01Entry
Pi 0.86.0
Pi 0.86.0 adds prompt cache warming to keep caches alive during long tool runs, plus per-model compaction budgets. Breaking: custom pi-ai providers now receive TranscriptContext instead of Context.
01Entry
Pi 0.86.0 adds prompt cache warming to keep caches alive during long tool runs, plus per-model compaction budgets. Breaking: custom pi-ai providers now receive TranscriptContext instead of Context.