LLeMbas/tests/test_agent_jobs.py

"""Background jobs, exercised against a real local shell.

The sshd fixture elsewhere is a *fake* shell (it echoes the command), which
cannot run `setsid`, `base64`, a wait loop, or an exit-file. So these run the
wrappers through the machine's own `/bin/sh` with the same contract
`SshExecutor.run` has — cd-prefix, interleaved output, a timeout that leaves the
detached child alive — because the shell logic is the whole of the risk here.
"""

from __future__ import annotations

import asyncio
import shutil
import time

import pytest

from lembas.services import tools as tools_service
from lembas.services.agent import jobs, policy
from lembas.services.agent import ssh as ssh_service
from lembas.services.agent.base import ExecRequest, ExecResult, clean_output
from lembas.services.agent.session import AgentContext
from lembas.services.agent.tools import _run_shell

pytestmark = pytest.mark.skipif(
    shutil.which("setsid") is None or shutil.which("base64") is None,
    reason="needs setsid and base64 (Linux)",
)


class LocalExecutor:
    """`SshExecutor.run`'s contract, run against the local shell.

    On timeout it kills only the outer shell -- exactly what an SSH channel
    teardown does -- so a `setsid`-detached child survives, which is the whole
    behaviour a background job depends on.
    """

    def __init__(self, project_dir: str) -> None:
        self.project_dir = project_dir

    async def run(self, request: ExecRequest) -> ExecResult:
        directory = request.cwd or self.project_dir
        command = request.command
        if directory:
            command = f"cd {ssh_service._quote(directory)} && {command}"
        started = time.monotonic()
        proc = await asyncio.create_subprocess_shell(
            command,
            stdout=asyncio.subprocess.PIPE,
            stderr=asyncio.subprocess.STDOUT,
            stdin=asyncio.subprocess.DEVNULL,
        )
        try:
            out, _ = await asyncio.wait_for(proc.communicate(), timeout=request.timeout)
        except TimeoutError:
            proc.kill()
            await proc.wait()
            return ExecResult(
                exit_status=-1,
                output=f"The command was still running after {request.timeout:g}s.",
                timed_out=True,
                duration_ms=int((time.monotonic() - started) * 1000),
            )
        output, truncated = clean_output(out.decode("utf-8", "replace"), limit=request.max_bytes)
        return ExecResult(
            exit_status=proc.returncode if proc.returncode is not None else -1,
            output=output,
            truncated=truncated,
            duration_ms=int((time.monotonic() - started) * 1000),
        )


@pytest.fixture(autouse=True)
def _clear_jobs():
    jobs.clear()
    yield
    jobs.clear()


def _agent(tmp_path, **over) -> AgentContext:
    fields = {
        "chat_id": "chat0001",
        "label": "Box",
        "project_dir": str(tmp_path),
        "mode": policy.MODE_AUTO,
        "max_output": 65536,
        "timeout": 60.0,
        "max_timeout": 600.0,
        "background": True,
        "background_on_timeout": True,
        "background_notify": True,
    }
    fields.update(over)
    ctx = AgentContext(**fields)
    ctx.executor = lambda: LocalExecutor(fields["project_dir"])  # type: ignore[method-assign]
    return ctx


def _context(agent):
    return tools_service.ToolContext(owner_id="u", agent=agent)


# --- The wrappers, as strings --------------------------------------------------
def test_the_command_is_never_in_a_quoted_context():
    """git commit -m 'fix' would shatter sh -c '<cmd>'. It is base64'd instead."""
    import base64

    cmd = "git commit -m 'fix: it'"
    wrapper = jobs.launch_and_wait_command("chatx", "abc123abc123", cmd, 4096)
    assert cmd not in wrapper, "the command leaked into the wrapper as shell text"
    blob = wrapper.split("printf %s '", 1)[1].split("'", 1)[0]
    inner = base64.b64decode(blob).decode()
    assert cmd in inner, "the command was lost in the base64 round-trip"


def test_every_wrapper_is_valid_shell():
    """`sh -n` parses without executing.

    The one that would have caught it: `{log}` for `{logf}` formatted the module
    logger into the launch-and-wait wrapper, and `<Logger … (WARNING)>` is shell
    syntax. The error landed after the sentinel, where nothing reads it, so the
    command still worked and the cleanup silently never ran.
    """
    import subprocess

    wrappers = [
        jobs.launch_command("chatx", "abc123abc123", "echo hi"),
        jobs.launch_and_wait_command("chatx", "abc123abc123", "echo hi", 4096),
        jobs.read_command("chatx", "abc123abc123", 4096),
        jobs.stop_command("chatx", "abc123abc123"),
        jobs.cleanup_command("chatx", "abc123abc123"),
    ]
    for wrapper in wrappers:
        done = subprocess.run(
            ["sh", "-n"], input=wrapper, capture_output=True, text=True, check=False
        )
        assert done.returncode == 0, f"not valid shell:\n{wrapper}\n{done.stderr}"


def test_launch_and_wait_removes_every_file_it_made():
    """Its last line is the only cleanup on the fast path -- nothing calls
    `_cleanup` when a command finishes in time."""
    wrapper = jobs.launch_and_wait_command("chatx", "abc123abc123", "echo hi", 4096)
    removal = next(line for line in wrapper.splitlines() if line.startswith("rm -f"))

    for extension in ("sh", "pid", "log", "exit"):
        assert jobs._file("chatx", "abc123abc123", extension) in removal, extension
    assert "<Logger" not in wrapper


def test_parse_reads_the_last_sentinel():
    out = ("line one\n__LEMBAS_jobjobjob01__:0\nmore\n__LEMBAS_jobjobjob01__:0")
    done = jobs.parse_completed(out, "jobjobjob01")
    assert done.exit_status == 0


def test_valid_id_refuses_a_path():
    assert jobs.valid_id("deadbeef0000")
    assert not jobs.valid_id("../../etc/passwd")
    assert not jobs.valid_id("")


# --- Real shell: launch-and-wait -----------------------------------------------
async def test_a_fast_command_completes_like_a_foreground_one(tmp_path):
    agent = _agent(tmp_path)
    outcome = await _run_shell(_context(agent), {"command": "echo hello"})

    assert "hello" in outcome.content
    assert outcome.event["status"] == "ok"
    assert not jobs.for_chat(agent.chat_id), "a finished command is not a job"


async def test_a_fast_command_leaves_nothing_behind(tmp_path):
    """With background on, *every* command goes through the wrapper, so a
    cleanup that does not run is four files per command on somebody's machine --
    including the log, which holds everything the command printed."""
    import os
    import pathlib
    import uuid

    # Its own chat id, so the directory is exclusively this run's. Job files are
    # namespaced by chat, so that is isolation by construction rather than by
    # tidying up after a previous run -- which is what a shared id would need,
    # and would quietly pass the moment the tidying broke.
    chat_id = uuid.uuid4().hex[:12]
    agent = _agent(tmp_path, chat_id=chat_id)
    await _run_shell(_context(agent), {"command": "echo hello"})

    root = pathlib.Path(os.environ.get("TMPDIR", "/tmp")) / "lembas-jobs" / chat_id
    left = sorted(p.name for p in root.iterdir()) if root.exists() else []
    assert left == [], f"left behind: {left}"


async def test_a_nonzero_exit_is_read_from_the_exit_file_not_the_wrapper(tmp_path):
    """The wrapper's own status is ~0 from its trailing rm; the command's real
    status is in the exit-file."""
    agent = _agent(tmp_path)
    outcome = await _run_shell(_context(agent), {"command": "sh -c 'exit 3'"})

    assert "exited 3" in outcome.content
    assert outcome.event["status"] == "error"


async def test_a_command_with_single_quotes_runs(tmp_path):
    agent = _agent(tmp_path)
    outcome = await _run_shell(_context(agent), {"command": "echo 'a'\\''b'"})

    assert "a'b" in outcome.content


async def test_output_is_captured(tmp_path):
    agent = _agent(tmp_path)
    outcome = await _run_shell(_context(agent), {"command": "printf 'one\\ntwo\\n'"})
    assert "one" in outcome.content and "two" in outcome.content


# --- Real shell: auto-background on timeout -------------------------------------
async def test_a_slow_command_is_kept_running_when_it_times_out(tmp_path):
    """The apt-install case. It is not killed; it becomes a job that finishes
    on its own, and its result is readable afterwards."""
    agent = _agent(tmp_path)
    outcome = await _run_shell(
        _context(agent), {"command": "sleep 2; echo done-late", "timeout": 1}
    )

    assert "background" in outcome.content.lower()
    running = jobs.for_chat(agent.chat_id)
    assert len(running) == 1
    job_id = running[0].id

    # The detached child survived the wait being cut off; give it time to finish.
    for _ in range(40):
        reading = await jobs.read(agent, job_id)
        if reading.status == "done":
            break
        await asyncio.sleep(0.2)
    assert reading.status == "done"
    assert "done-late" in reading.body


async def test_off_timeout_keeps_the_hard_stop(tmp_path):
    """With the auto-convert off, a timed-out command is killed as before and no
    job is left running."""
    agent = _agent(tmp_path, background_on_timeout=False)
    outcome = await _run_shell(
        _context(agent), {"command": "sleep 2; echo late", "timeout": 1}
    )

    assert "stopped after" in outcome.content
    assert not jobs.for_chat(agent.chat_id)


async def test_feature_off_is_the_plain_path(tmp_path):
    """No wrapper, no job, byte-for-byte the old wording."""
    agent = _agent(tmp_path, background=False)
    outcome = await _run_shell(_context(agent), {"command": "echo hi"})

    assert "hi" in outcome.content
    assert not jobs.for_chat(agent.chat_id)


# --- Explicit background=true --------------------------------------------------
async def test_background_true_returns_at_once_with_a_job(tmp_path):
    agent = _agent(tmp_path)
    started = time.monotonic()
    outcome = await _run_shell(
        _context(agent), {"command": "sleep 5", "background": True}
    )
    assert time.monotonic() - started < 3, "it should not wait for the command"

    running = jobs.for_chat(agent.chat_id)
    assert len(running) == 1
    assert "job " in outcome.content
    await jobs.stop(agent, running[0].id)


# --- The job tools -------------------------------------------------------------
async def test_job_output_reads_a_running_job(tmp_path):
    from lembas.services.agent.tools import _run_job_output

    agent = _agent(tmp_path)
    job = await jobs.launch(agent, "sleep 5")
    outcome = await _run_job_output(_context(agent), {"id": job.id})
    assert "running" in outcome.content.lower()
    await jobs.stop(agent, job.id)


async def test_job_stop_ends_it(tmp_path):
    from lembas.services.agent.tools import _run_job_output, _run_job_stop

    agent = _agent(tmp_path)
    job = await jobs.launch(agent, "sleep 30")
    stopped = await _run_job_stop(_context(agent), {"id": job.id})
    assert "Stopped" in stopped.content

    reading = await _run_job_output(_context(agent), {"id": job.id})
    assert "running" not in reading.content.lower()


async def test_job_output_refuses_a_bad_id(tmp_path):
    from lembas.services.agent.tools import _run_job_output

    agent = _agent(tmp_path)
    outcome = await _run_job_output(_context(agent), {"id": "../../etc/passwd"})
    assert outcome.event["status"] == "error"


async def test_a_job_is_only_visible_to_its_own_chat(tmp_path):
    """for_chat is keyed on chat id; the file paths are too, so a model in
    another chat cannot even name it."""
    agent_a = _agent(tmp_path, chat_id="chataaaa")
    await jobs.launch(agent_a, "sleep 5")
    assert jobs.for_chat("chatbbbb") == []
    for job in jobs.for_chat("chataaaa"):
        await jobs.stop(agent_a, job.id)


# --- Gating --------------------------------------------------------------------
def test_job_tools_appear_only_when_enabled(tmp_path):
    from lembas.services.agent.tools import tool_defs

    on = {t.name for t in tool_defs(_agent(tmp_path, background=True))}
    off = {t.name for t in tool_defs(_agent(tmp_path, background=False))}

    assert {"job_output", "job_list", "job_stop"} <= on
    assert not ({"job_output", "job_list", "job_stop"} & off)


def test_background_param_appears_only_when_enabled(tmp_path):
    from lembas.services.agent.tools import tool_defs

    def shell(agent):
        return next(t for t in tool_defs(agent) if t.name == "shell_run")

    on = shell(_agent(tmp_path, background=True)).parameters["properties"]
    off = shell(_agent(tmp_path, background=False)).parameters["properties"]
    assert "background" in on
    assert "background" not in off


# --- Waking the model when a job finishes --------------------------------------
def _chat(db, user_id) -> str:
    from lembas.db.models import Chat

    chat = Chat(user_id=user_id, model_id="m")
    db.add(chat)
    db.commit()
    return chat.id


def test_the_completion_names_itself_a_machine_event():
    text = jobs._completion_text("abc123abc123", "apt-get install -y x", "done", 0, "ok\n")
    assert "machine event" in text
    assert "[job abc123abc123]" in text
    assert "apt-get install" in text
    assert "finished successfully" in text.lower()


def test_a_nonzero_completion_reports_the_code():
    text = jobs._completion_text("j", "build", "done", 2, "")
    assert "exited 2" in text


def test_backticks_in_output_cannot_close_the_fence():
    text = jobs._completion_text("j", "c", "done", 0, "see ```code``` here")
    assert "```code```" not in text


async def test_an_idle_chat_gets_a_fresh_reply(db, user_id, registered, monkeypatch):
    from lembas.services import generation as generation_service

    chat_id = _chat(db, user_id)
    monkeypatch.setattr(generation_service, "running_for", lambda _c: None)
    started: list[str] = []
    monkeypatch.setattr(generation_service, "ensure", lambda c, m: started.append(m))

    await jobs.wake(chat_id, "abc123abc123", "sleep 1", "done", 0, "hi")

    from lembas.db.models import Message

    db.expire_all()
    msgs = db.query(Message).filter(Message.chat_id == chat_id).all()
    users = [m for m in msgs if m.role == "user"]
    assert len(users) == 1
    assert users[0].queued is False, "an idle chat's completion is delivered, not queued"
    assert any(m.role == "assistant" and not m.complete for m in msgs)
    assert len(started) == 1, "a reply was started"


async def test_a_busy_chat_gets_a_queued_turn_and_no_new_reply(
    db, user_id, registered, monkeypatch
):
    from lembas.services import generation as generation_service

    chat_id = _chat(db, user_id)
    monkeypatch.setattr(generation_service, "running_for", lambda _c: object())
    started: list[str] = []
    monkeypatch.setattr(generation_service, "ensure", lambda c, m: started.append(m))

    await jobs.wake(chat_id, "abc123abc123", "sleep 1", "done", 0, "hi")

    from lembas.db.models import Message

    db.expire_all()
    users = [
        m for m in db.query(Message).filter(Message.chat_id == chat_id).all() if m.role == "user"
    ]
    assert len(users) == 1
    assert users[0].queued is True, "a running reply's _inject/_drain will deliver it"
    assert started == [], "no second reply for a chat already writing one"


async def test_two_jobs_finishing_at_once_start_one_reply(db, user_id, registered, monkeypatch):
    """The per-chat lock. Without it, both wakes would each start a generation."""
    from lembas.services import generation as generation_service

    chat_id = _chat(db, user_id)
    live = {"running": False}
    monkeypatch.setattr(
        generation_service, "running_for", lambda _c: object() if live["running"] else None
    )
    started: list[str] = []

    def _ensure(c, m):
        live["running"] = True  # what running_for will now see
        started.append(m)

    monkeypatch.setattr(generation_service, "ensure", _ensure)

    await asyncio.gather(
        jobs.wake(chat_id, "aaaaaaaaaaaa", "a", "done", 0, "x"),
        jobs.wake(chat_id, "bbbbbbbbbbbb", "b", "done", 0, "y"),
    )

    assert len(started) == 1, "the lock made the second wake see the first's reply"


async def test_a_completion_is_marked_as_a_machine_event(db, user_id, registered, monkeypatch):
    """The role stays `user` -- `_inject` sends a queued turn verbatim and
    `build_messages` has to keep seeing a user turn -- and `machine` is what
    stops the transcript claiming the reader typed it."""
    from lembas.services import generation as generation_service

    chat_id = _chat(db, user_id)
    monkeypatch.setattr(generation_service, "running_for", lambda _c: None)
    monkeypatch.setattr(generation_service, "ensure", lambda c, m: None)

    await jobs.wake(chat_id, "abc123abc123", "sleep 1", "done", 0, "hi")

    from lembas.db.models import Message

    db.expire_all()
    users = [
        m for m in db.query(Message).filter(Message.chat_id == chat_id).all() if m.role == "user"
    ]
    assert users[0].role == "user", "the wire role is load-bearing and must not move"
    assert users[0].machine is True


async def test_a_queued_completion_is_marked_too(db, user_id, registered, monkeypatch):
    """The busy path writes the same row with `queued` set; it must not lose the
    marking on the way, or a completion delivered by `_drain` arrives wearing the
    reader's name."""
    from lembas.services import generation as generation_service

    chat_id = _chat(db, user_id)
    monkeypatch.setattr(generation_service, "running_for", lambda _c: object())
    monkeypatch.setattr(generation_service, "ensure", lambda c, m: None)

    await jobs.wake(chat_id, "abc123abc123", "sleep 1", "done", 0, "hi")

    from lembas.db.models import Message

    db.expire_all()
    users = [
        m for m in db.query(Message).filter(Message.chat_id == chat_id).all() if m.role == "user"
    ]
    assert users[0].queued is True
    assert users[0].machine is True


def test_the_prompt_quotes_the_words_the_completion_actually_carries():
    """`tool.background` tells the model a completion "begins" with a particular
    sentence, so that it reads one as a machine event rather than as the person
    speaking. Rewording `_completion_text` breaks that instruction, in a way
    nothing else here would notice -- the turn still arrives, the model just
    stops being told what it is."""
    from lembas.services import prompts as prompts_service

    text = jobs._completion_text("abc123abc123", "pytest -q", "done", 0, "")
    opening = "A background job you started has finished"
    assert text.startswith(opening)

    fragment = next(f for f in prompts_service.BUILTIN if f.key == "tool.background")
    assert opening in fragment.default


# --- What a job looks like in the panel ----------------------------------------
@pytest.mark.parametrize(
    ("status", "exit_status", "expected"),
    [
        ("running", None, "running"),
        ("done", 0, "ok"),
        ("done", 2, "failed"),
        ("killed", 143, "killed"),
        ("lost", None, "lost"),
    ],
)
def test_the_dot_tells_a_failure_from_a_success(status, exit_status, expected):
    """`status` is `done` for exit 0 and exit 2 alike, and the row beside the dot
    already says "Finished" or "Failed, exit 2". A dot keyed on the status would
    be green next to the sentence contradicting it."""
    view = jobs.JobView(id="a", command="x", status=status, exit_status=exit_status)
    assert view.tone == expected


def test_a_finished_job_says_how_long_it_took():
    from datetime import UTC, datetime, timedelta

    started = datetime(2026, 8, 5, 14, 0, tzinfo=UTC)
    view = jobs.JobView(
        id="a",
        command="x",
        status="done",
        exit_status=0,
        started_at=started,
        finished_at=started + timedelta(seconds=252),
    )
    assert view.duration == "4m 12s"


def test_a_running_job_reports_no_duration():
    """Not for want of an answer. The panel is fetched when somebody opens it and
    never polled, so a live figure would be frozen the instant it painted."""
    from datetime import UTC, datetime

    view = jobs.JobView(
        id="a",
        command="x",
        status="running",
        started_at=datetime(2026, 8, 5, 14, 0, tzinfo=UTC),
    )
    assert view.duration == ""


def test_a_job_with_no_row_reports_no_duration():
    """`_persist_row` is best-effort by design, so a job with no stamps is a real
    case rather than a defensive one."""
    assert jobs.JobView(id="a", command="x", status="done", exit_status=0).duration == ""


def test_a_duration_survives_a_stamp_read_back_from_disk():
    """SQLite stores no offset, so a row loaded from disk comes back naive while
    one still in the session's identity map keeps its tzinfo -- and a job started
    before a restart and finished after it has one of each. Subtracting them
    without normalising raises, and it raises in the panel, not in a test."""
    from datetime import UTC, datetime

    view = jobs.JobView(
        id="a",
        command="x",
        status="done",
        exit_status=0,
        started_at=datetime(2026, 8, 5, 14, 0),  # naive, as SQLite hands it back
        finished_at=datetime(2026, 8, 5, 15, 6, tzinfo=UTC),
    )
    assert view.duration == "1h 06m"


# --- The watcher, end to end ---------------------------------------------------
async def test_the_watcher_end_to_end(db, user_id, registered, monkeypatch, tmp_path):
    from lembas.services.agent import ssh as ssh_service

    chat_id = _chat(db, user_id)

    class _Local(LocalExecutor):
        def __init__(self, spec, project_dir):
            super().__init__(str(tmp_path))

    monkeypatch.setattr(ssh_service, "SshExecutor", _Local)
    monkeypatch.setattr(jobs, "_poll_interval", lambda _e: 0.1)
    woken: list = []

    async def _wake(chat, job_id, command, status, code, body):
        woken.append((status, code, body))

    monkeypatch.setattr(jobs, "wake", _wake)

    agent = _agent(tmp_path, chat_id=chat_id)
    agent.executor = lambda: _Local(None, str(tmp_path))
    job = await jobs.launch(agent, "sleep 0.5; echo finished")
    jobs.start_watch(agent, job)

    for _ in range(50):
        if woken:
            break
        await asyncio.sleep(0.1)
    assert woken, "the watcher never woke the model"
    status, code, body = woken[0]
    assert status == "done"
    assert "finished" in body