1052 lines
47 KiB
Python
1052 lines
47 KiB
Python
"""
|
||
AWOOOI API Configuration
|
||
========================
|
||
Pydantic Settings + Environment Variables
|
||
|
||
ADR-005: BFF Architecture
|
||
ADR-006: AI Fallback Strategy (Ollama -> Gemini -> Claude)
|
||
|
||
Four Iron Laws:
|
||
1. Async-First
|
||
2. CORS Whitelist (NO wildcard)
|
||
3. Pydantic Config (this file)
|
||
4. structlog
|
||
"""
|
||
|
||
from functools import lru_cache
|
||
from typing import Literal
|
||
|
||
from pydantic import Field, HttpUrl, field_validator
|
||
from pydantic_settings import BaseSettings, SettingsConfigDict
|
||
|
||
|
||
class Settings(BaseSettings):
|
||
"""
|
||
Application settings from environment variables
|
||
|
||
All settings can be overridden via .env file or environment variables.
|
||
"""
|
||
|
||
model_config = SettingsConfigDict(
|
||
env_file=".env",
|
||
env_file_encoding="utf-8",
|
||
case_sensitive=True,
|
||
extra="ignore",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Application
|
||
# ==========================================================================
|
||
VERSION: str = "1.0.0"
|
||
ENVIRONMENT: Literal["dev", "prod"] = "dev"
|
||
DEBUG: bool = False
|
||
LOG_LEVEL: Literal["DEBUG", "INFO", "WARNING", "ERROR"] = "INFO"
|
||
SYSTEM_NAME: str = "awoooi"
|
||
|
||
# ==========================================================================
|
||
# Mock Mode - 開發時模擬外部服務
|
||
# ==========================================================================
|
||
MOCK_MODE: bool = Field(
|
||
default=False,
|
||
description="Enable mock mode for external services (Redis, Ollama, OpenClaw, PostgreSQL, SigNoz)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# ==========================================================================
|
||
# Phase 24: AI Provider Registry (ADR-052)
|
||
# 2026-04-02 ogt: 絞殺者開關 — true=新 AIRouter, false=舊 openclaw.py if/else
|
||
# 回滾指令: kubectl set env deployment/awoooi-api USE_AI_ROUTER=false
|
||
# ==========================================================================
|
||
USE_AI_ROUTER: bool = Field(
|
||
default=False,
|
||
description="Phase 24: True=新 AIRouter 路由, False=舊 openclaw.py fallback chain",
|
||
)
|
||
ENABLE_OPENCLAW_AGENT_LOOP_SHADOW: bool = Field(
|
||
default=False,
|
||
description="ADR-105 P1: True=OpenClaw 生成 proposal 後用本地 Agent Loop 做 read-only shadow investigation, False=不執行",
|
||
)
|
||
OPENCLAW_AGENT_LOOP_MAX_ITERATIONS: int = Field(
|
||
default=3,
|
||
ge=1,
|
||
le=5,
|
||
description="ADR-105 P1: OpenClaw Agent Loop shadow 最大 tool_use 輪數",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# W1 PR-P1: Playbook 匹配 Feature Flag (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# 修復飛輪斷鏈 C1 — proposal_service 填 matched_playbook_id → EWMA 更新
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_PLAYBOOK_MATCHING=false
|
||
# ==========================================================================
|
||
ENABLE_PLAYBOOK_MATCHING: bool = Field(
|
||
default=True,
|
||
description="W1 PR-P1: True=generate_proposal 時執行 Playbook RAG 匹配並填 matched_playbook_id, False=行為與修復前完全相同（回滾用）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# W1 PR-R1: 規則 → Playbook 遷移 Feature Flag (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# 將 alert_rules.yaml 25 條規則遷移為 DRAFT Playbook（飛輪 RAG 冷啟動）
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_RULE_MIGRATION_DRAFT=false
|
||
# ==========================================================================
|
||
ENABLE_RULE_MIGRATION_DRAFT: bool = Field(
|
||
default=True,
|
||
description="W1 PR-R1: True=允許 migrate_rules_to_playbooks CLI 寫入 DB, False=停用寫入（回滾用）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# P1-1: KMWriter 統一契約 (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# KM_WRITE_AWAIT=true → 強制 await asyncio.wait_for(timeout=KM_WRITE_TIMEOUT_SECONDS)
|
||
# KM_WRITE_AWAIT=false → 舊 fire-and-forget 行為（回滾用）
|
||
# 回滾指令: kubectl set env deployment/awoooi-api KM_WRITE_AWAIT=false
|
||
# ==========================================================================
|
||
KM_WRITE_AWAIT: bool = Field(
|
||
default=True,
|
||
description="P1-1: True=強制 await KM 寫入（可靠）, False=緊急降級（1次嘗試+DLQ，回滾用）",
|
||
)
|
||
KM_WRITE_TIMEOUT_SECONDS: float = Field(
|
||
default=5.0,
|
||
description="P1-1: KMWriter await timeout（秒），超時記錄 warning 但不阻塞主流程",
|
||
)
|
||
# C1 2026-04-28 ogt + Claude Sonnet 4.6: KM Backfill Reconciler
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_KM_BACKFILL_RECONCILER=false
|
||
ENABLE_KM_BACKFILL_RECONCILER: bool = Field(
|
||
default=True,
|
||
description="C1: True=啟用 km:backfill:dlq 補掃 job（每 5 分鐘）, False=停用",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# W2 PR-R2: AOL → alert_rule_catalog Confidence EWMA Writeback
|
||
# ADR-091 Task T2 — 飛輪斷鏈 C2 修復：規則命中率回灌 catalog confidence
|
||
# default=false：先寫 code，人工驗證 AOL 資料品質後再開啟
|
||
# 啟用：kubectl set env deployment/awoooi-api ENABLE_AOL_WRITEBACK_JOB=true
|
||
# 回滾：kubectl set env deployment/awoooi-api ENABLE_AOL_WRITEBACK_JOB=false
|
||
# ==========================================================================
|
||
ENABLE_AOL_WRITEBACK_JOB: bool = Field(
|
||
default=False,
|
||
description="W2 PR-R2: True=每小時從 AOL 聚合 alertname 成功率並 EWMA 更新 alert_rule_catalog.confidence, False=停用（預設）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# W2 PR-L1: KM → Playbook 互饋回路 (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# 飛輪斷鏈 C3 + C4 修復 — KM 與 Playbook 演化互饋
|
||
# 邏輯 1: promote/demote 觸發 → 寫 KM 演化條目（path_type=playbook_evolution）
|
||
# 邏輯 2: 同 symptom_pattern_hash 累積 N=5 條 KM → 標記 playbook.review_required=true
|
||
# 邏輯 3: DEPRECATED Playbook → 降低 alert_rule_catalog.confidence *= 0.5
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_KM_PLAYBOOK_FEEDBACK_LOOP=false
|
||
# ==========================================================================
|
||
ENABLE_KM_PLAYBOOK_FEEDBACK_LOOP: bool = Field(
|
||
default=False,
|
||
description="W2 PR-L1: True=啟用 KM↔Playbook 互饋回路（飛輪 C3+C4 修復）, False=停用（default，驗證後才開）",
|
||
)
|
||
KM_PLAYBOOK_REVIEW_THRESHOLD: int = Field(
|
||
default=5,
|
||
description="W2 PR-L1: 同 symptom_pattern_hash 累積幾條 KM 後觸發 Playbook review_required 標記（預設 N=5）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# ADR-104: LLM Playbook Generator
|
||
# 成功修復且未命中既有 Playbook 時，用本地 LLM 生成 DRAFT/REVIEW Playbook。
|
||
# 成本護欄：實作層只走 local provider（GCP-A → GCP-B → 111），不新增雲端 fallback。
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_LLM_PLAYBOOK_GENERATION=false
|
||
# ==========================================================================
|
||
ENABLE_LLM_PLAYBOOK_GENERATION: bool = Field(
|
||
default=True,
|
||
description="ADR-104 T1: True=成功修復無 matched_playbook_id 時啟動本地 LLM 生成 Playbook, False=只用 deterministic extraction",
|
||
)
|
||
ENABLE_PLAYBOOK_DRAFT_GOVERNANCE_JOB: bool = Field(
|
||
default=True,
|
||
description="ADR-104 T2: True=定期治理 LLM Playbook DRAFT/REVIEW 晉級, False=停用",
|
||
)
|
||
PLAYBOOK_DRAFT_GOVERNANCE_INTERVAL_SECONDS: int = Field(
|
||
default=3600,
|
||
ge=60,
|
||
description="ADR-104 T2: Playbook DRAFT governance job interval seconds",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# aider-watch v2 integration (2026-04-20 ADR-091)
|
||
# 整合 Mac aider CLI 監控進 awoooi 飛輪（events → incident → ai_router feedback）
|
||
# 回滾：kubectl set env deployment/awoooi-api USE_AIDER_FEEDBACK=false
|
||
# ==========================================================================
|
||
AIDER_WEBHOOK_SECRET: str = Field(
|
||
default="",
|
||
description="HMAC secret for /api/v1/aider/events webhook verification",
|
||
)
|
||
AIDER_EVENTS_STREAM_KEY: str = Field(
|
||
default="signals:aider:events",
|
||
description="Redis stream key for aider event ingestion",
|
||
)
|
||
AIDER_PATTERN_EXTRACT_INTERVAL_HOURS: float = Field(
|
||
default=24.0,
|
||
description="Aider event pattern extraction interval (future use)",
|
||
)
|
||
USE_AIDER_FEEDBACK: bool = Field(
|
||
default=False,
|
||
description="Phase 24 A8: True=ai_router.route() 讀 aider 成功率調權重, False=不讀（預設）",
|
||
)
|
||
|
||
# Phase 22: OpenClaw + Nemotron 協作 (ADR-044)
|
||
# 2026-03-31 Claude Code: 統帥批准實作
|
||
#
|
||
# 功能:
|
||
# - ENABLE_NEMOTRON_COLLABORATION: 啟用 OpenClaw + Nemotron 雙軌協作
|
||
# - NEMOTRON_TIMEOUT_SECONDS: Nemotron API 呼叫超時
|
||
# - NEMOTRON_ASYNC_UPDATE: 異步更新模式 (先推 OpenClaw，後更新 Nemotron)
|
||
#
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_NEMOTRON_COLLABORATION=false
|
||
# ==========================================================================
|
||
ENABLE_NEMOTRON_COLLABORATION: bool = Field(
|
||
default=True,
|
||
description="Phase 22: True=啟用 OpenClaw+Nemotron 協作, False=僅 OpenClaw",
|
||
)
|
||
NEMOTRON_TIMEOUT_SECONDS: int = Field(
|
||
default=45,
|
||
description="Phase 22: Nemotron API 呼叫超時 (秒)",
|
||
)
|
||
NEMOTRON_ASYNC_UPDATE: bool = Field(
|
||
default=True,
|
||
description="Phase 22: True=異步更新 (先推 OpenClaw), False=同步等待",
|
||
)
|
||
# 2026-04-05 Claude Code: Phase 25 P0 v4.3 — DIAGNOSE timeout 依實測修正
|
||
# 實測依據 (2026-04-05):
|
||
# NIM (nvidia/nemotron-mini-4b-instruct): 2.2s~27.3s，平均 10.6s → 60s timeout (27s * 2 + buffer)
|
||
# Ollama llama3.2:3b CPU-only: 238s 回 {"ok":true} → 不可用於生產，timeout 保留但實際走 NIM
|
||
NEMOTRON_DIAGNOSE_TIMEOUT_SECONDS: int = Field(
|
||
default=60,
|
||
description="Phase 25 P0: DIAGNOSE NIM timeout (秒)，實測 2.2-27.3s avg 10.6s，60s 含 buffer",
|
||
)
|
||
OLLAMA_DIAGNOSE_TIMEOUT_SECONDS: int = Field(
|
||
default=300,
|
||
description="Ollama diagnose timeout (秒)。GCP qwen3:14b CPU-only can exceed the old 120s proxy limit.",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Gitea — ADR-057 adopt() Gitea PR API (2026-04-05)
|
||
# ==========================================================================
|
||
GITEA_API_URL: str = Field(
|
||
default="http://192.168.0.110:3001",
|
||
description="Gitea 內網 API base URL",
|
||
)
|
||
GITEA_API_TOKEN: str = Field(
|
||
default="",
|
||
description="Gitea API Token（需 write:repository scope），ADR-057 adopt() 使用",
|
||
)
|
||
GITEA_REPO_OWNER: str = Field(default="wooo", description="Gitea repo owner")
|
||
GITEA_REPO_NAME: str = Field(default="awoooi", description="Gitea repo name")
|
||
|
||
# ==========================================================================
|
||
# CORS - 嚴格白名單 (無 UAT, 無 wildcard)
|
||
# ==========================================================================
|
||
CORS_ORIGINS: list[str] = Field(
|
||
default=[
|
||
"http://localhost:3000",
|
||
"http://localhost:3001",
|
||
"http://localhost:3002",
|
||
"http://localhost:3003",
|
||
"http://localhost:3333",
|
||
"http://192.168.0.168:3000", # 168 MacBook 本機開發
|
||
"http://192.168.0.188:3000", # 188 本機開發
|
||
"http://192.168.0.125:32335", # K3s VIP NodePort (staging/QA)
|
||
"http://192.168.0.120:32335", # K3s node-1 NodePort
|
||
"http://192.168.0.121:32335", # K3s node-2 NodePort
|
||
"https://awoooi.wooo.work",
|
||
],
|
||
description="Allowed CORS origins - NO wildcards allowed",
|
||
)
|
||
|
||
@field_validator("CORS_ORIGINS", mode="before")
|
||
@classmethod
|
||
def parse_cors_origins(cls, v: str | list[str]) -> list[str]:
|
||
if isinstance(v, str):
|
||
origins = [origin.strip() for origin in v.split(",")]
|
||
else:
|
||
origins = v
|
||
# Security check: reject wildcards
|
||
if "*" in origins:
|
||
raise ValueError("Wildcard (*) is NOT allowed in CORS_ORIGINS")
|
||
return origins
|
||
|
||
# ==========================================================================
|
||
# Database (PostgreSQL on 192.168.0.188)
|
||
# ==========================================================================
|
||
# 2026-04-22 ogt: 移除含 changeme 的 default，改為必填。
|
||
# 來源: K8s Secret awoooi-secrets → DATABASE_URL
|
||
DATABASE_URL: str = Field(
|
||
description="PostgreSQL connection URL (必填，從 K8s Secret awoooi-secrets → DATABASE_URL 取得)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Redis (192.168.0.188:6380, DB 0 - 與 OpenClaw 共用)
|
||
# ==========================================================================
|
||
REDIS_URL: str = Field(
|
||
default="redis://192.168.0.188:6380/0",
|
||
description="Redis connection URL (DB 0 shared with OpenClaw)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# External Services - Four Host Architecture
|
||
# ==========================================================================
|
||
# 2026-05-03 ogt: GCP 三層容災（ADR-110），GCP-A → GCP-B → Local → Gemini
|
||
OLLAMA_URL: str = Field(
|
||
default="http://34.143.170.20:11434", # 2026-05-03 ogt: 切換至 GCP-A SSD 主機（9x 載速 + 2x 推理）
|
||
description="Ollama LLM service URL (GCP-A Primary)",
|
||
)
|
||
# 2026-05-03 ogt: GCP-B SSD 備援（ADR-110 三層容災第二層）
|
||
OLLAMA_SECONDARY_URL: str = Field(
|
||
default="http://34.21.145.224:11434", # 2026-05-03 ogt: GCP-B SSD 備援
|
||
description="Ollama LLM secondary URL (GCP-B Secondary)",
|
||
)
|
||
# 2026-05-03 ogt: Local HDD 最後防線（原 2026-04-08 M1 Pro 主機降為第三層）
|
||
OLLAMA_FALLBACK_URL: str = Field(
|
||
default="http://192.168.0.111:11434", # 2026-05-03 ogt: M1 Pro Local HDD 最後防線
|
||
description="Ollama local fallback URL (Local HDD, 最後防線)",
|
||
)
|
||
# 2026-04-27 Wave8-X2 by Claude — vuln #1 URL endpoint poisoning 修復
|
||
# 攻擊情境：攻擊者改 ConfigMap OLLAMA_FALLBACK_URL=http://attacker.com:11434
|
||
# → ai_router 盲信 → C&C 通道。修法：啟動時拒絕非私網/loopback 的外部 URL。
|
||
# 2026-05-03 ogt: 擴充 validator 覆蓋 OLLAMA_SECONDARY_URL；新增 GCP IP 白名單（ADR-110）
|
||
@field_validator("OLLAMA_URL", "OLLAMA_SECONDARY_URL", "OLLAMA_FALLBACK_URL")
|
||
@classmethod
|
||
def _validate_ollama_url(cls, v: str) -> str:
|
||
"""
|
||
Ollama URL 安全校驗：拒絕非 private/loopback IP 或非已知服務名稱的 URL。
|
||
|
||
允許：
|
||
- 空字串（未設定）
|
||
- 已知 Kubernetes Service hostname 白名單
|
||
- 私網 IP（RFC 1918）或 loopback（127.x.x.x）
|
||
- GCP 核准公網 IP 白名單（ADR-110 GCP-A / GCP-B）
|
||
|
||
拒絕：
|
||
- 非白名單公網 IP（8.8.8.8）
|
||
- 外部域名（attacker.com）
|
||
"""
|
||
if not v:
|
||
return v
|
||
import ipaddress
|
||
from urllib.parse import urlparse
|
||
|
||
try:
|
||
host = urlparse(v).hostname or ""
|
||
except Exception as exc:
|
||
raise ValueError(f"OLLAMA URL 格式無效：{v!r}，錯誤：{exc}") from exc
|
||
if not host:
|
||
raise ValueError(f"OLLAMA URL 缺少 hostname：{v!r}")
|
||
|
||
# Kubernetes Service hostname 白名單（K8s DNS + 開發別名）
|
||
_ALLOWED_HOSTNAMES = {
|
||
"localhost",
|
||
"ollama",
|
||
"ollama-svc",
|
||
"ollama-fallback-svc",
|
||
"ollama-111",
|
||
"ollama-188",
|
||
}
|
||
if host in _ALLOWED_HOSTNAMES:
|
||
return v
|
||
|
||
# GCP 核准公網 IP 白名單（ADR-110，2026-05-03 ogt）
|
||
# GCP-A: 34.143.170.20（SSD, 9x 載速）
|
||
# GCP-B: 34.21.145.224（SSD, 9x 載速）
|
||
_ALLOWED_PUBLIC_IPS: frozenset[str] = frozenset({
|
||
"34.143.170.20", # GCP-A Ollama Primary (SSD)
|
||
"34.21.145.224", # GCP-B Ollama Secondary (SSD)
|
||
})
|
||
if host in _ALLOWED_PUBLIC_IPS:
|
||
return v
|
||
|
||
# 否則必須是 private/loopback IP
|
||
try:
|
||
ip = ipaddress.ip_address(host)
|
||
except ValueError:
|
||
# hostname 不是 IP 也不在白名單 → 拒絕
|
||
raise ValueError(
|
||
f"OLLAMA URL host 不允許的外部域名：{host!r}（完整 URL：{v!r}）"
|
||
"，必須使用私網 IP 或已知 K8s Service hostname"
|
||
) from None
|
||
if not (ip.is_private or ip.is_loopback):
|
||
raise ValueError(
|
||
f"OLLAMA URL 必須是私網/loopback IP、已知 K8s SVC 或 GCP 白名單 IP，"
|
||
f"收到公網 IP {host!r}（{v!r}），可能是端點中毒攻擊"
|
||
)
|
||
return v
|
||
|
||
# 2026-05-05 Codex: health inference must stay on alert-fast model; qwen2.5
|
||
# keeps reloading a 7B model on CPU-only GCP and slows incident fallback.
|
||
OLLAMA_HEALTH_CHECK_MODEL: str = Field(
|
||
default="gemma3:4b",
|
||
description="OllamaHealthMonitor 推理測試使用模型（P1.1）",
|
||
)
|
||
OLLAMA_EMBEDDING_MODEL: str = Field(
|
||
default="bge-m3:latest",
|
||
description="Ollama embedding model. ADR-110 migrated embeddings from nomic-embed-text to bge-m3.",
|
||
)
|
||
# 2026-04-12 ogt: 心跳必須確認載入的 Ollama 模型清單
|
||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級，更新必要模型清單（nomic→bge-m3 + 新增 qwen3:14b + hermes3）
|
||
OLLAMA_REQUIRED_MODELS: list[str] = Field(
|
||
default=["bge-m3:latest", "qwen2.5:7b-instruct", "qwen3:14b", "deepseek-r1:14b", "hermes3:latest"],
|
||
description="HeartbeatReportService 探測必要模型是否載入",
|
||
)
|
||
# 2026-04-25 critic-fix Part2 H7 by Claude Engineer-C2
|
||
# Gemini 帳單熔斷：每日呼叫上限，超過改走 188+Nemotron
|
||
# 超過上限後寫 Redis key ollama:gemini_daily_count:{date}，TTL 86400s
|
||
GEMINI_DAILY_QUOTA: int = Field(
|
||
default=1000,
|
||
description="每日 Gemini 呼叫上限，超過切到 188+Nemotron（P1.1 帳單熔斷）",
|
||
)
|
||
# Deprecated: use OPENCLAW_URL instead
|
||
CLAWBOT_URL: str = Field(
|
||
default="http://192.168.0.188:8088", # 🔧 修正: OpenClaw 實際 port 是 8088
|
||
description="[Deprecated] Legacy OpenClaw URL - use OPENCLAW_URL",
|
||
)
|
||
KALI_SCANNER_URL: str = Field(
|
||
default="http://192.168.0.112:8080",
|
||
description="Kali security scanner URL",
|
||
)
|
||
SIGNOZ_URL: str = Field(
|
||
default="http://192.168.0.188:3301",
|
||
description="SigNoz observability URL",
|
||
)
|
||
CLICKHOUSE_URL: str = Field(
|
||
default="http://192.168.0.188:8123",
|
||
description="ClickHouse HTTP API URL (SignOz backend, direct query)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Sentry Self-Hosted (Phase 10: Error Tracking + AI Analysis)
|
||
# 端點: http://192.168.0.110:9000 (DevOps 金庫)
|
||
# ==========================================================================
|
||
SENTRY_SELF_HOSTED_URL: str = Field(
|
||
default="http://192.168.0.110:9000",
|
||
description="Sentry Self-Hosted API URL",
|
||
)
|
||
SENTRY_ORG: str = Field(
|
||
default="sentry",
|
||
description="Sentry organization slug",
|
||
)
|
||
SENTRY_PROJECT: str = Field(
|
||
default="awoooi-api",
|
||
description="Sentry project slug",
|
||
)
|
||
SENTRY_AUTH_TOKEN: str = Field(
|
||
default="",
|
||
description="Sentry Auth Token for API access (from K8s Secret)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# OpenTelemetry (可觀測性鐵律)
|
||
# 四主機架構強制校驗: OTEL 必須指向 192.168.0.188（AWOOOI 主站）
|
||
# ADR-121 + P0-08 修正：改為 config-driven，允許 EwoooC 指向不同 host
|
||
# ==========================================================================
|
||
OTEL_ENABLED: bool = Field(
|
||
default=True,
|
||
description="Enable OpenTelemetry tracing (disable in MOCK_MODE)",
|
||
)
|
||
OTEL_EXPORTER_OTLP_ENDPOINT: str = Field(
|
||
default="192.168.0.188:24317",
|
||
description="SigNoz OTLP gRPC endpoint (Host port 24317 -> Container 4317) - NO http:// prefix for gRPC",
|
||
)
|
||
OTEL_ALLOWED_ENDPOINTS: list[str] = Field(
|
||
default=["192.168.0.188"],
|
||
description="允許的 OTEL endpoint host 列表（逗號分隔可用 env 覆寫）。EwoooC 可設自己的 SigNoz host。",
|
||
)
|
||
OTEL_FORBIDDEN_ENDPOINTS: list[str] = Field(
|
||
default=["192.168.0.110", "192.168.0.112", "192.168.0.120", "192.168.0.121"],
|
||
description="明確禁止的 OTEL endpoint host 列表（不允許誤指向非 SigNoz 主機）",
|
||
)
|
||
AWOOOI_K8S_NAMESPACE: str = Field(
|
||
default="awoooi-prod",
|
||
description="K8s namespace（P0-13 修正：不再硬碼，EwoooC/Tsenyang 可設自己的 namespace）",
|
||
)
|
||
OTEL_SERVICE_NAME: str = Field(
|
||
default="awoooi-api",
|
||
description="Service name for tracing",
|
||
)
|
||
OTEL_TRACES_SAMPLER_ARG: float = Field(
|
||
default=1.0,
|
||
description="Trace sampling rate (1.0 = 100%)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Langfuse LLMOps (Phase 15.1)
|
||
# LLM 呼叫追蹤、成本監控、Prompt 版本管理
|
||
# 端點: http://192.168.0.110:3100 (DevOps 金庫)
|
||
# ==========================================================================
|
||
LANGFUSE_ENABLED: bool = Field(
|
||
default=True,
|
||
description="Enable Langfuse LLM observability",
|
||
)
|
||
LANGFUSE_URL: str = Field(
|
||
default="http://192.168.0.110:3100",
|
||
description="Langfuse self-hosted URL",
|
||
)
|
||
LANGFUSE_PUBLIC_KEY: str = Field(
|
||
default="",
|
||
description="Langfuse public key (from K8s Secret)",
|
||
)
|
||
LANGFUSE_SECRET_KEY: str = Field(
|
||
default="",
|
||
description="Langfuse secret key (from K8s Secret)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# AI Fallback Strategy (ADR-006 v1.3 + ADR-036)
|
||
# Order: Ollama (local) -> NVIDIA NIM -> Gemini (cloud) -> Claude (cloud)
|
||
# Tool Calling: Nemotron (專用) -> Gemini -> Claude
|
||
# 2026-04-28 ogt + Claude Opus 4.7: 補 nvidia 對齊 ConfigMap (k8s/awoooi-prod/04-configmap.yaml)
|
||
# 之前 default 缺 nvidia 與 ConfigMap drift，feedback_ai_fallback_order.md 鐵律
|
||
# ==========================================================================
|
||
AI_FALLBACK_ORDER: list[str] = Field(
|
||
default=["ollama", "nvidia", "gemini", "claude"],
|
||
description="AI provider fallback order",
|
||
)
|
||
GEMINI_API_KEY: str = Field(default="", description="Google Gemini API key")
|
||
CLAUDE_API_KEY: str = Field(default="", description="Anthropic Claude API key")
|
||
LOCAL_CODE_REVIEW_ALLOW_GEMINI_FALLBACK: bool = Field(
|
||
default=False,
|
||
description=(
|
||
"Allow LocalCodeReviewService to fall back to Gemini when the "
|
||
"local Ollama code-review lane fails. Default false to avoid "
|
||
"unexpected cloud spend from Gitea push/PR alerts."
|
||
),
|
||
)
|
||
ALERT_AI_ALLOW_CLOUD_FALLBACK: bool = Field(
|
||
default=True,
|
||
description=(
|
||
"Allow incident/alert OpenClaw analysis to use cloud fallback "
|
||
"providers after the GCP-A/GCP-B/111 Ollama lane is exhausted. "
|
||
"Default true so Gemini can act as the final backup, after the "
|
||
"ordered Ollama lane is exhausted."
|
||
),
|
||
)
|
||
ALERT_AI_ENFORCE_OLLAMA_FIRST: bool = Field(
|
||
default=True,
|
||
description=(
|
||
"Force incident/alert OpenClaw analysis to try GCP-A, then GCP-B, "
|
||
"then local 111 before cloud backup providers such as Gemini."
|
||
),
|
||
)
|
||
ALERT_OLLAMA_MODEL: str = Field(
|
||
default="qwen3:14b",
|
||
description=(
|
||
"Ollama model used for incident/alert deep diagnosis. Alert cards "
|
||
"may wait for this model; Gemini remains a backup after GCP-A, "
|
||
"GCP-B, and 111 fail."
|
||
),
|
||
)
|
||
INCIDENT_LLM_TIMEOUT_SECONDS: int = Field(
|
||
default=360,
|
||
description=(
|
||
"Outer timeout for incident OpenClaw proposal generation. This must "
|
||
"be long enough for the GCP-A/GCP-B/111 Ollama lane to complete "
|
||
"before Gemini backup is considered useful."
|
||
),
|
||
)
|
||
# 2026-03-29 ogt: ADR-036 Nemotron Tool Calling 整合
|
||
NVIDIA_API_KEY: str = Field(
|
||
default="",
|
||
description="NVIDIA NIM API key for Nemotron Tool Calling (ADR-036)",
|
||
)
|
||
# 2026-04-09 Claude Sonnet 4.6: Ollama Tool Calling — 替代 NVIDIA 雲端，本機推理
|
||
USE_OLLAMA_TOOL_CALLING: bool = Field(
|
||
default=True,
|
||
description="使用 Ollama 本機做 Tool Calling，取代 NVIDIA NIM 雲端 (44s→5s)",
|
||
)
|
||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級，改 hermes3:latest（工具調用能力優於 llama3.1:8b）
|
||
OLLAMA_TOOL_MODEL: str = Field(
|
||
default="hermes3:latest",
|
||
description="Ollama Tool Calling 模型 (支援 function calling 格式)",
|
||
)
|
||
|
||
@field_validator("AI_FALLBACK_ORDER", mode="before")
|
||
@classmethod
|
||
def parse_ai_fallback(cls, v: str | list[str]) -> list[str]:
|
||
"""
|
||
解析 AI_FALLBACK_ORDER，支援三種格式:
|
||
1. JSON: '["gemini","ollama","claude"]'
|
||
2. CSV: 'gemini,ollama,claude'
|
||
3. List: ["gemini", "ollama", "claude"]
|
||
|
||
2026-03-27 修復: ConfigMap 用 JSON 格式，原本只支援 CSV
|
||
"""
|
||
import json
|
||
|
||
if isinstance(v, str):
|
||
v = v.strip()
|
||
# 嘗試 JSON 解析 (ConfigMap 格式)
|
||
if v.startswith("["):
|
||
try:
|
||
parsed = json.loads(v)
|
||
return [p.strip().lower() for p in parsed]
|
||
except json.JSONDecodeError:
|
||
pass # 降級到 CSV 解析
|
||
# CSV 格式
|
||
return [provider.strip().lower() for provider in v.split(",")]
|
||
return [p.lower() for p in v]
|
||
|
||
# ==========================================================================
|
||
# Kubernetes / K3s (CTO-201)
|
||
# ==========================================================================
|
||
KUBECONFIG_PATH: str = Field(
|
||
default="k3s-prod.yaml",
|
||
description="Path to kubeconfig file for K3s cluster (192.168.0.120)",
|
||
)
|
||
K8S_NAMESPACE_DEFAULT: str = Field(
|
||
default="default",
|
||
description="Default Kubernetes namespace for operations",
|
||
)
|
||
K8S_OPERATION_TIMEOUT: int = Field(
|
||
default=30,
|
||
description="Timeout for K8s operations in seconds",
|
||
)
|
||
K8S_API_KEY: str = Field(
|
||
default="",
|
||
description="API Key for K8s admin endpoints (X-K8s-Api-Key header)",
|
||
)
|
||
AWOOOP_OPERATOR_API_KEY: str = Field(
|
||
default="",
|
||
description=(
|
||
"API key for AwoooP operator mutation endpoints "
|
||
"(X-AwoooP-Operator-Key header)"
|
||
),
|
||
)
|
||
ENABLE_AWOOOP_ANSIBLE_CHECK_MODE_WORKER: bool = Field(
|
||
default=False,
|
||
description=(
|
||
"True=consume ansible_candidate_matched AOL rows and run "
|
||
"ansible-playbook --check --diff only. Apply remains disabled."
|
||
),
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_INTERVAL_SECONDS: int = Field(
|
||
default=300,
|
||
ge=60,
|
||
description="AwoooP Ansible check-mode worker polling interval.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_BATCH_LIMIT: int = Field(
|
||
default=1,
|
||
ge=1,
|
||
le=5,
|
||
description="Maximum Ansible check-mode candidates claimed per worker tick.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_TIMEOUT_SECONDS: int = Field(
|
||
default=180,
|
||
ge=30,
|
||
le=600,
|
||
description="Timeout for one ansible-playbook --check --diff execution.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_STARTUP_SLEEP_SECONDS: int = Field(
|
||
default=120,
|
||
ge=0,
|
||
le=900,
|
||
description="Delay before the check-mode worker first tick after API startup.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_TRANSPORT_PROFILE: str = Field(
|
||
default="ssh_mcp",
|
||
description=(
|
||
"SSH transport profile used by Ansible check-mode. Production uses "
|
||
"the existing ssh-mcp key so repair-bot forced-command remains reserved "
|
||
"for whitelist repairs."
|
||
),
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_SSH_KEY_PATH: str = Field(
|
||
default="/run/secrets/ssh_mcp_key",
|
||
description="Private key path for Ansible check-mode SSH transport.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_KNOWN_HOSTS_PATH: str = Field(
|
||
default="/etc/ssh-mcp/known_hosts",
|
||
description="known_hosts path for Ansible check-mode SSH transport.",
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_CANDIDATE_MAX_AGE_HOURS: int = Field(
|
||
default=24,
|
||
ge=1,
|
||
le=168,
|
||
description=(
|
||
"Only recent Ansible candidate audit rows are eligible for automatic "
|
||
"check-mode claims; older backlog remains visible but is not drained as noise."
|
||
),
|
||
)
|
||
AWOOOP_ANSIBLE_CHECK_MODE_TRANSPORT_COOLDOWN_SECONDS: int = Field(
|
||
default=21_600,
|
||
ge=300,
|
||
le=86_400,
|
||
description=(
|
||
"Cooldown after transport-level check-mode blockers such as "
|
||
"forced-command repair SSH denial."
|
||
),
|
||
)
|
||
|
||
# ==========================================================================
|
||
# 統帥鐵律：禁止 SQLite (AWOOOI 憲法)
|
||
# ==========================================================================
|
||
# ❌ 已移除 SQLITE_DATABASE_URL - 違反 AWOOOI 憲法
|
||
# 所有持久化必須使用 PostgreSQL (DATABASE_URL)
|
||
# 審計日誌請使用 PostgreSQL audit_logs 表
|
||
# ==========================================================================
|
||
|
||
# ==========================================================================
|
||
# Cache TTL (seconds)
|
||
# ==========================================================================
|
||
CACHE_TTL_DASHBOARD: int = Field(default=300, description="Dashboard cache TTL (5 min)")
|
||
CACHE_TTL_HOST_STATUS: int = Field(default=30, description="Host status cache TTL (30 sec)")
|
||
CACHE_TTL_AI_RESPONSE: int = Field(default=3600, description="AI response cache TTL (1 hour)")
|
||
|
||
# ==========================================================================
|
||
# Health Check Timeouts (seconds)
|
||
# ==========================================================================
|
||
HEALTH_CHECK_TIMEOUT: float = Field(default=5.0, description="Health check timeout")
|
||
|
||
# ==========================================================================
|
||
# Phase 5: OpenClaw AI Engine (正名自 OpenClaw)
|
||
# Synced from models.json - Ollama First Strategy
|
||
# ==========================================================================
|
||
OPENCLAW_URL: str = Field(
|
||
default="http://192.168.0.188:8088", # 🔧 修正: OpenClaw 實際 port 是 8088
|
||
description="OpenClaw AI Agent service URL",
|
||
)
|
||
# 2026-05-04 ogt + Claude Sonnet 4.6: ADR-110 GCP 升級，改 qwen3:14b（GCP-A SSD 算力，RCA 推理更強）
|
||
OPENCLAW_DEFAULT_MODEL: str = Field(
|
||
default="qwen3:14b",
|
||
description="Default Ollama model for RCA analysis",
|
||
)
|
||
OPENCLAW_TIMEOUT: int = Field(
|
||
default=30, # 2026-04-14 Claude Sonnet 4.6: 從 120s 改 30s，配合 ADR-052 GAP-B4
|
||
# 25s LLM hard timeout + 5s buffer。原 120s 違反 defense-in-depth 設計，
|
||
# 導致 Ollama 過載時 thread 飢餓 120s 才降級 fallback。
|
||
description="Timeout for OpenClaw AI calls (seconds, aligned with GAP-B4 25s)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Phase 5: Telegram Gateway (繼承自 AIOPS)
|
||
# CISO 要求: Token 必須存放於 K8s Secret，此處為開發預設
|
||
# ==========================================================================
|
||
OPENCLAW_TG_BOT_TOKEN: str = Field(
|
||
default="",
|
||
description="Telegram Bot Token (from K8s Secret in prod)",
|
||
)
|
||
OPENCLAW_TG_CHAT_ID: str = Field(
|
||
default="",
|
||
description="Telegram Chat ID for notifications",
|
||
)
|
||
# 使用 str 避免 pydantic-settings 自動 JSON 解析
|
||
# Pydantic v2 禁止底線開頭的 Field 名稱
|
||
OPENCLAW_TG_USER_WHITELIST: str = Field(
|
||
default="",
|
||
description="Telegram user IDs allowed to sign approvals (comma-separated or JSON array)",
|
||
)
|
||
# 2026-03-23 架構修正 (遵循 C-Suite 決議)
|
||
# 鐵律: .188 為唯一大腦，禁止腦分裂
|
||
# OpenClaw (192.168.0.188) = 唯一 Telegram Gateway
|
||
# AWOOOI API (K8s) = Web API + Sensor，不做 Polling
|
||
TELEGRAM_ENABLE_POLLING: bool = Field(
|
||
default=False,
|
||
description="Telegram Polling (False: OpenClaw handles it; True: only if OpenClaw unavailable)",
|
||
)
|
||
# 2026-04-03 ogt: SRE 戰情室群組三頭政治 (Triumvirate) — ADR-053
|
||
OPENCLAW_BOT_TOKEN: str = Field(
|
||
default="",
|
||
description="@OpenClawAwoooI_Bot Token — 群組內代表 OpenClaw AI 發言",
|
||
)
|
||
NEMOTRON_BOT_TOKEN: str = Field(
|
||
default="",
|
||
description="@NemoTronAwoooI_Bot Token — 群組內代表 NemoClaw AI 發言",
|
||
)
|
||
SRE_GROUP_CHAT_ID: str = Field(
|
||
default="",
|
||
description="AwoooI SRE 戰情室群組 Chat ID",
|
||
)
|
||
SSH_MCP_HOST_USERS: str = Field(
|
||
default="192.168.0.188=ollama",
|
||
description="Per-host SSH MCP username overrides, format host=user,host=user",
|
||
)
|
||
# ADR-093 灰階切流：True 時由 notification_matrix 控制所有路由
|
||
# False（預設）時維持舊行為（TYPE-3/4/4D/8M 僅 DM）
|
||
TG_GROUP_CUTOVER: bool = Field(
|
||
default=False,
|
||
description="ADR-093: True 時啟用 notification_matrix 路由矩陣，取代 telegram_gateway 硬碼",
|
||
)
|
||
# ADR-095 2026-04-25 ogt + Claude Sonnet 4.6: 12-Agent ConsensusEngine
|
||
ENABLE_12AGENT_CONSENSUS: bool = Field(
|
||
default=False,
|
||
description="ADR-095: 啟用 12-Agent ConsensusEngine weights（預設關閉）",
|
||
)
|
||
# ==========================================================================
|
||
# ADR-091 Task T1: AI 自學規則雙寫 alert_rule_catalog (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# True=auto_generate_rule() 成功後同步寫入 DB source='ai_generated'
|
||
# False=回滾開關，只寫 YAML，不寫 DB
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_AI_RULE_CATALOG_WRITE=false
|
||
# ==========================================================================
|
||
ENABLE_AI_RULE_CATALOG_WRITE: bool = Field(
|
||
default=True,
|
||
description="ADR-091 T1: True=AI 自學規則雙寫 alert_rule_catalog DB, False=僅 YAML（回滾用）",
|
||
)
|
||
# ==========================================================================
|
||
# 2026-05-04 ogt + Claude Sonnet 4.6: Drift 自動採納開關
|
||
# 根因修復後啟用（report.interpretation in-memory 未更新 bug 已修）
|
||
# 回滾指令: kubectl set env deployment/awoooi-api DRIFT_AUTO_ADOPT_ENABLED=false
|
||
# ==========================================================================
|
||
DRIFT_AUTO_ADOPT_ENABLED: bool = Field(
|
||
default=True,
|
||
description="2026-05-04: True=啟用 drift auto_adopt_if_safe 自動採納低風險漂移, False=回滾停用",
|
||
)
|
||
# ==========================================================================
|
||
# 2026-05-04 ogt + Claude Sonnet 4.6: Coverage Gap → AI 規則自動生成
|
||
# evaluate_once() 末段：對 auto_alerting=red 的 asset 自動生成 alert_rule_catalog 記錄
|
||
# 回滾指令: kubectl set env deployment/awoooi-api COVERAGE_AUTO_RULE_ENABLED=false
|
||
# ==========================================================================
|
||
COVERAGE_AUTO_RULE_ENABLED: bool = Field(
|
||
default=True,
|
||
description="2026-05-04: True=coverage 缺口自動生成 alert_rule_catalog（source='ai_generated'，review_status='pending_review'）, False=停用",
|
||
)
|
||
# 2026-04-27 P3.1-T2-PathA by Claude — DiagAggregator 信號分類層補 PDI
|
||
# 路徑 A 已啟用：DA 只取 PDI 已收集的 raw 資料做業務邏輯分類（OOMKilled/CrashLoop 等），
|
||
# 不重複呼叫 K8s/SignOz API（純邏輯分類，不打外部服務）。
|
||
# 啟用：kubectl set env deployment/awoooi-api ENABLE_DIAGNOSIS_AGGREGATOR=true
|
||
ENABLE_DIAGNOSIS_AGGREGATOR: bool = Field(
|
||
default=True,
|
||
description="P3.1-T2-PathA: 啟用 DiagnosisAggregator 信號分類層補 PDI（路徑 A：不重複收集，只分類已有 raw 資料）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# W2 PR-V1: SelfHealingValidator Feature Flag (2026-04-28 ogt + Claude Sonnet 4.6)
|
||
# 飛輪斷鏈 C6 修復 — 驗證層串接自愈品質評估
|
||
# 回滾指令: kubectl set env deployment/awoooi-api ENABLE_SELF_HEALING_VALIDATOR=false
|
||
# ==========================================================================
|
||
ENABLE_SELF_HEALING_VALIDATOR: bool = Field(
|
||
default=False,
|
||
description="W2 PR-V1: True=PostExecutionVerifier 執行後評估自愈品質分數（score<0.5發Telegram警示）, False=跳過（回滾用）",
|
||
)
|
||
|
||
def get_tg_user_whitelist(self) -> list[int]:
|
||
"""Parse comma-separated or JSON array user IDs to list[int]"""
|
||
raw = self.OPENCLAW_TG_USER_WHITELIST
|
||
# 已是 list（測試 monkeypatch 或程式碼直接傳入）
|
||
if isinstance(raw, list):
|
||
return [int(uid) for uid in raw]
|
||
if not raw or not raw.strip():
|
||
return []
|
||
# Handle JSON array format or comma-separated
|
||
if raw.startswith("["):
|
||
import json
|
||
return json.loads(raw)
|
||
return [int(uid.strip()) for uid in raw.split(",")]
|
||
|
||
# ==========================================================================
|
||
# Phase 5: Webhook Security (CISO 要求)
|
||
# HMAC-SHA256 簽章驗證 + Nonce 防重放
|
||
# ==========================================================================
|
||
WEBHOOK_HMAC_SECRET: str = Field(
|
||
default="",
|
||
description="HMAC secret for webhook signature verification",
|
||
)
|
||
# ADR-116 P0-05: Callback Nonce 防偽造 HMAC Secret
|
||
# 2026-05-04 Claude Sonnet 4.6 (ADR-116): 附加至 callback nonce 末尾的 HMAC-SHA256[:16]
|
||
# 空字串 → 過渡期跳過驗證並記錄 warning
|
||
CALLBACK_HMAC_SECRET: str = Field(
|
||
default="",
|
||
description="ADR-116: HMAC secret for callback nonce anti-forgery (HMAC-SHA256 appended to nonce)",
|
||
)
|
||
# 2026-04-24 Claude Sonnet 4.6 (ADR-094): Telegram Webhook Secret Token
|
||
# 與 setWebhook API 呼叫時的 secret_token 相同；空字串 → dev 環境跳過驗證
|
||
TELEGRAM_WEBHOOK_SECRET: str = Field(
|
||
default="",
|
||
description="Telegram Webhook Secret Token（setWebhook 設定的同一值）",
|
||
)
|
||
# 2026-04-24 Claude Sonnet 4.6 (ADR-095 WS4): Hermes NL 自然語言閘道
|
||
# false=不啟用（預設），true=啟用 @mention 問答（需 ANTHROPIC_API_KEY）
|
||
HERMES_NL_ENABLED: bool = Field(
|
||
default=False,
|
||
description="Hermes NL 對話功能開關（ADR-095）",
|
||
)
|
||
TELEGRAM_BOT_USERNAME: str = Field(
|
||
default="tsenyangbot",
|
||
description="Telegram Bot username（不含 @），用於 @mention 識別",
|
||
)
|
||
WEBHOOK_NONCE_TTL: int = Field(
|
||
default=300,
|
||
description="Nonce TTL in seconds for replay attack prevention",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Phase 5: Shadow Mode (物理繳械)
|
||
# 統帥戰略 C: 接入真實告警，但物理閹割 AI 破壞力
|
||
# ==========================================================================
|
||
SHADOW_MODE_ENABLED: bool = Field(
|
||
default=True,
|
||
description="Shadow Mode: Force dry-run for all K8s operations (safe by default)",
|
||
)
|
||
SHADOW_MODE_LOG_ONLY: bool = Field(
|
||
default=True,
|
||
description="Shadow Mode: Only log operations without any K8s API calls",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Phase 5: Context Gatherer (首席架構師要求)
|
||
# 日誌清洗: 僅保留 ERROR/FATAL/CRITICAL
|
||
# ==========================================================================
|
||
CONTEXT_LOG_LEVELS: list[str] = Field(
|
||
default=["ERROR", "FATAL", "CRITICAL", "WARN", "WARNING"],
|
||
description="Log levels to include in AI context (ERROR Only principle)",
|
||
)
|
||
CONTEXT_MAX_LINES: int = Field(
|
||
default=100,
|
||
description="Maximum log lines to include in context",
|
||
)
|
||
|
||
@field_validator("CONTEXT_LOG_LEVELS", mode="before")
|
||
@classmethod
|
||
def parse_log_levels(cls, v: str | list[str]) -> list[str]:
|
||
if isinstance(v, str):
|
||
return [level.strip().upper() for level in v.split(",")]
|
||
return [level.upper() for level in v]
|
||
|
||
# ==========================================================================
|
||
# Notification Plugins (leWOOOgo Output)
|
||
# Fail-Fast: HttpUrl 驗證確保啟動時攔截設定錯誤
|
||
# ==========================================================================
|
||
DISCORD_WEBHOOK_URL: str = Field(
|
||
default="",
|
||
description="Discord webhook URL for sending execution reports",
|
||
)
|
||
SLACK_WEBHOOK_URL: str = Field(
|
||
default="",
|
||
description="Slack webhook URL for sending execution reports",
|
||
)
|
||
NOTIFICATION_ENABLED: bool = Field(
|
||
default=True,
|
||
description="Enable post-execution notifications",
|
||
)
|
||
|
||
@field_validator("DISCORD_WEBHOOK_URL", "SLACK_WEBHOOK_URL", mode="before")
|
||
@classmethod
|
||
def validate_webhook_url(cls, v: str | None) -> str:
|
||
"""
|
||
Fail-Fast Webhook URL 驗證
|
||
|
||
- 空字串 = 停用 (合法)
|
||
- 非空字串必須是合法 HttpUrl (否則啟動失敗)
|
||
"""
|
||
if not v or v.strip() == "":
|
||
return ""
|
||
# Validate as HttpUrl (raises ValueError if invalid)
|
||
HttpUrl(v)
|
||
return v
|
||
|
||
# ==========================================================================
|
||
# Phase 23 (ADR-048): Sentry Webhook → OpenClaw AI Triage
|
||
# Sentry Issue Alert Webhook 簽章驗證 (sentry-hook-signature header)
|
||
# ==========================================================================
|
||
SENTRY_WEBHOOK_SECRET: str = Field(
|
||
default="",
|
||
description="Sentry Webhook secret for HMAC-SHA256 signature verification",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Phase 13.1: GitHub Webhook → OpenClaw 整合
|
||
# Gitea PR/Push 事件自動觸發 AI 代碼審查 (ADR-059: GitHub → Gitea 遷移)
|
||
# ==========================================================================
|
||
GITEA_WEBHOOK_SECRET: str = Field(
|
||
default="",
|
||
description="Gitea Webhook secret for HMAC-SHA256 signature verification (X-Gitea-Signature)",
|
||
)
|
||
GITEA_ALLOWED_REPOS: str = Field(
|
||
default="wooo/awoooi",
|
||
description="Comma-separated list of allowed Gitea repositories (e.g., 'wooo/awoooi')",
|
||
)
|
||
|
||
def get_gitea_allowed_repos(self) -> list[str]:
|
||
"""Parse comma-separated allowed repos to list"""
|
||
# 2026-04-05 Claude Code (ADR-059): GitHub → Gitea webhook 遷移
|
||
raw = self.GITEA_ALLOWED_REPOS
|
||
if not raw or not raw.strip():
|
||
return []
|
||
return [repo.strip() for repo in raw.split(",") if repo.strip()]
|
||
|
||
# ==========================================================================
|
||
# MCP Phase 2b: Prometheus MCP Server (ADR-071, 2026-04-11 Claude Sonnet 4.6)
|
||
# ==========================================================================
|
||
# 2026-04-29 ogt + Claude Opus 4.7: drift fix — Prometheus 實際在 110
|
||
# ConfigMap 04-configmap.yaml 也是 110；governance_agent / SLO check 連 188 會 timeout
|
||
# 此 drift 是 SPF-4 (governance_agent silently fail) 根因之一
|
||
PROMETHEUS_URL: str = Field(
|
||
default="http://192.168.0.110:9090",
|
||
description="Prometheus server URL (DevOps 金庫主機)",
|
||
)
|
||
PROMETHEUS_MCP_ENABLED: bool = Field(
|
||
default=True,
|
||
description="啟用 Prometheus MCP Provider",
|
||
)
|
||
|
||
# MCP Phase 2a: SSH MCP Server (ADR-071, 2026-04-11 Claude Sonnet 4.6)
|
||
# ==========================================================================
|
||
SSH_MCP_ENABLED: bool = Field(
|
||
default=False,
|
||
description="啟用 SSH MCP Provider（需 K8s Secret ssh-mcp-key 掛載）",
|
||
)
|
||
SSH_MCP_ALLOWED_HOSTS: str = Field(
|
||
default="192.168.0.188,192.168.0.110,192.168.0.111",
|
||
description="允許 SSH 的主機 IP 清單（逗號分隔）",
|
||
)
|
||
|
||
# MCP Phase 3: ArgoCD MCP Server (2026-04-11 Claude Sonnet 4.6)
|
||
# ==========================================================================
|
||
# 2026-04-29 ogt + Claude Opus 4.7: drift fix — ArgoCD 實際在 121，125 是舊位置
|
||
# ConfigMap 04-configmap.yaml 已寫 121；T0 G3 drift 已知，此次正式對齊
|
||
ARGOCD_URL: str = Field(
|
||
default="https://192.168.0.121:30443",
|
||
description="ArgoCD API Server URL（K3s NodePort HTTPS）",
|
||
)
|
||
ARGOCD_API_TOKEN: str = Field(
|
||
default="",
|
||
description="ArgoCD API Token（從 K8s Secret 取得）",
|
||
)
|
||
ARGOCD_MCP_ENABLED: bool = Field(
|
||
default=True,
|
||
description="啟用 ArgoCD MCP Provider（需 ARGOCD_API_TOKEN）",
|
||
)
|
||
|
||
# MCP Phase 3: Sentry MCP Server (2026-04-11 Claude Sonnet 4.6)
|
||
# ==========================================================================
|
||
SENTRY_MCP_ENABLED: bool = Field(
|
||
default=True,
|
||
description="啟用 Sentry MCP Provider（需 SENTRY_AUTH_TOKEN）",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Phase 13.2: Grafana MCP Tool (#83)
|
||
# ==========================================================================
|
||
GRAFANA_URL: str = Field(
|
||
default="http://192.168.0.188:3000",
|
||
description="Grafana server URL",
|
||
)
|
||
GRAFANA_API_KEY: str = Field(
|
||
default="",
|
||
description="Grafana API key for authentication (Bearer token)",
|
||
)
|
||
|
||
# ==========================================================================
|
||
# Computed Properties
|
||
# ==========================================================================
|
||
@property
|
||
def is_production(self) -> bool:
|
||
"""Check if running in production"""
|
||
return self.ENVIRONMENT == "prod"
|
||
|
||
@property
|
||
def four_hosts(self) -> dict[str, str]:
|
||
"""Four host architecture reference"""
|
||
return {
|
||
"devops": "192.168.0.110", # Harbor, GH Runner
|
||
"security": "192.168.0.112", # Kali Scanner
|
||
"k3s_master": "192.168.0.120", # K3s Master
|
||
"ai_web": "192.168.0.188", # Nginx, Postgres, Redis, SignOz
|
||
}
|
||
|
||
|
||
@lru_cache
|
||
def get_settings() -> Settings:
|
||
"""Get cached settings instance"""
|
||
return Settings()
|
||
|
||
|
||
# Singleton for direct import
|
||
settings = get_settings()
|