PROCITY/tools/qa.sh
m3ultra e4a49b5bc8 Lane F R17 (v3.2): real towns boot in the engine + the town-matrix scout gate (ledger #7)
F wired the last mile of the real-map scout and gated the whole matrix.

- index.js barrel re-exports registerTownCache/validateTownCache; the shell fetches + registers
  assets/towns/<key>.json before generatePlanFor when the town isn't a checked-in fixture — so
  ?plansrc=osm&town=bendigo_real boots a REAL AU town in the engine (the gap: E's caches were on disk +
  in the node selfcheck, but the shell never loaded them → silent Melbourne fallback). Fail-soft
  (404 / invalid / ?noassets -> fixture fallback); opt-in, never on the default or ?classic path.
- tools/qa/town_matrix.py (opt-in qa.sh --matrix): boot / determinism / budget / district / ?noassets
  across 10 towns (2 synthetic hero seeds + 3 osm fixtures + E's 5 real AU caches). ALL 5x10 GREEN —
  Castlemaine at the 6-shop floor still lands a 3-venue district. The existing CityPlan contract eats real
  Australian geography: the evidence John charters v4 = THE REAL MAP on.
- docs: LANE_F_NOTES §17 (the town x gate table), README real-town row, F-progress R17.

qa.sh --strict --soak GREEN 7/7. Verified: ?plansrc=osm&town=bendigo_real -> Bendigo, 9 shops, 3 venues, 0 errors.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 15:23:15 +10:00

155 lines
8.9 KiB
Bash
Executable File
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env bash
# PROCITY Lane F — the QA gate runner (CITY_SPEC / LANE_F acceptance).
#
# tools/qa.sh run every gate whose inputs have landed; skip the rest
# tools/qa.sh --strict also FAIL on any still-pending lane deliverable (use at v1 sign-off)
#
# Design: F runs before AE finish. A gate whose target file does not exist yet is reported
# SKIPPED (yellow), not failed — so this is safe to run continuously as lanes land. Once every
# lane is in, `--strict` turns the skips into hard failures: that is the v1 readiness gate.
#
# Gates:
# 1. scaffold_check.mjs — scaffold + PRNG determinism law + lane-readiness matrix (F-owned)
# 2. citygen selfcheck — node web/js/citygen/selfcheck.js (Lane A ships it)
# 3. manifest validator — python3 pipeline/validate_manifest.py (Lane E ships it)
#
# Browser-driven gates (determinism-PNG, 10-min soak, budget-HUD, ?noassets run) need the running
# game; they live in tools/soak.md + tools/shots.md and run once Lane B's index.html lands.
set -uo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$ROOT"
STRICT=0
[ "${1:-}" = "--strict" ] && STRICT=1
pass=0; failn=0; skip=0
c_red=$'\033[31m'; c_grn=$'\033[32m'; c_yel=$'\033[33m'; c_bold=$'\033[1m'; c_off=$'\033[0m'
hr() { printf '%s\n' "────────────────────────────────────────────────────────"; }
run_gate() { # run_gate "name" cmd...
local name="$1"; shift
printf '%s▶ %s%s\n' "$c_bold" "$name" "$c_off"
if "$@"; then printf '%s ✓ PASS%s %s\n\n' "$c_grn" "$c_off" "$name"; pass=$((pass+1));
else printf '%s ✗ FAIL%s %s\n\n' "$c_red" "$c_off" "$name"; failn=$((failn+1)); fi
}
skip_gate() { # skip_gate "name" "reason"
printf '%s▶ %s%s\n' "$c_bold" "$1" "$c_off"
printf '%s ⊘ SKIP%s %s\n\n' "$c_yel" "$c_off" "$2"
skip=$((skip+1))
}
warnn=0
soft_skip() { # non-blocking skip for a warn-level gate — does NOT trip --strict readiness
printf '%s▶ %s%s\n' "$c_bold" "$1" "$c_off"
printf '%s ⊘ SKIP%s %s (warn-level, non-blocking)\n\n' "$c_yel" "$c_off" "$2"
}
warn_gate() { # warn_gate "name" cmd... — runs, but a failure is a WARN not a FAIL (round-6 policy)
local name="$1"; shift
printf '%s▶ %s%s (warn-level)\n' "$c_bold" "$name" "$c_off"
if "$@"; then printf '%s ✓ PASS%s %s\n\n' "$c_grn" "$c_off" "$name"; pass=$((pass+1));
else printf '%s ! WARN%s %s (non-blocking this round — strict in r7)\n\n' "$c_yel" "$c_off" "$name"; warnn=$((warnn+1)); fi
}
printf '%sPROCITY QA GATES%s (%s)\n' "$c_bold" "$c_off" "$([ $STRICT = 1 ] && echo strict || echo lenient)"
hr
# ── Gate 1: scaffold + determinism + readiness (always) ──────────────────────
run_gate "scaffold_check (scaffold · PRNG determinism · readiness matrix)" \
node tools/qa/scaffold_check.mjs
# ── Gate 1b: cross-lane consistency (plan ↔ registry ↔ assets ↔ manifest) ────
# Self-skips (exit 0) until Lane A's plan.js + registry.js exist.
run_gate "consistency (plan ↔ registry ↔ assets ↔ manifest)" \
node tools/qa/consistency_check.mjs
# ── Gate 2: Lane A citygen selfcheck ─────────────────────────────────────────
if [ -f web/js/citygen/selfcheck.js ]; then
run_gate "citygen selfcheck (determinism · <100ms · lots/shops integrity)" \
node web/js/citygen/selfcheck.js
else
skip_gate "citygen selfcheck" "web/js/citygen/selfcheck.js not landed yet (Lane A)"
fi
# ── Gate 3: Lane E manifest validator ────────────────────────────────────────
# [Lane F R3] --depot: the 16 GLBs are published + live on the 3GOD depot (Fable, 2026-07-14), so the
# gate now REQUIRES them reachable (was a soft local-only check). Override the endpoint with GOD3_DEPOT
# (tailnet path) if digalot.fyi is unreachable; the validator falls back to the manifest's depot field.
if [ -f pipeline/validate_manifest.py ]; then
run_gate "manifest validator (files exist · footprints sane · GLBs live on depot · JSON parses)" \
python3 pipeline/validate_manifest.py --depot
else
skip_gate "manifest validator" "pipeline/validate_manifest.py not landed yet (Lane E)"
fi
# ── Gate 4 (warn-level, round 6): v2 flag enforcement harness ────────────────
# Flags-off regression (prime-law) + per-flag + all-on-combo smokes. Needs the Playwright venv +
# a browser (self-contained server), auto-skips where absent. STRICT as of R7 (F2): a harness FAIL
# now fails qa (flags-off regression + the four existing flags + all-on combo). New flags (stock,
# weather) report at warn inside the harness, so they never trip this gate until they graduate.
# Skip explicitly with --no-flags (fast determinism-only runs).
FLAGS_SKIP=0; for a in "$@"; do [ "$a" = "--no-flags" ] && FLAGS_SKIP=1; done
if [ "$FLAGS_SKIP" = 1 ]; then
soft_skip "v2 flags harness" "--no-flags"
elif [ -x tools/.venv/bin/python ] && tools/.venv/bin/python -c "import playwright" 2>/dev/null; then
run_gate "flags harness (classic regression · default-boot gate · per-flag · smokes · STRICT · R16 flip)" \
tools/.venv/bin/python tools/flags_check.py
else
soft_skip "v2 flags harness" "Playwright venv absent (python3 -m venv tools/.venv && …/pip install playwright)"
fi
# ── Gate 5 (Lane D, round 10): interior figure-scale regression guard ────────
# Enters a sample of open shops and asserts every interior rig figure's crown is human-sized
# [1.4,2.0] m AND under the room ceiling — so the R9 giant blocker (buildFigure normalised off
# head-above-hips → ~2× too tall) can never pass a gate again. run_gate ⇒ a giant FAILS qa.
# Needs the Playwright venv (auto-skips where absent, like the flags harness). Wired per ROUND10 §D.
SCALE_SKIP=0; for a in "$@"; do [ "$a" = "--no-scale" ] && SCALE_SKIP=1; done
if [ "$SCALE_SKIP" = 1 ]; then
soft_skip "interior figure-scale gate" "--no-scale"
elif [ -x tools/.venv/bin/python ] && tools/.venv/bin/python -c "import playwright" 2>/dev/null; then
run_gate "interior figure-scale (no giants: crown ∈ [1.4,2.0] m, under ceiling · Lane D R10)" \
tools/.venv/bin/python tools/qa/interior_scale_check.py
else
soft_skip "interior figure-scale gate" "Playwright venv absent (python3 -m venv tools/.venv && …/pip install playwright)"
fi
# ── Gate 6 (Lane F, round 15): full-week gig soak — OPT-IN (--soak), NON-STRICT ─
# The v3.0 release soak: 7 nights × every playing venue in one context — latch state per plan.gigs,
# cover stamp per venue per night, roster clears per night, leak geo/tex to a warmed baseline across
# ≥20 enter/exit cycles. Slow (~90s) + diagnostic, so it is OPT-IN and warn-level (never blocks a tag);
# the core 6 gates stay a fast strict run. Wired per ROUND15 §Lane F.3.
SOAK_RUN=0; for a in "$@"; do [ "$a" = "--soak" ] && SOAK_RUN=1; done
if [ "$SOAK_RUN" = 1 ]; then
if [ -x tools/.venv/bin/python ] && tools/.venv/bin/python -c "import playwright" 2>/dev/null; then
warn_gate "full-week gig soak (7 nights · cover/roster per night · leak-free · Lane F R15)" \
tools/.venv/bin/python tools/qa/week_soak.py
else
soft_skip "full-week gig soak" "Playwright venv absent"
fi
fi
# ── Gate 7 (Lane F, round 17): town-matrix smoke — OPT-IN (--matrix), NON-STRICT ─
# The v4 real-map scout evidence: boot / determinism / budget / district / noassets across the full town
# matrix — synthetic hero seeds + the 3 osm fixtures + Lane E's 5 real AU town caches. One town × gate
# table. Slow (~20 boots) + diagnostic, so OPT-IN + warn-level. Wired per ROUND17 §Lane F (ledger #7).
MATRIX_RUN=0; for a in "$@"; do [ "$a" = "--matrix" ] && MATRIX_RUN=1; done
if [ "$MATRIX_RUN" = 1 ]; then
if [ -x tools/.venv/bin/python ] && tools/.venv/bin/python -c "import playwright" 2>/dev/null; then
warn_gate "town-matrix (synthetic + fixtures + real caches × 5 gates · Lane F R17)" \
tools/.venv/bin/python tools/qa/town_matrix.py
else
soft_skip "town-matrix" "Playwright venv absent"
fi
fi
# ── Summary ──────────────────────────────────────────────────────────────────
hr
printf '%sSUMMARY%s %s%d passed%s · %s%d failed%s · %s%d warn%s · %s%d skipped%s\n' \
"$c_bold" "$c_off" "$c_grn" "$pass" "$c_off" "$c_red" "$failn" "$c_off" "$c_yel" "$warnn" "$c_off" "$c_yel" "$skip" "$c_off"
if [ "$failn" -gt 0 ]; then
printf '%s● QA RED%s — fix the failing gate(s) above.\n' "$c_red" "$c_off"; exit 1
fi
if [ "$STRICT" = 1 ] && [ "$skip" -gt 0 ]; then
printf '%s● QA NOT READY%s — %d gate(s) still pending; not v1 yet.\n' "$c_yel" "$c_off" "$skip"; exit 2
fi
printf '%s● QA GREEN%s — every landed gate passed.\n' "$c_grn" "$c_off"; exit 0