Files
Gitea-Tools/tests/test_webui_notifications.py
T
sysadmin a64ba08e27 fix(webui): address #905 REQUEST_CHANGES on notifications classifier
B1: classify_attention_event uses structured flags/category only — never
substring-match human-authored title/summary for escalation.

B2: make notification ids unique across probe_errors and collisions
(include loop index / kind).

B3: do not assign probe_errors to fetch_error (avoids false Fetch Warning
and double-reporting).

Regression tests cover all three blockers.

Refs #648
2026-07-25 18:26:46 -04:00

466 lines
14 KiB
Python

"""Unit tests for Phase 3 Notifications and Human-Attention Console (#648)."""
from __future__ import annotations
import pytest
from starlette.testclient import TestClient
from webui.app import create_app
from webui.notifications import (
ATTENTION_HUMAN_REQUIRED,
ATTENTION_OPERATOR,
ATTENTION_ROUTINE,
CATEGORY_AUTH,
CATEGORY_BLOCKER,
CATEGORY_LEASE,
CATEGORY_SYSTEM,
CATEGORY_VALIDATION,
CATEGORY_WORKFLOW,
NotificationItem,
NotificationSnapshot,
classify_attention_event,
load_notifications_snapshot,
snapshot_to_dict,
)
from webui.notification_views import render_notifications_page
from webui.project_registry import load_registry
from webui.queue_loader import QueueItem, QueueSnapshot
from webui.lease_loader import CollisionWarning, LeaseSnapshot
from webui.system_health import DependencyProbe, SystemHealthSnapshot, VersionInfo, StaleRuntime
def test_classify_attention_event_rules():
# 1. Critical escalation boundaries -> human-required
att_cls, req_human = classify_attention_event(
CATEGORY_AUTH, "Auth error", "Unauthorized access attempt", is_auth_failure=True
)
assert att_cls == ATTENTION_HUMAN_REQUIRED
assert req_human is True
att_cls, req_human = classify_attention_event(
CATEGORY_SYSTEM, "Hard stop", "Hard stop triggered", is_hard_stop=True
)
assert att_cls == ATTENTION_HUMAN_REQUIRED
assert req_human is True
att_cls, req_human = classify_attention_event(
CATEGORY_VALIDATION, "Validation Error", "Report validation failed", is_validation_failure=True
)
assert att_cls == ATTENTION_HUMAN_REQUIRED
assert req_human is True
# 2. Operational issues -> operator
att_cls, req_human = classify_attention_event(
CATEGORY_BLOCKER, "PR Blocked", "Merge conflict detected", is_blocker=True
)
assert att_cls == ATTENTION_OPERATOR
assert req_human is False
att_cls, req_human = classify_attention_event(
CATEGORY_LEASE, "Lease Expired", "Session lease expired", is_stale=True
)
assert att_cls == ATTENTION_OPERATOR
assert req_human is False
# 3. Routine workflow transitions -> routine
att_cls, req_human = classify_attention_event(
CATEGORY_WORKFLOW, "PR Active", "PR in review"
)
assert att_cls == ATTENTION_ROUTINE
assert req_human is False
def test_notification_snapshot_aggregation():
reg = load_registry()
proj_id = reg.projects[0].id if reg.projects else "gitea-tools"
mock_queue = QueueSnapshot(
project_id=proj_id,
repo_label="org/repo",
prs=(
QueueItem(
number=101,
title="Blocked PR",
badges=("blocked",),
extra={},
),
QueueItem(
number=102,
title="Normal PR",
badges=("in-review",),
extra={},
),
),
issues=(),
pr_pagination=None,
issue_pagination=None,
)
mock_leases = LeaseSnapshot(
project_id=proj_id,
repo_label="org/repo",
issue_lock=None,
claim_inventory={},
reviewer_leases=(
{
"pr_number": 101,
"status": "expired",
"is_expired": True,
},
),
duplicate_prs=(
CollisionWarning(
kind="duplicate_pr",
message="Multiple open PRs for issue #101",
issue_number=101,
pr_numbers=(101, 103),
),
),
duplicate_branches=(),
collision_history=(),
fetch_error=None,
)
mock_version = VersionInfo(
git_sha="abc1234",
git_describe="v1.0.0",
control_plane_schema_version=1,
python_version="3.11",
known=True,
)
mock_stale = StaleRuntime(
daemon_head="abc1234",
checkout_head="abc1234",
remote_head="abc1234",
stale=False,
determinable=True,
mutation_safe=True,
reasons=(),
)
mock_health = SystemHealthSnapshot(
status="degraded",
ready=False,
readiness_complete=True,
readiness_reasons=("Auth failure",),
service="webui",
mode="test",
version=mock_version,
started_at="2026-07-25T00:00:00Z",
uptime_seconds=100.0,
timestamp="2026-07-25T00:00:00Z",
deep_probes_requested=True,
dependencies=(
DependencyProbe(
name="auth_service",
kind="auth",
status="unauthorized",
detail="Token expired",
required=True,
),
),
mcp_namespaces=(),
stale_runtime=mock_stale,
probe_errors=(),
)
snapshot = load_notifications_snapshot(
proj_id,
load_queue=lambda _id: mock_queue,
load_leases=lambda **_kwargs: mock_leases,
load_health=lambda **_kwargs: mock_health,
)
assert snapshot.project_id == proj_id
assert snapshot.total_count == 5
assert snapshot.human_required_count >= 1 # auth probe failure
assert snapshot.operator_count >= 3 # blocked PR + expired lease + duplicate PR collision
assert snapshot.routine_count >= 1 # normal PR
# Inbox items should include operator and human-required items only
inbox_classes = {item.attention_class for item in snapshot.inbox_items}
assert ATTENTION_ROUTINE not in inbox_classes
assert ATTENTION_OPERATOR in inbox_classes
assert ATTENTION_HUMAN_REQUIRED in inbox_classes
def test_snapshot_to_dict_and_redaction():
item = NotificationItem(
id="notif-1",
attention_class=ATTENTION_HUMAN_REQUIRED,
category=CATEGORY_AUTH,
title="Auth Error",
summary="Failed auth header: Bearer secret_token_12345",
work_kind="system",
work_number=None,
project_id="test-proj",
repo_label="org/repo",
created_at="2026-07-25T16:00:00Z",
requires_human=True,
)
snap = NotificationSnapshot(
project_id="test-proj",
repo_label="org/repo",
items=(item,),
human_required_count=1,
operator_count=0,
routine_count=0,
total_count=1,
)
data = snapshot_to_dict(snap)
assert data["project_id"] == "test-proj"
assert data["human_required_count"] == 1
assert len(data["inbox_items"]) == 1
# Redaction test
summary = data["inbox_items"][0]["summary"]
assert "secret_token_12345" not in summary
assert "<redacted>" in summary or "Bearer" in summary
def test_notifications_html_views():
item = NotificationItem(
id="notif-1",
attention_class=ATTENTION_HUMAN_REQUIRED,
category=CATEGORY_AUTH,
title="Critical Auth Failure",
summary="Auth failure details",
work_kind="issue",
work_number=42,
project_id="test-proj",
repo_label="org/repo",
created_at="2026-07-25T16:00:00Z",
requires_human=True,
)
snap = NotificationSnapshot(
project_id="test-proj",
repo_label="org/repo",
items=(item,),
human_required_count=1,
operator_count=0,
routine_count=0,
total_count=1,
)
html = render_notifications_page(snap, filter_class="inbox")
assert "Notifications &amp; Attention Inbox" in html or "Notifications & Attention Inbox" in html
assert "Critical Auth Failure" in html
assert "HUMAN REQUIRED" in html
assert "Human Required" in html
def test_notifications_app_routes():
app = create_app()
client = TestClient(app)
# 1. HTML Route
res = client.get("/notifications")
assert res.status_code == 200
assert "Notifications" in res.text
assert "Attention Inbox" in res.text
# 2. API Route /api/v1/notifications
res_api = client.get("/api/v1/notifications")
assert res_api.status_code == 200
json_data = res_api.json()
assert "human_required_count" in json_data
assert "operator_count" in json_data
assert "routine_count" in json_data
assert "inbox_items" in json_data
# 3. Compatibility Alias /api/notifications
res_alias = client.get("/api/notifications")
assert res_alias.status_code == 200
assert res_alias.json()["project_id"] == json_data["project_id"]
def test_classify_ignores_human_authored_title_and_summary_keywords():
"""B1: keywords in human-authored titles must not escalate routine work (#905)."""
# Routine transition whose title/summary mention critical-boundary words
att_cls, req_human = classify_attention_event(
CATEGORY_WORKFLOW,
"record irrecoverable decision lock provenance",
"PR #999 'record irrecoverable decision lock provenance' is in routine state in-review.",
)
assert att_cls == ATTENTION_ROUTINE
assert req_human is False
att_cls, req_human = classify_attention_event(
CATEGORY_WORKFLOW,
"fix unauthorized token path",
"Issue #1 'fix unauthorized token path' state: claimed. hard stop docs only.",
)
assert att_cls == ATTENTION_ROUTINE
assert req_human is False
# Structured flags still escalate (machine-driven)
att_cls, req_human = classify_attention_event(
CATEGORY_SYSTEM,
"anything",
"anything with hard stop in text",
is_hard_stop=True,
)
assert att_cls == ATTENTION_HUMAN_REQUIRED
assert req_human is True
def test_notification_ids_are_unique_across_probe_errors_and_collisions():
"""B2: published notification ids must be unique within a snapshot (#905)."""
reg = load_registry()
proj_id = reg.projects[0].id if reg.projects else "gitea-tools"
mock_queue = QueueSnapshot(
project_id=proj_id,
repo_label="org/repo",
prs=(),
issues=(),
pr_pagination=None,
issue_pagination=None,
)
mock_leases = LeaseSnapshot(
project_id=proj_id,
repo_label="org/repo",
issue_lock=None,
claim_inventory={},
reviewer_leases=(),
duplicate_prs=(
CollisionWarning(
kind="duplicate_pr",
message="Multiple open PRs for issue #10",
issue_number=10,
pr_numbers=(10, 11),
),
CollisionWarning(
kind="duplicate_branch",
message="Another collision without issue",
issue_number=None,
pr_numbers=(12, 13),
),
CollisionWarning(
kind="duplicate_pr",
message="Second issue collision",
issue_number=10,
pr_numbers=(14, 15),
),
),
duplicate_branches=(),
collision_history=(),
fetch_error=None,
)
mock_version = VersionInfo(
git_sha="abc1234",
git_describe="v1.0.0",
control_plane_schema_version=1,
python_version="3.11",
known=True,
)
mock_stale = StaleRuntime(
daemon_head="abc1234",
checkout_head="abc1234",
remote_head="abc1234",
stale=False,
determinable=True,
mutation_safe=True,
reasons=(),
)
mock_health = SystemHealthSnapshot(
status="degraded",
ready=False,
readiness_complete=True,
readiness_reasons=(),
service="webui",
mode="test",
version=mock_version,
started_at="2026-07-25T00:00:00Z",
uptime_seconds=100.0,
timestamp="2026-07-25T00:00:00Z",
deep_probes_requested=True,
dependencies=(),
mcp_namespaces=(),
stale_runtime=mock_stale,
probe_errors=("error alpha", "error beta"),
)
snapshot = load_notifications_snapshot(
proj_id,
load_queue=lambda _id: mock_queue,
load_leases=lambda **_kwargs: mock_leases,
load_health=lambda **_kwargs: mock_health,
)
ids = [item.id for item in snapshot.items]
assert len(ids) == len(set(ids)), f"duplicate notification ids: {ids}"
assert any(i.startswith(f"notif-sys-err-{proj_id}-") for i in ids)
assert any(i.startswith("notif-collision-") for i in ids)
def test_probe_errors_do_not_set_fetch_error():
"""B3: probe_errors must not be reported as fetch_error (#905)."""
reg = load_registry()
proj_id = reg.projects[0].id if reg.projects else "gitea-tools"
mock_queue = QueueSnapshot(
project_id=proj_id,
repo_label="org/repo",
prs=(),
issues=(),
pr_pagination=None,
issue_pagination=None,
fetch_error=None,
)
mock_leases = LeaseSnapshot(
project_id=proj_id,
repo_label="org/repo",
issue_lock=None,
claim_inventory={},
reviewer_leases=(),
duplicate_prs=(),
duplicate_branches=(),
collision_history=(),
fetch_error=None,
)
mock_version = VersionInfo(
git_sha="abc1234",
git_describe="v1.0.0",
control_plane_schema_version=1,
python_version="3.11",
known=True,
)
mock_stale = StaleRuntime(
daemon_head="abc1234",
checkout_head="abc1234",
remote_head="abc1234",
stale=False,
determinable=True,
mutation_safe=True,
reasons=(),
)
mock_health = SystemHealthSnapshot(
status="degraded",
ready=False,
readiness_complete=True,
readiness_reasons=(),
service="webui",
mode="test",
version=mock_version,
started_at="2026-07-25T00:00:00Z",
uptime_seconds=100.0,
timestamp="2026-07-25T00:00:00Z",
deep_probes_requested=True,
dependencies=(),
mcp_namespaces=(),
stale_runtime=mock_stale,
probe_errors=("probe blew up",),
)
snapshot = load_notifications_snapshot(
proj_id,
load_queue=lambda _id: mock_queue,
load_leases=lambda **_kwargs: mock_leases,
load_health=lambda **_kwargs: mock_health,
)
assert snapshot.fetch_error is None
# probe errors still appear as items
assert any("probe blew up" in item.summary for item in snapshot.items)