nisse/nisse-dev/tests/test_loop_labels.py

"""Threads, commands and labels in the new loop (M2.3): commands that name
their item, ambiguous ones asked about (L5); plain-language go-aheads; `bug`
grace periods, `discuss` and `design` (D1)."""

from pathlib import Path
from typing import Any

import pytest
from test_loop import DON, RESTATED, FakeGitea, Harness, ScriptedModel, call, issue
from test_loop import h as h  # noqa: PLC0414 -- the fixture

from nisse_dev.canonical import Fact, ToolCall
from nisse_dev.llm import LLMError
from nisse_dev.loop.items import ANSWER, GO_AHEAD, READY, WAITING, loop_of
from nisse_dev.loop.reader import GoAheadReader

STARTED = [call("ask_human", question="started; anything else?")]


class Clock:
    def __init__(self) -> None:
        self.now = 1000.0

    def __call__(self) -> float:
        return self.now


class Reader:
    """A scripted go-ahead reader: agrees with what it's told to."""

    def __init__(self, *yes: str) -> None:
        self.yes = set(yes)
        self.asked: list[tuple[str, str]] = []

    def agrees(self, proposal: str, reply: str, model: str = "") -> bool:
        self.asked.append((proposal, reply))
        return reply in self.yes


def facts(h: Harness) -> list[str]:
    return [
        e.event.text
        for e in h.store.transcript(h.item().id, "orchestrator").read()
        if isinstance(e.event, Fact)
    ]


def two(tmp_path: Path, *turns: list[Any]) -> Harness:
    return Harness(
        tmp_path,
        ScriptedModel(*turns),
        FakeGitea(issue(14), issue(15, title="Add count_lines")),
    )


# --- commands that name their item, and ambiguous ones (L5) -------------------


def test_a_named_go_at_top_level_applies_to_its_item(tmp_path: Path) -> None:
    h = two(tmp_path, RESTATED, RESTATED, STARTED)
    h.agent.intake()
    h.say("go #15", thread=None)
    items = {loop_of(i).issue: i for i in h.store.work_items()}
    assert loop_of(items[15]).started and not loop_of(items[14]).started


def test_a_named_abandon_in_another_thread_still_names_its_item(
    tmp_path: Path,
) -> None:
    h = two(tmp_path, RESTATED, RESTATED)
    h.agent.intake()
    items = {loop_of(i).issue: i for i in h.store.work_items()}
    h.transport.receive(DON, "Abandon #15.", thread=loop_of(items[14]).thread)
    items = {loop_of(i).issue: i for i in h.store.work_items()}
    assert items[15].status == "closed" and items[14].status == "open"


def test_an_unnamed_command_at_top_level_is_asked_about(tmp_path: Path) -> None:
    h = two(tmp_path, RESTATED, RESTATED)
    h.agent.intake()
    h.say("abandon", thread=None)
    assert all(i.status == "open" for i in h.store.work_items())
    asked = h.posted()[-1]
    assert "Which item?" in asked and "#14" in asked and "#15" in asked


def test_naming_an_item_that_isnt_open_says_so(h: Harness) -> None:
    h.agent.intake()
    h.say("go #99", thread=None)
    assert "#99 isn't one of my open work items" in h.posted()[-1]


def test_stop_in_a_waiting_items_thread_is_not_an_answer(h: Harness) -> None:
    h.agent.intake()
    h.say("stop")
    assert (h.item().position, loop_of(h.item()).wait) == (WAITING, GO_AHEAD)
    assert "nothing to stop" in h.posted()[-1]


# --- plain-language go-aheads (L5, D1) ------------------------------------------


def test_a_plain_yes_is_a_go_ahead_said_so_first(tmp_path: Path) -> None:
    reader = Reader("Yep, that's it")
    h = Harness(
        tmp_path, ScriptedModel(RESTATED, STARTED), FakeGitea(issue()), reader=reader
    )
    h.agent.intake()
    h.say("Yep, that's it")
    assert loop_of(h.item()).started
    assert "Taking that as a go-ahead on rev-1" in " ".join(h.posted())
    assert reader.asked == [
        ("I'll add count_words to text.py, with tests.", "Yep, that's it")
    ]
    assert any(f.startswith("go-ahead on rev-1 from") for f in facts(h))


def test_anything_else_goes_to_the_driver(tmp_path: Path) -> None:
    h = Harness(
        tmp_path,
        ScriptedModel(RESTATED, [call("restate", text="v2", changed="as you asked")]),
        FakeGitea(issue()),
        reader=Reader(),
    )
    h.agent.intake()
    h.say("Mostly, but call it word_count")
    loop = loop_of(h.item())
    assert not loop.started and loop.rev == 2


def test_a_question_never_reaches_the_reader(tmp_path: Path) -> None:
    reader = Reader("sounds good?")
    h = Harness(
        tmp_path,
        ScriptedModel(RESTATED, [call("restate", text="v2", changed="as you asked")]),
        FakeGitea(issue()),
        reader=reader,
    )
    h.agent.intake()
    h.say("sounds good?")
    assert not loop_of(h.item()).started and reader.asked == []


def test_a_plain_yes_to_an_older_revision_is_not_a_go(tmp_path: Path) -> None:
    reader = Reader("yes")
    h = Harness(
        tmp_path,
        ScriptedModel(
            RESTATED, [call("restate", text="v2", changed="as you asked")], STARTED
        ),
        FakeGitea(issue()),
        reader=reader,
    )
    h.agent.intake()
    h.say("change it a bit")  # rev-2 goes up
    h.agent.handle(_msg("yes", h.thread()), about=1)
    assert not loop_of(h.item()).started
    assert [reply for _, reply in reader.asked] == ["change it a bit"]


class _Model:
    def __init__(self, result: Any) -> None:
        self.result = result

    def complete(self, events, tools, model, system=None) -> list[Any]:
        if isinstance(self.result, Exception):
            raise self.result
        return self.result


@pytest.mark.parametrize(
    ("result", "agrees"),
    [
        ([ToolCall(call_id="v", tool="verdict", arguments={"answer": "yes"})], True),
        (
            [ToolCall(call_id="v", tool="verdict", arguments={"answer": "unclear"})],
            False,
        ),
        ([], False),
        (LLMError("down"), False),
    ],
)
def test_the_reader_agrees_only_on_a_clear_yes(result: Any, agrees: bool) -> None:
    reader = GoAheadReader(_Model(result), "m")  # type: ignore[arg-type]
    assert reader.agrees("add count_words", "ok") is agrees


# --- labels (D1) ----------------------------------------------------------------


def bug(tmp_path: Path, *turns: list[Any], **kw: Any) -> tuple[Harness, Clock]:
    clock = Clock()
    h = Harness(
        tmp_path,
        ScriptedModel(*turns),
        FakeGitea(issue(labels=("bug",))),
        clock=clock,
        bug_grace_s=600,
        **kw,
    )
    return h, clock


def test_a_bug_goes_ahead_after_the_grace_period(tmp_path: Path) -> None:
    h, clock = bug(tmp_path, RESTATED, STARTED)
    h.agent.intake()
    assert "go ahead in 10 min unless you reply" in h.posted()[-1]
    assert "going ahead in 10 min" in h.agent.status()
    clock.now += 599
    h.agent.intake()
    assert not loop_of(h.item()).started
    clock.now += 1
    h.agent.intake()
    assert loop_of(h.item()).started
    assert "go-ahead on rev-1 from the bug grace period" in facts(h)


def test_a_reply_stops_the_bugs_countdown(tmp_path: Path) -> None:
    h, clock = bug(tmp_path, RESTATED, [call("ask_human", question="which file?")])
    h.agent.intake()
    h.say("hmm, what about unicode")
    clock.now += 3600
    h.agent.intake()
    loop = loop_of(h.item())
    assert not loop.started and loop.grace_until == 0 and loop.wait == ANSWER


def test_a_new_revision_of_a_bug_gets_its_own_countdown(tmp_path: Path) -> None:
    h, clock = bug(
        tmp_path,
        RESTATED,
        [call("restate", text="v2", changed="as you asked")],
        STARTED,
    )
    h.agent.intake()
    clock.now += 300
    h.say("use the other file")
    assert loop_of(h.item()).grace_until == clock.now + 600
    clock.now += 600
    h.agent.intake()
    assert "go-ahead on rev-2 from the bug grace period" in facts(h)


def test_the_bug_label_reaches_the_driver(tmp_path: Path) -> None:
    seen: list[str] = []

    class Spy(ScriptedModel):
        def complete(self, events, tools, model, system=None):  # type: ignore[no-untyped-def]
            seen.append(system or "")
            return super().complete(events, tools, model, system)

    h = Harness(tmp_path, Spy(RESTATED), FakeGitea(issue(labels=("bug", "ui"))))
    h.agent.intake()
    assert "never fix a bug you couldn't see" in seen[0]
    assert "labelled discuss" not in seen[0]


def test_discuss_talks_before_it_restates(tmp_path: Path) -> None:
    offered: list[set[str]] = []

    class Spy(ScriptedModel):
        def complete(self, events, tools, model, system=None):  # type: ignore[no-untyped-def]
            offered.append({t["function"]["name"] for t in tools})
            return super().complete(events, tools, model, system)

    h = Harness(
        tmp_path,
        Spy([call("ask_human", question="what's it for?")], RESTATED),
        FakeGitea(issue(labels=("discuss",))),
    )
    h.agent.intake()
    assert "restate" not in offered[0]
    assert loop_of(h.item()).wait == ANSWER
    h.say("for the stats page")
    assert "restate" in offered[1]
    assert loop_of(h.item()).wait == GO_AHEAD


def test_an_unlabelled_issue_waits_for_go_with_no_countdown(h: Harness) -> None:
    h.agent.intake()
    loop = loop_of(h.item())
    assert loop.wait == GO_AHEAD and loop.grace_until == 0
    assert h.item().position != READY


def _msg(text: str, thread: str) -> Any:
    from nisse_dev.transport import InboundMessage

    return InboundMessage(DON, text, thread=thread)


def test_a_restatement_that_asks_is_sent_back(tmp_path: Path) -> None:
    """A restatement is agreed to as it stands; one ending in a question
    (models add "Is this right?") never goes up."""
    h = Harness(
        tmp_path,
        ScriptedModel(
            [call("restate", text="I'll add count_words. Is this right?")],
            [call("restate", text="I'll add count_words to text.py, with tests.")],
        ),
        FakeGitea(issue()),
    )
    h.agent.intake()
    loop = loop_of(h.item())
    assert (loop.wait, loop.rev) == (GO_AHEAD, 1)
    posted = [p for p in h.posted() if p.startswith("rev-")]
    assert posted == [
        (
            "rev-1: I'll add count_words to text.py, with tests.\n\n"
            "Say go to start, or reply with changes."
        )
    ]
    results = [
        e.event.result
        for e in h.store.transcript(h.item().id, "driver").read()
        if hasattr(e.event, "result")
    ]
    assert any("a restatement asks no questions" in r for r in results)