Close the three gaps the scoring report itself flagged for H6 plus V15, each as a real MVP + fail-able adversarial test (same pattern that lifted H5): - D1 alert-dispatch.sh: alerts POST to a real HTTP webhook (severity routing, dedup window, retry) + dead-letter queue with redelivery; fail-loud in strict. Wired into agent-metrics.sh so a failing step pages live end-to-end. - D2 provider-usage-fetch.sh + telemetry-reconcile.sh: pull usage from a provider usage HTTP API (all-or-nothing schema gate, fail-loud) + reconcile local vs provider ground truth — token under-reporting/hidden runs => TELEMETRY_DISCREPANCY. - D3 dashboard-serve.sh + dashboard-server.py: serve the dashboard over HTTP with a stale-aware /healthz probe (fresh=200 ok, telemetry silent-death=503 stale). - D4 circuit-breaker-check.sh: sliding-window failure-rate breaker (V15) — interleaved successes no longer evade the consecutive-failure breaker (CIRCUIT_OPEN_WINDOW). New suite phase-h6-agentops-tests.sh: 20/20, all live against local HTTP endpoints (webhook sink, mock provider API, dashboard server) — deterministic, no model needed. Also fix sign-policy-bundle.sh key-sync invariant: the local-fallback branch only exported policy-public.pem when generating a NEW key, so a Vault-DOWN run after a Vault-signed run verified a local-key signature against the Vault pubkey (RSA padding error, run-casan4 died mid-suite). Now always re-exports the pubkey before signing — same fix class as tool-audit-lib.sh / governance-check.sh. Full battery re-run sequentially: 175/175 PASS, 0 FAIL across 8 suites (KMS SKIP this run — Vault down; validated live 2026-07-04). Docs synced: scoring-run-report (H6 79→80, no harness below 80, 155→175), CASAN_HARDENING_STATUS (Phase 5 D1–D4), Plan-07, submission README, and run-hardening.sh (H6+ scenes HO1–HO4). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
108 lines
3.8 KiB
Bash
Executable File
108 lines
3.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
# CASAN Level 5 signed central policy bundle.
|
|
# Usage:
|
|
# sign-policy-bundle.sh sign
|
|
# sign-policy-bundle.sh verify
|
|
|
|
MODE="${1:-}"
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
|
|
GOV_DIR="$PROJECT_ROOT/.specify/level5/central-governance"
|
|
BUNDLE="$GOV_DIR/policy-bundle.yaml"
|
|
MANIFEST="$GOV_DIR/policy-manifest.json"
|
|
PRIVATE_KEY="$GOV_DIR/policy-private.pem"
|
|
PUBLIC_KEY="$GOV_DIR/policy-public.pem"
|
|
SIGNATURE="$GOV_DIR/policy-manifest.sig"
|
|
mkdir -p "$GOV_DIR"
|
|
|
|
if [[ "$MODE" != "sign" && "$MODE" != "verify" ]]; then
|
|
echo "Usage: sign-policy-bundle.sh sign|verify" >&2
|
|
exit 64
|
|
fi
|
|
|
|
if ! command -v openssl >/dev/null 2>&1; then
|
|
echo "POLICY_SIGNING_UNAVAILABLE openssl not found" >&2
|
|
exit 1
|
|
fi
|
|
|
|
generate_manifest() {
|
|
python - "$PROJECT_ROOT" "$BUNDLE" "$MANIFEST" <<'PY'
|
|
import hashlib
|
|
import json
|
|
import pathlib
|
|
import re
|
|
import sys
|
|
from datetime import datetime, timezone
|
|
|
|
root = pathlib.Path(sys.argv[1])
|
|
bundle = pathlib.Path(sys.argv[2])
|
|
manifest = pathlib.Path(sys.argv[3])
|
|
text = bundle.read_text(encoding="utf-8")
|
|
paths = re.findall(r"^\s*path:\s*(.+?)\s*$", text, flags=re.MULTILINE)
|
|
files = []
|
|
for raw in paths:
|
|
rel = raw.strip().strip('"')
|
|
path = root / rel
|
|
if not path.exists():
|
|
raise SystemExit(f"missing policy file: {rel}")
|
|
data = path.read_bytes()
|
|
files.append({
|
|
"path": rel,
|
|
"sha256": hashlib.sha256(data).hexdigest(),
|
|
"bytes": len(data),
|
|
})
|
|
payload = {
|
|
"bundle_id": "casan-okr-harness-policy",
|
|
"generated_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
|
|
"files": files,
|
|
}
|
|
manifest.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n", encoding="utf-8")
|
|
print(f"POLICY_MANIFEST_GENERATED files={len(files)} manifest={manifest}")
|
|
PY
|
|
}
|
|
|
|
if [[ "$MODE" == "sign" ]]; then
|
|
generate_manifest
|
|
|
|
if [[ -n "${VAULT_ADDR:-}" && -n "${VAULT_TOKEN:-}" ]] && \
|
|
curl -sf "$VAULT_ADDR/v1/sys/health" >/dev/null 2>&1; then
|
|
# ── KMS path: sign via HashiCorp Vault Transit (key never stored on disk) ──
|
|
VAULT_KMS="$SCRIPT_DIR/vault-kms.sh"
|
|
bash "$VAULT_KMS" enable-transit
|
|
bash "$VAULT_KMS" sign "$MANIFEST" "$SIGNATURE" "casan-policy-key"
|
|
bash "$VAULT_KMS" pubkey "$PUBLIC_KEY" "casan-policy-key"
|
|
echo "POLICY_BUNDLE_SIGNED manifest=$MANIFEST signature=$SIGNATURE public_key=$PUBLIC_KEY key_backend=vault-kms"
|
|
else
|
|
# ── Fallback: local key file (dev / no Vault) ─────────────────────────────
|
|
if [[ ! -f "$PRIVATE_KEY" ]]; then
|
|
openssl genrsa -out "$PRIVATE_KEY" 2048 >/dev/null 2>&1
|
|
fi
|
|
# Key-sync invariant: the on-disk public key must ALWAYS match the key that
|
|
# signs (a prior Vault-signed run leaves the Vault pubkey here — verifying
|
|
# a local-key signature against it would fail with an RSA padding error).
|
|
openssl rsa -in "$PRIVATE_KEY" -pubout -out "$PUBLIC_KEY" >/dev/null 2>&1
|
|
openssl dgst -sha256 -sign "$PRIVATE_KEY" -out "$SIGNATURE" "$MANIFEST"
|
|
echo "POLICY_BUNDLE_SIGNED manifest=$MANIFEST signature=$SIGNATURE public_key=$PUBLIC_KEY key_backend=local-file"
|
|
fi
|
|
exit 0
|
|
fi
|
|
|
|
python - "$PROJECT_ROOT" "$MANIFEST" <<'PY'
|
|
import hashlib
|
|
import json
|
|
import pathlib
|
|
import sys
|
|
root = pathlib.Path(sys.argv[1])
|
|
manifest = json.loads(pathlib.Path(sys.argv[2]).read_text(encoding="utf-8"))
|
|
for item in manifest["files"]:
|
|
data = (root / item["path"]).read_bytes()
|
|
actual = hashlib.sha256(data).hexdigest()
|
|
if actual != item["sha256"]:
|
|
raise SystemExit(f"POLICY_HASH_MISMATCH path={item['path']} expected={item['sha256']} actual={actual}")
|
|
print(f"POLICY_HASHES_VALID files={len(manifest['files'])}")
|
|
PY
|
|
openssl dgst -sha256 -verify "$PUBLIC_KEY" -signature "$SIGNATURE" "$MANIFEST" >/dev/null
|
|
echo "POLICY_SIGNATURE_VALID manifest=$MANIFEST"
|