OpenAI’s Codex uses encrypted server-side context compaction, and Pi can now enable it
dotey · x · 2026-07-23
OpenAI’s Codex uses server-side encrypted context compaction that appears to work better than local alternatives for long-running tasks.
- The catch: this compaction is implemented on the service side and is encrypted, so third-party harnesses such as Pi do not enable it by default.
- Pi can still turn it on through an extension/plugin, which brings the same server-side compaction behavior into that environment.
- The post also points to benchmark evidence suggesting OpenAI’s compaction performs better than other approaches on extended tasks.
More from coding & agent
- Ben Bajarin: Frontier AI is becoming the enterprise cyber-defense stack — BenBajarin · 2026-10-26
- Building AI bots on raw APIs? Devs say models are 'dumb without the harness' — madeofAjala · 2026-10-26
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- The CLI is no longer the ideal interface for AI agents, argues AI communicator Elvis Omarsar — omarsar0 · 2026-10-26
- Microsoft demos intent-classifying agents built with Copilot App and Foundry, deployable across Teams and Outlook — marlene_zw · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26