Hacker News Reader

Comment by tacone | Hacker News Reader

Noticed they are present in OpenRouter, but Qwen 3.8 is not there yet. Hopefully it'll get there soon.

For those who haven't noticed though, the context size they allow for Qwen is just 128k. Still interesting as a specialized sub-agent but not really well suited for long tasks.

View on HN

128k is effectively useless on even trivial toy size "not for real business use" coding projects, by the time you reach 105k to 115k tokens with loading code into context and new research/tasks, and ask it to modify something, it'll be vacating older stuff out of context and forgetting the whole picture of what you're working on.

Isn't context size one of the central motivations of the whole agent / orchestration business - fanning out increasingly detailed work to a tree of subagents. Orchestrator vs worker, hierarchical multitier trees, etc.

I guess this smaller context but faster llm engine could be good to develop your harness on to get faster results and faster iteration.

128k isn't even big enough to give a sub-agent a specific task on some very 'small' projects I work on, based just on the size of the python to work with (including extensive comments in the code) and documentation files, it'll run out of context before it can even accomplish one thing and report back to the main orchestrator.

128k is pretty much only good for chat/conversational/question asking (including tool calls for searching things and spitting back/parsing a set of results) or human interactive agent purposes.

128k tokens is about 12-20k lines of code/prompt right? Or more than an average novel. And you don't need all the source code or entire files in the context after all.

I wonder what the approximate context window of a human programmer is... less than 12k lines I'm sure.

Tokens are also occupied by the internal reuslts of 'thinking', for instance, using the latest opencode, give qwen 3.8-flash-next with 'high' thinking mode 50KB total of python to read in six different files, count the expected tokens you'd expect it to occupy in just the size of the python. Then count the actual token count taken up after it's finished thinking about the contents of the python and analyzing it before you give it a single directive.

It is common for the agent tools, MCP tool, skills, project context and system prompt to take between 5k and 25k tokens. This depends heavily on your agent and tool setup.

But that's before the prompt.

Then after the prompt, every tool call the agent makes adds to the context. Longer turns can easily consume 50k-100k tokens between the agent and various tool calls (reading the filesystem, reading files, reading compiler output, reading memories).

Then each "turn" with the agent stays in context and is fed into the next turn. Two or three turns and you're up near 250k.

I actually decided to run YOLO mode once on GPT 5.6 Luna setting it to the fastest speed and I struggled to fill up the context while I kept sending several dozen feature prompts in the same session.

One of the most boring tasks to give to a subagent is to make it run cargo test and summarize the result so that the main agent doesn't get polluted by the irrelevant tests.

You have to have a pretty inefficient use case for a subagent to think that 128k is not enough.

I have done the vast majority of my agentic coding work under 128k on a 256k context model and when I cross 128k, all I do is just ask for a handoff prompt to feed back into the next session. I do this because I was told the quality degrades as the context fills up and I fundamentally dislike random compaction, I don't even know what compaction does, it is completely intransparent.

Great observation. That’s not enough context even for some one shot xhigh requests.

When I put Qwen3.8 27B xhigh towards adding scope proxying to the Guice library, it one shotted a great impl using 250k context before stopping.

Part of the greatness of the model is that it just keeps going until it gets a great result. 128k context is disappointing.

Reply on news.ycombinator.com