用 Plugin 组合生命周期

// experiments/shared/memory.ts
import { definePlugin } from "niceeval/plugin";

type MemoryOptions = {
  readonly model: string;
};

export const memory = definePlugin<MemoryOptions>({
  name: "acme.memory",
  behaviorRevision: "1",
  instanceKey: ({ model }) => model,
  experiment: ({ model }) => ({
    identity: { model },
    setup: (ctx) => ctx.progress({ message: `启动 ${model} memory service` }),
    teardown: (ctx) => ctx.diagnostic({
      code: "memory-service-stopped",
      level: "warning",
      message: `${model} memory service stopped`,
    }),
  }),
  sandbox: ({ model }) => ({
    identity: { model },
    setup: (_sandbox, ctx) => ctx.progress({ message: "连接当前 Sandbox" }),
    teardown: (_sandbox, ctx) => ctx.progress({ message: "断开当前 Sandbox" }),
  }),
});

export default defineExperiment({
  agent: codexAgent({
    skills: [{ kind: "local", path: ".agents/skills/memory" }],
  }),
  model: "gpt-5.6-luna",
  plugins: [
    memory({ model: "gpt-5.6-luna" }),
    telemetry(),
  ],
  sandbox: dockerSandbox({
    source: { type: "image", image: "acme/codex-memory:1" },
  }),
});

export default defineEval({
  plugins: [fixtureLifecycle(), diagnosticsLifecycle()],
  async test(t) {
    const turn = await t.send("完成任务");
    await turn.succeeded().orStop();
  },
});

npx niceeval exp codex-memory --dry
npx niceeval exp codex-memory memory/smoke