gramps
f4caea09ad
Three gate runs in two days died the same way: every test passed, then the test host failed to exit, so vstest never printed its "Passed!" line and the gate waited until the harness gave up. One of those hours was a real product bug hiding inside the noise (a close handler that could refuse to close), which is exactly why the noise has to go. - The suite runs with a 300 s bound and per-test console output. - Output goes to a FILE, not command substitution: `timeout` kills the host with SIGTERM and a substituted buffer dies with it, which left the previous attempt with no summary at all. - If the summary is missing, the per-test lines decide: zero "Failed" among real results is a pass, and the counts are printed so the verdict is never taken on faith. - The orphaned testhost is swept afterwards. - `pipefail` no longer kills the gate when the summary grep finds nothing (the fallback already decided). Scope justification: Assets/starting-background.jpg is outside this unit — the creator's replacement art, checked and committed earlier today.
132 lines
6.3 KiB
Bash
132 lines
6.3 KiB
Bash
#!/usr/bin/env bash
|
|
# verify.sh — One gate before committing: clean build (0 warnings) + full test run + scope check.
|
|
# Usage: ./scripts/verify.sh "file1.cs" "file2.cs" ...
|
|
#
|
|
# Why a clean build? An incremental build SKIPS recompiling unchanged projects, so a
|
|
# "0 Warning(s)" from an incremental build can be a lie (CS8601 slipped past this way on
|
|
# 2026-08-29). This script forces a full rebuild so the 0-warning claim is only ever made
|
|
# against fresh compiler output.
|
|
#
|
|
# Requires WINDOWS dotnet (never Linux dotnet — it re-downloads the windowsdesktop packs
|
|
# over the slow 9p bridge; see docs/ai/environment.md -> Run). Reads the Windows path from the
|
|
# WSL mount.
|
|
#
|
|
# Two switches, both for running this on a machine somebody is using:
|
|
# FAST=1 skip the twelve heaviest test classes (527 tests, ~50s of test time) —
|
|
# most of their cost is the RealApp fixture: the WPF App, its XAML resources
|
|
# and audio/WebView2 startup, created once and charged to whichever UI test
|
|
# runs first. Full suite: 575 tests, ~1m50s.
|
|
# PHYSICAL_TESTS=1 include tests that drive the REAL cursor (SetCursorPos + mouse_event).
|
|
# Excluded by default: running them hijacks the machine you are typing on.
|
|
# (The old mouse-drag test is gone; its arithmetic is pure now — see
|
|
# DragReorderMathTests. The switch stays for anything of that kind later.)
|
|
# Scoped runs while working: dotnet vstest <dll> --TestCaseFilter:"FullyQualifiedName~TheClass"
|
|
|
|
set -euo pipefail
|
|
|
|
DOTNET="/mnt/c/Program Files/dotnet/dotnet.exe"
|
|
[ -x "$DOTNET" ] || { echo "❌ Windows dotnet not found at $DOTNET"; exit 1; }
|
|
|
|
ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
|
ROOTWIN="$(wslpath -w "$ROOT")"
|
|
|
|
echo "══ 1/4 DOC BUDGETS ══"
|
|
# The map stays cheap to read. A commit that PADS a capped file instead of replacing or
|
|
# moving detail fails here (see AGENTS.md -> Reading budget).
|
|
check_budget() {
|
|
local rel="$1" cap="$2" lines
|
|
[ -f "$ROOT/$rel" ] || { echo "✗ $rel is missing"; exit 1; }
|
|
lines=$(wc -l < "$ROOT/$rel")
|
|
if [ "$lines" -gt "$cap" ]; then
|
|
echo "✗ $rel is $lines lines (cap $cap)."
|
|
echo " Move the detail to docs/ai/<subsystem>.md, MyMistakes.md or git log — do not pad."
|
|
exit 1
|
|
fi
|
|
printf " ✓ %-12s %3s/%s lines\n" "$rel" "$lines" "$cap"
|
|
}
|
|
check_budget "AGENTS.md" 210
|
|
check_budget "ai.md" 100
|
|
check_budget "HANDOFF.md" 40
|
|
check_budget "TASKS.md" 120
|
|
|
|
echo "══ 2/4 CLEAN BUILD (expect 0 warnings) ══"
|
|
"$DOTNET" clean "$ROOTWIN\\ytLive.csproj" > /dev/null
|
|
OUT="$("$DOTNET" build "$ROOTWIN\\ytLive.csproj" 2>&1)"
|
|
if echo "$OUT" | grep -qI ": warning"; then
|
|
echo "✗ WARNINGS FOUND:"
|
|
echo "$OUT" | grep -iE ": warning" | sort -u
|
|
exit 1
|
|
fi
|
|
echo "$OUT" | grep -E "Build succeeded" || { echo "$OUT" | tail -5; exit 1; }
|
|
echo "✓ Build clean, 0 warnings."
|
|
|
|
echo "══ 3/4 TEST SUITE ══"
|
|
TESTDLL="$ROOTWIN\\ytLive.Tests\\bin\\Debug\\net8.0-windows10.0.19041.0\\ytLive.Tests.dll"
|
|
"$DOTNET" build "$ROOTWIN\\ytLive.Tests\\ytLive.Tests.csproj" > /dev/null
|
|
set +e
|
|
TEST_ARGS=("$TESTDLL")
|
|
FILTER="FullyQualifiedName!~RealMouseDrag"
|
|
if [ "${FAST:-0}" = "1" ]; then
|
|
for slow in ZoomBoxInteractionTests TextLayerOutputTests NotificationAreaIntegrationTests \
|
|
WebcamStartupResourceTests SocialsPreviewTests TopBarModeTests \
|
|
TextLayerEditorPreviewTests TextLayerDropdownTests WebcamMenuGateTests \
|
|
SceneThumbnailTests AlertTickerPreviewDisplayTests FramePumpTests; do
|
|
FILTER="$FILTER&FullyQualifiedName!~$slow"
|
|
done
|
|
fi
|
|
if [ "${PHYSICAL_TESTS:-0}" != "1" ]; then
|
|
TEST_ARGS+=("--TestCaseFilter:$FILTER")
|
|
fi
|
|
# The test HOST sometimes finishes the suite and then never exits, spinning CPU with a multi-GB working
|
|
# set (three separate sightings, 2026-11-12/13). The suite's own summary line proves the run completed, so
|
|
# bound the wait instead of hanging the gate forever, and sweep the orphan afterwards.
|
|
# Captured to a FILE, not command substitution: `timeout` kills the host with SIGTERM and a substituted
|
|
# buffer is lost with it, which left the gate with no summary at all (the exact silent failure this is
|
|
# meant to remove). A file keeps whatever the suite printed before the kill.
|
|
RAW_FILE="$(mktemp)"
|
|
# Per-test lines (not just the summary): when the host dies before summarising, the individual
|
|
# results are still the evidence, and 679 "Passed" lines with zero "Failed" is a pass.
|
|
timeout 300 "$DOTNET" vstest "${TEST_ARGS[@]}" --logger:"console;verbosity=normal" > "$RAW_FILE" 2>&1
|
|
TEST_EXIT=$?
|
|
RUN_RAW="$(cat "$RAW_FILE")"
|
|
rm -f "$RAW_FILE"
|
|
if [ "$TEST_EXIT" = "124" ]; then
|
|
echo "⚠ test host did not exit after the suite; judging on what the suite printed"
|
|
taskkill.exe /F /IM testhost.exe > /dev/null 2>&1 || true
|
|
# No summary? Fall back to the per-test lines: zero failures among real results is a pass.
|
|
if echo "$RUN_RAW" | grep -qiE "Passed!|Failed!"; then
|
|
TEST_EXIT=0
|
|
else
|
|
PASSED_COUNT=$(echo "$RUN_RAW" | grep -cE "^ Passed ")
|
|
FAILED_COUNT=$(echo "$RUN_RAW" | grep -cE "^ Failed ")
|
|
echo " per-test lines: $PASSED_COUNT passed, $FAILED_COUNT failed"
|
|
if [ "$FAILED_COUNT" = "0" ] && [ "$PASSED_COUNT" -gt 0 ]; then
|
|
TEST_EXIT=0
|
|
fi
|
|
fi
|
|
fi
|
|
set -e
|
|
# `pipefail` is on: a grep that finds no summary would fail the whole pipeline and kill the gate even
|
|
# though the per-test fallback above already decided. Hence the explicit `|| true`.
|
|
echo "$RUN_RAW" | grep -iE "Passed!|Failed!" | tail -1 || true
|
|
|
|
# Known pre-existing failures (see HANDOFF.md: do not chase). Anything beyond
|
|
# these is a real regression and fails the gate.
|
|
FAILS="$(echo "$RUN_RAW" | grep -iE "\[FAIL\]" || true)"
|
|
KNOWN=$(echo "$FAILS" | grep -cE "Mix_HonorsProviderGains_AndGameMute_KillsTheLoopback|Round_Clip_Corner_Is_Grabbable_And_Shape_Is_Circle" || true)
|
|
echo "$FAILS" | sort -u || true
|
|
|
|
if [ "$TEST_EXIT" -ne 0 ] && [ "$KNOWN" -eq 0 ]; then
|
|
echo "✗ TEST FAILURES that are NOT the known pre-existing pair — investigate."
|
|
exit 1
|
|
fi
|
|
if [ "$TEST_EXIT" -ne 0 ]; then
|
|
echo "⚠ Test exit=$TEST_EXIT but only the 2 known pre-existing failures present (OK)."
|
|
fi
|
|
|
|
echo "══ 4/4 SCOPE CHECK ══"
|
|
"$ROOT/scripts/scope-check.sh" "$@"
|
|
|
|
echo ""
|
|
echo "✓ All gates passed — safe to commit."
|