feat(hub): 事件去重(A-4) + 审计写入路径(A-8)

A-4 FeishuEventReceipt:
- 新增 FeishuEventReceipt 表(eventId @unique),lark ws 至少一次投递的幂等兜底
- MessageReceiveEvent 加 header.event_id 字段
- trigger 入口查重:已存在的 event_id → 跳过(不建第二次 run)
- resetDb 加入 FeishuEventReceipt

A-8 审计写入:
- AuditEntry 加 projectId(权限拒绝/slash 命令等无 run 的审计点可定位)
- 新建 src/audit.ts:writeAudit(prisma, entry) best-effort 写入(吞错,不阻断 trigger)
- trigger 五个审计点:trigger.denied / trigger.role_denied / run.created / run.lock_race / run.finished / run.failed
- 新增 audit unit 测试(3) + trigger 集成测试(去重 + 审计,2)

59 tests 全过。

docs/adr/0017-agent-session-is-provider-bound.md

@@ -36,9 +36,12 @@ Per-run model selection (the run carries its model) is the switching point.
 
 - Switching model mid-project = new session; the new run seeds from project
   memory/anchors (ADR-0003), not the prior session's live context.
-- The agent layer is provider-agnostic: the agent loop is ours; model calls go
-  through an OpenAI-compatible client. No hard dependency on a single-vendor
-  agent SDK.
+- The agent layer is provider-agnostic: model calls go through an
+  OpenAI-compatible client, and the tool-calling loop is delegated to the
+  Vercel AI SDK (`generateText` + `tool`). The provider seam is the SDK's
+  `LanguageModel` interface, not a hand-rolled loop; swapping provider is
+  swapping the `createOpenAICompatible` factory, not rewriting the loop. No
+  hard dependency on a single-vendor agent SDK.
 - Role-based model routing (different run kinds default to different models) is
   a product/admin configuration concern, not a spec invariant.
 - "AgentSession reused by many runs" (ADR-0002) holds *within* one