ops-warden/tests/test_plan.py
tegwick 66db87e6ae feat: refuse to answer a write with a read (WARDEN-WP-0038)
`warden plan` scored needs by keyword overlap with no notion of what the
caller wanted to DO, so "generate a successor secret and CAS-write it to two
custodians" matched the lane that READS that path and inherited its
`autonomous` verdict -- answered with --out/--exec/--wrap.

Two counterparties reported it in two days. key-cape distrusted the output on
principle and was right to; railiance-platform, answering as the write
authority being wrongly bypassed, said plainly that `founder_required` is the
verdict it should have returned and that until it is fixed a plan result must
not stand in for the owner's answer.

A mutating need on a lane ops-warden does not permanently own can no longer
reach any branch returning `autonomous`: it becomes `founder_required` with
an approve act naming the write owner, or `unroutable` with a CCR stub when
the lane admits no rotation route. Commands carry no read transport either
way, which is the half that made the wrong verdict actionable.

The ownership test does the work a verb list cannot. SSH certificate
issuance is itself a mutating act, so `delegation.mode: permanent` -- not the
absence of a verb -- separates ops-warden's own front door from someone
else's custody. A regression asserts `warden sign` still proceeds; a guard
that refused our own lane would be worse than the defect it fixes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013EPuTc18FjU5WFqoSEKH3C

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1276224@bnt-lap001
Assistant-Session: 426ec497-e1c4-4dd3-b417-dfce1ca1dbc3
2026-09-10 08:02:10 +02:00

205 lines
8.3 KiB
Python

"""Tests for warden plan (WARDEN-WP-0029 T01)."""
from __future__ import annotations
import json
from pathlib import Path
import pytest
from typer.testing import CliRunner
from warden.cli import app
from warden.plan import build_plan
from warden.posture import load_posture
from warden.routing.catalog import load_catalog
runner = CliRunner()
REPO = Path(__file__).resolve().parents[1]
@pytest.fixture(autouse=True)
def _catalog_env(monkeypatch):
monkeypatch.setenv("WARDEN_ROUTING_CATALOG", str(REPO / "registry/routing/catalog.yaml"))
monkeypatch.setenv("WARDEN_POSTURE_CATALOG", str(REPO / "registry/policy/security-posture.yaml"))
def test_plan_forgejo_deploy_key_autonomous():
plan = build_plan("forgejo deploy key for binky-control")
assert plan.verdict == "autonomous"
assert plan.organization_posture == "build"
assert plan.lane_id == "agent-harness-forgejo-deploy"
assert plan.commands
assert plan.founder_act is None
assert plan.catalog.get("content_hash")
def test_plan_forgejo_admin_autonomous():
plan = build_plan("forgejo admin api token")
assert plan.verdict == "autonomous"
assert plan.lane_id == "forgejo-admin-api-token"
assert any("warden access forgejo-admin-api-token" in c for c in plan.commands)
def test_plan_new_secret_founder_required():
plan = build_plan("provision a new secret token for a tenant workload")
assert plan.verdict == "founder_required"
assert plan.founder_act is not None
assert plan.founder_act.kind in ("paste_once_provision", "approve", "oidc_login")
def test_plan_login_founder_required():
plan = build_plan("oidc login mfa key-cape")
assert plan.verdict == "founder_required"
assert plan.founder_act is not None
assert plan.founder_act.kind == "oidc_login"
def test_plan_first_time_openbao_database_admin_uses_platform_admin_login():
plan = build_plan(
"first-time OpenBao database engine administration for "
"database/config/platform-pg-2 dynamic roles policies and token roles; "
"requires attended platform-admin handoff"
)
assert plan.verdict == "founder_required"
assert plan.lane_id == "openbao-platform-admin-login"
assert plan.founder_act is not None
assert plan.founder_act.kind == "oidc_login"
command = plan.founder_act.details["fetch_command"]
assert command == (
"warden access openbao-platform-admin-login --exec -- <reviewed-command>"
)
assert "financials" not in command
assert "paste_once" not in plan.founder_act.details["desk_hint"]
assert any(
item
== "warden access openbao-platform-admin-login --exec -- <reviewed-command>"
for item in plan.commands
)
assert not any("--fetch" in item for item in plan.commands)
assert not any("--out" in item or "--wrap" in item for item in plan.commands)
def test_plan_openbao_shamir_recovery_uses_approval_ceremony_not_secret_provision():
plan = build_plan(
"coordinate one attended production OpenBao emergency seal/unseal drill "
"with a fresh encrypted off-host Raft snapshot receipt, verified "
"provider-console access, two-of-three Shamir custodian quorum, named "
"driver and abort operator, without exposing credential values"
)
assert plan.verdict == "founder_required"
assert plan.lane_id == "openbao-shamir-recovery-ceremony"
assert plan.founder_act is not None
assert plan.founder_act.kind == "approve"
assert "openbao-shamir-recovery-ceremony" in plan.founder_act.details["desk_hint"]
assert "paste_once" not in plan.founder_act.details["desk_hint"]
assert all("warden access" not in item for item in plan.commands)
assert any("openbao-shamir-recovery-ceremony" in item for item in plan.commands)
def test_plan_unroutable():
# Zero keyword overlap with catalog (avoid tokens like secret/key/token)
plan = build_plan("xyzzy-plugh-fnord-qqq-zzzz")
assert plan.verdict == "unroutable"
assert plan.ccr_stub is not None
assert plan.lane_id is None
def test_plan_composes_catalog_find():
"""Plan must use Catalog.find — exact id match wins."""
cat = load_catalog()
plan = build_plan("ssh-cert-host-access", catalog=cat, posture=load_posture())
assert plan.verdict == "autonomous"
assert plan.lane_id == "ssh-cert-host-access"
assert any("warden sign" in c for c in plan.commands)
def test_cli_plan_json():
r = runner.invoke(app, ["plan", "forgejo deploy key for binky-control", "--json"])
assert r.exit_code == 0, r.stdout + r.stderr
payload = json.loads(r.stdout)
assert payload["verdict"] == "autonomous"
assert payload["organization_posture"] == "build"
assert payload["lane_id"] == "agent-harness-forgejo-deploy"
# --- mutate intent (WARDEN-WP-0038) -------------------------------------------
#
# `warden plan` scored a need by keyword overlap with no notion of what the
# caller wanted to DO, so "generate a successor secret and CAS-write it to two
# custodians" matched the lane that READS that path and inherited its
# `autonomous` verdict, answered with --out/--exec/--wrap. Reported independently
# by key-cape (2026-09-08) and railiance-platform (2026-09-09), who added: "this
# is the same verdict your warden plan should have returned; until that is fixed,
# do not let a plan result stand in for this answer."
QONTO_ROTATION_NEED = (
"generate a successor client secret for rapp-qonto keycape client and "
"CAS-write it to OpenBao platform/workloads/rapp-qonto/keycape-client "
"and sso/keycape-rapp-qonto-client"
)
def test_reported_qonto_write_no_longer_returns_autonomous():
"""The exact need from the report. Regression, in the manner of WP-0033-T06."""
plan = build_plan(QONTO_ROTATION_NEED)
assert plan.verdict == "founder_required"
assert plan.lane_id == "rapp-qonto-keycape-client"
assert plan.founder_act is not None
assert plan.founder_act.kind == "approve"
assert plan.founder_act.details["write_owner"] == "key-cape"
def test_a_write_need_is_never_answered_with_a_read_transport():
"""The half that made the wrong verdict actionable rather than merely wrong."""
plan = build_plan(QONTO_ROTATION_NEED)
joined = " ".join(plan.commands)
for read_transport in ("--out", "--wrap", "--fetch", "bao kv get", "--exec"):
assert read_transport not in joined, read_transport
def test_mutating_need_names_why_it_escalated():
"""WP-0029's property: a verdict carries the reasons that produced it."""
plan = build_plan(QONTO_ROTATION_NEED)
assert any("change a credential" in r for r in plan.reasons)
assert any("write authority" in r for r in plan.reasons)
# The lane records automatable: false; a driver must be told so.
assert any("not automatable" in r for r in plan.reasons)
def test_ops_warden_still_proceeds_autonomously_on_the_lane_it_owns():
"""Signing IS a mutating act. The test is ownership, not the absence of a verb.
`delegation.mode: permanent` is the whole distinction — if this ever fails,
the guard has started refusing ops-warden's own front door.
"""
for need in (
"sign an ssh certificate for agt-state-hub-bridge",
"issue a short-lived ssh cert for adm",
):
plan = build_plan(need)
assert plan.verdict == "autonomous", need
assert plan.lane_id == "ssh-cert-host-access"
def test_reading_the_same_lane_is_unaffected():
plan = build_plan("I need the npm token to publish whynot-design")
assert plan.verdict == "autonomous"
assert plan.lane_id == "whynot-design-npm-publish"
@pytest.mark.parametrize(
"verb", ["rotate", "revoke", "regenerate", "reset", "replace"]
)
def test_mutating_verbs_escalate_on_a_lane_ops_warden_does_not_own(verb):
plan = build_plan(f"{verb} the forgejo admin api token")
assert plan.verdict == "founder_required"
assert plan.founder_act.details["write_owner"] == "railiance-platform"
def test_intent_classifier_matches_tokens_not_substrings():
from warden.plan import _need_intent
assert _need_intent("rotate the forgejo token") == "mutate"
assert _need_intent("CAS-write to two custodians") == "mutate"
# "created" and "updated" are not the verbs; a need describing state is a read.
assert _need_intent("read the token created for whynot-design") == "read"
assert _need_intent("which subsystem owns the npm token") == "read"