AgentHub/server/__tests__/pty-run.test.js

/**
 * @file pty-run.test.js
 * @description Unit tests for the tmux-backed run lifecycle. Injects a fake
 * tmux exec implementation (via tmux.js's test seam) so no real tmux binary
 * is invoked.
 * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
 */
const { describe, it, beforeEach, before, after } = require("node:test");
const assert = require("node:assert/strict");
const path = require("node:path");
const fs = require("node:fs");
const os = require("node:os");

const TMP = fs.mkdtempSync(path.join(os.tmpdir(), "pty-run-test-"));
process.env.DASHBOARD_DB_PATH = path.join(TMP, "dashboard.db");

const tmux = require("../lib/tmux");
const pty = require("../lib/pty-run");

describe("pty-run", () => {
  after(() => {
    try {
      fs.rmSync(TMP, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
    } catch {
      /* best-effort */
    }
  });

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

  it("spawnRun creates a new tmux session named agenthub-lane-<id> when none exists", () => {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "has-session") {
        const e = new Error("no such session");
        e.status = 1;
        throw e;
      }
      return "";
    });
    const handle = pty.spawnRun({ laneId: 42, cwd: "/tmp/repo", model: "opus" });
    assert.equal(handle.id, "agenthub-lane-42");
    const newSessionCall = calls.find((c) => c[0] === "new-session");
    assert.ok(newSessionCall, "expected a new-session call");
    assert.deepEqual(newSessionCall.slice(0, 6), [
      "new-session",
      "-d",
      "-s",
      "agenthub-lane-42",
      "-c",
      "/tmp/repo",
    ]);
    assert.ok(newSessionCall.includes("claude"));
    assert.ok(newSessionCall.includes("--model"));
    assert.ok(newSessionCall.includes("opus"));
  });

  it("spawnRun refuses with ETMUXMISSING, naming the fix, when tmux is not installed", () => {
    // Before this guard the ENOENT escaped from three calls down as
    // `spawnSync tmux ENOENT` and the route answered 400 — blaming the request
    // for a missing host package, with no hint of what to install.
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      const e = new Error("spawnSync tmux ENOENT");
      e.code = "ENOENT";
      throw e;
    });

    assert.throws(
      () => pty.spawnRun({ laneId: 42, cwd: "/tmp/repo" }),
      (err) => err.code === "ETMUXMISSING" && /install/i.test(err.message),
      "a missing tmux must be reported as such, with the install command"
    );
    assert.ok(
      !calls.some((c) => c[0] === "new-session"),
      "must not attempt a session it already knows cannot be created"
    );
  });

  it("spawnRun is a no-op (adopts) when the existing session's pane runs claude", () => {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "display-message") return "claude\n";
      return ""; // has-session succeeds → already running
    });
    const handle = pty.spawnRun({ laneId: 7, cwd: "/tmp/repo" });
    assert.equal(handle.id, "agenthub-lane-7");
    assert.ok(!calls.some((c) => c[0] === "new-session"), "must not create a duplicate session");
    assert.ok(!calls.some((c) => c[0] === "send-keys"), "must not type over a live agent");
  });

  it("spawnRun runs the argv in an existing session idling at a shell prompt", () => {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "display-message") return "bash\n";
      return ""; // has-session succeeds → session exists, pane is a shell
    });
    pty.spawnRun({ laneId: 8, cwd: "/tmp/repo", resumeSessionId: "abc12345" });
    assert.ok(!calls.some((c) => c[0] === "new-session"), "must not create a duplicate session");
    const respawn = calls.find((c) => c[0] === "respawn-pane");
    assert.ok(respawn, "expected the idle shell to be replaced by the argv");
    const argv = respawn.slice(respawn.indexOf("--") + 1);
    assert.equal(argv[0], "claude");
    assert.deepEqual(argv.slice(-2), ["--resume", "abc12345"]);
  });

  it("spawnRun passes an initial prompt as one argv element, never a shell line", () => {
    // No shell is involved any more, so a prompt full of shell metacharacters
    // is just a string — but it must still arrive whole and unmangled.
    let respawn = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "display-message") return "zsh\n";
      if (args[0] === "respawn-pane") respawn = args;
      return "";
    });
    pty.spawnRun({ laneId: 9, cwd: "/tmp/repo", initialPrompt: "don't; rm -rf /" });
    assert.equal(respawn.at(-1), "don't; rm -rf /");
  });

  it("spawnRun puts AGENTHUB_LANE_ID in the new session's environment", () => {
    let newSessionArgv = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "has-session") {
        const e = new Error("gone");
        e.status = 1;
        throw e;
      }
      if (args[0] === "new-session") newSessionArgv = args;
      return "";
    });
    pty.spawnRun({ laneId: 33, cwd: "/tmp/repo", tool: "codex" });
    const at = newSessionArgv.indexOf("-e");
    assert.ok(at > -1, "expected a tmux -e environment flag");
    assert.equal(newSessionArgv[at + 1], "AGENTHUB_LANE_ID=33");
    // Must stay ahead of the `--` that starts the pane's own argv.
    assert.ok(at < newSessionArgv.indexOf("--"));
  });

  it("spawnRun passes AGENTHUB_LANE_ID through tmux -e when reusing a shell pane", () => {
    let respawn = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "display-message") return "bash\n";
      if (args[0] === "respawn-pane") respawn = args;
      return "";
    });
    pty.spawnRun({ laneId: 12, cwd: "/tmp/repo", tool: "codex" });
    // Through argv, never as a shell assignment typed into the pane: this is
    // also the path an AI Router's API key takes, and a typed line would be
    // rendered to every attached browser and land in the shell history.
    const at = respawn.indexOf("-e");
    assert.ok(at > -1, "expected a tmux -e environment flag");
    assert.equal(respawn[at + 1], "AGENTHUB_LANE_ID=12");
    assert.ok(at < respawn.indexOf("--"));
    assert.equal(respawn.at(-1), "codex");
  });

  it("spawnRun with resumeSessionId passes --resume in argv", () => {
    let newSessionArgv = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "has-session") {
        const e = new Error("gone");
        e.status = 1;
        throw e;
      }
      if (args[0] === "new-session") newSessionArgv = args;
      return "";
    });
    pty.spawnRun({ laneId: 1, cwd: "/tmp/repo", resumeSessionId: "abc12345" });
    assert.ok(newSessionArgv.includes("--resume"));
    assert.ok(newSessionArgv.includes("abc12345"));
  });

  it("spawnRun offers bypass in the pane's shift+tab cycle without starting in it", () => {
    let newSessionArgv = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "has-session") {
        const e = new Error("gone");
        e.status = 1;
        throw e;
      }
      if (args[0] === "new-session") newSessionArgv = args;
      return "";
    });
    pty.spawnRun({ laneId: 4, cwd: "/tmp/repo" });
    assert.ok(newSessionArgv.includes("--allow-dangerously-skip-permissions"));
    // ...as an OPTION only: the starting mode stays the requested one, and
    // `--dangerously-skip-permissions` (which would enable it) is never passed.
    assert.ok(!newSessionArgv.includes("--dangerously-skip-permissions"));
    const modeAt = newSessionArgv.indexOf("--permission-mode");
    // `auto` is the default when the caller named no mode: the CLI's own
    // classifier asks for what it reads as risky and stays out of the way
    // otherwise.
    assert.equal(newSessionArgv[modeAt + 1], "auto");
  });

  it("spawnRun appends a positional initial prompt after argv flags", () => {
    let newSessionArgv = null;
    tmux.__setExecImpl((args) => {
      if (args[0] === "has-session") {
        const e = new Error("gone");
        e.status = 1;
        throw e;
      }
      if (args[0] === "new-session") newSessionArgv = args;
      return "";
    });
    pty.spawnRun({ laneId: 3, cwd: "/tmp/repo", initialPrompt: "fix the bug" });
    assert.equal(newSessionArgv[newSessionArgv.length - 1], "fix the bug");
  });

  it("killRun calls tmux kill-session with the run id", () => {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      return "";
    });
    assert.equal(pty.killRun("agenthub-lane-5"), true);
    assert.ok(calls.some((c) => c[0] === "kill-session" && c[2] === "agenthub-lane-5"));
  });

  it("listRuns reflects live tmux-session state, not cached memory", () => {
    tmux.__setExecImpl((args) => {
      if (args[0] === "list-sessions") return "agenthub-lane-1\nagenthub-lane-2\n";
      return "";
    });
    const first = pty.listRuns();
    assert.deepEqual(first.map((r) => r.id).sort(), ["agenthub-lane-1", "agenthub-lane-2"]);

    // Session killed out-of-band (not through killRun) — next list() call
    // must self-correct, proving state is computed, not stored.
    tmux.__setExecImpl((args) => {
      if (args[0] === "list-sessions") return "agenthub-lane-1\n";
      return "";
    });
    const second = pty.listRuns();
    assert.deepEqual(
      second.map((r) => r.id),
      ["agenthub-lane-1"]
    );
  });

  it("laneIdFromRunId parses the numeric lane id back out", () => {
    assert.equal(pty.laneIdFromRunId("agenthub-lane-42"), 42);
    assert.equal(pty.laneIdFromRunId("not-a-run-id"), null);
  });

  it("getRun returns the recorded prompt for a live run", () => {
    let sessionExists = false;
    tmux.__setExecImpl((args) => {
      if (args[0] === "has-session") {
        if (sessionExists) {
          return ""; // session exists
        }
        // Session doesn't exist yet
        const e = new Error("no such session");
        e.status = 1;
        throw e;
      }
      if (args[0] === "new-session") {
        sessionExists = true; // Mark session as created
      }
      return "";
    });
    const handle = pty.spawnRun({
      laneId: 99,
      cwd: "/tmp/test",
      initialPrompt: "the live prompt",
    });
    const retrieved = pty.getRun(handle.id);
    assert.equal(retrieved.id, "agenthub-lane-99");
    assert.equal(retrieved.promptPreview, "the live prompt");
    assert.equal(retrieved.status, "running");
  });

  function captureNewSession(fn) {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "has-session") {
        const e = new Error("no such session");
        e.status = 1;
        throw e;
      }
      return "";
    });
    fn();
    return calls.find((c) => c[0] === "new-session");
  }

  /** The pane's own command line — everything tmux passes after the `--`. */
  function paneArgv(newSessionCall) {
    return newSessionCall.slice(newSessionCall.indexOf("--") + 1);
  }

  it("spawnRun builds a codex argv for a codex lane", () => {
    const call = captureNewSession(() =>
      pty.spawnRun({
        laneId: 7,
        cwd: "/tmp/repo",
        tool: "codex",
        model: "gpt-5.1-codex",
        sandbox: "workspace-write",
        approval: "on-request",
        effort: "high",
        initialPrompt: "hello",
      })
    );
    const argv = paneArgv(call);
    assert.deepEqual(argv, [
      "codex",
      "-m",
      "gpt-5.1-codex",
      "-s",
      "workspace-write",
      "-a",
      "on-request",
      "-c",
      "model_reasoning_effort=high",
      "hello",
    ]);
  });

  it("spawnRun puts codex resume first, as a subcommand", () => {
    const withId = captureNewSession(() =>
      pty.spawnRun({
        laneId: 8,
        cwd: "/tmp/repo",
        tool: "codex",
        resumeSessionId: "0199aaaa-bbbb-cccc-dddd-eeeeffff0000",
      })
    );
    assert.deepEqual(paneArgv(withId).slice(0, 3), [
      "codex",
      "resume",
      "0199aaaa-bbbb-cccc-dddd-eeeeffff0000",
    ]);

    tmux.__reset();
    const last = captureNewSession(() =>
      pty.spawnRun({ laneId: 9, cwd: "/tmp/repo", tool: "codex", resumeLast: true })
    );
    assert.deepEqual(paneArgv(last).slice(0, 3), ["codex", "resume", "--last"]);
  });

  it("spawnRun rejects a codex sandbox/approval outside the allowlist", () => {
    tmux.__setExecImpl(() => "");
    assert.throws(
      () => pty.spawnRun({ laneId: 10, cwd: "/tmp/repo", tool: "codex", sandbox: "rm -rf" }),
      (err) => err.code === "EBADSANDBOX"
    );
    assert.throws(
      () => pty.spawnRun({ laneId: 10, cwd: "/tmp/repo", tool: "codex", approval: "always" }),
      (err) => err.code === "EBADAPPROVAL"
    );
  });

  it("spawnRun never emits codex bypass flags", () => {
    const call = captureNewSession(() =>
      pty.spawnRun({ laneId: 11, cwd: "/tmp/repo", tool: "codex", sandbox: "danger-full-access" })
    );
    assert.ok(!call.some((a) => String(a).startsWith("--dangerously-bypass")));
  });

  // `dashboard_runs.mode` is NOT NULL and recordRun swallows insert errors, so a
  // null there persisted nothing at all while every call still looked fine: the
  // runs modal rendered a row with no cwd, model, prompt or start time, and a
  // resumed session kept its separate `external` row because no run row ever
  // carried its session id. These assert the row actually lands.
  it("refuses to swallow a resume or a prompt when the pane already runs an agent", () => {
    // Adopting silently here answered 200 while spawning no `--resume` at all:
    // the dashboard reported a resumed session that never happened.
    tmux.__setExecImpl((args) => {
      if (args[0] === "display-message") return "claude\n";
      return ""; // has-session succeeds → pane is busy with a live agent
    });
    assert.throws(
      () => pty.spawnRun({ laneId: 51, cwd: "/tmp/repo", resumeSessionId: "abc12345" }),
      (err) => err.code === "ERUNLIVE"
    );
    assert.throws(
      () => pty.spawnRun({ laneId: 51, cwd: "/tmp/repo", initialPrompt: "do the thing" }),
      (err) => err.code === "ERUNLIVE"
    );
  });

  it("still adopts a busy pane when the request asked for nothing but a pane", () => {
    const calls = [];
    tmux.__setExecImpl((args) => {
      calls.push(args);
      if (args[0] === "display-message") return "claude\n";
      return "";
    });
    const handle = pty.spawnRun({ laneId: 52, cwd: "/tmp/repo" });
    assert.equal(handle.id, "agenthub-lane-52");
    assert.ok(!calls.some((c) => c[0] === "new-session"));
    assert.ok(!calls.some((c) => c[0] === "send-keys"));
  });

  describe("run persistence", () => {
    const dashboardRuns = require("../lib/dashboard-runs");

    it("spawnRun persists the run so the runs list has cwd, model and prompt", () => {
      tmux.__setExecImpl((args) => {
        if (args[0] === "has-session") {
          const e = new Error("gone");
          e.status = 1;
          throw e;
        }
        return "";
      });
      pty.spawnRun({
        laneId: 71,
        cwd: "/tmp/persisted",
        model: "claude-opus-5",
        initialPrompt: "ship it",
      });

      const row = dashboardRuns.getRun("agenthub-lane-71");
      assert.ok(row, "expected a dashboard_runs row for the spawned run");
      assert.equal(row.cwd, "/tmp/persisted");
      assert.equal(row.model, "claude-opus-5");
      assert.equal(row.prompt_preview, "ship it");
      assert.equal(row.lane_id, 71);
      assert.ok(row.started_at, "started_at must be set, or the UI dates the row to the epoch");
      assert.ok(row.mode, "mode is NOT NULL — a null here silently drops the whole insert");
    });

    it("a resumed run carries the session id, which is what dedupes the external row", () => {
      tmux.__setExecImpl((args) => {
        if (args[0] === "has-session") {
          const e = new Error("gone");
          e.status = 1;
          throw e;
        }
        return "";
      });
      const sessionId = "c2055094-09cf-4735-9712-09e5cdf7023f";
      const handle = pty.spawnRun({
        laneId: 72,
        cwd: "/tmp/resumed",
        resumeSessionId: sessionId,
      });

      // The UI reads sessionId off the run list; an external session whose id is
      // already on a run row is not repeated as its own `external` row.
      assert.equal(handle.sessionId, sessionId);
      assert.equal(dashboardRuns.getRun("agenthub-lane-72").resume_session_id, sessionId);
    });
  });
});