Jev in production › Agent context and memory
OpenCode V2 plugin asks Jev which completed tool calls and results are still needed, compacting agent context without a model-generated summary.
Instead of asking a generative model to rewrite old conversation history into a summary, this plugin asks a decision model which completed tool calls and outputs are still useful.
This project ports the core approach from tamaratran/fast-jev-compaction to the OpenCode V2 plugin API, with hosted JEV and native local System One support for LM Studio and Ollama. The legacy LM Studio chat adapter remains available.
Status: experimental. The compaction strategy is intentionally conservative and falls back to OpenCode's native compaction when classification fails or the reduction is too small to justify an override. Supported today: hosted TypeSafe JEV, native local System One (LM Studio 0.4.26+, Ollama 0.35+, or another compatible server), and the...
For the project's own README, linking back here: