Open Code Config to point at a local running Llama server with Qwen 3.6, plus multi agent setup

opencode.json

{
  "$schema": "https://opencode.ai/config.json",

  "provider": {
    "llamacpp": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "llama-server (local)",
      "options": {
        "baseURL": "http://127.0.0.1:8080/v1"
      },
      "models": {
        "qwen3.6-35b-a3b": {
          "name": "Qwen3.6 35B-A3B (UD-IQ4_NL)",
          "tool_call": true,
          "reasoning": true,
          "limit": {
            "context": 65536,
            "output": 8192
          }
        }
      }
    }
  },

  "model": "llamacpp/qwen3.6-35b-a3b",
  "small_model": "llamacpp/qwen3.6-35b-a3b",
  "default_agent": "build",

  "compaction": {
    "auto": true,
    "prune": true
  },

  "agent": {
    "build": {
      "mode": "primary",
      "description": "Orchestrator. Decomposes work and delegates to subagents.",
      "temperature": 0.4,
      "top_p": 0.95,
      "steps": 60
    },

    "plan": {
      "mode": "primary",
      "description": "Read-only planning. Point this at a stronger model when you have one.",
      "temperature": 0.4,
      "top_p": 0.95
    },

    "implement": {
      "mode": "subagent",
      "description": "Implements ONE narrow, fully-specified change in a named set of files. Give it the exact files and the exact change; it will not plan or expand scope. Use one per independent change so each gets a clean context.",
      "temperature": 0.4,
      "top_p": 0.95,
      "steps": 40,
      "prompt": "{file:./.opencode/prompts/implement.md}"
    },

    "review": {
      "mode": "subagent",
      "description": "Reviews a change for correctness against its acceptance criteria and re-runs the tests. Read-only, cannot edit. Use after implement, and before telling the user something works.",
      "temperature": 0.3,
      "top_p": 0.95,
      "steps": 25,
      "permission": {
        "edit": "deny"
      },
      "prompt": "{file:./.opencode/prompts/review.md}"
    }
  }
}