brain-of-reese/tests/integration/test_admin_settings_live.py

"""Phase 168 (task 03): the end-to-end proof of "no restart", in-process.

After ``invalidate_settings()`` (the save-side wrapper), the NEXT
request behaves under the new value — pinned for the three settings
that are NOT covered by the cache clear alone or that prove it end
to end: the retrieval honesty gate (``relevance_threshold`` — the
per-use read, ``app/api/chat.py``'s ``plan_turn`` gate), the shared
``LLMClient`` (rebuilt: model + timeout from the new ``Settings``
snapshot, ``app/api/chat.py::get_llm``), and the chat concurrency
semaphore (``chat_max_concurrent``). Plus the kill-switch counterpart
(``BOR_SETTINGS_DB=0`` with rows present → env values are back) and
the ``scripts/``-consumer surface (``import_extension_set``), and the
phase-172 thinking level (``llm_chat_thinking_level`` — the value the
LLM layer reads per request via ``get_settings()``; the off switch is
live-settable, A2) and its phase-178 summary twin (task 02:
``llm_summary_thinking_level``, default ``""`` = off, A2).

The rows are inserted directly through the ``db`` session (the admin
API is task 04); the save itself is ``invalidate_settings()`` —
exactly what task 04's PUT/DELETE call after the write.

Real Postgres (``podman compose up -d db``); no LLM involved.

Requires:  podman compose up -d db
"""
from __future__ import annotations

import uuid
from collections.abc import Iterator
from datetime import UTC, datetime

import pytest
from sqlalchemy import text
from sqlalchemy.orm import Session

from app.api import chat as chat_api
from app.config import get_settings, invalidate_settings
from app.core import settings_overlay
from app.core.settings_overlay import register_invalidator
from app.models import Document
from app.rag.retriever import RetrievedChunk


@pytest.fixture(autouse=True)
def _clean_state(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> Iterator[None]:
    """A clean ``app_settings`` table + a fresh overlay/hook slate.

    ``reset_state_for_tests()`` clears the process-wide hook list (a
    prior suite's test may have wiped the hook ``app.main`` registered
    at import — re-wire what ``create_app()`` wires: the chat runtime
    reset), then the table is emptied and the switch is ON for the
    test. Teardown deletes the rows and invalidates (runs the reset
    hook — a test-built ``LLMClient``/semaphore snapshot never leaks
    into a later suite) + clears the cache; ``monkeypatch`` then
    restores ``BOR_SETTINGS_DB`` and the next resolution is the
    conftest-pinned env-only view.
    """
    settings_overlay.reset_state_for_tests()
    register_invalidator(chat_api.reset_runtime_caches)
    db.execute(text("DELETE FROM app_settings"))
    db.commit()
    monkeypatch.setenv("BOR_SETTINGS_DB", "1")
    invalidate_settings()
    yield
    db.execute(text("DELETE FROM app_settings"))
    db.commit()
    invalidate_settings()
    get_settings.cache_clear()


def _save(db: Session, key: str, value: str) -> None:
    """One upserted override row (the panel's Save, minus the API)."""
    db.execute(
        text(
            "INSERT INTO app_settings (key, value) VALUES (:k, :v)"
            " ON CONFLICT (key) DO UPDATE SET value = EXCLUDED.value"
        ),
        {"k": key, "v": value},
    )
    db.commit()


def _doc(title: str) -> Document:
    return Document(
        id=uuid.uuid4(),
        source="Homelab",
        path=f"{title.lower().replace(' ', '-')}.md",
        full_path="/tmp/doc.md",
        title=title,
        content=f"{title} content body for the gate pin",
        summary=None,
        content_hash="0" * 64,
        created_at=datetime(2024, 6, 15, 12, 0, 0, tzinfo=UTC),
    )


def _chunk(doc: Document, score: float, cosine: float) -> RetrievedChunk:
    """A non-FTS candidate: *cosine* is the honesty-gate input."""
    return RetrievedChunk(
        chunk_id=uuid.uuid4(),
        position=0,
        content=doc.content[:32],
        score=score,
        document=doc,
        cosine=cosine,
    )


# ---------------------------------------------------------------------------
# the per-use read: the A8 gate behaves under the saved threshold
# ---------------------------------------------------------------------------


def test_relevance_threshold_db_value_bites_in_the_gate(db: Session) -> None:
    base = get_settings().relevance_threshold
    if base >= 0.95:
        pytest.skip("env threshold too close to 1.0 to bracket a DB override")
    # A DB value over the base; a cosine BETWEEN them — grounded under
    # the base, deflected under the DB value (no FTS: fts_hits = 0).
    db_value = min(base + 0.2, 0.9)
    cosine = (base + db_value) / 2
    chunk = _chunk(_doc("Gate Pin"), score=0.1, cosine=cosine)
    assert chat_api.plan_turn([chunk], get_settings()).deflected is False
    _save(db, "relevance_threshold", str(db_value))
    invalidate_settings()
    assert get_settings().relevance_threshold == db_value
    # the SAME chunk, the SAME function, the overlay-fed settings —
    # the gate now deflects (no process restart in between)
    assert chat_api.plan_turn([chunk], get_settings()).deflected is True


# ---------------------------------------------------------------------------
# the LLM client snapshot: Save swaps the shared LLMClient
# ---------------------------------------------------------------------------


def test_llm_client_rebuilt_from_saved_values(db: Session) -> None:
    _save(db, "llm_chat_model", "gpt-test")
    _save(db, "llm_timeout", "7")
    invalidate_settings()
    llm = chat_api.get_llm()
    # the rebuilt client holds the DB-overridden snapshot…
    assert llm.settings.llm_chat_model == "gpt-test"
    assert llm.settings.llm_timeout == 7.0
    # …and its AsyncOpenAI transport was built from it (base_url +
    # the timeout's connect value — the way llm.py's __init__ builds
    # it; the openai client enforces a trailing slash on base_url)
    assert llm._client.base_url == (  # pyright: ignore[reportPrivateUsage]
        llm.settings.llm_base_url.rstrip("/") + "/"
    )
    assert llm._client._client.timeout.connect == 7.0  # pyright: ignore[reportPrivateUsage]


def test_llm_client_repoints_on_the_next_save(db: Session) -> None:
    _save(db, "llm_chat_model", "gpt-first")
    invalidate_settings()
    assert chat_api.get_llm().settings.llm_chat_model == "gpt-first"
    # the NEXT save re-points the singleton (not just the first)
    _save(db, "llm_chat_model", "gpt-second")
    invalidate_settings()
    llm = chat_api.get_llm()
    assert llm.settings.llm_chat_model == "gpt-second"


# ---------------------------------------------------------------------------
# the chat thinking level: save/reset resolve the live value
# (phase 178, task 01 — the phase-172 test, renamed)
# ---------------------------------------------------------------------------


def test_llm_chat_thinking_level_live_apply_no_restart(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Phase 178 (task 01): the chat thinking level follows the overlay
    live — a save (the PUT's write, minus the API: ``_save`` +
    ``invalidate_settings()`` is exactly what task 04's PUT/DELETE
    call after the write) resolves
    ``get_settings().llm_chat_thinking_level`` WITHOUT a restart (the
    proof the LLM layer — task 03 reads the setting per request via
    ``get_settings()`` — picks the override up live), the EMPTY value
    resolves live too (the off switch is live-settable, A2/A4), and a
    reset (the DELETE) returns the env value.
    """
    # A deterministic base (machine-independent, the kill-switch test's
    # idiom): the code default, no row in the table.
    monkeypatch.delenv("BOR_LLM_CHAT_THINKING_LEVEL", raising=False)
    invalidate_settings()
    assert get_settings().llm_chat_thinking_level == "low"
    _save(db, "llm_chat_thinking_level", "high")
    invalidate_settings()
    assert get_settings().llm_chat_thinking_level == "high"  # NO restart
    # The off switch is live-settable too (A2/A4): the empty value
    # resolves through the overlay, not stripped or coerced.
    _save(db, "llm_chat_thinking_level", "")
    invalidate_settings()
    assert get_settings().llm_chat_thinking_level == ""
    # The reset returns the env value (no process restart in between —
    # the LLM layer re-reads per request, task 03).
    db.execute(
        text("DELETE FROM app_settings WHERE key = 'llm_chat_thinking_level'")
    )
    db.commit()
    invalidate_settings()
    assert get_settings().llm_chat_thinking_level == "low"


# ---------------------------------------------------------------------------
# the summary thinking level: save/reset resolve the live value
# (phase 178, task 02 — the chat twin's summary counterpart)
# ---------------------------------------------------------------------------


def test_llm_summary_thinking_level_live_apply_no_restart(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Phase 178 (task 02): the summary thinking level follows the
    overlay live — a save (the PUT's write, minus the API: ``_save`` +
    ``invalidate_settings()`` is exactly what task 04's PUT/DELETE call
    after the write) resolves ``get_settings().llm_summary_thinking_level``
    WITHOUT a restart (the proof the LLM layer — task 03 reads the
    setting per request via ``get_settings()`` — picks the override up
    live), the EMPTY value resolves live too (the off switch is
    live-settable, A2/A4), and a reset (the DELETE) returns the env
    value (``""`` — the code default; the chat twin's reset returns
    ``"low"``, the two levels are independent).
    """
    # A deterministic base (machine-independent, the kill-switch test's
    # idiom): the code default, no row in the table.
    monkeypatch.delenv("BOR_LLM_SUMMARY_THINKING_LEVEL", raising=False)
    invalidate_settings()
    assert get_settings().llm_summary_thinking_level == ""
    _save(db, "llm_summary_thinking_level", "high")
    invalidate_settings()
    assert get_settings().llm_summary_thinking_level == "high"  # NO restart
    # The off switch is live-settable too (A2/A4): the empty value
    # resolves through the overlay, not stripped or coerced.
    _save(db, "llm_summary_thinking_level", "")
    invalidate_settings()
    assert get_settings().llm_summary_thinking_level == ""
    # The reset returns the env value (no process restart in between —
    # the LLM layer re-reads per request, task 03).
    db.execute(
        text("DELETE FROM app_settings WHERE key = 'llm_summary_thinking_level'")
    )
    db.commit()
    invalidate_settings()
    assert get_settings().llm_summary_thinking_level == ""


# ---------------------------------------------------------------------------
# the chat concurrency semaphore follows the saved cap
# ---------------------------------------------------------------------------


def test_chat_semaphore_follows_saved_cap(db: Session) -> None:
    base_cap = get_settings().chat_max_concurrent
    first = 3 if base_cap != 3 else 5
    _save(db, "chat_max_concurrent", str(first))
    invalidate_settings()
    assert get_settings().chat_max_concurrent == first
    sem = chat_api._get_chat_semaphore()
    assert sem._value == first  # pyright: ignore[reportPrivateUsage]
    # the next save re-points the semaphore too
    second = 5 if first == 3 else 3
    _save(db, "chat_max_concurrent", str(second))
    invalidate_settings()
    rebuilt = chat_api._get_chat_semaphore()
    assert rebuilt is not sem
    assert rebuilt._value == second  # pyright: ignore[reportPrivateUsage]


# ---------------------------------------------------------------------------
# the kill switch: rows present, switch off → the env values are back
# ---------------------------------------------------------------------------


def test_kill_switch_returns_env_values(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    base = get_settings().input_placeholder
    _save(db, "input_placeholder", "DB-WINS-PLACEHOLDER")
    invalidate_settings()
    assert get_settings().input_placeholder == "DB-WINS-PLACEHOLDER"
    monkeypatch.setenv("BOR_SETTINGS_DB", "0")
    invalidate_settings()
    assert get_settings().input_placeholder == base


# ---------------------------------------------------------------------------
# the scripts/ consumer: the importer reads the same overlay
# ---------------------------------------------------------------------------


def test_import_extensions_override_reaches_script_consumer(db: Session) -> None:
    base = get_settings().import_extension_set
    # a REAL change — guard against a dev .env that already carries
    # exactly this set (a no-op would still pass the final assert)
    if base == {".md", ".txt", ".csv"}:
        saved, expect = "md,txt,csv,ini", {".md", ".txt", ".csv", ".ini"}
    else:
        saved, expect = "md,txt,csv", {".md", ".txt", ".csv"}
    _save(db, "import_extensions", saved)
    invalidate_settings()
    assert get_settings().import_extension_set == expect