Skip to content

Agent! 1.1.1 (build 195)

Choose a tag to compare

@AgentiLoop AgentiLoop released this 30 Aug 04:43
· 33 commits to main since this release
image

Highlights

πŸ—œοΈ Compaction β€” Lossless, Bounded & Everywhere

Closes out the remaining compaction gaps behind #37:

  • Tier 2 pruning is no longer lossy β€” pruneMessages now spills every tool result to the recovery cache before collapsing it, and each summary line carries the exact restore_tool_result(tool_use_id:"...") recipe. Nothing compaction touches is unrecoverable anymore
  • Spill cache bounded at 50MB β€” .agent/toolcache evicts oldest-first after each spill instead of growing forever
  • Per-project spills for ALL providers β€” LM Studio/Ollama/vLLM/OpenAI-compatible services now point the spill cache at the project folder like Claude always did (previously their spills landed in a temp dir)
  • Per-iteration threshold refresh β€” the async context-window fetch (LM Studio /api/v0/models, Ollama /api/show, vLLM /v1/models) can land after a task starts; all three loops (main, tab, sub-agent) now pick up the real threshold on the next turn instead of running the whole task on the 32Kβ†’17,600 fallback
  • Circuit breaker recovers β€” after 3 failed compaction attempts, compaction retries once the transcript grows ~25% past the last attempt instead of never compacting again
  • Screenshot tool results now compact β€” block-array tool_result content (image returns) is finally token-counted (nested text + per-image cost) and microcompacted: text spilled, images dropped, recoverable stub left behind. Vision-heavy sessions were previously invisible to the compactor
  • Sub-agents compact too β€” long research agents ran without any compaction and grew until the provider rejected the transcript; they now run the same tiered compaction as the main loop
  • Sharper trigger for code β€” the cheap chars/4 pre-estimate is inflated 25% (dense code β‰ˆ 3.3 chars/token) so the precise on-device token count isn't skipped when it matters; scaled keepRecent now applies to Tier 2 as well (6–24 messages by context budget)
  • Bounded summary cache β€” the in-memory Apple AI summary cache caps at 512 entries

πŸ”’ Versioning

  • Bumped version 1.1.0 (build 194) β†’ 1.1.1 (build 195)

Full Changelog: v1.1.0.194...v1.1.1.195