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

"""Phase 114 E2E (Playwright): the 4,000-char (composer-clamp) question
sends a CLEAN turn — the L6 acceptance pin (TODO.md L179–181).

Source: TODO.md L149–181 — "L6 — 4,000-char question clamp exceeds the
embed model's input cap → misleading 'couldn't reach the embedding model'
error (2026-09-15, brain-of-reese interactive test)". The repro was 100%
reliable: a question at the composer's 4,000-char clamp (~903 tokens)
made the REAL aipi endpoint's litellm reject the embedding with
``input (903 tokens) is too large to process`` (HTTP 500) — and the
turn died pre-token with the banner "I couldn't reach the embedding
model — please try again."

The fix under test (LOCKED A1 + A2, 00_phase.md): the embed step now
embeds at most ``embed_question_max_chars`` (default 1200 — the
chunker's ``HARD_MAX_CHARS`` budget, env-tunable) of the question —
the unit suite (``tests/unit/test_embed_question_length.py``) pins that
``embed_one`` receives EXACTLY the 1200-char prefix while the FULL
question still reaches the LLM prompt — while the 4,000-char composer
clamp stays (locked A2: truncation, not a lower clamp).

Pinned here (the truncated-embed success path — the unit suite pins the
prefix itself and the too-long error mapping):

* a question typed to the FULL clamp (EXACTLY 4,000 chars — the counter
  reads ``4000/4000 — character limit`` + ``.is-max``) sends: the turn
  streams to ``done`` on the mock LLM with the grounded answer marker,
  NO error banner (the pre-phase "couldn't reach the embedding model"
  death is gone), the user bubble carries the FULL 4,000-char question,
  and the input + counter clear (never stale, PLAN §7.4).

The question repeats a fixture-KB sentence (``kubernetes`` — indexed by
``tests/fixtures/docs/homelab/kubernetes.md``) so the hybrid retrieval
grounds (the mock-calibrated 0.30 threshold in the e2e conftest) and
the brain bubble carries ``MOCK_ANSWER_MARKER`` — the strongest
"the turn completed" reading.

The endpoint and the chat are authed (phase 79, ``require_user``), so
the test signs in as admin first (``auth_helpers.login``). The send
auto-saves a ``saved_chats`` row, so the autouse fixture truncates that
table before and after the test (the phase-80/103 isolation pattern).

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

    uv run pytest tests/e2e/test_embed_question_length.py -v --no-cov
"""
from __future__ import annotations

import asyncio
import re
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
from e2e.auth_helpers import login

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"
MOCK_ANSWER_MARKER = "Deterministic mock answer for E2E"

#: The composer's hard cap (``maxlength="4000"`` mirroring the server
#: ``ChatRequest.message max_length=4000`` — the phase-104 A3 clamp).
_CAP = 4_000

#: A sentence the fixture KB indexes (``kubernetes`` — the FTS leg of
#: the hybrid retrieval hits, so the turn GROUNDS) repeated to the
#: clamp: the L6 repro shape — a legal 4,000-char question whose pre-
#: phase embedding input (~903 tokens) exceeded the real endpoint's
#: per-request input cap.
_QUESTION_SENTENCE = (
    "How is my homelab kubernetes cluster configured for long-running batch jobs? "
)
QUESTION = (_QUESTION_SENTENCE * 52)[:_CAP]
assert len(QUESTION) == _CAP, "the question must land EXACTLY at the clamp"


@pytest.fixture(autouse=True)
def clean_chats(db_ready: None) -> Iterator[None]:
    """The send auto-saves a row per turn — truncate ``saved_chats``
    before and after the test so it starts from (and leaves) an empty
    deployment (the phase-80/103 autouse pattern)."""
    with SessionLocal() as db:
        db.execute(text("TRUNCATE saved_chats"))
        db.commit()
    yield
    with SessionLocal() as db:
        db.execute(text("TRUNCATE saved_chats"))
        db.commit()


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 owns the test loop)."""
    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 _seed_kb(mock_port: int) -> ImportSummary:
    """Deterministic KB: truncate the KB tables, import the fixture
    docs (needed for the grounded answer)."""
    with SessionLocal() as db:
        db.execute(text("TRUNCATE chunks, documents, query_log"))
        db.commit()
    summary = _run_in_thread(_import_fixtures(mock_port))
    assert summary is not None and summary.added == 13  # A9 formats (phase 47 added quadlet+j2)
    return summary


def _wait_chat_booted(page: Page) -> None:
    """Wait until app.js has FINISHED booting the chat page. The login
    helper returns on the URL change (navigation commit) — the page's
    module script may still be executing, and an ``input`` event
    dispatched before its top-level listener registrations land on a
    page whose listeners do not exist yet (the event is simply lost).
    ``#view-chat.chat-booted`` is added two frames after the boot
    settles (AFTER every top-level listener), so it is the "the app's
    JS is live" sentinel."""
    page.wait_for_function(
        "() => document.getElementById('view-chat')?."
        "classList.contains('chat-booted')",
        timeout=15_000,
    )
    expect(page.locator("#view-chat")).to_have_class(re.compile(r"\bchat-booted\b"))


def test_question_at_the_composer_clamp_sends_a_clean_turn(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    """L6 acceptance: a question typed to the FULL 4,000-char clamp
    (counter ``4000/4000 — character limit`` + ``.is-max``) sends — the
    embed step sends only the bounded 1200-char prefix to the model
    (unit-pinned), so the turn streams to ``done`` on the mock LLM:
    the user bubble carries the FULL 4,000-char question, the brain
    bubble carries the grounded mock marker, NO error banner (the
    pre-phase "couldn't reach the embedding model" death), and the
    input + counter clear."""
    _seed_kb(mock_llm)
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    _wait_chat_booted(page)

    counter = page.locator("#char-count")
    input_el = page.locator("#message-input")
    banner = page.locator("#kb-banner")
    expect(counter).to_be_hidden()
    expect(banner).to_be_hidden()

    # Type the full-clamp question: fill sets the value + dispatches
    # the input event (the counter path) — EXACTLY 4,000 chars.
    page.fill("#message-input", QUESTION)
    expect(input_el).to_have_value(QUESTION)
    expect(counter).to_be_visible(timeout=5_000)
    expect(counter).to_have_text("4000/4000 — character limit")
    expect(counter).to_have_class(re.compile("is-max"))

    # Send at the clamp: the bounded-prefix embed succeeds and the turn
    # streams to done — no error frame of any kind.
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble")).to_have_count(1, timeout=30_000)
    expect(page.locator(".msg.user .bubble")).to_have_text(QUESTION)
    brain = page.locator(".msg.brain .bubble").first
    expect(brain).to_contain_text(MOCK_ANSWER_MARKER, timeout=30_000)
    expect(page.locator(".msg.brain.is-deflected")).to_have_count(0)
    expect(banner).to_be_hidden()  # NO "couldn't reach the embedding model" death

    # Never stale: the turn cleared the input AND the counter, and the
    # send button recovered.
    expect(input_el).to_have_value("")
    expect(counter).to_be_hidden()
    expect(page.locator("#send-btn")).to_be_enabled()