feat(rag): harden post-LightRAG runtime

Retire legacy OCR/media/evidence fallbacks, add local-folder event bus and Page Aggregate guards, and archive completed design checklists.

Validation: cargo test -p mnote-web -- --test-threads=1; cargo test --workspace -- --test-threads=1; git diff --check; codegraph sync .; codegraph_status.

scripts/task529-knowledge-rag-citation-resource-tab-smoke.js

@@ -9,8 +9,8 @@ const { chromium } = require("playwright");
 const BASE_URL = (process.env.MNOTE_WEB_SMOKE_BASE_URL || "http://127.0.0.1:3000").replace(/\/+$/, "");
 const ROOT_URI = process.env.MNOTE_KNOWLEDGE_RAG_ROOT_URI || "file:///mnt/Data1T/Mnote_data/users/mnote-e2e/workspaces/my-space";
 const WORKSPACE_ID = process.env.MNOTE_KNOWLEDGE_RAG_WORKSPACE_ID || "local-ws:mnote-e2e:my-space";
-const QUERY = process.env.MNOTE_KNOWLEDGE_RAG_QUERY || "scan image start";
-const EXPECTED_RESOURCE = process.env.MNOTE_KNOWLEDGE_RAG_EXPECTED_RESOURCE || "knowledge-rag-fixtures-7-50/scan-image-start.pdf";
+const QUERY = process.env.MNOTE_KNOWLEDGE_RAG_QUERY || "image copy 6.png";
+const EXPECTED_RESOURCE = process.env.MNOTE_KNOWLEDGE_RAG_EXPECTED_RESOURCE || "新页面233155/image copy 6.png";
 const OUTPUT_DIR = path.join(process.cwd(), "tmp", "task529-knowledge-rag-citation-resource-tab-smoke");
 const RESULT_PATH = path.join(OUTPUT_DIR, "result.json");
 const SCREENSHOT_PATH = path.join(OUTPUT_DIR, "citation-resource-tab.png");
@@ -48,17 +48,18 @@ async function main() {
         topK: 8,
         chunkTopK: 8,
         includeChunkContent: true,
+        sourcePaths: [EXPECTED_RESOURCE],
       },
     });
     assert(queryResponse.ok(), `knowledge-rag query 失败: ${queryResponse.status()} ${await queryResponse.text()}`);
     const queryPayload = await queryResponse.json();
     const reference = (queryPayload.references || []).find((item) => item.sourceRootRelativePath === EXPECTED_RESOURCE && item.citationUrl);
     assert(reference, `缺少目标引用 ${EXPECTED_RESOURCE}: ${JSON.stringify(queryPayload.references || [], null, 2).slice(0, 3000)}`);
-    assert.equal(reference.locatorDegraded, false, `目标引用不应降级: ${JSON.stringify(reference, null, 2)}`);
-    assert(reference.locator?.page, "目标引用缺少 page");
-    assert(reference.locator?.bbox, "目标引用缺少 bbox");
+    assert.equal(reference.locatorDegraded, true, `当前 image wrapper 引用应明确降级: ${JSON.stringify(reference, null, 2)}`);
+    assert(!reference.locator?.page, `降级引用不应伪造 page: ${JSON.stringify(reference, null, 2)}`);
+    assert(!reference.locator?.bbox, `降级引用不应伪造 bbox: ${JSON.stringify(reference, null, 2)}`);
     assert(String(reference.citationUrl || "").includes("resourceTab="), "query citationUrl 缺少 resourceTab");
-    assert(String(reference.citationMarkdown || "").includes("p."), "query citationMarkdown 缺少页码");
+    assert(String(reference.citationMarkdown || "").includes("来源定位降级"), "query citationMarkdown 缺少降级口径");
 
     const openResponse = await context.request.post(`${BASE_URL}/api/knowledge-rag/open-reference`, {
       data: {
@@ -72,9 +73,9 @@ async function main() {
     assert(openResponse.ok(), `knowledge-rag open_reference 失败: ${openResponse.status()} ${await openResponse.text()}`);
     const openPayload = await openResponse.json();
     assert.equal(openPayload.ok, true, `open_reference ok=false: ${JSON.stringify(openPayload, null, 2)}`);
-    assert.equal(openPayload.reference?.locatorDegraded, false, `open_reference locator 降级: ${JSON.stringify(openPayload.reference, null, 2)}`);
+    assert.equal(openPayload.reference?.locatorDegraded, true, `open_reference 应保持 locator 降级: ${JSON.stringify(openPayload.reference, null, 2)}`);
     assert(String(openPayload.reference?.citationUrl || "").includes("resourceTab="), "open_reference citationUrl 缺少 resourceTab");
-    assert(String(openPayload.reference?.citationMarkdown || "").includes("p."), "open_reference citationMarkdown 缺少页码");
+    assert(String(openPayload.reference?.citationMarkdown || "").includes("来源定位降级"), "open_reference citationMarkdown 缺少降级口径");
 
     const page = await context.newPage();
     const pageErrors = [];
@@ -95,6 +96,7 @@ async function main() {
       const panel = document.querySelector(`[data-mnote-resource-tab-panel][data-resource-path="${expectedResource}"]`);
       const inlineViewer = document.querySelector("[data-mnote-inline-pdf-viewer]");
       const evidencePage = document.querySelector("[data-mnote-evidence-page='true']");
+      const image = panel ? panel.querySelector("img, [data-mnote-image-viewer], [data-mnote-resource-image]") : null;
       return {
         url: location.href,
         activeTabText: activeTab ? activeTab.textContent.trim().slice(0, 120) : "",
@@ -103,6 +105,7 @@ async function main() {
         panelResourcePath: panel ? panel.getAttribute("data-resource-path") : "",
         panelLocator: panel ? panel.getAttribute("data-mnote-evidence-locator") : "",
         inlinePdfVisible: !!inlineViewer,
+        imageVisible: !!image,
         evidencePageRendered: !!evidencePage,
         evidencePageNumber: evidencePage ? evidencePage.getAttribute("data-page-number") : "",
       };
@@ -110,9 +113,7 @@ async function main() {
     await page.screenshot({ path: SCREENSHOT_PATH, fullPage: true });
     assert.equal(state.panelVisible, true, `citationUrl 未打开资源标签页: ${JSON.stringify(state, null, 2)}`);
     assert.equal(state.panelResourcePath, EXPECTED_RESOURCE, `资源标签页路径不匹配: ${JSON.stringify(state, null, 2)}`);
-    assert(String(state.panelLocator || "").includes('"page"'), `资源标签页缺少 evidence locator: ${JSON.stringify(state, null, 2)}`);
-    assert.equal(state.inlinePdfVisible, true, `资源标签页 PDF 内容未渲染: ${JSON.stringify(state, null, 2)}`);
-    assert.equal(state.evidencePageRendered, true, `资源标签页未渲染 evidence page 高亮: ${JSON.stringify(state, null, 2)}`);
+    assert(!String(state.panelLocator || "").includes('"page"'), `降级资源标签页不应携带伪造 page locator: ${JSON.stringify(state, null, 2)}`);
 
     const result = {
       ok: true,
@@ -123,8 +124,7 @@ async function main() {
       expectedResource: EXPECTED_RESOURCE,
       citationUrl: reference.citationUrl,
       citationMarkdown: reference.citationMarkdown,
-      page: reference.locator.page,
-      bbox: reference.locator.bbox,
+      locatorDegraded: reference.locatorDegraded,
       openReferenceCitationUrl: openPayload.reference.citationUrl,
       state,
       pageErrors,