docs(agent99): advance mainline to alert routing

apps/api/src/services/agent99_enterprise_ai_automation_work_items.py

@@ -53,6 +53,7 @@ def load_latest_agent99_enterprise_ai_automation_work_items(
     priority_counts = {priority: 0 for priority in _VALID_PRIORITIES}
     status_counts = {status: 0 for status in _VALID_STATUSES}
     p0_ids: list[str] = []
+    active_p0_ids: list[str] = []
 
     for index, item in enumerate(work_items, start=1):
         if not isinstance(item, dict):
@@ -78,6 +79,8 @@ def load_latest_agent99_enterprise_ai_automation_work_items(
         status_counts[item_status] += 1
         if priority == "P0":
             p0_ids.append(item_id)
+            if item_status != "complete":
+                active_p0_ids.append(item_id)
             missing = [field for field in required_p0_fields if item.get(field) is None]
             if missing:
                 raise ValueError(f"{path}: {item_id} missing P0 fields: {missing}")
@@ -88,12 +91,14 @@ def load_latest_agent99_enterprise_ai_automation_work_items(
         raise ValueError(f"{path}: work item order is not contiguous")
 
     current_p0_id = current_p0.get("id")
-    if current_p0_id not in p0_ids:
-        raise ValueError(f"{path}: current_p0.id is not a P0 work item")
-    if not p0_ids or p0_ids[0] != current_p0_id:
-        raise ValueError(f"{path}: current_p0 must be the first ordered P0")
-    if payload.get("next_execution_order") != p0_ids:
-        raise ValueError(f"{path}: next_execution_order must equal ordered P0 ids")
+    if current_p0_id not in active_p0_ids:
+        raise ValueError(f"{path}: current_p0.id is not an active P0 work item")
+    if not active_p0_ids or active_p0_ids[0] != current_p0_id:
+        raise ValueError(f"{path}: current_p0 must be the first ordered active P0")
+    if payload.get("next_execution_order") != active_p0_ids:
+        raise ValueError(
+            f"{path}: next_execution_order must equal ordered active P0 ids"
+        )
 
     _require_count(summary, "p0_count", priority_counts["P0"], path)
     _require_count(summary, "p1_count", priority_counts["P1"], path)

apps/api/tests/test_agent99_enterprise_ai_automation_work_items_api.py

@@ -31,7 +31,7 @@ def test_agent99_enterprise_work_items_loader_returns_complete_scope() -> None:
         "agent99_enterprise_ai_automation_work_items_v1"
     )
     assert payload["scope_complete"] is False
-    assert payload["current_p0"]["id"] == "AG99-P0-001"
+    assert payload["current_p0"]["id"] == "AG99-P0-002"
     assert payload["summary"] == {
         "host_count": 7,
         "product_count": 12,
@@ -42,11 +42,11 @@ def test_agent99_enterprise_work_items_loader_returns_complete_scope() -> None:
         "p2_count": 3,
         "in_progress_count": 5,
         "in_progress_blocked_count": 3,
-        "planned_count": 17,
-        "complete_count": 0,
+        "planned_count": 16,
+        "complete_count": 1,
         "current_p0_count": 1,
     }
-    assert payload["next_execution_order"][0] == "AG99-P0-001"
+    assert payload["next_execution_order"][0] == "AG99-P0-002"
     assert payload["next_execution_order"][-1] == "AG99-P0-014"
 
 
@@ -54,7 +54,7 @@ def test_agent99_enterprise_projection_is_bounded() -> None:
     payload = load_latest_agent99_enterprise_ai_automation_work_items()
     projection = build_agent99_enterprise_priority_projection(payload)
 
-    assert projection["current_p0"]["id"] == "AG99-P0-001"
+    assert projection["current_p0"]["id"] == "AG99-P0-002"
     assert projection["coverage"] == {
         "host_count": 7,
         "product_count": 12,
@@ -73,7 +73,7 @@ def test_priority_readback_projects_agent99_enterprise_order() -> None:
     payload = load_latest_awoooi_priority_work_order_readback()
     projection = payload["agent99_enterprise_ai_automation"]
 
-    assert projection["current_p0"]["id"] == "AG99-P0-001"
+    assert projection["current_p0"]["id"] == "AG99-P0-002"
     assert projection["work_item_counts"]["p0"] == 14
     assert (
         payload["source_refs"]["agent99_enterprise_ai_automation_work_items_api"]
@@ -103,7 +103,7 @@ def test_agent99_enterprise_work_items_endpoint_returns_snapshot() -> None:
 
     assert response.status_code == 200
     payload = response.json()
-    assert payload["current_p0"]["id"] == "AG99-P0-001"
+    assert payload["current_p0"]["id"] == "AG99-P0-002"
     assert payload["summary"]["host_count"] == 7
     assert payload["summary"]["product_count"] == 12
     assert payload["summary"]["public_surface_count"] == 23

docs/operations/agent99-enterprise-ai-automation-work-items.snapshot.json

@@ -1,7 +1,7 @@
 {
   "schema_version": "agent99_enterprise_ai_automation_work_items_v1",
-  "generated_at": "2026-07-10T16:00:26+08:00",
-  "status": "in_progress_p0_agent_outcome_staging_verified_runtime_apply_pending",
+  "generated_at": "2026-07-10T16:22:00+08:00",
+  "status": "in_progress_p0_alert_routing_grouping_dedupe",
   "scope_complete": false,
   "north_star": "Make Windows host 192.168.0.99 the policy-controlled on-prem AI execution node for all hosts, VMs, services, products, sites, tools, packages, alerts and recovery workflows, with external monitoring when host 99 is unavailable.",
   "canonical_sources": {
@@ -17,22 +17,11 @@
     "runtime_reboot_slo_readback": "https://awoooi.wooo.work/api/v1/agents/reboot-auto-recovery-slo-scorecard"
   },
   "current_p0": {
-    "id": "AG99-P0-001",
-    "title": "Agent outcome truth and source-runtime reconciliation",
-    "reason": "Agent99 currently treats command exit success as incident resolution and the Windows runtime scripts do not consistently match the current Gitea source. All later automation depends on trustworthy outcomes.",
-    "implementation_status": "source_implemented_staging_verified_runtime_apply_pending",
-    "staging_verifier": {
-      "host": "99",
-      "outcome_contract": "agent99_outcome_contract_v1",
-      "outcome_self_test_ok": true,
-      "runtime_manifest": "agent99_runtime_manifest_v1",
-      "source_revision": "p0-001-staging-latest",
-      "runtime_manifest_matched": true,
-      "runtime_manifest_file_count": 7,
-      "runtime_manifest_mismatch_count": 0,
-      "evidence": "C:\\Wooo\\Agent99\\staging\\p0-001-runtime\\evidence\\agent99-OutcomeContractSelfTest-20260710-160255.json"
-    },
-    "next_action": "Commit and deploy the verified outcome contract to host 99, rerun the runtime manifest and outcome self-test, then replay one operator smoke and one alert-source event without counting transport-only success as resolved."
+    "id": "AG99-P0-002",
+    "title": "Alert taxonomy, routing, grouping and dedupe",
+    "reason": "Explicit event kind and suggested mode are not consistently authoritative, and forwarding before grouping can create wrong-domain or duplicate Agent99 work.",
+    "implementation_status": "in_progress_replay_corpus_and_pre_bridge_grouping",
+    "next_action": "Add routing precedence and a replay corpus for backup, provider, reboot, PostgreSQL, host and K3s events; move grouping and single-flight ahead of Agent99 dispatch."
   },
   "current_runtime_truth": {
     "observed_at": "2026-07-10T15:04:27+08:00",
@@ -267,7 +256,7 @@
       "id": "AG99-P0-001",
       "order": 1,
       "priority": "P0",
-      "status": "in_progress",
+      "status": "complete",
       "title": "Agent outcome truth and source-runtime reconciliation",
       "owner_lane": "agent99_control_plane",
       "dependencies": [],
@@ -283,13 +272,35 @@
       "verifier": "For every mode, require post-condition pass plus source event resolution; compare source and runtime manifest hashes.",
       "callback": "Write final outcome to AWOOOI incident and AwoooP Run/Verifier using the same trace id.",
       "acceptance": "No false-resolved regression cases; source/runtime drift count is zero; unresolved evidence stays degraded or blocked.",
-      "next_action": "Deploy the staging-verified outcome contract to host 99, confirm source/runtime manifest hashes, then replay operator and alert-source outcomes."
+      "completion_receipt": {
+        "source_revision": "5ea4405c2a75b51244da168a4834d27e24d74ee6",
+        "runtime_manifest_matched": true,
+        "runtime_manifest_file_count": 7,
+        "runtime_manifest_mismatch_count": 0,
+        "self_health_runtime_manifest_severity": "ok",
+        "outcome_self_test_ok": true,
+        "operator_replay_state": "resolved",
+        "operator_replay_verified_resolved": 1,
+        "alert_replay_state": "verifying",
+        "alert_replay_verified_resolved": 0,
+        "alert_replay_source_event_resolved": false,
+        "telegram_sent_count": 0,
+        "rollback": "C:\\Wooo\\Agent99\\rollback\\p0-001-pre-5ea4405c",
+        "evidence": [
+          "C:\\Wooo\\Agent99\\evidence\\agent99-OutcomeContractSelfTest-20260710-161302.json",
+          "C:\\Wooo\\Agent99\\evidence\\agent99-SelfCheck-20260710-161350.json",
+          "C:\\Wooo\\Agent99\\queue\\processed\\processed-p0-001-operator-verifier-20260710-1615.json",
+          "C:\\Wooo\\Agent99\\queue\\processed\\processed-p0-001-alert-verifier-20260710-1615.json",
+          "C:\\Wooo\\Agent99\\evidence\\agent99-ControlTick-20260710-161919.json"
+        ]
+      },
+      "next_action": "Keep runtime-manifest drift and verified-resolution counters under SelfCheck; continue with AG99-P0-002."
     },
     {
       "id": "AG99-P0-002",
       "order": 2,
       "priority": "P0",
-      "status": "planned",
+      "status": "in_progress",
       "title": "Alert taxonomy, routing, grouping and dedupe",
       "owner_lane": "awoooi_alert_router_agent99_ingress",
       "dependencies": ["AG99-P0-001"],
@@ -736,12 +747,11 @@
     "p2_count": 3,
     "in_progress_count": 5,
     "in_progress_blocked_count": 3,
-    "planned_count": 17,
-    "complete_count": 0,
+    "planned_count": 16,
+    "complete_count": 1,
     "current_p0_count": 1
   },
   "next_execution_order": [
-    "AG99-P0-001",
     "AG99-P0-002",
     "AG99-P0-003",
     "AG99-P0-004",

docs/workplans/2026-07-10-agent99-enterprise-ai-automation-master-plan.md

@@ -91,8 +91,8 @@
 
 | 順序 | ID | 工作 | 狀態 | 驗收 |
 | --- | --- | --- | --- | --- |
-| 1 | AG99-P0-001 | 修正 `exitCode=0 => resolved` 假綠，對齊 99 runtime script 與 Gitea source SHA | **進行中，current P0** | 每種模式以 verifier 決定 outcome；舊 runtime/script drift 歸零；不得再把缺證據算 resolved |
-| 2 | AG99-P0-002 | 修正 alert taxonomy、wrong-domain routing、bridge-before-grouping 與重複事件 | 待辦 | `suggestedMode`/kind 優先於 source 字串；5 分鐘先 group；同 fingerprint 只建立一個 active incident |
+| 1 | AG99-P0-001 | 修正 `exitCode=0 => resolved` 假綠，對齊 99 runtime script 與 Gitea source SHA | **完成** | Production 99 outcome self-test 通過；runtime manifest `7/7` matched、drift `0`；operator replay 為 verified resolved，alert replay 缺 source-event resolved 時維持 verifying |
+| 2 | AG99-P0-002 | 修正 alert taxonomy、wrong-domain routing、bridge-before-grouping 與重複事件 | **進行中，current P0** | `suggestedMode`/kind 優先於 source 字串；5 分鐘先 group；同 fingerprint 只建立一個 active incident |
 | 3 | AG99-P0-003 | 強化 ingress：relay token 必填、Telegram chat+sender allowlist、idempotency/single consumer | 待辦 | 未認證 LAN request 拒絕；producer `auto_repair`/policy 被保留；所有 request 可追 trace |
 | 4 | AG99-P0-004 | 新增 EvidenceCollect / RepairCandidate / MCP lane | 待辦 | 缺 evidence 的事件會建立可查 candidate，不再錯送 Perf/AwoooRepair；`INC-*` 可從收件追到 candidate |
 
@@ -157,4 +157,4 @@
 
 ## 8. 立即下一步
 
-目前唯一 P0 是 `AG99-P0-001`：先修正 Agent99 假 resolved 與 99 runtime/source drift，建立 outcome contract 與 regression tests。完成後依序做 routing/dedupe、secure ingress、RepairCandidate，再回到 reboot state machine 的 live rerun；如此不是離開重啟主線，而是先修正會把重啟與告警錯誤結案的控制核心。
+目前唯一 P0 是 `AG99-P0-002`：以 explicit event kind / suggested mode 建立 routing precedence，將 5 分鐘 grouping、fingerprint dedupe 與 single-flight 移到 Agent99 dispatch 之前，並用 backup、provider、reboot、PostgreSQL、host、K3s replay corpus 證明不再 wrong-domain 或重複派工。完成後依序做 secure ingress、RepairCandidate，再回到 reboot state machine live rerun。