feat: plan 16 P1 (SEC-08/09/19/20/21) — fail-open/DoS/authz hardening

- SEC-08 pii-mask: fail-closed on missing rules / broken regex (no unmasked leak)
- SEC-09: input-size cap + fail-closed reads (security-check/drift-detect/context-compress); non-UTF8 no longer crashes
- SEC-19: control-plane store POSIX flock + atomic tmp+rename write
- SEC-20: new toolchain-verify.sh (missing/PATH-shadowed/in-workspace binary -> refuse); wired into harness-preflight
- SEC-21: model-call timeout 180->60s configurable + per-run call budget
- SEC-11 realized by SEC-17 prod profile (no code)
- 5 fail-able test suites wired into ci-harness-gate.sh; test-integrity manifest regenerated

Verify: SEC+integrity gate 16/0, run-casan4 0-FAIL, adversarial 44/44, no regressions.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

AINative_OKR_CASAN5/.specify/tests/phase-sec21-tests.sh

@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+# CASAN Plan-16 SEC-21 (ARCH-07) — bounded model timeout + per-run call budget.
+#
+# A 180s-per-call timeout across many steps let a hung model stall a run for tens
+# of minutes. Now the per-call timeout is lower + configurable, and total model
+# calls per run are capped so a wedged model cannot amplify into a DoS. Proves the
+# budget refuses once exhausted, and no cap set means no limit (dev default).
+#
+# Deterministic (budget is checked BEFORE any backend call, so it holds whether or
+# not a model is reachable). No network required.
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+MC="$PROJECT_ROOT/.specify/scripts/bash/model-call.py"
+WORK="$(mktemp -d)"
+trap 'git -C "$PROJECT_ROOT" checkout -- .specify/logs/level5/provider-usage.jsonl 2>/dev/null; rm -rf "$WORK"' EXIT
+
+PASS=0; FAIL=0
+pass() { echo "PASS: $1"; PASS=$((PASS + 1)); }
+fail() { echo "FAIL: $1"; FAIL=$((FAIL + 1)); }
+
+echo "===== Plan-16 SEC-21: model timeout + per-run call budget ====="
+
+# Per-call timeout is reduced from 180s and configurable.
+grep -q 'timeout=180' "$MC" && fail "hardcoded 180s timeout still present" \
+  || pass "no hardcoded 180s per-call timeout"
+grep -q 'CASAN_MODEL_TIMEOUT_SEC' "$MC" \
+  && pass "per-call timeout is configurable via CASAN_MODEL_TIMEOUT_SEC" \
+  || fail "timeout not configurable"
+
+# Budget: cap=1. Call 1 charges the budget (proceeds); call 2 is refused BEFORE any
+# backend work, with a clear budget error, regardless of model availability.
+echo "hello" > "$WORK/p.txt"
+CNT="$WORK/counter"
+export CASAN_MODEL_MAX_CALLS=1 CASAN_MODEL_CALL_COUNTER_FILE="$CNT"
+
+python3 "$MC" "$WORK/p.txt" "$WORK/o1.json" --role classify >/dev/null 2>&1  # charges to 1
+ERR2="$(python3 "$MC" "$WORK/p.txt" "$WORK/o2.json" --role classify 2>&1 >/dev/null)"; RC2=$?
+if [[ "$RC2" -ne 0 ]] && echo "$ERR2" | grep -q "run_call_budget_exceeded"; then
+  pass "call over budget is REFUSED (rc=$RC2, budget error)"
+else
+  fail "over-budget call not refused (rc=$RC2 err='$ERR2')"
+fi
+
+# No cap set → no budget error (dev default unchanged).
+unset CASAN_MODEL_MAX_CALLS CASAN_MODEL_CALL_COUNTER_FILE
+ERR3="$(python3 "$MC" "$WORK/p.txt" "$WORK/o3.json" --role classify 2>&1 >/dev/null || true)"
+echo "$ERR3" | grep -q "run_call_budget_exceeded" \
+  && fail "budget error fired with no cap set" \
+  || pass "no cap set → no budget limit (dev default)"
+
+echo ""
+echo "===== SEC-21 SUMMARY: PASS=$PASS FAIL=$FAIL ====="
+[[ "$FAIL" -eq 0 ]] || exit 1