Merge branch 'master' into fix/issue-897-permission-stale-runtime-classification

This commit is contained in:
2026-07-25 06:42:27 -05:00
18 changed files with 3098 additions and 44 deletions
@@ -0,0 +1,381 @@
"""``apply_authorized`` requires BOTH authorizations (#886 review blocker B1).
The #663 restart-class matrix and the #661 drain-proof hard gate are independent
authorizations that first coexisted when PR #882 landed on master and PR #886
merged it into the restart-class branch. The union preserved both, but the apply
decision consulted only the drain gate::
payload["apply_authorized"] = gate.allow # pre-fix
so a clean drain proof — or an authorized break-glass, which needs no proof at
all — reported ``apply_authorized: True`` for a restart class the least-privilege
matrix had just denied, in the same payload that carried
``allow_restart: False`` and "role 'author' may not request full_mcp_restart".
These tests pin the conjunction and the properties that must survive it. They
exercise the real MCP tool, which previously had no test coverage at all — that
absence is why the defect shipped.
"""
from __future__ import annotations
import json
import os
import unittest
from unittest.mock import patch
import drain_proof
import gitea_mcp_server as srv
CONTROLLER_APPROVAL_ENV = "GITEA_CONTROLLER_RESTART_APPROVAL_AUTHORIZATION"
BREAK_GLASS_ENV = "GITEA_BREAKGLASS_RESTART_AUTHORIZATION"
# A quiet control plane: nothing live, so the blast radius never masks the
# authorization outcome under test.
QUIET_SESSIONS: list[dict] = []
QUIET_LEASES: list[dict] = []
class _FakeDB:
"""Minimal control-plane DB stand-in for the restart inventory."""
def __init__(self, sessions=QUIET_SESSIONS, terminal=None):
self._sessions = list(sessions)
self._terminal = terminal
def list_sessions(self, statuses=None, limit=None):
return list(self._sessions)
def get_active_terminal_lock(self, remote=None, org=None, repo=None):
return self._terminal
def _profile(role: str) -> dict:
return {"profile_name": f"prgs-{role}", "role_kind": role, "role": role}
class _RestartToolHarness(unittest.TestCase):
"""Drives the real ``gitea_request_mcp_restart`` with a stubbed inventory."""
def _call(self, *, role: str, env: dict | None = None, **kwargs) -> dict:
environ = {k: v for k, v in os.environ.items()
if k not in (CONTROLLER_APPROVAL_ENV, BREAK_GLASS_ENV)}
environ.update(env or {})
with patch.object(srv, "_profile_operation_gate", return_value=None), \
patch.object(srv, "_resolve",
return_value=("gitea.prgs.cc",
"Scaled-Tech-Consulting",
"Gitea-Tools")), \
patch.object(srv, "get_profile", return_value=_profile(role)), \
patch.object(srv, "_control_plane_db_or_error",
return_value=(_FakeDB(), [])), \
patch.object(srv.lease_lifecycle, "list_active_leases",
return_value={"leases": list(QUIET_LEASES)}), \
patch.dict(os.environ, environ, clear=True):
return srv.gitea_request_mcp_restart(
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
session_id="probe-session",
**kwargs,
)
def _clean_proof_for(self, preview: dict) -> str:
"""Mint a genuinely clean, signature-valid proof bound to *preview*.
Built from the tool's own dry-run report, so the fingerprint matches and
the proof is rejected for authorization reasons only — never because it
was stale or forged.
"""
proof = drain_proof.build_drain_proof(
impact_report=preview,
drain_state={
"assignments_stopped": True,
"checkpoints_complete": True,
"handoffs_verified": True,
"leases_handled": True,
"acks": {},
},
requesting_session_id="probe-session",
)
self.assertTrue(proof.clean, "harness must mint a clean proof")
return json.dumps(proof.as_dict())
class TestConjunction(_RestartToolHarness):
"""AC1/AC2 — the two authorizations are ANDed, in both directions."""
def test_gate_allow_with_class_denied_yields_apply_authorized_false(self):
# An author may not request full_mcp_restart (CONTROL_ROLES only).
preview = self._call(role="author", restart_class="full_mcp_restart")
self.assertFalse(preview["allow_restart"])
result = self._call(
role="author",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertTrue(result["apply_gate"]["drain_gate_allow"],
"drain gate itself should have allowed this proof")
self.assertFalse(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"],
"a clean proof must not authorize a denied class")
self.assertFalse(result["allow_restart"])
def test_gate_allow_with_class_allowed_can_yield_apply_authorized_true(self):
preview = self._call(
role="operator",
restart_class="full_mcp_restart",
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(preview["allow_restart"],
"operator + controller approval must authorize the class")
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["apply_gate"]["drain_gate_allow"])
self.assertTrue(result["apply_gate"]["restart_class_authorized"])
self.assertTrue(result["apply_authorized"],
"both authorizations pass; apply must be authorized")
def test_denial_is_attributable_to_the_authorization_that_caused_it(self):
preview = self._call(role="author", restart_class="full_mcp_restart")
result = self._call(
role="author",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
blob = " ".join(result["apply_gate"]["reasons"]).lower()
self.assertIn("restart class authorization denied", blob)
self.assertIn("full_mcp_restart", blob)
class TestProofCannotOverrideAuthorization(_RestartToolHarness):
"""AC3 — a clean proof never overrides a class or requester-role denial."""
def test_clean_proof_cannot_override_role_denial(self):
for role in ("author", "reviewer", "merger", "reconciler"):
with self.subTest(role=role):
preview = self._call(role=role, restart_class="full_mcp_restart")
result = self._call(
role=role,
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_missing_controller_approval(self):
# Correct role, but the class demands controller approval and the
# environment carries none.
preview = self._call(role="operator", restart_class="full_mcp_restart")
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_unknown_class(self):
preview = self._call(role="operator", restart_class="not_a_real_class",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="not_a_real_class",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_missing_scope_target(self):
# worker_restart without target_session_id fails closed on scoping.
preview = self._call(role="operator", restart_class="worker_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="worker_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(result["apply_authorized"])
class TestBreakGlassDoesNotCollapseTheMatrix(_RestartToolHarness):
"""AC4 — break-glass bypasses the drain proof only, never the class matrix."""
def test_break_glass_does_not_authorize_a_denied_class(self):
result = self._call(
role="author",
restart_class="host_restart",
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued"},
)
self.assertTrue(result["break_glass_authorized"])
self.assertTrue(result["apply_gate"]["drain_gate_allow"],
"break-glass does satisfy the drain gate")
self.assertFalse(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"],
"break-glass must not collapse the class matrix")
def test_break_glass_across_every_worker_role_and_restricted_class(self):
for role in ("author", "reviewer", "merger", "reconciler"):
for klass in ("rolling_mcp_restart", "full_mcp_restart",
"host_restart"):
with self.subTest(role=role, restart_class=klass):
result = self._call(
role=role,
restart_class=klass,
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued"},
)
self.assertFalse(result["apply_authorized"])
def test_break_glass_still_works_when_the_class_is_authorized(self):
# Break-glass keeps its purpose: skipping the drain proof for a caller
# the matrix does allow.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued",
CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["apply_authorized"])
self.assertEqual(result["apply_gate"]["verdict"], "break_glass")
def test_break_glass_is_not_self_assertable(self):
# Requested but no environment authorization -> no bypass, and the
# unproven apply is denied.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
request_break_glass=True,
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["break_glass_requested"])
self.assertFalse(result["break_glass_authorized"])
self.assertFalse(result["apply_authorized"])
self.assertIn("incident", result)
class TestRestrictedClassesStayDenied(_RestartToolHarness):
"""AC5 — restricted classes remain denied to unauthorized requesters."""
def test_restricted_classes_denied_for_worker_roles(self):
for role in ("author", "reviewer", "merger", "reconciler"):
for klass in ("rolling_mcp_restart", "full_mcp_restart",
"host_restart"):
with self.subTest(role=role, restart_class=klass):
preview = self._call(
role=role,
restart_class=klass,
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(preview["allow_restart"])
self.assertFalse(preview["permission_authorized"])
self.assertFalse(preview["role_authorized"])
def test_host_restart_needs_controller_and_infrastructure_operator(self):
# controller approval alone is not enough for host_restart.
preview = self._call(role="controller", restart_class="host_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["approval_satisfied"])
self.assertFalse(preview["allow_restart"])
class TestExistingPathsStillWork(_RestartToolHarness):
"""AC6 — valid scoped and unscoped restart paths are unaffected."""
def test_dry_run_never_reports_apply_authorization(self):
result = self._call(role="operator", restart_class="full_mcp_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertNotIn("apply_authorized", result)
self.assertNotIn("apply_gate", result)
self.assertFalse(result["apply_supported"])
self.assertFalse(result["restart_performed"])
def test_self_service_unscoped_classes_authorize_for_every_role(self):
for role in ("author", "reviewer", "merger", "reconciler",
"controller", "operator", "admin"):
for klass in ("client_reconnect", "session_reconnect"):
with self.subTest(role=role, restart_class=klass):
preview = self._call(role=role, restart_class=klass)
self.assertTrue(preview["allow_restart"])
def test_scoped_class_with_target_authorizes_and_applies(self):
env = {CONTROLLER_APPROVAL_ENV: "operator-approved"}
preview = self._call(role="operator", restart_class="worker_restart",
target_session_id="worker-1", env=env)
self.assertTrue(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="worker_restart",
target_session_id="worker-1",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env=env,
)
self.assertTrue(result["apply_authorized"])
def test_apply_still_denies_without_any_proof(self):
# The #661 hard gate is untouched by the conjunction.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertFalse(result["apply_gate"]["drain_gate_allow"])
self.assertTrue(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"])
self.assertEqual(result["incident"]["kind"], "restart_drain_gate_denied")
def test_apply_denies_on_malformed_proof(self):
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json="{not valid json",
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertFalse(result["apply_authorized"])
self.assertTrue(any("invalid drain_proof_json" in reason
for reason in result["apply_gate"]["reasons"]))
def test_tool_never_restarts_on_any_path(self):
for kwargs in (
{"restart_class": "client_reconnect"},
{"restart_class": "full_mcp_restart", "dry_run": False},
{"restart_class": "host_restart", "dry_run": False,
"request_break_glass": True},
):
with self.subTest(**kwargs):
result = self._call(role="operator", env={
CONTROLLER_APPROVAL_ENV: "yes", BREAK_GLASS_ENV: "yes"},
**kwargs)
self.assertFalse(result["restart_performed"])
self.assertFalse(result["apply_supported"])
if __name__ == "__main__":
unittest.main()
+117
View File
@@ -105,3 +105,120 @@ def test_cross_links_do_not_embed_secrets():
text = _read(path)
for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"):
assert marker not in text, f"{path} contains {marker!r}"
# --- Coordinator doc stays in lock-step with the tool (#886 review blocker B2) --
#
# PR #882 moved the #661 drain-proof hard gate *into* gitea_request_mcp_restart,
# but the coordinator document still described the proof as "a separate child"
# and omitted both new parameters. Nothing referenced that document, so nothing
# caught the drift. These tests bind the prose to the real signature.
COORDINATOR_DOC = REPO_ROOT / "docs" / "mcp-restart-coordinator.md"
# Affirmative claims that were accurate before #661 landed and are now false.
# Matched against whitespace-normalized text so re-wrapping cannot hide them.
# Deliberately not the bare phrase "a separate child": the corrected prose uses
# it in a negation ("no longer a separate child operation"), and a guard that
# forbids naming the old behaviour would block explaining that it changed.
STALE_PRE_661_PHRASES = (
"gated by a drain proof (a separate child)",
"is a later child gated by a drain proof",
"mutative apply path is explicitly out of scope",
"apply is gated by a drain proof (a separate child)",
)
def _documented_signature_block() -> str:
"""The fenced signature block for the tool, as published in the doc."""
text = _read(COORDINATOR_DOC)
marker = "gitea_request_mcp_restart("
start = text.index(marker)
end = text.index("```", start)
return text[start:end]
def test_documented_signature_matches_the_real_tool_signature():
import inspect
import gitea_mcp_server
block = _documented_signature_block()
real = inspect.signature(gitea_mcp_server.gitea_request_mcp_restart)
for name in real.parameters:
assert name in block, (
f"docs/mcp-restart-coordinator.md documents no {name!r} parameter; "
"the published signature has drifted from the tool"
)
def test_drain_proof_and_break_glass_parameters_are_documented():
block = _documented_signature_block()
for name in ("drain_proof_json", "request_break_glass"):
assert name in block, f"signature block missing {name}"
def test_restart_class_and_target_scoping_parameters_survive():
block = _documented_signature_block()
for name in ("restart_class", "target_session_id", "target_role",
"target_connector"):
assert name in block, f"signature block lost #663 parameter {name}"
def test_gate_is_documented_as_executing_inside_this_tool():
lower = _read(COORDINATOR_DOC).lower()
assert "inside this tool" in lower, (
"the coordinator doc must state that the drain-proof gate executes in "
"gitea_request_mcp_restart, not in a later child"
)
assert "no longer a separate child operation" in lower
def test_stale_pre_661_wording_cannot_return():
normalized = " ".join(_read(COORDINATOR_DOC).split()).lower()
for phrase in STALE_PRE_661_PHRASES:
assert phrase not in normalized, (
f"stale pre-#661 wording returned to the coordinator doc: {phrase!r}"
)
def test_dry_run_versus_apply_behavior_is_documented():
lower = _read(COORDINATOR_DOC).lower()
assert "dry_run=true" in lower and "dry_run=false" in lower
assert "apply_supported" in lower and "restart_performed" in lower
assert "never restarts anything" in lower
def test_authorization_ordering_and_conjunction_are_documented():
text = _read(COORDINATOR_DOC)
lower = text.lower()
assert "authorization ordering" in lower
assert "allow_restart" in text
assert "apply_authorized" in text
# The conjunction itself, and the attribution fields behind it.
assert "gate.allow and allow_restart" in text
for field in ("drain_gate_allow", "restart_class_authorized"):
assert field in text, f"doc omits apply_gate.{field}"
def test_break_glass_scope_is_documented_as_drain_proof_only():
text = _read(COORDINATOR_DOC)
lower = text.lower()
assert "break-glass" in lower
assert "drain proof only" in lower, (
"doc must state break-glass never bypasses the restart-class matrix"
)
assert "GITEA_BREAKGLASS_RESTART_AUTHORIZATION" in text
def test_fail_closed_on_apply_is_documented():
lower = _read(COORDINATOR_DOC).lower()
assert "fail closed" in lower
for condition in ("expired", "unclean", "tampered", "stale"):
assert condition in lower, f"fail-closed list omits {condition!r}"
def test_coordinator_doc_embeds_no_secrets():
text = _read(COORDINATOR_DOC)
for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"):
assert marker not in text, f"{COORDINATOR_DOC} contains {marker!r}"
+232
View File
@@ -0,0 +1,232 @@
"""Permission, drain, routing, and audit matrix for restart classes (#663)."""
from __future__ import annotations
import os
from datetime import datetime, timezone
import restart_coordinator as rc
NOW = datetime(2026, 7, 24, 20, 0, tzinfo=timezone.utc)
def _inventory() -> dict:
return {
"inventory_complete": True,
"sessions": [
{
"session_id": "requester",
"role": "author",
"profile": "prgs-author",
"pid": os.getpid(),
"status": "active",
"last_heartbeat_at": NOW.isoformat(),
},
{
"session_id": "reviewer",
"role": "reviewer",
"profile": "prgs-reviewer",
"pid": os.getpid(),
"status": "active",
"last_heartbeat_at": NOW.isoformat(),
},
],
"leases": [
{
"lease_id": "review-lease",
"session_id": "reviewer",
"role": "reviewer",
"phase": "reviewing",
"work_kind": "pr",
"work_number": 900,
"worktree_path": "/tmp/review-900",
"freshness": {"freshness": "active"},
}
],
}
def _evaluate(
restart_class: rc.RestartClass,
*,
role: str = "controller",
permissions: tuple[str, ...] | None = None,
approved: bool = True,
operator: bool = True,
**targets,
):
return rc.evaluate_restart_impact(
_inventory(),
now=NOW,
requesting_session_id="requester",
restart_class=restart_class,
requester_role=role,
requester_permissions=(
permissions if permissions is not None
else rc.permissions_for_role(role)
),
controller_approved=approved,
operator_authorized=operator,
**targets,
)
def test_policy_table_covers_exactly_all_nine_classes():
assert set(rc.RESTART_CLASS_POLICIES) == set(rc.RestartClass)
assert len(rc.RESTART_CLASS_POLICIES) == 9
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items():
assert policy.restart_class is restart_class
assert policy.required_permission
assert policy.expected_blast_radius in {
rc.BLAST_NONE, rc.BLAST_LOW, rc.BLAST_MEDIUM, rc.BLAST_HIGH
}
assert policy.drain_requirement
assert policy.approval_requirement
assert policy.audit_requirement
assert policy.recovery_behavior
def test_permission_matrix_allows_each_class_with_exact_permission():
targets = {
rc.RestartClass.WORKER_RESTART: {"target_session_id": "reviewer"},
rc.RestartClass.ROLE_RUNTIME_RESTART: {"target_role": "reviewer"},
rc.RestartClass.CONNECTOR_RESTART: {"target_connector": "github"},
}
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items():
report = _evaluate(
restart_class,
permissions=(policy.required_permission,),
**targets.get(restart_class, {}),
)
assert report.permission_authorized, restart_class
assert report.role_authorized, restart_class
assert report.approval_satisfied, restart_class
assert report.audit_record["restart_class"] == restart_class.value
assert (
report.audit_record["required_permission"]
== policy.required_permission
)
def test_missing_or_nearby_permission_denies():
report = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
permissions=("mcp.restart.worker.request",),
target_role="reviewer",
)
assert report.verdict == rc.VERDICT_UNSAFE
assert not report.allow_restart
assert not report.permission_authorized
assert any("missing required permission" in r for r in report.reasons)
def test_unknown_restart_class_denies_fail_closed():
report = rc.evaluate_restart_impact(
_inventory(),
now=NOW,
restart_class="surprise_reboot",
requester_role="admin",
requester_permissions=("mcp.restart.host.request",),
controller_approved=True,
operator_authorized=True,
)
assert report.verdict == rc.VERDICT_UNSAFE
assert not report.allow_restart
assert report.restart_policy == {}
assert any("unknown restart class" in r for r in report.reasons)
def test_worker_roles_cannot_request_full_or_host_restart():
for role in rc.WORKER_ROLES:
granted = rc.permissions_for_role(role)
assert "mcp.restart.full.request" not in granted
assert "mcp.restart.host.request" not in granted
report = _evaluate(
rc.RestartClass.FULL_MCP_RESTART,
role=role,
permissions=granted,
)
assert not report.role_authorized
assert not report.allow_restart
def test_controller_approval_is_independent_of_permission():
report = _evaluate(
rc.RestartClass.WORKER_RESTART,
approved=False,
target_session_id="reviewer",
)
assert report.permission_authorized
assert not report.approval_satisfied
assert not report.allow_restart
def test_narrow_classes_do_not_inherit_full_drain_or_peer_lease_block():
for restart_class in (
rc.RestartClass.CLIENT_RECONNECT,
rc.RestartClass.SESSION_RECONNECT,
rc.RestartClass.CONFIGURATION_RELOAD,
):
report = _evaluate(restart_class)
assert not report.restart_policy["full_drain_required"]
assert report.counts["leases_disruptive"] == 0
assert report.counts["sessions_live_other"] == 0
assert report.counts["critical_sections"] == 0
assert report.counts["mutations"] == 0
assert report.allow_restart, (restart_class, report.reasons)
def test_client_reconnect_does_not_wait_for_unrelated_terminal_lock():
inventory = _inventory()
inventory["terminal_lock"] = {"terminal_pr": 901}
report = rc.evaluate_restart_impact(
inventory,
now=NOW,
requesting_session_id="requester",
restart_class=rc.RestartClass.CLIENT_RECONNECT,
requester_role="author",
requester_permissions=rc.permissions_for_role("author"),
)
assert report.allow_restart
assert report.terminal_lock is None
def test_scoped_restart_only_counts_named_target():
report = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
target_role="author",
)
assert report.counts["leases_disruptive"] == 0
assert report.affected_prs == []
assert report.allow_restart
reviewer = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
target_role="reviewer",
)
assert reviewer.counts["leases_disruptive"] == 1
assert reviewer.affected_prs == [900]
assert not reviewer.allow_restart
def test_missing_scoped_target_denies_instead_of_widening():
for restart_class in (
rc.RestartClass.WORKER_RESTART,
rc.RestartClass.ROLE_RUNTIME_RESTART,
rc.RestartClass.CONNECTOR_RESTART,
):
report = _evaluate(restart_class)
assert not report.allow_restart
assert any("target required" in r for r in report.reasons)
def test_only_full_and_host_classes_require_full_drain():
requiring_full = {
restart_class
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items()
if policy.full_drain_required
}
assert requiring_full == {
rc.RestartClass.FULL_MCP_RESTART,
rc.RestartClass.HOST_RESTART,
}
+6
View File
@@ -444,6 +444,12 @@ class TestAuditEmission(unittest.TestCase):
)
self.assertEqual(record["target"]["namespace"], NAMESPACE)
self.assertEqual(record["target"]["mode"], "restart")
self.assertEqual(
record["target"]["restart_class"], "role_runtime_restart"
)
self.assertEqual(
record["metadata"]["restart_class"], "role_runtime_restart"
)
self.assertEqual(record["result"], console_audit.RESULT_ALLOWED)
self.assertEqual(record["actor"]["subject"], "[email protected]")
self.assertFalse(record["metadata"]["process_kill_executed"])
+739
View File
@@ -0,0 +1,739 @@
"""Tests for the Runtime and session view (Phase 1, #641).
Covers clean and stale session rendering, contamination marker surfacing,
worktree binding display, sanctioned recovery links (no pkill), nav/live
status, and the JSON API export.
Also pins the two invariants a reviewer found violated at head a81db754:
degraded ownership sections must render as *unknown* rather than as an
affirmative "none"/"unbound", and contamination payload text must be redacted
at the display boundary rather than trusted from the write-time denylist.
"""
from __future__ import annotations
import os
import sys
import unittest
from pathlib import Path
from unittest import mock
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from tests.webui_testclient import TestClient
from webui.app import create_app
from webui.inventory import (
AUTHORITY_CONTROL_PLANE_DB,
AUTHORITY_FILESYSTEM,
InventorySection,
InventorySnapshot,
STATUS_DEGRADED,
STATUS_OK,
STATUS_UNAVAILABLE,
)
from webui.nav import NAV_GROUPS, STUB_PAGES, iter_nav_items
from webui.runtime_health import FileHash, RuntimeSnapshot
from webui.session_loader import (
ContaminationMarker,
SessionRow,
SessionViewSnapshot,
_build_session_rows,
_inspect_contamination,
load_session_view_snapshot,
snapshot_to_dict,
)
from webui.session_views import render_sessions_page
def _runtime(
*,
stale: str | None = None,
profile: str = "prgs-author",
role: str = "author",
) -> RuntimeSnapshot:
return RuntimeSnapshot(
project_id="gitea-tools",
repo_root="/tmp/repo",
remote="prgs",
host="gitea.prgs.cc",
profile_name=profile,
role_kind=role,
config_model="v2-contexts",
profile_mode="dynamic-profile",
profile_source="config file profile",
authenticated_username="jcwalker3",
identity_error=None,
repo_sha="a" * 40,
remote_master_sha="a" * 40,
commits_behind_master=0,
stale_runtime_warning=stale,
shell_health={"shell_use_allowed": True, "consecutive_spawn_failures": 0},
workflow_hashes=(
FileHash(label="SKILL.md", path="skills/llm-project-workflow/SKILL.md", sha256="abc"),
),
schema_hashes=(),
restart_guidance="docs/mcp-namespace-eof-recovery.md",
fetch_error=None,
)
def _inventory(
*,
sessions: tuple[dict, ...] = (),
leases: tuple[dict, ...] = (),
locks: tuple[dict, ...] = (),
worktrees: tuple[dict, ...] = (),
namespaces: tuple[dict, ...] = (),
statuses: dict[str, str] | None = None,
) -> InventorySnapshot:
"""Build a snapshot; ``statuses`` degrades named sections (default all ok)."""
status_of = statuses or {}
def _status(name: str) -> str:
return status_of.get(name, STATUS_OK)
sections = (
InventorySection(
name="sessions",
authority=AUTHORITY_CONTROL_PLANE_DB,
status=_status("sessions"),
items=sessions,
),
InventorySection(
name="leases",
authority=AUTHORITY_CONTROL_PLANE_DB,
status=_status("leases"),
items=leases,
),
InventorySection(
name="locks",
authority=AUTHORITY_FILESYSTEM,
status=_status("locks"),
items=locks,
),
InventorySection(
name="worktrees",
authority=AUTHORITY_FILESYSTEM,
status=_status("worktrees"),
items=worktrees,
),
InventorySection(
name="namespaces",
authority=AUTHORITY_FILESYSTEM,
status=_status("namespaces"),
items=namespaces
or (
{
"profile_name": "prgs-author",
"role": "author",
"mcp_namespace": "gitea-author",
"capability_summary": {
"can_author": True,
"can_review": False,
"can_merge": False,
},
"active": True,
},
),
reason="only the profile serving this web process is observable",
),
)
index = {section.name: section for section in sections}
return InventorySnapshot(
generated_at="2026-07-25T00:00:00+00:00",
sections=sections,
collisions=(),
correlations=(),
scan_ms=1.0,
_section_index=index,
)
def _clean_session() -> dict:
return {
"session_id": "prgs-author-111-clean",
"role": "author",
"profile": "prgs-author",
"namespace": "gitea-author",
"pid": 1111,
"pid_alive": True,
"status": "active",
"started_at": "2026-07-25T00:00:00Z",
"last_heartbeat_at": "2026-07-25T01:00:00Z",
}
def _stale_session() -> dict:
return {
"session_id": "prgs-author-222-stale",
"role": "author",
"profile": "prgs-author",
"namespace": "gitea-author",
"pid": 2222,
"pid_alive": False,
"status": "active",
"started_at": "2026-07-24T00:00:00Z",
"last_heartbeat_at": "2026-07-24T01:00:00Z",
}
class TestBuildSessionRows(unittest.TestCase):
def test_clean_session_has_no_stale_or_contamination_flags(self):
inventory = _inventory(
sessions=(_clean_session(),),
leases=(
{
"lease_id": "lease-clean",
"session_id": "prgs-author-111-clean",
"status": "active",
"expired": False,
"work_kind": "issue",
"work_number": 641,
},
),
locks=(
{
"issue_number": 641,
"branch_name": "feat/issue-641-runtime-session-view",
"worktree_path": "~/Development/Gitea-Tools/branches/feat-issue-641",
"live": True,
},
),
)
rows = _build_session_rows(inventory, contamination=())
self.assertEqual(len(rows), 1)
row = rows[0]
self.assertEqual(row.session_id, "prgs-author-111-clean")
self.assertEqual(row.role, "author")
self.assertEqual(row.namespace, "gitea-author")
self.assertEqual(row.pid_alive, True)
self.assertEqual(row.lease_ids, ("lease-clean",))
self.assertEqual(row.work_refs, ("issue#641",))
self.assertTrue(row.worktree_paths)
self.assertEqual(row.stale_flags, ())
self.assertEqual(row.contamination_flags, ())
def test_stale_session_flags_dead_pid(self):
inventory = _inventory(sessions=(_stale_session(),))
rows = _build_session_rows(inventory, contamination=())
self.assertEqual(rows[0].stale_flags, ("pid-dead",))
def test_contamination_marker_binds_to_session(self):
inventory = _inventory(sessions=(_clean_session(),))
marker = ContaminationMarker(
kind="runtime_recovery_contamination",
on_disk=True,
has_payload=True,
summary="manual daemon kill",
reason_class="manual_daemon_kill",
session_id="prgs-author-111-clean",
role="author",
command_summary="pkill -f mcp_server.py",
cleared=False,
)
rows = _build_session_rows(inventory, contamination=(marker,))
self.assertIn("runtime_recovery_contamination", rows[0].contamination_flags)
def test_process_wide_contamination_surfaces_on_all_sessions(self):
inventory = _inventory(sessions=(_clean_session(), _stale_session()))
marker = ContaminationMarker(
kind="stable_branch_contamination",
on_disk=True,
has_payload=True,
summary="direct master push attempt",
reason_class="stable_branch_push",
session_id=None,
cleared=False,
)
rows = _build_session_rows(inventory, contamination=(marker,))
self.assertEqual(len(rows), 2)
for row in rows:
self.assertTrue(
any("stable_branch_contamination" in f for f in row.contamination_flags)
)
class TestRenderSessionsPage(unittest.TestCase):
def _snapshot(
self,
*,
sessions: tuple[dict, ...],
contamination: tuple[ContaminationMarker, ...] = (),
stale_runtime: str | None = None,
) -> SessionViewSnapshot:
inventory = _inventory(
sessions=sessions,
leases=(
{
"lease_id": "lease-1",
"session_id": sessions[0]["session_id"] if sessions else "",
"status": "active",
"expired": False,
"work_kind": "issue",
"work_number": 641,
},
)
if sessions
else (),
locks=(
{
"issue_number": 641,
"worktree_path": "branches/feat-issue-641",
},
)
if sessions
else (),
worktrees=(
{
"rel_path": "branches/feat-issue-641",
"branch": "feat/issue-641-runtime-session-view",
"classification": "active_issue_work",
"registered_worktree": True,
"dirty": False,
},
),
)
rows = _build_session_rows(inventory, contamination)
return SessionViewSnapshot(
runtime=_runtime(stale=stale_runtime),
inventory=inventory,
sessions=rows,
contamination_markers=contamination,
)
def test_clean_session_render(self):
html = render_sessions_page(self._snapshot(sessions=(_clean_session(),)))
self.assertIn("Runtime and sessions", html)
self.assertIn("prgs-author-111-clean", html)
self.assertIn("gitea-author", html)
self.assertIn("branches/feat-issue-641", html)
self.assertIn("Sanctioned recovery", html)
self.assertIn("docs/mcp-namespace-eof-recovery.md", html)
# Recovery section must name reconnect and forbid manual kill.
recovery_idx = html.lower().find("sanctioned recovery")
self.assertGreaterEqual(recovery_idx, 0)
recovery = html[recovery_idx:].lower()
self.assertIn("reconnect", recovery)
self.assertIn("contamination", recovery)
self.assertIn("not recovery", recovery)
self.assertNotIn("run pkill", recovery)
self.assertNotIn("killall", recovery)
def test_stale_session_render(self):
html = render_sessions_page(self._snapshot(sessions=(_stale_session(),)))
self.assertIn("prgs-author-222-stale", html)
self.assertIn("pid-dead", html)
self.assertIn("badge-stale", html)
def test_contamination_render_is_not_silent(self):
marker = ContaminationMarker(
kind="runtime_recovery_contamination",
on_disk=True,
has_payload=True,
summary="manual kill",
reason_class="manual_daemon_kill",
session_id="prgs-author-111-clean",
command_summary="pkill -f mcp_server.py",
cleared=False,
)
html = render_sessions_page(
self._snapshot(sessions=(_clean_session(),), contamination=(marker,))
)
self.assertIn("Contamination markers", html)
self.assertIn("runtime_recovery_contamination", html)
self.assertIn("ACTIVE", html)
self.assertIn("badge-blocked", html)
def test_stale_runtime_banner(self):
html = render_sessions_page(
self._snapshot(
sessions=(_clean_session(),),
stale_runtime="server behind master by 3 commits",
)
)
self.assertIn("Stale runtime", html)
self.assertIn("server behind master", html)
class TestSessionLoaderComposition(unittest.TestCase):
def test_load_with_injected_sources(self):
inventory = _inventory(sessions=(_clean_session(), _stale_session()))
snap = load_session_view_snapshot(
load_runtime=lambda: _runtime(),
load_inventory=lambda: inventory,
inspect_contamination=lambda **_k: {
"on_disk": False,
"has_payload": False,
"summary": "absent",
},
load_contamination_payload=lambda **_k: None,
)
self.assertEqual(len(snap.sessions), 2)
self.assertEqual(snap.stale_session_count, 1)
self.assertEqual(snap.contaminated_session_count, 0)
data = snapshot_to_dict(snap)
self.assertEqual(data["view"], "runtime-sessions")
self.assertEqual(data["issue"], 641)
self.assertTrue(data["read_only"])
self.assertEqual(data["session_counts"]["total"], 2)
self.assertEqual(data["session_counts"]["stale"], 1)
self.assertIn("recovery_docs", data)
class TestSessionsRoutes(unittest.TestCase):
def setUp(self):
self.client = TestClient(create_app())
inventory = _inventory(
sessions=(_clean_session(), _stale_session()),
leases=(
{
"lease_id": "lease-x",
"session_id": "prgs-author-111-clean",
"status": "active",
"expired": False,
"work_kind": "issue",
"work_number": 641,
},
),
locks=(
{
"issue_number": 641,
"worktree_path": "branches/feat-issue-641",
},
),
worktrees=(
{
"rel_path": "branches/feat-issue-641",
"branch": "feat/issue-641-runtime-session-view",
"classification": "active_issue_work",
"registered_worktree": True,
"dirty": False,
},
),
)
rows = _build_session_rows(inventory, contamination=())
self.snapshot = SessionViewSnapshot(
runtime=_runtime(stale="stale for test"),
inventory=inventory,
sessions=rows,
contamination_markers=(),
)
self._patch = mock.patch(
"webui.app.load_session_view_snapshot",
return_value=self.snapshot,
)
self._patch.start()
def tearDown(self):
self._patch.stop()
def test_sessions_page_live(self):
response = self.client.get("/sessions")
self.assertEqual(response.status_code, 200)
self.assertIn("Runtime and sessions", response.text)
self.assertIn("prgs-author-111-clean", response.text)
self.assertIn("prgs-author-222-stale", response.text)
self.assertIn("pid-dead", response.text)
self.assertIn("Sanctioned recovery", response.text)
self.assertNotIn("Phase 1 shell placeholder", response.text)
self.assertNotIn("child issue of #425", response.text.lower())
def test_api_sessions_json(self):
for path in ("/api/sessions", "/api/v1/sessions"):
response = self.client.get(path)
self.assertEqual(response.status_code, 200, path)
data = response.json()
self.assertEqual(data["view"], "runtime-sessions")
self.assertEqual(data["session_counts"]["total"], 2)
self.assertEqual(data["session_counts"]["stale"], 1)
self.assertTrue(data["read_only"])
self.assertEqual(data["mutations"], [])
def test_nav_marks_sessions_live(self):
sessions_items = [
item for item in iter_nav_items() if item.href == "/sessions"
]
self.assertEqual(len(sessions_items), 1)
self.assertEqual(sessions_items[0].status, "live")
self.assertNotIn("/sessions", STUB_PAGES)
# Home page should not mark Sessions as stub.
home = self.client.get("/")
self.assertEqual(home.status_code, 200)
self.assertIn('href="/sessions"', home.text)
# Stub marker only appears next to remaining stub destinations.
self.assertNotIn(
'href="/sessions">Sessions</a> <span class="muted">(stub)</span>',
home.text,
)
class TestDegradedOwnershipAuthority(unittest.TestCase):
"""B1: a section that could not be read must never render as absence."""
def _snapshot(self, inventory: InventorySnapshot) -> SessionViewSnapshot:
return SessionViewSnapshot(
runtime=_runtime(),
inventory=inventory,
sessions=_build_session_rows(inventory, contamination=()),
contamination_markers=(),
)
def test_unavailable_leases_mark_row_authority_unproven(self):
inventory = _inventory(
sessions=(_clean_session(),),
statuses={"leases": STATUS_UNAVAILABLE},
)
row = _build_session_rows(inventory, contamination=())[0]
self.assertEqual(row.lease_ids, ())
self.assertEqual(row.lease_authority, STATUS_UNAVAILABLE)
# Worktree binding is correlated through lease work numbers, so it
# inherits the unreadable lease section.
self.assertEqual(row.worktree_authority, STATUS_UNAVAILABLE)
self.assertFalse(row.ownership_authority_complete)
def test_readable_locks_are_not_reported_unbound_when_leases_degrade(self):
# The narrow variant: locks hold a real worktree_path and read cleanly,
# but the lease section that supplies the correlating work number does
# not. The row must say unknown, not "unbound".
inventory = _inventory(
sessions=(_clean_session(),),
locks=(
{
"issue_number": 641,
"worktree_path": "branches/feat-issue-641",
},
),
statuses={"leases": STATUS_DEGRADED},
)
row = _build_session_rows(inventory, contamination=())[0]
self.assertEqual(row.worktree_paths, ())
self.assertEqual(row.worktree_authority, STATUS_DEGRADED)
self.assertFalse(row.ownership_authority_complete)
def test_degraded_render_says_unknown_not_none_or_unbound(self):
inventory = _inventory(
sessions=(_clean_session(),),
statuses={"leases": STATUS_UNAVAILABLE, "locks": STATUS_UNAVAILABLE},
)
html = render_sessions_page(self._snapshot(inventory))
self.assertIn("unknown (inventory unavailable)", html)
self.assertIn("authority unproven", html)
self.assertIn("Ownership authority incomplete", html)
# The affirmative-absence strings must be gone from the row entirely.
self.assertNotIn(">none<", html)
self.assertNotIn(">unbound<", html)
def test_clean_inventory_still_renders_affirmative_absence(self):
# Guards against over-correcting B1 into "everything is unknown".
inventory = _inventory(sessions=(_clean_session(),))
html = render_sessions_page(self._snapshot(inventory))
self.assertIn(">none<", html)
self.assertIn(">unbound<", html)
# The column legend mentions "unknown (inventory …)" as static copy, so
# assert on the per-row marker and the concrete statuses instead.
self.assertNotIn("authority unproven", html)
self.assertNotIn("unknown (inventory unavailable)", html)
self.assertNotIn("unknown (inventory degraded)", html)
self.assertNotIn("Ownership authority incomplete", html)
def test_json_export_carries_snapshot_and_per_row_authority(self):
inventory = _inventory(
sessions=(_clean_session(),),
statuses={"locks": STATUS_UNAVAILABLE},
)
data = snapshot_to_dict(self._snapshot(inventory))
self.assertFalse(data["ownership_authority_complete"])
self.assertEqual(
data["ownership_section_status"]["locks"], STATUS_UNAVAILABLE
)
self.assertEqual(data["ownership_section_status"]["leases"], STATUS_OK)
self.assertIn("unknown, not unowned", data["ownership_note"])
row = data["sessions"][0]
self.assertTrue(row["lease_authority_complete"])
self.assertFalse(row["worktree_authority_complete"])
self.assertEqual(row["worktree_authority"], STATUS_UNAVAILABLE)
self.assertFalse(row["ownership_authority_complete"])
self.assertIn("unknown, not unowned", row["ownership_note"])
def test_json_export_is_affirmative_when_every_source_reads(self):
inventory = _inventory(sessions=(_clean_session(),))
data = snapshot_to_dict(self._snapshot(inventory))
self.assertTrue(data["ownership_authority_complete"])
self.assertTrue(data["sessions"][0]["ownership_authority_complete"])
def test_missing_session_list_is_not_reported_as_no_sessions(self):
inventory = _inventory(statuses={"sessions": STATUS_UNAVAILABLE})
html = render_sessions_page(self._snapshot(inventory))
self.assertIn("could not be read", html)
self.assertIn("not evidence that no sessions exist", html)
def test_expired_lease_flags_row_as_stale(self):
inventory = _inventory(
sessions=(_clean_session(),),
leases=(
{
"lease_id": "lease-expired-1",
"session_id": "prgs-author-111-clean",
"status": "active",
"expired": True,
"work_kind": "issue",
"work_number": 641,
},
),
)
row = _build_session_rows(inventory, contamination=())[0]
self.assertIn("lease-expired", row.stale_flags)
self.assertIn("active-lease-past-expiry", row.stale_flags)
class TestContaminationRedaction(unittest.TestCase):
"""B2: marker payload text is redacted at the display boundary."""
def _marker(self, payload: dict) -> ContaminationMarker:
return _inspect_contamination(
"runtime_recovery_contamination",
remote="prgs",
inspect=lambda **_k: {
"on_disk": True,
"has_payload": True,
"summary": "",
},
load=lambda **_k: payload,
)
def test_home_paths_are_collapsed(self):
home = os.path.expanduser("~")
marker = self._marker(
{"command_summary": f"pkill -f {home}/Development/Gitea-Tools/x.py"}
)
self.assertNotIn(home, marker.command_summary)
self.assertIn("~/Development/Gitea-Tools/x.py", marker.command_summary)
def test_secrets_missed_by_the_write_time_denylist_are_redacted(self):
# Each of these was verified in review to survive
# stable_branch_push_guard.redact_command untouched.
cases = (
("curl -H 'X-Api-Key: SUPERSECRET123' https://example.invalid", "SUPERSECRET123"),
("cmd --password hunter2 origin master", "hunter2"),
("PRIVATE_KEY=abc123 python deploy.py", "abc123"),
("fetch https://user:[email protected]/x.git", "user:pw"),
)
for raw, secret in cases:
with self.subTest(raw=raw):
marker = self._marker({"command_summary": raw})
self.assertNotIn(secret, marker.command_summary)
self.assertIn("[redacted]", marker.command_summary)
def test_command_summary_is_redacted_not_removed(self):
# It is legitimate #630 evidence: the operator must still see which
# daemon was killed.
marker = self._marker(
{
"command_summary": "pkill -f gitea_mcp_server.py",
"reason_class": "manual_daemon_kill",
"session_id": "prgs-author-111-clean",
"role": "author",
}
)
self.assertIn("pkill -f gitea_mcp_server.py", marker.command_summary)
self.assertEqual(marker.reason_class, "manual_daemon_kill")
self.assertEqual(marker.session_id, "prgs-author-111-clean")
self.assertEqual(marker.role, "author")
def test_rendered_page_exposes_no_home_path_from_a_marker(self):
home = os.path.expanduser("~")
marker = self._marker(
{
"command_summary": f"pkill -f {home}/Development/Gitea-Tools/x.py",
"reason_class": "manual_daemon_kill",
}
)
inventory = _inventory(sessions=(_clean_session(),))
html = render_sessions_page(
SessionViewSnapshot(
runtime=_runtime(),
inventory=inventory,
sessions=_build_session_rows(inventory, (marker,)),
contamination_markers=(marker,),
)
)
self.assertIn("Contamination markers", html)
self.assertNotIn(home, html)
class TestSessionsPageEscaping(unittest.TestCase):
"""Hostile values from every rendered source stay inert (N2)."""
HOSTILE = '<script>alert("xss")</script>'
def test_hostile_session_and_marker_values_are_escaped(self):
session = dict(_clean_session())
session["session_id"] = f"sid-{self.HOSTILE}"
session["role"] = self.HOSTILE
session["profile"] = self.HOSTILE
session["namespace"] = self.HOSTILE
session["status"] = self.HOSTILE
inventory = _inventory(
sessions=(session,),
leases=(
{
"lease_id": self.HOSTILE,
"session_id": session["session_id"],
"status": "active",
"expired": False,
"work_kind": self.HOSTILE,
"work_number": 641,
},
),
locks=(
{
"issue_number": 641,
"worktree_path": self.HOSTILE,
},
),
)
marker = ContaminationMarker(
kind="runtime_recovery_contamination",
on_disk=True,
has_payload=True,
summary=self.HOSTILE,
reason_class=self.HOSTILE,
session_id=session["session_id"],
role=self.HOSTILE,
command_summary=self.HOSTILE,
cleared=False,
)
html = render_sessions_page(
SessionViewSnapshot(
runtime=_runtime(),
inventory=inventory,
sessions=_build_session_rows(inventory, (marker,)),
contamination_markers=(marker,),
)
)
self.assertNotIn("<script>", html)
self.assertNotIn('alert("xss")', html)
self.assertIn("&lt;script&gt;", html)
def test_hostile_values_in_a_degraded_render_are_escaped(self):
inventory = _inventory(
sessions=(dict(_clean_session(), session_id=f"sid-{self.HOSTILE}"),),
statuses={"leases": STATUS_UNAVAILABLE, "locks": STATUS_DEGRADED},
)
html = render_sessions_page(
SessionViewSnapshot(
runtime=_runtime(),
inventory=inventory,
sessions=_build_session_rows(inventory, contamination=()),
contamination_markers=(),
)
)
self.assertNotIn("<script>", html)
self.assertIn("&lt;script&gt;", html)
self.assertIn("unknown (inventory", html)
if __name__ == "__main__":
unittest.main()