Vibeleaderboard
← All Intel
Intel / repo

opencode v2.2.5

Source
github.com
Author
github-actions[bot]Top Viber
Date
Why it matters

opencode now accepts a percentage compaction buffer (e.g. 20%) in config, so one setting fits models with different context windows. Edit and read errors now point to the nearest matching lines or folder, helping the agent self-correct.

Key takeaways · AI-distilled
  • opencode v2.2.5 lets .buffer take a percentage of the model's , such as "20%", so one setting reserves free context on both small- and large-window models. Token counts still work.
  • Calls to a tool named bash now run as opencode's shell tool with the same permissions instead of failing. Failed edit and read calls now report the file's closest lines or the nearest existing folder, giving the something to correct against.
  • servers that send stdio messages over 10 MiB are no longer disconnected, and LiteLLM context-window errors now trigger compaction instead of stopping the session.
Terms in this piece · Glossary
  • context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
  • context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
More from github-actions[bot]
Recommended reads
Comments

Checking sign-in…

Loading comments…