feat(km): add full corpus asset taxonomy readback

apps/api/src/repositories/interfaces.py

@@ -265,6 +265,10 @@ class IKnowledgeRepository(Protocol):
         """取得分類統計 [(category, count)]"""
         ...
 
+    async def get_asset_taxonomy_counts(self) -> list[tuple[str, int]]:
+        """取得 AI 自動化資產維度統計 [(taxonomy_key, count)]"""
+        ...
+
     async def search(self, query: str, limit: int = 20) -> list[KnowledgeEntry]:
         """關鍵字搜尋 (title + content + tags)"""
         ...

apps/api/src/repositories/knowledge_repository.py

@@ -29,6 +29,113 @@ logger = structlog.get_logger(__name__)
 
 _DEFAULT_CATEGORY = "general"
 
+_ASSET_TAXONOMY_KEYS = (
+    "project",
+    "product",
+    "website",
+    "service",
+    "package",
+    "tool",
+    "log",
+    "alert",
+    "playbook",
+    "rag",
+    "mcp",
+    "schedule",
+)
+
+_ASSET_TAXONOMY_TERMS: dict[str, tuple[str, ...]] = {
+    "project": (
+        "project",
+        "repo",
+        "repository",
+        "gitea",
+        "branch",
+        "workflow",
+        "source_control",
+    ),
+    "product": (
+        "product",
+        "awoooi",
+        "awooop",
+        "iwooos",
+        "stockplatform",
+        "momo",
+        "awooogo",
+        "agent-bounty",
+        "agent_bounty",
+        "tsenyang",
+        "vibework",
+        "2026fifa",
+    ),
+    "website": ("website", "site", "nginx", "ssl", "domain", "route", "frontend"),
+    "service": ("service", "daemon", "api", "worker", "runtime", "container", "pod"),
+    "package": (
+        "package",
+        "dependency",
+        "npm",
+        "pnpm",
+        "node",
+        "python",
+        "pip",
+        "prisma",
+        "next",
+        "library",
+    ),
+    "tool": (
+        "tool",
+        "ansible",
+        "mcp",
+        "playbook",
+        "telegram",
+        "wazuh",
+        "kali",
+        "sentry",
+        "signoz",
+        "runner",
+    ),
+    "log": (
+        "log",
+        "logs",
+        "event",
+        "timeline",
+        "trace",
+        "audit",
+        "callback",
+        "conversation_event",
+        "telemetry",
+    ),
+    "alert": (
+        "alert",
+        "telegram",
+        "sentry",
+        "signoz",
+        "notification",
+        "warning",
+        "critical",
+    ),
+    "playbook": ("playbook", "runbook", "sop"),
+    "rag": ("rag", "vector", "embedding", "semantic", "retrieval"),
+    "mcp": ("mcp", "connector", "gateway", "tool integration", "tool-integration"),
+    "schedule": ("schedule", "cron", "job", "worker", "patrol", "recurrence", "cadence"),
+}
+
+_ASSET_TAXONOMY_CATEGORY_HINTS: dict[str, tuple[str, ...]] = {
+    "website": ("external_site",),
+    "service": (
+        "infrastructure",
+        "application",
+        "ai_system",
+        "database",
+        "host_resource",
+        "kubernetes",
+        "alert_handling",
+    ),
+    "tool": ("devops_tool", "AI自動化/Ansible受控修復"),
+    "alert": ("alert_handling",),
+    "playbook": ("auto_repair",),
+}
+
 
 def _enum_text(column):
     """Return a lowercase text view for enum/varchar columns across old KM schemas."""
@@ -85,6 +192,32 @@ def _knowledge_entry_columns():
     )
 
 
+def _asset_taxonomy_condition(key: str):
+    """Build a broad-but-readable taxonomy matcher for AI automation surfaces."""
+    category_expr = _normalized_category_expr()
+    category_text = func.lower(category_expr.cast(String))
+    text_columns = (
+        KnowledgeEntryRecord.title,
+        KnowledgeEntryRecord.content,
+        KnowledgeEntryRecord.tags.cast(String),
+        category_expr.cast(String),
+    )
+    conditions = []
+    category_hints = tuple(
+        hint.lower() for hint in _ASSET_TAXONOMY_CATEGORY_HINTS.get(key, ())
+    )
+    if category_hints:
+        conditions.append(category_text.in_(category_hints))
+    for term in _ASSET_TAXONOMY_TERMS.get(key, ()):
+        pattern = f"%{term.lower()}%"
+        conditions.extend(func.lower(column).like(pattern) for column in text_columns)
+    if key == "playbook":
+        conditions.append(KnowledgeEntryRecord.related_playbook_id.is_not(None))
+    if not conditions:
+        return category_text == key
+    return or_(*conditions)
+
+
 class KnowledgeDBRepository:
     """
     Knowledge Repository - PostgreSQL 實作
@@ -290,6 +423,26 @@ class KnowledgeDBRepository:
         )
         return [(_normalize_category(row.category), row.cnt) for row in result.all()]
 
+    async def get_asset_taxonomy_counts(self) -> list[tuple[str, int]]:
+        """取得 AI 自動化資產維度統計。
+
+        這不是替代原始 category，而是讓 UI / Agent 可以用穩定 taxonomy
+        將 KM 依專案、產品、網站、服務、套件、工具、Log、Alert、PlayBook、
+        RAG、MCP 與排程分群。
+        """
+        rows: list[tuple[str, int]] = []
+        for key in _ASSET_TAXONOMY_KEYS:
+            result = await self.db.execute(
+                select(func.count())
+                .select_from(KnowledgeEntryRecord)
+                .where(
+                    _active_status_filter(),
+                    _asset_taxonomy_condition(key),
+                )
+            )
+            rows.append((key, int(result.scalar() or 0)))
+        return rows
+
     async def search(self, query: str, limit: int = 20) -> list[KnowledgeEntry]:
         """關鍵字搜尋 (title + content + tags)"""
         like_q = f"%{query}%"