multi-agent-mux/tests/test_issue24_resume_dialogs.py

"""Issue #24, resume path: start-up dialogs are answered for every agent.

resume_session.sh called handle_startup_dialogs only for claude and passed no
agent, so a resumed agy/grok/codex sat on its directory-trust prompt exactly as
the create path did before this branch. These fix the call contract resume
now shares with create.

What is real: the shipped create/stop/resume scripts run end to end against
the mock herdr in a sandbox. What is not: the mock's pane always shows a
ready banner, so no test here drives a real trust dialog - the create-side
tests (test_issue23_24_startup_path.py, S4-S6) fix which keys each dialog
gets, and R4 shows the same shipped function is now reached from resume.
"""

import json
import os
import subprocess
import time

import pytest

SCRIPTS = ("multi-agent-mux-create/scripts/create_session.sh",
           "multi-agent-mux-stop/scripts/stop_session.sh",
           "multi-agent-mux-resume/scripts/resume_session.sh")


def _script(tmp_path, rel):
    return str(tmp_path / ".agents" / "skills" / rel)


def _create_and_stop(tmp_path, agent, name):
    ws = str(tmp_path / ("ws_" + name))
    os.makedirs(ws, exist_ok=True)
    create, stop, _ = (_script(tmp_path, s) for s in SCRIPTS)
    subprocess.run(["bash", create, "--workspace", ws, "--agent", agent,
                    "--role", "creator", "--session", name, "--no-onboard"],
                   check=True, cwd=str(tmp_path), capture_output=True, text=True)
    subprocess.run(["bash", stop, "--session", name, "--agent", agent],
                   check=True, cwd=str(tmp_path), capture_output=True, text=True)
    return ws


def _resume(tmp_path, agent, name, ws, extra=()):
    _, _, resume = (_script(tmp_path, s) for s in SCRIPTS)
    return subprocess.run(["bash", resume, "--workspace", ws, "--agent", agent,
                           "--session", name, *extra],
                          cwd=str(tmp_path), capture_output=True, text=True)


def _record_dialog_calls(tmp_path):
    """Override handle_startup_dialogs in the SANDBOX copy of lib.sh (never the
    repo's) so the call resume makes - session, timeout, agent, MAM_AUTO_TRUST
    - is written down. Bash keeps the last definition, so appending wins."""
    log = tmp_path / "dialog_calls.log"
    lib = tmp_path / ".agents" / "skills" / "lib.sh"
    with open(lib, "a") as f:
        f.write('\nhandle_startup_dialogs() {\n'
                '  printf \'%%s\\n\' "sess=$1 timeout=${2:-} agent=${3:-<none>} '
                'auto_trust=${MAM_AUTO_TRUST:-<unset>}" >> "%s"\n'
                '}\n' % log)
    return log


def _calls(log):
    return log.read_text().splitlines() if log.exists() else []


@pytest.mark.parametrize("agent", ["agy", "codex"])
def test_r1_resume_answers_dialogs_for_a_non_claude_agent_and_names_it(
        mam_sandbox, mock_herdr, mock_agents, agent):
    """R1: the gate is gone and the agent is passed - the two halves of the
    create contract resume was missing."""
    tmp_path = mam_sandbox
    name = "test-r1-" + agent
    ws = _create_and_stop(tmp_path, agent, name)
    log = _record_dialog_calls(tmp_path)   # armed after create, so only resume is recorded
    res = _resume(tmp_path, agent, name, ws)
    assert res.returncode == 0, res.stdout + res.stderr
    assert _calls(log) == ["sess=%s timeout=20 agent=%s auto_trust=1" % (name, agent)]


def test_r2_claude_keeps_its_dialog_handling(mam_sandbox, mock_herdr, mock_agents):
    """R2: claude is still handled, now by the same call as everyone else."""
    tmp_path = mam_sandbox
    ws = _create_and_stop(tmp_path, "claude", "test-r2-claude")
    log = _record_dialog_calls(tmp_path)
    res = _resume(tmp_path, "claude", "test-r2-claude", ws)
    assert res.returncode == 0, res.stdout + res.stderr
    assert _calls(log) == ["sess=test-r2-claude timeout=20 agent=claude auto_trust=1"]


def test_r3_no_auto_trust_reaches_the_dialog_handler(mam_sandbox, mock_herdr, mock_agents):
    """R3: --no-auto-trust on resume sets MAM_AUTO_TRUST=0 for the handler,
    the same switch with the same meaning as create's."""
    tmp_path = mam_sandbox
    ws = _create_and_stop(tmp_path, "codex", "test-r3-codex")
    log = _record_dialog_calls(tmp_path)
    res = _resume(tmp_path, "codex", "test-r3-codex", ws, extra=("--no-auto-trust",))
    assert res.returncode == 0, res.stdout + res.stderr
    assert _calls(log) == ["sess=test-r3-codex timeout=20 agent=codex auto_trust=0"]


@pytest.mark.parametrize("env_value,flag,expected", [
    ("0", (), "0"),               # the documented environment form alone
    ("0", ("--auto-trust",), "1"),  # an explicit flag wins over the environment
    ("1", ("--no-auto-trust",), "0"),
])
def test_r3b_the_environment_form_of_the_switch_reaches_the_handler_on_resume(
        mam_sandbox, mock_herdr, mock_agents, monkeypatch, env_value, flag, expected):
    """R3b (merge review, codex probe): MAM_AUTO_TRUST=0 without a flag used to
    be overwritten by the script's own export of its default."""
    tmp_path = mam_sandbox
    ws = _create_and_stop(tmp_path, "codex", "test-r3b-codex")
    log = _record_dialog_calls(tmp_path)
    monkeypatch.setenv("MAM_AUTO_TRUST", env_value)
    res = _resume(tmp_path, "codex", "test-r3b-codex", ws, extra=flag)
    assert res.returncode == 0, res.stdout + res.stderr
    assert _calls(log) == ["sess=test-r3b-codex timeout=20 agent=codex auto_trust=%s" % expected]


@pytest.mark.parametrize("env_value,flag,expected", [
    ("0", (), "0"),
    ("0", ("--auto-trust",), "1"),
    ("1", ("--no-auto-trust",), "0"),
])
def test_c3_the_environment_form_of_the_switch_reaches_the_handler_on_create(
        mam_sandbox, mock_herdr, mock_agents, monkeypatch, env_value, flag, expected):
    """C3 (merge review, codex probe): the same contract on create_session."""
    tmp_path = mam_sandbox
    log = _record_dialog_calls(tmp_path)
    ws = str(tmp_path / "ws_c3")
    os.makedirs(ws, exist_ok=True)
    create = _script(tmp_path, SCRIPTS[0])
    monkeypatch.setenv("MAM_AUTO_TRUST", env_value)
    res = subprocess.run(["bash", create, "--workspace", ws, "--agent", "codex",
                          "--role", "creator", "--session", "test-c3-codex", "--no-onboard", *flag],
                         cwd=str(tmp_path), capture_output=True, text=True)
    assert res.returncode == 0, res.stdout + res.stderr
    assert _calls(log) == ["sess=test-c3-codex timeout=15 agent=codex auto_trust=%s" % expected]


def test_r4_the_shipped_handler_really_runs_for_a_non_claude_resume(
        mam_sandbox, mock_herdr, mock_agents):
    """R4 (no override): with the real handle_startup_dialogs, a codex resume
    completes and the pane is read after the spawn - the handler was reached
    and returned on the ready banner. Before this change no pane read happened
    between new-session and the YAML update for a non-claude agent."""
    tmp_path = mam_sandbox
    ws = _create_and_stop(tmp_path, "codex", "test-r4-codex")
    before = len(json.load(open(mock_herdr)).get("calls", []))
    t0 = time.monotonic()
    res = _resume(tmp_path, "codex", "test-r4-codex", ws)
    elapsed = time.monotonic() - t0
    assert res.returncode == 0, res.stdout + res.stderr
    # Review B-1: the handler used to idle its whole 20 s timeout here because
    # it had no ready tokens on the resume path. rc 0 alone cannot tell early
    # return from timeout; the clock can.
    assert elapsed < 12, "resume took %.1fs: the dialog handler idled to its timeout" % elapsed
    calls = json.load(open(mock_herdr)).get("calls", [])[before:]

    def _has(c, *verbs):   # the mock records argv with a leading `--session <name>`
        return any(tuple(c[i:i + len(verbs)]) == verbs for i in range(len(c)))

    spawn = next(i for i, c in enumerate(calls) if _has(c, "agent", "start"))
    reads = [c for c in calls[spawn + 1:] if _has(c, "agent", "read") or _has(c, "pane", "read")]
    assert reads, "no pane read after the spawn: handle_startup_dialogs never ran\n%s" % calls