multi-agent-mux/tests/test_issue50_pane_lock.py

"""Issue #50 follow-up: the herdr shim claims one pane at a time per server.

- P: lib_py.pane_lock - the lock file per server, the acquire decision and its
  bound, a lock that ends with its holder's process (no stale lock after
  kill -9), the wait knob.
- H: the race itself, on a real herdr server: test_issue50_dispatch_herdr.py
  (test_s_three_concurrent_new_sessions_in_one_folder_take_distinct_panes,
  test_a3_three_concurrent_creates_in_one_folder_take_distinct_panes).
- the shim's use of the lock against the mock herdr: test_herdr_shim_contract.py h26.
"""
from __future__ import annotations

import json
import os
import signal
import subprocess
import sys
import time
from pathlib import Path

import pytest

REPO_ROOT = Path(__file__).resolve().parent.parent
SKILLS = REPO_ROOT / ".agents" / "skills"
if str(SKILLS) not in sys.path:
    sys.path.insert(0, str(SKILLS))

from lib_py import pane_lock  # noqa: E402

# a bash holder, as the shim is: fd 9 on the file, the lock taken by the helper, then it sleeps
HOLDER = 'exec 9>>"$1"; python3 -m lib_py.pane_lock acquire --fd 9; echo held; exec sleep "${2:-600}"'


def _holder(path: Path, seconds: str = "600", **env) -> subprocess.Popen:
    p = subprocess.Popen(["bash", "-c", HOLDER, "holder", str(path), seconds], stdout=subprocess.PIPE, text=True,
                         env=dict(os.environ, PYTHONPATH=str(SKILLS), **env))
    assert p.stdout.readline().strip() == "locked"
    assert p.stdout.readline().strip() == "held"
    return p


def _acquire(path: Path, **env) -> subprocess.CompletedProcess:
    return subprocess.run(["bash", "-c", 'exec 9>>"$1"; python3 -m lib_py.pane_lock acquire --fd 9', "x", str(path)],
                          capture_output=True, text=True, env=dict(os.environ, PYTHONPATH=str(SKILLS), **env), timeout=60)


def test_p1_the_lock_file_is_per_server_under_the_sessions_home(tmp_path):
    env = {"HOME": str(tmp_path)}
    assert pane_lock.lock_path("t50-x", env) == str(tmp_path / ".local/state/mam/pane-lock/t50-x.lock")
    assert pane_lock.lock_path("", env) == str(tmp_path / ".local/state/mam/pane-lock/default.lock")
    assert pane_lock.lock_path("t50-x", {"HOME_DIR": str(tmp_path / "h")}).startswith(str(tmp_path / "h"))
    assert pane_lock.lock_path("t50-x", env) != pane_lock.lock_path("t50-y", env)
    res = subprocess.run([sys.executable, "-m", "lib_py.pane_lock", "path", "--session", "t50-x"], capture_output=True,
                         text=True, env=dict(os.environ, PYTHONPATH=str(SKILLS), HOME=str(tmp_path)), timeout=60)
    assert res.stdout.strip() == pane_lock.lock_path("t50-x", env), res.stderr


# review e8e471ff R1: the ambient target (no -L, HERDR_SESSION_NAME empty or
# `default`) is answered by the server of the pane the caller runs in - the
# pane's HERDR_SESSION / HERDR_SOCKET_PATH say which - so that is the lock;
# only outside a pane is it the default server's

def test_p1b_the_ambient_target_locks_the_callers_server(tmp_path):
    home = {"HOME": str(tmp_path)}
    sock = {"HERDR_SOCKET_PATH": str(tmp_path / ".config/herdr/sessions/t50-x/herdr.sock")}
    named = pane_lock.lock_path("t50-x", home)
    for ambient in ("", "default", None):
        assert pane_lock.lock_path(ambient, {**home, **sock}) == named, ambient
        assert pane_lock.lock_path(ambient, {**home, "HERDR_SESSION": "t50-x"}) == named, ambient
        assert pane_lock.lock_path(ambient, {**home, "HERDR_SESSION": "t50-x",          # HERDR_SESSION first
                                             "HERDR_SOCKET_PATH": str(tmp_path / ".config/herdr/sessions/t50-y/herdr.sock")}) == named
        assert pane_lock.lock_path(ambient, {**home, "HERDR_SOCKET_PATH": str(tmp_path / ".config/herdr/herdr.sock")}) \
            == pane_lock.lock_path("default", home) == str(tmp_path / ".local/state/mam/pane-lock/default.lock")
        assert pane_lock.lock_path(ambient, {**home, "HERDR_SOCKET_PATH": "/elsewhere/herdr.sock"}).endswith("/default.lock")
        assert pane_lock.lock_path(ambient, home).endswith("/default.lock")
    assert pane_lock.lock_path("t50-y", {**home, **sock}) != named, "a named target is that server's, wherever it is called from"
    outside = {k: v for k, v in os.environ.items() if not k.startswith("HERDR_")}   # this test may run in a pane
    res = subprocess.run([sys.executable, "-m", "lib_py.pane_lock", "path", "--session", ""], capture_output=True, text=True,
                         env=dict(outside, PYTHONPATH=str(SKILLS), HOME=str(tmp_path), **sock), timeout=60)
    assert res.stdout.strip() == named, res.stderr


def test_p2_a_free_lock_is_taken_at_once_and_a_held_one_times_out(tmp_path):
    lock = tmp_path / "s.lock"
    t0 = time.time()
    assert _acquire(lock).stdout.strip() == "locked" and time.time() - t0 < 5
    holder = _holder(lock)
    try:
        t0 = time.time()
        res = _acquire(lock, MAM_PANE_CLAIM_WAIT_S="2")
        assert res.stdout.strip() == "timeout", res.stderr
        assert 1.5 <= time.time() - t0 < 10
        assert _acquire(tmp_path / "other-server.lock", MAM_PANE_CLAIM_WAIT_S="2").stdout.strip() == "locked"
    finally:
        holder.kill()
        holder.wait()


def test_p3_the_lock_ends_with_its_holders_process(tmp_path):
    lock = tmp_path / "s.lock"
    holder = _holder(lock)
    os.kill(holder.pid, signal.SIGKILL)
    holder.wait()
    t0 = time.time()
    assert _acquire(lock, MAM_PANE_CLAIM_WAIT_S="30").stdout.strip() == "locked"
    assert time.time() - t0 < 5, "nothing stale to wait out"


def test_p4_a_waiter_gets_the_lock_when_the_holder_ends(tmp_path):
    lock = tmp_path / "s.lock"
    holder = _holder(lock, "2")
    t0 = time.time()
    res = _acquire(lock, MAM_PANE_CLAIM_WAIT_S="30")
    assert res.stdout.strip() == "locked"
    assert 1 <= time.time() - t0 < 10
    holder.wait()


def test_p5_the_wait_knob_is_a_decimal_with_a_floor_of_one(monkeypatch):
    assert pane_lock.wait_s({}) == 120
    assert pane_lock.wait_s({"MAM_PANE_CLAIM_WAIT_S": "7"}) == 7
    assert pane_lock.wait_s({"MAM_PANE_CLAIM_WAIT_S": "0700"}) == 700
    for bad in ("0", "abc", "", "-1", " "):
        assert pane_lock.wait_s({"MAM_PANE_CLAIM_WAIT_S": bad}) == 120, bad


# ---------------------------------------------------------------------------
# A - create keeps its own pane when the monitor registered it first. With
# pane claims serialised, one create can reach its end-of-run reconcile while
# another is between `agent start` and its row write; the adopted row is that
# create's own pane, not a second live session of its name.
# ---------------------------------------------------------------------------



SERVER = "t50-srv"   # the server _create names; a monitor row carries the server it found the pane on


def _seed_row(tmp_path, name, epoch, note="auto-registered by monitor", job=None, server=SERVER):
    row = {"name": name, "status": "running", "role": "creator", "herdr_session_created_at": "2026-10-11T00:00:00Z",
           "herdr_session_epoch": epoch, "herdr_session": server, "herdr_server": server,
           "pane": {"index": 0, "pid": 9999, "cmd": "claude", "cmd_full": "claude", "cwd": str(tmp_path)},
           "last_visible_status": "running"}
    if note:
        row["last_visible_note"] = note
    if job:
        row["delegate_job_id"] = job
    yaml_path = tmp_path / ".mam" / "agent-sessions.yaml"
    yaml_path.parent.mkdir(parents=True, exist_ok=True)
    yaml_path.write_text("herdr_sessions:\n- " + json.dumps(row) + "\n")
    return yaml_path


def _create(tmp_path, name, role="creator"):
    return subprocess.run(["bash", str(tmp_path / "skills" / "multi-agent-mux-create" / "scripts" / "create_session.sh"),
                           "--workspace", str(tmp_path), "--agent", "claude", "--role", role, "--session", name,
                           "--herdr-session", SERVER, "--no-onboard"], capture_output=True, text=True, cwd=str(tmp_path), timeout=300)


def _rows(yaml_path):
    import yaml
    return yaml.safe_load(yaml_path.read_text())["herdr_sessions"]


def test_a1_create_replaces_the_monitors_registration_of_its_own_pane(mam_sandbox, mock_herdr, mock_agents):
    name = "t50-adopted-creator-claude"
    yaml_path = _seed_row(mam_sandbox, name, int(time.time()) + 60)  # registered after this create began
    res = _create(mam_sandbox, name, role="Creator")               # the monitor guessed "creator" off the name
    assert res.returncode == 0, res.stdout + res.stderr
    assert f"NOTE: the monitor registered {name} while it was being created" in res.stdout
    rows = [r for r in _rows(yaml_path) if r["name"] == name]
    assert len(rows) == 1 and rows[0]["status"] == "running" and rows[0]["role"] == "Creator"
    assert rows[0].get("last_visible_note") != "auto-registered by monitor" and rows[0].get("start_command")


@pytest.mark.parametrize("kind", ["real", "old-adoption", "adoption-with-job", "other-server"])
def test_a2_another_live_session_of_that_name_is_still_refused(mam_sandbox, mock_herdr, mock_agents, kind):
    name = "t50-taken-creator-claude"
    now = int(time.time())
    if kind == "real":
        yaml_path = _seed_row(mam_sandbox, name, now, note=None)
    elif kind == "old-adoption":
        yaml_path = _seed_row(mam_sandbox, name, now - 3600)        # a pane from before this create
    elif kind == "other-server":                                    # review 1e25cf2f F2: names are unique per server
        yaml_path = _seed_row(mam_sandbox, name, now + 60, server="different-server")
    else:
        yaml_path = _seed_row(mam_sandbox, name, now, job="deadbeef")
    res = _create(mam_sandbox, name)
    assert res.returncode == 4, res.stdout + res.stderr
    assert f"ERROR: {name} already running in agent-sessions.yaml" in res.stdout
    rows = [r for r in _rows(yaml_path) if r["name"] == name]
    assert len(rows) == 1 and rows[0]["status"] == "running"