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

"""Integration: the auth surface (phase 16 admin; phase 79 token users).

Covers the full admin 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 phase-79
token flows: ``POST /api/token-auth`` (valid → 204 + the ``user`` role;
invalid / malformed / revoked / empty → ONE generic 401), the
three-role ``whoami``, logout clearing the token session, and the
LIVE revocation check (a revoked token is refused on the next request
and the dead session's keys are dropped — whoami falls to anonymous).

The phase-16 anonymous pins are SUPERSEDED by the phase-79 contract:
the ONLY anonymous content is the shared chats (plus the login/infra
endpoints the gate itself needs) — anonymous chat / suggestions /
document content now 401 ``authentication required``.

Rate limiting (phase 81, audit SEC-03): the sign-in failure counter is
PROCESS state (in-memory per IP), and TestClient's
``request.client.host`` is the fixed value ``"testclient"`` — so every
client in this module (including ``_admin_client``'s separate
TestClient) shares ONE limiter entry. The ``clean_rate_limit`` autouse
fixture resets that entry around every test so the deliberate 429 pins
can't poison the other tests (and the table TRUNCATEs can't help: the
counter is not row state).

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.api.auth import TOO_MANY_DETAIL
from app.core import rate_limit
from app.core.rate_limit import WINDOW_SECONDS
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_rate_limit() -> Iterator[None]:
    """Reset the in-memory sign-in-failure counter around every test.

    TestClient's ``request.client.host`` is the fixed value
    ``"testclient"``, so every client in this module — including the
    ``_admin_client`` helper's separate TestClient — shares ONE limiter
    entry, and the counter is process state the table TRUNCATEs cannot
    clear. Without this reset, the deliberate 429 tests below (which
    block the shared IP on purpose) would make every later test in the
    process hit the throttled 429 path instead of the 401/204 contract
    it pins.
    """
    rate_limit.reset("testclient")
    yield
    rate_limit.reset("testclient")


@pytest.fixture(autouse=True)
def clean_tables(db) -> Iterator[None]:
    """Docs + steering + query log + tokens are global state: reset
    around tests."""
    db.execute(
        text("TRUNCATE chunks, documents, query_log, steering_notes, api_tokens")
    )
    db.commit()
    yield
    db.execute(
        text("TRUNCATE chunks, documents, query_log, steering_notes, api_tokens")
    )
    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 user-gated 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 _admin_client() -> TestClient:
    """A SEPARATE client signed in as the admin — for tests that need an
    admin and a token user at the same time (the shared ``client``
    fixture is the token holder in those)."""
    admin = TestClient(fastapi_app)
    r = admin.post("/api/login", json={"password": ADMIN_PASSWORD})
    assert r.status_code == 204, f"admin login failed: {r.status_code} {r.text}"
    return admin


def _create_token(admin: TestClient, label: str = "alice") -> tuple[str, str]:
    """Admin issues one token; returns ``(token_id, plaintext)`` — the
    plaintext is the 201 body's one-and-only wire moment (task 02)."""
    r = admin.post("/api/tokens", json={"label": label})
    assert r.status_code == 201, r.text
    body = r.json()
    return body["id"], body["token"]


# ---------- phase 16: the admin lifecycle (unchanged contract) ----------


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 (phase 79: the anonymous whoami
    # gains the explicit role — the UI keys its admin surfaces off it).
    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


# ---------- phase 79: the token login + the user role ----------


def test_token_auth_valid_signs_in_token_user(client: TestClient) -> None:
    """A valid token → 204 + session cookie → whoami reports the THIRD
    role: ``{authenticated: true, role: "user"}``."""
    admin = _admin_client()
    _token_id, token = _create_token(admin)

    r = client.post("/api/token-auth", json={"token": token})
    assert r.status_code == 204
    assert "bor_session" in client.cookies  # the signed session cookie

    assert client.get("/api/whoami").json() == {
        "authenticated": True,
        "role": "user",
    }


def test_token_auth_all_failures_share_one_generic_401(client: TestClient) -> None:
    """Malformed / unknown / revoked / empty are INDISTINGUISHABLE — one
    401 ``{"detail": "invalid token"}`` for every failure shape (the
    phase-16 no-enumeration pattern; a 422 would hint at input-shape
    differences on a credential endpoint)."""
    admin = _admin_client()
    _token_id, token = _create_token(admin)

    failures = [
        token + "0",  # unknown (no row for this hash)
        "bor_" + "0" * 32,  # well-shaped, never issued
        "short",  # malformed: too short
        "wrongprefix_" + "0" * 32,  # malformed: wrong prefix
        "",  # empty
        "   ",  # whitespace only
    ]
    for bad in failures:
        r = client.post("/api/token-auth", json={"token": bad})
        assert r.status_code == 401, bad
        assert r.json() == {"detail": "invalid token"}, bad
        assert "bor_session" not in client.cookies  # no session on failure

    # A failed attempt must not sign anyone in.
    assert client.get("/api/whoami").json() == {
        "authenticated": False,
        "role": "anonymous",
    }

    # Revoked → the SAME 401 (not a different "revoked" message).
    _bob_id, bob_token = _create_token(admin, "bob")
    bob_id = next(
        t["id"] for t in admin.get("/api/tokens").json()["tokens"] if t["label"] == "bob"
    )
    assert admin.post(f"/api/tokens/{bob_id}/revoke").status_code == 204
    r = client.post("/api/token-auth", json={"token": bob_token})
    assert r.status_code == 401
    assert r.json() == {"detail": "invalid token"}


def test_token_user_surface_matrix(client: TestClient, db, seeded_kb: FakeRagLLM) -> None:
    """The owner's sentence (phase 79): a token user gets the app surface
    — chat streams, suggestion chips, cited document content — and NO
    admin surface (tokens, docs list, saved chats, steering, git
    sources stay 403 for them; saved chats have no per-user
    attribution)."""
    admin = _admin_client()
    _token_id, token = _create_token(admin)
    assert client.post("/api/token-auth", json={"token": token}).status_code == 204

    # Chat streams (the mocked LLM — the real turn pipeline).
    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")
    assert frames[-1]["type"] == "done"
    assert frames[-1]["deflected"] is False
    # Phase 119 (A1): the citation surface is the agent's READ docs
    # only — the canned turn reads nothing ⇒ no chips (the cited
    # document's content pin below is the surface's other half).
    assert frames[-1]["sources"] == []

    # Suggestion chips + the cited document's content (the viewer).
    assert client.get("/api/suggestions").status_code == 200
    r = client.get(
        "/api/documents/content", params={"source": "docs", "path": "homelab/kubernetes.md"}
    )
    assert r.status_code == 200
    assert r.json()["title"] == "Kubernetes Homelab Cluster"

    # The admin surface stays admin-only for a token user (A3 scope).
    for path in ("/api/tokens", "/api/docs", "/api/chats", "/api/steering", "/api/git-sources"):
        r = client.get(path)
        assert r.status_code == 403, path
        assert r.json() == {"detail": "admin only"}, path


def test_token_user_cannot_create_or_list_tokens(client: TestClient) -> None:
    """The token ADMIN surface is closed to token holders on every
    method, not just GET (A3: only the admin manages tokens)."""
    admin = _admin_client()
    _token_id, token = _create_token(admin)
    assert client.post("/api/token-auth", json={"token": token}).status_code == 204

    assert client.post("/api/tokens", json={"label": "evil"}).status_code == 403
    assert client.get("/api/tokens").status_code == 403
    assert client.post("/api/tokens/00000000-0000-0000-0000-000000000000/revoke").status_code == 403
    # The admin's own token list is untouched.
    assert [t["label"] for t in admin.get("/api/tokens").json()["tokens"]] == ["alice"]


def test_logout_clears_token_session(client: TestClient) -> None:
    """One logout, one session dict: a token holder's logout drops the
    ``user`` role — whoami anonymous and the gated surface 401s again."""
    admin = _admin_client()
    _token_id, token = _create_token(admin)
    assert client.post("/api/token-auth", json={"token": token}).status_code == 204
    assert client.get("/api/whoami").json()["role"] == "user"

    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/suggestions").status_code == 401
    assert client.post("/api/chat", json={"message": "hi"}).status_code == 401


def test_revocation_mid_session_enforced_live(
    client: TestClient, db, seeded_kb: FakeRagLLM
) -> None:
    """The live check (A4): a token revoked MID-SESSION is refused on
    the holder's next request — chat 401 — and the dead session's keys
    are dropped right there (whoami falls to anonymous without a
    logout)."""
    admin = _admin_client()
    token_id, token = _create_token(admin)
    assert client.post("/api/token-auth", json={"token": token}).status_code == 204
    assert client.get("/api/whoami").json()["role"] == "user"

    # The turn BEFORE the revocation still streams.
    fastapi_app.dependency_overrides[chat_api.get_llm] = lambda: seeded_kb
    try:
        status, _ct, frames = _stream_chat(client, QUESTION)
    finally:
        fastapi_app.dependency_overrides.clear()
    assert status == 200
    assert frames[-1]["type"] == "done"

    # The admin revokes (idempotent 204 from task 02).
    assert admin.post(f"/api/tokens/{token_id}/revoke").status_code == 204

    # The NEXT request is refused — 401, not a stream — and the session
    # is dead (the live check popped both user keys).
    r = client.post("/api/chat", json={"message": "hello"})
    assert r.status_code == 401
    assert r.json() == {"detail": "authentication required"}
    assert client.get("/api/whoami").json() == {
        "authenticated": False,
        "role": "anonymous",
    }

    # …and a FRESH login attempt with the revoked token fails too (the
    # token itself is dead, not just this session).
    r = client.post("/api/token-auth", json={"token": token})
    assert r.status_code == 401
    assert r.json() == {"detail": "invalid token"}


# ---------- phase 79: the enforcement matrix (the 401 contract) ----------


def test_anonymous_chat_now_401s(client: TestClient, db) -> None:
    """The phase-16 "chat still streams anonymously" pin is SUPERSEDED:
    anonymous chat gets a plain 401 ``authentication required`` (401,
    not 403 — no higher privilege would unblock them)."""
    r = client.post("/api/chat", json={"message": "hello"})
    assert r.status_code == 401
    assert r.json() == {"detail": "authentication required"}


def test_anonymous_suggestions_and_document_content_401(client: TestClient, db) -> None:
    """The other two gated endpoints share the same 401 contract."""
    r = client.get("/api/suggestions")
    assert r.status_code == 401
    assert r.json() == {"detail": "authentication required"}

    _seed_one_doc(db)
    r = client.get(
        "/api/documents/content", params={"source": "docs", "path": "homelab/kubernetes.md"}
    )
    assert r.status_code == 401
    assert r.json() == {"detail": "authentication required"}


def test_document_content_admin_contract(client: TestClient, db) -> None:
    """The phase-16 soft rule (viewer public) is superseded: the viewer
    content is token-or-admin — the admin gets the full DocContent
    shape, unknown pairs still 404 (no enumeration of titles)."""
    client.post("/api/login", json={"password": ADMIN_PASSWORD})
    _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)
        "created_at",  # added in phase 106 (task 05)
        "content",
        "indexed_at",
        "chunks",
        "is_image",  # added in phase 122 (task 04) — always present
    }
    assert body["summary"] is None
    assert body["is_image"] is False  # text doc — and no image_url key (never null)
    assert "image_url" not in body

    # Unknown docs still 404 (same shape as the phase-16 pin).
    r = client.get("/api/documents/content", params={"source": "docs", "path": "nope.md"})
    assert r.status_code == 404
    assert r.json() == {"detail": "document not found"}


def test_admin_chat_still_streams(client: TestClient, db, seeded_kb: FakeRagLLM) -> None:
    """The streaming assertions of the old anonymous pin survive under a
    signed-in (admin) client — sign-in locked out strangers, not the
    owner."""
    assert client.post("/api/login", json={"password": ADMIN_PASSWORD}).status_code == 204

    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
    # Phase 119 (A1): read docs only — nothing was read ⇒ no chips.
    assert frames[-1]["sources"] == []


# ---------- phase 81: rate-limited failed sign-ins (audit SEC-03) ----------


def test_eleventh_failed_login_429_with_retry_after(client: TestClient) -> None:
    """10 wrong passwords → 401 (the phase-16 contract, unchanged
    detail); the 11th attempt is the FIRST 429 — one generic detail + a
    ``Retry-After`` header carrying whole-window seconds."""
    for _ in range(10):
        r = client.post("/api/login", json={"password": "nope"})
        assert r.status_code == 401
        assert r.json() == {"detail": "invalid password"}
    r = client.post("/api/login", json={"password": "nope"})
    assert r.status_code == 429
    assert r.json()["detail"] == TOO_MANY_DETAIL
    retry_after = int(r.headers["Retry-After"])
    assert retry_after > 0
    assert retry_after <= WINDOW_SECONDS  # the whole-window wait, never more


def test_correct_password_while_blocked_still_429(client: TestClient) -> None:
    """An exhausted window stays exhausted until it slides: the pre-check
    fires BEFORE the password is compared, so even a CORRECT password
    gets the 429 while blocked (success only resets a CLEAN counter —
    this is the intended semantics, pinned)."""
    for _ in range(10):
        assert client.post("/api/login", json={"password": "nope"}).status_code == 401
    r = client.post("/api/login", json={"password": ADMIN_PASSWORD})
    assert r.status_code == 429
    assert r.json()["detail"] == TOO_MANY_DETAIL
    assert "bor_session" not in client.cookies  # not signed in while throttled


def test_success_on_clean_counter_resets_it(client: TestClient) -> None:
    """9 failures + 1 success (204) → the counter is back to 0: the next
    9 failures are all plain 401s (a fresh 10 would be needed to block
    again). A fat-fingered owner is not poisoned by earlier misses."""
    for _ in range(9):
        assert client.post("/api/login", json={"password": "nope"}).status_code == 401
    assert client.post("/api/login", json={"password": ADMIN_PASSWORD}).status_code == 204
    for _ in range(9):
        r = client.post("/api/login", json={"password": "nope"})
        assert r.status_code == 401
        assert r.json() == {"detail": "invalid password"}


def test_login_and_token_failures_share_the_counter(client: TestClient) -> None:
    """The counter is SHARED by both routes (a token-spraying attack must
    not dodge the window by alternating routes): 5 login failures + 5
    token failures exhaust it, so the 11th attempt of EITHER shape — even
    with a VALID token — is a 429."""
    # Admin + token FIRST: the successful admin login resets the shared
    # counter, so it must not happen after failures have accumulated.
    admin = _admin_client()
    _token_id, token = _create_token(admin)
    for _ in range(5):
        assert client.post("/api/login", json={"password": "nope"}).status_code == 401
    for _ in range(5):
        r = client.post("/api/token-auth", json={"token": "bor_" + "0" * 32})
        assert r.status_code == 401
        assert r.json() == {"detail": "invalid token"}
    r = client.post("/api/token-auth", json={"token": token})
    assert r.status_code == 429
    assert r.json()["detail"] == TOO_MANY_DETAIL
    assert int(r.headers["Retry-After"]) > 0