AgentHub/server/lib/dashboard-runs.js

/**
 * @file dashboard-runs.js
 * @description Persistence layer for runs spawned via the dashboard's
 * /api/run endpoint. The in-memory handle map in run-spawner.js reaps
 * handles 5 min after exit, which is fine for live re-attach but loses
 * historical data. This module mirrors every spawn / status transition
 * into a sqlite row so the Run page can show a full history of what
 * the user has spawned and resume any of those sessions.
 *
 * All db operations are wrapped in try/catch so a failure here can never
 * take down a live run — persistence is a side benefit, not a blocker.
 *
 * A run started through a lane also carries that lane's id (`lane_id`), so the
 * Workspace page can list one lane's own run history; runs spawned straight
 * from POST /api/run leave it null.
 *
 * A run's id is its tmux pane name (`agenthub-lane-<id>[-slot]`), which every
 * Start in that pane reuses. So a new run first ARCHIVES the row it replaces
 * under `<id>@<its started_at>` (flagged `abandoned` if it never said it
 * ended) — history is kept, and `getRun(<pane name>)` is always the pane's
 * current run. A row is flagged dead only once its tmux session is gone
 * (`reconcileOrphans(isAlive)`): panes outlive a server restart.
 *
 * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
 */

const { db } = require("../db");

const PROMPT_PREVIEW_LIMIT = 500;

const insertStmt = db.prepare(`
  INSERT OR REPLACE INTO dashboard_runs (
    id, session_id, mode, cwd, model, permission_mode, effort,
    resume_session_id, prompt_preview, status, exit_code, started_at, ended_at,
    lane_id, tool, worktree, router
  ) VALUES (
    @id, @session_id, @mode, @cwd, @model, @permission_mode, @effort,
    @resume_session_id, @prompt_preview, @status, @exit_code, @started_at, @ended_at,
    @lane_id, @tool, @worktree, @router
  )
`);

const updateStmt = db.prepare(`
  UPDATE dashboard_runs
  SET session_id = COALESCE(@session_id, session_id),
      status = COALESCE(@status, status),
      exit_code = COALESCE(@exit_code, exit_code),
      ended_at = COALESCE(@ended_at, ended_at)
  WHERE id = @id
`);

const RUN_COLUMNS = `id, session_id, mode, cwd, model, permission_mode, effort,
         resume_session_id, prompt_preview, status, exit_code,
         started_at, ended_at, lane_id, tool, worktree, router`;

const listStmt = db.prepare(`
  SELECT ${RUN_COLUMNS}
  FROM dashboard_runs
  ORDER BY started_at DESC
  LIMIT @limit
`);

const listByLaneStmt = db.prepare(`
  SELECT ${RUN_COLUMNS}
  FROM dashboard_runs
  WHERE lane_id = @laneId
  ORDER BY started_at DESC
  LIMIT @limit
`);

const getStmt = db.prepare(`
  SELECT ${RUN_COLUMNS}
  FROM dashboard_runs WHERE id = @id
`);

// The row a new run in the same pane replaces, kept under its own id.
const archiveStmt = db.prepare(`
  UPDATE dashboard_runs
  SET id = id || '@' || started_at,
      status = CASE WHEN status IN ('running', 'spawning') THEN 'abandoned' ELSE status END,
      ended_at = COALESCE(ended_at, strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
  WHERE id = ?
`);

/**
 * Insert a new run record at spawn time; the pane's previous run, if any, is
 * archived first rather than overwritten.
 */
function recordRun(handle) {
  try {
    try {
      archiveStmt.run(handle.id);
    } catch (err) {
      // An archive id already taken (an imported bundle) — fall back to the
      // replace below rather than lose the new run.
      console.warn(`[dashboard-runs] could not archive run ${handle?.id}: ${err.message}`);
    }
    const startedAt = new Date(handle.startedAt || Date.now()).toISOString();
    const endedAt = handle.endedAt ? new Date(handle.endedAt).toISOString() : null;
    const prompt = typeof handle.prompt === "string" ? handle.prompt : "";
    insertStmt.run({
      id: handle.id,
      session_id: handle.sessionId || null,
      mode: handle.mode,
      cwd: handle.cwd || "",
      model: handle.model || null,
      permission_mode: handle.permissionMode || null,
      effort: handle.effort || null,
      resume_session_id: handle.resumeSessionId || null,
      prompt_preview: prompt.slice(0, PROMPT_PREVIEW_LIMIT) || null,
      status: handle.status || "spawning",
      exit_code: typeof handle.exitCode === "number" ? handle.exitCode : null,
      started_at: startedAt,
      ended_at: endedAt,
      lane_id: typeof handle.laneId === "number" ? handle.laneId : null,
      tool: typeof handle.tool === "string" && handle.tool ? handle.tool : "claude",
      worktree: handle.worktree ? 1 : 0,
      router: handle.router || null,
    });
  } catch (err) {
    // Best-effort by design (a live run must never fail because sqlite did),
    // but not silent: a swallowed insert leaves the runs modal showing rows with
    // no cwd, model, prompt or start time, which reads as a UI bug rather than a
    // persistence one. Say it once, here, where the cause is known.
    console.warn(`[dashboard-runs] failed to record run ${handle?.id}: ${err.message}`);
  }
}

/**
 * Patch an existing run record. Pass null/undefined for fields you don't
 * want to overwrite — COALESCE in SQL leaves the existing value untouched.
 */
function patchRun({ id, sessionId, status, exitCode, endedAt }) {
  try {
    updateStmt.run({
      id,
      session_id: sessionId ?? null,
      status: status ?? null,
      exit_code: typeof exitCode === "number" ? exitCode : null,
      ended_at: endedAt ? new Date(endedAt).toISOString() : null,
    });
  } catch {
    /* ignore */
  }
}

/** @param {{limit?: number, laneId?: number|null}} [opts] laneId narrows to one lane's runs. */
function listRuns({ limit = 50, laneId = null } = {}) {
  try {
    const safeLimit = Math.max(1, Math.min(500, Math.floor(Number(limit) || 50)));
    if (laneId != null) return listByLaneStmt.all({ limit: safeLimit, laneId });
    return listStmt.all({ limit: safeLimit });
  } catch {
    return [];
  }
}

function getRun(id) {
  try {
    return getStmt.get({ id }) || null;
  } catch {
    return null;
  }
}

const sessionRouterStmt = db.prepare(`
  SELECT router FROM dashboard_runs
  WHERE session_id = @sessionId OR resume_session_id = @sessionId
  ORDER BY started_at DESC LIMIT 1
`);

/**
 * The AI Router the newest run holding `sessionId` started on (null = native,
 * or no run known) — what a resume that names no router goes back to.
 */
function routerForSession(sessionId) {
  try {
    return sessionRouterStmt.get({ sessionId })?.router || null;
  } catch {
    return null;
  }
}

const runningStmt = db.prepare(
  "SELECT id FROM dashboard_runs WHERE status IN ('running', 'spawning')"
);
const abandonStmt = db.prepare(`
  UPDATE dashboard_runs
  SET status = 'abandoned',
      ended_at = COALESCE(ended_at, strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
  WHERE id = ? AND status IN ('running', 'spawning')
`);

/**
 * Flags `abandoned` every row still marked running/spawning whose pane is
 * gone — the pane's process quit (Ctrl+C, `exit`), or the machine rebooted.
 * A pane is a tmux session, which outlives a server restart, so liveness is
 * asked of `isAlive(id)` (tmux), never assumed from the restart. Run at boot
 * and on the server's run-heal beat.
 *
 * Returns the number of rows updated.
 */
function reconcileOrphans(isAlive = () => false) {
  try {
    let changes = 0;
    for (const { id } of runningStmt.all()) {
      if (!isAlive(id)) changes += abandonStmt.run(id).changes;
    }
    return changes;
  } catch {
    return 0;
  }
}

module.exports = { recordRun, patchRun, listRuns, getRun, reconcileOrphans, routerForSession };