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

"""Integration: the phase-173 (task 04, C3) legacy-credentials
migration, end-to-end against the real ``app_settings`` table.

The shape (the 00_phase / task-04 pins):

* seed env ``BOR_DOCS_REPO=https://u:pass@host/r.git`` (no DB rows)
  → run the migration (the direct call — the ``create_app()`` wiring
  is covered by the unit seam in ``test_main.py``) → the migration
  returns ``True`` and the three rows land in ``app_settings``
  (clean repo / ``docs_user`` / ``docs_token``);
* DB rows SHADOW the env — the effective settings resolve the clean
  URL + the credentials FROM the DB (the env value still embeds the
  credentials, ``.env`` is never rewritten: the process env is
  untouched by the migration);
* idempotent — a second run is a no-op (``False``, the rows
  byte-identical);
* the settings API reports the clean ``docs_repo`` (``source="db"``)
  and the ``docs_token`` masked (``secret=true``, ``value=null``,
  ``has_value=true``) with the token text NOWHERE in the raw body —
  the leak is gone from the page.

The module's teardown leaves NO row behind (the ``test_admin_settings_
api`` discipline — 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 os
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 get_settings, invalidate_settings
from app.core import settings_overlay
from app.core.settings_migrate import migrate_legacy_docs_creds
from app.core.settings_overlay import register_invalidator, resolve_settings
from app.main import app as fastapi_app
from tests.conftest import ADMIN_PASSWORD

API = "/api/admin/settings"

#: The legacy value the migration splits (the production shape — the
#: token is distinctive so the "absent from the raw body" pin cannot
#: false-positive on a catalogue label).
_LEGACY = "https://u:tok-legacy-123@host/r.git"


@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_api`` idiom:
    reset the process-wide hook list and re-wire what
    ``create_app()`` wires). 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")
    monkeypatch.setenv("BOR_DOCS_REPO", "")
    invalidate_settings()
    get_settings.cache_clear()
    yield
    db.execute(text("DELETE FROM app_settings"))
    db.commit()
    invalidate_settings()
    get_settings.cache_clear()
    settings_overlay.reset_state_for_tests()


def _table(db: Session) -> dict[str, str]:
    """The whole ``app_settings`` table (the display fact, never a
    query surface — one SELECT)."""
    return {
        key: value
        for key, value in db.execute(
            text("SELECT key, value FROM app_settings")
        )
    }


def _admin_client() -> TestClient:
    """A fresh client signed in as the admin (the ``_admin_client``
    pattern from ``test_ui_settings_api``)."""
    client = TestClient(fastapi_app)
    r = client.post("/api/login", json={"password": ADMIN_PASSWORD})
    assert r.status_code == 204, f"admin login failed: {r.status_code}"
    return client


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_legacy_env_is_split_into_db_rows(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """The end-to-end shape: seed env (no DB rows) → migration runs →
    the three rows land, the effective settings resolve the clean URL
    + the credentials FROM THE DB (the rows shadow the env), the env
    is untouched (``.env`` is never rewritten), and the second run is
    a no-op (idempotent)."""
    monkeypatch.setenv("BOR_DOCS_REPO", _LEGACY)
    assert _table(db) == {}  # no DB rows (the fixture's clean slate)

    assert migrate_legacy_docs_creds() is True

    # the three rows — the clean repo + user + token, and NOTHING
    # else (the leak class dies: the repo row no longer carries the
    # credentials).
    rows = _table(db)
    assert rows == {
        "docs_repo": "https://host/r.git",
        "docs_user": "u",
        "docs_token": "tok-legacy-123",
    }

    # the effective settings resolve FROM THE DB (invalidate first —
    # the module import primed the cache before this module's rows):
    # the clean URL shadows the credentials-bearing env value.
    invalidate_settings()
    effective = resolve_settings()
    assert effective.docs_repo == "https://host/r.git"
    assert effective.docs_user == "u"
    assert effective.docs_token == "tok-legacy-123"

    # the env is untouched — the migration never rewrites the env
    # (``.env`` stays the base; the DB rows shadow it).
    assert os.environ["BOR_DOCS_REPO"] == _LEGACY

    # idempotent: the ``docs_token`` row is present now — a second
    # run is a no-op, the rows byte-identical.
    assert migrate_legacy_docs_creds() is False
    assert _table(db) == rows


def test_migrated_values_are_masked_on_the_settings_api(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Completion criterion (the leak is gone from the page): after a
    (b)-shape migration the settings API reports the clean
    ``docs_repo`` (``source="db"``) + ``docs_token``
    ``secret=true`` / ``value=null`` / ``has_value=true`` (masked)
    with the token text NOWHERE in the raw response body."""
    monkeypatch.setenv("BOR_DOCS_REPO", _LEGACY)
    assert migrate_legacy_docs_creds() is True
    invalidate_settings()

    admin = _admin_client()
    r = admin.get(API)
    assert r.status_code == 200, r.text

    repo = _item(r.json(), "docs_repo")
    assert repo["value"] == "https://host/r.git"  # the clean URL
    assert repo["source"] == "db"  # the DB row is in effect
    assert repo["db_value"] == "https://host/r.git"

    token = _item(r.json(), "docs_token")
    assert token["secret"] is True
    assert token["masked"] is True
    assert token["value"] is None  # write-only: never the value
    assert token["db_value"] is None  # a masked row never exposes text
    assert token["has_value"] is True  # a value IS in effect
    assert token["has_override"] is True  # the DB row
    assert token["source"] == "db"

    user = _item(r.json(), "docs_user")
    assert user["value"] == "u"
    assert user["source"] == "db"

    # the core pin: the token text is NOWHERE in the raw body (the
    # leak class this phase kills — asserted on response.text, not
    # the parsed model; the value is distinctive so the substring
    # check cannot false-positive on a catalogue label).
    assert "tok-legacy-123" not in r.text


def test_migration_is_a_noop_for_a_clean_env(
    db: Session, monkeypatch: pytest.MonkeyPatch
) -> None:
    """The no-op shape end-to-end: a clean env URL (the pre-phase
    state) → ``False``, the table stays empty (nothing half-
    migrates, nothing written)."""
    monkeypatch.setenv("BOR_DOCS_REPO", "https://host/r.git")
    assert migrate_legacy_docs_creds() is False
    assert _table(db) == {}
    invalidate_settings()
    assert resolve_settings().docs_repo == "https://host/r.git"