AgentHub/server/__tests__/codex-nudge.test.js

/**
 * @file Unit tests for the codex evidence safety net: nudges a live codex pane
 * to run `agenthub stage --evidence` when the lane has sat at an inferred (
 * evidence-less) stage past the delay, without ever writing stage itself.
 * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
 */

const os = require("node:os");
const path = require("node:path");

const SUITE_DB_PATH = path.join(
  os.tmpdir(),
  `dashboard-codex-nudge-${Date.now()}-${process.pid}.db`
);
process.env.DASHBOARD_DB_PATH = SUITE_DB_PATH;

const { describe, it, beforeEach, afterEach } = require("node:test");
const assert = require("node:assert/strict");

const { db } = require("../db");
const lanes = require("../lib/lanes");
const tmux = require("../lib/tmux");
const nudge = require("../lib/codex-nudge");

/** Backdate the current stage's enteredAt so it looks `minutes` old. */
function backdateStage(laneId, minutes) {
  const lane = lanes.getLane(laneId);
  const stages = { ...lane.stages };
  stages[lane.stage] = {
    ...stages[lane.stage],
    enteredAt: new Date(Date.now() - minutes * 60_000).toISOString(),
  };
  db.prepare("UPDATE lanes SET stages = ? WHERE id = ?").run(JSON.stringify(stages), laneId);
}

describe("codex-nudge sweep", () => {
  let calls;

  beforeEach(() => {
    calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "display-message") return "codex"; // pane running the codex CLI
      return "";
    });
    nudge.__resetNudgeState();
  });

  afterEach(() => {
    tmux.__reset();
  });

  function makeCodexLane({ cwd, stage = "tests", evidence }) {
    const lane = lanes.createLane({ title: "cx", cwd, tool: "codex" });
    lanes.updateLane(lane.id, { run_id: `agenthub-lane-${lane.id}` });
    lanes.setStage(lane.id, { stage, evidence });
    return lane;
  }

  it("nudges once the lane has held an evidence-less stage past the delay", () => {
    const cwd = os.tmpdir();
    const lane = makeCodexLane({ cwd: `${cwd}/nudge-a` });
    backdateStage(lane.id, 3); // older than the 2 min delay

    assert.equal(nudge.sweepCodexNudges(), 1);
    const sendKeys = calls.filter((a) => a[0] === "send-keys" && a[3] === "-l");
    assert.equal(sendKeys.length, 1);
    assert.match(sendKeys[0][4], /agenthub stage tests --tool codex --evidence/);

    // A second pass for the same still-unevidenced stage must not repeat it.
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never nudges before the delay has elapsed", () => {
    const cwd = os.tmpdir();
    const lane = makeCodexLane({ cwd: `${cwd}/nudge-b` });
    // enteredAt is "now" — setStage just wrote it.
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never nudges a stage the session already backed with evidence", () => {
    const cwd = os.tmpdir();
    const lane = makeCodexLane({ cwd: `${cwd}/nudge-c`, evidence: "12 tests green" });
    backdateStage(lane.id, 10);
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never nudges a lane that has not entered a pipeline node", () => {
    const cwd = os.tmpdir();
    const lane = lanes.createLane({ title: "cx", cwd: `${cwd}/nudge-h`, tool: "codex" });
    lanes.updateLane(lane.id, { run_id: `agenthub-lane-${lane.id}` });
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never nudges a claude lane", () => {
    const cwd = os.tmpdir();
    const lane = lanes.createLane({ title: "cc", cwd: `${cwd}/nudge-d`, tool: "claude" });
    lanes.updateLane(lane.id, { run_id: `agenthub-lane-${lane.id}` });
    lanes.setStage(lane.id, { stage: "tests" });
    backdateStage(lane.id, 3);
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never nudges a lane with no live run", () => {
    const cwd = os.tmpdir();
    const lane = lanes.createLane({ title: "cx", cwd: `${cwd}/nudge-e`, tool: "codex" });
    lanes.setStage(lane.id, { stage: "tests" });
    backdateStage(lane.id, 3);
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("never types into a pane sitting at a bare shell prompt", () => {
    const cwd = os.tmpdir();
    const lane = makeCodexLane({ cwd: `${cwd}/nudge-f` });
    backdateStage(lane.id, 3);
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "display-message") return "bash";
      return "";
    });
    assert.equal(nudge.sweepCodexNudges(), 0);
    lanes.deleteLane(lane.id);
  });

  it("nudges again once the lane moves to another evidence-less stage", () => {
    const cwd = os.tmpdir();
    const lane = makeCodexLane({ cwd: `${cwd}/nudge-g` });
    backdateStage(lane.id, 3);
    assert.equal(nudge.sweepCodexNudges(), 1);

    lanes.setStage(lane.id, { stage: "review" });
    backdateStage(lane.id, 3);
    assert.equal(nudge.sweepCodexNudges(), 1);
    lanes.deleteLane(lane.id);
  });
});