feat(page-ai): add resumable run journal descriptors

2026-06-09 18:48:46 +08:00
parent 6ef233772e
commit 922965d30f
17 changed files with 3254 additions and 58 deletions
@@ -22,6 +22,7 @@ const WORKSPACE_ID = "local-ws:mnote-e2e:my-space";
 const ROOT_PATH = "/mnt/Data1T/Mnote_data/users/mnote-e2e/workspaces/my-space";
 const ROOT_URI = `file://${ROOT_PATH}`;
 const OWNER_REL = "knowledge-rag-fixtures-7-50/PageAiKnowledgeRagSmoke.md";
+const EXPECTED_RESOURCE = "新页面233155/image copy 6.png";
 const DOCUMENT_ID = `local-md:${OWNER_REL.replaceAll("/", "~2F")}`;

 function sqlQuote(value) {
@@ -79,6 +80,75 @@ async function signIn(context) {
  assert(response.ok(), `/api/auth 登录失败: ${response.status()} ${text.slice(0, 500)}`);
 }

+async function assertKnowledgeRagDescriptor(context) {
+  const response = await context.request.get(`${BASE_URL}/api/page-ai/agents/descriptors?profile=reasonix`, {
+    headers: {
+      "x-mnote-actor-id": ACTOR_ID,
+      "x-mnote-actor-type": "user",
+      accept: "application/json",
+    },
+  });
+  assert(response.ok(), `descriptor API 失败: ${response.status()} ${await response.text()}`);
+  const payload = await response.json();
+  const reasonix = (payload.descriptors || []).find((descriptor) => descriptor.agentId === "reasonix");
+  assert(reasonix, "descriptor 缺少 Reasonix");
+  assert.equal(reasonix.capabilityStates?.knowledge_rag?.enabled, true, "Reasonix descriptor 应声明 knowledge_rag enabled");
+  assert((reasonix.capabilities || []).includes("knowledge_rag"), "Reasonix descriptor capabilities 应包含 knowledge_rag");
+  const toolNames = new Set((reasonix.tools || []).map((tool) => tool.name));
+  for (const toolName of ["mnote.knowledge_rag.status", "mnote.knowledge_rag.query", "mnote.knowledge_rag.open_reference"]) {
+    assert(toolNames.has(toolName), `Reasonix descriptor 缺少 ${toolName}`);
+  }
+}
+
+async function knowledgeRagStatus(context) {
+  const params = new URLSearchParams({ rootUri: ROOT_URI, workspaceId: WORKSPACE_ID });
+  const response = await context.request.get(`${BASE_URL}/api/knowledge-rag/status?${params.toString()}`);
+  assert(response.ok(), `knowledge-rag status 失败: ${response.status()} ${await response.text()}`);
+  return await response.json();
+}
+
+async function ensureKnowledgeRagSourceIndexed(context) {
+  const response = await context.request.post(`${BASE_URL}/api/knowledge-rag/ingest`, {
+    data: {
+      rootUri: ROOT_URI,
+      workspaceId: WORKSPACE_ID,
+      sources: [{ sourcePath: EXPECTED_RESOURCE }],
+    },
+  });
+  assert(response.ok(), `knowledge-rag ingest 失败: ${response.status()} ${await response.text()}`);
+  const startedAt = Date.now();
+  let lastEntry = null;
+  while (Date.now() - startedAt < 90_000) {
+    const payload = await knowledgeRagStatus(context);
+    lastEntry = (payload.registry?.entries || []).find((entry) => entry.sourceRootRelativePath === EXPECTED_RESOURCE) || null;
+    if (lastEntry?.indexedAtMs && lastEntry?.lightRagDocId && !lastEntry?.stale && !lastEntry?.deletedAtMs) return lastEntry;
+    await new Promise((resolve) => setTimeout(resolve, 5_000));
+  }
+  throw new Error(`等待目标资料入库超时: ${JSON.stringify(lastEntry, null, 2)}`);
+}
+
+async function assertKnowledgeRagQueryReturnsCitationMarkdown(context) {
+  const response = await context.request.post(`${BASE_URL}/api/knowledge-rag/query`, {
+    data: {
+      rootUri: ROOT_URI,
+      workspaceId: WORKSPACE_ID,
+      query: "这个图片资料在资料库里是什么内容？",
+      mode: "mix",
+      topK: 8,
+      chunkTopK: 8,
+      includeChunkContent: true,
+      sourcePaths: [EXPECTED_RESOURCE],
+    },
+  });
+  assert(response.ok(), `knowledge-rag query 失败: ${response.status()} ${await response.text()}`);
+  const payload = await response.json();
+  const references = Array.isArray(payload.references) ? payload.references : [];
+  assert(
+    references.some((reference) => String(reference.citationMarkdown || "").trim() && String(reference.citationUrl || "").includes("resourceTab=")),
+    `query 输出缺少 citationMarkdown，Page AI 最终回答 smoke 不能继续: ${JSON.stringify(references, null, 2).slice(0, 3000)}`,
+  );
+}
+
 async function selectReasonix(page) {
  await page.locator("[data-page-ai-agent-button]").click({ timeout: UI_TIMEOUT_MS });
  await page.locator("[data-page-ai-agent-popover]").waitFor({ state: "visible", timeout: UI_TIMEOUT_MS });
@@ -219,6 +289,9 @@ async function main() {

  try {
    await signIn(context);
+    await assertKnowledgeRagDescriptor(context);
+    await ensureKnowledgeRagSourceIndexed(context);
+    await assertKnowledgeRagQueryReturnsCitationMarkdown(context);
    const documentUrl = new URL(`${BASE_URL}/documents/${encodeURIComponent(DOCUMENT_ID)}`);
    documentUrl.searchParams.set("sourceKind", "local_folder");
    documentUrl.searchParams.set("rootUri", ROOT_URI);
@@ -232,7 +305,7 @@ async function main() {
      .count();
    const prompt = [
      "请调用 mnote_knowledge_rag_query 检索资料库。",
-      "问题：这个图片资料在资料库里是什么内容？调用工具时请把 sourcePaths 参数设为 [\"新页面233155/image copy 6.png\"]。",
+      `问题：这个图片资料在资料库里是什么内容？调用工具时请把 sourcePaths 参数设为 ["${EXPECTED_RESOURCE}"]。`,
      "最终只输出一句中文结论，必须包含返回的 citationMarkdown 链接；如果 locatorDegraded=true，必须说明来源定位降级，不要描述检索过程，不要输出 raw JSON，不要编造页码或 bbox。",
    ].join("\n");
    await page.locator("[data-page-ai-input]").fill(prompt, { timeout: UI_TIMEOUT_MS });