agnes-the-ai-analyst/tests/test_api_scripts.py
ZdenekSrotyr e9d7af3cce feat(rbac+marketplace): RBAC v13 + Claude Code marketplace + #81/#83/#44 hardening
This squashes 13 commits from ma/staging plus a small docstring translation
into a single coherent unit. Three workstreams.

== RBAC v13 redesign ==
- Drops core.viewer/analyst/km_admin/admin hierarchy and the
  internal_roles / group_mappings / user_role_grants / plugin_access tables.
- Replaced by user_group_members + resource_grants. Atomic v12→v13 backfill
  wrapped in BEGIN/COMMIT; ROLLBACK leaves schema_version at 12 for retry.
- Two authorization primitives in app.auth.access:
    require_admin                        — Admin-group god-mode
    require_resource_access(rt, "{path}") — entity-scoped grants
  Single DB lookup per request; no session cache; no implies BFS.
- /admin/access UI (single page) replaces /admin/role-mapping +
  /admin/plugin-access. CLI `da admin group/grant *` replaces
  `da admin role/mapping/grant-role/revoke-role/effective-roles`.
- ResourceType.TABLE listing-only — admins can record table grants,
  runtime enforcement still flows through legacy dataset_permissions
  (migration plan in docs/TODO-rbac-data-enforcement.md).

== Claude Code marketplace ==
- Aggregated /marketplace.zip + /marketplace.git/* (PAT-gated,
  RBAC-filtered, content-addressed cache via dulwich).
- Admin god-mode dropped on the marketplace surface — admins curate
  their own view via grants like everyone else.
- Bare-repo cache materializes per RBAC-filtered ETag; stale entries
  not pruned in this iteration (disclaimed in git_backend.py docstring).

== #81 #83 #44 security/ops hardening ==
- #81 Group A — orchestrator ATTACH allow-listing (extension/url/alias).
- #81 Group B — Keboola extractor 3-state exit codes:
    0 success / 1 total fail / 2 PARTIAL fail
  Sync API logs PARTIAL FAILURE alert on exit 2. Operators with binary
  alerting must teach it the new partial signal.
- #81 Group C — schema v10 view_ownership; rejects silent overwrite
  of a prior connector's view name on collision.
- #81 Group D — extractor-side identifier validation.
- #83 — Jira webhook fail-closed when JIRA_WEBHOOK_SECRET unset
  + path-traversal fix.
- #44 — entire /api/scripts/* surface is admin-only (planted-script +
  sandbox-bypass risk closed).

== Web UI polish + deploy fix ==
- /admin/access: live grant-count badges (no stale snapshot revert),
  shared-header CSS link added to /catalog and /admin/{tables,permissions},
  per-resource-type colored stripes.
- docker-compose.host-mount.yml: bind,rbind so dual-disk hosts don't
  silently shadow sub-mounts and write state to the wrong disk.

== OSS vendor-neutralization (waves 1+2) ==
- scripts/grpn/ → scripts/ops/. Customer-specific identifiers
  (project IDs, internal hostnames, dev/prod VM IPs, brand names)
  replaced with placeholders across code, docs, Terraform, Caddyfile,
  OAuth probe, and planning docs. Downstream infra repos that copied
  scripts/grpn/agnes-tls-rotate.sh or agnes-auto-upgrade.sh must
  update the path.

== Translation ==
- src/repositories/user_groups.py::ensure_system docstring translated
  from Czech to English for codebase consistency.

Co-authored-by: Mina Rustamyan <mina@keboola.com>
2026-04-28 14:25:04 +02:00

128 lines
4.6 KiB
Python

"""Tests for scripts and settings API endpoints."""
import os
import pytest
from fastapi.testclient import TestClient
@pytest.fixture
def client(tmp_path, monkeypatch):
monkeypatch.setenv("DATA_DIR", str(tmp_path))
monkeypatch.setenv("JWT_SECRET_KEY", "test-secret-32chars-minimum!!!!!")
monkeypatch.setenv("SCRIPT_TIMEOUT", "10")
from app.main import create_app
from src.db import get_system_db
from src.repositories.users import UserRepository
from src.repositories.sync_settings import DatasetPermissionRepository
from app.auth.jwt import create_access_token
from tests.helpers.auth import grant_admin
conn = get_system_db()
user_repo = UserRepository(conn)
user_repo.create(id="admin1", email="admin@acme.com", name="Admin", role="admin")
user_repo.create(id="analyst1", email="analyst@acme.com", name="Analyst", role="analyst")
grant_admin(conn, "admin1")
perm_repo = DatasetPermissionRepository(conn)
perm_repo.grant("analyst1", "sales", "read")
perm_repo.grant("analyst1", "support", "read")
conn.close()
app = create_app()
test_client = TestClient(app)
admin_token = create_access_token("admin1", "admin@acme.com", "admin")
analyst_token = create_access_token("analyst1", "analyst@acme.com", "analyst")
return test_client, admin_token, analyst_token
class TestScriptsAPI:
def test_list_scripts_empty(self, client):
c, admin_token, _ = client
resp = c.get("/api/scripts", headers={"Authorization": f"Bearer {admin_token}"})
assert resp.status_code == 200
assert resp.json()["count"] == 0
def test_deploy_and_list(self, client):
c, admin_token, _ = client
headers = {"Authorization": f"Bearer {admin_token}"}
resp = c.post("/api/scripts/deploy", json={
"name": "hello", "source": "print('hello world')",
}, headers=headers)
assert resp.status_code == 201
script_id = resp.json()["id"]
resp = c.get("/api/scripts", headers=headers)
assert resp.json()["count"] == 1
def test_run_script(self, client):
c, admin_token, _ = client
headers = {"Authorization": f"Bearer {admin_token}"}
resp = c.post("/api/scripts/run", json={
"source": "print('hello from script')", "name": "test",
}, headers=headers)
assert resp.status_code == 200
data = resp.json()
assert data["exit_code"] == 0
assert "hello from script" in data["stdout"]
def test_run_blocked_import(self, client):
c, admin_token, _ = client
headers = {"Authorization": f"Bearer {admin_token}"}
resp = c.post("/api/scripts/run", json={
"source": "import subprocess; subprocess.run(['ls'])", "name": "bad",
}, headers=headers)
assert resp.status_code == 400
detail = resp.json()["detail"]
assert "disallowed" in detail or "Blocked" in detail
def test_deploy_run_undeploy(self, client):
c, admin_token, _ = client
admin_headers = {"Authorization": f"Bearer {admin_token}"}
resp = c.post("/api/scripts/deploy", json={
"name": "calc", "source": "print(2+2)", "schedule": "0 8 * * MON",
}, headers=admin_headers)
script_id = resp.json()["id"]
resp = c.post(f"/api/scripts/{script_id}/run", headers=admin_headers)
assert resp.status_code == 200
assert "4" in resp.json()["stdout"]
# Undeploy (requires admin)
resp = c.delete(f"/api/scripts/{script_id}", headers=admin_headers)
assert resp.status_code == 204
class TestSettingsAPI:
def test_get_settings(self, client):
c, _, analyst_token = client
resp = c.get("/api/settings", headers={"Authorization": f"Bearer {analyst_token}"})
assert resp.status_code == 200
data = resp.json()
assert data["user_id"] == "analyst1"
assert len(data["permissions"]) == 2
def test_enable_dataset(self, client):
c, _, analyst_token = client
headers = {"Authorization": f"Bearer {analyst_token}"}
resp = c.put("/api/settings/dataset", json={
"dataset": "sales", "enabled": True,
}, headers=headers)
assert resp.status_code == 200
assert resp.json()["enabled"] is True
def test_enable_unauthorized_dataset(self, client):
c, _, analyst_token = client
headers = {"Authorization": f"Bearer {analyst_token}"}
resp = c.put("/api/settings/dataset", json={
"dataset": "hr_secret", "enabled": True,
}, headers=headers)
assert resp.status_code == 403