Repo · SDKs & integrations

opencode-smart-reasoning

OpenCode plugin: TypeSafe Jev (via OpenCode Zen SystemOne) picks per-request reasoning effort before the model call—cheap prompts stay cheap;…

Open github.com ↗

From the repository

OpenCode plugin that routes per-request reasoning effort for agents via Jev (TypeSafe SystemOne) — cheap prompts stay cheap, hard ones get full reasoning

ai-codingjevllm-agentsopencodeopencode-pluginreasoningtypesafe

How builders describe it

OpenCode plugin: TypeSafe Jev (via OpenCode Zen SystemOne) picks per-request reasoning effort before the model call—cheap prompts stay cheap; high-stakes work can bump effort—fail-open without a key.

OpenCode plugin that asks Jev once per prompt how much reasoning is needed, then maps minimal to xhigh effort onto the model's own variants without rewriting prompts.

The decision Jev makes

Any Jev question: yes or no, a choice, or a score, from your own stack.

Where it fits

Official and community SDKs, MCP servers and integrations for calling Jev from the languages and tools you already use. All 625 sdks & integrations projects →

Related projects