"""Integration: the admin settings panel's read/write surface (phase 168,
task 04) — ``/api/admin/settings`` GET / PUT ``/{key}`` / DELETE
``/{key}`` / DELETE all, driven through the real app (TestClient keeps
the cookie jar — the house ``test_ui_settings_api`` /
``test_tokens_api`` pattern).

The pins (00_phase, Testing & Quality):

* the auth matrix — anonymous AND a signed-in token USER get 403 on ALL
  four routes (the router-wide ``require_admin`` closes the surface on
  every method), the admin 200s on all four;
* the shape — ``items`` length == ``len(Settings.model_fields)`` (75),
  groups in ``GROUPS`` order (the stable order the E2E pins against),
  ``totals.count`` / ``overridden`` correct, ``overlay_enabled`` true;
  on an empty table a field whose ``BOR_*`` var the test env sets
  reports ``source="env"``, an untouched one ``source="default"`` and
  none reports ``"db"``;
* write → live — a saved ``relevance_threshold`` is in
  ``get_settings()`` with NO restart (the cache clear + task-03 hooks
  are the whole job), the row is in the table with a non-null
  ``updated_at``, and the DB value reaches the ANONYMOUS
  ``/api/config`` endpoint through the same overlay;
* errors — unknown key 404; the two LOCKED A3 keys 422 naming the env
  var; a bad shape 422 naming the field with NOTHING stored; a
  cross-field pair that only breaks in combination (the second PUT 422s
  and the first row is unchanged);
* masking (LOCKED A4) — a stored secret reports ``masked``/``has_value``
  only, the plaintext appears NOWHERE in the raw response text, a blank
  secret PUT 422s, and a DELETE clears it;
* reset — a DELETE ``/{key}`` restores the env value (idempotent);
  DELETE ``""`` clears everything (``{"cleared": 3}``);
* the kill switch (D6) — ``BOR_SETTINGS_DB=0``: ``overlay_enabled``
  false, a PUT still stores the row, ``get_settings()`` still reports
  the env value — the switch disables the mechanism, not the panel;
* the byte budget — the whole catalogue stays under the phase-167 INFO
  bar (64 KB), so it never floods the log;
* fail-soft boot — a malformed row inserted DIRECTLY into the table
  (bypassing the API's 422 gate) never bricks: a fresh ``create_app()``
  runs with it in the table, the row is skipped with a logged reason,
  the rest of the table still applies, and ``/api/health`` is 200.

The module's teardown leaves NO row behind (the same discipline
``test_admin_theme_tab.py`` applies to ``ui_settings`` — a surviving
row would retune every later suite through the overlay).

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

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

import logging
from collections.abc import Iterator

import pytest
from fastapi.testclient import TestClient
from sqlalchemy import text
from sqlalchemy.orm import Session

from app.api import chat as chat_api
from app.config import Settings, get_settings, invalidate_settings
from app.core import settings_overlay
from app.core.settings_catalog import CATALOG, GROUPS
from app.core.settings_overlay import register_invalidator
from app.main import app as fastapi_app
from app.main import create_app
from tests.conftest import ADMIN_PASSWORD

API = "/api/admin/settings"


@pytest.fixture(autouse=True)
def clean_state(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> Iterator[None]:
    """A clean ``app_settings`` table + the overlay switch ON + a fresh
    overlay/hook slate (the ``test_admin_settings_live`` idiom: reset
    the process-wide hook list and re-wire what ``create_app()``
    wires, so a save in this module runs the chat runtime reset).
    Teardown deletes the rows + invalidates + clears the cache — NO row
    may survive this module (a surviving row would retune every later
    suite through the overlay).
    """
    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 _admin_client() -> TestClient:
    """A fresh client signed in as the admin (the ``_admin_client``
    pattern from ``test_ui_settings_api``)."""
    c = TestClient(fastapi_app)
    r = c.post("/api/login", json={"password": ADMIN_PASSWORD})
    assert r.status_code == 204, f"admin login failed: {r.status_code} {r.text}"
    return c


def _token_user_client(admin: TestClient, anon: TestClient) -> TestClient:
    """A signed-in token USER (role ``"user"`` — issue the token the way
    ``test_tokens_api`` does): the only non-admin identity, 403 on this
    surface on every method (the phase-79 token matrix contract)."""
    r = admin.post("/api/tokens", json={"label": "alice"})
    assert r.status_code == 201, r.text
    token = r.json()["token"]
    assert anon.post("/api/token-auth", json={"token": token}).status_code == 204
    return anon


def _item(body: dict, key: str) -> dict:
    """One catalogue item by key (the GET body's ``items`` list)."""
    for item in body["items"]:
        if item["key"] == key:
            return item
    raise AssertionError(f"catalogue item missing: {key}")


def test_auth_matrix_all_four_routes(client: TestClient, db: Session) -> None:
    """Anonymous AND token user: 403 ``admin only`` on ALL four routes
    (the router-wide dependency closes the surface on every method);
    the admin passes on all four."""
    admin = _admin_client()
    token_user = _token_user_client(admin, client)

    for caller in (client, token_user):
        r = caller.get(API)
        assert r.status_code == 403 and r.json() == {"detail": "admin only"}
        r = caller.put(f"{API}/relevance_threshold", json={"value": "0.5"})
        assert r.status_code == 403 and r.json() == {"detail": "admin only"}
        r = caller.delete(f"{API}/relevance_threshold")
        assert r.status_code == 403 and r.json() == {"detail": "admin only"}
        r = caller.delete(API)
        assert r.status_code == 403 and r.json() == {"detail": "admin only"}

    r = admin.get(API)
    assert r.status_code == 200
    r = admin.put(f"{API}/top_n_docs", json={"value": "3"})
    assert r.status_code == 200, r.text
    r = admin.delete(f"{API}/top_n_docs")
    assert r.status_code == 200, r.text
    r = admin.delete(API)
    assert r.status_code == 200, r.text
    assert r.json() == {"cleared": 0}
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 0


def test_catalogue_shape_and_sources_on_empty_table(admin_client) -> None:
    """The whole catalogue, grouped and stable: 75 items (exactly
    ``Settings.model_fields``), groups in ``GROUPS`` order (each group a
    contiguous block, the block order = ``GROUPS``), ``totals`` correct,
    ``overlay_enabled`` true. On an empty table: the env-var-set field
    reports ``"env"``, the untouched one ``"default"`` and NOTHING
    reports ``"db"``."""
    r = admin_client.get(API)
    assert r.status_code == 200, r.text
    body = r.json()
    items = body["items"]
    assert len(items) == len(Settings.model_fields)
    assert body["totals"] == {
        "count": len(Settings.model_fields),
        "overridden": 0,
    }
    assert body["overlay_enabled"] is True

    # The stable order: each group a contiguous block, block order GROUPS.
    groups_seen: list[str] = []
    for item in items:
        assert item["group"] in GROUPS
        if not groups_seen or groups_seen[-1] != item["group"]:
            groups_seen.append(item["group"])
    assert groups_seen == [g for g in GROUPS if g in groups_seen]
    assert len(groups_seen) == len(set(groups_seen))
    # Every item carries the full contract (the panel generates from it).
    for item in items:
        assert set(item) == {
            "key", "env_var", "group", "label", "type", "secret",
            "restart_required", "overridable", "source", "value",
            "masked", "has_value", "has_override", "db_value", "default",
        }
        assert item["env_var"] == "BOR_" + item["key"].upper()
        assert item["source"] in ("db", "env", "default")

    # Empty table: env / default / never db.
    sources = {item["key"]: item["source"] for item in items}
    assert "db" not in sources.values()
    assert sources["input_placeholder"] == "env"  # BOR_… set in tests/conftest.py
    assert sources["docs_work_dir"] == "default"  # no BOR_… in the test env
    assert sources["relevance_threshold"] == "env"  # pinned 0.30 in conftest


def test_write_is_live_without_restart(admin_client, db: Session) -> None:
    """Write → live (no restart): the saved value is in ``get_settings()``
    in the SAME process, the row is in the table with a non-null
    ``updated_at``, the item reports ``source="db"`` and
    ``totals.overridden == 1`` — and the DB value reaches the ANONYMOUS
    ``/api/config`` endpoint through the same overlay (the DB-over-env
    rule is deployment-wide, not panel-local)."""
    assert get_settings().relevance_threshold == 0.30  # the conftest env value

    r = admin_client.put(f"{API}/relevance_threshold", json={"value": "0.5"})
    assert r.status_code == 200, r.text
    body = r.json()
    assert body["key"] == "relevance_threshold"
    assert body["source"] == "db"
    assert body["has_override"] is True
    assert body["db_value"] == "0.5"
    assert get_settings().relevance_threshold == 0.5  # NO restart (task 03)

    row = db.execute(
        text("SELECT value, updated_at FROM app_settings WHERE key = 'relevance_threshold'")
    ).first()
    assert row is not None
    assert row[0] == "0.5"
    assert row[1] is not None  # the server-side now()

    r = admin_client.get(API)
    assert r.json()["totals"]["overridden"] == 1

    # Visible through the public config endpoint (no auth) — the same
    # overlay retunes every consumer at once (D2).
    anon = TestClient(fastapi_app)
    r = anon.get("/api/config")
    assert r.status_code == 200
    assert r.json()["input_placeholder"] == "Ask me anything…"
    r = admin_client.put(f"{API}/input_placeholder", json={"value": "Type your question…"})
    assert r.status_code == 200, r.text
    r = anon.get("/api/config")
    assert r.status_code == 200
    assert r.json()["input_placeholder"] == "Type your question…"


def test_put_errors_404_and_422(admin_client, db: Session) -> None:
    """The write-path guards (LOCKED A5, A3, A4): unknown key 404; the
    two A3 keys 422 naming the env var; a bad shape 422 naming the FIELD
    with NOTHING stored; a cross-field pair that only breaks in
    combination — the second PUT 422s and the first row is unchanged."""
    r = admin_client.put(f"{API}/bogus_key", json={"value": "1"})
    assert r.status_code == 404
    assert r.json() == {"detail": "Unknown setting bogus_key"}

    r = admin_client.put(f"{API}/database_url", json={"value": "postgresql://x"})
    assert r.status_code == 422
    assert "BOR_DATABASE_URL is not settable from the database" in r.json()["detail"]
    r = admin_client.put(f"{API}/embedding_dim", json={"value": "384"})
    assert r.status_code == 422
    assert "BOR_EMBEDDING_DIM is not settable from the database" in r.json()["detail"]

    # A bad shape: names the field, stores nothing.
    r = admin_client.put(f"{API}/relevance_threshold", json={"value": "abc"})
    assert r.status_code == 422
    assert "relevance_threshold" in r.json()["detail"]
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 0

    # The one list[str] field (K2): a malformed JSON array is a 422
    # naming the field (the _coerce ValueError branch), nothing stored.
    r = admin_client.put(f"{API}/suggestions", json={"value": "[not json"})
    assert r.status_code == 422
    assert "suggestions" in r.json()["detail"]
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 0
    # A well-formed JSON array stores fine (the JSON round-trip works).
    r = admin_client.put(
        f"{API}/suggestions", json={"value": '["How do I deploy gitea?"]'}
    )
    assert r.status_code == 200, r.text
    assert r.json()["db_value"] == '["How do I deploy gitea?"]'
    assert db.execute(
        text("SELECT value FROM app_settings WHERE key = 'suggestions'")
    ).scalar() == '["How do I deploy gitea?"]'
    # (Clean up the row — the cross-field pin below counts rows.)
    assert admin_client.delete(f"{API}/suggestions").status_code == 200

    # The cross-field pair (only breaks in combination): store
    # relevance_threshold=0.2 (valid alone), then lexical_support_floor=0.9
    # — above the DB-overridden threshold: the SECOND PUT 422s and the
    # first row is unchanged.
    r = admin_client.put(f"{API}/relevance_threshold", json={"value": "0.2"})
    assert r.status_code == 200, r.text
    r = admin_client.put(f"{API}/lexical_support_floor", json={"value": "0.9"})
    assert r.status_code == 422
    assert "lexical_support_floor" in r.json()["detail"]
    value = db.execute(
        text("SELECT value FROM app_settings WHERE key = 'relevance_threshold'")
    ).scalar()
    assert value == "0.2"  # the first row is unchanged
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 1
    # The failed write did not disturb the live view.
    assert get_settings().relevance_threshold == 0.2


def test_secrets_are_masked_and_write_only(admin_client, db: Session) -> None:
    """LOCKED A4: a stored secret reports ``masked``/``has_value`` only —
    ``value``/``db_value`` are ``None`` and the plaintext appears NOWHERE
    in the raw response text (asserted on ``response.text``, not the
    parsed model); a blank secret PUT 422s (a self-lockout — DELETE is
    the explicit clear); a DELETE clears it."""
    db.execute(
        text("INSERT INTO app_settings (key, value) VALUES ('llm_api_key', :v)"),
        {"v": "sk-secret-12345"},
    )
    db.commit()
    invalidate_settings()

    r = admin_client.get(API)
    assert r.status_code == 200
    item = _item(r.json(), "llm_api_key")
    assert item["masked"] is True
    assert item["value"] is None
    assert item["db_value"] is None
    assert item["has_value"] is True  # a non-empty value is in effect
    assert item["has_override"] is True
    assert item["source"] == "db"
    assert item["default"] == ""  # masked: the code default is never shown
    assert "sk-secret-12345" not in r.text  # NOWHERE in the raw body
    # The other write-only fields are masked too (set in the test env).
    for key in ("admin_password", "session_secret", "database_url"):
        other = _item(r.json(), key)
        assert other["masked"] is True and other["value"] is None

    # A blank secret PUT is a 422 (an empty API key / session secret
    # would self-lockout — DELETE is the explicit clear).
    r = admin_client.put(f"{API}/llm_api_key", json={"value": "   "})
    assert r.status_code == 422
    assert "BOR_LLM_API_KEY must not be blank" in r.json()["detail"]
    assert db.execute(
        text("SELECT value FROM app_settings WHERE key = 'llm_api_key'")
    ).scalar() == "sk-secret-12345"  # unchanged

    # A DELETE clears the row — the effective value falls back to the
    # env value (whatever this deployment's env/.env provides — the
    # test only pins that it is NOT the stored secret and that the
    # item reports the fallback state).
    r = admin_client.delete(f"{API}/llm_api_key")
    assert r.status_code == 200
    assert r.json()["source"] == "default"  # no BOR_LLM_API_KEY in the PROCESS env
    assert r.json()["has_override"] is False
    assert r.json()["value"] is None
    assert r.json()["has_value"] == bool(get_settings().llm_api_key)
    assert get_settings().llm_api_key != "sk-secret-12345"  # the override is gone
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 0


def test_reset_to_env_and_clear_all(admin_client, db: Session) -> None:
    """Reset semantics: DELETE ``/{key}`` deletes the row (idempotent — a
    double Reset is a success, not a 404) and the env value wins again;
    DELETE ``""`` clears every row (``{"cleared": 3}``) and
    ``totals.overridden`` is back to 0."""
    r = admin_client.put(f"{API}/relevance_threshold", json={"value": "0.5"})
    assert r.status_code == 200, r.text
    assert get_settings().relevance_threshold == 0.5

    r = admin_client.delete(f"{API}/relevance_threshold")
    assert r.status_code == 200, r.text
    assert r.json()["source"] == "env"  # BOR_RELEVANCE_THRESHOLD is set (0.30)
    assert r.json()["has_override"] is False
    assert get_settings().relevance_threshold == 0.30  # the env value wins again
    # Idempotent: the double Reset is a success, not a 404.
    r = admin_client.delete(f"{API}/relevance_threshold")
    assert r.status_code == 200, r.text

    # Three rows, then "Clear all overrides".
    for key, value in (("relevance_threshold", "0.5"), ("llm_retries", "7"), ("top_n_docs", "3")):
        r = admin_client.put(f"{API}/{key}", json={"value": value})
        assert r.status_code == 200, r.text
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 3

    r = admin_client.delete(API)
    assert r.status_code == 200
    assert r.json() == {"cleared": 3}
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 0
    assert get_settings().relevance_threshold == 0.30  # env values win again
    r = admin_client.get(API)
    assert r.json()["totals"]["overridden"] == 0


def test_kill_switch_disables_the_mechanism_not_the_panel(
    admin_client, db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """D6: with ``BOR_SETTINGS_DB=0`` the catalogue reports
    ``overlay_enabled`` false (the panel shows a banner instead of
    pretending a save took effect), a PUT STILL stores the row, and
    ``get_settings()`` still reports the ENV value — the switch disables
    the mechanism, not the panel."""
    r = admin_client.put(f"{API}/relevance_threshold", json={"value": "0.5"})
    assert r.status_code == 200, r.text
    assert get_settings().relevance_threshold == 0.5  # the switch was ON
    # Deterministic env base for the pin (machine-independent):
    monkeypatch.setenv("BOR_LLM_RETRIES", "3")
    invalidate_settings()

    monkeypatch.setenv("BOR_SETTINGS_DB", "0")
    invalidate_settings()

    r = admin_client.get(API)
    assert r.status_code == 200
    assert r.json()["overlay_enabled"] is False
    assert r.json()["totals"]["overridden"] == 0  # no row is IN EFFECT
    item = _item(r.json(), "relevance_threshold")
    assert item["source"] == "env"  # the row exists but is not in effect
    assert item["has_override"] is True
    assert item["db_value"] == "0.5"  # the stored string is visible (non-secret)
    assert get_settings().relevance_threshold == 0.30  # the env value stands

    # The panel stays writable: the PUT stores the row …
    r = admin_client.put(f"{API}/llm_retries", json={"value": "7"})
    assert r.status_code == 200, r.text
    assert db.execute(text("SELECT count(*) FROM app_settings")).scalar() == 2
    # … but the env value stays in effect while the switch is off.
    assert get_settings().llm_retries == 3  # the env value (pinned 3 above)


def test_catalogue_stays_under_the_byte_budget(admin_client) -> None:
    """The whole catalogue stays under the phase-167 INFO bar (64 KB —
    ``BOR_LOG_LARGE_RESPONSE_BYTES``), so ``GET /api/admin/settings``
    never floods the log (75 items ≈ 20 KB; the audit script re-verifies
    the 256 KB budget in task 06)."""
    r = admin_client.get(API)
    assert r.status_code == 200
    assert len(r.content) < 65_536


def test_unknown_delete_is_a_404(admin_client) -> None:
    """A DELETE of an UNKNOWN SETTING is a 404 like the PUT (a typo in
    the key is a client bug; the idempotency pin is about a known key
    whose row is already gone — the double Reset in
    ``test_reset_to_env_and_clear_all``)."""
    r = admin_client.delete(f"{API}/bogus_key")
    assert r.status_code == 404
    assert r.json() == {"detail": "Unknown setting bogus_key"}


def test_write_log_lines_carry_never_the_value(
    admin_client, caplog: pytest.LogCaptureFixture
) -> None:
    """AGENTS rule 10 / A4: one line per write (``settings action=…`` on
    the ``app.api.admin_settings`` logger) carrying the key and the
    action — NEVER the value (a secret write must not leak the
    plaintext into the log)."""
    caplog.set_level(logging.INFO, logger="app.api.admin_settings")

    r = admin_client.put(f"{API}/llm_api_key", json={"value": "sk-log-secret-xyz"})
    assert r.status_code == 200, r.text
    set_lines = [rec.message for rec in caplog.records
                if rec.name == "app.api.admin_settings"]
    assert "settings action=set key=llm_api_key status=200" in set_lines
    assert "sk-log-secret-xyz" not in "\n".join(set_lines)

    caplog.clear()
    r = admin_client.delete(f"{API}/llm_api_key")
    assert r.status_code == 200
    assert "settings action=clear key=llm_api_key" in [
        rec.message for rec in caplog.records
        if rec.name == "app.api.admin_settings"
    ]

    caplog.clear()
    admin_client.put(f"{API}/top_n_docs", json={"value": "3"})
    r = admin_client.delete(API)
    assert r.status_code == 200 and r.json() == {"cleared": 1}
    assert "settings action=clear_all count=1" in [
        rec.message for rec in caplog.records
        if rec.name == "app.api.admin_settings"
    ]


def test_bad_row_inserted_directly_never_bricks_boot(
    db: Session, caplog: pytest.LogCaptureFixture
) -> None:
    """Completion criterion (00_phase, item 5): a malformed row written
    straight into ``app_settings`` (bypassing the API's 422 gate — the
    operator SQL, the failed migration) must never brick boot. A FRESH
    ``create_app()`` — the full boot path: fail-loud auth gate, resolver
    prime, middleware wiring — runs with the bad row present, the row is
    SKIPPED with a logged reason, the rest of the table still applies,
    and ``/api/health`` is 200 (A5)."""
    # One bad row (the API's 422 gate would refuse it) + one good row:
    # the bad one is skipped, the good one stands.
    db.execute(text(
        "INSERT INTO app_settings (key, value)"
        " VALUES ('relevance_threshold', 'not-a-number')"
    ))
    db.execute(text(
        "INSERT INTO app_settings (key, value) VALUES ('top_n_docs', '3')"
    ))
    db.commit()
    caplog.set_level(logging.ERROR, logger="app.settings")

    # The boot path with the bad row in the table — must not raise.
    app = create_app()

    s = get_settings()
    env_only = Settings()  # the env value the skipped key falls back to
    assert s.relevance_threshold == env_only.relevance_threshold
    assert s.top_n_docs == 3  # the rest of the table still applies
    assert any(
        "settings override ignored" in rec.message
        and "relevance_threshold" in rec.message
        for rec in caplog.records
    )

    r = TestClient(app).get("/api/health")
    assert r.status_code == 200


def test_catalog_covers_every_settings_field(admin_client) -> None:
    """The catalogue's keys are exactly ``Settings.model_fields`` (the
    API-level face of the unit completeness pin — a new setting cannot
    be missing from the panel's data)."""
    r = admin_client.get(API)
    assert r.status_code == 200
    assert {item["key"] for item in r.json()["items"]} == set(Settings.model_fields)
    assert set(CATALOG) == set(Settings.model_fields)