brain-of-reese/tests/e2e/test_no_reply_autoscroll.py

"""Phase 42 E2E (Playwright, mock-only): the chat NEVER autoscrolls.

Story: ``.agent/user_stories/no-reply-autoscroll.md`` — owner direction
2026-08-27 (TODO.md L5) revising the phase-18 follow-the-bottom choice:
"Get rid of the chat reply autoscroll, it's breaking things like making
it impossible for the user to scroll while a reply generates."

Run in isolation (DB must be up: ``podman compose up -d db``):

    uv run pytest tests/e2e/test_no_reply_autoscroll.py -v --no-cov

This is the INVERSE of the phase-18 contract: while a turn streams
(thinking, tool, or answer frames), nothing moves the viewport — a user
reading earlier content stays exactly where they put it for the rest of
the turn. The only scrolls left in the app are user intent: the submit
(the user's own message is revealed) and the phase-14 restore landing
(one-shot, load-time). The phase-18 suite
(``tests/e2e/test_follow_bottom_scroll.py``) is deleted with this one —
its behavior was intentionally removed.

MOCK-ONLY suite: the scenarios key off the deterministic mock's
``write a long answer`` trigger (~900 words ≈ 8–11s of streaming — a
wide, reliable window to scroll away in) and the phase-17
``think out loud`` trigger (~4.5s reasoning stream). ``E2E_REAL_LLM=1``
would make the scroll-away windows unpredictable, so it is not supported
here.

Measurement convention: the scroller is the DOCUMENT — there is no inner
scroll container. ``window.scrollY`` is read via ``page.evaluate``;
"stable" means every sample is within 1px of every other sample (the
story's tolerance). The stylesheet sets no ``scroll-behavior``, so
``window.scrollTo(0, y)`` is instant — the recorded position is the exact
position the stream must not move.

Test → story mapping (Playwright Mapping Rule):
1. ``test_no_autoscroll_during_long_answer``
2. ``test_no_autoscroll_during_thinking``
3. ``test_submit_reveals_user_message``
4. ``test_restore_landing_one_shot``
5. ``test_answer_content_intact``
"""
from __future__ import annotations

import asyncio
import json
import time
from collections.abc import Iterator
from pathlib import Path
from threading import Thread
from typing import Any

import pytest
from playwright.sync_api import Page, expect
from sqlalchemy import text

from app.config import Settings
from app.db import SessionLocal
from app.rag.importer import ImportSummary, import_sources
from app.rag.llm import LLMClient

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"

#: Mock long-answer trigger (~900 words ≈ 8–11s of streaming at the mock's
#: 0.02s/frame pace) — the wide, deterministic window to scroll away in.
LONG_QUESTION = "write a long answer about my kubernetes cluster"
#: Phase-17 thinking trigger: a ~4.5s reasoning stream, then a short
#: grounded mock answer (both fire independently of the long trigger).
THINKING_QUESTION = "think out loud about my kubernetes cluster"
#: Short grounded question (phase-14 marker answer).
SHORT_QUESTION = "How is my Kubernetes cluster set up?"
#: The mock long answer's unique final line (mock_llm.LONG_ANSWER_END) —
#: proves the whole stream landed even while the viewport was up.
LONG_ANSWER_END = "LONG-ANSWER-END"
#: Line fragment the mock's deterministic scratchpad carries
#: (mock_llm.compose_thinking) — same key phase 17's suite uses.
THINKING_FRAGMENT = "Step 2: Check my notes"
MOCK_ANSWER_MARKER = "Deterministic mock answer for E2E"
STORAGE_KEY = "bor.chat.v1"

#: The story's stability tolerance: the viewport must not move more than
#: 1px while a turn streams with the user scrolled away.
STABLE_PX = 1


async def _import_fixtures(mock_port: int) -> ImportSummary:
    kwargs: dict[str, Any] = {"_env_file": None, "llm_base_url": f"http://127.0.0.1:{mock_port}/v1"}
    settings = Settings(**kwargs)  # pyright: ignore[reportCallIssue]
    return await import_sources([FIXTURES], LLMClient(settings))


def _run_in_thread(coro: Any) -> Any:
    """Run a coroutine on a worker thread.

    Playwright's sync API keeps an asyncio loop running on the test thread,
    so ``asyncio.run`` cannot be called directly from a test body.
    """
    box: dict[str, Any] = {}

    def runner() -> None:
        try:
            box["value"] = asyncio.run(coro)
        except BaseException as e:  # noqa: BLE001 — re-raised on the test thread
            box["error"] = e

    t = Thread(target=runner)
    t.start()
    t.join()
    if "error" in box:
        raise box["error"]
    return box["value"]


def _reset_db(mock_port: int, seed: bool) -> ImportSummary | None:
    """Truncate the KB (and query log), then optionally re-import fixtures."""
    with SessionLocal() as db:
        db.execute(text("TRUNCATE chunks, documents, query_log"))
        db.commit()
    if not seed:
        return None
    return _run_in_thread(_import_fixtures(mock_port))


@pytest.fixture()
def seeded_kb(mock_llm: int, db_ready: None) -> Iterator[None]:
    """A fresh KB seeded from ``tests/fixtures/docs`` (8 docs, A9 formats),
    truncated again on teardown. ``db_ready`` (conftest) skips with clear
    instructions when Postgres is down."""
    summary = _reset_db(mock_llm, seed=True)
    assert summary is not None and summary.added == 8
    yield
    _reset_db(mock_llm, seed=False)


# ---------------------------------------------------------------------------
# Measurement + flow helpers
# ---------------------------------------------------------------------------


def scroll_state(page: Page) -> dict[str, float]:
    """The document scroller's state (there is no inner scroll container)."""
    return page.evaluate(
        "() => ({ y: window.scrollY, "
        "sh: document.documentElement.scrollHeight, "
        "ch: window.innerHeight })"
    )


def brain_bubble_longer_than(n: int, min_bubbles: int = 1) -> str:
    """JS predicate: there are at least ``min_bubbles`` brain bubbles and
    the LAST one's rendered text is > n chars (i.e. that far into the
    stream). ``min_bubbles=2`` guards a second turn: before its first
    delta, ``.last`` would still be the PREVIOUS turn's bubble."""
    return (
        "() => { const els = document.querySelectorAll('.msg.brain .bubble');"
        f" return els.length >= {min_bubbles} && els[els.length - 1].innerText.length > {n}; }}"
    )


def wait_settled(page: Page) -> None:
    """The turn is over: the never-stale contract re-enabled the button."""
    expect(page.locator("#send-btn")).to_be_enabled(timeout=30_000)
    expect(page.locator("#send-label")).to_have_text("Send")


def wait_scroll_still(page: Page, timeout: float = 10.0) -> float:
    """window.scrollY once the viewport has stopped moving (two consecutive
    reads within STABLE_PX). The submit's smooth reveal and the restore
    landing's smooth scroll are the only animations left — both settle
    this way before any stream measurement begins."""
    deadline = time.monotonic() + timeout
    prev: float | None = None
    while True:
        y = scroll_state(page)["y"]
        if prev is not None and abs(y - prev) <= STABLE_PX:
            return y
        prev = y
        if time.monotonic() >= deadline:
            raise AssertionError("the viewport did not settle within timeout")
        time.sleep(0.25)


def submit(page: Page, question: str) -> None:
    """Submit through the composer (the real-user flow). Playwright's
    fill/click scroll the composer into view first — a user-initiated
    move, never an app scroll."""
    page.fill("#message-input", question)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(question)


def submit_from_top(page: Page, question: str) -> None:
    """Submit with the viewport where the user left it (the very top).

    ``page.fill``/``page.click`` would scroll the composer into view
    first — which IS the viewport move under test — so the send goes
    through the page's own DOM: set the value, fire ``input`` (autoGrow),
    click the submit button. A JS click never scrolls the page."""
    page.evaluate(
        """(q) => {
            const input = document.querySelector('#message-input');
            input.value = q;
            input.dispatchEvent(new Event('input', { bubbles: true }));
            document.querySelector('#send-btn').click();
        }""",
        question,
    )
    expect(page.locator(".msg.user .bubble").last).to_contain_text(question)


def user_message_in_view(page: Page) -> bool:
    """The LAST user message's box is fully inside the viewport
    (the submit reveal aligns it to the bottom edge)."""
    box = page.locator(".msg.user").last.bounding_box()
    if box is None:
        return False
    ch = scroll_state(page)["ch"]
    return box["y"] >= -1 and box["y"] + box["height"] <= ch + 1


# ---------------------------------------------------------------------------
# 1. No autoscroll: scrolled up mid-ANSWER — the viewport holds for the
#    rest of the turn (the answer finishes off-screen below, by design)
# ---------------------------------------------------------------------------


def test_no_autoscroll_during_long_answer(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    page.goto(app_url)

    # Turn 1 (settled) makes the document overflow the 800px viewport.
    submit(page, LONG_QUESTION)
    wait_settled(page)
    state = scroll_state(page)
    assert state["sh"] > state["ch"], "a long answer must make the document scrollable"

    # Turn 2: the same long answer. The submit reveals the user's message
    # (the one kept app scroll) — let that smooth reveal settle first.
    submit(page, LONG_QUESTION)
    page.wait_for_function(brain_bubble_longer_than(200, min_bubbles=2), timeout=30_000)
    y0 = wait_scroll_still(page)

    # The user scrolls UP ~2× the answer's current height to read earlier
    # context while the stream is still running.
    box = page.locator(".msg.brain").last.bounding_box()
    assert box is not None
    target = max(0.0, y0 - 2 * box["height"])
    assert target <= y0 - STABLE_PX, "the scroll-up must actually move the viewport"
    page.evaluate("y => window.scrollTo(0, y)", target)
    assert abs(scroll_state(page)["y"] - target) <= STABLE_PX

    # Sample the viewport across the rest of the stream ...
    samples: list[float] = []
    mid_stream = 0
    deadline = time.monotonic() + 40
    while time.monotonic() < deadline:
        time.sleep(0.25)
        samples.append(scroll_state(page)["y"])
        if not page.locator("#send-btn").is_enabled():
            mid_stream += 1
        if len(samples) >= 10 and page.locator("#send-btn").is_enabled():
            # ... and a few more AFTER `done` (the turn is over; nothing
            # queued behind the stream may move the page either).
            for _ in range(3):
                time.sleep(0.3)
                samples.append(scroll_state(page)["y"])
            break
    else:
        raise AssertionError("the long turn did not settle within 40s")
    assert mid_stream >= 8, "the samples must land while the stream is running"

    spread = max(samples) - min(samples)
    assert spread <= STABLE_PX, (
        f"the viewport moved {spread:.1f}px while the user was scrolled up "
        "(no-reply-autoscroll contract)"
    )

    # The whole answer still landed (off-screen below — by design).
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(LONG_ANSWER_END)


# ---------------------------------------------------------------------------
# 2. No autoscroll: scrolled up during THINKING — the whole reasoning
#    stream plus the answer's start happen with the viewport held
# ---------------------------------------------------------------------------


def test_no_autoscroll_during_thinking(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    page.goto(app_url)

    # One settled long turn so the document overflows (scrollable).
    submit(page, LONG_QUESTION)
    wait_settled(page)

    # The thinking turn: the submit reveals the user's message (the kept
    # app scroll) ...
    submit(page, THINKING_QUESTION)
    details = page.locator(".msg.brain").last.locator("details.thinking")
    details.wait_for(state="attached", timeout=10_000)
    expect(details).to_have_attribute("open", "")  # created open (phase 17)
    # ... and, once the reasoning stream is clearly running ...
    page.wait_for_function(
        "() => { const el = document.querySelector('details.thinking .thinking-text');"
        " return !!el && el.innerText.length > 300; }",
        timeout=30_000,
    )
    # ... let the submit's smooth reveal settle, then the user goes up.
    wait_scroll_still(page)
    page.evaluate("() => window.scrollTo(0, 0)")

    # Sample across the remaining thinking stream: no per-chunk follow.
    samples: list[float] = []
    open_samples = 0
    deadline = time.monotonic() + 25
    while time.monotonic() < deadline:
        time.sleep(0.3)
        state = page.evaluate(
            """() => {
                const block = document.querySelector('details.thinking');
                const wrap = block ? block.closest('.msg.brain') : null;
                const el = wrap ? wrap.querySelector('.bubble') : null;
                return { y: window.scrollY,
                         open: !!(block && block.open),
                         bubble: el ? el.innerText.length : 0 };
            }"""
        )
        samples.append(state["y"])
        if state["open"]:
            open_samples += 1
        if state["bubble"] > 0 and len(samples) >= 8:
            break
    else:
        raise AssertionError("the first answer token never arrived")
    assert open_samples >= 6, "the samples must land while the thinking stream is open"

    spread = max(samples) - min(samples)
    assert spread <= STABLE_PX, (
        f"the viewport moved {spread:.1f}px during the thinking stream "
        "(no per-chunk page follow)"
    )

    # Settled: still at the top, everything landed (off-screen, which is
    # the point of the story).
    wait_settled(page)
    assert abs(scroll_state(page)["y"]) <= STABLE_PX
    expect(details.locator(".thinking-text")).to_contain_text(THINKING_FRAGMENT)
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(MOCK_ANSWER_MARKER)


# ---------------------------------------------------------------------------
# 3. Submit: scrolled to the very top, sending a question still reveals
#    the user's own message (the kept, user-initiated scroll)
# ---------------------------------------------------------------------------


def test_submit_reveals_user_message(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    page.goto(app_url)

    # A populated conversation that overflows the viewport.
    submit(page, LONG_QUESTION)
    wait_settled(page)
    state = scroll_state(page)
    assert state["sh"] > state["ch"], "a long answer must make the document scrollable"

    # The user is reading at the very top ...
    page.evaluate("() => window.scrollTo(0, 0)")
    assert scroll_state(page)["y"] <= STABLE_PX

    # ... and sends a question without first scrolling down.
    submit_from_top(page, SHORT_QUESTION)

    # The submit's reveal is the kept app scroll: the user's own message
    # ends up in view (its box fully inside the viewport).
    deadline = time.monotonic() + 10
    while time.monotonic() < deadline and not user_message_in_view(page):
        time.sleep(0.2)
    assert user_message_in_view(page), (
        "the submit must reveal the user's message — its box is not in the viewport"
    )

    # The turn completes; the answer lands off-screen below, but the user
    # message stays revealed (nothing re-positions it).
    wait_settled(page)
    assert user_message_in_view(page)
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(MOCK_ANSWER_MARKER)


# ---------------------------------------------------------------------------
# 4. Restore landing (phase 14, owner-kept): a reload lands one-shot on
#    the latest message and stays there while idle
# ---------------------------------------------------------------------------


def test_restore_landing_one_shot(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    page.goto(app_url)

    # Settle a conversation (phase-14 persistence): long + short turns.
    submit(page, LONG_QUESTION)
    wait_settled(page)
    submit(page, SHORT_QUESTION)
    wait_settled(page)
    time.sleep(0.5)  # let the persistence writes land before the reload

    page.reload()
    # Restore re-renders from localStorage; wait until the last restored
    # brain answer (the short one — the long answer carries no mock
    # marker) is fully back.
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(
        MOCK_ANSWER_MARKER, timeout=30_000
    )
    # The one-shot landing rides a smooth scroll — let it settle ...
    wait_scroll_still(page)
    state = scroll_state(page)
    assert state["sh"] > state["ch"]

    # ... and it lands on the latest message: its bubble is in view, in
    # the lower half of the viewport (the chips + composer sit just
    # below the fold — the landing predates them by design).
    box = page.locator(".msg.brain").last.locator(".bubble").bounding_box()
    assert box is not None
    assert box["y"] < state["ch"] and box["y"] + box["height"] >= state["ch"] * 0.6, (
        "the restore landing must put the latest message in view"
    )

    # ... and STAYS: idle samples (no stream active) never move.
    samples = [state["y"]]
    for _ in range(4):
        time.sleep(0.4)
        samples.append(scroll_state(page)["y"])
    spread = max(samples) - min(samples)
    assert spread <= STABLE_PX, (
        f"the restored page moved {spread:.1f}px while idle"
    )


# ---------------------------------------------------------------------------
# 5. Content intact (regression): the long answer completes with sources;
#    a thinking turn persists + restores its collapsed block (phase 17)
# ---------------------------------------------------------------------------


def test_answer_content_intact(page: Page, app_url: str, seeded_kb: None) -> None:
    page.set_default_timeout(30_000)
    page.goto(app_url)

    # The long answer streams to completion with its sources ...
    submit(page, LONG_QUESTION)
    wait_settled(page)
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(LONG_ANSWER_END)
    expect(
        page.locator(".msg.brain .source-chip", has_text="kubernetes.md")
    ).to_have_count(1)

    # ... and a thinking turn completes with its block auto-collapsed
    # (phase 17: open while streaming, closed from the first delta on).
    submit(page, THINKING_QUESTION)
    wait_settled(page)
    details = page.locator(".msg.brain").last.locator("details.thinking")
    expect(details).not_to_have_attribute("open")
    expect(details.locator(".thinking-text")).to_contain_text(THINKING_FRAGMENT)
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(MOCK_ANSWER_MARKER)

    # Persistence: four messages, the thinking text + sources stored raw.
    raw = page.evaluate(f"() => localStorage.getItem('{STORAGE_KEY}')")
    stored = json.loads(raw)
    assert [m["who"] for m in stored["messages"]] == ["user", "brain", "user", "brain"]
    assert LONG_ANSWER_END in stored["messages"][1]["text"]
    assert THINKING_FRAGMENT in stored["messages"][3]["thinking"]
    assert any(
        s["path"] == "homelab/kubernetes.md" for s in stored["messages"][3]["sources"]
    )

    # Restore: the long answer (with its chip) and the COLLAPSED thinking
    # block come back intact.
    page.reload()
    expect(page.locator(".msg.user .bubble")).to_have_count(2)
    expect(page.locator(".msg.brain .bubble")).to_have_count(2)
    expect(page.locator(".msg.brain .bubble").first).to_contain_text(LONG_ANSWER_END)
    expect(
        page.locator(".msg.brain .source-chip", has_text="kubernetes.md")
    ).to_have_count(2)
    restored = page.locator(".msg.brain").last.locator("details.thinking")
    expect(restored).not_to_have_attribute("open")
    expect(restored.locator(".thinking-text")).to_contain_text(THINKING_FRAGMENT)
    wait_settled(page)