Surprised people still expect this in a world where Codex and Claude both hide all reasoning traces. Sadly there wasn't really anything we could show you here because we had probably not received anything from OpenAI yet. Fun fact: in most real-world cases agents spend less than 1% of their time streaming text. They spend the majority of the time doing reasoning (which doesn't stream), and running tools (which would be malformed if streamed).

thomasgauvin@thomasgauvin14h ago

ok i'm taking t3code for a spin. but like... responses are not streamed? compare with Hermes (also plugged in to Codex). what am I doing wrong? https://t.co/ReDV6LH1wH