mnote/scripts/task538-knowledge-rag-source-scope-api-smoke.js

#!/usr/bin/env node
"use strict";

const assert = require("node:assert");
const fs = require("node:fs");
const path = require("node:path");
const { request } = require("playwright");

const BASE_URL = (process.env.MNOTE_WEB_SMOKE_BASE_URL || "http://127.0.0.1:3000").replace(/\/+$/, "");
const ROOT_PATH = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_PATH || "/mnt/Data1T/Mnote_data/users/mnote-e2e/workspaces/my-space";
const ROOT_URI = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_URI || `file://${ROOT_PATH}`;
const WORKSPACE_ID = process.env.MNOTE_KNOWLEDGE_RAG_WORKSPACE_ID || "local-ws:mnote-e2e:my-space";
const FIXTURE_DIR = "knowledge-rag-fixtures-7-50";
const OUTPUT_DIR = path.join(process.cwd(), "tmp", "task538-knowledge-rag-source-scope-api-smoke");
const RESULT_PATH = path.join(OUTPUT_DIR, "result.json");
const UI_TIMEOUT_MS = Number(process.env.MNOTE_SMOKE_UI_TIMEOUT_MS || 30_000);
const POLL_TIMEOUT_MS = Number(process.env.MNOTE_KNOWLEDGE_RAG_SCOPE_TIMEOUT_MS || 240_000);

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

async function apiJson(context, method, url, data) {
  const response = await context.fetch(url, {
    method,
    data,
    headers: {
      "x-mnote-actor-id": "mnote-e2e",
      "x-mnote-actor-type": "user",
      "x-mnote-workspace-id": WORKSPACE_ID,
      accept: "application/json",
    },
    timeout: UI_TIMEOUT_MS,
  });
  const text = await response.text();
  let payload = null;
  try {
    payload = text ? JSON.parse(text) : null;
  } catch (_) {
    payload = { rawText: text };
  }
  return { ok: response.ok(), status: response.status(), payload, text };
}

async function signIn(context) {
  const response = await context.post(`${BASE_URL}/api/auth`, {
    data: {
      action: "auth:signIn",
      args: {
        provider: "password",
        params: {
          email: "mnote.e2e@example.com",
          password: process.env.MNOTE_E2E_PASSWORD || "MnoteE2E123!",
          flow: "signIn",
        },
      },
    },
    timeout: UI_TIMEOUT_MS,
  });
  assert(response.ok(), `登录失败: ${response.status()} ${await response.text()}`);
}

async function assertKnowledgeRagDescriptor(context) {
  const result = await apiJson(context, "GET", `${BASE_URL}/api/page-ai/agents/descriptors?profile=task538-knowledge-rag`);
  assert(result.ok, `descriptor API 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  const reasonix = (result.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 status(context) {
  const params = new URLSearchParams({ rootUri: ROOT_URI, workspaceId: WORKSPACE_ID });
  const result = await apiJson(context, "GET", `${BASE_URL}/api/knowledge-rag/status?${params.toString()}`);
  assert(result.ok, `knowledge-rag status 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

function entryFor(statusPayload, sourcePath) {
  const entries = statusPayload?.registry?.entries;
  return Array.isArray(entries) ? entries.find((entry) => entry.sourceRootRelativePath === sourcePath) : null;
}

async function waitForIndexed(context, sourcePaths) {
  const startedAt = Date.now();
  let lastStatus = null;
  while (Date.now() - startedAt < POLL_TIMEOUT_MS) {
    lastStatus = await status(context);
    const allIndexed = sourcePaths.every((sourcePath) => {
      const entry = entryFor(lastStatus, sourcePath);
      return entry && entry.indexedAtMs && entry.lightRagDocId && !entry.stale && !entry.deletedAtMs;
    });
    if (allIndexed) return lastStatus;
    await sleep(5_000);
  }
  throw new Error(`等待 source scope fixture 入库超时: ${JSON.stringify({ sourcePaths, lastStatus }, null, 2).slice(0, 4000)}`);
}

async function ingest(context, sourcePaths) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/ingest`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    sources: sourcePaths.map((sourcePath) => ({ sourcePath })),
  });
  assert(result.ok, `knowledge-rag ingest 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

async function query(context, queryText, sourcePaths) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/query`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    query: queryText,
    mode: "mix",
    topK: 12,
    chunkTopK: 12,
    includeChunkContent: true,
    sourcePaths,
  });
  assert(result.ok, `knowledge-rag query 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

async function search(context, queryText, sourcePaths) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/search`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    query: queryText,
    mode: "mix",
    topK: 12,
    chunkTopK: 12,
    includeChunkContent: true,
    sourcePaths,
  });
  assert(result.ok, `knowledge-rag search 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

async function deleteSource(context, sourcePath) {
  const result = await apiJson(context, "POST", `${BASE_URL}/api/knowledge-rag/delete-source`, {
    rootUri: ROOT_URI,
    workspaceId: WORKSPACE_ID,
    sourcePath,
  });
  assert(result.ok, `knowledge-rag delete-source 失败: ${result.status} ${result.text.slice(0, 1000)}`);
  return result.payload;
}

async function main() {
  fs.mkdirSync(OUTPUT_DIR, { recursive: true });
  fs.mkdirSync(path.join(ROOT_PATH, FIXTURE_DIR), { recursive: true });
  const marker = `SOURCE SCOPE API RAG ${Date.now()}`;
  const sourceA = `${FIXTURE_DIR}/scope-api-alpha-${Date.now()}.md`;
  const sourceB = `${FIXTURE_DIR}/scope-api-beta-${Date.now()}.md`;
  fs.writeFileSync(path.join(ROOT_PATH, sourceA), `# Scope API Alpha\n${marker}\nOnly alpha source should remain after API scope filter.\n`, "utf8");
  fs.writeFileSync(path.join(ROOT_PATH, sourceB), `# Scope API Beta\n${marker}\nBeta source must be filtered when sourcePaths targets alpha.\n`, "utf8");

  const context = await request.newContext({ baseURL: BASE_URL });
  try {
    await signIn(context);
    await assertKnowledgeRagDescriptor(context);
    await ingest(context, [sourceA, sourceB]);
    const indexedStatus = await waitForIndexed(context, [sourceA, sourceB]);
    const scoped = await query(context, marker, [sourceA]);
    const references = Array.isArray(scoped.references) ? scoped.references : [];
    assert.equal(scoped.sourceScopeMode, "post_filter_mapped_references", `sourceScopeMode 不正确: ${JSON.stringify(scoped, null, 2).slice(0, 3000)}`);
    assert.equal(scoped.rawScopeFiltered, false, `rawScopeFiltered 应为 false: ${JSON.stringify(scoped, null, 2).slice(0, 3000)}`);
    assert(references.length > 0, `sourcePaths scope 应至少返回 alpha: ${JSON.stringify(scoped, null, 2).slice(0, 3000)}`);
    assert(
      references.every((reference) => reference.sourceRootRelativePath === sourceA),
      `sourcePaths scope 不应返回非 alpha 来源: ${JSON.stringify(references, null, 2).slice(0, 3000)}`,
    );
    assert(scoped.raw, "HTTP API 仍应保留 raw 供调试调用方使用");
    const searched = await search(context, marker, [sourceA]);
    const searchResults = Array.isArray(searched.results) ? searched.results : [];
    assert.equal(searched.schema, "mnote.knowledge_rag.search_results.v1", `search schema 不正确: ${JSON.stringify(searched, null, 2).slice(0, 3000)}`);
    assert.equal(searched.sourceScopeMode, "post_filter_mapped_references", `search sourceScopeMode 不正确: ${JSON.stringify(searched, null, 2).slice(0, 3000)}`);
    assert(searchResults.length > 0, `资料库 search 应至少返回 alpha: ${JSON.stringify(searched, null, 2).slice(0, 3000)}`);
    assert(
      searchResults.every((item) => item.provider === "lightrag" && item.matchSource === "lightrag_reference"),
      `资料库 search 结果必须来自 LightRAG references: ${JSON.stringify(searchResults, null, 2).slice(0, 3000)}`,
    );
    assert(
      searchResults.every((item) => item.path === sourceA),
      `资料库 search sourcePaths scope 不应返回非 alpha 来源: ${JSON.stringify(searchResults, null, 2).slice(0, 3000)}`,
    );
    assert(
      searchResults.some((item) => item.citationUrl || item.locator || item.openAction),
      `资料库 search 结果必须可打开来源: ${JSON.stringify(searchResults, null, 2).slice(0, 3000)}`,
    );

    await deleteSource(context, sourceA);
    assert(fs.existsSync(path.join(ROOT_PATH, sourceA)), "delete-source 不应删除用户原始 source 文件");
    const afterDelete = await query(context, marker, [sourceA]);
    const afterReferences = Array.isArray(afterDelete.references) ? afterDelete.references : [];
    assert.equal(afterReferences.length, 0, `删除索引后 source-scoped query 不应继续返回 alpha: ${JSON.stringify(afterReferences, null, 2)}`);

    const result = {
      ok: true,
      baseUrl: BASE_URL,
      rootUri: ROOT_URI,
      workspaceId: WORKSPACE_ID,
      marker,
      sourceA,
      sourceB,
      sourceScopeMode: scoped.sourceScopeMode,
      rawScopeFiltered: scoped.rawScopeFiltered,
      scopedReferenceCount: references.length,
      searchResultCount: searchResults.length,
      alphaDocId: entryFor(indexedStatus, sourceA)?.lightRagDocId || null,
      betaDocId: entryFor(indexedStatus, sourceB)?.lightRagDocId || null,
      sourceAExistsAfterDelete: fs.existsSync(path.join(ROOT_PATH, sourceA)),
      afterDeleteReferenceCount: afterReferences.length,
    };
    fs.writeFileSync(RESULT_PATH, `${JSON.stringify(result, null, 2)}\n`, "utf8");
    console.log(JSON.stringify(result, null, 2));
  } finally {
    await context.dispose().catch(() => undefined);
  }
}

main().catch((error) => {
  fs.mkdirSync(OUTPUT_DIR, { recursive: true });
  fs.writeFileSync(
    path.join(OUTPUT_DIR, "failure.json"),
    `${JSON.stringify({ ok: false, error: error.stack || error.message || String(error) }, null, 2)}\n`,
    "utf8",
  );
  console.error(error.stack || error.message || String(error));
  process.exit(1);
});