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

"""Integration: the auth surface (phase 16) + the public-API regression
guards.

Covers the full login/logout lifecycle against the real app (TestClient
keeps the cookie jar): wrong password → 401 + still-gated; correct →
204 + cookie → admin everywhere gated; logout → 403 again. And the
**anonymous** guarantees that phase 16 must not break: the document
viewer stays public (soft rule) and ``POST /api/chat`` still streams.

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

import asyncio
from collections.abc import Iterator
from pathlib import Path

import pytest
from fastapi.testclient import TestClient
from sqlalchemy import text
from test_chat_api import FakeRagLLM, _stream_chat

from app.api import chat as chat_api
from app.main import app as fastapi_app
from app.models import Document
from app.rag.importer import import_sources
from tests.conftest import ADMIN_PASSWORD

FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "docs"
QUESTION = "How is my Kubernetes cluster set up?"


@pytest.fixture(autouse=True)
def clean_tables(db) -> Iterator[None]:
    """Docs + steering + query log are global state: reset around tests."""
    db.execute(text("TRUNCATE chunks, documents, query_log, steering_notes"))
    db.commit()
    yield
    db.execute(text("TRUNCATE chunks, documents, query_log, steering_notes"))
    db.commit()


@pytest.fixture()
def seeded_kb(db) -> Iterator[FakeRagLLM]:
    """Fresh Postgres with the fixture docs imported (real pipeline)."""
    db.execute(text("TRUNCATE chunks, documents, query_log"))
    db.commit()
    llm = FakeRagLLM()
    summary = asyncio.run(import_sources([FIXTURES], llm, session=db))
    assert summary.added == 13  # A9 formats (phase 47 added quadlet+j2); .hidden/ skipped
    yield llm
    db.execute(text("TRUNCATE chunks, documents, query_log"))
    db.commit()


def _seed_one_doc(db) -> Document:
    """One minimal document (for the public document-content endpoint)."""
    doc = Document(
        source="docs",
        path="homelab/kubernetes.md",
        full_path="/tmp/kubernetes.md",
        title="Kubernetes Homelab Cluster",
        content="# Kubernetes Homelab Cluster\n\nTalos on 3 nodes.",
        content_hash="c" * 64,
    )
    db.add(doc)
    db.commit()
    db.refresh(doc)
    return doc


def test_wrong_password_401_and_still_gated(client: TestClient) -> None:
    r = client.post("/api/login", json={"password": "not-the-password"})
    assert r.status_code == 401
    assert r.json() == {"detail": "invalid password"}
    # No session state was created by the failed attempt.
    assert "bor_session" not in client.cookies

    r = client.post("/api/login", json={"password": ""})  # empty → same 401
    assert r.status_code == 401
    assert r.json() == {"detail": "invalid password"}

    # The gated surface stays closed (anonymous).
    assert client.get("/api/docs").status_code == 403
    r = client.get("/api/steering")
    assert r.status_code == 403
    assert r.json() == {"detail": "admin only"}
    assert client.post("/api/steering", json={"note": "x"}).status_code == 403
    assert client.get("/api/whoami").json() == {
        "authenticated": False,
        "role": "anonymous",
    }


def test_login_logout_lifecycle(client: TestClient) -> None:
    # Anonymous shape before anything.
    who = client.get("/api/whoami").json()
    assert who == {"authenticated": False, "role": "anonymous"}

    # Wrong first, right second — one generic 401, then success.
    assert client.post("/api/login", json={"password": "nope"}).status_code == 401
    r = client.post("/api/login", json={"password": ADMIN_PASSWORD})
    assert r.status_code == 204
    assert "bor_session" in client.cookies  # the signed session cookie

    # Admin: whoami + the gated endpoints all open up.
    assert client.get("/api/whoami").json() == {
        "authenticated": True,
        "role": "admin",
    }
    assert client.get("/api/docs").status_code == 200

    created = client.post("/api/steering", json={"note": "  be terse  "})
    assert created.status_code == 201
    note = created.json()
    assert note["note"] == "be terse"
    listing = client.get("/api/steering")
    assert listing.status_code == 200
    assert [n["note"] for n in listing.json()["notes"]] == ["be terse"]
    assert client.delete(f"/api/steering/{note['id']}").status_code == 204
    assert client.get("/api/steering").json() == {"notes": []}

    # Logout: 204, cookie gone, gated again.
    assert client.post("/api/logout").status_code == 204
    assert "bor_session" not in client.cookies
    assert client.get("/api/whoami").json() == {
        "authenticated": False,
        "role": "anonymous",
    }
    assert client.get("/api/docs").status_code == 403
    r = client.get("/api/steering")
    assert r.status_code == 403
    assert r.json() == {"detail": "admin only"}
    # Logout is idempotent (anonymous logout is still a clean 204).
    assert client.post("/api/logout").status_code == 204
    assert client.get("/api/whoami").json()["authenticated"] is False


def test_forged_cookie_is_rejected(client: TestClient) -> None:
    client.cookies.set("bor_session", "tampered-session-blob")
    assert client.get("/api/whoami").json() == {
        "authenticated": False,
        "role": "anonymous",
    }
    assert client.get("/api/docs").status_code == 403


def test_anonymous_document_content_stays_public(client: TestClient, db) -> None:
    """Soft rule (phase 16): the catalog is gated, the viewer is not."""
    _seed_one_doc(db)

    r = client.get(
        "/api/documents/content", params={"source": "docs", "path": "homelab/kubernetes.md"}
    )
    assert r.status_code == 200
    body = r.json()
    assert body["title"] == "Kubernetes Homelab Cluster"
    assert "Talos" in body["content"]
    assert set(body) == {
        "source",
        "path",
        "title",
        "format",
        "summary",  # nullable field added in phase 36 (null here — markdown)
        "content",
        "indexed_at",
        "chunks",
    }
    assert body["summary"] is None

    # Unknown docs still 404 anonymously (no enumeration of titles).
    r = client.get("/api/documents/content", params={"source": "docs", "path": "nope.md"})
    assert r.status_code == 404


def test_anonymous_chat_still_streams(
    client: TestClient, seeded_kb: FakeRagLLM
) -> None:
    """Regression guard: sign-in must not have locked chat (A10 public)."""
    fastapi_app.dependency_overrides[chat_api.get_llm] = lambda: seeded_kb
    try:
        status, content_type, frames = _stream_chat(client, QUESTION)
    finally:
        fastapi_app.dependency_overrides.clear()

    assert status == 200
    assert content_type.startswith("text/event-stream")
    deltas = [f for f in frames if f.get("type") == "delta"]
    assert len(deltas) >= 2  # genuinely streamed
    assert frames[-1]["type"] == "done"
    assert frames[-1]["deflected"] is False
    assert frames[-1]["sources"][0]["path"] == "homelab/kubernetes.md"