News for hackers. Stuff that matters.

sasipi247

Re:All your agents are going async on Wednesday April 22, 2026 @12:25PM (#47865825)
OpenAI Responses API has WebSocket mode, which can be used instead of SSE, which works very well and feels like a leap forward in terms of performance.

https://developers.openai.com/api/docs/guides/websocket-mode

I have been building on it over the past month holding WebSocket sessions on workers warm, and command routing using NATS JetStream. With this, it has made using sidecar threads for a main thread very simple, as the worker treats them similar.

Re:Codex for almost everything on Thursday April 16, 2026 @02:27PM (#47797485)
The macOS app version of Codex I have doesn't show reasoning summaries, just simply 'Thinking'.

Reasoning deltas add additional traffic, especially if running many subagents etc. So on large scale, those deltas maybe are just dropped somewhere.

Saying that, sometimes the GPT reasoning summary is funny to read, in particular when it's working through a large task.

Also, the summaries can reveal real issues with logic in prompts and tool descriptions+configuration, so it allowing debugging.

i.e. "User asked me to do X, system instructions say do Y, tool says Z which is different to what everyone else wants. I am rather confused here! Lets just assume..."

It has previously allowed me to adjust prompts, etc.

Re:Claude Opus 4.7 on Thursday April 16, 2026 @02:16PM (#47797354)
I noticed this also, and was abit taken back at first...

But I think this is good thing the model checks the code, when adding new packages etc. Especially given that thousands of lines of code aren't even being read anymore.

Re:Ask HN: What Are You Working On? (April 2026) on Sunday April 12, 2026 @06:22PM (#47745174)
I am working on a system built around the OpenAI Responses API WebSocket mode as performance is something that interests me.

Its like a microservices architecture with NATS JetStream coordinating stuff. I want to keep the worker core as clean as possible, just managing open sockets, threads and continuation.

Document querying is something I am interested in also. This system allows me to pin a document to a socket as a subagent, which is then called upon.

I have hit alot of slip ups along the way, such as infinite loops trying to call OpenAI API, etc ...

Example usage: 10 documents on warm sockets on GPT 5.4 nano. Then the main thread can call out to those other sockets to query the documents in parallel. It allows alot of possibilities : cheaper models for cheaper tasks, input caching and lower latency.

There is also a frontend

Alot of information is in here, just thoughts, designs etc: https://github.com/SamSam12121212/ExplorerPRO/tree/main/docs