feat: add evidence search and stabilize pdf previews

- add document evidence parsing/search/open routes, Hermes tool wiring, local index settings/status, and the document-evidence skill plus design notes - fix PDF resource tabs by rendering PDFs inline with pdf.js canvases instead of iframe preview pages, release PDF documents on close, and document the fourth-PDF stall bug - keep PDF preview at 2x rendering while removing the previous lazy-load/placeholder direction, and make dev:hot bind loopback defaults externally reachable Verification: - node --check rust/crates/mnote-web/browser/document-resource-tab-runtime.js - node scripts/task-dev-hot-plan-test.js - cargo test -p mnote-web --manifest-path rust/Cargo.toml pdf_preview_page_does_not_render_visible_toolbar - cargo test -p mnote-web --manifest-path rust/Cargo.toml document_shell_returns_page_aggregate_snapshot - cargo build -p mnote-web --manifest-path rust/Cargo.toml - browser smoke: sequentially opened the four tea_seed_oil_cosmetic PDFs; fourth PDF rendered 15/15 canvases, iframeCount=0, browser errors=0
2026-06-04 18:51:16 +08:00
parent 9f4b5c4d48
commit 627213dc01
51 changed files with 15960 additions and 1844 deletions
@@ -0,0 +1,362 @@
+#!/usr/bin/env node
+"use strict";
+
+const assert = require("node:assert");
+const fs = require("node:fs");
+const os = require("node:os");
+const path = require("node:path");
+const { execFileSync } = require("node:child_process");
+
+const BASE_URL = (process.env.MNOTE_UI_BASE_URL || "http://127.0.0.1:3000").replace(/\/+$/, "");
+const OUTPUT_DIR = path.join(process.cwd(), "tmp", "task528-document-evidence-liteparse-agent-smoke");
+const RESULT_PATH = path.join(OUTPUT_DIR, "result.json");
+const ACTOR_ID = "mnote-e2e";
+const TEST_PASSWORD = process.env.MNOTE_E2E_PASSWORD || "MnoteE2E123!";
+const RUN_REASONIX_ACP = process.env.MNOTE_TASK528_SKIP_REASONIX_ACP !== "1";
+
+function fileUrl(localPath) {
+  return `file://${localPath}`;
+}
+
+function localMdDocumentId(relativePath) {
+  return `local-md:${relativePath}`;
+}
+
+async function fetchJson(pathname, init = {}) {
+  const response = await fetch(`${BASE_URL}${pathname}`, init);
+  const text = await response.text();
+  let payload = null;
+  try {
+    payload = text ? JSON.parse(text) : null;
+  } catch {
+    payload = text;
+  }
+  assert(
+    response.ok,
+    `${pathname} 请求失败: ${response.status} ${typeof payload === "string" ? payload : JSON.stringify(payload)}`,
+  );
+  return { payload, response };
+}
+
+async function postJson(pathname, data, headers = {}) {
+  return (await fetchJson(pathname, {
+    method: "POST",
+    headers: { "content-type": "application/json", ...headers },
+    body: JSON.stringify(data),
+  })).payload;
+}
+
+async function getText(pathname, headers = {}, timeoutMs = 180_000) {
+  const controller = new AbortController();
+  const timer = setTimeout(() => controller.abort(), timeoutMs);
+  try {
+    const response = await fetch(`${BASE_URL}${pathname}`, {
+      method: "GET",
+      headers,
+      signal: controller.signal,
+    });
+    const text = await response.text();
+    assert(response.ok, `${pathname} 请求失败: ${response.status} ${text.slice(0, 500)}`);
+    return text;
+  } finally {
+    clearTimeout(timer);
+  }
+}
+
+async function signInCookie() {
+  const { response } = await fetchJson("/api/auth", {
+    method: "POST",
+    headers: { "content-type": "application/json" },
+    body: JSON.stringify({
+      action: "auth:signIn",
+      args: {
+        provider: "password",
+        params: {
+          account: ACTOR_ID,
+          password: TEST_PASSWORD,
+          flow: "signIn",
+        },
+      },
+    }),
+  });
+  const setCookie = response.headers.get("set-cookie") || "";
+  const session = setCookie.match(/mnote_session=[^;]+/u)?.[0];
+  assert(session, `登录响应缺少 mnote_session cookie: ${setCookie}`);
+  return session;
+}
+
+async function createAiGrant(rootUri) {
+  const payload = await postJson("/api/admin/access-policy/grants", {
+    userId: ACTOR_ID,
+    rootUri,
+    permission: "write",
+    recursive: true,
+    capabilities: ["ai"],
+  }, {
+    "x-mnote-actor-id": ACTOR_ID,
+    "x-mnote-actor-type": "admin",
+  });
+  assert(payload.grant?.id, "创建 AI 目录授权后缺少 grant id");
+  return payload.grant;
+}
+
+function assertEvidenceHit(hit, expected) {
+  assert(hit, `${expected.label} 缺少正文级 PDF evidence 命中`);
+  assert(String(hit.quote || "").includes("Printer test page"), `${expected.label} quote 不包含 PDF 正文 token`);
+  assert.strictEqual(hit.source?.ownerDocumentPath, expected.ownerRel, `${expected.label} ownerDocumentPath`);
+  assert.strictEqual(hit.source?.resourcePath, expected.pdfRel, `${expected.label} resourcePath`);
+  assert.strictEqual(hit.source?.resourceKind, "pdf", `${expected.label} resourceKind`);
+  assert(hit.source?.page, `${expected.label} 缺少 page locator`);
+  assert(hit.source?.bbox, `${expected.label} 缺少 bbox locator`);
+  assert(hit.source?.sourceMapPath, `${expected.label} 缺少 sourceMapPath`);
+}
+
+function decodeSseToolPayloads(sse) {
+  return String(sse || "")
+    .split(/\n\n+/u)
+    .map((eventText) => {
+      const eventName = eventText
+        .split(/\n/u)
+        .find((line) => line.startsWith("event:"))
+        ?.slice("event:".length)
+        .trim();
+      const dataLines = eventText
+        .split(/\n/u)
+        .filter((line) => line.startsWith("data:"))
+        .map((line) => line.slice("data:".length).trimStart());
+      if (!dataLines.length) return null;
+      try {
+        return { event: eventName || null, payload: JSON.parse(dataLines.join("\n")) };
+      } catch {
+        return null;
+      }
+    })
+    .filter(Boolean);
+}
+
+function assertReasonixAcpEvidenceSse(sse) {
+  assert(sse.includes('"tool":"mnote_evidence_search"'), "Reasonix ACP SSE 未出现 mnote_evidence_search 工具调用");
+  assert(sse.includes("event: tool.completed"), "Reasonix ACP evidence 工具未标记为 completed");
+  assert(!sse.includes("event: tool.failed"), "Reasonix ACP evidence 工具被错误标记为 failed");
+  const payloads = decodeSseToolPayloads(sse);
+  const completedTool = payloads.find(({ event, payload }) =>
+    event === "tool.completed" && payload?.status === "completed"
+  );
+  assert(completedTool, "Reasonix ACP SSE 缺少 completed evidence tool payload");
+  const outputText = (completedTool.payload.output || [])
+    .map((item) => item?.content?.text || "")
+    .join("\n");
+  assert(outputText.includes('"quote":"Printer test page"'), "Reasonix ACP 工具结果未返回 PDF 正文 quote");
+  assert(outputText.includes('"page":1'), "Reasonix ACP 工具结果未返回 page locator");
+  assert(outputText.includes("mnote.agent_run_receipt.evidence.v1"), "Reasonix ACP 工具结果缺少 evidence run receipt");
+}
+
+async function runReasonixAcpEvidenceCheck(input) {
+  const { workspaceId, rootUri, documentId, actorHeaders } = input;
+  await createAiGrant(rootUri);
+  const sessionId = `task528_reasonix_tools_${Date.now().toString(36)}`;
+  const traceId = `task528-reasonix-tools-${Date.now().toString(36)}`;
+  const run = await postJson("/api/hermes/client/runs", {
+    workspaceId,
+    documentId,
+    sessionId,
+    sourceKind: "local_folder",
+    rootUri,
+    agentId: "reasonix",
+    profile: "reasonix",
+    acpRuntime: "reasonix",
+    contextScope: "page",
+    contextRefs: ["current_page", "folder"],
+    allowedRoots: [{ rootUri, permission: "write" }],
+    skillPreferences: {
+      mnote: {
+        "mnote-document-evidence": true,
+        "mnote-chat-only": false,
+      },
+    },
+    message: "请调用 mnote_evidence_search 搜索 Printer test page，然后用一句中文回答页码和 quote。必须使用工具，不能只说正在搜索。",
+    traceId,
+    pageContext: {
+      contextScope: "page",
+      node: { documentId, title: "EvidenceLive" },
+      aiContext: {
+        schema: "mnote.page_ai_context.v1",
+        workspaceId,
+        documentId,
+        scope: "page",
+        selectedText: "",
+        selectedBlockIds: [],
+        contextBlocks: [],
+        pageText: "",
+        pageXml: `<page id=\"${documentId}\"></page>`,
+        truncated: false,
+        warnings: [],
+      },
+    },
+  }, actorHeaders);
+  assert(run.ok === true && run.runId, `Reasonix ACP run 创建失败: ${JSON.stringify(run)}`);
+
+  const sse = await getText(`/api/hermes/client/events/${encodeURIComponent(run.runId)}`, actorHeaders);
+  fs.writeFileSync(path.join(OUTPUT_DIR, "reasonix-tools-events.sse"), sse, "utf8");
+  assertReasonixAcpEvidenceSse(sse);
+  fs.writeFileSync(path.join(OUTPUT_DIR, "reasonix-live-run.json"), `${JSON.stringify(run, null, 2)}\n`, "utf8");
+  return {
+    runId: run.runId,
+    sessionId: run.sessionId,
+    eventPath: path.join(OUTPUT_DIR, "reasonix-tools-events.sse"),
+  };
+}
+
+async function main() {
+  fs.mkdirSync(OUTPUT_DIR, { recursive: true });
+  const root = fs.mkdtempSync(path.join(os.tmpdir(), "mnote-evidence-live-"));
+  const workspaceId = `local-ws:${ACTOR_ID}:task528-evidence`;
+  const rootUri = fileUrl(root);
+  const ownerRel = "EvidenceLive.md";
+  const pdfRel = "assets/default-testpage.pdf";
+  const documentId = localMdDocumentId(ownerRel);
+  const actorHeaders = {
+    "x-mnote-actor-id": ACTOR_ID,
+    "x-mnote-actor-type": "user",
+    "x-mnote-workspace-id": workspaceId,
+  };
+
+  fs.mkdirSync(path.join(root, ".mnote"), { recursive: true });
+  fs.mkdirSync(path.join(root, "assets"), { recursive: true });
+  fs.writeFileSync(
+    path.join(root, ".mnote", "workspace.json"),
+    `${JSON.stringify({
+      workspaceId,
+      ownerId: ACTOR_ID,
+      createdAt: new Date().toISOString(),
+      capabilities: ["local_files", "ai_sessions", "markdown_edit"],
+    }, null, 2)}\n`,
+    "utf8",
+  );
+  fs.copyFileSync("/usr/share/cups/data/default-testpage.pdf", path.join(root, pdfRel));
+  fs.writeFileSync(
+    path.join(root, ownerRel),
+    ["# Evidence Live", "", "测试正文级 PDF evidence。", "", `[Printer PDF](${pdfRel})`, ""].join("\n"),
+    "utf8",
+  );
+
+  const cookie = await signInCookie();
+  const toolsPayload = (await fetchJson("/api/hermes/client/tools?scope=mnote&profile=reasonix", {
+    headers: { cookie },
+  })).payload;
+  const toolNames = (toolsPayload.tools || []).map((tool) => tool.name);
+  for (const name of ["mnote.evidence.search", "mnote.evidence.read", "mnote.evidence.open"]) {
+    assert(toolNames.includes(name), `Reasonix tools 列表缺少 ${name}`);
+  }
+  const skillsPayload = (await fetchJson("/api/hermes/client/skills?runtime=mnote&agentId=reasonix", {
+    headers: { cookie },
+  })).payload;
+  const mnoteSkills = (skillsPayload.categories || []).flatMap((category) => category.skills || []);
+  assert(
+    mnoteSkills.some((skill) => skill.id === "mnote-document-evidence" && skill.enabled !== false),
+    "Reasonix agent 缺少启用的 mnote-document-evidence skill",
+  );
+
+  const refresh = await postJson("/api/search/local-index/refresh", { workspaceId, rootUri }, actorHeaders);
+  assert.strictEqual(refresh.ok, true, "local evidence index refresh ok");
+
+  const direct = await postJson("/api/evidence/search", {
+    query: "Printer test page",
+    scope: { workspaceId, rootUri, includeResources: true, includeOcr: true },
+    mode: "hybrid",
+    topK: 5,
+  }, actorHeaders);
+  const directHit = (direct.results || []).find((result) => String(result.quote || "").includes("Printer test page"));
+  assertEvidenceHit(directHit, { label: "direct", ownerRel, pdfRel });
+
+  const read = await postJson("/api/evidence/read", {
+    locator: directHit.source,
+    context: { beforeBlocks: 1, afterBlocks: 1, includeSectionSummary: true },
+  }, actorHeaders);
+  assert.strictEqual(read.ok, true, "evidence read ok");
+  assert(String(read.quote || "").includes("Printer test page"), "evidence read 未读回 PDF 正文 quote");
+
+  const open = await postJson("/api/evidence/open", { locator: directHit.source }, actorHeaders);
+  assert.strictEqual(open.ok, true, "evidence open ok");
+  assert(open.openAction?.params?.sourceMapPath, "evidence open 缺少 sourceMapPath params");
+
+  const toolEnvelope = await postJson("/api/hermes/tools/mnote/call", {
+    toolName: "mnote.evidence.search",
+    workspaceId,
+    documentId,
+    sourceKind: "local_folder",
+    rootUri,
+    actorId: ACTOR_ID,
+    profile: "reasonix",
+    sessionId: "task528_evidence_session",
+    runId: "task528_evidence_run",
+    toolCallId: "task528_evidence_tool_call",
+    args: { query: "Printer test page", includeResources: true, includeOcr: true, topK: 5 },
+  }, actorHeaders);
+  assert.strictEqual(toolEnvelope.ok, true, "MNote evidence tool envelope ok");
+  const toolResult = toolEnvelope.result || toolEnvelope;
+  const toolHit = (toolResult.results || []).find((result) => String(result.quote || "").includes("Printer test page"));
+  assertEvidenceHit(toolHit, { label: "agent-tool", ownerRel, pdfRel });
+  assert((toolEnvelope.audit?.evidenceIds || []).includes(toolHit.evidenceId), "agent tool audit 缺少 evidence id");
+  assert.strictEqual(toolEnvelope.audit?.runReceipt?.toolName, "mnote.evidence.search", "run receipt toolName");
+
+  const reasonixAcp = RUN_REASONIX_ACP
+    ? await runReasonixAcpEvidenceCheck({ workspaceId, rootUri, documentId, actorHeaders })
+    : { skipped: true };
+
+  execFileSync(process.execPath, ["scripts/reasonix-acp-wrapper.mjs"], {
+    cwd: process.cwd(),
+    env: { ...process.env, MNOTE_REASONIX_ACP_SELFTEST: "1" },
+    stdio: ["ignore", "pipe", "pipe"],
+  });
+
+  const parseMd = path.join(root, "EvidenceLive.ocr", "default-testpage.pdf.parse.md");
+  const sourceMap = path.join(root, "EvidenceLive.ocr", "default-testpage.pdf.source-map.json");
+  const sqlitePath = path.join(root, ".mnote", "index", "evidence.sqlite");
+  assert(fs.existsSync(parseMd), `缺少 LiteParse parse sidecar: ${parseMd}`);
+  assert(fs.existsSync(sourceMap), `缺少 source-map sidecar: ${sourceMap}`);
+  assert(fs.existsSync(sqlitePath), `缺少 evidence sqlite: ${sqlitePath}`);
+  const ftsCount = Number(execFileSync(
+    "sqlite3",
+    [sqlitePath, "SELECT count(*) FROM evidence_fts WHERE evidence_fts MATCH 'Printer';"],
+    { encoding: "utf8" },
+  ).trim());
+  assert(ftsCount >= 1, `evidence.sqlite FTS 未命中 PDF 正文: ${ftsCount}`);
+
+  const result = {
+    ok: true,
+    baseUrl: BASE_URL,
+    root,
+    workspaceId,
+    documentId,
+    directEvidenceId: directHit.evidenceId,
+    toolEvidenceId: toolHit.evidenceId,
+    quote: directHit.quote,
+    page: directHit.source.page,
+    bbox: directHit.source.bbox,
+    ownerDocumentPath: directHit.source.ownerDocumentPath,
+    resourcePath: directHit.source.resourcePath,
+    sourceMapPath: directHit.source.sourceMapPath,
+    parseMd,
+    sourceMap,
+    sqlitePath,
+    ftsCount,
+    reasonixTools: toolNames.filter((name) => name.startsWith("mnote.evidence.")),
+    evidenceSkillEnabled: true,
+    receiptToolName: toolEnvelope.audit.runReceipt.toolName,
+    reasonixAcp,
+  };
+  fs.writeFileSync(RESULT_PATH, `${JSON.stringify(result, null, 2)}\n`, "utf8");
+  console.log(JSON.stringify(result, null, 2));
+}
+
+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);
+});