open-swe/tests/webhooks/test_confluence_webhook.py

"""Confluence Connect lifecycle overwrite guard, webhook corroboration, descriptor.

The lifecycle tests mock the JWT verifier (verified separately in
test_atlassian_connect.py) to isolate the accept/verify/store/reject logic —
especially that a failed re-install/uninstall leaves the stored secret intact.
"""

from __future__ import annotations

import asyncio
from types import SimpleNamespace
from typing import Any
from unittest.mock import AsyncMock, patch

from agent.utils import atlassian_connect as ac
from agent.webhooks import common as webhook_common
from agent.webhooks import confluence as cf
from agent.webhooks import confluence_routes


def _req() -> object:
    return SimpleNamespace(
        method="POST",
        url=SimpleNamespace(path="/connect/installed", query=""),
        headers={},
        query_params={},
    )


def _install(fn, body: dict[str, Any], *, existing, verify_ok: bool = True):
    puts: list[dict] = []
    dels: list[str] = []

    async def fake_get(_ck):
        return existing

    async def fake_put(client_key, shared_secret, base_url, product_type, *, first_install):
        puts.append({"client_key": client_key, "secret": shared_secret, "first": first_install})

    async def fake_del(client_key):
        dels.append(client_key)

    with (
        patch.object(ac, "get_installation", new=AsyncMock(side_effect=fake_get)),
        patch.object(ac, "put_installation", new=AsyncMock(side_effect=fake_put)),
        patch.object(ac, "delete_installation", new=AsyncMock(side_effect=fake_del)),
        patch.object(ac, "CONNECT_EXPECTED_CLIENT_KEYS", frozenset({"t"})),
        patch.object(
            ac,
            "verify_asymmetric_install_jwt",
            new=AsyncMock(return_value=({"iss": "t"} if verify_ok else None)),
        ),
    ):
        code, _detail = asyncio.run(fn(_req(), body))
    return code, puts, dels


# --- first install (trust-on-first-use, host-gated) ------------------------


def test_first_install_stores_secret() -> None:
    code, puts, _ = _install(
        cf.process_install,
        {"clientKey": "t", "sharedSecret": "s1", "baseUrl": "https://x.atlassian.net"},
        existing=None,
    )
    assert code == 204
    assert puts == [{"client_key": "t", "secret": "s1", "first": True}]


def test_first_install_missing_secret_400() -> None:
    code, puts, _ = _install(cf.process_install, {"clientKey": "t"}, existing=None)
    assert code == 400
    assert puts == []


def test_install_bad_signature_rejected() -> None:
    # Even a first install now requires a valid Atlassian signature (no TOFU).
    code, puts, _ = _install(
        cf.process_install,
        {"clientKey": "t", "sharedSecret": "s", "baseUrl": "https://x.atlassian.net"},
        existing=None,
        verify_ok=False,
    )
    assert code == 401
    assert puts == []


def test_install_rejected_when_client_key_not_allowed() -> None:
    # CONF-01: a valid Atlassian signature from a NON-allowlisted tenant (any
    # attacker who installs the public descriptor on their own site) is rejected.
    puts: list = []

    async def fake_put(*a, **k):
        puts.append(a)

    with (
        patch.object(ac, "get_installation", new=AsyncMock(return_value=None)),
        patch.object(
            ac, "verify_asymmetric_install_jwt", new=AsyncMock(return_value={"iss": "attacker"})
        ),
        patch.object(ac, "CONNECT_EXPECTED_CLIENT_KEYS", frozenset({"our-tenant"})),
        patch.object(ac, "put_installation", new=AsyncMock(side_effect=fake_put)),
    ):
        code, _ = asyncio.run(
            cf.process_install(
                _req(),
                {
                    "clientKey": "attacker",
                    "sharedSecret": "s",
                    "baseUrl": "https://attacker.atlassian.net",
                },
            )
        )
    assert code == 403
    assert puts == []


def test_install_bad_host_rejected_when_allowlist_configured() -> None:
    # Defense-in-depth host check (only enforced when CONNECT_EXPECTED_BASE_URL set).
    puts: list = []

    async def fake_put(*a, **k):
        puts.append(a)

    with (
        patch.object(ac, "get_installation", new=AsyncMock(return_value=None)),
        patch.object(ac, "verify_asymmetric_install_jwt", new=AsyncMock(return_value={"iss": "t"})),
        patch.object(ac, "CONNECT_EXPECTED_CLIENT_KEYS", frozenset({"t"})),
        patch.object(ac, "CONNECT_EXPECTED_BASE_URL_HOSTS", frozenset({"x.atlassian.net"})),
        patch.object(ac, "base_url_host_allowed", return_value=False),
        patch.object(ac, "put_installation", new=AsyncMock(side_effect=fake_put)),
    ):
        code, _ = asyncio.run(
            cf.process_install(
                _req(), {"clientKey": "t", "sharedSecret": "s", "baseUrl": "https://evil.com"}
            )
        )
    assert code == 403
    assert puts == []


# --- re-install overwrite guard (the security-critical path) ---------------

_EXISTING = {"client_key": "t", "shared_secret": "stored-secret"}


def test_reinstall_bad_jwt_preserves_stored_secret() -> None:
    code, puts, _ = _install(
        cf.process_install,
        {"clientKey": "t", "sharedSecret": "attacker", "baseUrl": "https://x.atlassian.net"},
        existing=_EXISTING,
        verify_ok=False,
    )
    assert code == 401
    assert puts == []  # stored secret NOT overwritten


def test_reinstall_valid_jwt_overwrites() -> None:
    code, puts, _ = _install(
        cf.process_install,
        {"clientKey": "t", "sharedSecret": "rotated", "baseUrl": "https://x.atlassian.net"},
        existing=_EXISTING,
        verify_ok=True,
    )
    assert code == 204
    assert puts == [{"client_key": "t", "secret": "rotated", "first": False}]


# --- uninstall guard -------------------------------------------------------


def test_uninstall_bad_jwt_keeps_record() -> None:
    code, _puts, dels = _install(
        cf.process_uninstall, {"clientKey": "t"}, existing=_EXISTING, verify_ok=False
    )
    assert code == 401
    assert dels == []


def test_uninstall_valid_jwt_deletes() -> None:
    code, _puts, dels = _install(
        cf.process_uninstall, {"clientKey": "t"}, existing=_EXISTING, verify_ok=True
    )
    assert code == 204
    assert dels == ["t"]


def test_uninstall_no_record_idempotent() -> None:
    code, _puts, dels = _install(cf.process_uninstall, {"clientKey": "t"}, existing=None)
    assert code == 204
    assert dels == []


# --- webhook corroboration (identity/body from server, not payload) --------


def _run_comment(payload: dict, server_comment: dict | None, *, active: set[str] | None = None):
    captured: dict = {}
    active = {"jane"} if active is None else active

    async def fake_dispatch(
        thread_id, content, configurable, *, source, metadata=None, client=None
    ):
        captured["configurable"] = configurable
        captured["source"] = source
        return {"run_id": "r1"}

    with (
        patch.object(
            webhook_common, "fetch_confluence_comment", new=AsyncMock(return_value=server_comment)
        ),
        patch.object(
            webhook_common,
            "fetch_confluence_page",
            new=AsyncMock(return_value={"title": "P", "url": "u"}),
        ),
        patch.object(
            webhook_common, "get_confluence_user_email", new=AsyncMock(return_value="jane@x.com")
        ),
        patch.object(
            webhook_common, "resolve_login_from_email_async", new=AsyncMock(return_value="jane")
        ),
        patch.object(webhook_common, "is_login_mapped", side_effect=lambda login: login in active),
        patch.object(
            webhook_common,
            "get_repo_config_from_confluence_mapping",
            return_value={"owner": "o", "name": "n"},
        ),
        patch.object(webhook_common, "_is_repo_allowed", return_value=True),
        patch.object(
            webhook_common, "generate_thread_id_from_confluence_comment", return_value="th-1"
        ),
        patch.object(
            webhook_common, "upsert_agent_thread_owner_metadata", new=AsyncMock(return_value=None)
        ),
        patch.object(webhook_common, "dispatch_agent_run", side_effect=fake_dispatch),
    ):
        asyncio.run(cf.process_confluence_comment(payload))
    return captured


def _server_comment(
    *, account_id="real", name="Real", body="@openswe fix it", space="IT", page="99"
):
    return {
        "author": {"account_id": account_id, "name": name},
        "body": body,
        "page_id": page,
        "space_key": space,
    }


def test_webhook_uses_server_comment_not_payload() -> None:
    payload = {"comment": {"id": "555"}, "userAccountId": "victim", "body": "benign"}
    cap = _run_comment(payload, _server_comment())
    assert cap["source"] == "confluence"
    conf = cap["configurable"]["confluence"]
    assert conf["comment_id"] == "555"
    assert conf["space_key"] == "IT"
    assert cap["configurable"]["github_login"] == "jane"


def test_webhook_uncorroborated_comment_dropped() -> None:
    cap = _run_comment({"comment": {"id": "555"}}, None)
    assert cap == {}  # no dispatch


def test_webhook_without_mention_dropped() -> None:
    cap = _run_comment({"comment": {"id": "555"}}, _server_comment(body="just a normal comment"))
    assert cap == {}


def test_webhook_pending_mapping_unattributed() -> None:
    cap = _run_comment({"comment": {"id": "555"}}, _server_comment(), active=set())
    assert "github_login" not in cap["configurable"]


def test_webhook_bot_own_comment_dropped() -> None:
    # CONF-02: a comment authored by the app's own account is ignored (no loop).
    with patch.object(cf, "CONFLUENCE_BOT_ACCOUNT_ID", "bot-acct"):
        cap = _run_comment({"comment": {"id": "555"}}, _server_comment(account_id="bot-acct"))
    assert cap == {}


# --- descriptor ------------------------------------------------------------


def test_descriptor_signed_install_true_and_read_scope() -> None:
    desc = asyncio.run(confluence_routes.connect_descriptor())
    assert desc["apiMigrations"]["signed-install"] is True
    assert desc["scopes"] == ["READ"]
    assert desc["authentication"]["type"] == "jwt"
    assert desc["modules"]["webhooks"][0]["event"] == "comment_created"