Merge pull request 'fix(converter+schema): эмфаза при инлайн-коде не теряется — снять excludes у code (#515)' (#519) from fix/515-code-emphasis into feat/493-converter

Reviewed-on: #519

CHANGELOG.md

@@ -129,6 +129,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- **A drifted comment suggestion can be re-synced instead of failing forever
+  with a 409.** A suggestion whose stored anchor no longer matched the live
+  document used to reject every apply attempt with an unrecoverable conflict; a
+  new resync path re-reads the live anchor so the suggestion applies against the
+  current text, and orphaned anchors (whose marked run was deleted) are
+  reconciled rather than left blocking. (#496)
+
 - **Place several images side by side in a row.** A new "Inline (side by
   side)" alignment mode in the image bubble menu renders consecutive inline
   images as a row that wraps onto the next line on narrow screens. The row is
@@ -352,7 +359,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   body-timeout so a legitimate >1-min idle between the model's tool calls no
   longer breaks a long-lived SSE socket (new `AI_MCP_SSE_BODY_TIMEOUT_MS`, default
   10 min; see `.env.example`). (#489)
-
+- **Decisions on comment suggestions now leave a durable audit record.**
+  Applying or dismissing a comment suggestion hard-deletes the (childless)
+  subject comment, so the only surviving trace of who decided what is the audit
+  event — but the audit trail was wired to a Noop service that silently
+  swallowed every event. The trail is now DB-backed, so
+  `comment.suggestion_applied` / `comment.suggestion_dismissed` (and the other
+  comment-decision events) persist to the `audit` table and can be reviewed
+  after the comment is gone. A persistence failure is still swallowed with a
+  warning so it never breaks the originating request. (#496)
+- **Applying a comment suggestion no longer strips the replaced run's inline
+  formatting.** The suggested text was re-inserted carrying only the comment
+  anchor mark, silently dropping bold/italic/code/link on the affected run; the
+  prevailing formatting of the replaced run is now carried onto the applied
+  text. (#496)
+- **Markdown round-trips no longer silently drop a line that opens with a block
+  trigger.** When a document is exported to Markdown and re-imported (git-sync
+  stabilize, agent writes), a paragraph or continuation line (after a hard break)
+  that begins with a block marker — an ATX heading `#`, a blockquote/callout `>`,
+  a list marker (`-`/`*`/`+`/`N.`/`N)`), a code fence, a table `|`, a thematic
+  break (`---`), or a setext underline (`--`, `----`, or a lone `=`) — is now
+  backslash-escaped so it round-trips as text instead of being re-parsed into a
+  heading/list/quote/rule and losing its content. Front-matter stripping is
+  scoped to the import path only. (#493)
 - **The server no longer runs out of heap during long autonomous agent runs.** A
   new pnpm patch on `ai@6.0.134` stops the SDK from building a cumulative
   snapshot of the ENTIRE turn text on every streamed text-delta when no output

apps/client/src/features/comment/components/comment-editor.tsx

@@ -1,7 +1,7 @@
 import { EditorContent, ReactNodeViewRenderer, useEditor } from "@tiptap/react";
 import { Placeholder } from "@tiptap/extension-placeholder";
 import { StarterKit } from "@tiptap/starter-kit";
-import { Mention, LinkExtension } from "@docmost/editor-ext";
+import { Mention, LinkExtension, Code } from "@docmost/editor-ext";
 import classes from "./comment.module.css";
 import { useFocusWithin } from "@mantine/hooks";
 import clsx from "clsx";
@@ -44,7 +44,12 @@ const CommentEditor = forwardRef(
           gapcursor: false,
           dropcursor: false,
           link: false,
+          // #515: use the shared editor-ext `Code` (excludes: "") instead of
+          // StarterKit's excluding one, so inline code in a comment can carry
+          // other marks and does not drop them when the comment is edited.
+          code: false,
         }),
+        Code,
         Placeholder.configure({
           placeholder: placeholder || t("Reply..."),
         }),

apps/client/src/features/editor/extensions/extensions.ts

@@ -1,6 +1,5 @@
 import { markInputRule } from "@tiptap/core";
 import { StarterKit } from "@tiptap/starter-kit";
-import { Code } from "@tiptap/extension-code";
 import { TextAlign } from "@tiptap/extension-text-align";
 import { TaskList, TaskItem } from "@tiptap/extension-list";
 import { Placeholder, CharacterCount, UndoRedo } from "@tiptap/extensions";
@@ -67,6 +66,7 @@ import {
   FootnoteReference,
   FootnotesList,
   FootnoteDefinition,
+  Code,
 } from "@docmost/editor-ext";
 import {
   randomElement,
@@ -153,6 +153,10 @@ export const mainExtensions = [
     codeBlock: false,
     code: false,
   }),
+  // Base `Code` comes from @docmost/editor-ext, which overrides `excludes: ""`
+  // (#515) so inline code can co-occur with bold/italic/… — the SINGLE shared
+  // source also used by the collab server and comment editor. Here we keep the
+  // existing client-only behavior on top of it:
   // Override TipTap's Code extension to fix the inline code input rule.
   // The upstream regex /(^|[^`])`([^`]+)`(?!`)$/ captures the character
   // before the opening backtick as part of the match, causing markInputRule

apps/client/src/features/editor/gitmost/gitmost-recording.test.ts

@@ -9,7 +9,7 @@ import { Italic } from "@tiptap/extension-italic";
 import { Link } from "@tiptap/extension-link";
 import { gitmostInsertTranscriptIntoEditor } from "./gitmost-recording.ts";
 
-const ZWSP = "​"; // U+200B, the helper's block-trigger neutralizer
+const ZWSP = "​"; // U+200B — asserted ABSENT (the block-escape lives in the serializer now)
 
 /**
  * #377 — the web-side bridge must append the native host's transcript below the
@@ -18,8 +18,9 @@ const ZWSP = "​"; // U+200B, the helper's block-trigger neutralizer
  * regression would be caught), asserting the resulting document rather than
  * mocking the editor: transcript present -> "Transcript" heading + one paragraph
  * per non-empty line; content is inserted as LITERAL TEXT (no HTML/markdown
- * parsing); col-0 markdown block triggers are neutralized so git-sync keeps them
- * paragraphs; absent/empty/non-string -> no-op.
+ * parsing); col-0 markdown block triggers are stored verbatim (the git-sync
+ * serializer block-escapes them, so no client-side ZWSP is needed);
+ * absent/empty/non-string -> no-op.
  */
 describe("gitmostInsertTranscriptIntoEditor", () => {
   const makeEditor = () =>
@@ -91,19 +92,22 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
     editor.destroy();
   });
 
-  it("neutralizes col-0 markdown block triggers with a leading ZWSP (git-sync safety)", () => {
+  it("inserts col-0 markdown block triggers as verbatim paragraph text (no ZWSP workaround)", () => {
     const editor = makeEditor();
-    // Trigger lines (some with a leaked indent) + a normal prefixed line.
+    // Trigger lines (some with a leaked indent) + a normal prefixed line. The
+    // git-sync serializer now block-escapes a leading trigger itself, so the
+    // bridge inserts each line's TEXT byte-exact (only the leaked indent is
+    // trimmed) — no invisible ZWSP is prepended anymore.
     const inserted = gitmostInsertTranscriptIntoEditor(
       editor,
       [
         "- dash",
-        "  > quote", // leading indent must be trimmed then neutralized
+        "  > quote", // leading indent is trimmed, text otherwise verbatim
         "# hash",
         "1. one",
         "> [!info] note",
         "```js",
-        "---", // solid thematic break -> horizontalRule (text-losing) if unneutralized
+        "---",
         "***",
         "___",
         "You: normal line",
@@ -116,20 +120,23 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
       .map((n: any) => n.content?.[0]?.text)
       .filter((t: any) => typeof t === "string") as string[];
 
-    // Every block-trigger line is prefixed with the invisible ZWSP (indent
-    // trimmed first); the normal `You:` line is left byte-exact.
+    // Each trigger line is stored as its own byte-exact text (indent trimmed);
+    // the git-sync round-trip keeps it a paragraph via the serializer's
+    // block-escape, so no ZWSP is needed here.
     expect(texts).toEqual([
-      ZWSP + "- dash",
-      ZWSP + "> quote",
-      ZWSP + "# hash",
-      ZWSP + "1. one",
-      ZWSP + "> [!info] note",
-      ZWSP + "```js",
-      ZWSP + "---",
-      ZWSP + "***",
-      ZWSP + "___",
+      "- dash",
+      "> quote",
+      "# hash",
+      "1. one",
+      "> [!info] note",
+      "```js",
+      "---",
+      "***",
+      "___",
       "You: normal line",
     ]);
+    // Guard: no invisible ZWSP leaked into any inserted line.
+    for (const t of texts) expect(t).not.toContain(ZWSP);
 
     editor.destroy();
   });

apps/client/src/features/editor/gitmost/gitmost-recording.ts

@@ -240,45 +240,22 @@ export async function gitmostUploadFileToEditor(
   }
 }
 
-// Zero-width space (U+200B). Prepended to a transcript line that begins with a
-// markdown BLOCK trigger: it is invisible in the rendered doc but shifts the
-// trigger off column 0, so the git-sync doc->markdown->doc round-trip keeps the
-// line a plain paragraph (see GITMOST_MD_BLOCK_TRIGGER_RE).
-const GITMOST_ZWSP = "​";
-
-// A markdown BLOCK-level construct that, sitting at column 0 of a paragraph
-// line, the git-sync markdown serializer (packages/prosemirror-markdown
-// markdown-converter.ts, `case "paragraph"`) would re-parse into a NON-paragraph
-// block on the doc->markdown->doc cycle. That serializer emits paragraph text
-// verbatim with NO block-escape (the pre-existing root cause), so a leading
-// `#`/`-`/`*`/`+`/`>`, an ordered-list `N.`/`N)`, a code fence ```/~~~, a table
-// `|`, or a `> [!info]` callout opener would silently become a heading / list /
-// quote / code block / table / callout. The final alternative matches a WHOLE-
-// LINE thematic break — solid `---`/`***`/`___` or spaced `- - -`/`_ _ _` (3+ of
-// the same `-`/`*`/`_`) — which round-trips into a `horizontalRule`; because
-// that node carries NO text, an un-neutralized separator line would LOSE its
-// text entirely (worse than the list/quote case). This matches a TRIMMED line's
-// start; the transcript's own `You:` / `Speaker N:` prefix begins with a letter
-// and never matches, so prefixed lines are left byte-exact.
-const GITMOST_MD_BLOCK_TRIGGER_RE =
-  /^(?:#{1,6}(?:\s|$)|[-*+](?:\s|$)|>|\d+[.)](?:\s|$)|```|~~~|\||([-*_])(?:\s*\1){2,}\s*$)/;
-
 // Append a transcript block BELOW the recording's audio node in a live editor:
 // a "Transcript" heading followed by one paragraph per non-empty transcript
 // line. The transcript is plain text, `\n`-separated, each line already
 // formatted as `You: ...` / `Speaker N: ...` by the native host — line text is
 // inserted as a TEXT node (never HTML/markdown), so there is no injection or
 // mark-parsing surface. Each kept line is trimmed (drops an indent that would
-// both leak into the display and, at col 0, form a markdown block trigger) and,
-// if it still begins with a col-0 markdown block trigger, gets an invisible
-// zero-width space prepended so the git-sync round-trip cannot turn it into a
-// list/quote/heading/callout/code/table (defensive boundary against the
-// serializer's missing block-escape). This is best-effort and meant to run
-// AFTER the audio has already been inserted; the caller must guard against a
-// throw so a transcript failure never fails the (already successful) recording.
-// Returns true when a block was inserted, false when there was nothing to
-// insert (transcript undefined/empty/not-a-string). A non-string value is a
-// no-op, not an error.
+// leak into the display). A line that begins with a col-0 markdown block
+// trigger (`#`/`-`/`>`/`1.`/fence/`---`/…) needs no client-side workaround: the
+// git-sync serializer (packages/prosemirror-markdown, `case "paragraph"`) now
+// block-escapes such a leading trigger, so the doc->markdown->doc round-trip
+// keeps the line a paragraph on its own — the former invisible-ZWSP defense is
+// gone. This is best-effort and meant to run AFTER the audio has already been
+// inserted; the caller must guard against a throw so a transcript failure never
+// fails the (already successful) recording. Returns true when a block was
+// inserted, false when there was nothing to insert (transcript
+// undefined/empty/not-a-string). A non-string value is a no-op, not an error.
 export function gitmostInsertTranscriptIntoEditor(
   editor: Editor,
   transcript: unknown,
@@ -288,13 +265,7 @@ export function gitmostInsertTranscriptIntoEditor(
     .split("\n")
     // Trim each line and drop blank (whitespace-only) ones.
     .map((line) => line.trim())
-    .filter((line) => line.length > 0)
-    // Neutralize a col-0 markdown block trigger with an invisible ZWSP so the
-    // git-sync round-trip keeps the line a paragraph. Host lines (`You:` /
-    // `Speaker N:`) never match and stay byte-exact.
-    .map((line) =>
-      GITMOST_MD_BLOCK_TRIGGER_RE.test(line) ? GITMOST_ZWSP + line : line,
-    );
+    .filter((line) => line.length > 0);
   if (lines.length === 0) return false;
 
   const content = [

apps/server/package.json

@@ -41,6 +41,7 @@
     "@aws-sdk/s3-request-presigner": "3.1050.0",
     "@azure/storage-blob": "12.31.0",
     "@clickhouse/client": "^1.18.2",
+    "@docmost/editor-ext": "workspace:*",
     "@docmost/mcp": "workspace:*",
     "@docmost/pdf-inspector": "1.9.6",
     "@docmost/prosemirror-markdown": "workspace:*",

apps/server/src/app.module.ts

@@ -25,7 +25,7 @@ import { CacheModule } from '@nestjs/cache-manager';
 import KeyvRedis from '@keyv/redis';
 import { LoggerModule } from './common/logger/logger.module';
 import { ClsModule } from 'nestjs-cls';
-import { NoopAuditModule } from './integrations/audit/audit.module';
+import { AuditModule } from './integrations/audit/audit.module';
 import { ThrottleModule } from './integrations/throttle/throttle.module';
 import { McpModule } from './integrations/mcp/mcp.module';
 import { SandboxModule } from './integrations/sandbox/sandbox.module';
@@ -55,7 +55,7 @@ try {
       middleware: { mount: true },
     }),
     LoggerModule,
-    NoopAuditModule,
+    AuditModule,
     CoreModule,
     DatabaseModule,
     EnvironmentModule,

apps/server/src/collaboration/collaboration.util.ts

@@ -49,6 +49,7 @@ import {
   FootnotesList,
   FootnoteDefinition,
   PageEmbed,
+  Code,
 } from '@docmost/editor-ext';
 import { convertProseMirrorToMarkdown } from '@docmost/prosemirror-markdown';
 import { generateText, getSchema, JSONContent } from '@tiptap/core';
@@ -67,7 +68,12 @@ export const tiptapExtensions = [
     link: false,
     trailingNode: false,
     heading: false,
+    // #515: replace StarterKit's bundled inline `code` (which inherits tiptap's
+    // `excludes: "_"`) with the shared editor-ext `Code` below, so the server's
+    // HTML->PM parse/export keeps code co-occurring with other marks.
+    code: false,
   }),
+  Code,
   Heading,
   UniqueID.configure({
     types: ['heading', 'paragraph', 'transclusionSource'],

apps/server/src/collaboration/yjs.util.spec.ts

@@ -529,4 +529,107 @@ describe('replaceYjsMarkedText', () => {
     expect(result).toEqual({ applied: false, currentText: 'abcdef' });
     expect(text.toDelta()).toEqual(before);
   });
+
+  // #496: apply must NOT silently strip the replaced run's inline formatting.
+  // Build a paragraph and format the marked range with extra marks, then assert
+  // the replacement carries them.
+  function buildFormatted(
+    runs: Array<{ text: string; attrs?: Record<string, any> }>,
+  ): { fragment: Y.XmlFragment; text: Y.XmlText } {
+    const ydoc = new Y.Doc();
+    const fragment = ydoc.getXmlFragment('default');
+    const para = new Y.XmlElement('paragraph');
+    fragment.insert(0, [para]);
+    const text = new Y.XmlText();
+    para.insert(0, [text]);
+    text.insert(0, runs.map((r) => r.text).join(''));
+    let offset = 0;
+    for (const run of runs) {
+      if (run.attrs) text.format(offset, run.text.length, run.attrs);
+      offset += run.text.length;
+    }
+    return { fragment, text };
+  }
+
+  it('preserves the original run formatting (bold + link) on the replacement', () => {
+    const { fragment, text } = buildFormatted([
+      { text: 'see ' },
+      {
+        text: 'old',
+        attrs: {
+          comment: { commentId: 'c1', resolved: false },
+          bold: true,
+          link: { href: 'https://x.test' },
+        },
+      },
+      { text: ' end' },
+    ]);
+
+    const result = replaceYjsMarkedText(fragment, 'c1', 'old', 'new');
+
+    expect(result).toEqual({ applied: true, currentText: 'new' });
+    // The comment anchor AND the bold/link marks survive the delete+insert.
+    expect(text.toDelta()).toEqual([
+      { insert: 'see ' },
+      {
+        insert: 'new',
+        attributes: {
+          comment: { commentId: 'c1', resolved: false },
+          bold: true,
+          link: { href: 'https://x.test' },
+        },
+      },
+      { insert: ' end' },
+    ]);
+  });
+
+  it('mixed formatting under the mark: replacement takes the DOMINANT (longest) run, NOT the leading one', () => {
+    // Leading run is SHORT + plain ("x", 1 char); the following run is LONGER +
+    // bold ("bolded", 6 chars), same commentId. The longest run is deliberately
+    // NOT first: a "first-wins" pick would carry plain (no bold), so asserting
+    // bold on the result only holds if the code genuinely selects the LONGEST run.
+    const { fragment, text } = buildFormatted([
+      { text: 'x', attrs: { comment: { commentId: 'c1', resolved: false } } },
+      {
+        text: 'bolded',
+        attrs: { comment: { commentId: 'c1', resolved: false }, bold: true },
+      },
+    ]);
+
+    const result = replaceYjsMarkedText(fragment, 'c1', 'xbolded', 'Z');
+
+    expect(result).toEqual({ applied: true, currentText: 'Z' });
+    expect(text.toDelta()).toEqual([
+      {
+        insert: 'Z',
+        attributes: { comment: { commentId: 'c1', resolved: false }, bold: true },
+      },
+    ]);
+  });
+
+  it('mixed formatting under the mark: on a length tie the FIRST run wins', () => {
+    // Two equal-length runs (2 chars each) with different formatting, same
+    // commentId. The reduce keeps the accumulator on a tie, so the FIRST run
+    // (italic) prevails over the later bold one.
+    const { fragment, text } = buildFormatted([
+      {
+        text: 'AA',
+        attrs: { comment: { commentId: 'c1', resolved: false }, italic: true },
+      },
+      {
+        text: 'BB',
+        attrs: { comment: { commentId: 'c1', resolved: false }, bold: true },
+      },
+    ]);
+
+    const result = replaceYjsMarkedText(fragment, 'c1', 'AABB', 'Z');
+
+    expect(result).toEqual({ applied: true, currentText: 'Z' });
+    expect(text.toDelta()).toEqual([
+      {
+        insert: 'Z',
+        attributes: { comment: { commentId: 'c1', resolved: false }, italic: true },
+      },
+    ]);
+  });
 });

apps/server/src/collaboration/yjs.util.ts

@@ -145,6 +145,10 @@ type MarkedSegment = {
   length: number;
   text: string;
   markAttrs: Record<string, any>;
+  // The FULL attribute set of this delta run — the `comment` mark plus any
+  // inline formatting (bold/italic/code/link/…). Captured so apply can carry the
+  // original run's formatting onto the replacement instead of dropping it.
+  attributes: Record<string, any>;
 };
 
 /**
@@ -202,6 +206,7 @@ export function replaceYjsMarkedText(
             length,
             text: insert,
             markAttrs: markAttr,
+            attributes,
           });
         }
         offset += length;
@@ -251,15 +256,25 @@ export function replaceYjsMarkedText(
     return { applied: false, currentText: joinedText };
   }
 
-  // 3. All guards passed: delete the marked run and re-insert newText with the
-  // same comment attributes at the same offset. Atomic within the caller's
-  // transaction.
+  // 3. All guards passed: delete the marked run and re-insert newText at the
+  // same offset. Atomic within the caller's transaction.
   const start = segments[0].offset;
   const len = segments.reduce((sum, s) => sum + s.length, 0);
-  const markAttrs = segments[0].markAttrs;
+
+  // Carry the ORIGINAL run's formatting onto the replacement (#496): inserting
+  // with only the `comment` mark silently dropped bold/italic/code/link of the
+  // replaced text. Yjs applies one flat attribute set to the whole insert, so
+  // when the marked run mixes formatting we pick the DOMINANT segment (the one
+  // covering the most characters) and apply its attributes — a v1 that preserves
+  // the common single-format case exactly and, for a mixed run, keeps the
+  // prevailing style rather than losing all of it. `attributes` already carries
+  // the `comment` mark (every collected segment is filtered on it above), so the
+  // anchor is preserved by copying the run's attribute set verbatim.
+  const dominant = segments.reduce((a, b) => (b.length > a.length ? b : a));
+  const insertAttrs = { ...dominant.attributes };
 
   node.delete(start, len);
-  node.insert(start, newText, { comment: markAttrs });
+  node.insert(start, newText, insertAttrs);
 
   return { applied: true, currentText: newText };
 }

apps/server/src/core/comment/comment.controller.ts

@@ -16,6 +16,7 @@ import { UpdateCommentDto } from './dto/update-comment.dto';
 import { ResolveCommentDto } from './dto/resolve-comment.dto';
 import { ApplySuggestionDto } from './dto/apply-suggestion.dto';
 import { DismissSuggestionDto } from './dto/dismiss-suggestion.dto';
+import { ResyncSuggestionAnchorDto } from './dto/resync-suggestion-anchor.dto';
 import { PageIdDto, CommentIdDto } from './dto/comments.input';
 import { AuthUser } from '../../common/decorators/auth-user.decorator';
 import { AuthWorkspace } from '../../common/decorators/auth-workspace.decorator';
@@ -235,6 +236,39 @@ export class CommentController {
     return this.commentService.applySuggestion(comment, user, provenance);
   }
 
+  @HttpCode(HttpStatus.OK)
+  @Post('resync-suggestion-anchor')
+  async resyncSuggestionAnchor(
+    @Body() dto: ResyncSuggestionAnchorDto,
+    @AuthUser() user: User,
+    @AuthWorkspace() workspace: Workspace,
+  ) {
+    const comment = await this.commentRepo.findById(dto.commentId, {
+      includeCreator: true,
+      includeResolvedBy: true,
+    });
+    if (!comment) {
+      throw new NotFoundException('Comment not found');
+    }
+
+    const page = await this.pageRepo.findById(comment.pageId);
+    if (!page || page.deletedAt) {
+      throw new NotFoundException('Page not found');
+    }
+
+    // Authorize BEFORE revealing structural detail (mirrors apply/dismiss).
+    // Re-anchoring does NOT change the page text — it only corrects the stored
+    // selection metadata — so the page-level gate is comment access. The service
+    // further restricts it to the suggestion's own author.
+    await this.pageAccessService.validateCanComment(page, user, workspace.id);
+
+    return this.commentService.resyncSuggestionAnchor(
+      comment,
+      dto.selection,
+      user,
+    );
+  }
+
   @HttpCode(HttpStatus.OK)
   @Post('dismiss-suggestion')
   async dismissSuggestion(

apps/server/src/core/comment/comment.service.apply-suggestion.spec.ts

@@ -146,11 +146,19 @@ describe('CommentService — applySuggestion', () => {
       'page-1',
       expect.objectContaining({ operation: 'commentDeleted', commentId: 'c-1' }),
     );
+    // #496: hard-deleted row → the audit payload is the only surviving record.
     expect(auditService.log).toHaveBeenCalledWith(
       expect.objectContaining({
         event: AuditEvent.COMMENT_SUGGESTION_APPLIED,
         resourceType: AuditResource.COMMENT,
         resourceId: 'c-1',
+        metadata: expect.objectContaining({
+          pageId: 'page-1',
+          suggestedText: 'new text',
+          selection: 'old text',
+          commentAuthor: 'user-1',
+          decidedBy: 'user-1',
+        }),
       }),
     );
     expect(result.outcome).toBe('deleted');
@@ -189,17 +197,25 @@ describe('CommentService — applySuggestion', () => {
     expect(resolvePatch.resolvedAt).toBeInstanceOf(Date);
     expect(resolvePatch.resolvedById).toBe('user-1');
 
-    // NOT deleted; broadcast an update, not a deletion.
+    // NOT deleted.
     expect(commentRepo.deleteComment).not.toHaveBeenCalled();
     expect(collaborationGateway.handleYjsEvent).not.toHaveBeenCalledWith(
       'deleteCommentMark',
       expect.anything(),
       expect.anything(),
     );
+    // #496 dedup: resolveComment broadcasts `commentResolved` with the enriched
+    // row; finalize must NOT ALSO emit a redundant `commentUpdated`. So the
+    // thread receives exactly ONE resolve broadcast and no update broadcast.
     expect(wsService.emitCommentEvent).toHaveBeenCalledWith(
       'space-1',
       'page-1',
-      expect.objectContaining({ operation: 'commentUpdated', comment: UPDATED }),
+      expect.objectContaining({ operation: 'commentResolved', comment: UPDATED }),
+    );
+    expect(wsService.emitCommentEvent).not.toHaveBeenCalledWith(
+      'space-1',
+      'page-1',
+      expect.objectContaining({ operation: 'commentUpdated' }),
     );
 
     expect(auditService.log).toHaveBeenCalledWith(
@@ -211,6 +227,36 @@ describe('CommentService — applySuggestion', () => {
     expect(result.outcome).toBe('resolved');
   });
 
+  it('re-entry: already applied+resolved WITH replies → emits commentUpdated (dedup does not over-suppress)', async () => {
+    // suggestionAppliedAt set → idempotent finalize; resolvedAt set → resolveComment
+    // is skipped, so there is NO commentResolved broadcast. The applied-stamp state
+    // must still reach clients via a single commentUpdated.
+    const { service, wsService } = makeService(
+      { applied: false, currentText: 'new text' },
+      true,
+    );
+
+    await service.applySuggestion(
+      suggestionComment({
+        suggestionAppliedAt: new Date(),
+        resolvedAt: new Date(),
+      }),
+      user(),
+    );
+
+    expect(wsService.emitCommentEvent).toHaveBeenCalledWith(
+      'space-1',
+      'page-1',
+      expect.objectContaining({ operation: 'commentUpdated', comment: UPDATED }),
+    );
+    // Nothing resolved this time (already resolved) → no resolve broadcast.
+    expect(wsService.emitCommentEvent).not.toHaveBeenCalledWith(
+      'space-1',
+      'page-1',
+      expect.objectContaining({ operation: 'commentResolved' }),
+    );
+  });
+
   // --- error / rejection branches -----------------------------------------
 
   it('applied=false and currentText differs → ConflictException with currentText in payload', async () => {

apps/server/src/core/comment/comment.service.dismiss-suggestion.spec.ts

@@ -107,11 +107,21 @@ describe('CommentService — dismissSuggestion', () => {
       'page-1',
       expect.objectContaining({ operation: 'commentDeleted', commentId: 'c-1' }),
     );
+    // #496: the row is hard-deleted, so the audit payload must carry the
+    // decision's substance (what was suggested, the anchored text, who authored
+    // it, who decided) — it is the only surviving record.
     expect(auditService.log).toHaveBeenCalledWith(
       expect.objectContaining({
         event: AuditEvent.COMMENT_SUGGESTION_DISMISSED,
         resourceType: AuditResource.COMMENT,
         resourceId: 'c-1',
+        metadata: expect.objectContaining({
+          pageId: 'page-1',
+          suggestedText: 'new text',
+          selection: 'old text',
+          commentAuthor: 'user-1',
+          decidedBy: 'user-1',
+        }),
       }),
     );
     expect(result.outcome).toBe('deleted');

apps/server/src/core/comment/comment.service.resync-anchor.spec.ts

@@ -0,0 +1,126 @@
+import { BadRequestException, ForbiddenException } from '@nestjs/common';
+import { CommentService } from './comment.service';
+
+/**
+ * Coverage for CommentService.resyncSuggestionAnchor (#496): re-anchoring a
+ * suggestion's stored selection (== apply-time expectedText) to the live-doc
+ * substring. The service is built directly with jest-mocked deps (the
+ * @InjectQueue tokens can't be resolved by Test.createTestingModule — see the
+ * sibling specs).
+ */
+describe('CommentService — resyncSuggestionAnchor', () => {
+  const UPDATED = { id: 'c-1', selection: 'new anchor', __updated: true } as any;
+
+  function makeService() {
+    const commentRepo: any = {
+      updateComment: jest.fn(async () => undefined),
+      findById: jest.fn(async () => UPDATED),
+    };
+    const service = new CommentService(
+      commentRepo,
+      {} as any,
+      { emitCommentEvent: jest.fn() } as any,
+      {} as any,
+      { add: jest.fn() } as any,
+      { add: jest.fn() } as any,
+      { log: jest.fn() } as any,
+    );
+    return { service, commentRepo };
+  }
+
+  const suggestion = (over?: Partial<any>): any => ({
+    id: 'c-1',
+    creatorId: 'user-1',
+    parentCommentId: null,
+    selection: 'old anchor',
+    suggestedText: 'new text',
+    suggestionAppliedAt: null,
+    resolvedAt: null,
+    ...over,
+  });
+  const user = (over?: Partial<any>): any => ({ id: 'user-1', ...over });
+
+  it('persists the new selection and returns the enriched comment', async () => {
+    const { service, commentRepo } = makeService();
+
+    const out = await service.resyncSuggestionAnchor(
+      suggestion(),
+      'new anchor',
+      user(),
+    );
+
+    expect(commentRepo.updateComment).toHaveBeenCalledWith(
+      { selection: 'new anchor' },
+      'c-1',
+    );
+    expect(out).toBe(UPDATED);
+  });
+
+  it('is idempotent: no write when the anchor already matches', async () => {
+    const { service, commentRepo } = makeService();
+
+    const out = await service.resyncSuggestionAnchor(
+      suggestion({ selection: 'same' }),
+      'same',
+      user(),
+    );
+
+    expect(commentRepo.updateComment).not.toHaveBeenCalled();
+    expect(out).toEqual(suggestion({ selection: 'same' }));
+  });
+
+  it('rejects a non-author (only the suggestion owner may re-anchor)', async () => {
+    const { service, commentRepo } = makeService();
+    await expect(
+      service.resyncSuggestionAnchor(suggestion(), 'new anchor', user({ id: 'other' })),
+    ).rejects.toBeInstanceOf(ForbiddenException);
+    expect(commentRepo.updateComment).not.toHaveBeenCalled();
+  });
+
+  it('rejects a reply / a comment with no suggestion', async () => {
+    const { service } = makeService();
+    await expect(
+      service.resyncSuggestionAnchor(
+        suggestion({ parentCommentId: 'p-1' }),
+        'x',
+        user(),
+      ),
+    ).rejects.toBeInstanceOf(BadRequestException);
+    await expect(
+      service.resyncSuggestionAnchor(
+        suggestion({ suggestedText: null }),
+        'x',
+        user(),
+      ),
+    ).rejects.toBeInstanceOf(BadRequestException);
+  });
+
+  it('rejects re-anchoring an already applied or resolved suggestion', async () => {
+    const { service } = makeService();
+    await expect(
+      service.resyncSuggestionAnchor(
+        suggestion({ suggestionAppliedAt: new Date() }),
+        'x',
+        user(),
+      ),
+    ).rejects.toBeInstanceOf(BadRequestException);
+    await expect(
+      service.resyncSuggestionAnchor(
+        suggestion({ resolvedAt: new Date() }),
+        'x',
+        user(),
+      ),
+    ).rejects.toBeInstanceOf(BadRequestException);
+  });
+
+  it('rejects a no-op selection equal to the suggested text', async () => {
+    const { service } = makeService();
+    await expect(
+      service.resyncSuggestionAnchor(
+        suggestion({ suggestedText: 'new text' }),
+        'new text',
+        user(),
+      ),
+    ).rejects.toBeInstanceOf(BadRequestException);
+  });
+});

apps/server/src/core/comment/comment.service.ts

@@ -370,6 +370,76 @@ export class CommentService {
     return updatedComment;
   }
 
+  /**
+   * Re-sync a suggestion's stored `selection` (== apply-time expectedText) to the
+   * RAW substring the inline mark actually covers in the LIVE document (#496).
+   *
+   * The MCP client creates the comment from a DEBOUNCED REST snapshot, then
+   * anchors the mark in the live collab doc. When the two disagree (the doc moved
+   * on in the debounce window) the stored selection no longer equals the marked
+   * text, so EVERY apply 409s ("the commented text changed"). After anchoring the
+   * client re-reads the exact marked substring and calls this to store it, making
+   * apply's strict equality hold.
+   *
+   * Only meaningful for an un-settled top-level suggestion authored by the
+   * caller: applying/resolving freezes the anchor, and a reply-carrying thread is
+   * preserved rather than mutated. The new text must still differ from the
+   * suggestion (else "apply" would be a no-op), preserving create()'s invariant.
+   */
+  async resyncSuggestionAnchor(
+    comment: Comment,
+    selection: string,
+    user: User,
+  ): Promise<Comment> {
+    if (comment.creatorId !== user.id) {
+      throw new ForbiddenException(
+        'You can only re-anchor your own suggestion',
+      );
+    }
+    if (comment.parentCommentId) {
+      throw new BadRequestException(
+        'Only a top-level comment can carry a suggested edit',
+      );
+    }
+    if (!comment.suggestedText) {
+      throw new BadRequestException('This comment has no suggested edit');
+    }
+    // A settled suggestion's anchor is frozen: re-anchoring an applied/resolved
+    // thread is meaningless and could resurrect a stale expectedText.
+    if (comment.suggestionAppliedAt || comment.resolvedAt) {
+      throw new BadRequestException(
+        'Cannot re-anchor a suggestion that was already applied or resolved',
+      );
+    }
+    const trimmed = selection.trim();
+    if (trimmed.length === 0) {
+      throw new BadRequestException('The re-anchored selection cannot be empty');
+    }
+    // Same no-op guard as create(): the suggestion must differ from the text it
+    // replaces, or apply becomes indistinguishable from already-applied.
+    if (trimmed === comment.suggestedText.trim()) {
+      throw new BadRequestException(
+        'A suggested edit must differ from the selected text',
+      );
+    }
+
+    // Idempotent: nothing to persist when the anchor already matches.
+    if (comment.selection === selection) {
+      return comment;
+    }
+
+    await this.commentRepo.updateComment({ selection }, comment.id);
+
+    const updatedComment = await this.commentRepo.findById(comment.id, {
+      includeCreator: true,
+      includeResolvedBy: true,
+    });
+
+    // Re-anchoring only corrects stored metadata; it does not change the page
+    // text or the comment body, so no ws broadcast / notification is warranted.
+    return updatedComment;
+  }
+
   /**
    * Apply the suggested edit carried by a top-level inline comment: atomically
    * replace the text under the comment mark in the collaborative document with
@@ -524,7 +594,7 @@ export class CommentService {
         resourceType: AuditResource.COMMENT,
         resourceId: comment.id,
         spaceId: comment.spaceId,
-        metadata: { pageId: comment.pageId },
+        metadata: this.suggestionAuditMetadata(comment, user),
       });
       return { ...updatedComment, outcome: 'resolved' };
     }
@@ -538,7 +608,7 @@ export class CommentService {
       resourceType: AuditResource.COMMENT,
       resourceId: comment.id,
       spaceId: comment.spaceId,
-      metadata: { pageId: comment.pageId },
+      metadata: this.suggestionAuditMetadata(comment, user),
     });
     return settled;
   }
@@ -577,8 +647,10 @@ export class CommentService {
 
       // Auto-resolve the thread. resolveComment handles the resolve mark, its ws
       // broadcast and the resolve notification. Stay defensive on re-entry.
+      let didResolveBroadcast = false;
       if (!comment.resolvedAt) {
         await this.resolveComment(comment, true, user, provenance);
+        didResolveBroadcast = true;
       }
 
       const updatedComment = await this.commentRepo.findById(comment.id, {
@@ -586,18 +658,27 @@ export class CommentService {
         includeResolvedBy: true,
       });
 
-      this.wsService.emitCommentEvent(comment.spaceId, comment.pageId, {
-        operation: 'commentUpdated',
-        pageId: comment.pageId,
-        comment: updatedComment,
-      });
+      // #496 dedup: resolveComment already broadcast `commentResolved` carrying
+      // the fully-enriched row (the applied stamps were persisted above, before
+      // that call, so its re-read reflects them). Emitting `commentUpdated` here
+      // too made the client receive TWO events for one apply. Broadcast the
+      // update ONLY when we did NOT resolve — i.e. the rare re-entry on an
+      // already-resolved thread, where the applied-stamp change still needs a
+      // broadcast and resolveComment did not run.
+      if (!didResolveBroadcast) {
+        this.wsService.emitCommentEvent(comment.spaceId, comment.pageId, {
+          operation: 'commentUpdated',
+          pageId: comment.pageId,
+          comment: updatedComment,
+        });
+      }
 
       this.auditService.log({
         event: AuditEvent.COMMENT_SUGGESTION_APPLIED,
         resourceType: AuditResource.COMMENT,
         resourceId: comment.id,
         spaceId: comment.spaceId,
-        metadata: { pageId: comment.pageId },
+        metadata: this.suggestionAuditMetadata(comment, user),
       });
 
       return { ...updatedComment, outcome: 'resolved' };
@@ -616,7 +697,7 @@ export class CommentService {
       resourceType: AuditResource.COMMENT,
       resourceId: comment.id,
       spaceId: comment.spaceId,
-      metadata: { pageId: comment.pageId },
+      metadata: this.suggestionAuditMetadata(comment, user),
     });
 
     return settled;
@@ -627,14 +708,17 @@ export class CommentService {
    * inline `comment` anchor mark, then ATOMICALLY hard-delete the row only if it
    * is still childless. Shared by the apply/dismiss no-replies branches (#329).
    *
-   * ORDER MATTERS: the anchor mark is removed FIRST and FATALLY (mirrors
-   * applySuggestion, which mutates the doc before writing the DB). The row
-   * delete is irreversible, so if the mark removal fails — including the
-   * COLLAB_DISABLE_REDIS "no live instance" hard-error — we must NOT delete the
-   * row and report success, or the document is left with a permanent orphan
-   * anchor pointing at a comment that no longer exists (the exact data-integrity
-   * bug #329 targets). Let the exception propagate (→ 5xx); the operation is
-   * then repeatable with row + mark still consistent.
+   * ORDER MATTERS (updated #399 → #496): what runs FIRST and FATALLY here is the
+   * mark-removal ENQUEUE (a fast, durable Redis add), NOT the mark op itself.
+   * deleteCommentMark awaits only the enqueue, so a failed add throws BEFORE the
+   * irreversible row delete — the row + mark stay consistent and the operation is
+   * repeatable. The actual anchor strip then runs off the HTTP path in the worker
+   * (idempotent, 3 retries). Only an EXHAUSTED-retries job could leave the doc
+   * with an orphan anchor pointing at a hard-deleted comment (the data-integrity
+   * bug #329 targets); that residual divergence is now self-healed by the
+   * resolve/unresolve mark worker, which strips an orphan mark whenever its
+   * comment row is gone (#496), and it is meanwhile VISIBLE via BullMQ failed-job
+   * metrics rather than a silently-swallowed warn.
    *
    * RACE (#338 F4): the caller read `hasChildren` BEFORE the (slow) mark
    * removal, so a reply can land in that window. `comments.parent_comment_id` is
@@ -732,6 +816,27 @@ export class CommentService {
     return this.generalQueue.add(QueueJob.COMMENT_MARK_UPDATE, jobData);
   }
 
+  /**
+   * Build the audit metadata for a suggestion apply/dismiss decision (#496).
+   * The subject comment is HARD-DELETED on the childless path, so the audit row
+   * is the only surviving record — capture the decision's substance (what was
+   * suggested, the anchored text it replaced, who authored it, who decided)
+   * before the row can vanish. `decidedBy` is the acting user; `commentAuthor`
+   * is the suggestion's creator.
+   */
+  private suggestionAuditMetadata(
+    comment: Comment,
+    user: User,
+  ): Record<string, any> {
+    return {
+      pageId: comment.pageId,
+      suggestedText: comment.suggestedText ?? null,
+      selection: comment.selection ?? null,
+      commentAuthor: comment.creatorId ?? null,
+      decidedBy: user.id,
+    };
+  }
+
   private async queueCommentNotification(
     content: any,
     oldMentionIds: string[],

apps/server/src/core/comment/dto/resync-suggestion-anchor.dto.ts

@@ -0,0 +1,20 @@
+import { IsString, IsUUID, MaxLength, MinLength } from 'class-validator';
+
+/**
+ * #496: after the MCP client anchors a suggestion in the LIVE collab doc, it
+ * re-reads the exact substring under the new mark and syncs it here as the
+ * comment's stored `selection` (== apply-time expectedText). Fixes the perpetual
+ * 409 where expectedText came from a debounced REST snapshot while the mark sat
+ * in the live doc.
+ */
+export class ResyncSuggestionAnchorDto {
+  @IsUUID()
+  commentId: string;
+
+  // The raw substring the mark now covers in the live document. Bounded like the
+  // create-time selection (2000) so a legitimate anchored span is never cut.
+  @IsString()
+  @MinLength(1)
+  @MaxLength(2000)
+  selection: string;
+}

apps/server/src/core/page/services/page.service.ts

@@ -53,8 +53,10 @@ import {
   extractPageSlugId,
 } from '../../../integrations/export/utils';
 import { canonicalizeFootnotes } from '@docmost/editor-ext';
-import { markdownToProseMirror } from '@docmost/prosemirror-markdown';
-import { normalizeForeignMarkdown } from '../../../integrations/import/utils/foreign-markdown';
+import {
+  markdownToProseMirror,
+  normalizeForeignMarkdown,
+} from '@docmost/prosemirror-markdown';
 import { WatcherService } from '../../watcher/watcher.service';
 import { sql } from 'kysely';
 import { TransclusionService } from '../transclusion/transclusion.service';

apps/server/src/integrations/audit/audit.module.ts

@@ -1,14 +1,19 @@
 import { Global, Module } from '@nestjs/common';
-import { AUDIT_SERVICE, NoopAuditService } from './audit.service';
+import { AUDIT_SERVICE } from './audit.service';
+import { DatabaseAuditService } from './database-audit.service';
 
+// #496: bind the audit token to a real DB-backed trail (was NoopAuditService,
+// which silently dropped every event). Kysely (@Global DatabaseModule) and
+// ClsService (@Global ClsModule) are both globally available, so this module
+// needs no extra imports.
 @Global()
 @Module({
   providers: [
     {
       provide: AUDIT_SERVICE,
-      useClass: NoopAuditService,
+      useClass: DatabaseAuditService,
     },
   ],
   exports: [AUDIT_SERVICE],
 })
-export class NoopAuditModule {}
+export class AuditModule {}

apps/server/src/integrations/audit/database-audit.service.spec.ts

@@ -0,0 +1,198 @@
+import { Logger } from '@nestjs/common';
+import { DatabaseAuditService } from './database-audit.service';
+import { AUDIT_CONTEXT_KEY } from '../../common/middlewares/audit-context.middleware';
+import { AuditEvent, AuditResource } from '../../common/events/audit-events';
+
+/**
+ * Observable-property coverage for the DB-backed audit trail (#496): every
+ * assertion pins what actually reaches the `audit` table (or that nothing does),
+ * driven through a chainable Kysely mock that captures the inserted rows.
+ */
+describe('DatabaseAuditService', () => {
+  function makeService(clsContext: any) {
+    const inserted: any[] = [];
+    const updated: any[] = [];
+    let failNextInsert = false;
+
+    const db: any = {
+      insertInto: jest.fn(() => ({
+        values: jest.fn((rows: any) => ({
+          execute: jest.fn(async () => {
+            if (failNextInsert) {
+              failNextInsert = false;
+              throw new Error('boom');
+            }
+            inserted.push(rows);
+          }),
+        })),
+      })),
+      updateTable: jest.fn(() => ({
+        set: jest.fn((patch: any) => ({
+          where: jest.fn(() => ({
+            execute: jest.fn(async () => {
+              updated.push(patch);
+            }),
+          })),
+        })),
+      })),
+    };
+
+    const store: Record<string, any> = { [AUDIT_CONTEXT_KEY]: clsContext };
+    const cls: any = {
+      get: jest.fn((key: string) => store[key]),
+      set: jest.fn((key: string, val: any) => {
+        store[key] = val;
+      }),
+    };
+
+    const service = new DatabaseAuditService(db, cls);
+    return {
+      service,
+      inserted,
+      updated,
+      cls,
+      store,
+      failInsert: () => {
+        failNextInsert = true;
+      },
+    };
+  }
+
+  const applyPayload = () => ({
+    event: AuditEvent.COMMENT_SUGGESTION_APPLIED,
+    resourceType: AuditResource.COMMENT,
+    resourceId: 'c-1',
+    spaceId: 'space-1',
+    metadata: { pageId: 'p-1', suggestedText: 'new', decidedBy: 'u-2' },
+  });
+
+  const ctx = (over?: any) => ({
+    workspaceId: 'ws-1',
+    actorId: 'u-2',
+    actorType: 'user',
+    ipAddress: '10.0.0.1',
+    userAgent: 'jest',
+    ...over,
+  });
+
+  it('log() persists a row with the CLS context merged onto the payload', async () => {
+    const { service, inserted } = makeService(ctx());
+    service.log(applyPayload());
+    // log() is fire-and-forget; flush the microtask queue.
+    await Promise.resolve();
+    await Promise.resolve();
+
+    expect(inserted).toHaveLength(1);
+    expect(inserted[0]).toMatchObject({
+      workspaceId: 'ws-1',
+      actorId: 'u-2',
+      actorType: 'user',
+      event: AuditEvent.COMMENT_SUGGESTION_APPLIED,
+      resourceType: AuditResource.COMMENT,
+      resourceId: 'c-1',
+      spaceId: 'space-1',
+      ipAddress: '10.0.0.1',
+      metadata: { pageId: 'p-1', suggestedText: 'new', decidedBy: 'u-2' },
+    });
+  });
+
+  it('log() is a no-op when there is no workspace in scope', async () => {
+    const { service, inserted } = makeService(ctx({ workspaceId: null }));
+    service.log(applyPayload());
+    await Promise.resolve();
+    expect(inserted).toHaveLength(0);
+  });
+
+  it('log() drops EXCLUDED_AUDIT_EVENTS (e.g. comment.created)', async () => {
+    const { service, inserted } = makeService(ctx());
+    service.log({
+      event: AuditEvent.COMMENT_CREATED,
+      resourceType: AuditResource.COMMENT,
+      resourceId: 'c-1',
+      spaceId: 'space-1',
+    });
+    await Promise.resolve();
+    await Promise.resolve();
+    expect(inserted).toHaveLength(0);
+  });
+
+  it('a failed insert is swallowed with a warn and floats no rejection (audit is a side-record)', async () => {
+    // This pins the load-bearing swallow inside persist(). Because log() is
+    // fire-and-forget (`void this.persist(...)`), it always returns synchronously
+    // without throwing — so `not.toThrow()` alone would stay green even if the
+    // try/catch were removed. We instead observe the two effects the catch is
+    // responsible for: a warn IS emitted, and NO unhandled rejection floats.
+    // Removing persist()'s try/catch reddens both assertions (warn count 0 + a
+    // captured rejection).
+    const warnSpy = jest
+      .spyOn(Logger.prototype, 'warn')
+      .mockImplementation(() => undefined as any);
+    const rejections: unknown[] = [];
+    const onRejection = (err: unknown) => rejections.push(err);
+    process.on('unhandledRejection', onRejection);
+    try {
+      const { service, failInsert } = makeService(ctx());
+      failInsert();
+      expect(() => service.log(applyPayload())).not.toThrow();
+      // Flush microtasks so the rejected insert settles, then give any floated
+      // rejection a macrotask tick to be reported by the runtime.
+      await Promise.resolve();
+      await Promise.resolve();
+      await new Promise((r) => setImmediate(r));
+
+      expect(warnSpy).toHaveBeenCalledTimes(1);
+      expect(String(warnSpy.mock.calls[0][0])).toContain(
+        'Failed to persist audit event',
+      );
+      expect(rejections).toHaveLength(0);
+    } finally {
+      process.off('unhandledRejection', onRejection);
+      warnSpy.mockRestore();
+    }
+  });
+
+  it('logWithContext() persists with an explicit (non-request) context', async () => {
+    const { service, inserted } = makeService(undefined);
+    service.logWithContext(applyPayload(), ctx({ actorType: 'system' }) as any);
+    await Promise.resolve();
+    await Promise.resolve();
+    expect(inserted).toHaveLength(1);
+    expect(inserted[0].actorType).toBe('system');
+    expect(inserted[0].workspaceId).toBe('ws-1');
+  });
+
+  it('logBatchWithContext() inserts only non-excluded events', async () => {
+    const { service, inserted } = makeService(undefined);
+    service.logBatchWithContext(
+      [
+        applyPayload(),
+        {
+          event: AuditEvent.COMMENT_CREATED,
+          resourceType: AuditResource.COMMENT,
+          resourceId: 'c-2',
+        },
+      ],
+      ctx() as any,
+    );
+    await Promise.resolve();
+    await Promise.resolve();
+    // Batch is a single insert call carrying only the applied event.
+    expect(inserted).toHaveLength(1);
+    expect(inserted[0]).toHaveLength(1);
+    expect(inserted[0][0].event).toBe(AuditEvent.COMMENT_SUGGESTION_APPLIED);
+  });
+
+  it('setActorId / setActorType mutate the ambient CLS context', () => {
+    const { service, store } = makeService(ctx({ actorId: null }));
+    service.setActorId('u-9');
+    service.setActorType('api_key');
+    expect(store[AUDIT_CONTEXT_KEY].actorId).toBe('u-9');
+    expect(store[AUDIT_CONTEXT_KEY].actorType).toBe('api_key');
+  });
+
+  it('updateRetention() writes the workspace retention window', async () => {
+    const { service, updated } = makeService(ctx());
+    await service.updateRetention('ws-1', 30);
+    expect(updated).toEqual([{ auditRetentionDays: 30 }]);
+  });
+});

apps/server/src/integrations/audit/database-audit.service.ts

@@ -0,0 +1,160 @@
+import { Injectable, Logger } from '@nestjs/common';
+import { InjectKysely } from 'nestjs-kysely';
+import { ClsService } from 'nestjs-cls';
+import { KyselyDB } from '@docmost/db/types/kysely.types';
+import {
+  AuditContext,
+  AUDIT_CONTEXT_KEY,
+} from '../../common/middlewares/audit-context.middleware';
+import {
+  AuditLogPayload,
+  ActorType,
+  EXCLUDED_AUDIT_EVENTS,
+} from '../../common/events/audit-events';
+import { AuditLogContext, IAuditService } from './audit.service';
+
+/**
+ * Minimal DB-backed audit trail (#496). Replaces NoopAuditService so that
+ * decision-bearing events — notably comment.suggestion_applied /
+ * comment.suggestion_dismissed, whose subject comment is HARD-DELETED on the
+ * childless path — leave a durable record of who decided what. Without this the
+ * events were emitted (comment.service / *.controller) but swallowed, so an
+ * applied/dismissed suggestion was unrecoverable once the row was gone.
+ *
+ * Rows land in the pre-existing `audit` table (migration 20260228T223532). The
+ * per-request actor/workspace/ip come from the CLS AuditContext populated by
+ * AuditContextMiddleware + AuditActorInterceptor; callers that run OUTSIDE a
+ * request (queue workers, imports) pass an explicit context via
+ * logWithContext / logBatchWithContext.
+ *
+ * Audit is a side-record: a write failure MUST NOT break the originating
+ * request, so every persistence path swallows its error with a warn. Events in
+ * EXCLUDED_AUDIT_EVENTS (high-volume/low-signal) are dropped.
+ */
+@Injectable()
+export class DatabaseAuditService implements IAuditService {
+  private readonly logger = new Logger(DatabaseAuditService.name);
+
+  constructor(
+    @InjectKysely() private readonly db: KyselyDB,
+    private readonly cls: ClsService,
+  ) {}
+
+  /**
+   * Persist a single event using the ambient request-scoped AuditContext. A
+   * no-op when there is no workspace in scope (the table's workspace_id is NOT
+   * NULL) or the event is excluded. Fire-and-forget: the returned promise is not
+   * awaited by hot callers, and its rejection is swallowed here.
+   */
+  log(payload: AuditLogPayload): void {
+    const context = this.cls?.get<AuditContext>(AUDIT_CONTEXT_KEY);
+    if (!context?.workspaceId) {
+      // No workspace in scope — nothing we can attribute the row to. This is
+      // expected for events emitted outside an HTTP request; those callers must
+      // use logWithContext instead.
+      return;
+    }
+    void this.persist(payload, {
+      workspaceId: context.workspaceId,
+      actorId: context.actorId ?? undefined,
+      actorType: context.actorType,
+      ipAddress: context.ipAddress ?? undefined,
+      userAgent: context.userAgent ?? undefined,
+    });
+  }
+
+  /** Persist a single event with an explicit (non-request) context. */
+  logWithContext(payload: AuditLogPayload, context: AuditLogContext): void {
+    if (!context?.workspaceId) return;
+    void this.persist(payload, context);
+  }
+
+  /** Persist a batch of events sharing one explicit context (imports). */
+  logBatchWithContext(
+    payloads: AuditLogPayload[],
+    context: AuditLogContext,
+  ): void {
+    if (!context?.workspaceId || payloads.length === 0) return;
+    const rows = payloads
+      .filter((p) => !EXCLUDED_AUDIT_EVENTS.has(p.event))
+      .map((p) => this.toRow(p, context));
+    if (rows.length === 0) return;
+    this.db
+      .insertInto('audit')
+      .values(rows)
+      .execute()
+      .catch((err: any) =>
+        this.logger.warn(`Failed to persist ${rows.length} audit events: ${err?.message}`),
+      );
+  }
+
+  /** Update the ambient request actor (e.g. after login resolves the user). */
+  setActorId(actorId: string): void {
+    const context = this.cls?.get<AuditContext>(AUDIT_CONTEXT_KEY);
+    if (context) {
+      context.actorId = actorId;
+      this.cls.set(AUDIT_CONTEXT_KEY, context);
+    }
+  }
+
+  /** Update the ambient request actor type (user | system | api_key). */
+  setActorType(actorType: ActorType): void {
+    const context = this.cls?.get<AuditContext>(AUDIT_CONTEXT_KEY);
+    if (context) {
+      context.actorType = actorType;
+      this.cls.set(AUDIT_CONTEXT_KEY, context);
+    }
+  }
+
+  /** Persist a workspace's audit-log retention window (days). */
+  async updateRetention(
+    workspaceId: string,
+    retentionDays: number,
+  ): Promise<void> {
+    try {
+      await this.db
+        .updateTable('workspaces')
+        .set({ auditRetentionDays: retentionDays })
+        .where('id', '=', workspaceId)
+        .execute();
+    } catch (err: any) {
+      this.logger.warn(
+        `Failed to update audit retention for workspace ${workspaceId}: ${err?.message}`,
+      );
+    }
+  }
+
+  private async persist(
+    payload: AuditLogPayload,
+    context: AuditLogContext,
+  ): Promise<void> {
+    if (EXCLUDED_AUDIT_EVENTS.has(payload.event)) return;
+    try {
+      await this.db
+        .insertInto('audit')
+        .values(this.toRow(payload, context))
+        .execute();
+    } catch (err: any) {
+      // Audit is a side-record; never let a failed write surface to the caller.
+      this.logger.warn(
+        `Failed to persist audit event ${payload.event}: ${err?.message}`,
+      );
+    }
+  }
+
+  private toRow(payload: AuditLogPayload, context: AuditLogContext) {
+    return {
+      workspaceId: context.workspaceId,
+      actorId: context.actorId ?? null,
+      actorType: context.actorType ?? 'user',
+      event: payload.event,
+      resourceType: payload.resourceType,
+      resourceId: payload.resourceId ?? null,
+      spaceId: payload.spaceId ?? null,
+      // jsonb columns: node-postgres serializes plain objects to JSON.
+      changes: payload.changes ? (payload.changes as any) : null,
+      metadata: payload.metadata ? (payload.metadata as any) : null,
+      ipAddress: context.ipAddress ?? null,
+    };
+  }
+}

apps/server/src/integrations/import/services/file-import-task.service.ts

@@ -22,10 +22,12 @@ import { v7 } from 'uuid';
 import { generateJitteredKeyBetween } from 'fractional-indexing-jittered';
 import { FileTask, InsertablePage } from '@docmost/db/types/entity.types';
 import { canonicalizeFootnotes } from '@docmost/editor-ext';
-import { markdownToProseMirror } from '@docmost/prosemirror-markdown';
+import {
+  markdownToProseMirror,
+  normalizeForeignMarkdown,
+} from '@docmost/prosemirror-markdown';
 import { getProsemirrorContent } from '../../../common/helpers/prosemirror/utils';
 import { formatImportHtml } from '../utils/import-formatter';
-import { normalizeForeignMarkdown } from '../utils/foreign-markdown';
 import {
   buildAttachmentCandidates,
   collectMarkdownAndHtmlFiles,

apps/server/src/integrations/import/services/import.service.ts

@@ -18,8 +18,10 @@ import { generateJitteredKeyBetween } from 'fractional-indexing-jittered';
 import { TiptapTransformer } from '@hocuspocus/transformer';
 import * as Y from 'yjs';
 import { canonicalizeFootnotes } from '@docmost/editor-ext';
-import { markdownToProseMirror } from '@docmost/prosemirror-markdown';
-import { normalizeForeignMarkdown } from '../utils/foreign-markdown';
+import {
+  markdownToProseMirror,
+  normalizeForeignMarkdown,
+} from '@docmost/prosemirror-markdown';
 import {
   FileTaskStatus,
   FileTaskType,

apps/server/src/integrations/queue/processors/general-queue.processor.comment-mark.spec.ts

@@ -139,13 +139,19 @@ describe('GeneralQueueProcessor — COMMENT_MARK_UPDATE (#399)', () => {
     );
   });
 
-  it('skips (no throw) when the comment row has vanished', async () => {
+  it('reconcile (#496): comment row vanished → strips the orphan anchor mark', async () => {
     const { proc, collaborationGateway, commentRepo } = makeProc();
     commentRepo.findById.mockResolvedValue(undefined);
 
     await expect(
       proc.process(job({ ...base, action: 'resolve', ts: 1000 })),
     ).resolves.toBeUndefined();
-    expect(collaborationGateway.handleYjsEvent).not.toHaveBeenCalled();
+    // A resolve/unresolve mark job whose comment row is gone leaves a silent
+    // orphan; the worker self-heals by stripping the anchor instead of returning.
+    expect(collaborationGateway.handleYjsEvent).toHaveBeenCalledWith(
+      'deleteCommentMark',
+      'page.page-1',
+      { commentId: 'c-1', user: { id: 'user-1' } },
+    );
   });
 });

apps/server/src/integrations/queue/processors/general-queue.processor.ts

@@ -95,7 +95,8 @@ export class GeneralQueueProcessor
    * #399: apply a comment's inline-mark mirror in the collab Y.Doc, off the HTTP
    * critical path. Runs the SAME gateway path the synchronous comment.service
    * code used (byte-identical mark op):
-   *   - resolve / unresolve → resolveCommentMark (flip the `resolved` attribute);
+   *   - resolve / unresolve → resolveCommentMark (flip the `resolved` attribute),
+   *     OR strip an orphan anchor when the comment row has vanished (#496);
    *   - delete → deleteCommentMark (strip the ephemeral-suggestion anchor #329).
    * The op is idempotent, so a BullMQ retry is safe. Throwing propagates to
    * WorkerHost → the job is retried and, on exhaustion, surfaces in failed-job
@@ -133,7 +134,18 @@ export class GeneralQueueProcessor
     // of this resolve), skip it rather than flip the mark to a stale state.
     const comment = await this.commentRepo.findById(commentId);
     if (!comment) {
-      // The comment vanished (e.g. hard-deleted) → nothing left to mirror.
+      // #496 reconcile: the comment row is GONE (e.g. an ephemeral apply/dismiss
+      // hard-deleted it while this resolve/unresolve mark job sat in the queue),
+      // but its inline anchor may still live in the doc — a silent orphan mark
+      // pointing at a comment that no longer exists. Self-heal by stripping it
+      // instead of just returning: this closes the divergence the fire-and-forget
+      // resolve/unresolve enqueue (comment.service resolveComment) could leave.
+      // Idempotent — deleteCommentMark on an already-absent mark is a no-op.
+      await this.getCollaborationGateway().handleYjsEvent(
+        'deleteCommentMark',
+        documentName,
+        { commentId, user },
+      );
       return;
     }
     const wantResolved = action === 'resolve';

packages/editor-ext/src/index.ts

@@ -1,4 +1,5 @@
 export * from "./lib/trailing-node";
+export * from "./lib/code";
 export * from "./lib/comment/comment";
 export * from "./lib/utils";
 export * from "./lib/math";

packages/editor-ext/src/lib/code.ts

@@ -0,0 +1,20 @@
+import { Code as TiptapCode } from "@tiptap/extension-code";
+
+// #515: canonical inline `code` mark for Docmost.
+//
+// Tiptap's stock Code mark (via StarterKit) declares `excludes: "_"`, which
+// makes it exclude EVERY other inline mark: applying `code` drops any co-
+// occurring bold/italic/… on both the HTML->PM import and editor transactions.
+// That silently stripped emphasis adjacent to inline code (`` **`--flag`** ``
+// lost its bold on markdown import). CommonMark nests them (`<strong><code>`),
+// so Docmost lets `code` combine with all marks by overriding `excludes` to the
+// empty string (excludes nothing).
+//
+// This is the SINGLE shared source imported by the live editor, the collab
+// server and the comment editor schemas. The markdown-import mirror in
+// @docmost/prosemirror-markdown re-declares the same override locally (it must
+// not pull this React-aware package into its node runtime) and a parity test
+// keeps the two in lockstep.
+export const Code = TiptapCode.extend({
+  excludes: "",
+});

packages/git-sync/src/engine/stabilize.ts

@@ -72,7 +72,13 @@ export async function stabilizePageFile(
  * keeps re-pulls of an unchanged page byte-identical (no churn, loop-guard).
  */
 export async function stabilizePageBody(content: unknown): Promise<string> {
-  const md1 = convertProseMirrorToMarkdown(content);
+  // git-sync is the LOSSLESS mirror path, so run the serializer in `strict`
+  // mode: a node/mark type the converter has no case for (e.g. one added to the
+  // schema without a matching serializer arm) throws a ConverterLossError here
+  // rather than silently degrading — surfacing the loss loudly at write time
+  // instead of committing a lossy file. Valid content (every current schema type
+  // has a case) is unaffected.
+  const md1 = convertProseMirrorToMarkdown(content, { strict: true });
   const doc2 = await markdownToProseMirror(md1);
-  return convertProseMirrorToMarkdown(doc2);
+  return convertProseMirrorToMarkdown(doc2, { strict: true });
 }

packages/git-sync/test/stabilize.test.ts

@@ -4,6 +4,7 @@ import { stabilizePageFile, type PageMeta } from '../src/engine/stabilize.js';
 // global DOM via jsdom at module load time (required for @tiptap/html under Node).
 import { markdownToProseMirror } from '@docmost/prosemirror-markdown';
 import { parseDocmostMarkdown } from '@docmost/prosemirror-markdown';
+import { ConverterLossError } from '@docmost/prosemirror-markdown';
 
 // stabilize.ts (SPEC §11 normalize-on-write) was 0% covered (only the gated e2e
 // touched it). stabilizePageFile is import-testable: build a small ProseMirror
@@ -66,6 +67,23 @@ describe('stabilizePageFile — normalize-on-write fixpoint (SPEC §11)', () =>
     expect(body1).toContain('data-src="/d.drawio"');
   });
 
+  it('runs the serializer in STRICT mode — an unmappable node throws, not a lossy write (#493)', async () => {
+    // git-sync is the lossless mirror path: a node type the converter has no
+    // case for (here a fabricated one, standing in for a schema type added
+    // without a matching serializer arm) must surface loudly at write time
+    // rather than being silently flattened into a lossy .md file.
+    const content = {
+      type: 'doc',
+      content: [
+        { type: 'paragraph', content: [{ type: 'text', text: 'ok' }] },
+        { type: 'quantumWidget', content: [{ type: 'text', text: 'lost?' }] },
+      ],
+    };
+    await expect(stabilizePageFile(content, meta)).rejects.toBeInstanceOf(
+      ConverterLossError,
+    );
+  });
+
   it('already-stable content is unchanged by the pass (idempotent)', async () => {
     // Plain prose is already a fixpoint; stabilizing it once and twice agree.
     const content = {

packages/mcp/src/client/comments.ts

@@ -450,6 +450,12 @@ export function CommentsMixin<TBase extends GConstructor<DocmostClientContext>>(
     // can surface the closest-block / spans-multiple-blocks hint built from the
     // LIVE document (the pre-check page is not in scope there).
     let liveNotFoundError: Error | null = null;
+    // #496: the RAW substring the mark actually covers in the LIVE doc. The
+    // stored selection (payload.selection) came from a DEBOUNCED REST snapshot,
+    // which can differ from the live doc — and apply compares the marked live
+    // text to the stored selection strictly, so a stale snapshot 409s on EVERY
+    // apply. Captured here (same doc version the mark is set in) and synced below.
+    let liveAnchoredSelection: string | null = null;
     try {
       const collabToken = await this.getCollabTokenWithReauth();
       // Open the collab doc by the canonical UUID, never the slugId (#260). The
@@ -489,6 +495,12 @@ export function CommentsMixin<TBase extends GConstructor<DocmostClientContext>>(
           }
           if (applyAnchorInDoc(doc, selection as string, newCommentId)) {
             anchored = true;
+            // For a suggestion, re-read the exact substring now under the mark
+            // (the mark is an attribute, so it does not change the raw text) to
+            // sync as the stored expectedText after the mutation resolves.
+            if (hasSuggestion) {
+              liveAnchoredSelection = getAnchoredText(doc, selection as string);
+            }
             return doc;
           }
           // Selection text not found in the LIVE document: abort the write. The
@@ -527,6 +539,36 @@ export function CommentsMixin<TBase extends GConstructor<DocmostClientContext>>(
       );
     }
 
+    // #496: sync the stored selection (== apply-time expectedText) to the RAW
+    // substring the mark actually covers in the LIVE doc when it diverged from
+    // the debounced REST snapshot we stored at create time. Without this, apply
+    // strictly compares the marked live text to a stale stored selection and
+    // 409s every time. Best-effort: the comment is already correctly anchored, so
+    // a resync failure must NOT roll it back — it only risks a later apply 409,
+    // which we surface as a soft warning.
+    if (
+      hasSuggestion &&
+      liveAnchoredSelection != null &&
+      liveAnchoredSelection !== payload.selection
+    ) {
+      try {
+        await this.client.post("/comments/resync-suggestion-anchor", {
+          commentId: newCommentId,
+          selection: liveAnchoredSelection,
+        });
+        // Reflect the corrected anchor in the returned comment.
+        if (result.data) result.data.selection = liveAnchoredSelection;
+      } catch (e) {
+        if (process.env.DEBUG) {
+          console.error("Failed to resync suggestion anchor:", e);
+        }
+        result.warning =
+          "The suggestion was anchored, but its stored selection could not be " +
+          "synced to the live document; applying it may report a conflict if the " +
+          "text changed. Re-create the suggestion if Apply fails.";
+      }
+    }
+
     // Soft warning (like editPageText): the selection only matched after
     // stripping markdown, so the caller likely quoted a styled fragment.
     if (anchorNormalized) {

packages/mcp/src/lib/collaboration.ts

@@ -10,7 +10,10 @@ import { JSDOM } from "jsdom";
 // handled there). MCP consumes it directly instead of maintaining its own
 // drifted marked pipeline; only the collab/yjs write glue and the footnote
 // canonicalization wrapper stay mcp-side.
-import { markdownToProseMirror } from "@docmost/prosemirror-markdown";
+import {
+  markdownToProseMirror,
+  normalizeAgentMarkdown,
+} from "@docmost/prosemirror-markdown";
 import { docmostExtensions, docmostSchema } from "./docmost-schema.js";
 import { withPageLock } from "./page-lock.js";
 import {
@@ -20,6 +23,7 @@ import {
 } from "@docmost/prosemirror-markdown";
 import { canonicalizeFootnotes } from "./footnote-canonicalize.js";
 import { normalizeAndMergeFootnotes } from "./footnote-normalize-merge.js";
+import { regraftResolvedComments } from "./comment-anchor.js";
 import { VerifyReport } from "./diff.js";
 import { acquireCollabSession } from "./collab-session.js";
 
@@ -97,6 +101,15 @@ global.WebSocket = WebSocket;
  * plain `markdownToProseMirror` (no canonicalization) — safe now because inline
  * `^[body]` footnotes carry their body at the reference point, so a comment can
  * no longer produce a reference-less footnote definition to be dropped.
+ *
+ * #493: `normalizeAgentMarkdown` runs FIRST, so an agent's `updatePageMarkdown`
+ * body gets the SAME GFM `[^id]` reference-footnote -> inline `^[body]` rewrite as
+ * the server import path (instead of the reference leaking as literal text / a
+ * bogus link). It DELIBERATELY does NOT strip a leading YAML front-matter block:
+ * a full-body agent rewrite that opens with a `---…---` is (almost) always a
+ * horizontalRule the serializer emitted, and stripping it would silently drop the
+ * page's leading content (#493 review). The front-matter strip stays on the
+ * server FILE-import boundary only (`normalizeForeignMarkdown`).
  */
 export async function markdownToProseMirrorCanonical(
   markdownContent: string,
@@ -105,7 +118,9 @@ export async function markdownToProseMirrorCanonical(
   // canonicalizing, so the canonicalizer re-hangs references and drops the
   // now-orphaned duplicate definitions.
   return canonicalizeFootnotes(
-    normalizeAndMergeFootnotes(await markdownToProseMirror(markdownContent)),
+    normalizeAndMergeFootnotes(
+      await markdownToProseMirror(normalizeAgentMarkdown(markdownContent)),
+    ),
   );
 }
 
@@ -344,6 +359,12 @@ export async function updatePageContentRealtime(
     pageId,
     collabToken,
     baseUrl,
-    () => tiptapJson,
+    // #493: an agent read HIDES resolved-comment anchors (#337), so the markdown
+    // it sends here no longer carries them — a naive full rewrite would erase
+    // every resolved comment mark. Re-graft the resolved marks from the LIVE doc
+    // onto the matching text in the freshly-imported body. Active comments are
+    // untouched (they ride through the markdown themselves); a resolved span whose
+    // text the agent changed simply does not re-anchor and is dropped.
+    (liveDoc) => regraftResolvedComments(liveDoc, tiptapJson),
   );
 }

packages/mcp/src/lib/comment-anchor.ts

@@ -312,10 +312,9 @@ export function canAnchorInDoc(doc: any, selection: string): boolean {
 function spliceCommentMark(
   blockContent: any[],
   match: AnchorMatch,
-  commentId: string,
+  commentMark: any,
 ): void {
   const { startChild, startOffset, endChild, endOffset } = match;
-  const commentMark = makeCommentMark(commentId);
   const fragments: any[] = [];
 
   for (let k = startChild; k <= endChild; k++) {
@@ -451,6 +450,22 @@ export function applyAnchorInDoc(
   doc: any,
   selection: string,
   commentId: string,
+): boolean {
+  return applyCommentMarkInDoc(doc, selection, makeCommentMark(commentId));
+}
+
+/**
+ * Core of {@link applyAnchorInDoc}, but splices an ARBITRARY comment mark object
+ * (not just a fresh `{ commentId, resolved:false }`) across the first matching
+ * range. This lets a caller re-apply a mark that carries `resolved:true` and any
+ * other stored attrs. Depth-first (same order as canAnchorInDoc); mutates in
+ * place on the first matching block and returns true, else returns false without
+ * mutating.
+ */
+export function applyCommentMarkInDoc(
+  doc: any,
+  selection: string,
+  commentMark: any,
 ): boolean {
   const { selection: effective, found } = resolveAnchorSelection(doc, selection);
   if (!found) return false;
@@ -459,7 +474,7 @@ export function applyAnchorInDoc(
     if (!Array.isArray(node.content)) return false;
     const match = findAnchorInBlock(node.content, effective);
     if (match) {
-      spliceCommentMark(node.content, match, commentId);
+      spliceCommentMark(node.content, match, commentMark);
       return true;
     }
     for (const child of node.content) {
@@ -471,3 +486,97 @@ export function applyAnchorInDoc(
   };
   return visit(doc, 0);
 }
+
+/** A resolved inline-comment span lifted from a doc: its mark + anchored text. */
+export interface ResolvedCommentSpan {
+  commentId: string;
+  /** The full comment mark (carrying `resolved:true` + any stored attrs). */
+  mark: any;
+  /** The concatenated raw text the mark spans — used as the re-anchor selection. */
+  text: string;
+}
+
+/** True when a text node carries a RESOLVED comment mark; returns that mark. */
+function resolvedCommentMarkOf(node: any): any | null {
+  if (!node || node.type !== "text" || !Array.isArray(node.marks)) return null;
+  return (
+    node.marks.find(
+      (m: any) =>
+        m && m.type === "comment" && m.attrs?.resolved === true && m.attrs?.commentId,
+    ) || null
+  );
+}
+
+/**
+ * Collect every RESOLVED inline-comment span in `doc`, in document order. Within
+ * each block's direct content, a maximal run of consecutive text nodes sharing
+ * the same resolved `commentId` is ONE span; its concatenated raw text is the
+ * selection used to re-anchor it elsewhere. Active (unresolved) comment marks are
+ * ignored — they survive a markdown round-trip on their own (a page read emits
+ * their `<span data-comment-id>` wrapper), whereas resolved anchors are hidden
+ * from agent reads (#337) and would be erased by a full-body markdown rewrite.
+ */
+export function collectResolvedCommentSpans(doc: any): ResolvedCommentSpan[] {
+  const spans: ResolvedCommentSpan[] = [];
+  const visit = (node: any, depth: number): void => {
+    if (depth > MAX_DEPTH || !node || typeof node !== "object") return;
+    if (!Array.isArray(node.content)) return;
+    const content = node.content;
+    let i = 0;
+    while (i < content.length) {
+      const mark = resolvedCommentMarkOf(content[i]);
+      if (mark) {
+        const commentId = mark.attrs.commentId;
+        let text = "";
+        let j = i;
+        while (j < content.length) {
+          const mj = resolvedCommentMarkOf(content[j]);
+          if (!mj || mj.attrs.commentId !== commentId) break;
+          text += typeof content[j].text === "string" ? content[j].text : "";
+          j++;
+        }
+        if (text.length > 0) spans.push({ commentId, mark, text });
+        i = j > i ? j : i + 1;
+      } else {
+        i++;
+      }
+    }
+    for (const child of content) {
+      if (child && typeof child === "object" && Array.isArray(child.content)) {
+        visit(child, depth + 1);
+      }
+    }
+  };
+  visit(doc, 0);
+  return spans;
+}
+
+/**
+ * Re-graft RESOLVED comment marks from `oldDoc` onto matching text ranges in
+ * `newDoc`, returning a NEW doc (never mutates the inputs).
+ *
+ * WHY (#493): an agent read hides resolved-comment anchors (#337), so the
+ * markdown it sends to a FULL-body rewrite (`updatePageMarkdown`) no longer
+ * carries them — a naive full write would erase every resolved comment mark.
+ * This restores them: each resolved span from the previous document is re-anchored
+ * onto the SAME text in the newly-imported body (first occurrence, using the
+ * shared anchoring / markdown-strip fallback), preserving `resolved:true` and the
+ * stored attrs. A span whose text the agent changed or deleted simply does not
+ * re-anchor and is dropped (its anchor is gone; it was already resolved). Active
+ * comments are untouched — they ride through the markdown themselves.
+ */
+export function regraftResolvedComments<T = any>(oldDoc: any, newDoc: T): T {
+  if (!newDoc || typeof newDoc !== "object") return newDoc;
+  const spans = collectResolvedCommentSpans(oldDoc);
+  if (spans.length === 0) return newDoc;
+  const out =
+    typeof structuredClone === "function"
+      ? structuredClone(newDoc)
+      : (JSON.parse(JSON.stringify(newDoc)) as T);
+  for (const span of spans) {
+    // Clone the mark so the new document never shares a mark object with oldDoc.
+    const markClone = { type: "comment", attrs: { ...span.mark.attrs } };
+    applyCommentMarkInDoc(out, span.text, markClone);
+  }
+  return out;
+}

packages/mcp/src/lib/text-normalize.ts

@@ -1,64 +1,30 @@
 /**
- * Locator normalization: strip inline markdown wrappers and trailing
- * decoration from a LOCATOR string so a find/anchor that the model wrote with
- * markdown (or a stray emoji) can still match the document's plain text.
+ * Locator normalization helpers for mcp. The two PRIMITIVES —
+ * `stripInlineMarkdown` (lenient locator normalizer) and `stripWrappersAndLinks`
+ * (strict balanced-wrapper/link collapse) — live in the canonical package
+ * `@docmost/prosemirror-markdown` (#493 dedup: they used to be forked verbatim
+ * here). This module now only re-exports `stripInlineMarkdown` and adds the two
+ * mcp-only helpers built on top: `stripBalancedWrappers` and `closestBlockHint`.
  *
- * This is used ONLY as a fallback for LOCATING (after an exact match fails);
- * it is never applied to replacement text or inserted node content, so no
- * formatting is ever lost.
+ * They are used ONLY as a fallback for LOCATING (after an exact match fails) and
+ * for formatting-vs-plain intent detection; never applied to replacement text or
+ * inserted node content, so no formatting is ever lost.
  */
+import {
+  stripInlineMarkdown,
+  stripWrappersAndLinks,
+} from "@docmost/prosemirror-markdown";
 
-/** Maximum unwrap passes, so pathological/nested input cannot loop forever. */
-const MAX_PASSES = 8;
+// Re-export the canonical locator normalizer so mcp call sites keep importing it
+// from `./text-normalize.js` unchanged.
+export { stripInlineMarkdown };
 
 /**
- * Inline emphasis/code/strikethrough wrappers, strong BEFORE emphasis so
- * `**x**` collapses to `x` rather than leaving a stray `*x*`. Each pattern is
- * non-greedy and capture group 1 is the inner text. Applied repeatedly until
- * the string stops changing (nested wrappers like `**_x_**`).
- */
-const WRAPPER_PATTERNS: RegExp[] = [
-  /\*\*([^*]+?)\*\*/g, // **x**
-  /__([^_]+?)__/g, // __x__
-  /~~([^~]+?)~~/g, // ~~x~~
-  /\*([^*]+?)\*/g, // *x*
-  /_([^_]+?)_/g, // _x_
-  /``([^`]+?)``/g, // ``x``
-  /`([^`]+?)`/g, // `x`
-];
-
-/** Links/images -> their visible text. `!?` covers both `[t](u)` and `![a](s)`. */
-const LINK_IMAGE_RE = /!?\[([^\]]*)\]\([^)]*\)/g;
-
-/**
- * Apply ONLY the two balanced/link passes shared by both normalizers: first
- * collapse links/images to their visible text, then collapse balanced inline
- * wrappers repeatedly until stable. Does NOT trim decoration, does NOT guard
- * against an empty result — it returns exactly the transformed string.
- */
-function stripWrappersAndLinks(s: string): string {
-  // 1. Links/images -> their visible text.
-  let out = s.replace(LINK_IMAGE_RE, "$1");
-
-  // 2. Strip balanced wrappers, repeating until the string is stable so nested
-  //    wrappers (`**_x_**`) and adjacent runs both collapse.
-  for (let pass = 0; pass < MAX_PASSES; pass++) {
-    const before = out;
-    for (const re of WRAPPER_PATTERNS) {
-      out = out.replace(re, "$1");
-    }
-    if (out === before) break;
-  }
-  return out;
-}
-
-/**
- * STRICT formatting detector — distinct from the lenient locator
- * normalization below. It strips ONLY what unambiguously is markdown markup:
- *  1. links/images `[text](url)` -> `text`, `![alt](src)` -> `alt`, and
- *  2. balanced inline `**`/`__`/`~~`/`*`/`_`/`` ` `` wrappers (repeat-until-stable),
- * and DELIBERATELY does NOT trim leading/trailing whitespace, emoji, or lone
- * marker chars (the lenient extras `stripInlineMarkdown` does in its step 3).
+ * STRICT formatting detector — distinct from the lenient locator normalization.
+ * It strips ONLY what unambiguously is markdown markup (links/images to visible
+ * text, and balanced inline `**`/`__`/`~~`/`*`/`_`/`` ` `` wrappers) and
+ * DELIBERATELY does NOT trim leading/trailing whitespace, emoji, or lone marker
+ * chars (the lenient extras `stripInlineMarkdown` does).
  *
  * It exists ONLY to recognize formatting-vs-plain INTENT in `applyTextEdits`
  * (deciding whether find/replace differ purely by markdown markers). Because it
@@ -77,44 +43,6 @@ export function stripBalancedWrappers(s: string): string {
   return stripWrappersAndLinks(s);
 }
 
-/**
- * Conservatively strip inline markdown from a locator string.
- *
- * Deterministic, order-fixed steps:
- *  1. Links/images: `[text](url)` -> `text`, `![alt](src)` -> `alt`.
- *  2. Balanced inline wrappers (strong before emphasis, code, strikethrough),
- *     applied repeatedly until stable for nested cases.
- *  3. Trim leading/trailing decoration only: whitespace, leftover marker chars
- *     (`* _ ~ \``) and emoji. Letters/digits and sentence punctuation (`.`/`,`
- *     etc.) are NEVER trimmed.
- *
- * If the result is empty (e.g. the input was only markers like `***`), the
- * ORIGINAL string is returned so a locator can never normalize down to "" and
- * match everything.
- */
-export function stripInlineMarkdown(s: string): string {
-  if (typeof s !== "string" || s.length === 0) return s;
-
-  // 1 + 2. Shared link/image and balanced-wrapper passes.
-  let out = stripWrappersAndLinks(s);
-
-  // 3. Trim leading/trailing decoration: whitespace, leftover markdown markers,
-  //    and emoji (Extended_Pictographic plus the VS16 / ZWJ joiners, plus the
-  //    regional-indicator range U+1F1E6–U+1F1FF for flag emoji, which are NOT
-  //    Extended_Pictographic). The `u` flag enables the Unicode property escape.
-  //    Anchored runs only — interior text and sentence punctuation are untouched.
-  const DECORATION =
-    "[\\s*_~\\x60\\p{Extended_Pictographic}\\u{1F1E6}-\\u{1F1FF}\\u{FE0F}\\u{200D}]+";
-  out = out
-    .replace(new RegExp("^" + DECORATION, "u"), "")
-    .replace(new RegExp(DECORATION + "$", "u"), "");
-
-  // 4. Never normalize a locator down to nothing.
-  if (out.length === 0) return s;
-
-  return out;
-}
-
 /**
  * Build a bounded "closest text" hint for an anchor/find MISS, shared by
  * editPageText (json-edit) and createComment (client) so both surface the

packages/mcp/test/mock/create-comment.test.mjs

@@ -553,6 +553,189 @@ test("suggestedText: the stored selection is the doc's RAW typographic substring
   assert.equal(createPayload.suggestedText, "goodbye");
 });
 
+// -----------------------------------------------------------------------------
+// 8b) #496: the DEBOUNCED REST snapshot (pages/info) DIFFERS from the LIVE collab
+//     doc (mutatePage) — the doc moved on in the debounce window. The stored
+//     selection is captured from the snapshot at create time, but the mark is set
+//     in the live doc, so apply would 409 forever. After anchoring, the client
+//     re-reads the RAW substring under the mark from the LIVE doc and POSTs it to
+//     /comments/resync-suggestion-anchor so the stored expectedText matches.
+// -----------------------------------------------------------------------------
+test("suggestion: re-syncs the stored selection to the LIVE doc substring when the REST snapshot lagged", async () => {
+  let createPayload = null;
+  let resyncPayload = null;
+
+  const { baseURL } = await spawn(async (req, res) => {
+    const raw = await readBody(req);
+    if (req.url === "/api/auth/login") {
+      sendJson(res, 200, { success: true }, {
+        "Set-Cookie": "authToken=t; Path=/; HttpOnly",
+      });
+      return;
+    }
+    if (req.url === "/api/pages/info") {
+      // DEBOUNCED snapshot: ASCII quotes (stale — the live doc has since been
+      // typographically corrected).
+      sendJson(res, 200, {
+        data: {
+          id: "33333333-3333-3333-3333-333333333333",
+          content: {
+            type: "doc",
+            content: [
+              {
+                type: "paragraph",
+                content: [{ type: "text", text: 'he said "hello" loudly' }],
+              },
+            ],
+          },
+        },
+      });
+      return;
+    }
+    if (req.url === "/api/comments/create") {
+      createPayload = JSON.parse(raw);
+      sendJson(res, 200, {
+        data: {
+          id: "cmt-resync-1",
+          content: createPayload.content,
+          selection: createPayload.selection,
+          suggestedText: createPayload.suggestedText,
+          type: createPayload.type,
+        },
+      });
+      return;
+    }
+    if (req.url === "/api/comments/resync-suggestion-anchor") {
+      resyncPayload = JSON.parse(raw);
+      sendJson(res, 200, { data: { id: "cmt-resync-1" } });
+      return;
+    }
+    sendJson(res, 404, { message: "not found" });
+  });
+
+  class TestClient extends DocmostClient {
+    async getCollabTokenWithReauth() {
+      return "collab-token";
+    }
+    async resolvePageId() {
+      return "33333333-3333-3333-3333-333333333333";
+    }
+    async mutatePage(pageId, collabToken, apiUrl, transform) {
+      // LIVE doc: SMART quotes (what the mark is actually set over).
+      const doc = {
+        type: "doc",
+        content: [
+          {
+            type: "paragraph",
+            content: [{ type: "text", text: "he said “hello” loudly" }],
+          },
+        ],
+      };
+      const out = transform(doc);
+      return { doc: out, verify: { ok: true } };
+    }
+  }
+
+  const client = new TestClient(baseURL, "user@example.com", "pw");
+
+  const result = await client.createComment(
+    "33333333-3333-3333-3333-333333333333",
+    "please change",
+    "inline",
+    '"hello"', // ASCII quotes
+    undefined,
+    "goodbye",
+  );
+
+  assert.equal(result.success, true);
+  assert.equal(result.anchored, true);
+  // Create stored the STALE snapshot substring (ASCII quotes).
+  assert.equal(createPayload.selection, '"hello"');
+  // …then the client re-synced to the LIVE marked substring (smart quotes).
+  assert.ok(resyncPayload, "/comments/resync-suggestion-anchor must be called");
+  assert.equal(resyncPayload.commentId, "cmt-resync-1");
+  assert.equal(resyncPayload.selection, "“hello”");
+  // The returned comment reflects the corrected anchor.
+  assert.equal(result.data.selection, "“hello”");
+});
+
+// -----------------------------------------------------------------------------
+// 8c) #496: when the REST snapshot and the LIVE doc AGREE, no resync round-trip
+//     is made (the common case must stay a single write).
+// -----------------------------------------------------------------------------
+test("suggestion: no resync call when the snapshot already matches the live doc", async () => {
+  let resyncCalls = 0;
+
+  const { baseURL } = await spawn(async (req, res) => {
+    const raw = await readBody(req);
+    if (req.url === "/api/auth/login") {
+      sendJson(res, 200, { success: true }, {
+        "Set-Cookie": "authToken=t; Path=/; HttpOnly",
+      });
+      return;
+    }
+    if (req.url === "/api/pages/info") {
+      sendJson(res, 200, {
+        data: {
+          id: "44444444-4444-4444-4444-444444444444",
+          content: {
+            type: "doc",
+            content: [
+              { type: "paragraph", content: [{ type: "text", text: "Hello brave world" }] },
+            ],
+          },
+        },
+      });
+      return;
+    }
+    if (req.url === "/api/comments/create") {
+      const p = JSON.parse(raw);
+      sendJson(res, 200, {
+        data: { id: "cmt-nosync-1", content: p.content, selection: p.selection, suggestedText: p.suggestedText, type: p.type },
+      });
+      return;
+    }
+    if (req.url === "/api/comments/resync-suggestion-anchor") {
+      resyncCalls++;
+      sendJson(res, 200, { data: {} });
+      return;
+    }
+    sendJson(res, 404, { message: "not found" });
+  });
+
+  class TestClient extends DocmostClient {
+    async getCollabTokenWithReauth() {
+      return "collab-token";
+    }
+    async resolvePageId() {
+      return "44444444-4444-4444-4444-444444444444";
+    }
+    async mutatePage(pageId, collabToken, apiUrl, transform) {
+      const doc = {
+        type: "doc",
+        content: [
+          { type: "paragraph", content: [{ type: "text", text: "Hello brave world" }] },
+        ],
+      };
+      const out = transform(doc);
+      return { doc: out, verify: { ok: true } };
+    }
+  }
+
+  const client = new TestClient(baseURL, "user@example.com", "pw");
+  const result = await client.createComment(
+    "44444444-4444-4444-4444-444444444444",
+    "rename",
+    "inline",
+    "brave",
+    undefined,
+    "bold",
+  );
+
+  assert.equal(result.anchored, true);
+  assert.equal(resyncCalls, 0, "matching snapshot must NOT trigger a resync round-trip");
+});
+
 // -----------------------------------------------------------------------------
 // 8) #408: a not-found selection error QUOTES the closest block text so the
 //    model can self-correct instead of blind-retrying.

packages/mcp/test/mock/markdown-patch-insert.test.mjs

@@ -108,6 +108,17 @@ async function spawnCollabStack(seedDoc) {
   return { state, baseURL };
 }
 
+// y-prosemirror stores an OVERLAPPING mark (one whose type does not exclude
+// itself — e.g. `comment`, and since #515 `code` with `excludes: ""`) under a
+// HASHED Yjs attribute key `name--<8-char hash>` so several may coexist on a
+// range. The real read path (yDocToProsemirrorJSON) strips that suffix back to
+// the bare mark name via this exact regex; mirror it here so this minimal decoder
+// reports the same mark names Docmost actually returns (without it an overlapping
+// `code` would leak as `code--<hash>`).
+const hashedMarkNameRegex = /(.*)(--[a-zA-Z0-9+/=]{8})$/;
+const yattr2markname = (attrName) =>
+  hashedMarkNameRegex.exec(attrName)?.[1] ?? attrName;
+
 // Minimal XmlFragment -> ProseMirror JSON decode, mirroring the shape Docmost
 // stores. Reads element name as node type, attributes as attrs, and recurses into
 // children; text nodes carry their string.
@@ -121,8 +132,8 @@ function fragmentToJson(frag) {
         if (d.attributes && Object.keys(d.attributes).length) {
           node.marks = Object.entries(d.attributes).map(([type, attrs]) =>
             attrs && typeof attrs === "object" && Object.keys(attrs).length
-              ? { type, attrs }
-              : { type },
+              ? { type: yattr2markname(type), attrs }
+              : { type: yattr2markname(type) },
           );
         }
         return node;

packages/mcp/test/unit/regraft-resolved-comments.test.mjs

@@ -0,0 +1,107 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+
+import {
+  collectResolvedCommentSpans,
+  regraftResolvedComments,
+  applyCommentMarkInDoc,
+} from "../../build/lib/comment-anchor.js";
+
+/**
+ * #493 commit 6 — resolved-comment anchors must survive a full markdown rewrite
+ * (updatePageMarkdown). An agent read HIDES resolved anchors (#337), so its
+ * markdown drops them; a naive full write would erase the resolved comment marks.
+ * `regraftResolvedComments(oldDoc, newDoc)` re-anchors them onto the matching
+ * text. These exercise the real anchoring (no mock).
+ */
+
+const doc = (...content) => ({ type: "doc", content });
+const para = (...content) => ({ type: "paragraph", content });
+const text = (t, marks) => (marks ? { type: "text", text: t, marks } : { type: "text", text: t });
+const resolvedComment = (commentId) => ({ type: "comment", attrs: { commentId, resolved: true } });
+const activeComment = (commentId) => ({ type: "comment", attrs: { commentId, resolved: false } });
+
+/** The comment mark on a text node, or null. */
+function commentMarkOf(node) {
+  const marks = Array.isArray(node?.marks) ? node.marks : [];
+  return marks.find((m) => m && m.type === "comment") || null;
+}
+/** Flatten every text node in a doc (deep). */
+function textNodes(node, out = []) {
+  if (!node || typeof node !== "object") return out;
+  if (node.type === "text") out.push(node);
+  if (Array.isArray(node.content)) for (const c of node.content) textNodes(c, out);
+  return out;
+}
+
+test("collectResolvedCommentSpans: only resolved marks, concatenated across a run", () => {
+  const old = doc(
+    para(
+      text("keep "),
+      text("resolved bit", [resolvedComment("r1")]),
+      text(" and "),
+      text("active bit", [activeComment("a1")]),
+    ),
+  );
+  const spans = collectResolvedCommentSpans(old);
+  assert.equal(spans.length, 1);
+  assert.equal(spans[0].commentId, "r1");
+  assert.equal(spans[0].text, "resolved bit");
+  assert.equal(spans[0].mark.attrs.resolved, true);
+});
+
+test("regraft restores a resolved mark the agent's markdown dropped", () => {
+  // OLD doc has a resolved comment on "important note".
+  const old = doc(para(text("An "), text("important note", [resolvedComment("r1")]), text(" here.")));
+  // NEW doc (re-imported from the agent's markdown) has the SAME text but NO
+  // comment mark — the resolved anchor was hidden on read.
+  const fresh = doc(para(text("An important note here.")));
+
+  const out = regraftResolvedComments(old, fresh);
+  // Inputs are not mutated.
+  assert.equal(commentMarkOf(textNodes(fresh)[0]), null);
+  // The resolved mark is back on exactly "important note".
+  const marked = textNodes(out).filter((n) => commentMarkOf(n));
+  assert.equal(marked.length, 1);
+  assert.equal(marked[0].text, "important note");
+  assert.equal(commentMarkOf(marked[0]).attrs.commentId, "r1");
+  assert.equal(commentMarkOf(marked[0]).attrs.resolved, true);
+});
+
+test("a resolved span whose text the agent changed is dropped (no re-anchor)", () => {
+  const old = doc(para(text("stale text", [resolvedComment("r1")])));
+  const fresh = doc(para(text("completely rewritten body")));
+  const out = regraftResolvedComments(old, fresh);
+  assert.equal(textNodes(out).filter((n) => commentMarkOf(n)).length, 0);
+});
+
+test("regraft is a no-op when the old doc has no resolved comments", () => {
+  const old = doc(para(text("plain "), text("active", [activeComment("a1")])));
+  const fresh = doc(para(text("plain active")));
+  const out = regraftResolvedComments(old, fresh);
+  assert.equal(textNodes(out).filter((n) => commentMarkOf(n)).length, 0);
+});
+
+test("multiple distinct resolved comments are all restored", () => {
+  const old = doc(
+    para(text("first", [resolvedComment("r1")]), text(" middle "), text("second", [resolvedComment("r2")])),
+  );
+  const fresh = doc(para(text("first middle second")));
+  const out = regraftResolvedComments(old, fresh);
+  const byId = Object.fromEntries(
+    textNodes(out)
+      .filter((n) => commentMarkOf(n))
+      .map((n) => [commentMarkOf(n).attrs.commentId, n.text]),
+  );
+  assert.equal(byId["r1"], "first");
+  assert.equal(byId["r2"], "second");
+});
+
+test("applyCommentMarkInDoc preserves an arbitrary mark's attrs (resolved:true)", () => {
+  const d = doc(para(text("anchor me somewhere")));
+  const ok = applyCommentMarkInDoc(d, "anchor me", { type: "comment", attrs: { commentId: "x9", resolved: true } });
+  assert.equal(ok, true);
+  const marked = textNodes(d).filter((n) => commentMarkOf(n));
+  assert.equal(marked[0].text, "anchor me");
+  assert.equal(commentMarkOf(marked[0]).attrs.resolved, true);
+});

packages/prosemirror-markdown/src/lib/docmost-schema.ts

@@ -16,6 +16,7 @@
  * `@docmost/editor-ext` before updating the snapshot.
  */
 import StarterKit from "@tiptap/starter-kit";
+import { Code } from "@tiptap/extension-code";
 import Image from "@tiptap/extension-image";
 import TaskList from "@tiptap/extension-task-list";
 import TaskItem from "@tiptap/extension-task-item";
@@ -1481,7 +1482,20 @@ export const docmostExtensions = [
     codeBlock: {},
     heading: {},
     link: { openOnClick: false },
+    // #515: disable StarterKit's bundled inline `code` mark so it can be replaced
+    // by the local override below. StarterKit's `code` inherits tiptap's
+    // `excludes: "_"`, which strips every co-occurring mark on HTML->PM import
+    // (`generateJSON`) — so `` **`--flag`** `` lost its bold. This mirror is a
+    // DELIBERATE standalone copy (it must not pull @docmost/editor-ext into the
+    // node import runtime — that would drag in React/node-views; see #293), so
+    // the `excludes: ""` override is declared LOCALLY here and kept in lockstep
+    // with the canonical `Code` in @docmost/editor-ext by a parity test.
+    code: false,
   }),
+  // #515: inline code that COMBINES with other marks (CommonMark-consistent).
+  // `excludes: ""` means the mark excludes nothing, so bold/italic/strike/… may
+  // co-occur with `code` and survive import.
+  Code.extend({ excludes: "" }),
   // Preserve image width/height as the AUTHORED string. Without an explicit
   // parseHTML the stock Image node attribute falls back to tiptap core's
   // `fromString`, which coerces a numeric width like "320" into the number 320

packages/prosemirror-markdown/src/lib/foreign-markdown.ts

@@ -1,7 +1,14 @@
 /**
  * Foreign-markdown normalizer — an input-liberal / output-canonical adapter that
  * runs at the IMPORT boundary, BEFORE the canonical parser
- * (`markdownToProseMirror` from `@docmost/prosemirror-markdown`).
+ * (`markdownToProseMirror`, this package).
+ *
+ * OWNED BY THIS PACKAGE (#493): the normalizer used to live only in
+ * apps/server's import path, so the MCP page-write path (`updatePageMarkdown` ->
+ * `markdownToProseMirrorCanonical`) handled the SAME foreign input differently
+ * (no front-matter strip, no `[^id]` reference-footnote rewrite) than the server
+ * importer. Moving it here — and calling it from `markdownToProseMirrorCanonical`
+ * — makes every canonical import boundary treat foreign markdown identically.
  *
  * The canonical parser is deliberately STRICT: it only understands Docmost's
  * canonical markdown surface (Obsidian-style `> [!type]` callouts, Pandoc/Obsidian
@@ -247,11 +254,18 @@ function convertReferenceFootnotes(markdown: string): string {
 const YAML_FRONT_MATTER_RE = /^\uFEFF?---\n[\s\S]*?\n---\n?/;
 
 /**
- * Normalize a foreign markdown string into Docmost's canonical markdown surface
- * so the strict canonical parser accepts it losslessly: normalize line endings,
- * strip a leading YAML front-matter block, then rewrite GFM reference footnotes
- * into inline footnotes. Add further fixture-driven foreign-surface cases here as
- * they are found.
+ * Normalize a foreign markdown string from a FILE IMPORT into Docmost's canonical
+ * markdown surface so the strict canonical parser accepts it losslessly: normalize
+ * line endings, strip a leading YAML front-matter block, then rewrite GFM reference
+ * footnotes into inline footnotes. Add further fixture-driven foreign-surface cases
+ * here as they are found.
+ *
+ * FRONT-MATTER STRIP IS IMPORT-ONLY (#493 review): use this ONLY at the server
+ * file-import boundary, where a `.md` file really can open with an Obsidian/Hugo
+ * YAML header. Do NOT use it on the canonical AGENT-WRITE path — see
+ * {@link normalizeAgentMarkdown} for why a full-body agent rewrite must NOT strip
+ * a leading `---…---` (it is normally a horizontalRule the serializer emitted, and
+ * stripping it would silently drop the page's leading content).
  */
 export function normalizeForeignMarkdown(markdown: string): string {
   if (!markdown) return markdown;
@@ -264,3 +278,26 @@ export function normalizeForeignMarkdown(markdown: string): string {
   const withoutFrontMatter = src.replace(YAML_FRONT_MATTER_RE, '').trimStart();
   return convertReferenceFootnotes(withoutFrontMatter);
 }
+
+/**
+ * Canonical AGENT-WRITE normalization: normalize line endings and rewrite GFM
+ * `[^id]` reference footnotes to inline `^[body]` — but DELIBERATELY NOT strip a
+ * leading YAML front-matter block.
+ *
+ * WHY the split (#493 review): the reference-footnote rewrite is the drift the
+ * MCP page-write path (`updatePageMarkdown` -> `markdownToProseMirrorCanonical`)
+ * needed unified with the server import (an agent may paste GFM footnotes). The
+ * front-matter strip, however, is a FILE-import concern: on a full-body agent
+ * rewrite a leading `---…---` is (almost) always a `horizontalRule` the
+ * serializer emitted plus a later rule/heading — NOT a foreign YAML header — so
+ * `YAML_FRONT_MATTER_RE` would match it and SILENTLY DELETE the page's leading
+ * content (a page that starts with a horizontal rule and contains a second `---`
+ * lost everything up to it). Agent writes must never lose already-stored content,
+ * so this variant skips the strip. It IS a no-op on canonical serialized content
+ * (which never emits `[^id]:` reference-definition lines).
+ */
+export function normalizeAgentMarkdown(markdown: string): string {
+  if (!markdown) return markdown;
+  const src = markdown.replace(/\r\n/g, '\n');
+  return convertReferenceFootnotes(src);
+}

packages/prosemirror-markdown/src/lib/index.ts

@@ -15,7 +15,10 @@ export {
 } from "./markdown-document.js";
 export type { DocmostMdMeta } from "./markdown-document.js";
 
-export { convertProseMirrorToMarkdown } from "./markdown-converter.js";
+export {
+  convertProseMirrorToMarkdown,
+  ConverterLossError,
+} from "./markdown-converter.js";
 export type { ConvertProseMirrorToMarkdownOptions } from "./markdown-converter.js";
 
 export {
@@ -23,6 +26,19 @@ export {
   markdownToProseMirrorSync,
 } from "./markdown-to-prosemirror.js";
 
+// Foreign-markdown normalizer (#493): the input-liberal pre-pass that rewrites
+// GFM `[^id]` reference footnotes to canonical inline `^[body]`. Two variants:
+// `normalizeForeignMarkdown` (server FILE-import boundary) ALSO strips a leading
+// YAML front-matter block; `normalizeAgentMarkdown` (canonical AGENT-WRITE path,
+// mcp `markdownToProseMirrorCanonical`) does NOT — a full-body agent rewrite must
+// not lose a leading `---…---` horizontalRule to the front-matter strip (#493
+// review). The reference-footnote rewrite is shared so agent + import stay unified
+// where it matters, without the content-losing strip on the write path.
+export {
+  normalizeForeignMarkdown,
+  normalizeAgentMarkdown,
+} from "./foreign-markdown.js";
+
 // The Docmost tiptap schema mirror. Exposed so consumers (and the sync
 // engine's schema-validity regression tests) can build the exact ProseMirror
 // schema the converter targets.
@@ -76,6 +92,17 @@ export type { OutlineEntry } from "./node-ops.js";
 // string (#414: single copy shared by mcp and the CommonJS server app).
 export { parseNodeArg } from "./parse-node-arg.js";
 
+// Locator markdown-stripping (#493 dedup): the single canonical copy of the
+// markdown-tolerant anchor-normalization primitives, imported by mcp's
+// text-normalize.ts instead of a forked duplicate. `stripInlineMarkdown` is the
+// lenient locator normalizer (trims stray decoration); `stripWrappersAndLinks`
+// is the strict balanced-wrapper/link primitive mcp builds `stripBalancedWrappers`
+// on top of.
+export {
+  stripInlineMarkdown,
+  stripWrappersAndLinks,
+} from "./text-normalize.js";
+
 // Inline-footnote authoring convention (#414: single copy, formerly the mcp
 // `footnote-authoring.ts` fork), shared with the importer's `assembleFootnotes`.
 export {

packages/prosemirror-markdown/src/lib/markdown-converter.ts

@@ -33,6 +33,26 @@ import {
  */
 const MAX_NODE_DEPTH = 400;
 
+/**
+ * Thrown by {@link convertProseMirrorToMarkdown} in `strict` mode when it hits a
+ * node or mark type it has no lossless markdown form for (the serializer would
+ * otherwise silently degrade it — drop an unknown mark, flatten an unknown node
+ * to its children). Carries the offending kind/name so a caller (git-sync) can
+ * surface exactly what would have been lost.
+ */
+export class ConverterLossError extends Error {
+  readonly kind: "node" | "mark";
+  readonly typeName: string;
+  constructor(kind: "node" | "mark", typeName: string) {
+    super(
+      `convertProseMirrorToMarkdown: unknown ${kind} type "${typeName}" has no lossless markdown representation (strict mode)`,
+    );
+    this.name = "ConverterLossError";
+    this.kind = kind;
+    this.typeName = typeName;
+  }
+}
+
 /**
  * Options for {@link convertProseMirrorToMarkdown}.
  */
@@ -46,6 +66,23 @@ export interface ConvertProseMirrorToMarkdownOptions {
    * path where resolved anchors MUST be preserved for round-tripping.
    */
   dropResolvedCommentAnchors?: boolean;
+  /**
+   * Optional sink for LOSS warnings. When the serializer reaches a node or mark
+   * type it has no dedicated case for, it degrades gracefully (flattens an
+   * unknown node to its children, drops an unknown mark) — historically a SILENT
+   * data loss. When this array is provided, one human-readable message per such
+   * event is pushed here so the caller can observe (and log) what was degraded.
+   * Not provided by default -> behavior is byte-identical to before for existing
+   * callers.
+   */
+  warnings?: string[];
+  /**
+   * When true, THROW a {@link ConverterLossError} on the FIRST unknown node/mark
+   * instead of degrading silently — a warning becomes a hard error. Used by the
+   * lossless git-sync export path and the converter tests, where an unmapped
+   * type is a bug to surface, not data to quietly drop.
+   */
+  strict?: boolean;
 }
 
 /**
@@ -63,6 +100,70 @@ export interface ConvertProseMirrorToMarkdownOptions {
  * separator is emitted for any other join, so non-list output is unchanged.
  */
 const LIST_MARKER_SEPARATOR = "<!-- -->";
+
+/**
+ * Backslash-escape a leading markdown BLOCK trigger so a serialized paragraph
+ * line re-parses as a PARAGRAPH, not another block. Without this, a paragraph
+ * whose text begins at column 0 with an ATX heading `#`, a blockquote/callout
+ * `>`, a bullet marker `-`/`*`/`+`, an ordered marker `N.`/`N)`, a code fence
+ * (```` ``` ````/`~~~`), a table `|`, or a thematic break (`---`/`***`/`___`,
+ * solid or spaced) silently becomes a heading/list/quote/code block/table/rule
+ * on the next markdown -> ProseMirror import — a known data-loss class (the
+ * thematic-break case drops the text entirely, since a horizontalRule carries
+ * none). CommonMark's escape tokenizer decodes the inserted `\` back to the
+ * literal character on import AND stops the block interpretation, so the line
+ * round-trips byte-exact as paragraph text. Only the FIRST offending character
+ * is escaped (the minimum needed to break block recognition); a line that does
+ * NOT open a block — emphasis `**x**`, an inline code span, ordinary prose — is
+ * returned verbatim, so there is no backslash churn for the common case.
+ *
+ * Applied ONLY to paragraph text, once per `\n`-separated LINE (the paragraph
+ * case splits on `\n` — each hardBreak emits `  \n` — so a trigger on a
+ * continuation line is escaped too): headings/lists/blockquotes legitimately
+ * open with these markers and render them from their own cases. This is the
+ * single, canonical fix for the class the client bridge worked around with a
+ * ZWSP (`gitmost-recording.ts`) and the generative suite self-censored around
+ * (`text-arbitraries.ts`) — both now removed.
+ */
+function escapeLeadingBlockTrigger(line: string): string {
+  // ATX heading: 1..6 `#` then whitespace/EOL.
+  if (/^#{1,6}(?:\s|$)/.test(line)) return "\\" + line;
+  // Blockquote / Docmost callout opener (`>` or `> [!info]`).
+  if (line.startsWith(">")) return "\\" + line;
+  // Bullet list marker then whitespace/EOL. Emphasis (`*x*`, `**x**`) has no
+  // space after the leading marker and is intentionally left verbatim.
+  if (/^[-*+](?:\s|$)/.test(line)) return "\\" + line;
+  // Ordered list marker `N.` / `N)`: escape the DELIMITER so the digits stay
+  // literal (`1. x` -> `1\. x`, which imports back as the text `1. x`).
+  const ordered = line.match(/^(\d+)[.)](?:\s|$)/);
+  if (ordered) {
+    const digits = ordered[1].length;
+    return line.slice(0, digits) + "\\" + line.slice(digits);
+  }
+  // Fenced code block: 3+ backticks or tildes. A single/double backtick is an
+  // inline code span and is left verbatim.
+  if (/^(?:`{3,}|~{3,})/.test(line)) return "\\" + line;
+  // Thematic break: a WHOLE line of 3+ identical `-`/`*`/`_`, optionally spaced.
+  if (/^([-*_])(?:\s*\1){2,}\s*$/.test(line)) return "\\" + line;
+  // Setext underline: a continuation line (after a hardBreak) that is ONLY `-`
+  // or ONLY `=` (any count, trailing spaces allowed). Under a paragraph line
+  // such a line re-parses as a SETEXT HEADING and SILENTLY DROPS its own text
+  // (`a\n--` -> heading "a", the `--` is LOST; `a\n=` -> heading "a", `=` LOST).
+  // The bullet arm above catches a lone `-` (via its `$`) and the thematic arm
+  // catches 3+ dashes, but exactly TWO dashes (`--`) fall through both; and no
+  // arm covers a lone `=` at all (a `==` pair is neutralized earlier by the
+  // inline `==`->`\=\=` escape, so only a single `=` line reaches here). Escaping
+  // the leading char (`\--`, `\=`) breaks the setext interpretation so the line
+  // round-trips as paragraph text. The WHOLE line must be the marker (anchored
+  // `^-+`/`^=+` to EOL), so a mid-content `-`/`=` is never spuriously escaped;
+  // and a `---`/`----` already handled by the thematic arm never reaches here,
+  // so there is no double-escape.
+  if (/^-+[ \t]*$/.test(line) || /^=+[ \t]*$/.test(line)) return "\\" + line;
+  // GFM table row opener.
+  if (line.startsWith("|")) return "\\" + line;
+  return line;
+}
+
 function listMarkerFamily(type: string | undefined): "ul" | "ol" | null {
   if (type === "bulletList" || type === "taskList") return "ul";
   if (type === "orderedList") return "ol";
@@ -109,6 +210,26 @@ export function convertProseMirrorToMarkdown(
   // callers (mcp getPage / in-app AI chat) pass it true.
   const dropResolvedCommentAnchors = options.dropResolvedCommentAnchors === true;
 
+  // Loss reporting for node/mark types with no dedicated serializer case. In
+  // `strict` mode the FIRST such type throws (git-sync, tests); otherwise the
+  // serializer degrades gracefully (as it always has) but records one warning
+  // per unmapped type into the optional sink so the loss is observable, not
+  // silent. Deduped per type so a document with many unknown nodes of one type
+  // produces one message.
+  const strict = options.strict === true;
+  const warningsSink = options.warnings;
+  const seenLossTypes = new Set<string>();
+  const warnLoss = (kind: "node" | "mark", typeName: string): void => {
+    if (strict) throw new ConverterLossError(kind, typeName);
+    if (!warningsSink) return;
+    const key = `${kind}:${typeName}`;
+    if (seenLossTypes.has(key)) return;
+    seenLossTypes.add(key);
+    warningsSink.push(
+      `Unknown ${kind} type "${typeName}" has no lossless markdown form; it was degraded on export.`,
+    );
+  };
+
   // Escape a value interpolated into an HTML double-quoted attribute value
   // (textAlign, colors, image src, math `text`, all data-* attrs, etc.). In the
   // ATTRIBUTE context only the quote that delimits the value and the ampersand
@@ -362,6 +483,99 @@ export function convertProseMirrorToMarkdown(
     return `<table><tbody>${htmlRows}</tbody></table>`;
   };
 
+  // Layer the intentional inline escapes onto a NON-code text run BEFORE its
+  // marks are applied. Extracted so both `case "text"` and the #515 code-emphasis
+  // run factoring (renderInlineChildren) escape the inner text identically. NEVER
+  // called on code content (a code span is literal — see the gating in the text
+  // case and the run helper). Order is load-bearing: the footnote raw-backslash
+  // doubling MUST precede the `==`/`$`/`^[` escapes (see inFootnoteBody).
+  const escapeInlineText = (text: string): string => {
+    let t = text;
+    if (inFootnoteBody) t = t.replace(/\\/g, "\\\\");
+    t = t.replace(/==/g, "\\=\\=");
+    t = escapeProseMath(t);
+    t = t.replace(/\^\[/g, "^\\[");
+    return t;
+  };
+
+  // Wrap `text` with the markdown/HTML form of a SINGLE inline mark. Extracted
+  // from `case "text"` so the same per-mark emission is reused when the #515
+  // run factoring layers a shared outer mark over a code-emphasis run. `code` is
+  // handled by the callers (wrapped innermost, before this runs), so this branch
+  // is defensive only. For any non-code mark the output is byte-identical to the
+  // pre-#515 inline switch.
+  const applyInlineMark = (text: string, mark: any): string => {
+    switch (mark.type) {
+      case "bold":
+        return `**${text}**`;
+      case "italic":
+        return `*${text}*`;
+      case "code":
+        // Callers wrap the code span innermost themselves; reached only if a
+        // mark list is applied through here directly. Emit the backtick span.
+        return `\`${text}\``;
+      case "link": {
+        const href = mark.attrs?.href || "";
+        const title = mark.attrs?.title;
+        if (title) {
+          // Emit the optional markdown link title; escape an embedded double-
+          // quote so it cannot terminate the title string early.
+          const safeTitle = String(title).replace(/"/g, '\\"');
+          return `[${text}](${href} "${safeTitle}")`;
+        }
+        return `[${text}](${href})`;
+      }
+      case "strike":
+        return `~~${text}~~`;
+      case "underline":
+        return `<u>${text}</u>`;
+      case "subscript":
+        return `<sub>${text}</sub>`;
+      case "superscript":
+        return `<sup>${text}</sup>`;
+      case "highlight": {
+        // #293 canon #7: a highlight WITHOUT a color serializes as the
+        // Obsidian/GFM `==text==` syntax; a colored highlight keeps the `<mark
+        // style>` HTML form. The inner text already had any literal `==`
+        // backslash-escaped upstream.
+        const color = mark.attrs?.color;
+        return color
+          ? `<mark style="background-color: ${escapeAttr(color)}">${text}</mark>`
+          : `==${text}==`;
+      }
+      case "textStyle":
+        if (mark.attrs?.color) {
+          return `<span style="color: ${escapeAttr(mark.attrs.color)}">${text}</span>`;
+        }
+        return text;
+      case "spoiler":
+        // Markdown has no native spoiler syntax, so emit the same raw inline HTML
+        // the editor-ext/MCP stack uses (span[data-spoiler] round-trips).
+        return `<span data-spoiler="true">${text}</span>`;
+      case "comment": {
+        // Inline comment anchor (span[data-comment-id]); resolved anchors are
+        // optionally dropped for agent reads, keeping only the bare text.
+        const cid = mark.attrs?.commentId;
+        if (cid) {
+          if (mark.attrs?.resolved && dropResolvedCommentAnchors) {
+            return text;
+          }
+          const resolvedAttr = mark.attrs?.resolved
+            ? ` data-resolved="true"`
+            : "";
+          return `<span data-comment-id="${escapeAttr(cid)}"${resolvedAttr}>${text}</span>`;
+        }
+        return text;
+      }
+      default:
+        // Unknown mark: no dedicated case, so it has no markdown form and is
+        // dropped from the run. Report the loss (throws in strict mode) then
+        // leave the text unwrapped — the historical behavior.
+        warnLoss("mark", String(mark.type));
+        return text;
+    }
+  };
+
   const processNode = (node: any): string => {
     if (nodeDepth >= MAX_NODE_DEPTH) {
       // Bail out of deeper recursion without throwing. A text node still has
@@ -412,7 +626,17 @@ export function convertProseMirrorToMarkdown(
       }
 
       case "paragraph": {
-        const text = renderInlineChildren(nodeContent);
+        // Escape a leading block trigger on EVERY line of the paragraph, not
+        // just the first: a hardBreak serializes as `  \n`, so a `#`/`-`/`>`/
+        // `1.`/`|`/fence/`---` at the start of a CONTINUATION line would also
+        // re-parse into another block on the next import (a heading/list/table/
+        // setext-`---`), and for the text-less thematic/setext case would LOSE
+        // that line's text entirely. Escaping each `\n`-separated line closes
+        // the class for multi-line paragraphs too.
+        const text = renderInlineChildren(nodeContent)
+          .split("\n")
+          .map(escapeLeadingBlockTrigger)
+          .join("\n");
         const align = node.attrs?.textAlign;
         // Non-default alignment round-trips as an ATTACHED HTML comment at the
         // END of the block line (#293 canon #9):
@@ -451,154 +675,38 @@ export function convertProseMirrorToMarkdown(
         return headingLine;
       }
 
-      case "text":
+      case "text": {
         let textContent = node.text || "";
-        // #293 canon #7: `==` is now a LIVE inline highlight syntax on import (a
-        // marked inline extension turns `==text==` into a color-less highlight
-        // mark). A LITERAL `==` in a text run would therefore be misparsed as a
-        // highlight on the next import, so backslash-escape each `=` of a `==`
-        // pair; marked's escape tokenizer decodes `\=` back to a literal `=`, so
-        // a literal `==` round-trips as text (never materializes a phantom mark).
-        // This runs for BOTH unmarked text and marked non-code runs, but NOT for
-        // an inline code span (a run carrying the `code` mark returns a backtick
-        // span below with `==` verbatim, matching `` `a == b` `` staying code).
-        // A highlight run's own `==` delimiters are appended AFTER this in the
-        // marks loop, so they are never escaped; only the run's inner text is.
-        if (!(node.marks || []).some((m: any) => m.type === "code")) {
-          // #293 canon #2 (F2): inside a footnote body, DOUBLE every RAW user
-          // backslash FIRST, so it survives `^[…]` (the import tokenizer treats
-          // `\<char>` as an escape when balancing brackets, and `parseInline`
-          // decodes escapes). Doing it before the intentional escapes below keeps
-          // the serializer's own single escapes (`\=` `\$` `^\[`, and the `\[`/
-          // `\]` balanceBrackets adds) single; only genuine user backslashes are
-          // doubled. Skipped for code runs (a code span's content is NOT decoded
-          // by parseInline, so its backslashes must stay verbatim).
-          if (inFootnoteBody) {
-            textContent = textContent.replace(/\\/g, "\\\\");
-          }
-          textContent = textContent.replace(/==/g, "\\=\\=");
-          // #293 canon #6: escape a would-be inline-math `$…$` span so it stays
-          // literal text on re-import (currency `$5` is left clean — see
-          // escapeProseMath). Runs on the SAME non-code runs as the `==` escape
-          // above; an inline `code` run returns verbatim below, matching the
-          // codeBlock path (a `$…$` inside code must stay code, never math).
-          textContent = escapeProseMath(textContent);
-          // #293 canon #2: `^[` opens a LIVE inline-footnote span on import
-          // (`^[text]` -> a footnote reference). A LITERAL `^[` in prose text
-          // would therefore materialize a phantom footnote on the next import, so
-          // backslash-escape the bracket (`^[` -> `^\[`); marked's escape
-          // tokenizer decodes `\[` back to `[`, so a literal `^[…]` round-trips
-          // as text and never opens a footnote. Only the OPENING `^[` needs
-          // breaking (the tokenizer requires it), so this is a minimal, idempotent
-          // escape. A real footnoteReference node emits `^[body]` from its own
-          // case, never through here.
-          textContent = textContent.replace(/\^\[/g, "^\\[");
+        // #515: `code` is no longer exclusive (`excludes: ""`), so a run may
+        // carry `code` TOGETHER with other marks. The inner escapes below apply
+        // ONLY to a NON-code run (a code span's content is literal — `==`, `$…$`,
+        // `^[` must stay verbatim, matching `` `a == b` `` staying code). See
+        // #293 canon #2/#6/#7 for why each escape exists (extracted into
+        // escapeInlineText). A code run's `==`/`$`/`^[` are protected by the
+        // backticks, so they are never misparsed on re-import.
+        const hasCode = (node.marks || []).some((m: any) => m.type === "code");
+        if (!hasCode) {
+          textContent = escapeInlineText(textContent);
         }
-        // Apply marks (bold, italic, code, etc.)
         if (node.marks) {
-          // The schema's `code` mark declares `excludes: "_"` — it excludes every
-          // other inline mark — so the editor can NEVER produce a text run that
-          // carries `code` together with another mark, and on import any
-          // co-occurring mark is always dropped (the run comes back as code-only).
-          // The lossless, byte-stable behavior is therefore: when a run has the
-          // `code` mark, emit ONLY the backtick code span and ignore every other
-          // mark, so md1 is already code-only and md2 === md1. Runs WITHOUT a code
-          // mark are rendered exactly as before.
-          const markTypes = node.marks.map((m: any) => m.type);
-          const hasCode = markTypes.includes("code");
+          // #515: wrap the backtick code span FIRST (innermost mark), then layer
+          // the REMAINING marks in array order. For a run WITHOUT a code mark the
+          // loop applies every mark exactly as the pre-#515 switch did, so the
+          // output is byte-identical. For a code+emphasis run the code span sits
+          // inside the emphasis delimiters (`` **`code`** ``), matching CommonMark.
+          // The shared-mark grouping across ADJACENT nodes (`` **`a` + `b`** ``)
+          // lives in renderInlineChildren; this direct path handles a lone run
+          // and the table/`default` callers that invoke processNode per node.
           if (hasCode) {
             textContent = `\`${textContent}\``;
-            return textContent;
           }
           for (const mark of node.marks) {
-            switch (mark.type) {
-              case "bold":
-                textContent = `**${textContent}**`;
-                break;
-              case "italic":
-                textContent = `*${textContent}*`;
-                break;
-              case "code":
-                // A `code` run already returned above (hasCode early return), so
-                // this branch is only reached for a non-code run that somehow
-                // still lists `code`; emit the plain backtick span.
-                textContent = `\`${textContent}\``;
-                break;
-              case "link": {
-                const href = mark.attrs?.href || "";
-                const title = mark.attrs?.title;
-                if (title) {
-                  // Emit the optional markdown link title; escape an embedded
-                  // double-quote so it cannot terminate the title string early.
-                  const safeTitle = String(title).replace(/"/g, '\\"');
-                  textContent = `[${textContent}](${href} "${safeTitle}")`;
-                } else {
-                  textContent = `[${textContent}](${href})`;
-                }
-                break;
-              }
-              case "strike":
-                textContent = `~~${textContent}~~`;
-                break;
-              case "underline":
-                textContent = `<u>${textContent}</u>`;
-                break;
-              case "subscript":
-                textContent = `<sub>${textContent}</sub>`;
-                break;
-              case "superscript":
-                textContent = `<sup>${textContent}</sup>`;
-                break;
-              case "highlight": {
-                // #293 canon #7: a highlight WITHOUT a color serializes as the
-                // Obsidian/GFM `==text==` syntax (the importer's marked inline
-                // `==` extension parses it back to a color-less highlight mark).
-                // A highlight WITH a color keeps the `<mark style="background-
-                // color: …">` HTML form (the condition is deterministic on the
-                // `color` attr), so a colored highlight is not flattened. The
-                // inner textContent already had any literal `==` backslash-
-                // escaped above, so a highlight over text containing `==` still
-                // round-trips.
-                const color = mark.attrs?.color;
-                textContent = color
-                  ? `<mark style="background-color: ${escapeAttr(color)}">${textContent}</mark>`
-                  : `==${textContent}==`;
-                break;
-              }
-              case "textStyle":
-                if (mark.attrs?.color) {
-                  textContent = `<span style="color: ${escapeAttr(mark.attrs.color)}">${textContent}</span>`;
-                }
-                break;
-              case "spoiler":
-                // Markdown has no native spoiler syntax, so emit the same raw
-                // inline HTML the editor-ext/MCP stack uses. The schema's Spoiler
-                // mark parses span[data-spoiler] back on import, so the mark
-                // survives the PM -> MD -> PM round-trip.
-                textContent = `<span data-spoiler="true">${textContent}</span>`;
-                break;
-              case "comment": {
-                // Emit the inline comment anchor so highlights round-trip. The
-                // schema's Comment mark parses span[data-comment-id] (attrs
-                // commentId/resolved).
-                const cid = mark.attrs?.commentId;
-                if (cid) {
-                  // Hide resolved anchors from agent reads: drop the wrapper and
-                  // keep only the bare text. Active anchors keep their wrapper.
-                  if (mark.attrs?.resolved && dropResolvedCommentAnchors) {
-                    break;
-                  }
-                  const resolvedAttr = mark.attrs?.resolved
-                    ? ` data-resolved="true"`
-                    : "";
-                  textContent = `<span data-comment-id="${escapeAttr(cid)}"${resolvedAttr}>${textContent}</span>`;
-                }
-                break;
-              }
-            }
+            if (mark.type === "code") continue; // wrapped innermost above
+            textContent = applyInlineMark(textContent, mark);
           }
         }
         return textContent;
+      }
 
       case "codeBlock":
         const language = node.attrs?.language || "";
@@ -1173,7 +1281,11 @@ export function convertProseMirrorToMarkdown(
       }
 
       default:
-        // Fallback: process children
+        // Unknown node type: no dedicated case, so the node's identity + attrs
+        // have no lossless markdown form. Report the loss (throws in strict
+        // mode) then degrade by flattening to its children — the historical
+        // graceful fallback.
+        warnLoss("node", String(type));
         return nodeContent.map(processNode).join("");
     }
   };
@@ -1186,18 +1298,165 @@ export function convertProseMirrorToMarkdown(
   // For that node ONLY we fall back to the lossless schema-HTML `<span>` form.
   // Every other inline node is rendered exactly as processNode would, so output
   // is unchanged whenever no math sits directly before a digit.
+  // #515: a "bare-delimiter" emphasis mark is one that serializes as a naked
+  // markdown delimiter run (`**` `*` `~~` `==`) — bold / italic / strike /
+  // UNCOLORED highlight. These delimiters COLLIDE with the backtick-flanking
+  // delimiters emitted around a code+emphasis run: rendering `[code,bold]` next
+  // to `[italic]` node-by-node would produce `` **`a`***b* `` (a `***` run that
+  // re-imports wrong). Every OTHER mark (underline/sub/sup/spoiler/comment/
+  // textStyle/colored-highlight/link) emits an HTML/bracket form whose boundaries
+  // do NOT collapse, so those neighbors never join a run.
+  const isBareEmphasisMark = (mark: any): boolean => {
+    switch (mark?.type) {
+      case "bold":
+      case "italic":
+      case "strike":
+        return true;
+      case "highlight":
+        return !mark.attrs?.color; // colored highlight emits <mark>, not `==`
+      default:
+        return false;
+    }
+  };
+
+  // A text node participates in a code-emphasis run iff it carries at least one
+  // bare-delimiter emphasis mark. A code-ONLY node (no emphasis) does NOT — so a
+  // plain `` `code` `` next to `**bold**` keeps its clean, byte-identical
+  // markdown (they share no colliding delimiter). Existing pages, where a code
+  // node could never carry emphasis, therefore serialize exactly as before.
+  const isEmphasisMember = (node: any): boolean =>
+    node?.type === "text" &&
+    (node.marks || []).some((m: any) => isBareEmphasisMark(m));
+
+  // The run's non-code marks (order preserved) — the candidate marks to factor.
+  const nonCodeMarks = (node: any): any[] =>
+    (node.marks || []).filter((m: any) => m.type !== "code");
+
+  // Deep structural equality of two marks (type + full attrs). Two `link` marks
+  // are equal only when EVERY attr matches (class/href/internal/rel/target/title
+  // — not just href), so a homogeneous run never merges links that differ.
+  const marksEqual = (a: any, b: any): boolean =>
+    a.type === b.type &&
+    JSON.stringify(a.attrs ?? null) === JSON.stringify(b.attrs ?? null);
+
+  // Two non-code mark lists are equal AS SETS (a run is homogeneous when every
+  // node shares the identical non-code mark set — order-independent).
+  const markSetsEqual = (a: any[], b: any[]): boolean =>
+    a.length === b.length &&
+    a.every((ma) => b.some((mb) => marksEqual(ma, mb))) &&
+    b.every((mb) => a.some((ma) => marksEqual(mb, ma)));
+
+  // Serialize one node's INNER form for a homogeneous run: the factored marks are
+  // applied by the caller, so here a code node emits only its literal backtick
+  // span and a non-code node emits only its (escaped) text.
+  const renderRunInner = (node: any): string => {
+    const text = node.text || "";
+    if ((node.marks || []).some((m: any) => m.type === "code")) {
+      return `\`${text}\``; // code content is literal
+    }
+    return escapeInlineText(text);
+  };
+
+  // A markdown emphasis delimiter (`**`/`*`/`~~`/`==`) wrapping a code span opens
+  // with the delimiter immediately followed by a backtick and closes immediately
+  // preceded by one. A backtick is CommonMark punctuation, so such a delimiter is
+  // only left/right-flanking — able to open/close emphasis — when the character
+  // on its OUTER side is start/end, whitespace or punctuation. If a run boundary
+  // abuts a word character, the delimiter would NOT flank (`a**` `code` `**`
+  // never opens) and the emphasis silently degrades on re-import. This checks the
+  // outer boundary char conservatively: ASCII whitespace or ASCII punctuation (or
+  // the string edge) is safe; anything else (a letter/number, unicode letter or
+  // emoji) is treated as unsafe so the run takes the lossless HTML fallback.
+  const SAFE_BOUNDARY = /[\s!-/:-@[-`{-~]/;
+  const isSafeBoundary = (c: string): boolean => c === "" || SAFE_BOUNDARY.test(c);
+
+  // Serialize a maximal run of adjacent emphasis-member text nodes that contains
+  // at least one `code` node (#515). HOMOGENEOUS (all share the identical
+  // non-code mark set) AND flank-safe on both boundaries: factor the common marks
+  // ONCE around the concatenated inner spans — `` **`aaa` + `bbb`** ``, code
+  // innermost. Otherwise — HETEROGENEOUS (non-code sets differ, e.g. `[code,bold]`
+  // next to `[italic]`) OR a boundary abuts a word char — emit the whole run as
+  // schema-HTML via the lossless inlineToHtml fallback, avoiding a colliding
+  // `***` delimiter run or a non-flanking `a**` that would drop the emphasis.
+  const renderCodeEmphasisRun = (
+    run: any[],
+    prevChar: string,
+    nextChar: string,
+  ): string => {
+    const firstNonCode = nonCodeMarks(run[0]);
+    const homogeneous = run.every((n) =>
+      markSetsEqual(nonCodeMarks(n), firstNonCode),
+    );
+    if (!homogeneous || !isSafeBoundary(prevChar) || !isSafeBoundary(nextChar)) {
+      return inlineToHtml(run);
+    }
+    let out = run.map(renderRunInner).join("");
+    // Apply the common non-code marks in the FIRST node's array order (code is
+    // already innermost inside each span).
+    for (const mark of firstNonCode) out = applyInlineMark(out, mark);
+    return out;
+  };
+
   const renderInlineChildren = (nodes: any[]): string => {
-    const parts = nodes.map(processNode);
-    for (let i = 0; i < nodes.length - 1; i++) {
-      if (
-        nodes[i]?.type === "mathInline" &&
-        parts[i].startsWith("$") &&
-        /^[0-9]/.test(parts[i + 1] || "")
-      ) {
-        parts[i] = mathInlineHtml(nodes[i].attrs?.text || "");
+    // Pass 1: segment the nodes. Each segment is either an already-rendered
+    // non-run node / pure-emphasis node (byte-identical to the pre-#515 output),
+    // or a DEFERRED code-emphasis run (a maximal block of consecutive
+    // emphasis-member text nodes containing a code node) — its markdown-vs-HTML
+    // choice needs the neighbor boundary chars, resolved in pass 2.
+    type Seg = { firstNode: any; text?: string; run?: any[] };
+    const segs: Seg[] = [];
+    let i = 0;
+    while (i < nodes.length) {
+      const node = nodes[i];
+      if (isEmphasisMember(node)) {
+        let j = i;
+        while (j < nodes.length && isEmphasisMember(nodes[j])) j++;
+        const run = nodes.slice(i, j);
+        const hasCode = run.some((n: any) =>
+          (n.marks || []).some((m: any) => m.type === "code"),
+        );
+        if (hasCode) {
+          segs.push({ firstNode: run[0], run });
+        } else {
+          // Pure-emphasis run (no code): render each node as before.
+          for (const n of run) segs.push({ firstNode: n, text: processNode(n) });
+        }
+        i = j;
+      } else {
+        segs.push({ firstNode: node, text: processNode(node) });
+        i++;
       }
     }
-    return parts.join("");
+    // A deferred run always emits either a delimiter/backtick (markdown) or `<`
+    // (HTML) first — both punctuation — so a following run counts as a safe
+    // boundary for the current one without resolving it first.
+    const firstCharOf = (seg: Seg): string =>
+      seg.text !== undefined ? seg.text[0] || "" : "*";
+    // Pass 2: resolve deferred runs left-to-right, tracking the previous emitted
+    // char (for the opening boundary) and peeking the next segment (for closing).
+    let prevChar = "";
+    for (let k = 0; k < segs.length; k++) {
+      const seg = segs[k];
+      if (seg.text === undefined) {
+        const nextChar = k + 1 < segs.length ? firstCharOf(segs[k + 1]) : "";
+        seg.text = renderCodeEmphasisRun(seg.run!, prevChar, nextChar);
+      }
+      if (seg.text.length > 0) prevChar = seg.text[seg.text.length - 1];
+    }
+    // Preserve the mathInline-before-digit guard: a `$…$` immediately followed by
+    // a digit-leading segment would re-tokenize as a longer math span, so emit
+    // that math node as HTML instead. A code-emphasis run never starts with a
+    // digit (it opens with a delimiter or `<`), so segment granularity is safe.
+    for (let k = 0; k < segs.length - 1; k++) {
+      if (
+        segs[k].firstNode?.type === "mathInline" &&
+        (segs[k].text || "").startsWith("$") &&
+        /^[0-9]/.test(segs[k + 1].text || "")
+      ) {
+        segs[k].text = mathInlineHtml(segs[k].firstNode.attrs?.text || "");
+      }
+    }
+    return segs.map((s) => s.text).join("");
   };
 
   // Render inline content (text runs + their marks) to HTML. Used by the raw
@@ -1232,7 +1491,22 @@ export function convertProseMirrorToMarkdown(
           return processNode(n);
         }
         let t = escapeHtmlText(n.text || "");
+        // #515: wrap `<code>` INNERMOST first (before the array-order mark loop),
+        // then skip `code` in the loop. The imported mark order is NOT fixed — it
+        // DEPENDS on the emphasis extension: import (`generateJSON`) yields code
+        // LAST for bold/italic/strike (`[emphasis, code]`) but code FIRST for the
+        // `==`-highlight extension (`[code, highlight]`). So we cannot rely on a
+        // fixed array position; the invariant is instead "wrap `<code>` innermost
+        // regardless of the imported order". That keeps `<code>` nested inside the
+        // emphasis tag both directions (preserving the byte fixpoint — an order-
+        // sensitive loop would flip `<strong><code>`↔`<code><strong>` depending on
+        // which order it happened to see) and matches the markdown path (case
+        // "text" / run factoring).
+        if ((n.marks || []).some((m: any) => m.type === "code")) {
+          t = `<code>${t}</code>`;
+        }
         for (const mark of n.marks || []) {
+          if (mark.type === "code") continue; // wrapped innermost above
           switch (mark.type) {
             case "bold":
               t = `<strong>${t}</strong>`;
@@ -1297,6 +1571,12 @@ export function convertProseMirrorToMarkdown(
                 t = `<span data-comment-id="${escapeAttr(mark.attrs.commentId)}"${r}>${t}</span>`;
               }
               break;
+            default:
+              // Unknown mark on the raw-HTML path: dropped (no HTML form). Report
+              // the loss (throws in strict mode) — same policy as the markdown
+              // path's marks loop above.
+              warnLoss("mark", String(mark.type));
+              break;
           }
         }
         return t;

packages/prosemirror-markdown/src/lib/text-normalize.ts

@@ -7,13 +7,12 @@
  * it is never applied to replacement text or inserted node content, so no
  * formatting is ever lost.
  *
- * Scope note (#414): this package-local copy exists so `node-ops.ts` — which
- * lives here now (the single canonical copy) — can resolve its markdown-tolerant
- * anchor fallback without a circular dependency back on `@docmost/mcp`. It
- * intentionally carries ONLY `stripInlineMarkdown` (the primitive `node-ops`
- * needs); the mcp-side `text-normalize.ts` (which additionally serves
- * `json-edit.ts` via `stripBalancedWrappers`) is the subject of a separate
- * dedup task and is left untouched here.
+ * CANONICAL HOME (#414/#493): this is the single source of truth for locator
+ * markdown-stripping. `node-ops.ts` (which lives here) uses it directly, and the
+ * mcp-side `text-normalize.ts` now IMPORTS `stripInlineMarkdown` and the shared
+ * `stripWrappersAndLinks` primitive from here (via `@docmost/prosemirror-markdown`)
+ * instead of keeping a drifting copy — mcp only adds its own thin
+ * `stripBalancedWrappers`/`closestBlockHint` on top.
  */
 
 /** Maximum unwrap passes, so pathological/nested input cannot loop forever. */
@@ -44,7 +43,7 @@ const LINK_IMAGE_RE = /!?\[([^\]]*)\]\([^)]*\)/g;
  * Does NOT trim decoration, does NOT guard against an empty result — it returns
  * exactly the transformed string.
  */
-function stripWrappersAndLinks(s: string): string {
+export function stripWrappersAndLinks(s: string): string {
   // 1. Links/images -> their visible text.
   let out = s.replace(LINK_IMAGE_RE, "$1");
 

packages/prosemirror-markdown/test/converter-loss-warnings.test.ts

@@ -0,0 +1,112 @@
+import { describe, expect, it } from "vitest";
+import {
+  convertProseMirrorToMarkdown,
+  ConverterLossError,
+} from "../src/lib/markdown-converter.js";
+
+/**
+ * #493 commit 3 — a node/mark type the serializer has no dedicated case for used
+ * to be degraded SILENTLY (an unknown node flattened to its children, an unknown
+ * mark dropped from the run). The serializer now REPORTS the loss:
+ *   - default (non-strict): unchanged graceful degradation, but one warning per
+ *     unmapped type is pushed into an optional `warnings` sink so callers can
+ *     observe it;
+ *   - strict: the FIRST unmapped type throws a ConverterLossError (git-sync +
+ *     tests), turning a silent loss into a hard, surfaced error.
+ *
+ * Exercised through the REAL converter (no mock): the observable properties are
+ * the emitted markdown, the warnings collected, and the thrown error.
+ */
+
+const doc = (...nodes: any[]) => ({ type: "doc", content: nodes });
+
+describe("converter loss reporting — unknown node types", () => {
+  const unknownNode = doc({
+    type: "quantumWidget",
+    content: [{ type: "text", text: "inner text" }],
+  });
+
+  it("degrades to children AND records a warning (non-strict, sink provided)", () => {
+    const warnings: string[] = [];
+    const md = convertProseMirrorToMarkdown(unknownNode, { warnings });
+    // Graceful degrade: the child text still survives (historical behavior).
+    expect(md).toContain("inner text");
+    // The loss is now observable.
+    expect(warnings).toHaveLength(1);
+    expect(warnings[0]).toContain("quantumWidget");
+    expect(warnings[0]).toContain("node");
+  });
+
+  it("stays byte-identical for callers that pass no sink (zero behavior change)", () => {
+    const withSink: string[] = [];
+    const a = convertProseMirrorToMarkdown(unknownNode, { warnings: withSink });
+    const b = convertProseMirrorToMarkdown(unknownNode);
+    expect(b).toBe(a); // the sink does not alter the produced markdown
+  });
+
+  it("throws ConverterLossError in strict mode", () => {
+    try {
+      convertProseMirrorToMarkdown(unknownNode, { strict: true });
+      expect.unreachable("strict mode must throw on an unknown node");
+    } catch (e) {
+      expect(e).toBeInstanceOf(ConverterLossError);
+      expect((e as ConverterLossError).kind).toBe("node");
+      expect((e as ConverterLossError).typeName).toBe("quantumWidget");
+    }
+  });
+
+  it("dedupes the warning per type (many unknown nodes -> one message)", () => {
+    const warnings: string[] = [];
+    convertProseMirrorToMarkdown(
+      doc(
+        { type: "quantumWidget", content: [{ type: "text", text: "a" }] },
+        { type: "quantumWidget", content: [{ type: "text", text: "b" }] },
+      ),
+      { warnings },
+    );
+    expect(warnings).toHaveLength(1);
+  });
+});
+
+describe("converter loss reporting — unknown mark types", () => {
+  const unknownMark = doc({
+    type: "paragraph",
+    content: [{ type: "text", text: "glowing", marks: [{ type: "glow" }] }],
+  });
+
+  it("drops the mark but keeps the text AND records a warning (non-strict)", () => {
+    const warnings: string[] = [];
+    const md = convertProseMirrorToMarkdown(unknownMark, { warnings });
+    expect(md).toBe("glowing"); // text survives, mark silently had no form
+    expect(warnings).toHaveLength(1);
+    expect(warnings[0]).toContain("glow");
+    expect(warnings[0]).toContain("mark");
+  });
+
+  it("throws ConverterLossError in strict mode", () => {
+    expect(() =>
+      convertProseMirrorToMarkdown(unknownMark, { strict: true }),
+    ).toThrow(ConverterLossError);
+  });
+});
+
+describe("converter loss reporting — known content is never flagged", () => {
+  it("a fully-mapped document produces no warnings and does not throw in strict mode", () => {
+    const d = doc(
+      { type: "heading", attrs: { level: 2 }, content: [{ type: "text", text: "Title" }] },
+      {
+        type: "paragraph",
+        content: [
+          { type: "text", text: "bold", marks: [{ type: "bold" }] },
+          { type: "text", text: " and " },
+          { type: "text", text: "link", marks: [{ type: "link", attrs: { href: "https://x.y" } }] },
+        ],
+      },
+      { type: "bulletList", content: [{ type: "listItem", content: [{ type: "paragraph", content: [{ type: "text", text: "item" }] }] }] },
+    );
+    const warnings: string[] = [];
+    const md = convertProseMirrorToMarkdown(d, { warnings, strict: true });
+    expect(warnings).toEqual([]);
+    expect(md).toContain("## Title");
+  });
+});

packages/prosemirror-markdown/test/foreign-markdown.test.ts

@@ -1,12 +1,15 @@
+import { describe, it, expect } from 'vitest';
+import { convertProseMirrorToMarkdown } from '../src/lib/markdown-converter.js';
+import { markdownToProseMirror } from '../src/lib/markdown-to-prosemirror.js';
 import {
-  convertProseMirrorToMarkdown,
-  markdownToProseMirror,
-} from '@docmost/prosemirror-markdown';
-import { normalizeForeignMarkdown } from './foreign-markdown';
+  normalizeForeignMarkdown,
+  normalizeAgentMarkdown,
+} from '../src/lib/foreign-markdown.js';
 
 /**
- * STEP 2 goldens for issue #345: the foreign-markdown normalizer that runs at the
- * import boundary BEFORE the strict canonical parser (`markdownToProseMirror`).
+ * STEP 2 goldens for issue #345 (moved into the package with the normalizer in
+ * #493): the foreign-markdown normalizer that runs at the import boundary BEFORE
+ * the strict canonical parser (`markdownToProseMirror`).
  *
  * Two layers:
  *  1. PURE string→string cases pinning the normalizer's own behavior (GFM
@@ -216,3 +219,53 @@ describe('foreign markdown import acceptance (normalizer + canonical parser)', (
     ).toHaveLength(1);
   });
 });
+
+describe('normalizeAgentMarkdown vs normalizeForeignMarkdown — front-matter strip is IMPORT-only (#493 review)', () => {
+  // A page that OPENS with a horizontalRule and contains a later `---` serializes
+  // to a `---…---`-shaped body. On a full-body AGENT rewrite this must NOT be
+  // mistaken for YAML front-matter and stripped — that silently dropped the
+  // page's leading content.
+  const rulePage = '---\n\nIntro\n\nMore\n\n---\n\nRest';
+
+  it('normalizeAgentMarkdown does NOT strip a leading ---…--- (no content loss)', () => {
+    expect(normalizeAgentMarkdown(rulePage)).toBe(rulePage);
+  });
+
+  it('normalizeForeignMarkdown (file import) STILL strips a real leading YAML front-matter block', () => {
+    const withYaml = '---\ntitle: My Page\ntags: [a, b]\n---\n\nBody here.';
+    const out = normalizeForeignMarkdown(withYaml);
+    expect(out).toBe('Body here.');
+    // And the horizontalRule-shaped body IS stripped on the import path (its
+    // documented file-import behavior) — the two variants differ ONLY here.
+    expect(normalizeForeignMarkdown(rulePage)).not.toContain('Intro');
+  });
+
+  it('agent-write round-trip keeps a horizontalRule-led doc with a second rule intact', async () => {
+    // Simulate the serializer output for [horizontalRule, para, para, horizontalRule, para].
+    const doc = {
+      type: 'doc',
+      content: [
+        { type: 'horizontalRule' },
+        { type: 'paragraph', content: [{ type: 'text', text: 'Intro' }] },
+        { type: 'paragraph', content: [{ type: 'text', text: 'More' }] },
+        { type: 'horizontalRule' },
+        { type: 'paragraph', content: [{ type: 'text', text: 'Rest' }] },
+      ],
+    };
+    const body = convertProseMirrorToMarkdown(doc);
+    // The agent-write normalization must NOT eat the head; re-import keeps every
+    // paragraph's text.
+    const back = await markdownToProseMirror(normalizeAgentMarkdown(body));
+    const texts = JSON.stringify(back);
+    for (const t of ['Intro', 'More', 'Rest']) expect(texts).toContain(t);
+    // Both horizontal rules survive.
+    expect(back.content.filter((n: any) => n.type === 'horizontalRule')).toHaveLength(2);
+  });
+
+  it('agent-write STILL rewrites GFM reference footnotes (the shared drift-fix)', () => {
+    const gfm = 'See[^1].\n\n[^1]: the note.';
+    const out = normalizeAgentMarkdown(gfm);
+    expect(out).toContain('^[the note.]');
+    expect(out).not.toMatch(/\[\^1\]:/);
+  });
+});

packages/prosemirror-markdown/test/generative/text-arbitraries.ts

@@ -11,9 +11,11 @@
  *
  * The corpus deliberately spans the CommonMark / canon hostile alphabet
  * (`* _ [ ] ( ) { } | < > & # ! ~ = + -`), unicode / emoji / RTL, and the legal
- * mark combinations on runs (including the `code` mark, which the schema's
- * `excludes: "_"` makes suppress every co-occurring mark — so it is never
- * combined with another mark in the byte-stable space).
+ * mark combinations on runs. As of #515 the `code` mark no longer excludes other
+ * marks (`excludes: ""`), so the corpus ALSO combines `code` with bold / italic /
+ * strike / highlight — exercising both the HOMOGENEOUS run factoring (adjacent
+ * code+bold spans -> `` **`a` `b`** ``) and the HETEROGENEOUS anti-collision
+ * fallback (`[code,bold]` next to `[italic]` -> schema-HTML, never `` `a`***b* ``).
  */
 import fc from 'fast-check';
 
@@ -106,16 +108,16 @@ export const urlArb: fc.Arbitrary<string> = fc
 /**
  * A text run with an OPTIONAL single non-code formatting mark (bold/italic/
  * strike/underline/superscript/subscript/spoiler), or a SOLE `code` mark, or a
- * link, or an inline comment anchor. `code` is NEVER combined with another mark
- * in the byte-stable space (that combination is a documented converter
- * limitation — the schema's `code` mark declares `excludes: "_"`). Marks wrap
- * `safeTextArb`, which stays stable even when it contains isolated specials.
+ * `code` mark COMBINED with a bare-delimiter emphasis mark (#515), or a link, or
+ * an inline comment anchor. Marks wrap `safeTextArb`, which stays stable even
+ * when it contains isolated specials.
  *
- * The mark set here is broadened past the sibling test's {bold,italic,strike}
- * to also cover underline / superscript / subscript / spoiler / textStyle /
- * highlight (all single, non-code marks), so the marks-on-text generator
- * exercises every mark the schema declares except the deliberately-excluded
- * `code`+other combination.
+ * The mark set here is broadened past the sibling test's {bold,italic,strike} to
+ * also cover underline / superscript / subscript / spoiler / textStyle /
+ * highlight (all single, non-code marks). As of #515 it ALSO emits `code`
+ * combined with bold/italic/strike, so the assembled inline content exercises the
+ * converter's code-emphasis run detection (adjacent combos -> homogeneous
+ * factoring or heterogeneous HTML fallback, both lossless).
  */
 export const markedTextRunArb: fc.Arbitrary<any> = fc.oneof(
   // Plain text.
@@ -138,6 +140,25 @@ export const markedTextRunArb: fc.Arbitrary<any> = fc.oneof(
   // Sole code mark (backtick span). safeTextArb is backtick-free, so the span
   // content cannot contain an inner backtick.
   safeTextArb.map((t) => ({ type: 'text', text: t, marks: [{ type: 'code' }] })),
+  // #515: code COMBINED with a bare-delimiter emphasis mark. The converter nests
+  // the backtick span inside the emphasis delimiters (`` **`x`** ``) and, when
+  // such runs sit adjacent, factors a shared mark or falls back to schema-HTML.
+  // Mark order here is `[emphasis, code]` — the order the HTML->PM import yields
+  // for bold/italic/strike specifically (code last). This is NOT universal: the
+  // `==`-highlight case below imports code FIRST — so match each case to its own
+  // imported order for the order-exact P1 round-trip (do not assume a fixed order).
+  fc
+    .tuple(safeTextArb, fc.constantFrom('bold', 'italic', 'strike'))
+    .map(([t, m]) => ({ type: 'text', text: t, marks: [{ type: m }, { type: 'code' }] })),
+  // #515: code combined with an UNCOLORED highlight (also a bare-delimiter mark,
+  // `==…==`), so the highlight+code delimiter interaction is covered too. Import
+  // yields `[code, highlight]` here (the `==` inline extension nests code first),
+  // so the generator matches that order for the order-exact P1 round-trip.
+  safeTextArb.map((t) => ({
+    type: 'text',
+    text: t,
+    marks: [{ type: 'code' }, { type: 'highlight' }],
+  })),
   // Link with safe text, a paren/space-free href, optionally a letter-bearing
   // title (a purely numeric title is coerced to a number and dropped).
   fc
@@ -212,25 +233,93 @@ export function normalizeInline(nodes: any[]): any[] {
   return out;
 }
 
+/**
+ * #493 commit 1: a plain-text run whose text DELIBERATELY OPENS with a markdown
+ * BLOCK trigger — ATX heading `#`, bullet `-`/`*`/`+`, blockquote `>`, ordered
+ * `N.`/`N)`, or a table `|` — followed by safe text. Pre-#493 the corpus
+ * self-censored these away (safeTextArb's leading-word guarantee); the paragraph
+ * serializer now BLOCK-ESCAPES a leading trigger, so the generative round-trip
+ * itself proves the data-loss class is closed rather than avoiding it.
+ *
+ * DELIBERATELY excludes the code-fence (backtick) trigger — the backtick is a
+ * code-span delimiter that re-pairs globally (see specialCharArb's note), an
+ * instability UNRELATED to block-escape — and the whole-line thematic break
+ * (`---`), which only triggers when the line is ONLY dashes; both are covered by
+ * the deterministic pin (gitmost-transcript-neutralization.test.ts). Each still
+ * ENDS in a word (safeTextArb) so adjacent-run concatenation stays safe.
+ */
+export const blockTriggerLeadRunArb: fc.Arbitrary<any> = fc
+  .tuple(
+    fc.constantFrom('# ', '## ', '- ', '* ', '+ ', '> ', '1. ', '1) ', '| '),
+    safeTextArb,
+  )
+  .map(([trigger, rest]) => ({ type: 'text', text: trigger + rest }));
+
+/**
+ * A hardBreak IMMEDIATELY followed by a block-trigger-leading run — a two-node
+ * segment. Because a hardBreak serializes as `  \n`, the trigger then sits at
+ * the START of a CONTINUATION line, exercising the serializer's PER-LINE block
+ * escape (not just the first line). #493 review: without this the fuzzer never
+ * placed a trigger after a hardBreak, so a single-line-only escape passed P1–P3.
+ */
+export const hardBreakThenTriggerArb: fc.Arbitrary<any[]> = fc
+  .tuple(hardBreakArb, blockTriggerLeadRunArb)
+  .map(([hb, trigger]) => [hb, trigger]);
+
+/**
+ * #493 (setext data-loss): a WHOLE-LINE setext underline landing on a
+ * continuation line. A setext underline is a line of ONLY `-` (any count) or
+ * ONLY `=` (any count) that FOLLOWS a paragraph line; on re-parse it turns the
+ * preceding line into a heading and DROPS its own text. The block-escape must
+ * neutralize it. Unlike blockTriggerLeadRunArb, the underline must occupy the
+ * whole line, so we sandwich it between two hardBreaks (underline on its own
+ * line, preceded by earlier paragraph content, followed by a trailing word so
+ * the closing hardBreak is not dropped by normalizeInline). Covers underlines
+ * of every length: `--` (the two-dash case the bullet/thematic arms miss), a
+ * lone `=`, `==`/`====` (neutralized by the inline `==` escape), and `---`/
+ * `----` (regression for the existing thematic case).
+ */
+export const hardBreakThenSetextArb: fc.Arbitrary<any[]> = fc
+  .tuple(
+    fc.constantFrom('--', '=', '==', '====', '---', '----'),
+    safeTextArb,
+  )
+  .map(([underline, rest]) => [
+    { type: 'hardBreak' },
+    { type: 'text', text: underline },
+    { type: 'hardBreak' },
+    { type: 'text', text: rest },
+  ]);
+
 /**
  * Inline content for a paragraph: at least one marked text run, optionally with
- * inline atoms (math/mention) and hard breaks interspersed. Always starts with a
- * text run so the paragraph never opens with a block trigger. (Ported.)
+ * inline atoms (math/mention) and hard breaks interspersed. The FIRST run is
+ * usually an ordinary marked run, but sometimes a block-trigger-leading run
+ * (blockTriggerLeadRunArb) so the paragraph OPENS with a markdown block trigger;
+ * and a `hardBreak + trigger` segment can appear anywhere in the rest, so a
+ * trigger also lands at the start of a CONTINUATION line — both exercising the
+ * serializer's per-line block-escape end-to-end. (Ported, with the #493
+ * leading-trigger + post-hardBreak dimensions added.)
  */
 export const inlineContentArb: fc.Arbitrary<any[]> = fc
   .tuple(
-    markedTextRunArb,
+    fc.oneof(
+      { weight: 5, arbitrary: markedTextRunArb },
+      { weight: 1, arbitrary: blockTriggerLeadRunArb },
+    ),
     fc.array(
       fc.oneof(
-        { weight: 5, arbitrary: markedTextRunArb },
-        { weight: 1, arbitrary: mathInlineArb },
-        { weight: 1, arbitrary: mentionArb },
-        { weight: 1, arbitrary: hardBreakArb },
+        { weight: 5, arbitrary: markedTextRunArb.map((n) => [n]) },
+        { weight: 1, arbitrary: mathInlineArb.map((n) => [n]) },
+        { weight: 1, arbitrary: mentionArb.map((n) => [n]) },
+        { weight: 1, arbitrary: hardBreakArb.map((n) => [n]) },
+        { weight: 2, arbitrary: hardBreakThenTriggerArb },
+        { weight: 2, arbitrary: hardBreakThenSetextArb },
       ),
       { minLength: 0, maxLength: 4 },
     ),
   )
-  .map(([first, rest]) => normalizeInline([first, ...rest]));
+  .map(([first, rest]) => normalizeInline([first, ...rest.flat()]));
 
 /**
  * Inline content for a HEADING — identical to a paragraph's, but WITHOUT hard

packages/prosemirror-markdown/test/gitmost-transcript-neutralization.test.ts

@@ -5,32 +5,21 @@ import { convertProseMirrorToMarkdown } from "../src/lib/markdown-converter.js";
 import { markdownToProseMirror } from "../src/lib/markdown-to-prosemirror.js";
 
 /**
- * gitmost #377 (round-1 review, finding #1) — proof, against the REAL
- * converter, that the transcript-insert boundary defense survives git-sync.
+ * #493 commit 1 — the paragraph serializer's leading-block-escape closes the
+ * data-loss class where a paragraph whose text opens at column 0 with a markdown
+ * block trigger (`#`/`-`/`*`/`+`/`>`, an ordered `N.`/`N)`, a code fence, a
+ * table `|`, a callout opener, or a thematic break) silently re-parsed into a
+ * heading / list / quote / code block / table / horizontalRule on the git-sync
+ * doc -> markdown -> doc cycle. The thematic-break case was the worst: a
+ * horizontalRule carries NO text, so the line's text was lost entirely.
  *
- * The web bridge (apps/client .../gitmost/gitmost-recording.ts,
- * `gitmostInsertTranscriptIntoEditor`) appends each transcript line as a
- * PARAGRAPH text node. The paragraph serializer here (`case "paragraph"`) emits
- * that text VERBATIM with no block-escape, so a line whose text begins with a
- * col-0 markdown block trigger would, on the doc -> markdown -> doc git-sync
- * cycle, silently re-parse into a heading / list / quote / callout / code block.
- * That missing block-escape is the pre-existing root cause; the bridge's
- * boundary defense prepends an invisible zero-width space (U+200B) to a line
- * that begins with such a trigger, shifting it off column 0.
- *
- * This test keeps a COPY of the bridge's trigger regex (the bridge is in a
- * different package and can't be imported here) and asserts:
- *   1. bare trigger lines DO corrupt (documents the root cause), and
- *   2. the ZWSP-neutralized form round-trips as a single PARAGRAPH with the
- *      text byte-preserved.
+ * This is the deterministic PIN, one assertion per trigger, exercised through
+ * the REAL converter round-trip (not a mock): each bare trigger line now
+ * round-trips as a SINGLE paragraph with its text byte-preserved — proving the
+ * class is closed WITHOUT the former client-side ZWSP workaround (removed) or
+ * the generative suite's leading-word self-censorship (removed).
  */
 
-const ZWSP = "​"; // U+200B
-
-// MUST stay in sync with GITMOST_MD_BLOCK_TRIGGER_RE in the client bridge.
-const MD_BLOCK_TRIGGER_RE =
-  /^(?:#{1,6}(?:\s|$)|[-*+](?:\s|$)|>|\d+[.)](?:\s|$)|```|~~~|\||([-*_])(?:\s*\1){2,}\s*$)/;
-
 const doc = (...nodes: any[]) => ({ type: "doc", content: nodes });
 const para = (t: string) => ({
   type: "paragraph",
@@ -43,78 +32,117 @@ const roundtrip = async (text: string) => {
   return back.content as any[];
 };
 
-describe("gitmost transcript neutralization (git-sync round-trip)", () => {
-  // Lines that, at column 0, the serializer's missing block-escape would let
-  // git-sync re-parse into a non-paragraph block.
+describe("paragraph block-escape (git-sync round-trip)", () => {
+  // Every line here, at column 0, WOULD (pre-fix) re-parse into a non-paragraph
+  // block. Each is now block-escaped by the serializer and round-trips clean.
   const triggerLines = [
     "- dash",
     "* star",
     "+ plus",
     "> quote",
     "# hash",
+    "## two hash",
+    "###### six hash",
     "1. one",
     "1) one",
     "> [!info] note",
     "```js",
     "~~~",
-    // Solid + spaced thematic breaks — these re-parse into a `horizontalRule`,
-    // which carries NO text, so a bare separator line LOSES its text entirely
-    // (round-2 finding). `_` also only forms a block via this construct.
+    "| a | b |",
+    // Solid + spaced thematic breaks — the text-LOSING case pre-fix.
     "---",
     "***",
     "___",
-    "- - -", // spaced dash break (solid form is caught by [-*+]\s too, but this is the break)
+    "- - -",
     "_ _ _",
   ];
 
-  it("BARE trigger lines corrupt into non-paragraph blocks (root cause)", async () => {
+  it("every bare trigger line round-trips as a single paragraph, text byte-preserved", async () => {
     for (const line of triggerLines) {
       const blocks = await roundtrip(line);
-      // At least one produced block is NOT a paragraph — i.e. corruption.
-      const allParagraphs = blocks.every((b) => b.type === "paragraph");
-      expect(
-        allParagraphs,
-        `expected "${line}" to corrupt when inserted bare`,
-      ).toBe(false);
-    }
-  });
-
-  it("BARE solid thematic breaks corrupt into a text-LOSING horizontalRule", async () => {
-    // The severe case: no text node survives. Documents why neutralization
-    // matters more here than for list/quote (where the text survived).
-    for (const line of ["---", "***", "___"]) {
-      const blocks = await roundtrip(line);
-      expect(blocks.map((b) => b.type)).toContain("horizontalRule");
-      // No block carries the original text anywhere.
-      const flat = JSON.stringify(blocks);
-      expect(flat).not.toContain(line);
-    }
-  });
-
-  it("ZWSP-neutralized trigger lines round-trip as a single paragraph, text preserved", async () => {
-    for (const line of triggerLines) {
-      // The regex must actually classify each as a trigger.
-      expect(MD_BLOCK_TRIGGER_RE.test(line), `regex missed "${line}"`).toBe(
-        true,
+      expect(blocks, `"${line}" should be one block`).toHaveLength(1);
+      expect(blocks[0].type, `"${line}" should stay a paragraph`).toBe(
+        "paragraph",
       );
-      const neutralized = ZWSP + line;
-      const blocks = await roundtrip(neutralized);
-
-      expect(blocks).toHaveLength(1);
-      expect(blocks[0].type).toBe("paragraph");
-      // Text is byte-preserved (ZWSP + original line), so the display is the
-      // original line with only an invisible leading character.
-      expect(blocks[0].content[0].text).toBe(neutralized);
+      expect(
+        blocks[0].content?.[0]?.text,
+        `"${line}" text should survive byte-exact`,
+      ).toBe(line);
     }
   });
 
-  it("normal host-prefixed lines never match the trigger regex and round-trip byte-exact", async () => {
+  it("emphasis / inline-code paragraphs are NOT escaped (no backslash churn)", async () => {
+    // These open with `*`/`` ` `` but are NOT block triggers; the serialized
+    // markdown must not gain a stray leading backslash, and they round-trip.
+    for (const [text, mark] of [
+      ["bold", "bold"],
+      ["italic", "italic"],
+      ["code", "code"],
+    ] as const) {
+      const node = doc({
+        type: "paragraph",
+        content: [{ type: "text", text, marks: [{ type: mark }] }],
+      });
+      const md = convertProseMirrorToMarkdown(node);
+      expect(md.startsWith("\\"), `${mark} must not be block-escaped`).toBe(
+        false,
+      );
+      const back = await markdownToProseMirror(md);
+      expect(back.content[0].type).toBe("paragraph");
+      expect(back.content[0].content[0].text).toBe(text);
+      expect(back.content[0].content[0].marks?.[0]?.type).toBe(mark);
+    }
+  });
+
+  it("a block trigger on a CONTINUATION line (after a hardBreak) is escaped too", async () => {
+    // A hardBreak serializes as `  \n`, so a trigger on the second line would,
+    // without a per-line escape, re-parse into another block. The worst case is
+    // `---`: a setext underline would turn the first line into a heading and LOSE
+    // the `---` text entirely. Each pair round-trips as ONE paragraph with the
+    // hardBreak and both texts preserved.
+    for (const [first, second] of [
+      ["a", "# b"],
+      ["a", "- b"],
+      ["a", "> b"],
+      ["a", "1. b"],
+      ["a", "| b |"],
+      ["a", "---"], // setext / thematic (3 dashes) — the text-losing case
+      ["a", "--"], // setext underline, EXACTLY two dashes (bullet/thematic miss it)
+      ["a", "----"], // setext / thematic (4 dashes)
+      ["a", "="], // setext H1 underline, a lone `=` (no other arm covers it)
+      ["a", "===="], // setext H1 underline, run of `=`
+    ]) {
+      const d = doc({
+        type: "paragraph",
+        content: [
+          { type: "text", text: first },
+          { type: "hardBreak" },
+          { type: "text", text: second },
+        ],
+      });
+      const back = await markdownToProseMirror(convertProseMirrorToMarkdown(d));
+      expect(back.content, `"${first}⏎${second}" should be one block`).toHaveLength(1);
+      expect(back.content[0].type).toBe("paragraph");
+      const texts = (back.content[0].content as any[])
+        .filter((n) => n.type === "text")
+        .map((n) => n.text);
+      const hasBreak = (back.content[0].content as any[]).some(
+        (n) => n.type === "hardBreak",
+      );
+      expect(hasBreak, `"${first}⏎${second}" should keep the hardBreak`).toBe(true);
+      expect(texts, `"${first}⏎${second}" should preserve both line texts`).toEqual([
+        first,
+        second,
+      ]);
+    }
+  });
+
+  it("normal host-prefixed lines round-trip byte-exact (unaffected)", async () => {
     for (const line of [
       "You: hello there",
       "Speaker 1: - and then a dash mid-line",
       "Speaker 2: 1. not a list",
     ]) {
-      expect(MD_BLOCK_TRIGGER_RE.test(line)).toBe(false);
       const blocks = await roundtrip(line);
       expect(blocks).toHaveLength(1);
       expect(blocks[0].type).toBe("paragraph");

packages/prosemirror-markdown/test/markdown-converter-gaps.test.ts

@@ -294,10 +294,11 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
     );
   });
 
-  // 5. code + link co-occur: the schema's `code` mark excludes all other marks
-  //    (including link), so the link cannot survive import. The lossless,
-  //    byte-stable behavior is to emit ONLY the backtick code span (code wins).
-  it('a code+link run emits the backtick code form (code wins, link dropped)', () => {
+  // 5. code + link co-occur (#515): `code` no longer excludes other marks, so a
+  //    link can wrap inline code. The code span is emitted innermost and the link
+  //    wraps it — CommonMark allows inline code inside link text, so it survives
+  //    the round trip.
+  it('a code+link run nests the backtick span inside the link (#515)', () => {
     const out = convertProseMirrorToMarkdown(
       doc(
         para({
@@ -310,7 +311,7 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
         }),
       ),
     );
-    expect(out).toBe('`x`');
+    expect(out).toBe('[`x`](http://a?b&c"d)');
   });
 
   // 6. hardBreak inside a heading: prefix applied once, "  \n" between a and b.
@@ -430,7 +431,7 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
   });
 });
 
-describe('converter gap coverage — documented round-trip data loss (specs 12–14)', () => {
+describe('converter gap coverage — formerly-lossy round-trips, now closed (specs 12–14)', () => {
   // 12. A 3-backtick fence inside a codeBlock body is now lengthened: the outer
   //     fence widens to (longest inner run + 1) backticks per CommonMark, so the
   //     inner ``` is treated as content and the block survives as ONE node.
@@ -460,25 +461,24 @@ describe('converter gap coverage — documented round-trip data loss (specs 12
     expect(docsCanonicallyEqual(d, doc2)).toBe(false);
   });
 
-  // 13. A leading ordered-list marker in paragraph text is NOT escaped, so a
-  //     plain paragraph silently becomes an orderedList on re-import.
-  it('a paragraph starting with "1. " is promoted to an orderedList on re-import', async () => {
+  // 13. #493 commit 1: a leading ordered-list marker in paragraph text is now
+  //     BLOCK-ESCAPED, so the paragraph round-trips as a paragraph instead of
+  //     silently becoming an orderedList (was documented data loss, now closed).
+  it('a paragraph starting with "1. " is block-escaped and stays a paragraph', async () => {
     const d = doc({
       type: 'paragraph',
       content: [{ type: 'text', text: '1. not a list' }],
     });
     const md1 = convertProseMirrorToMarkdown(d);
-    expect(md1).toBe('1. not a list'); // no backslash escape
+    expect(md1).toBe('1\\. not a list'); // the ordered-list delimiter is escaped
 
     const doc2 = await markdownToProseMirror(md1);
-    expect(doc2.content?.[0]?.type).toBe('orderedList');
-    const li = doc2.content[0].content?.[0];
-    expect(li?.type).toBe('listItem');
-    expect(li.content?.[0]?.content?.[0]).toMatchObject({
+    expect(doc2.content?.[0]?.type).toBe('paragraph');
+    expect(doc2.content[0].content?.[0]).toMatchObject({
       type: 'text',
-      text: 'not a list', // the "1. " was consumed as a list marker
+      text: '1. not a list', // the escape decodes back to the literal text
     });
-    expect(docsCanonicallyEqual(d, doc2)).toBe(false);
+    expect(docsCanonicallyEqual(d, doc2)).toBe(true);
   });
 
   // 14. #293 canon #4: the image title now round-trips via the attached

packages/prosemirror-markdown/test/markdown-converter.test.ts

@@ -59,22 +59,21 @@ describe('convertProseMirrorToMarkdown', () => {
       ).toBe('`x`');
     });
 
-    it('code + another mark emits the backtick code form (code wins)', () => {
-      // The schema's `code` mark excludes all other marks, so the editor can
-      // never produce code+bold on one run and import always drops the co-mark.
-      // The lossless, byte-stable behavior is to emit ONLY the backtick code
-      // span and ignore the co-occurring mark.
+    it('code + bold nests the backtick span inside the emphasis (#515)', () => {
+      // #515: the `code` mark no longer excludes other marks (`excludes: ""`), so
+      // a run can carry code+bold. CommonMark nests them (`<strong><code>`), so
+      // the code span is emitted innermost and the bold delimiters wrap it.
       const out = convertProseMirrorToMarkdown(
         doc(para(text('x', [{ type: 'bold' }, { type: 'code' }]))),
       );
-      expect(out).toBe('`x`');
+      expect(out).toBe('**`x`**');
     });
 
-    it('code + strike combo emits the backtick code form (code wins)', () => {
+    it('code + strike nests the backtick span inside the emphasis (#515)', () => {
       const out = convertProseMirrorToMarkdown(
         doc(para(text('x', [{ type: 'strike' }, { type: 'code' }]))),
       );
-      expect(out).toBe('`x`');
+      expect(out).toBe('~~`x`~~');
     });
   });
 

packages/prosemirror-markdown/test/markdown-roundtrip.property.test.ts

@@ -80,13 +80,7 @@ import { stripBlockIds } from './roundtrip-helpers.js';
 // `it.fails` blocks below (so the suite stays green only because they are marked
 // expected-to-fail, never by hiding them):
 //
-//   1. The `code` mark COMBINED with any other mark. The converter emits nested
-//      HTML (`<strong><code>x</code></strong>`), but the schema's `code` mark
-//      declares `excludes: "_"`, so on import every co-occurring mark is dropped
-//      and the run comes back as `code` only -> md2 == "`x`". Acknowledged in
-//      markdown-converter.ts (the long comment above the marks switch);
-//      impossible to round-trip both while `code` excludes them.
-//   2. A BLOCK-level `image` placed BETWEEN other blocks. The Docmost image node
+//   1. A BLOCK-level `image` placed BETWEEN other blocks. The Docmost image node
 //      is block-level but `![](url)` is inline; marked wraps it in a <p>, the
 //      schema hoists the <img> out and leaves an empty paragraph sibling, which
 //      injects an extra blank gap on the second export. An image IS byte-stable
@@ -625,7 +619,7 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
   });
 
   // -------------------------------------------------------------------------
-  // KNOWN, DOCUMENTED non-roundtrip bug #2 (kept honest as it.fails).
+  // KNOWN, DOCUMENTED non-roundtrip bug #1 (kept honest as it.fails).
   //
   // BUG: a block-level `image` placed BETWEEN other blocks is not byte-stable.
   // The Docmost image node is BLOCK-level but its markdown form `![](url)` is
@@ -655,23 +649,18 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
   });
 
   // -------------------------------------------------------------------------
-  // KNOWN, DOCUMENTED non-roundtrip bug #1 (kept honest as it.fails).
+  // #515 ROUND-TRIP PIN: `code` combined with another mark.
   //
-  // BUG: the `code` mark combined with ANY other mark does NOT round-trip.
-  // The converter emits nested HTML so the output is well-formed, e.g.
-  //   marks [code, bold]  ->  md1 = "<strong><code>x</code></strong>"
-  // but the schema's `code` mark declares `excludes: "_"`, so on import the
-  // co-occurring mark is dropped and the run comes back as code-only:
-  //   md2 = "`x`"   (=> md2 !== md1).
-  // Minimal repro doc:
-  //   { type:'doc', content:[ { type:'paragraph', content:[
-  //       { type:'text', text:'x', marks:[{type:'code'},{type:'bold'}] } ] } ] }
-  // This is acknowledged in markdown-converter.ts (the long comment above the
-  // marks switch): preserving both marks is impossible while `code` excludes
-  // them. Documented here, not "fixed", because the source must not change.
+  // Before #515 the `code` mark declared `excludes: "_"`, dropping every co-
+  // occurring mark on import so `` **`x`** `` came back as code-only. Now
+  // `excludes: ""` lets code combine with all marks (CommonMark nests them,
+  // `<strong><code>x</code></strong>`), so the run BOTH round-trips byte-stably
+  // AND preserves the co-occurring mark. This asserts the observable property in
+  // both directions: md2 === md1 (idempotent export) and the imported doc still
+  // carries [code, other].
   // -------------------------------------------------------------------------
   it(
-    'code mark combined with another mark is byte-stable',
+    'code combined with another mark round-trips and keeps both marks (#515)',
     async () => {
       const codeComboArb = fc
         .tuple(safeTextArb, fc.constantFrom('bold', 'italic', 'strike'))
@@ -688,11 +677,90 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
         }));
       await fc.assert(
         fc.asyncProperty(codeComboArb, async (doc) => {
-          const { md1, md2 } = await roundTrip(doc);
+          const { md1, md2, doc2 } = await roundTrip(doc);
           expect(md2).toBe(md1);
+          // The re-imported run carries BOTH code and the co-occurring mark.
+          const run = doc2?.content?.[0]?.content?.[0];
+          const markTypes = (run?.marks || []).map((m: any) => m.type).sort();
+          expect(markTypes).toContain('code');
+          expect(markTypes.length).toBe(2);
         }),
         { numRuns: 20, seed: SEED },
       );
     },
   );
+
+  // -------------------------------------------------------------------------
+  // #515 REPRO CASES: the five markdown inputs from the issue must import to a
+  // code+bold node (import correctness) AND re-export byte-stably with no
+  // dangling `**` (export correctness). Import direction is checked against the
+  // real markdown->PM bridge; export direction via the md->pm->md fixpoint.
+  // -------------------------------------------------------------------------
+  it('the five #515 repro cases import to [code,bold] and round-trip clean', async () => {
+    // Collect every inline text run in a doc with its mark type set.
+    const runs = (node: any): { text: string; marks: string[] }[] => {
+      if (node?.type === 'text') {
+        return [{ text: node.text || '', marks: (node.marks || []).map((m: any) => m.type) }];
+      }
+      return (node?.content || []).flatMap(runs);
+    };
+    const findRun = (doc: any, text: string) =>
+      runs(doc).find((r) => r.text === text);
+
+    // Case 1: **`code1`** -> code1 = [code, bold].
+    {
+      const md = '**`code1`**';
+      const pm = await markdownToProseMirror(md);
+      const r = findRun(pm, 'code1');
+      expect(r?.marks.sort()).toEqual(['bold', 'code']);
+      const md2 = convertProseMirrorToMarkdown(pm);
+      expect(md2).toBe('**`code1`**');
+      // md -> pm -> md fixpoint.
+      expect(convertProseMirrorToMarkdown(await markdownToProseMirror(md2))).toBe(md2);
+    }
+
+    // Case 2: **`aaa` + `bbb`** -> aaa,bbb = [code,bold], "+" carries bold; no
+    // dangling `**` on export.
+    {
+      const md = '**`aaa` + `bbb`**';
+      const pm = await markdownToProseMirror(md);
+      expect(findRun(pm, 'aaa')?.marks.sort()).toEqual(['bold', 'code']);
+      expect(findRun(pm, 'bbb')?.marks.sort()).toEqual(['bold', 'code']);
+      const md2 = convertProseMirrorToMarkdown(pm);
+      expect(md2).toBe('**`aaa` + `bbb`**');
+      // NOT the old broken export with the bold delimiters split onto each span.
+      expect(md2).not.toBe('`aaa`** + **`bbb`');
+      expect(convertProseMirrorToMarkdown(await markdownToProseMirror(md2))).toBe(md2);
+    }
+
+    // Case 3 (control): **bold3** and `code3` -> bold and code stay SEPARATE.
+    {
+      const md = '**bold3** and `code3`';
+      const pm = await markdownToProseMirror(md);
+      expect(findRun(pm, 'bold3')?.marks).toEqual(['bold']);
+      expect(findRun(pm, 'code3')?.marks).toEqual(['code']);
+      const md2 = convertProseMirrorToMarkdown(pm);
+      expect(md2).toBe('**bold3** and `code3`');
+    }
+
+    // Case 4: **`code4` tail** -> code4 = [code,bold], " tail" = [bold].
+    {
+      const md = '**`code4` tail**';
+      const pm = await markdownToProseMirror(md);
+      expect(findRun(pm, 'code4')?.marks.sort()).toEqual(['bold', 'code']);
+      const md2 = convertProseMirrorToMarkdown(pm);
+      expect(md2).toBe('**`code4` tail**');
+      expect(convertProseMirrorToMarkdown(await markdownToProseMirror(md2))).toBe(md2);
+    }
+
+    // Case 5: pre **`code5`** post -> code5 = [code,bold], surroundings plain.
+    {
+      const md = 'pre **`code5`** post';
+      const pm = await markdownToProseMirror(md);
+      expect(findRun(pm, 'code5')?.marks.sort()).toEqual(['bold', 'code']);
+      const md2 = convertProseMirrorToMarkdown(pm);
+      expect(md2).toBe('pre **`code5`** post');
+      expect(convertProseMirrorToMarkdown(await markdownToProseMirror(md2))).toBe(md2);
+    }
+  });
 });

packages/prosemirror-markdown/test/schema-editor-ext-contract.test.ts

@@ -16,14 +16,16 @@ import * as editorExt from "@docmost/editor-ext";
 // or mark added upstream that the mirror forgets to vendor fails CI loudly
 // (otherwise it is silently dropped on the markdown <-> ProseMirror round-trip).
 //
-// LIMITATION (intentional, see schema-surface-snapshot.test.ts): this is a
-// NAME-LEVEL contract only, not a full attribute-level structural compare.
-// editor-ext's Tiptap representation (node views, commands, suggestion plugins,
-// addGlobalAttributes spread across separate extensions) differs from this
-// minimal mirror, so a mechanical attribute-by-attribute equality would be
-// fragile and produce false drift. Attribute parity is guarded by the inline
-// surface snapshot (reviewed in every diff); this test guards that no canonical
-// node/mark TYPE goes unmirrored. StarterKit-provided types (paragraph, bold,
+// This file now holds TWO contracts (see the two describe blocks): the original
+// NAME-LEVEL type contract (no canonical node/mark TYPE goes unmirrored) AND, as
+// of #493, an ATTRIBUTE-LEVEL contract that compares each editor-ext node/mark's
+// OWN declared attributes (names + defaults) against the mirror's built schema.
+// A full mechanical attribute-by-attribute EQUALITY would be fragile (the mirror
+// is a deliberate superset: it injects the global id/textAlign/indent attrs and
+// normalizes some editor-ext defaults to null), so the attribute contract is
+// asymmetric — editor-ext -> mirror — with a small, reasoned, stale-guarded
+// allowlist for the two blessed divergence kinds (non-round-trippable omissions
+// and null-normalized defaults). StarterKit-provided types (paragraph, bold,
 // heading, …) are contributed by @tiptap/starter-kit in the mirror rather than
 // by editor-ext, so they are naturally covered by the mirror's superset.
 //
@@ -85,3 +87,224 @@ describe("docmost schema vs @docmost/editor-ext (name-level contract)", () => {
     expect(missing).toEqual([]);
   });
 });
+
+// ── #515 CODE-MARK `excludes` PARITY (data-loss-sensitive) ──────────────────
+//
+// The `code` mark's `excludes` field decides whether inline code can co-occur
+// with other marks. #515 sets it to "" (excludes nothing) in the canonical
+// `Code` exported by @docmost/editor-ext AND, because the vendored markdown
+// mirror must NOT pull that React-aware package into its node runtime, RE-DECLARES
+// the same override locally in docmost-schema.ts. If the two drift, markdown
+// import would silently strip bold/italic adjacent to inline code again. Guard it
+// mechanically: the mirror's built `code` mark and the canonical editor-ext
+// `Code` must agree on `excludes` (both ""). getSchema surfaces the resolved
+// value on the mark spec.
+describe("docmost schema vs @docmost/editor-ext (#515 code excludes parity)", () => {
+  it("keeps the vendored `code` mark's excludes in lockstep with editor-ext Code", () => {
+    // Mirror side: the value the mirror's BUILT schema resolves for `code`.
+    const mirrorExcludes = getSchema(docmostExtensions as never).marks.code.spec
+      .excludes;
+    // Canonical side: the `excludes` DECLARED on the editor-ext `Code` extension
+    // (read from its config — getSchema needs a full node set, so a lone mark
+    // can't be built into a schema here).
+    const canonicalCode = (
+      editorExt as unknown as { Code?: { config?: { excludes?: unknown } } }
+    ).Code;
+    const canonicalExcludes = canonicalCode?.config?.excludes;
+    // Both must be the empty string: `code` excludes NOTHING, so bold/italic/…
+    // survive alongside inline code (#515). A drift here would silently strip
+    // marks adjacent to code on markdown import again.
+    expect(canonicalCode).toBeDefined();
+    expect(mirrorExcludes).toBe("");
+    expect(canonicalExcludes).toBe("");
+    expect(mirrorExcludes).toBe(canonicalExcludes);
+  });
+});
+
+// ── ATTRIBUTE-LEVEL CONTRACT (#493 commit 2) ────────────────────────────────
+//
+// The name-level contract above catches a WHOLE node/mark type going unmirrored,
+// but not ATTRIBUTE drift within a vendored type — the exact class that silently
+// dropped `subpages.recursive`: editor-ext grew an attribute the hand-synced
+// mirror forgot, so documents using it lost that attribute on a git-sync
+// round-trip while CI stayed green. This closes that gap by comparing each
+// editor-ext node/mark's OWN declared attributes (names + defaults) against the
+// mirror's built ProseMirror schema `spec.attrs`.
+//
+// DIRECTION: editor-ext -> mirror. The mirror is deliberately a SUPERSET (it
+// injects the global `id`/`textAlign`/`indent` attributes and normalizes some
+// editor-ext "required" attrs to a `null` default), so a reverse compare would
+// be pure false drift; the meaningful failure is an editor-ext attribute the
+// mirror DROPS (name) or whose DEFAULT it silently changes. Both directions of
+// staleness are guarded so the allowlists cannot rot.
+
+/**
+ * The attributes an editor-ext Tiptap Node/Mark DECLARES itself, read from its
+ * `config.addAttributes()`. Global attributes injected by separate extensions
+ * (unique-id, indent, textAlign) are NOT included here — they are the mirror's
+ * superset and are not part of a per-type declaration — so this isolates each
+ * type's own contribution. A declared attribute with no explicit `default` is a
+ * required attr (Tiptap default `undefined`); we surface that as-is so the
+ * default compare can skip it (the mirror makes such attrs optional/`null`).
+ */
+function editorExtOwnAttrs(): Map<
+  string,
+  { kind: "node" | "mark"; attrs: Record<string, unknown> }
+> {
+  const out = new Map<
+    string,
+    { kind: "node" | "mark"; attrs: Record<string, unknown> }
+  >();
+  for (const value of Object.values(editorExt)) {
+    if (!isTiptapNodeOrMark(value)) continue;
+    const ext = value as unknown as {
+      name: string;
+      type: "node" | "mark";
+      options?: unknown;
+      storage?: unknown;
+      config?: { addAttributes?: () => Record<string, { default?: unknown }> };
+    };
+    const fn = ext.config?.addAttributes;
+    // addAttributes reads `this.options`/`this.name`; bind a minimal context
+    // (verified sufficient for every editor-ext extension — none reach for
+    // `this.editor` here). A type with no addAttributes contributes no attrs.
+    const declared =
+      typeof fn === "function"
+        ? fn.call({
+            options: ext.options ?? {},
+            name: ext.name,
+            parent: undefined,
+            storage: ext.storage ?? {},
+          } as never)
+        : {};
+    const attrs: Record<string, unknown> = {};
+    for (const [attr, spec] of Object.entries(declared || {})) {
+      // `undefined` marks a required (no-default) attr; keep it so the default
+      // compare can distinguish "no default declared" from "default is null".
+      attrs[attr] = (spec as { default?: unknown })?.default;
+    }
+    out.set(ext.name, { kind: ext.type, attrs });
+  }
+  return out;
+}
+
+/** The mirror's built-schema `spec.attrs` for a type: attr name -> default. */
+function mirrorAttrs(
+  name: string,
+  kind: "node" | "mark",
+): Record<string, unknown> | null {
+  const schema = getSchema(docmostExtensions as never);
+  const spec = kind === "node" ? schema.nodes[name]?.spec : schema.marks[name]?.spec;
+  if (!spec) return null;
+  const out: Record<string, unknown> = {};
+  for (const [attr, def] of Object.entries(spec.attrs || {})) {
+    out[attr] = (def as { default?: unknown }).default;
+  }
+  return out;
+}
+
+// An editor-ext attribute the mirror deliberately does NOT vendor because it has
+// NO markdown round-trip representation — dropping it loses nothing on the
+// git-sync cycle (the same rationale the flat-roundtrip property suite uses to
+// allowlist e.g. `tableCell.backgroundColorName`). Blessed by the hand-curated
+// surface snapshot (schema-surface-snapshot.test.ts), reviewed in every diff.
+const ACCEPTED_ATTR_OMISSIONS = new Set<string>([
+  "highlight.colorName", // only `highlight.color` round-trips (==text==); the
+  // secondary palette-name is presentational and has no markdown form.
+]);
+
+// An editor-ext attribute the mirror vendors but with a DIFFERENT default: the
+// mirror normalizes an "absent" value to `null` (its uniform optional-attr
+// convention) rather than editor-ext's UI-oriented default. None of these attrs
+// is emitted on the markdown surface (the converter round-trips only the
+// serializable ones), so the default never round-trips and the divergence is
+// inert — but pinned here so a NEW default change on either side forces review.
+const ACCEPTED_DEFAULT_DIVERGENCE = new Set<string>([
+  "image.src", // mirror null vs editor "" (an image is never emitted src-less)
+  "link.internal", // mirror null vs editor false (routing attr, not in md link)
+  "pdf.width", // mirror null vs editor 800 (presentational sizing, not in md)
+  "pdf.height", // mirror null vs editor 600 (presentational sizing, not in md)
+]);
+
+describe("docmost schema vs @docmost/editor-ext (attribute-level contract)", () => {
+  it("vendors every editor-ext attribute (name) of every shared type — no silently-dropped attrs", () => {
+    const dropped: string[] = [];
+    for (const [name, { kind, attrs }] of editorExtOwnAttrs()) {
+      const mirror = mirrorAttrs(name, kind);
+      if (!mirror) continue; // whole-type omission is the name-level test's job
+      for (const attr of Object.keys(attrs)) {
+        const key = `${name}.${attr}`;
+        if (!(attr in mirror) && !ACCEPTED_ATTR_OMISSIONS.has(key)) {
+          dropped.push(key);
+        }
+      }
+    }
+    // Any entry here exists on the editor-ext node/mark but NOT in the mirror
+    // (and is not a blessed non-round-trippable omission): documents using it
+    // lose that attribute on a git-sync round-trip — the subpages.recursive
+    // class. Re-sync src/lib/docmost-schema.ts (and the surface snapshot) or add
+    // a reasoned ACCEPTED_ATTR_OMISSIONS entry before clearing.
+    expect(dropped.sort()).toEqual([]);
+  });
+
+  it("keeps every editor-ext attribute DEFAULT in sync — no silent default drift", () => {
+    const drift: string[] = [];
+    for (const [name, { kind, attrs }] of editorExtOwnAttrs()) {
+      const mirror = mirrorAttrs(name, kind);
+      if (!mirror) continue;
+      for (const [attr, extDefault] of Object.entries(attrs)) {
+        const key = `${name}.${attr}`;
+        // Skip attrs editor-ext declares WITHOUT a default (required attrs):
+        // the mirror deliberately makes them optional (`null`), a safe superset.
+        if (extDefault === undefined) continue;
+        if (!(attr in mirror)) continue; // a drop, reported by the name test
+        if (
+          JSON.stringify(mirror[attr]) !== JSON.stringify(extDefault) &&
+          !ACCEPTED_DEFAULT_DIVERGENCE.has(key)
+        ) {
+          drift.push(
+            `${key}: mirror=${JSON.stringify(mirror[attr])} editor-ext=${JSON.stringify(extDefault)}`,
+          );
+        }
+      }
+    }
+    expect(drift.sort()).toEqual([]);
+  });
+
+  it("the attribute allowlists have no stale rows (each is really omitted / divergent)", () => {
+    const ext = editorExtOwnAttrs();
+    const staleOmission: string[] = [];
+    for (const key of ACCEPTED_ATTR_OMISSIONS) {
+      const [name, attr] = key.split(".");
+      const entry = ext.get(name);
+      const mirror = entry ? mirrorAttrs(name, entry.kind) : null;
+      // Stale if editor-ext no longer declares it, or the mirror now DOES vendor
+      // it (so it should be removed from the omission allowlist).
+      if (!entry || !(attr in entry.attrs) || (mirror && attr in mirror)) {
+        staleOmission.push(key);
+      }
+    }
+    expect(staleOmission, "stale ACCEPTED_ATTR_OMISSIONS rows").toEqual([]);
+
+    const staleDivergence: string[] = [];
+    for (const key of ACCEPTED_DEFAULT_DIVERGENCE) {
+      const [name, attr] = key.split(".");
+      const entry = ext.get(name);
+      const mirror = entry ? mirrorAttrs(name, entry.kind) : null;
+      const extDefault = entry?.attrs[attr];
+      // Stale if the divergence no longer exists (attr gone, or defaults now
+      // agree) — the row should be dropped so the allowlist stays honest.
+      if (
+        !entry ||
+        !mirror ||
+        !(attr in entry.attrs) ||
+        !(attr in mirror) ||
+        extDefault === undefined ||
+        JSON.stringify(mirror[attr]) === JSON.stringify(extDefault)
+      ) {
+        staleDivergence.push(key);
+      }
+    }
+    expect(staleDivergence, "stale ACCEPTED_DEFAULT_DIVERGENCE rows").toEqual([]);
+  });
+});

packages/prosemirror-markdown/vitest.config.ts

@@ -9,11 +9,18 @@ import { defineConfig } from 'vitest/config';
 // envelope, markdownToProseMirror) is re-exported there.
 const here = path.dirname(fileURLToPath(import.meta.url));
 const libBarrel = path.resolve(here, 'src/lib/index.ts');
+// Resolve the cross-package `@docmost/editor-ext` specifier to the SIBLING
+// workspace SOURCE. In a normal checkout this is what pnpm's workspace link +
+// the package's `module` field already yield; pinning it here makes the schema
+// contract tests (incl. the #515 code-excludes parity) hermetic and independent
+// of node_modules layout (e.g. a shared/hoisted store in a git worktree).
+const editorExtBarrel = path.resolve(here, '../editor-ext/src/index.ts');
 
 export default defineConfig({
   resolve: {
     alias: {
       'docmost-client': libBarrel,
+      '@docmost/editor-ext': editorExtBarrel,
     },
   },
   test: {