441 lines
22 KiB
Python
441 lines
22 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
IwoooS Monitoring / Alerting / Observability owner response acceptance 只讀帳本產生器。
|
||
|
||
本工具讀取 monitoring / alerting / observability inventory 與 owner request
|
||
draft，建立未來 owner response 如何收件、補件、隔離、拒收或進入
|
||
monitoring reviewer review 的 metadata-only acceptance ledger。它不連 live
|
||
Prometheus、不 reload Alertmanager、不套用 Grafana / SigNoz / Sentry /
|
||
Langfuse、不 reload OTEL、不改 receiver route、不建立 silence、不送
|
||
Telegram、不 fire live alert、不跑 alert chain smoke、不 SSH、不 kubectl、
|
||
不讀 secret value、不寫 production。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import json
|
||
import subprocess
|
||
import sys
|
||
from datetime import datetime, timedelta, timezone
|
||
from pathlib import Path
|
||
from typing import Any
|
||
|
||
|
||
TAIPEI = timezone(timedelta(hours=8))
|
||
|
||
ACCEPTANCE_FIELDS = [
|
||
"acceptance_candidate_id",
|
||
"request_id",
|
||
"surface_id",
|
||
"label",
|
||
"expected_scope",
|
||
"config_kind",
|
||
"observability_scope",
|
||
"control_tier",
|
||
"repo_source_path",
|
||
"repo_sha256",
|
||
"source_line_count",
|
||
"write_capable_surface",
|
||
"requires_live_evidence",
|
||
"owner_response_ref",
|
||
"owner_role_or_team",
|
||
"decision",
|
||
"decision_reason",
|
||
"affected_scope",
|
||
"redacted_evidence_refs",
|
||
"live_config_hash_ref",
|
||
"reload_owner",
|
||
"receiver_owner",
|
||
"route_smoke_plan",
|
||
"incident_context_ref",
|
||
"alert_chain_health_ref",
|
||
"receiver_receipt_proof_ref",
|
||
"stale_alert_review",
|
||
"silence_or_dedup_review",
|
||
"false_green_risk_review",
|
||
"post_reload_readback_plan",
|
||
"cross_project_notification_ref",
|
||
"maintenance_window",
|
||
"rollback_owner",
|
||
"validation_plan",
|
||
"noise_budget_owner",
|
||
"reviewer_outcome",
|
||
"followup_owner",
|
||
"not_approval",
|
||
]
|
||
|
||
REVIEWER_CHECKS = [
|
||
{"check_id": "owner_identity_present", "instruction": "owner role / team 必須可追溯。"},
|
||
{"check_id": "decision_reason_present", "instruction": "decision 與 decision reason 必須同時存在。"},
|
||
{"check_id": "affected_scope_matches_surface", "instruction": "affected scope 必須能對回 committed surface_id。"},
|
||
{"check_id": "redacted_refs_only", "instruction": "evidence 只能是脫敏 ref、hash、ticket、commit 或 artifact pointer。"},
|
||
{"check_id": "secret_value_absent", "instruction": "不得出現 token、Bot token、DSN secret、cookie、private key、env dump 或 partial secret。"},
|
||
{"check_id": "live_config_hash_metadata_only", "instruction": "live config hash 只能是 owner-provided metadata ref，不得貼 raw config。"},
|
||
{"check_id": "reload_owner_present", "instruction": "Prometheus / Alertmanager / OTEL / Sentry 類變更必須有 reload / deploy owner。"},
|
||
{"check_id": "receiver_owner_present", "instruction": "receiver route、Telegram receipt 與 notification policy 必須有 receiver owner。"},
|
||
{"check_id": "route_smoke_plan_present", "instruction": "route smoke / receipt proof 必須是計畫或脫敏證據 ref，不得直接 fire alert。"},
|
||
{"check_id": "incident_context_present", "instruction": "事故回補必須有 incident / change / outage context ref；不得只寫服務已恢復。"},
|
||
{"check_id": "alert_chain_health_not_route_only", "instruction": "告警鏈路健康不得只用 public route 200 或 UI 可見判定，必須包含 rule、state、receiver 與 receipt/ref。"},
|
||
{"check_id": "receiver_receipt_proof_metadata_only", "instruction": "receiver receipt proof 只能是脫敏 ref、hash、message id 或 ticket，不得貼 raw notification payload。"},
|
||
{"check_id": "stale_alert_review_present", "instruction": "必須確認告警是否 stale、pending、resolved 未清或資料來源停止更新。"},
|
||
{"check_id": "silence_or_dedup_review_present", "instruction": "必須確認 silence、mute、dedup、inhibit 或 maintenance rule 是否造成 false green。"},
|
||
{"check_id": "false_green_risk_review_present", "instruction": "必須列 no-false-green 判定，避免把 route up、容器 up 或 dashboard up 當作告警鏈路 up。"},
|
||
{"check_id": "post_reload_readback_plan_present", "instruction": "若後續有 reload / deploy，必須先有 post-reload readback plan 與 stop condition。"},
|
||
{"check_id": "cross_project_notification_present", "instruction": "若影響 AwoooP、IwoooS、agent-bounty、StockPlatform、公開網站或監控，需有跨專案通知 ref。"},
|
||
{"check_id": "noise_budget_owner_present", "instruction": "告警噪音、silence、dedup 與測試通知必須有 noise budget owner。"},
|
||
{"check_id": "maintenance_window_present", "instruction": "reload、deploy、route change、smoke 或 notification send 必須另有維護窗口。"},
|
||
{"check_id": "rollback_owner_present", "instruction": "rollback owner、rollback ref 或 disable path 必須存在。"},
|
||
{"check_id": "validation_plan_present", "instruction": "validation / post-check 必須列 route、receipt、alert state、metrics 與 rollback stop condition。"},
|
||
{"check_id": "no_runtime_request", "instruction": "夾帶 reload、receiver route change、Telegram send、alert smoke、SSH 或 kubectl 要求時拒收。"},
|
||
{"check_id": "counts_transition_safe", "instruction": "只有 reviewer record 可更新 received / accepted / rejected；不得同時開 runtime gate。"},
|
||
]
|
||
|
||
OUTCOME_LANES = [
|
||
{"lane_id": "waiting_owner_response", "meaning": "尚未收到 owner response；所有 accepted / runtime count 維持 0。"},
|
||
{"lane_id": "quarantine_secret_or_raw_payload", "meaning": "收到 secret、raw config、raw receiver payload、未脫敏 log 或截圖時隔離。"},
|
||
{"lane_id": "reject_execution_request", "meaning": "夾帶 reload、deploy、route change、Telegram send、fire alert、SSH 或 kubectl 要求時拒收。"},
|
||
{"lane_id": "request_supplement", "meaning": "欄位不足、scope 不清、reload / receiver / route smoke / rollback / noise owner 缺失時要求補件。"},
|
||
{"lane_id": "ready_for_monitoring_review", "meaning": "metadata 合格後，只能進 monitoring reviewer review。"},
|
||
{"lane_id": "incident_recovery_backfill_required", "meaning": "事故後只看到服務恢復時，要求補 incident context、receiver receipt、stale / silence review 與 post-check refs。"},
|
||
{"lane_id": "no_false_green_supplement_required", "meaning": "只用 route 200、container up、dashboard up 或 UI 可見代表告警健康時，要求補 no-false-green 證據。"},
|
||
{"lane_id": "receiver_receipt_gap_required", "meaning": "缺 Telegram / webhook / receiver receipt proof 或 delivery state 時，不得接受告警鏈路健康。"},
|
||
{"lane_id": "stale_or_silenced_alert_review_required", "meaning": "缺 stale alert、silence、dedup、inhibit 或 maintenance rule review 時，要求補件。"},
|
||
{"lane_id": "post_reload_readback_required", "meaning": "reload / deploy / rule change 後必須有 readback、metrics、receipt 與 rollback stop condition。"},
|
||
{"lane_id": "owner_review_only_update", "meaning": "只允許更新只讀 owner review ledger，不得 reload、send Telegram 或 fire alert。"},
|
||
{"lane_id": "waiting_runtime_gate", "meaning": "即使 owner response accepted，runtime gate 仍等待獨立人工批准。"},
|
||
]
|
||
|
||
BLOCKED_ACTIONS = [
|
||
"prometheus_reload",
|
||
"alertmanager_reload",
|
||
"grafana_dashboard_apply",
|
||
"signoz_rule_apply",
|
||
"sentry_deploy",
|
||
"langfuse_config_change",
|
||
"otel_collector_reload",
|
||
"receiver_route_change",
|
||
"silence_policy_change",
|
||
"telegram_send",
|
||
"notification_route_change",
|
||
"webhook_receiver_change",
|
||
"remote_write_change",
|
||
"exporter_deploy",
|
||
"live_alert_fire",
|
||
"alert_chain_smoke",
|
||
"ssh_read",
|
||
"ssh_write",
|
||
"kubectl_action",
|
||
"secret_value_collection",
|
||
"host_write",
|
||
"active_scan",
|
||
"production_write",
|
||
"runtime_gate_open",
|
||
"raw_monitoring_payload_storage",
|
||
"accept_secret_value_evidence",
|
||
"mark_owner_response_accepted_without_reviewer_record",
|
||
"mark_route_200_as_alert_chain_healthy",
|
||
"mark_receiver_healthy_without_receipt",
|
||
"accept_silence_without_owner",
|
||
"accept_stale_alert_without_review",
|
||
"accept_reload_without_postcheck",
|
||
"store_raw_alert_payload",
|
||
"add_action_button",
|
||
]
|
||
|
||
|
||
def git_short_sha(root: Path) -> str:
|
||
try:
|
||
result = subprocess.run(
|
||
["git", "rev-parse", "--short", "HEAD"],
|
||
cwd=root,
|
||
check=True,
|
||
capture_output=True,
|
||
text=True,
|
||
)
|
||
return result.stdout.strip()
|
||
except Exception:
|
||
return "unknown"
|
||
|
||
|
||
def load_json(path: Path) -> dict[str, Any]:
|
||
return json.loads(path.read_text(encoding="utf-8"))
|
||
|
||
|
||
def acceptance_candidate(request: dict[str, Any]) -> dict[str, Any]:
|
||
surface_id = request["surface_id"]
|
||
return {
|
||
"acceptance_candidate_id": f"monitoring_owner_response_acceptance:{surface_id}",
|
||
"status": "waiting_owner_response",
|
||
"request_id": request["request_id"],
|
||
"surface_id": surface_id,
|
||
"label": request["label"],
|
||
"expected_scope": request["expected_scope"],
|
||
"config_kind": request["config_kind"],
|
||
"observability_scope": request["observability_scope"],
|
||
"control_tier": request["control_tier"],
|
||
"repo_source_path": request["repo_source_path"],
|
||
"repo_sha256": request["repo_sha256"],
|
||
"source_line_count": request["source_line_count"],
|
||
"write_capable_surface": request["write_capable_surface"],
|
||
"requires_live_evidence": request["requires_live_evidence"],
|
||
"owner_response_ref": None,
|
||
"owner_role_or_team": "pending_owner_response",
|
||
"decision": "pending_owner_response",
|
||
"decision_reason": "pending_owner_response",
|
||
"affected_scope": "pending_owner_response",
|
||
"redacted_evidence_refs": [],
|
||
"live_config_hash_ref": None,
|
||
"reload_owner": "pending_owner_response",
|
||
"receiver_owner": "pending_owner_response",
|
||
"route_smoke_plan": "pending_owner_response",
|
||
"incident_context_ref": None,
|
||
"alert_chain_health_ref": None,
|
||
"receiver_receipt_proof_ref": None,
|
||
"stale_alert_review": "pending_owner_response",
|
||
"silence_or_dedup_review": "pending_owner_response",
|
||
"false_green_risk_review": "pending_owner_response",
|
||
"post_reload_readback_plan": "pending_owner_response",
|
||
"cross_project_notification_ref": None,
|
||
"maintenance_window": "pending_owner_response",
|
||
"rollback_owner": "pending_owner_response",
|
||
"validation_plan": "pending_owner_response",
|
||
"noise_budget_owner": "pending_owner_response",
|
||
"reviewer_outcome": "waiting_owner_response",
|
||
"followup_owner": "pending_owner_response",
|
||
"acceptance_fields": ACCEPTANCE_FIELDS,
|
||
"required_owner_fields": request["required_owner_fields"],
|
||
"reviewer_checks": [item["check_id"] for item in REVIEWER_CHECKS],
|
||
"outcome_lanes": [item["lane_id"] for item in OUTCOME_LANES],
|
||
"blocked_actions": BLOCKED_ACTIONS,
|
||
"not_approval": True,
|
||
"request_sent": False,
|
||
"recipient_confirmed": False,
|
||
"owner_response_received": False,
|
||
"owner_response_accepted": False,
|
||
"owner_response_rejected": False,
|
||
"owner_response_quarantined": False,
|
||
"supplement_requested": False,
|
||
"live_evidence_received": False,
|
||
"live_config_hash_accepted": False,
|
||
"reload_owner_accepted": False,
|
||
"receiver_owner_accepted": False,
|
||
"route_smoke_accepted": False,
|
||
"incident_context_accepted": False,
|
||
"alert_chain_health_accepted": False,
|
||
"receiver_receipt_proof_accepted": False,
|
||
"stale_alert_review_accepted": False,
|
||
"silence_or_dedup_review_accepted": False,
|
||
"false_green_risk_review_accepted": False,
|
||
"post_reload_readback_plan_accepted": False,
|
||
"cross_project_notification_accepted": False,
|
||
"maintenance_window_accepted": False,
|
||
"rollback_owner_accepted": False,
|
||
"validation_plan_accepted": False,
|
||
"noise_budget_owner_accepted": False,
|
||
"prometheus_reload_authorized": False,
|
||
"alertmanager_reload_authorized": False,
|
||
"grafana_dashboard_apply_authorized": False,
|
||
"signoz_rule_apply_authorized": False,
|
||
"sentry_deploy_authorized": False,
|
||
"langfuse_config_change_authorized": False,
|
||
"otel_collector_reload_authorized": False,
|
||
"receiver_route_change_authorized": False,
|
||
"silence_policy_change_authorized": False,
|
||
"telegram_send_authorized": False,
|
||
"notification_route_change_authorized": False,
|
||
"webhook_receiver_change_authorized": False,
|
||
"remote_write_change_authorized": False,
|
||
"exporter_deploy_authorized": False,
|
||
"live_alert_fire_authorized": False,
|
||
"alert_chain_smoke_authorized": False,
|
||
"ssh_read_authorized": False,
|
||
"ssh_write_authorized": False,
|
||
"kubectl_action_authorized": False,
|
||
"secret_value_collection_allowed": False,
|
||
"host_write_authorized": False,
|
||
"active_scan_authorized": False,
|
||
"production_write_authorized": False,
|
||
"runtime_gate": False,
|
||
"action_buttons_allowed": False,
|
||
}
|
||
|
||
|
||
def build_report(
|
||
root: Path,
|
||
inventory: dict[str, Any],
|
||
request_draft_report: dict[str, Any],
|
||
generated_at: str | None,
|
||
) -> dict[str, Any]:
|
||
report_time = generated_at or datetime.now(TAIPEI).isoformat(timespec="seconds")
|
||
requests = request_draft_report.get("request_drafts", [])
|
||
acceptance_candidates = [acceptance_candidate(item) for item in requests]
|
||
write_capable = [item for item in acceptance_candidates if item["write_capable_surface"]]
|
||
live_evidence = [item for item in acceptance_candidates if item["requires_live_evidence"]]
|
||
|
||
return {
|
||
"schema_version": "monitoring_owner_response_acceptance_v1",
|
||
"generated_at": report_time,
|
||
"git_commit": git_short_sha(root),
|
||
"source_inventory_schema_version": inventory.get("schema_version"),
|
||
"source_inventory_status": inventory.get("status"),
|
||
"source_owner_request_schema_version": request_draft_report.get("schema_version"),
|
||
"source_owner_request_status": request_draft_report.get("status"),
|
||
"status": "owner_response_acceptance_ledger_ready_no_runtime_action",
|
||
"summary": {
|
||
"source_surface_count": inventory.get("summary", {}).get("surface_count", 0),
|
||
"source_request_draft_count": request_draft_report.get("summary", {}).get("request_draft_count", 0),
|
||
"acceptance_candidate_count": len(acceptance_candidates),
|
||
"write_capable_acceptance_candidate_count": len(write_capable),
|
||
"live_evidence_required_candidate_count": len(live_evidence),
|
||
"acceptance_field_count": len(ACCEPTANCE_FIELDS),
|
||
"required_owner_field_count": len(request_draft_report["required_owner_fields"]),
|
||
"reviewer_check_count": len(REVIEWER_CHECKS),
|
||
"outcome_lane_count": len(OUTCOME_LANES),
|
||
"blocked_action_count": len(BLOCKED_ACTIONS),
|
||
"request_sent_count": 0,
|
||
"recipient_confirmed_count": 0,
|
||
"owner_response_received_count": 0,
|
||
"owner_response_accepted_count": 0,
|
||
"owner_response_rejected_count": 0,
|
||
"owner_response_quarantined_count": 0,
|
||
"supplement_requested_count": 0,
|
||
"live_evidence_received_count": 0,
|
||
"live_config_hash_accepted_count": 0,
|
||
"reload_owner_accepted_count": 0,
|
||
"receiver_owner_accepted_count": 0,
|
||
"route_smoke_accepted_count": 0,
|
||
"incident_context_accepted_count": 0,
|
||
"alert_chain_health_accepted_count": 0,
|
||
"receiver_receipt_proof_accepted_count": 0,
|
||
"stale_alert_review_accepted_count": 0,
|
||
"silence_or_dedup_review_accepted_count": 0,
|
||
"false_green_risk_review_accepted_count": 0,
|
||
"post_reload_readback_plan_accepted_count": 0,
|
||
"cross_project_notification_accepted_count": 0,
|
||
"maintenance_window_accepted_count": 0,
|
||
"rollback_owner_accepted_count": 0,
|
||
"validation_plan_accepted_count": 0,
|
||
"noise_budget_owner_accepted_count": 0,
|
||
"prometheus_reload_authorized_count": 0,
|
||
"alertmanager_reload_authorized_count": 0,
|
||
"grafana_dashboard_apply_authorized_count": 0,
|
||
"signoz_rule_apply_authorized_count": 0,
|
||
"sentry_deploy_authorized_count": 0,
|
||
"langfuse_config_change_authorized_count": 0,
|
||
"otel_collector_reload_authorized_count": 0,
|
||
"receiver_route_change_authorized_count": 0,
|
||
"silence_policy_change_authorized_count": 0,
|
||
"telegram_send_authorized_count": 0,
|
||
"notification_route_change_authorized_count": 0,
|
||
"webhook_receiver_change_authorized_count": 0,
|
||
"remote_write_change_authorized_count": 0,
|
||
"exporter_deploy_authorized_count": 0,
|
||
"live_alert_fire_authorized_count": 0,
|
||
"alert_chain_smoke_authorized_count": 0,
|
||
"ssh_read_authorized_count": 0,
|
||
"ssh_write_authorized_count": 0,
|
||
"kubectl_action_authorized_count": 0,
|
||
"secret_value_collection_allowed_count": 0,
|
||
"host_write_authorized_count": 0,
|
||
"active_scan_authorized_count": 0,
|
||
"production_write_authorized_count": 0,
|
||
"runtime_gate_count": 0,
|
||
"action_button_count": 0,
|
||
},
|
||
"execution_boundaries": {
|
||
"request_dispatch_authorized": False,
|
||
"owner_response_accepted": False,
|
||
"live_evidence_received": False,
|
||
"prometheus_reload_authorized": False,
|
||
"alertmanager_reload_authorized": False,
|
||
"grafana_dashboard_apply_authorized": False,
|
||
"signoz_rule_apply_authorized": False,
|
||
"sentry_deploy_authorized": False,
|
||
"langfuse_config_change_authorized": False,
|
||
"otel_collector_reload_authorized": False,
|
||
"receiver_route_change_authorized": False,
|
||
"silence_policy_change_authorized": False,
|
||
"telegram_send_authorized": False,
|
||
"notification_route_change_authorized": False,
|
||
"webhook_receiver_change_authorized": False,
|
||
"remote_write_change_authorized": False,
|
||
"exporter_deploy_authorized": False,
|
||
"live_alert_fire_authorized": False,
|
||
"alert_chain_smoke_authorized": False,
|
||
"ssh_read_authorized": False,
|
||
"ssh_write_authorized": False,
|
||
"kubectl_action_authorized": False,
|
||
"secret_value_collection_allowed": False,
|
||
"host_write_authorized": False,
|
||
"active_scan_authorized": False,
|
||
"production_write_authorized": False,
|
||
"runtime_execution_authorized": False,
|
||
"route_200_alert_chain_health_accepted": False,
|
||
"receiver_health_without_receipt_accepted": False,
|
||
"false_green_acceptance_authorized": False,
|
||
"raw_alert_payload_storage_allowed": False,
|
||
"action_buttons_allowed": False,
|
||
"not_authorization": True,
|
||
},
|
||
"acceptance_fields": ACCEPTANCE_FIELDS,
|
||
"required_owner_fields": request_draft_report["required_owner_fields"],
|
||
"reviewer_checks": REVIEWER_CHECKS,
|
||
"outcome_lanes": OUTCOME_LANES,
|
||
"blocked_actions": BLOCKED_ACTIONS,
|
||
"acceptance_candidates": acceptance_candidates,
|
||
"next_steps": [
|
||
"等待 owner response；未收到前不得更新 received / accepted / rejected count。",
|
||
"收到回覆後先做欄位完整性、敏感 payload 隔離、reload / send / smoke execution request 拒收。",
|
||
"metadata 合格也只能進 monitoring reviewer review；reload、receiver route change、Telegram send、live alert fire、alert chain smoke 與 production write 仍需獨立人工批准。",
|
||
],
|
||
}
|
||
|
||
|
||
def main() -> int:
|
||
parser = argparse.ArgumentParser(description="IwoooS Monitoring owner response acceptance 只讀帳本產生器")
|
||
parser.add_argument("--root", default=".", help="repo root")
|
||
parser.add_argument(
|
||
"--inventory-report",
|
||
default="docs/security/monitoring-alerting-observability-inventory.snapshot.json",
|
||
help="monitoring-alerting-observability-inventory.py 輸出的 JSON",
|
||
)
|
||
parser.add_argument(
|
||
"--owner-request-report",
|
||
default="docs/security/monitoring-owner-request-draft.snapshot.json",
|
||
help="monitoring-owner-request-draft.py 輸出的 JSON",
|
||
)
|
||
parser.add_argument("--output", help="寫出 JSON 報告")
|
||
parser.add_argument("--generated-at", help="固定報告時間，供 committed snapshot 使用")
|
||
args = parser.parse_args()
|
||
|
||
root = Path(args.root).resolve()
|
||
inventory = load_json(root / args.inventory_report)
|
||
request_draft_report = load_json(root / args.owner_request_report)
|
||
report = build_report(root, inventory, request_draft_report, args.generated_at)
|
||
payload = json.dumps(report, ensure_ascii=False, indent=2, sort_keys=True)
|
||
|
||
if args.output:
|
||
output = Path(args.output)
|
||
output.parent.mkdir(parents=True, exist_ok=True)
|
||
output.write_text(payload + "\n", encoding="utf-8")
|
||
else:
|
||
print(payload)
|
||
|
||
summary = report["summary"]
|
||
print(
|
||
"MONITORING_OWNER_RESPONSE_ACCEPTANCE_OK "
|
||
f"candidates={summary['acceptance_candidate_count']} "
|
||
f"write_capable={summary['write_capable_acceptance_candidate_count']} "
|
||
f"checks={summary['reviewer_check_count']} "
|
||
f"lanes={summary['outcome_lane_count']} "
|
||
f"accepted={summary['owner_response_accepted_count']} "
|
||
f"runtime_gate={summary['runtime_gate_count']}",
|
||
file=sys.stderr,
|
||
)
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|