Files
FabledSteward/tests/mcp/test_automation.py
T
bvandeusenandClaude Opus 5.5 8dad79f17a
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 1m12s
CI / integration (push) Successful in 59s
CI / publish (push) Successful in 1m3s
feat(ansible): runs stay inside their source; controller-side vars are admin-only (#5034)
#5034 "Playbook runs: path and inventory checks in trigger_run, connection
vars admin-only, confirm enforced server-side, web actions audited".
Ansible runs inside the Steward container, so an operator who could name
any playbook path, set ansible_connection=local or ProxyCommand ssh args,
or put {{ lookup('pipe', …) }} in a value could run commands on Steward.

- steward/ansible/guards.py: check_playbook (the source must list it),
  check_inventory_scope (steward:* or an inventory file the source has),
  check_vars_for_role (ansible_* beyond host/port/user/password/become,
  and any Jinja in a value, are admin-only), changed_vars (an edit is
  held to the role only for what it changes).
- trigger_run applies the path checks, so every run path — web, MCP,
  alerts, schedules, plugins — gets them.
- Variables are checked by role on the web run form, host-page runs,
  schedule create/update, inventory group/target create/update, and MCP
  run_playbook / create_schedule / update_schedule.
- A steward:confirm playbook needs the confirmation ticked on the server
  side for a real (non-check) web run, as MCP already required.
- Audited: runs, cancel, schedule create/update/enable/disable/delete/
  run-now, playbook create/update/delete, inventory group and target
  create/update/delete (variable names only, never values). One
  audit_request helper serves the web routes.
- The CSRF form guard and the route guard now each test that they fail
  on a synthetic broken input (rule: a guard must be able to fail).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 10:57:34 -04:00

159 lines
8.0 KiB
Python

"""The automation tools' pure parts and their gates: check mode by default,
secrets kept out of what is stored, roles, and refusals that run nothing.
A real check-mode run, applied run and audit rows are covered against
Postgres in tests/integration/test_mcp_automation.py.
"""
from __future__ import annotations
import inspect
from types import SimpleNamespace as NS
import pytest
from steward.core.api_tokens import Caller
from steward.mcp.tools import automation
from steward.models.users import UserRole
VARS = [
{"name": "api_token", "default": "abc", "secret": True, "required": False, "prompt": None},
{"name": "greeting", "default": "hi", "secret": False, "required": False, "prompt": None},
{"name": "release", "default": "", "secret": False, "required": True, "prompt": "Release?"},
]
VIEWER_TOOLS = {"list_playbooks", "get_playbook", "list_inventory", "list_ansible_runs",
"get_ansible_run", "list_schedules", "wait_for_run"}
OPERATOR_TOOLS = {"run_playbook", "cancel_ansible_run", "create_schedule", "update_schedule",
"delete_schedule"}
def test_split_vars_keeps_secrets_apart_from_what_is_stored():
plain, secret = automation.split_vars(VARS, {"api_token": "s3cr3t", "greeting": "yo",
"release": "1.2", "other": 5})
assert plain == {"greeting": "yo", "release": "1.2", "other": 5}
assert secret == {"api_token": "s3cr3t"}
def test_split_vars_refuses_a_missing_prompt_and_odd_values():
with pytest.raises(ValueError, match="prompts for release.*Nothing was run"):
automation.split_vars(VARS, {"greeting": "yo"})
with pytest.raises(ValueError, match="string, number or boolean"):
automation.split_vars(VARS[:2], {"greeting": ["a"]})
def test_public_variables_mask_secret_defaults():
out = {v["name"]: v["default"] for v in automation.public_variables(VARS)}
assert out == {"api_token": "<secret>", "greeting": "hi", "release": ""}
def test_build_params():
assert automation.build_params({}, "", "", True) == {"check": True}
assert automation.build_params({"a": 1}, " web01 ", "deploy", False) == {
"extra_vars_map": {"a": 1}, "limit": "web01", "tags": "deploy"}
def test_writes_default_to_check_mode():
for fn in (automation.run_playbook, automation.create_schedule, automation.set_alert_action):
assert inspect.signature(fn).parameters["check"].default is True, fn.__name__
async def test_run_playbook_will_not_apply_a_confirm_playbook_unconfirmed(monkeypatch):
monkeypatch.setattr(automation, "_source", lambda name: {"name": name, "path": "/x"})
monkeypatch.setattr(automation, "_playbook",
lambda s, p: "# steward:confirm: true\n- hosts: all\n tasks: []\n")
def _no_run(*a, **k):
raise AssertionError("a run was started")
monkeypatch.setattr(automation, "trigger_run", _no_run)
with pytest.raises(ValueError, match="flagged destructive.*confirmed=true"):
await automation.run_playbook("s", "wipe.yml", check=False)
def test_recap_totals_sum_over_hosts():
results = {"hosts": {"a": {"ok": 3, "changed": 1}, "b": {"ok": 2, "failed": 1}}}
assert automation.recap_totals(results) == {
"hosts": 2, "ok": 5, "changed": 1, "failed": 1, "unreachable": 0, "skipped": 0}
assert automation.recap_totals(None) is None
def test_read_log_tail_and_grep(monkeypatch, tmp_path):
monkeypatch.setattr(automation.executor, "artifact_path", lambda rid: str(tmp_path / "none.log"))
run = NS(id="r1", output="\n".join(["PLAY [all]", "TASK [x]", "fatal: boom", "x" * 900, "PLAY RECAP"]))
out = automation.read_log(run, tail=2, grep="FATAL")
assert out["log_lines"] == 5
assert out["tail"][1] == "PLAY RECAP" and out["tail"][0].endswith("[… 400 more]")
assert out["matches"] == [{"line_no": 3, "line": "fatal: boom"}] and out["matches_total"] == 1
(tmp_path / "r1.log").write_text("from the artifact\n")
monkeypatch.setattr(automation.executor, "artifact_path", lambda rid: str(tmp_path / f"{rid}.log"))
assert automation.read_log(run, tail=10, grep="")["tail"] == ["from the artifact"]
def test_automation_tools_are_registered_with_their_roles(app):
mcp = app.mcp_server
for name in VIEWER_TOOLS:
assert mcp.tool_roles[name] is UserRole.viewer, name
assert mcp._tool_manager.get_tool(name).annotations.read_only_hint is True, name
for name in OPERATOR_TOOLS:
assert mcp.tool_roles[name] is UserRole.operator, name
assert mcp._tool_manager.get_tool(name).annotations.read_only_hint is False, name
assert mcp.tool_roles["set_alert_action"] is UserRole.admin
for name in VIEWER_TOOLS | OPERATOR_TOOLS | {"set_alert_action"}:
assert (mcp._tool_manager.get_tool(name).description or "").strip(), name
def test_a_viewer_token_cannot_start_a_run(app):
viewer = Caller(user_id="u", username="v", role=UserRole.viewer, token_id=1)
operator = Caller(user_id="u", username="o", role=UserRole.operator, token_id=2)
assert "needs the operator role" in app.mcp_server.refusal("run_playbook", viewer)
assert app.mcp_server.refusal("run_playbook", operator) is None
assert "needs the admin role" in app.mcp_server.refusal("set_alert_action", operator)
def test_builtin_playbooks_get_steward_url_from_steward():
from steward.mcp import _context
app = NS(config={"PUBLIC_BASE_URL": ""})
a, u = _context._app_ctx.set(app), _context._base_url_ctx.set("http://steward.lan")
try:
declared = [{"name": "steward_url", "default": "", "secret": False, "required": False,
"prompt": None}]
builtin = {"name": "steward-builtin"}
got, filled = automation.steward_defaults(builtin, declared, {"agent_interval": 30})
assert got == {"agent_interval": 30, "steward_url": "http://steward.lan"}
assert filled == {"steward_url": "http://steward.lan"}
# The configured public URL wins over the address the request came in on.
app.config["PUBLIC_BASE_URL"] = "https://steward.example/"
assert automation.steward_defaults(builtin, declared, {})[1] == {
"steward_url": "https://steward.example"}
# A value the caller passed stands; another source's playbook is untouched.
assert automation.steward_defaults(builtin, declared, {"steward_url": "http://x"})[1] == {}
assert automation.steward_defaults({"name": "homelab"}, declared, {}) == ({}, {})
# A playbook that doesn't declare it gets nothing extra.
assert automation.steward_defaults(builtin, [], {}) == ({}, {})
finally:
_context._app_ctx.reset(a)
_context._base_url_ctx.reset(u)
async def test_run_playbook_holds_variables_to_the_callers_role(monkeypatch):
monkeypatch.setattr(automation, "_source", lambda name: {"name": name, "path": "/x"})
monkeypatch.setattr(automation, "_playbook", lambda s, p: "- hosts: all\n tasks: []\n")
def _no_run(*a, **k):
raise AssertionError("a run was started")
monkeypatch.setattr(automation, "trigger_run", _no_run)
operator = Caller(user_id="u", username="op", role=UserRole.operator, token_id=1)
monkeypatch.setattr(automation, "current_caller_or_none", lambda: operator)
with pytest.raises(ValueError, match="Only an admin can set ansible_connection"):
await automation.run_playbook("s", "site.yml", extra_vars={"ansible_connection": "local"})
with pytest.raises(ValueError, match="Ansible evaluates it"):
await automation.run_playbook("s", "site.yml", extra_vars={"x": "{{ lookup('pipe','id') }}"})
def test_schedule_update_holds_only_changed_variables(monkeypatch):
operator = Caller(user_id="u", username="op", role=UserRole.operator, token_id=1)
monkeypatch.setattr(automation, "current_caller_or_none", lambda: operator)
stored = {"ansible_ssh_common_args": "-J bastion"}
automation.check_caller_vars({**stored, "release": "2"}, stored)
with pytest.raises(ValueError, match="Only an admin"):
automation.check_caller_vars({"ansible_ssh_common_args": "-o ProxyCommand=x"}, stored)