter madness. At least the Chinese mainly care about the money and power levers, the US about strange worlds of revenge and manipulation, trying to change or influence your government. E.g. which of the two countries ha…

The situation you reference is related to a specific investigation by US congress requesting documents about potentially illegal censorship actions by EU officials from a specific company (microsoft). The difference is that the laws in china are broadly defined to include giving all intellectual property of anyone back to the government with no oversight, for the purposes of espionage. The former relates to a specifi…

> no one would use cloud providers

I think many are trying to move away from US providers actually. FISA section 702 and the current administrations liberties taken towards international law are not helping. The trust problem is real.

Not sure I’d trust China with anything onshore. But offshore, it does seem they play by the rules, because it pragmatically serves the stability of the people. China has not started wars in the past 50 years or so. By that logic one may assume they’d not abuse the arguably broad powers over Chinese firms abroad to risk one now.

In a world where rules are increasingly less important how states use power matters more to me than how they claim to be monitored.

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

#250

Post by miroljub »

watwut wrote: post #245
jijji wrote: post #207

Earlier quoted context omitted.

The situation you reference is related to a specific investigation by US congress requesting documents about potentially illegal censorship actions by EU officials from a specific company (microsoft). The difference is that the laws in china are broadly defined to include giving all intellectual property of anyone back to the government with no oversight, for the purposes of espionage. The former relates to a specifi…

> If they did, no one would use cloud providers. EU has literal directive about location of data which has to be located in the EU and not in the USA, because the data are in danger otherwise.

Yep, and then they let US companies handle that data. One more proof EU regime is run by ... no, I won't tell, don't wanna get arrested.
Post reply on HN