OpenAI API adds 12-hour prompt caching; roboclawbot auto-opens config PR within minutes
heyneighbor · x · 2026-10-21
OpenAI's developer team announced that the API now supports opt-in 12-hour prompt caching: persistent agents can reuse context all day, keeping shared instructions, tools, and context cached longer while paying lower cached-input rates even as inputs change.
Developer Peter Steinberger then asked @roboclawbot (an OpenClaw-based automation agent) to research the feature, add a config option, and open a PR — the bot promptly spun up a session and created a prompt-cache-config branch. The poster then publicly asked the bot to produce a one-minute explainer video, calling it 'DevRel in public, extreme mode.'
More from coding & agent
- Dad's Codex setup catches his kid sneaking YouTube on the Portal while he's at work — msg · 2026-10-21
- Dev reports a possible 2x throughput improvement for once-campfire-Jai — lucasmeijer · 2026-10-21
- PhD student open-sources Homecoming, an app aggregating personal data from 2,000+ sites for user modeling — kenziyuliu · 2026-10-21
- Running >1 autonomous agent: doc bloat, review bottlenecks, and why "don't edit" fails — menhguin · 2026-10-21
- LangChain expands agent redteaming beta: 34 hypotheses tested, 9 findings in one run — hwchase17 · 2026-10-21
- OvertChat: a polished self-hosted ChatGPT-style UI for local models, one-command install — anitamaxwynnn69 · 2026-10-21