diff --git a/CONSTITUTION.md b/CONSTITUTION.md index 5cab4f1..c86a72c 100644 --- a/CONSTITUTION.md +++ b/CONSTITUTION.md @@ -2,7 +2,7 @@ > 本文件定義專案開發的核心準則與不可違反的規範 > **建立日期**: 2026-01-12 -> **當前版本**: V10.6 (四 AI Agent 自動化 Smoke Dashboard 版) +> **當前版本**: V10.7 (四 AI Agent 自動化 Smoke 趨勢版) > **最後更新**: 2026-04-29 --- diff --git a/TODO_NEXT_STEPS.txt b/TODO_NEXT_STEPS.txt index 9065aed..aecef29 100644 --- a/TODO_NEXT_STEPS.txt +++ b/TODO_NEXT_STEPS.txt @@ -7,14 +7,15 @@ - ADR-018：四 AI Agent 自動化控制面立案。 - Memory：新增 `docs/memory/ai_automation_closure_20260429.md`。 - Guide/Skills 替代：新增 `docs/guides/ai_automation_session_sop.md`。 - - SOT：更新 `docs/AI_INTELLIGENCE_MODULE_SOT.md` 至 V10.6 AI Automation Smoke Dashboard 架構。 + - SOT：更新 `docs/AI_INTELLIGENCE_MODULE_SOT.md` 至 V10.7 AI Automation Smoke Trend 架構。 - Codex 規則：更新 `AGENTS.md`、`CONSTITUTION.md`、ADR/memory 索引。 - Prometheus 指標化：新增 EventRouter / AutoHeal / safe action / replay in-process metrics，並接入 `/metrics`。 - 線上 smoke dashboard：新增 `/ai_automation_smoke` 與 `/api/ai-automation/smoke`，覆蓋 EventRouter、AutoHeal、NemoTron fallback、OpenClaw embedding queue、ElephantAlpha HITL。 + - Smoke 趨勢保存：`/api/ai-automation/smoke` 每次快檢追加 JSONL 精簡紀錄，dashboard 顯示最近趨勢。 【下次待辦】 - Superset / Grafana 視覺化：`momo_ai_event_router_dispatch_total`、`momo_ai_event_router_latency_ms_*`、`momo_ai_autoheal_action_total`。 - - Smoke dashboard 增加最近一次實際 smoke test 結果保存與趨勢圖。 + - Smoke trend 增加手動清理/匯出與每日摘要。 ================================================================================ 品牌資產最終處理與維護 (Phase 7) [DONE] diff --git a/app.py b/app.py index f39e13e..fd5e11f 100644 --- a/app.py +++ b/app.py @@ -95,9 +95,9 @@ except Exception as e: sys_log.error(f"無法檢測磁碟空間: {e}") # 🚩 系統版本定義 (備份與顯示用) -# 🚩 2026-04-29 V10.6: AI 自動化 Smoke Dashboard — EventRouter / AutoHeal / -# NemoTron / OpenClaw / ElephantAlpha 線上閉環快檢 -SYSTEM_VERSION = "V10.6" +# 🚩 2026-04-29 V10.7: AI Smoke 趨勢保存 — 最近快檢結果 JSONL +# 持久化與 dashboard 趨勢視覺化 +SYSTEM_VERSION = "V10.7" # ========================================== # 🔒 SQL Injection 防護函數 diff --git a/config.py b/config.py index ffe9d11..a850453 100644 --- a/config.py +++ b/config.py @@ -253,7 +253,7 @@ YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY', '') # ========================================== # 系統版本與路徑 # ========================================== -SYSTEM_VERSION = "V10.6" +SYSTEM_VERSION = "V10.7" LOG_FILE_PATH = os.path.join(BASE_DIR, 'logs/system.log') public_url = PUBLIC_URL # 用於模板顯示 diff --git a/docs/AI_INTELLIGENCE_MODULE_SOT.md b/docs/AI_INTELLIGENCE_MODULE_SOT.md index f6211d4..0ce4bb9 100644 --- a/docs/AI_INTELLIGENCE_MODULE_SOT.md +++ b/docs/AI_INTELLIGENCE_MODULE_SOT.md @@ -1,8 +1,8 @@ # MOMO PRO — AI 競價情報模組 Single Source of Truth > **最後更新**: 2026-04-29 (台北時間) -> **狀態**: 🟢 四 AI Agent 自動化閉環已落地 — EventRouter / AutoHeal / OpenClaw Memory / ElephantAlpha bridge / Prometheus metrics / Smoke Dashboard 具測試覆蓋 -> **適用版本**: V10.6 AI Automation Smoke Dashboard 架構 +> **狀態**: 🟢 四 AI Agent 自動化閉環已落地 — EventRouter / AutoHeal / OpenClaw Memory / ElephantAlpha bridge / Prometheus metrics / Smoke Dashboard / Smoke Trend 具測試覆蓋 +> **適用版本**: V10.7 AI Automation Smoke Trend 架構 --- @@ -64,6 +64,7 @@ SQL漏斗(~300筆) - `/metrics` 匯出 `momo_ai_autoheal_action_total` 與 `momo_ai_autoheal_duration_ms_count/sum/max`。 - `/ai_automation_smoke` 提供登入後 smoke dashboard。 - `/api/ai-automation/smoke` 提供 read-only JSON 狀態，不做外部網路呼叫。 +- Smoke API 會將最近快檢結果保存到 JSONL，dashboard 顯示最近狀態趨勢。 --- diff --git a/docs/adr/ADR-012-agent-action-ladder.md b/docs/adr/ADR-012-agent-action-ladder.md index fe04797..5d13d0d 100644 --- a/docs/adr/ADR-012-agent-action-ladder.md +++ b/docs/adr/ADR-012-agent-action-ladder.md @@ -145,7 +145,8 @@ L1 Hermes 掛 → L0 模板直出 + 🟡 「AI 分析暫不可用」 - L3 已擴展為 OpenClaw + ElephantAlpha：OpenClaw 負責策略/記憶，ElephantAlpha 負責 orchestration/HITL/AutoHeal bridge。 - 2026-04-29 已補 `/metrics` 匯出：EventRouter dispatch、L2 safe action、Telegram replay、AutoHeal action 與 latency/duration。 - 2026-04-29 已補 `/ai_automation_smoke` 與 `/api/ai-automation/smoke`：EventRouter、AutoHeal、NemoTron fallback、OpenClaw embedding queue、ElephantAlpha HITL 線上快檢。 -- 尚未完成：Grafana/Superset 視覺化面板與 smoke 結果趨勢保存。 +- 2026-04-29 已補 smoke 結果 JSONL 保存與 dashboard 趨勢視覺化。 +- 尚未完成：Grafana/Superset 視覺化面板與 smoke 每日摘要。 ## References - `services/event_router.py` — 分流入口（Phase 1） diff --git a/docs/guides/ai_automation_session_sop.md b/docs/guides/ai_automation_session_sop.md index 4de6ce8..25f1cff 100644 --- a/docs/guides/ai_automation_session_sop.md +++ b/docs/guides/ai_automation_session_sop.md @@ -26,6 +26,7 @@ - Telegram 失敗必須可暫存與 replay。 - EventRouter / AutoHeal 變更必須更新 `services/ai_automation_metrics.py` 指標或確認既有指標已覆蓋。 - AI 自動化閉環變更必須確認 `/api/ai-automation/smoke` 與 `/ai_automation_smoke` 仍能反映新狀態。 +- Smoke dashboard 會保存 JSONL 趨勢；若新增檢查項目，要確保 history compact record 仍保持小而可讀。 - L2 action 必須在 `SAFE_ACTIONS` 且可審計、可回放、低副作用。 - AutoHeal 不得 restart / stop / recreate `momo-db` 或 `momo-postgres`。 - raw `ai_insights` 寫入後必須 enqueue embedding；若 enqueue 失敗，必須可 backfill。 diff --git a/docs/memory/ai_automation_closure_20260429.md b/docs/memory/ai_automation_closure_20260429.md index 0af3763..52a7c6e 100644 --- a/docs/memory/ai_automation_closure_20260429.md +++ b/docs/memory/ai_automation_closure_20260429.md @@ -11,6 +11,7 @@ - ElephantAlpha 只負責 orchestration / HITL / AutoHeal bridge，不可繞過 ADR-011、ADR-012、ADR-013。 - AI 自動化最小 Prometheus 指標已接入 `/metrics`，來源為 `services/ai_automation_metrics.py`。 - 線上 smoke dashboard 已接入 `/ai_automation_smoke`，JSON API 為 `/api/ai-automation/smoke`。 +- Smoke API 會保存最近快檢 JSONL 趨勢，dashboard 顯示 OK / Warning / Critical 最近分布。 ## 已落地範圍 @@ -24,11 +25,13 @@ - L2 `agent_actions.py` 的 `flag_for_human_review`、`route_to_km`、`mark_for_relearn` 已從 stub 改為可審計 OpenClaw memory 寫入。 - `/metrics` 已匯出 EventRouter dispatch、latency、safe action、Telegram replay、AutoHeal action 與 duration 指標。 - Smoke dashboard read-only 檢查 EventRouter queue、AutoHeal protected resources、NemoTron fallback、OpenClaw embedding queue、ElephantAlpha HITL，不做外部網路呼叫。 +- Smoke history 只保存精簡紀錄，不保存完整 details，避免長期檔案膨脹與敏感資訊堆積。 ## 驗證紀錄 - 2026-04-29 AI metrics 批次：`26 passed`。 - 2026-04-29 AI smoke dashboard 批次：`2 passed`（單檔 smoke service），後續核心組需持續納入。 +- 2026-04-29 AI smoke trend 批次：`5 passed`（smoke + metrics）。 - 2026-04-29 L2 安全記憶批次：`24 passed`。 - collect-only：`48 tests collected`。 - `git diff --check` 已通過。 diff --git a/docs/memory/history_logs.md b/docs/memory/history_logs.md index 0b7d5d9..3d39473 100644 --- a/docs/memory/history_logs.md +++ b/docs/memory/history_logs.md @@ -26,6 +26,7 @@ - **L2 action 落地**: `flag_for_human_review`、`route_to_km`、`mark_for_relearn` 改為可審計 OpenClaw memory 寫入。 - **可觀測性落地**: `/metrics` 匯出 EventRouter dispatch/latency、safe action、Telegram replay、AutoHeal action/duration 指標。 - **Smoke Dashboard**: 新增 `/ai_automation_smoke` 與 `/api/ai-automation/smoke`，提供四 Agent 閉環 read-only 快檢。 +- **Smoke 趨勢保存**: Smoke API 追加 JSONL 精簡紀錄，dashboard 顯示最近 OK / Warning / Critical 趨勢。 ### 2026-04-28~29：Phase 3e 重構大戰 + daily_sales cache 隱形 bug 根除 - **app.py 縮減 -10.8%**: 7,386 → 6,590 行，11 commits 全綠零 502。 diff --git a/services/ai_automation_smoke_service.py b/services/ai_automation_smoke_service.py index 6f5948e..49799ac 100644 --- a/services/ai_automation_smoke_service.py +++ b/services/ai_automation_smoke_service.py @@ -7,6 +7,8 @@ are meant for a fast dashboard/API sanity check, not for deep production probes. from __future__ import annotations import os +import json +import threading from datetime import datetime from typing import Any, Dict, List @@ -17,6 +19,12 @@ from database.manager import get_session STATUS_RANK = {"ok": 0, "warning": 1, "critical": 2} +_HISTORY_PATH = os.getenv( + "MOMO_AI_AUTOMATION_SMOKE_HISTORY", + os.path.join(os.path.dirname(os.path.dirname(__file__)), "data", "ai_automation_smoke_history.jsonl"), +) +_HISTORY_LIMIT = int(os.getenv("MOMO_AI_AUTOMATION_SMOKE_HISTORY_LIMIT", "200")) +_HISTORY_LOCK = threading.Lock() def _check(name: str, status: str, summary: str, details: Dict[str, Any] | None = None) -> Dict[str, Any]: @@ -36,6 +44,73 @@ def _count_jsonl_lines(path: str) -> int: return 0 +def _compact_history_record(result: Dict[str, Any]) -> Dict[str, Any]: + return { + "generated_at": result.get("generated_at"), + "status": result.get("status", "critical"), + "summary": result.get("summary", {}), + "checks": [ + { + "name": item.get("name"), + "status": item.get("status"), + "summary": item.get("summary"), + } + for item in result.get("checks", []) + ], + } + + +def _load_history(limit: int = 20) -> List[Dict[str, Any]]: + if limit <= 0: + return [] + try: + with _HISTORY_LOCK: + with open(_HISTORY_PATH, "r", encoding="utf-8") as fh: + lines = fh.readlines() + except FileNotFoundError: + return [] + + records = [] + for line in lines[-limit:]: + try: + records.append(json.loads(line)) + except json.JSONDecodeError: + continue + return records + + +def _append_history(result: Dict[str, Any]) -> None: + record = _compact_history_record(result) + os.makedirs(os.path.dirname(_HISTORY_PATH), exist_ok=True) + with _HISTORY_LOCK: + existing = [] + try: + with open(_HISTORY_PATH, "r", encoding="utf-8") as fh: + existing = fh.readlines() + except FileNotFoundError: + pass + + existing.append(json.dumps(record, ensure_ascii=False, default=str) + "\n") + if len(existing) > _HISTORY_LIMIT: + existing = existing[-_HISTORY_LIMIT:] + + with open(_HISTORY_PATH, "w", encoding="utf-8") as fh: + fh.writelines(existing) + + +def _history_summary(records: List[Dict[str, Any]]) -> Dict[str, Any]: + counts = {"ok": 0, "warning": 0, "critical": 0} + for record in records: + status = record.get("status", "critical") + if status in counts: + counts[status] += 1 + return { + "counts": counts, + "recent": records, + "latest": records[-1] if records else None, + } + + def _event_router_check() -> Dict[str, Any]: try: from services import event_router @@ -187,7 +262,7 @@ def _elephant_hitl_check() -> Dict[str, Any]: return _check("ElephantAlpha HITL", "critical", f"ElephantAlpha smoke 失敗：{exc}") -def collect_ai_automation_smoke() -> Dict[str, Any]: +def collect_ai_automation_smoke(*, record_history: bool = True, history_limit: int = 20) -> Dict[str, Any]: checks: List[Dict[str, Any]] = [ _event_router_check(), _autoheal_check(), @@ -196,7 +271,7 @@ def collect_ai_automation_smoke() -> Dict[str, Any]: _elephant_hitl_check(), ] worst = max(checks, key=lambda item: STATUS_RANK.get(item["status"], 2))["status"] - return { + result = { "status": worst, "version": SYSTEM_VERSION, "generated_at": datetime.now().isoformat(timespec="seconds"), @@ -208,3 +283,10 @@ def collect_ai_automation_smoke() -> Dict[str, Any]: "total": len(checks), }, } + if record_history: + try: + _append_history(result) + except Exception as exc: + result["history_error"] = str(exc)[:300] + result["history"] = _history_summary(_load_history(limit=history_limit)) + return result diff --git a/templates/ai_automation_smoke.html b/templates/ai_automation_smoke.html index b782dcd..dd2d1b1 100644 --- a/templates/ai_automation_smoke.html +++ b/templates/ai_automation_smoke.html @@ -80,6 +80,23 @@ overflow: auto; white-space: pre-wrap; } + + .trend-strip { + display: grid; + grid-template-columns: repeat(auto-fit, minmax(14px, 1fr)); + gap: 6px; + align-items: end; + } + + .trend-dot { + height: 34px; + border-radius: 8px; + opacity: .92; + } + + .trend-dot.status-ok { background: #22c55e; } + .trend-dot.status-warning { background: #f59e0b; } + .trend-dot.status-critical { background: #ef4444; } {% endblock %} @@ -108,6 +125,19 @@
Generated
-
+
+
+
+
+
最近 Smoke 趨勢
+
每次 API 快檢會保存一筆精簡紀錄，保留最近 200 筆。
+
+
等待資料...
+
+
+
+
+
{% endblock %} @@ -134,6 +164,7 @@ function renderSmoke(data) { document.getElementById('warningCount').textContent = data.summary.warning ?? 0; document.getElementById('criticalCount').textContent = data.summary.critical ?? 0; document.getElementById('generatedAt').textContent = data.generated_at || '-'; + renderTrend(data.history || {}); const grid = document.getElementById('checkGrid'); grid.innerHTML = data.checks.map(item => ` @@ -150,6 +181,24 @@ function renderSmoke(data) { `).join(''); } +function renderTrend(history) { + const recent = history.recent || []; + const counts = history.counts || {ok: 0, warning: 0, critical: 0}; + document.getElementById('historySummary').textContent = + `OK ${counts.ok || 0} / Warning ${counts.warning || 0} / Critical ${counts.critical || 0}`; + + const strip = document.getElementById('trendStrip'); + if (!recent.length) { + strip.innerHTML = '
尚無歷史紀錄。
'; + return; + } + strip.innerHTML = recent.map(item => ` +
+
+ `).join(''); +} + async function loadSmoke() { const btn = document.getElementById('refreshBtn'); btn.disabled = true; diff --git a/tests/test_ai_automation_smoke_service.py b/tests/test_ai_automation_smoke_service.py index 43518db..d7fa194 100644 --- a/tests/test_ai_automation_smoke_service.py +++ b/tests/test_ai_automation_smoke_service.py @@ -32,7 +32,29 @@ def test_collect_ai_automation_smoke_uses_worst_status(monkeypatch): monkeypatch.setattr(smoke, "_embedding_queue_check", lambda: smoke._check("embedding", "critical", "boom")) monkeypatch.setattr(smoke, "_elephant_hitl_check", lambda: smoke._check("elephant", "ok", "ok")) - result = smoke.collect_ai_automation_smoke() + result = smoke.collect_ai_automation_smoke(record_history=False) assert result["status"] == "critical" assert result["summary"] == {"ok": 3, "warning": 1, "critical": 1, "total": 5} + + +def test_collect_ai_automation_smoke_persists_recent_history(tmp_path, monkeypatch): + from services import ai_automation_smoke_service as smoke + + history_path = tmp_path / "smoke_history.jsonl" + monkeypatch.setattr(smoke, "_HISTORY_PATH", str(history_path)) + monkeypatch.setattr(smoke, "_HISTORY_LIMIT", 2) + monkeypatch.setattr(smoke, "_event_router_check", lambda: smoke._check("event", "ok", "ok")) + monkeypatch.setattr(smoke, "_autoheal_check", lambda: smoke._check("autoheal", "ok", "ok")) + monkeypatch.setattr(smoke, "_nemotron_check", lambda: smoke._check("nemotron", "ok", "ok")) + monkeypatch.setattr(smoke, "_embedding_queue_check", lambda: smoke._check("embedding", "ok", "ok")) + monkeypatch.setattr(smoke, "_elephant_hitl_check", lambda: smoke._check("elephant", "ok", "ok")) + + first = smoke.collect_ai_automation_smoke(history_limit=5) + second = smoke.collect_ai_automation_smoke(history_limit=5) + third = smoke.collect_ai_automation_smoke(history_limit=5) + + assert first["status"] == "ok" + assert second["history"]["counts"]["ok"] == 2 + assert third["history"]["counts"]["ok"] == 2 + assert len(history_path.read_text(encoding="utf-8").strip().splitlines()) == 2