fix(t128+t129): 圖搜尋補 template:triplet＋AI 問答出處按頁去重

t128 真因（總管實測定罪）：t116 只補 kbdb_base，同一行 URL 還吃 {{input.template}} ⇒ /records/by-template/?owner_id=... 查不到；手動補 template 即 count=1 （企業版功能解鎖→控制→授權系統）。**同種病三犯，已記 mistakes。** t129：一卡切 3-5 block 每段都算一筆命中 ⇒ dedupeSourcesByPage 後端去重＋hit_count。 vitest 52 passed（1 紅＝console HTML 搬遷陳舊測試，非本案）。（實作＝子 CC；驗證+commit＝總管）
2026-07-29 14:11:52 +08:00
parent eb9f2db513
commit ccb86481ae
3 changed files with 183 additions and 3 deletions
@@ -73,6 +73,32 @@ export function mapGraphWorkflowOutput(data: unknown): { neighbors: unknown[]; e
  return { neighbors, edges, count: neighbors.length };
 }

+/**
+ * 出處清單按 page_name 去重（t129）：
+ * rag_chat workflow 把同一張卡拆成多個 block，每個 block 各回一筆 source（同頁名）→ 前端列一整頁重複。
+ * 後端去重：同一個 page_name / page 只保留第一筆，hit_count > 1 時附計數。
+ * page_name 優先；page 備用；兩者皆無 → key 為空字串（歸為同一「無頁名」組）。
+ * 純函式，單測用 export。
+ */
+export function dedupeSourcesByPage(sources: unknown[]): unknown[] {
+  const seen = new Map<string, { item: Record<string, unknown>; count: number }>();
+  for (const s of sources) {
+    if (!s || typeof s !== 'object') continue;
+    const item = s as Record<string, unknown>;
+    const page = typeof item.page_name === 'string' ? item.page_name :
+                 typeof item.page === 'string' ? item.page : '';
+    const existing = seen.get(page);
+    if (existing) {
+      existing.count += 1;
+    } else {
+      seen.set(page, { item, count: 1 });
+    }
+  }
+  return [...seen.values()].map(({ item, count }) =>
+    count > 1 ? { ...item, hit_count: count } : item,
+  );
+}
+
 /** 越庫/不存在 一律同一句 404（不洩存在性）。 */
 function notFound(c: Context<{ Bindings: Bindings }>): Response {
  return c.json({ error: '找不到這筆資料' }, 404);
@@ -274,7 +300,8 @@ portalDataRouter.get('/portal/data/graph/neighbors/:name', (c) =>
      const result = await executeWebhookGraph(
        c.env,
        wfGraph,
-        { node: nodeName, depth, namespace: tenant, owner: tenant },
+        // t116: 補傳 kbdb_base；t128: 補傳 template（workflow fetch_triplets.url 用 {{input.template}}）
+        { node: nodeName, depth, namespace: tenant, owner: tenant, kbdb_base: c.env.KBDB_BASE_URL ?? '', template: 'triplet' },
        'graph_neighbors',
        tenant,
        c.executionCtx,
@@ -390,10 +417,12 @@ portalDataRouter.get('/portal/data/chat', (c) =>
      return c.json({ error: `rag_chat workflow 執行失敗：${result.error ?? '未知錯誤'}` }, 502);
    }
    // 回 workflow 回應內層 data：{answer, sources, graph_facts}（缺欄位誠實回空，不編造）
+    // t129: sources 按 page_name 去重——同一卡拆多 block 每個各一筆，前端列一整頁重複；後端去重後乾淨。
    const inner = unwrapWorkflowData(result.data, 'answer');
+    const rawSources = Array.isArray(inner.sources) ? inner.sources : [];
    return c.json({
      answer: typeof inner.answer === 'string' ? inner.answer : '',
-      sources: Array.isArray(inner.sources) ? inner.sources : [],
+      sources: dedupeSourcesByPage(rawSources),
      graph_facts: inner.graph_facts ?? null,
    });
  }),
@@ -19,7 +19,7 @@
 import { SELF, env, fetchMock } from 'cloudflare:test';
 import { beforeAll, afterEach, describe, it, expect } from 'vitest';
 import { workflowsVisible } from '../src/routes/portal';
-import { entryLibrary, sanitizeUploadFilename, filterDeprecatedEntries, mapGraphWorkflowOutput, normalizeCjkQuery, findBestNodeMatch } from '../src/routes/portal-data';
+import { entryLibrary, sanitizeUploadFilename, filterDeprecatedEntries, mapGraphWorkflowOutput, normalizeCjkQuery, findBestNodeMatch, dedupeSourcesByPage } from '../src/routes/portal-data';
 import type { Bindings } from '../src/types';

 const KBDB = 'https://kbdb.test';
@@ -578,3 +578,134 @@ describe('GET /portal/data/graph/neighbors/:name（t96 fuzzy fallback）', () =>
    expect(data.neighbors.length).toBe(1);
  });
 });
+
+// ═══════════════ 12. t116: graph_neighbors workflow 補傳 kbdb_base ═══════════════
+
+describe('GET /portal/data/graph/neighbors/:name（t116 kbdb_base 補傳）', () => {
+  it('tenant 有 graph_neighbors workflow → portal 傳入 kbdb_base，workflow 正常執行不崩', async () => {
+    // 設定 session（["*"] 全庫，放行 graph 粗閘）
+    await seedSession('tok-t116', 'rec_t116');
+    mockGetRecord('rec_t116', userValues({ libraries: '["*"]', role: 'admin' }));
+
+    // 在 WEBHOOKS KV 放 graph_neighbors workflow（Input→Output 直通）
+    // 這個 workflow 不用 {{input.kbdb_base}}，只驗工作流路徑正常執行（不走 graphBase fallback）
+    // 若沒補傳 kbdb_base 但 workflow 內有 {{input.kbdb_base}} 的節點，URL 解析失敗 → executeWebhookGraph 回 error
+    // 此測試退而求其次：用無外部依賴的直通圖確認整個路徑都通（workflow 取代 plugin fallback）
+    const wfKey = `${TENANT}:wf:graph_neighbors`;
+    await env.WEBHOOKS.put(wfKey, JSON.stringify({
+      graph: {
+        id: 'gn-t116',
+        name: 'graph_neighbors',
+        nodes: [
+          { id: 'input', type: 'Input' },
+          // comp_passthrough 是內建零件，不需外部 fetch，直接回傳 context
+          { id: 'pass', type: 'Component', componentId: 'comp_passthrough' },
+          { id: 'output', type: 'Output' },
+        ],
+        edges: [
+          { from: 'input', to: 'pass', type: 'PIPE' },
+          { from: 'pass', to: 'output', type: 'PIPE' },
+        ],
+      },
+      description: 't116 test',
+      created_at: '2026-07-29T00:00:00.000Z',
+    }));
+
+    const res = await get('/portal/data/graph/neighbors/AI%E5%8D%94%E4%BD%9C', { Authorization: 'Bearer tok-t116' });
+    expect(res.status).toBe(200);
+    const data = (await res.json()) as { neighbors: unknown[]; edges: unknown[]; count: number; kbdb_base?: string };
+    // workflow 走 comp_passthrough，output = 整個 context（含 kbdb_base）
+    // mapGraphWorkflowOutput 只取 neighbors/edges，其他欄位不影響回應
+    expect(Array.isArray(data.neighbors)).toBe(true);
+    expect(Array.isArray(data.edges)).toBe(true);
+    // 確認不是 502（graph_neighbors workflow 執行失敗）
+    expect(res.status).not.toBe(502);
+
+    await env.WEBHOOKS.delete(wfKey);
+  });
+});
+
+// ═══════════════ 13. t128: graph_neighbors workflow 補傳 template ═══════════════
+
+describe('GET /portal/data/graph/neighbors/:name（t128 template 補傳）', () => {
+  it('tenant 有 graph_neighbors workflow → portal 傳入 template=triplet，workflow 不崩', async () => {
+    await seedSession('tok-t128', 'rec_t128');
+    mockGetRecord('rec_t128', userValues({ libraries: '["*"]', role: 'admin' }));
+
+    const wfKey = `${TENANT}:wf:graph_neighbors`;
+    await env.WEBHOOKS.put(wfKey, JSON.stringify({
+      graph: {
+        id: 'gn-t128',
+        name: 'graph_neighbors',
+        nodes: [
+          { id: 'input', type: 'Input' },
+          { id: 'pass', type: 'Component', componentId: 'comp_passthrough' },
+          { id: 'output', type: 'Output' },
+        ],
+        edges: [
+          { from: 'input', to: 'pass', type: 'PIPE' },
+          { from: 'pass', to: 'output', type: 'PIPE' },
+        ],
+      },
+    }));
+
+    const res = await get('/portal/data/graph/neighbors/AI%E5%8D%94%E4%BD%9C', { Authorization: 'Bearer tok-t128' });
+    // template 有進 context → workflow 執行不崩（非 502）
+    expect(res.status).toBe(200);
+    const data = (await res.json()) as { neighbors: unknown[]; edges: unknown[] };
+    expect(Array.isArray(data.neighbors)).toBe(true);
+
+    await env.WEBHOOKS.delete(wfKey);
+  });
+});
+
+// ═══════════════ 14. t129: dedupeSourcesByPage 純函式 ═══════════════
+
+describe('dedupeSourcesByPage（t129 出處去重）', () => {
+  it('同 page_name 合併，hit_count 標計數', () => {
+    const srcs = [
+      { page_name: '企業版功能', mode: 'semantic', source: 'gitea://docs/enterprise.md' },
+      { page_name: '企業版功能', mode: 'semantic', source: 'gitea://docs/enterprise.md' },
+      { page_name: '企業版功能', mode: 'keyword', source: 'gitea://docs/enterprise.md' },
+    ];
+    const out = dedupeSourcesByPage(srcs) as { page_name: string; hit_count?: number }[];
+    expect(out.length).toBe(1); // 3 筆→1 筆
+    expect(out[0].page_name).toBe('企業版功能');
+    expect(out[0].hit_count).toBe(3);
+  });
+
+  it('不同 page_name 各保留一筆；單筆無 hit_count', () => {
+    const srcs = [
+      { page_name: 'A 頁', mode: 'semantic' },
+      { page_name: 'B 頁', mode: 'keyword' },
+    ];
+    const out = dedupeSourcesByPage(srcs) as { page_name: string; hit_count?: number }[];
+    expect(out.length).toBe(2);
+    expect(out.every(s => s.hit_count === undefined)).toBe(true);
+  });
+
+  it('page 欄（備用）也能去重', () => {
+    const srcs = [
+      { page: '備用頁', mode: 'semantic' },
+      { page: '備用頁', mode: 'keyword' },
+    ];
+    const out = dedupeSourcesByPage(srcs) as { page?: string; hit_count?: number }[];
+    expect(out.length).toBe(1);
+    expect(out[0].hit_count).toBe(2);
+  });
+
+  it('空陣列 → 空陣列；非物件條目跳過', () => {
+    expect(dedupeSourcesByPage([])).toEqual([]);
+    const out = dedupeSourcesByPage([null, 'oops', { page_name: 'X' }]);
+    expect(out.length).toBe(1);
+  });
+
+  it('page_name 優先於 page', () => {
+    const srcs = [
+      { page_name: '優先頁', page: '備用頁' },
+      { page_name: '優先頁', page: '備用頁' },
+    ];
+    const out = dedupeSourcesByPage(srcs) as { hit_count?: number }[];
+    expect(out.length).toBe(1); // 同 page_name → 合為一筆
+  });
+});