AgentHub/server/lib/codex-nudge.js

/**
 * @file Safety-net reminder for codex lanes sitting at a stage nobody has
 * backed with evidence. `codex-ingest.js` auto-advances a codex lane's stage
 * from its rollout journal — that keeps the pipeline map moving, but an
 * inferred stage carries no evidence, so its node renders
 * `passed-no-evidence` (amber) rather than `done`. Only the session's own
 * `agenthub stage <node> --evidence "..."` call can supply that, and a codex
 * session has no hook or wrapper that does it for it.
 *
 * This module never writes `stage`, `stages` or `detected_stage` itself. It
 * only types a plain-text reminder into the lane's own live tmux pane
 * (`tmux.sendText`), the same way a human watching the dashboard would nudge
 * the agent — so the evidence that results is still a REAL declaration the
 * codex session made itself.
 * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
 */

const NUDGE_DELAY_MS = 120_000; // give the session 2 min to declare on its own first

// Per-lane memory of the last stage already nudged for, so the 60s sweep
// doesn't retype the same reminder every pass. Cleared implicitly: once the
// session declares with evidence, or the lane moves to another node, the value
// here no longer matches and a fresh nudge is due.
// ponytail: in-memory, resets on server restart — worst case one duplicate
// nudge after a restart, not worth a DB column for.
const nudgedFor = new Map();

/**
 * One sweep pass: nudge every codex lane whose CURRENT stage has been held for
 * at least NUDGE_DELAY_MS with no evidence recorded, and hasn't already been
 * nudged for that exact stage.
 * @returns {number} How many lanes were nudged.
 */
function sweepCodexNudges() {
  const lanes = require("./lanes");
  const tmux = require("./tmux");
  const { SHELL_COMMANDS, runIdForLane } = require("./pty-run");

  let codexLanes = [];
  try {
    codexLanes = lanes.listLanes().filter((l) => l.tool === "codex" && l.run_id);
  } catch {
    return 0;
  }

  let nudged = 0;
  for (const lane of codexLanes) {
    try {
      // No record under the current stage means the lane never entered a
      // pipeline node (a fresh lane sits at `idle`) — nothing to ask about.
      const record = (lane.stages || {})[lane.stage];
      if (!record || record.evidence) {
        nudgedFor.delete(lane.id);
        continue;
      }
      const enteredAt = Date.parse(record.enteredAt);
      if (!Number.isFinite(enteredAt) || Date.now() - enteredAt < NUDGE_DELAY_MS) continue;
      if (nudgedFor.get(lane.id) === lane.stage) continue;

      const runId = runIdForLane(lane.id);
      if (!tmux.hasSession(runId)) continue;
      // A bare shell prompt has no chat turn to submit into — pressing Enter
      // there would run the reminder text as a shell command instead.
      if (SHELL_COMMANDS.has(tmux.paneCommand(runId) || "")) continue;

      tmux.sendText(
        runId,
        `[agenthub] Stage "${lane.stage}" was inferred and has no evidence — run: agenthub stage ${lane.stage} --tool codex --evidence "..."`
      );
      nudgedFor.set(lane.id, lane.stage);
      nudged += 1;
    } catch {
      /* one lane's failure must not abort the sweep */
    }
  }
  return nudged;
}

/** Unref'd so it never blocks shutdown; disable with DASHBOARD_CODEX_NUDGE_MS=0. */
function startCodexNudge() {
  const POLL_MS = process.env.DASHBOARD_CODEX_NUDGE_MS
    ? Number(process.env.DASHBOARD_CODEX_NUDGE_MS)
    : 60_000;
  if (!Number.isFinite(POLL_MS) || POLL_MS <= 0) return;
  const timer = setInterval(() => {
    try {
      sweepCodexNudges();
    } catch {
      /* a sweep pass never throws into the event loop */
    }
  }, POLL_MS);
  if (timer.unref) timer.unref();
}

function __resetNudgeState() {
  nudgedFor.clear();
}

module.exports = {
  sweepCodexNudges,
  startCodexNudge,
  __resetNudgeState,
};