fix(aiops): route backup decisions through ssh

apps/api/src/services/callback_action_spec.yaml

@@ -22,7 +22,7 @@
 #     description: <說明>
 
 version: "1.0"
-last_updated: "2026-04-14"
+last_updated: "2026-05-01"
 
 actions:
   # ==========================================================================
@@ -188,6 +188,53 @@ actions:
     timeout_sec: 1
     description: "返回飛輪儀表板 URL"
 
+  backup_check_host_disk:
+    label: "查主機磁碟"
+    emoji: "💾"
+    risk: low
+    callback_format: info
+    category: backup_failure
+    mcp:
+      provider: ssh
+      tool: ssh_get_disk_usage
+      params:
+        host: "{labels.instance}"
+    reply_format: code
+    timeout_sec: 8
+    description: "備份失敗時檢查主機磁碟容量與 Docker 目錄大小"
+
+  backup_check_jobs:
+    label: "查備份 Job"
+    emoji: "📦"
+    risk: low
+    callback_format: info
+    category: backup_failure
+    mcp:
+      provider: k8s
+      tool: kubectl_get
+      params:
+        namespace: "awoooi-prod"
+        resource: "jobs"
+    reply_format: truncated
+    timeout_sec: 8
+    description: "列出 awoooi-prod 內的備份相關 Job 狀態"
+
+  backup_check_velero:
+    label: "查 Velero"
+    emoji: "🧰"
+    risk: low
+    callback_format: info
+    category: backup_failure
+    mcp:
+      provider: k8s
+      tool: kubectl_get
+      params:
+        namespace: "velero"
+        resource: "backups.velero.io"
+    reply_format: truncated
+    timeout_sec: 8
+    description: "列出 Velero backup CR 狀態"
+
   # ==========================================================================
   # 寫類按鈕（有副作用，4-part nonce callback）
   # ==========================================================================

apps/api/src/services/callback_dispatcher.py

@@ -35,6 +35,18 @@ import yaml
 logger = structlog.get_logger(__name__)
 
 
+_PROVIDER_ALIASES = {
+    "k8s": "kubernetes",
+    "ssh": "ssh_host",
+}
+
+
+def _resolve_provider_name(provider_name: str) -> str:
+    """Normalize legacy callback spec provider names to registered MCP providers."""
+
+    return _PROVIDER_ALIASES.get(provider_name, provider_name)
+
+
 # =============================================================================
 # Data Types
 # =============================================================================
@@ -262,14 +274,15 @@ async def dispatch_action(
 
         # MCP registry dispatch
         from src.plugins.mcp.registry import get_provider
-        provider = get_provider(spec.mcp_provider)
+        provider_name = _resolve_provider_name(spec.mcp_provider)
+        provider = get_provider(provider_name)
         if not provider:
             duration = (time.perf_counter() - start) * 1000
             return DispatchResult(
                 success=False, action=action_name, incident_id=incident_id,
                 user_id=user_id,
-                result_text=f"{spec.emoji} {spec.label} 失敗：MCP provider '{spec.mcp_provider}' 未註冊",
-                error=f"provider_not_found: {spec.mcp_provider}",
+                result_text=f"{spec.emoji} {spec.label} 失敗：MCP provider '{provider_name}' 未註冊",
+                error=f"provider_not_found: {provider_name}",
                 duration_ms=duration,
             )
 

apps/api/src/services/decision_manager.py

@@ -85,6 +85,22 @@ def _should_escalate_auto_approve_rejection(reason: Any) -> bool:
     }
 
 
+_HOST_LAYER_SSH_CATEGORIES = {"infrastructure", "host_resource", "backup_failure"}
+_NON_K8S_HOST_CATEGORIES = {"host_resource", "backup_failure"}
+
+
+def _is_host_layer_ssh_category(category: str | None) -> bool:
+    """Return True when DecisionManager must route non-kubectl actions to SSH."""
+
+    return (category or "") in _HOST_LAYER_SSH_CATEGORIES
+
+
+def _is_non_k8s_host_category(category: str | None) -> bool:
+    """Return True for host/backup alerts that must not auto-run kubectl."""
+
+    return (category or "") in _NON_K8S_HOST_CATEGORIES
+
+
 async def _escalate_decision_auto_repair_unavailable(
     *,
     incident: Incident,
@@ -1990,36 +2006,36 @@ class DecisionManager:
         except Exception as _rescue_err:
             logger.debug("target_rescue_skipped", error=str(_rescue_err))
 
-        # ADR-073 Phase 3-2: infrastructure 告警 (Docker/Host) → SSH MCP routing (2026-04-12 ogt)
-        # alert_category = "infrastructure" 表示 Docker 告警，非 kubectl action → SSH
+        # ADR-073 Phase 3-2: infrastructure/host/backup 告警 → SSH MCP routing.
+        # alert_category = "backup_failure" uses the same host-layer path as AutoRepairService.
         # P1-1 fix 2026-04-12: 必須在 kubectl safety guard 之前 routing，否則 docker 指令被 _action_safe=False 攔截
         _alert_category = getattr(incident, "alert_category", None) or ""
-        if _alert_category in {"infrastructure", "host_resource"} and action and not action.startswith("kubectl"):
+        if _is_host_layer_ssh_category(_alert_category) and action and not action.startswith("kubectl"):
             await self._ssh_execute(incident, token, action, _target)
             return
 
-        # 2026-04-15 ogt: host_resource 告警（HostHighCpuLoad 等）不是 K8s workload 問題
+        # 2026-04-15 ogt: host_resource/backup_failure 告警不是 K8s workload 問題
         # 不得執行 kubectl 操作，改降級人工審核
         # 根因：原本只擋了 infrastructure，忘記 host_resource 也不走 K8s
-        if _alert_category == "host_resource" and action and action.startswith("kubectl"):
+        if _is_non_k8s_host_category(_alert_category) and action and action.startswith("kubectl"):
             logger.warning(
-                "auto_execute_blocked_host_resource_no_k8s",
+                "auto_execute_blocked_host_layer_no_k8s",
                 incident_id=incident.incident_id,
                 alert_category=_alert_category,
                 action=action[:80],
-                reason="host_resource 告警不應執行 K8s kubectl 操作，降級人工審核",
+                reason="host/backup 告警不應執行 K8s kubectl 操作，降級人工審核",
             )
             token.state = DecisionState.READY
             token.proposal_data["auto_executed"] = False
             token.proposal_data["mcp_all_failed"] = True
-            token.proposal_data["blocked_reason"] = "host_resource 告警禁止 K8s kubectl，請人工排查主機"
+            token.proposal_data["blocked_reason"] = f"{_alert_category} 告警禁止 K8s kubectl，請人工排查主機/備份"
             await self._save_token(token)
             _fire_and_forget(
                 _escalate_decision_auto_repair_unavailable(
                     incident=incident,
                     token=token,
                     failure_reason=token.proposal_data["blocked_reason"],
-                    attempted_actions="auto_execute -> host_resource_k8s_block -> emergency_intervention",
+                    attempted_actions=f"auto_execute -> {_alert_category}_k8s_block -> emergency_intervention",
                 )
             )
             _fire_and_forget(_push_decision_to_telegram(incident, token.proposal_data))

apps/api/tests/test_alertmanager_rule_bypass.py

@@ -4,7 +4,11 @@ from src.api.v1.webhooks import (
     _should_bypass_alertmanager_llm,
     _should_use_alertmanager_rule_first,
 )
-from src.services.decision_manager import _should_escalate_auto_approve_rejection
+from src.services.decision_manager import (
+    _is_host_layer_ssh_category,
+    _is_non_k8s_host_category,
+    _should_escalate_auto_approve_rejection,
+)
 from src.services.telegram_gateway import _format_resolved_guard_stamp
 
 
@@ -84,6 +88,18 @@ def test_manual_gate_reasons_escalate_to_emergency_intervention():
     assert _should_escalate_auto_approve_rejection("critical_operation") is False
 
 
+def test_backup_failure_routes_to_decision_ssh_before_kubectl_parser():
+    assert _is_host_layer_ssh_category("backup_failure") is True
+    assert _is_host_layer_ssh_category("host_resource") is True
+    assert _is_host_layer_ssh_category("kubernetes") is False
+
+
+def test_backup_failure_blocks_k8s_auto_execute():
+    assert _is_non_k8s_host_category("backup_failure") is True
+    assert _is_non_k8s_host_category("host_resource") is True
+    assert _is_non_k8s_host_category("infrastructure") is False
+
+
 def test_resolved_guard_stamp_without_timestamp_is_clean():
     assert _format_resolved_guard_stamp(None) == "✅ 此事件已解決"
 

apps/api/tests/test_callback_dispatcher.py

@@ -21,6 +21,7 @@ from src.services.callback_dispatcher import (
     list_actions_for_category,
     load_action_registry,
     _lookup_context,
+    _resolve_provider_name,
     _resolve_template,
 )
 
@@ -68,6 +69,11 @@ class TestRegistryLoading:
             assert spec and spec.callback_format == "info", \
                 f"{qa} should use info format"
 
+    def test_legacy_provider_aliases_resolve_to_registered_names(self):
+        assert _resolve_provider_name("k8s") == "kubernetes"
+        assert _resolve_provider_name("ssh") == "ssh_host"
+        assert _resolve_provider_name("prometheus") == "prometheus"
+
 
 # =============================================================================
 # Category filtering
@@ -91,6 +97,16 @@ class TestCategoryFiltering:
         assert any(a.callback_format == "info" for a in actions), "需至少 1 個查類"
         assert any(a.callback_format == "nonce" for a in actions), "需至少 1 個寫類"
 
+    def test_backup_failure_has_read_only_diagnostics(self):
+        actions = list_actions_for_category("backup_failure")
+        names = {a.name for a in actions}
+        assert {
+            "backup_check_host_disk",
+            "backup_check_jobs",
+            "backup_check_velero",
+        }.issubset(names)
+        assert all(a.callback_format == "info" for a in actions)
+
 
 # =============================================================================
 # Template variable resolution