compaction
7 stories and discussions about compaction, aggregated from every source we track.
Make Claude Code, Codex, and Cursor use fewer tokens. Local context compaction with measured savings. - philipppohlmann/compaction
Most of my coding agent work now runs through more than one agent. A manager agent brainstorms with me, starts an executor, checks on it, and later brings in a reviewer. Sometimes I resume a sessio…
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique…
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique…
We ran three context-compaction strategies through the same 178-question exam. FutureOS kept 83% of the values that had been compacted away; OpenCode kept 47%, Codex 38%. The difference isn't a better summary — it's…
In Our framework for reporting model misalignment OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the last six months". This one here is my favorite: …
Claude Code Session Compaction in 2026: How Context Summarization Works and What Your Agent...