fix(mcp): форма сохраняет deny-all allowlist вместо тихого расширения до allow-all (#477 ревью)

F1: сервер с tool_allowlist=[] (deny-all) грузился в форму пустым TagsInput;
submit слал null (allow-all) → админ, открывший deny-all сервер сменить
имя/URL, молча отдавал агенту ВСЕ тулы (тот же silent-widen класс #476, что
PR закрывает на read-стороне). Вынесен pure-хелпер resolveToolAllowlist:
пустое поле + сервер был [] → [] (deny-all сохранён); пустое + был null →
null (реально неограниченный остаётся). +тест (5 кейсов, различие []vs null).

F2: CHANGELOG/Security — флип семантики allowlist ([]=deny-all, было
NULL/allow-all; corrupt→fail-closed deny-all; форма не расширяет deny-all).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/workflows/develop.yml

@@ -62,6 +62,38 @@ jobs:
     needs: [test, e2e-server, e2e-mcp, build]
     runs-on: ubuntu-latest
     timeout-minutes: 30
+    # Image boot-smoke (issue #476): every other job tests code from the working
+    # tree, but the :develop IMAGE that watchtower pulls was never actually
+    # started anywhere (incident classes #353/#452/#361-boot: startup-migrator
+    # crash-loop, runtime module missing from the image, wrong static-asset
+    # headers). The services below back a smoke boot of the exact image right
+    # before it is pushed; a smoke failure blocks the push.
+    services:
+      postgres:
+        # via mirror.gcr.io (Docker Hub pull-through cache; avoids Hub anonymous
+        # pull rate-limit that randomly fails on shared GitHub runner IPs).
+        image: mirror.gcr.io/pgvector/pgvector:pg18
+        env:
+          POSTGRES_DB: docmost
+          POSTGRES_USER: docmost
+          POSTGRES_PASSWORD: docmost
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd "pg_isready -U docmost"
+          --health-interval 5s
+          --health-timeout 5s
+          --health-retries 20
+      redis:
+        # via mirror.gcr.io (see postgres note above).
+        image: mirror.gcr.io/library/redis:7
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 5s
+          --health-timeout 5s
+          --health-retries 20
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -82,6 +114,37 @@ jobs:
         id: version
         run: echo "value=$(git describe --tags --always)" >> "$GITHUB_OUTPUT"
 
+      # Load the image into the local docker daemon so it can be booted (the
+      # push step below exports straight to the registry and leaves nothing
+      # runnable locally). CONVENTION: build-args here must stay TEXTUALLY
+      # IDENTICAL to the push step's build-args — same cache scope + same args
+      # means the layers are reused and the image we smoke IS the image we push.
+      - name: Build image for smoke (load, no push)
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          platforms: linux/amd64
+          build-args: |
+            APP_VERSION=${{ steps.version.outputs.value }}
+            AI_AGENT_ROLES_CATALOG_URL=https://raw.githubusercontent.com/vvzvlad/gitmost/develop/agent-roles-catalog
+          load: true
+          push: false
+          tags: gitmost:smoke
+          cache-from: type=gha,scope=develop-amd64
+
+      # Boot-smoke the exact image against the job services (see the comment on
+      # `services:` above): health (startup migrator), auth/setup, client dist
+      # served, immutable + brotli asset headers. Fails the job (and therefore
+      # the push) on any miss.
+      - name: Smoke the built image
+        run: bash scripts/ci/image-smoke.sh gitmost:smoke
+
+      # The smoke script leaves the container running on failure precisely so
+      # the boot error (migration mismatch, stack trace) is diagnosable here.
+      - name: Dump smoke container log on failure
+        if: failure()
+        run: docker logs gitmost-smoke 2>&1 | tail -200 || true
+
       - name: Build and push develop image
         uses: docker/build-push-action@v6
         with:

.github/workflows/test.yml

@@ -25,37 +25,65 @@ jobs:
   # filename sorts BEFORE migrations already applied on the target branch (and
   # thus in prod). The Kysely startup migrator rejects that as "corrupted
   # migrations" and crash-loops the app on boot (incident #361). This gate fails
-  # the PR so the migration is renamed to a current timestamp before merge. Only
-  # runs for pull_request events (needs a base branch to diff against).
+  # the PR so the migration is renamed to a current timestamp before merge.
+  # Runs for pull_request (diff against the base branch) AND for push (#476
+  # retrospective: a DIRECT push to develop used to bypass this PR-only gate
+  # entirely — now the push is diffed against its `before` SHA; workflow_call
+  # from develop.yml inherits the caller's push event). workflow_dispatch has
+  # nothing to diff against and still skips the job.
   migration-order:
-    if: github.event_name == 'pull_request'
+    if: github.event_name == 'pull_request' || github.event_name == 'push'
     runs-on: ubuntu-latest
     timeout-minutes: 5
     steps:
-      - name: Checkout (full history for the base-branch diff)
+      - name: Checkout (full history for the base diff)
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - name: Added migrations must sort after the newest on the base branch
+      - name: Added migrations must sort after the newest on the base
         env:
           TARGET_BRANCH: ${{ github.base_ref }}
+          BEFORE_SHA: ${{ github.event.before }}
         run: |
           set -euo pipefail
           MIG_DIR="apps/server/src/database/migrations"
-          # checkout above already did fetch-depth:0 (full history). Fetch the base
-          # WITHOUT --depth (a shallow graft would truncate the base history and
-          # break the merge-base when the base has moved ahead of the PR merge —
-          # exactly the long-branch-vs-moving-base case this gate guards, #361).
-          git fetch --no-tags origin "$TARGET_BRANCH"
-          newest_on_target=$(git ls-tree -r --name-only "origin/${TARGET_BRANCH}" "$MIG_DIR" | sort | tail -1)
+          if [ "${GITHUB_EVENT_NAME}" = "pull_request" ]; then
+            # checkout above already did fetch-depth:0 (full history). Fetch the base
+            # WITHOUT --depth (a shallow graft would truncate the base history and
+            # break the merge-base when the base has moved ahead of the PR merge —
+            # exactly the long-branch-vs-moving-base case this gate guards, #361).
+            git fetch --no-tags origin "$TARGET_BRANCH"
+            BASE="origin/${TARGET_BRANCH}"
+          else
+            # push event: compare against the pre-push tip of the branch.
+            if [ "$BEFORE_SHA" = "0000000000000000000000000000000000000000" ]; then
+              echo "::notice::branch creation push — nothing to compare"
+              exit 0
+            fi
+            if ! git cat-file -e "${BEFORE_SHA}^{commit}" 2>/dev/null; then
+              # The before-SHA is not in the clone (a force-push rewrote history).
+              # One recovery attempt — refresh every remote head (cheap: the
+              # checkout is already fetch-depth:0); a fetch failure aborts via
+              # `set -e`, which is fail-closed too.
+              git fetch --no-tags origin '+refs/heads/*:refs/remotes/origin/*'
+            fi
+            if ! git cat-file -e "${BEFORE_SHA}^{commit}" 2>/dev/null; then
+              # FAIL-CLOSED: without the before-SHA there is no base to prove the
+              # ordering against, and a gate whose job is to BLOCK must not guess.
+              echo "::error::force-push detected — verify migration order manually, then re-run via workflow_dispatch"
+              exit 1
+            fi
+            BASE="$BEFORE_SHA"
+          fi
+          newest_on_target=$(git ls-tree -r --name-only "$BASE" "$MIG_DIR" | sort | tail -1)
           # NO `|| true`: a diff failure (e.g. an unresolved merge-base) must fail
           # the job CLOSED — a gate whose job is to BLOCK must never pass on error.
           # `set -e` above already aborts on a non-zero diff exit.
-          added=$(git diff --diff-filter=A --name-only "origin/${TARGET_BRANCH}...HEAD" -- "$MIG_DIR")
+          added=$(git diff --diff-filter=A --name-only "${BASE}...HEAD" -- "$MIG_DIR")
           bad=0
           for f in $added; do
             if [[ "$f" < "$newest_on_target" || "$f" == "$newest_on_target" ]]; then
-              echo "::error::Migration $f sorts at or before the newest on ${TARGET_BRANCH} ($newest_on_target) — rename it with a CURRENT timestamp before merge (do not change its contents). See incident #361."
+              echo "::error::Migration $f sorts at or before the newest on the base ($newest_on_target) — rename it with a CURRENT timestamp before merge (do not change its contents). See incident #361."
               bad=1
             fi
           done

CHANGELOG.md

@@ -302,15 +302,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
-- **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
@@ -394,6 +385,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   through that exact share (its own share or an ancestor `includeSubPages`
   share); any other value now returns the generic "not found" instead of
   serving the page. (#218)
+- **MCP tool-allowlist semantics flipped: an empty `[]` now means deny-all
+  (previously it was coerced to "no restrictions").** For an external MCP server,
+  a stored `tool_allowlist` of `[]` now denies **every** tool of that server
+  (zero tools reach the agent) instead of being treated as an empty/unset filter
+  that allowed all of them. A corrupt or non-array stored value now **fails
+  closed** to deny-all rather than silently allowing everything. The admin form
+  no longer silently widens an existing deny-all server: leaving its tag field
+  empty preserves `[]` (deny-all) on save instead of NULL-ing the column to
+  allow-all, so a routine rename/toggle can no longer grant the agent every tool.
+  "No restrictions" is still expressible — a genuinely unrestricted server stores
+  NULL, and clearing the field on such a server keeps it NULL. Operationally
+  significant: audit any server that was created or left with a literal `[]`, as
+  it now exposes no tools until an explicit allowlist (or NULL) is set. (#476)
 
 ## [0.94.0] - 2026-06-26
 

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, Code } from "@docmost/editor-ext";
+import { Mention, LinkExtension } from "@docmost/editor-ext";
 import classes from "./comment.module.css";
 import { useFocusWithin } from "@mantine/hooks";
 import clsx from "clsx";
@@ -44,12 +44,7 @@ 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

@@ -1,5 +1,6 @@
 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";
@@ -66,7 +67,6 @@ import {
   FootnoteReference,
   FootnotesList,
   FootnoteDefinition,
-  Code,
 } from "@docmost/editor-ext";
 import {
   randomElement,
@@ -153,10 +153,6 @@ 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 — asserted ABSENT (the block-escape lives in the serializer now)
+const ZWSP = "​"; // U+200B, the helper's block-trigger neutralizer
 
 /**
  * #377 — the web-side bridge must append the native host's transcript below the
@@ -18,9 +18,8 @@ const ZWSP = "​"; // U+200B — asserted ABSENT (the block-escape lives in the
  * 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 stored verbatim (the git-sync
- * serializer block-escapes them, so no client-side ZWSP is needed);
- * absent/empty/non-string -> no-op.
+ * parsing); col-0 markdown block triggers are neutralized so git-sync keeps them
+ * paragraphs; absent/empty/non-string -> no-op.
  */
 describe("gitmostInsertTranscriptIntoEditor", () => {
   const makeEditor = () =>
@@ -92,22 +91,19 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
     editor.destroy();
   });
 
-  it("inserts col-0 markdown block triggers as verbatim paragraph text (no ZWSP workaround)", () => {
+  it("neutralizes col-0 markdown block triggers with a leading ZWSP (git-sync safety)", () => {
     const editor = makeEditor();
-    // 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.
+    // Trigger lines (some with a leaked indent) + a normal prefixed line.
     const inserted = gitmostInsertTranscriptIntoEditor(
       editor,
       [
         "- dash",
-        "  > quote", // leading indent is trimmed, text otherwise verbatim
+        "  > quote", // leading indent must be trimmed then neutralized
         "# hash",
         "1. one",
         "> [!info] note",
         "```js",
-        "---",
+        "---", // solid thematic break -> horizontalRule (text-losing) if unneutralized
         "***",
         "___",
         "You: normal line",
@@ -120,23 +116,20 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
       .map((n: any) => n.content?.[0]?.text)
       .filter((t: any) => typeof t === "string") as string[];
 
-    // 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.
+    // Every block-trigger line is prefixed with the invisible ZWSP (indent
+    // trimmed first); the normal `You:` line is left byte-exact.
     expect(texts).toEqual([
-      "- dash",
-      "> quote",
-      "# hash",
-      "1. one",
-      "> [!info] note",
-      "```js",
-      "---",
-      "***",
-      "___",
+      ZWSP + "- dash",
+      ZWSP + "> quote",
+      ZWSP + "# hash",
+      ZWSP + "1. one",
+      ZWSP + "> [!info] note",
+      ZWSP + "```js",
+      ZWSP + "---",
+      ZWSP + "***",
+      ZWSP + "___",
       "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

@@ -240,22 +240,45 @@ 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
-// 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.
+// 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.
 export function gitmostInsertTranscriptIntoEditor(
   editor: Editor,
   transcript: unknown,
@@ -265,7 +288,13 @@ export function gitmostInsertTranscriptIntoEditor(
     .split("\n")
     // Trim each line and drop blank (whitespace-only) ones.
     .map((line) => line.trim())
-    .filter((line) => line.length > 0);
+    .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,
+    );
   if (lines.length === 0) return false;
 
   const content = [

apps/client/src/features/workspace/components/settings/components/ai-mcp-server-form.tsx

@@ -28,6 +28,7 @@ import {
   IAiMcpServerCreate,
   IAiMcpServerUpdate,
 } from "@/features/workspace/services/ai-mcp-server-service.ts";
+import { resolveToolAllowlist } from "./ai-mcp-server-form.utils.ts";
 
 const formSchema = z.object({
   name: z.string().min(1),
@@ -121,13 +122,20 @@ export default function AiMcpServerForm({
   async function handleSubmit(values: FormValues) {
     const headers = resolveHeaders();
 
+    // An empty tag field means "no restriction" (sent as null) — since #476 the
+    // server persists a literal `[]` as deny-all (zero tools). But a server that
+    // was ALREADY deny-all loads into an empty field too; sending null there
+    // would silently widen it to allow-all on a routine edit, so preserve `[]`.
+    // See resolveToolAllowlist for the full rationale.
+    const toolAllowlist = resolveToolAllowlist(values.toolAllowlist, server);
+
     if (isEdit && server) {
       const payload: IAiMcpServerUpdate = {
         id: server.id,
         name: values.name,
         transport: values.transport,
         url: values.url,
-        toolAllowlist: values.toolAllowlist,
+        toolAllowlist,
         // Always sent: a blank value clears the stored guidance (server -> null).
         instructions: values.instructions,
         enabled: values.enabled,
@@ -140,7 +148,7 @@ export default function AiMcpServerForm({
         name: values.name,
         transport: values.transport,
         url: values.url,
-        toolAllowlist: values.toolAllowlist,
+        toolAllowlist,
         // Blank => server stores null (no guidance).
         instructions: values.instructions,
         enabled: values.enabled,

apps/client/src/features/workspace/components/settings/components/ai-mcp-server-form.utils.test.ts

@@ -0,0 +1,29 @@
+import { describe, it, expect } from "vitest";
+import { resolveToolAllowlist } from "./ai-mcp-server-form.utils.ts";
+
+describe("resolveToolAllowlist", () => {
+  it("sends the typed tools when the field is non-empty", () => {
+    expect(resolveToolAllowlist(["a", "b"], { toolAllowlist: null })).toEqual([
+      "a",
+      "b",
+    ]);
+  });
+
+  it("creates as null (unrestricted) when empty and there is no server", () => {
+    expect(resolveToolAllowlist([], undefined)).toBeNull();
+  });
+
+  it("sends null for an empty field on a previously-unrestricted server", () => {
+    expect(resolveToolAllowlist([], { toolAllowlist: null })).toBeNull();
+  });
+
+  it("preserves deny-all: an empty field on a `[]` server stays `[]`, not null", () => {
+    // The core #476/#477 guard: editing a deny-all server (rename/toggle) with
+    // an empty tag field must NOT silently widen it to allow-all.
+    expect(resolveToolAllowlist([], { toolAllowlist: [] })).toEqual([]);
+  });
+
+  it("still sends explicit tools even if the server was deny-all", () => {
+    expect(resolveToolAllowlist(["x"], { toolAllowlist: [] })).toEqual(["x"]);
+  });
+});

apps/client/src/features/workspace/components/settings/components/ai-mcp-server-form.utils.ts

@@ -0,0 +1,22 @@
+import { IAiMcpServer } from "@/features/workspace/services/ai-mcp-server-service.ts";
+
+// Resolve the tool allowlist value to persist from the form field.
+//
+// An empty tag field normally means "no restriction" and is sent as null so
+// the server drops the column (all tools allowed). But a server that was
+// ALREADY deny-all (a stored literal `[]`, meaning zero tools — creatable via
+// the API) loads into the form as an empty field too. Coercing that empty
+// field to null on submit would SILENTLY widen a deny-all server to allow-all
+// on any routine edit (rename, toggle) — the exact silent-widen class #476
+// closed on the read side. So when the edited server was deny-all, preserve
+// `[]` (deny-all); only a genuinely-unrestricted server (stored null/absent)
+// stays null.
+export function resolveToolAllowlist(
+  fieldValue: string[],
+  server?: Pick<IAiMcpServer, "toolAllowlist">,
+): string[] | null {
+  if (fieldValue.length > 0) return fieldValue;
+  const wasDenyAll =
+    Array.isArray(server?.toolAllowlist) && server.toolAllowlist.length === 0;
+  return wasDenyAll ? [] : null;
+}

apps/client/src/features/workspace/services/ai-mcp-server-service.ts

@@ -27,7 +27,9 @@ export interface IAiMcpServerCreate {
   // Auth headers map (e.g. { Authorization: 'Bearer ...' }). Encrypted on save;
   // never returned.
   headers?: Record<string, string>;
-  toolAllowlist?: string[];
+  // Omit/null => no restriction; `[]` is persisted verbatim and means
+  // deny-all (zero tools) since #476.
+  toolAllowlist?: string[] | null;
   // Admin-authored prompt guidance (#180). Blank => stored as null.
   instructions?: string;
   enabled?: boolean;
@@ -43,7 +45,9 @@ export interface IAiMcpServerUpdate {
   transport?: McpTransport;
   url?: string;
   headers?: Record<string, string>;
-  toolAllowlist?: string[];
+  // Absent => unchanged; null => no restriction; `[]` is persisted verbatim
+  // and means deny-all (zero tools) since #476.
+  toolAllowlist?: string[] | null;
   // Admin-authored prompt guidance (#180). Absent => unchanged; blank => cleared.
   instructions?: string;
   enabled?: boolean;

apps/server/package.json

@@ -41,7 +41,6 @@
     "@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/collaboration/collaboration.util.ts

@@ -49,7 +49,6 @@ import {
   FootnotesList,
   FootnoteDefinition,
   PageEmbed,
-  Code,
 } from '@docmost/editor-ext';
 import { convertProseMirrorToMarkdown } from '@docmost/prosemirror-markdown';
 import { generateText, getSchema, JSONContent } from '@tiptap/core';
@@ -68,12 +67,7 @@ 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/core/ai-chat/external-mcp/dto/create-mcp-server.dto.ts

@@ -37,10 +37,13 @@ export class CreateMcpServerDto {
   @IsObject()
   headers?: Record<string, string>;
 
+  // Omit/null => no restriction; `[]` is persisted verbatim and means deny-all
+  // (zero tools) since #476. @IsOptional() skips validation for null as well,
+  // so an explicit null is accepted.
   @IsOptional()
   @IsArray()
   @IsString({ each: true })
-  toolAllowlist?: string[];
+  toolAllowlist?: string[] | null;
 
   // Admin-authored guidance ("how/when to use this server's tools") injected
   // into the agent system prompt next to the tool descriptions (#180). Trusted,

apps/server/src/core/ai-chat/external-mcp/dto/update-mcp-server.dto.ts

@@ -38,10 +38,13 @@ export class UpdateMcpServerDto {
   @IsObject()
   headers?: Record<string, string>;
 
+  // Absent => unchanged; null => no restriction; `[]` is persisted verbatim
+  // and means deny-all (zero tools) since #476. @IsOptional() skips validation
+  // for null as well, so an explicit null is accepted.
   @IsOptional()
   @IsArray()
   @IsString({ each: true })
-  toolAllowlist?: string[];
+  toolAllowlist?: string[] | null;
 
   // Admin-authored prompt guidance (#180). Absent => unchanged; blank => cleared
   // (stored as null by the repo). Capped to bound prompt/token size.

apps/server/src/core/ai-chat/external-mcp/mcp-allowlist-filter.spec.ts

@@ -0,0 +1,169 @@
+import { type Tool } from 'ai';
+import { McpClientsService } from './mcp-clients.service';
+
+/**
+ * Tool-allowlist filtering semantics on the merged external toolset (#476).
+ *
+ * COVERAGE CHOICE (documented per issue #476): the full corrupt-row chain
+ * (DB value -> repo normalizeRow -> toolsFor filter) is covered on TWO levels
+ * instead of one live-stub-MCP-server integration test:
+ *   (a) apps/server/test/integration/ai-mcp-server-repo.int-spec.ts pins the
+ *       repo read/write semantics against a real Postgres — `[]` round-trips
+ *       as jsonb `[]`, a present-but-corrupt value fails CLOSED to `[]` with
+ *       an error log;
+ *   (b) THIS spec pins what the toolset builder does with the repo's output —
+ *       null = unrestricted, `['alpha']` = only alpha, `[]` (including the
+ *       corrupt-row fallback) = ZERO tools.
+ * Together they prove the end-to-end property "corrupt/empty allowlist can
+ * never widen to all tools" without a live stub HTTP MCP server.
+ *
+ * The drive path mirrors mcp-namespacing.spec.ts: stub the repo's listEnabled,
+ * spy the private `connect` to return a fake client, inspect the merged keys.
+ */
+
+function fakeTool(): Tool {
+  return { description: 'x', inputSchema: undefined } as unknown as Tool;
+}
+
+interface FakeServer {
+  id: string;
+  name: string;
+  transport: string;
+  url: string;
+  headersEnc: string | null;
+  toolAllowlist: string[] | null;
+}
+
+function server(
+  over: Partial<FakeServer> & { id: string; name: string },
+): FakeServer {
+  return {
+    transport: 'http',
+    url: 'https://example.com/mcp',
+    headersEnc: null,
+    toolAllowlist: null,
+    ...over,
+  };
+}
+
+/**
+ * Build a service whose repo returns `servers` and whose fake clients expose
+ * `rawTools` from tools(). Returns the merged tool keys produced by toolsFor.
+ */
+async function mergedKeysFor(
+  servers: FakeServer[],
+  rawTools: Record<string, Tool>,
+): Promise<string[]> {
+  const repoStub = {
+    listEnabled: jest.fn().mockResolvedValue(servers),
+  };
+  const service = new McpClientsService(repoStub as never, {} as never);
+
+  jest
+    .spyOn(
+      service as unknown as { connect: (s: FakeServer) => unknown },
+      'connect',
+    )
+    .mockImplementation(() =>
+      Promise.resolve({
+        tools: () => Promise.resolve(rawTools),
+        close: () => Promise.resolve(),
+      }),
+    );
+
+  const toolset = await service.toolsFor('ws-1');
+  // Release the lease so the service does not hold the fake clients open.
+  await Promise.all(toolset.clients.map((c) => c.close()));
+  return Object.keys(toolset.tools);
+}
+
+describe('external MCP tool-allowlist filtering (via toolsFor, #476)', () => {
+  afterEach(() => jest.restoreAllMocks());
+
+  const RAW = () => ({
+    alpha: fakeTool(),
+    beta: fakeTool(),
+    gamma: fakeTool(),
+  });
+
+  it("['alpha'] lets ONLY alpha through", async () => {
+    const keys = await mergedKeysFor(
+      [server({ id: 'id-1', name: 'srv', toolAllowlist: ['alpha'] })],
+      RAW(),
+    );
+    expect(keys).toEqual(['srv_alpha']);
+  });
+
+  it('null (no restriction) lets every tool through', async () => {
+    const keys = await mergedKeysFor(
+      [server({ id: 'id-1', name: 'srv', toolAllowlist: null })],
+      RAW(),
+    );
+    expect(keys.sort()).toEqual(['srv_alpha', 'srv_beta', 'srv_gamma']);
+  });
+
+  it('[] (deny-all) yields ZERO tools — an empty array is authoritative, not falsy (#476)', async () => {
+    // This is the regression the #476 change guards: `[]` used to fall through
+    // the old `allow.length > 0` check and expose ALL tools. It must expose NONE.
+    const keys = await mergedKeysFor(
+      [server({ id: 'id-1', name: 'srv', toolAllowlist: [] })],
+      RAW(),
+    );
+    expect(keys).toEqual([]);
+  });
+
+  it('the corrupt-row fallback ([] from the repo) also yields ZERO tools (#476)', async () => {
+    // The repo turns a present-but-corrupt tool_allowlist into `[]` (fail-closed,
+    // see normalizeRow in ai-mcp-server.repo.ts + the int-spec); this pins that
+    // the toolset builder honours that fallback as deny-all rather than allow-all.
+    const corruptFallback: string[] = [];
+    const keys = await mergedKeysFor(
+      [server({ id: 'id-1', name: 'srv', toolAllowlist: corruptFallback })],
+      RAW(),
+    );
+    expect(keys).toEqual([]);
+  });
+
+  it('allowlisted names not exposed by the server are ignored (no phantom tools)', async () => {
+    const keys = await mergedKeysFor(
+      [
+        server({
+          id: 'id-1',
+          name: 'srv',
+          toolAllowlist: ['alpha', 'does-not-exist'],
+        }),
+      ],
+      RAW(),
+    );
+    expect(keys).toEqual(['srv_alpha']);
+  });
+
+  it('a deny-all server contributes no prompt instructions (0 tools merged)', async () => {
+    const repoStub = {
+      listEnabled: jest.fn().mockResolvedValue([
+        {
+          ...server({ id: 'id-1', name: 'srv', toolAllowlist: [] }),
+          instructions: 'use the tools wisely',
+        },
+      ]),
+    };
+    const service = new McpClientsService(repoStub as never, {} as never);
+    jest
+      .spyOn(
+        service as unknown as { connect: (s: FakeServer) => unknown },
+        'connect',
+      )
+      .mockImplementation(() =>
+        Promise.resolve({
+          tools: () => Promise.resolve(RAW()),
+          close: () => Promise.resolve(),
+        }),
+      );
+
+    const toolset = await service.toolsFor('ws-1');
+    await Promise.all(toolset.clients.map((c) => c.close()));
+    expect(Object.keys(toolset.tools)).toEqual([]);
+    // mergeNamespaced reported 0 contributed tools, so no guidance is attached.
+    expect(toolset.instructions).toEqual([]);
+  });
+});

apps/server/src/core/ai-chat/external-mcp/mcp-clients.service.ts

@@ -285,9 +285,13 @@ export class McpClientsService {
       try {
         client = await this.connectWithTimeout(server, CONNECT_TIMEOUT_MS);
         const raw = await withTimeout(client.tools(), CONNECT_TIMEOUT_MS);
+        // Allowlist semantics (#476): null/absent = no restriction (all tools);
+        // ANY array — including `[]` — is authoritative, so an EMPTY allowlist
+        // yields ZERO tools (deny-all). Do NOT add a `.length > 0` escape here:
+        // that read `[]` as falsy and silently widened deny-all to allow-all
+        // (the repo also fails corrupt rows closed to `[]` for the same reason).
         const allow = server.toolAllowlist;
-        const picked =
-          Array.isArray(allow) && allow.length > 0 ? pick(raw, allow) : raw;
+        const picked = Array.isArray(allow) ? pick(raw, allow) : raw;
         // Bound each tool's execute with a per-call total-timeout guard before
         // merging, so a single chatty-but-stuck call is aborted after the cap.
         const guarded = wrapToolsWithCallTimeout(picked, callTimeoutMs);

apps/server/src/core/ai-chat/external-mcp/mcp-servers.service.ts

@@ -100,7 +100,8 @@ export class McpServersService {
       transport: dto.transport,
       url: dto.url,
       headersEnc,
-      // undefined => unchanged; [] / value handled by repo (empty => null).
+      // undefined => unchanged; null => no restriction; `[]` is persisted
+      // verbatim and means deny-all (#476).
       toolAllowlist: dto.toolAllowlist,
       // undefined => unchanged; blank => cleared (null) by the repo.
       instructions: dto.instructions,

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

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

apps/server/src/database/jsonb-bind.spec.ts

@@ -35,4 +35,25 @@ describe('jsonbBind', () => {
     expect(out).not.toBeNull();
     expect(out).toBeDefined();
   });
+
+  // preserveEmpty (#476): opts a column OUT of the empty-to-null collapse so an
+  // empty container is persisted verbatim (e.g. `[]` = deny-all for
+  // tool_allowlist). null stays null regardless of the flag.
+  describe('preserveEmpty', () => {
+    it('returns a (non-null) bind for an empty array', () => {
+      const out = jsonbBind([], { preserveEmpty: true });
+      expect(out).not.toBeNull();
+      expect(out).toBeDefined();
+    });
+
+    it('returns a (non-null) bind for an empty object', () => {
+      const out = jsonbBind({}, { preserveEmpty: true });
+      expect(out).not.toBeNull();
+      expect(out).toBeDefined();
+    });
+
+    it('still returns null for null (null means null, flag or not)', () => {
+      expect(jsonbBind(null, { preserveEmpty: true })).toBeNull();
+    });
+  });
 });

apps/server/src/database/repos/ai-chat/ai-mcp-server.repo.ts

@@ -78,7 +78,9 @@ export class AiMcpServerRepo {
         headersEnc: values.headersEnc ?? null,
         // jsonb column: the postgres driver would otherwise encode a JS array as
         // a Postgres array literal. Bind the JSON text and cast it to jsonb.
-        toolAllowlist: jsonbBind(values.toolAllowlist),
+        // preserveEmpty (#476): `[]` is a real value here (deny-all), distinct
+        // from null ("no restriction") — it must round-trip as `[]`, not null.
+        toolAllowlist: jsonbBind(values.toolAllowlist, { preserveEmpty: true }),
         // Plain text column: blank/whitespace-only guidance is stored as null.
         instructions: blankToNull(values.instructions),
         enabled: values.enabled ?? true,
@@ -111,7 +113,10 @@ export class AiMcpServerRepo {
     if (patch.url !== undefined) set.url = patch.url;
     if (patch.headersEnc !== undefined) set.headersEnc = patch.headersEnc;
     if (patch.toolAllowlist !== undefined) {
-      set.toolAllowlist = jsonbBind(patch.toolAllowlist);
+      // preserveEmpty (#476): see insert — `[]` (deny-all) must not become null.
+      set.toolAllowlist = jsonbBind(patch.toolAllowlist, {
+        preserveEmpty: true,
+      });
     }
     if (patch.instructions !== undefined) {
       // Blank/whitespace-only guidance clears the column (stored as null).
@@ -158,7 +163,9 @@ export function blankToNull(value: string | null | undefined): string | null {
  * fix), so the driver hands back a string like `'["a","b"]'` rather than an
  * array. Be tolerant: normalize a JSON string to its value, then accept it only
  * if it is an array of strings; null / a non-array / unparseable value / an
- * array with a non-string element all become null (unrestricted).
+ * array with a non-string element all become null. NOTE: null here only means
+ * "could not parse" — the null-vs-deny-all policy decision lives in
+ * normalizeRow (#476: present-but-corrupt fails CLOSED to `[]`).
  */
 export function parseToolAllowlist(value: unknown): string[] | null {
   // Shape guard only; the legacy double-encoding self-heal lives in
@@ -173,17 +180,20 @@ export function parseToolAllowlist(value: unknown): string[] | null {
 /**
  * Normalize a DB row so `toolAllowlist` is always `string[] | null`.
  *
- * FAIL-OPEN logging: a stored value that is present but cannot be parsed into a
- * string[] (corrupt JSON, a non-array, non-string elements) degrades to `null` =
- * "no restriction", so the agent silently gets ALL of the server's tools. Log
- * one line (server id only, never the contents) so that widening is not silent.
+ * FAIL-CLOSED (#476): a stored value that is PRESENT but cannot be parsed into
+ * a string[] (corrupt JSON, a non-array, non-string elements) degrades to `[]`
+ * = deny-all, so a corrupted allowlist can never silently widen to "the agent
+ * gets ALL of the server's tools" (the old fail-open null). An error line is
+ * logged (server id only, never the contents) so the admin can repair the row.
+ * A column that is truly NULL/absent stays `null` = "no restriction".
  */
 function normalizeRow(row: AiMcpServer): AiMcpServer {
   const parsed = parseToolAllowlist(row.toolAllowlist);
   if (parsed === null && row.toolAllowlist != null) {
-    logger.warn(
-      `Corrupt tool_allowlist for MCP server ${row.id}; ignoring it (no tool restriction applied)`,
+    logger.error(
+      `Corrupt tool_allowlist for MCP server ${row.id}; failing closed (NO tools allowed) — re-save the server's allowlist to repair it`,
     );
+    return { ...row, toolAllowlist: [] };
   }
   return { ...row, toolAllowlist: parsed };
 }

apps/server/src/database/utils.ts

@@ -78,18 +78,30 @@ export function violatedConstraint(err: unknown): string | undefined {
  * verbatim); `::jsonb` then parses it into a real array/object. Read-side
  * parsers repair rows written the old buggy way without a migration.
  *
- * Returns `null` for null/undefined and for "empty" values (an empty array, or
- * an object with no own enumerable keys) — callers treat empty as "clear/unset",
- * so an empty allowlist/config never round-trips as `[]`/`{}`.
+ * Returns `null` for null/undefined. By default it ALSO returns `null` for
+ * "empty" values (an empty array, or an object with no own enumerable keys) —
+ * most callers treat empty as "clear/unset", so an empty config never
+ * round-trips as `[]`/`{}`.
+ *
+ * `preserveEmpty` (issue #476) opts a column OUT of that empty-to-null
+ * normalization so `[]`/`{}` are persisted as real jsonb values. Needed where
+ * empty and null mean DIFFERENT things: an empty `tool_allowlist` is
+ * deny-all ("zero tools allowed"), while null is "no restriction" — collapsing
+ * `[]` to null silently widened deny-all to allow-all. Deliberately an opt-in
+ * flag, NOT a global change: the other jsonb callers (model_config, source)
+ * keep the empty-means-unset contract.
  */
 export function jsonbBind<T>(
   value: T | null | undefined,
+  opts?: { preserveEmpty?: boolean },
 ): RawBuilder<T> | null {
   if (value === null || value === undefined) return null;
-  if (Array.isArray(value)) {
-    if (value.length === 0) return null;
-  } else if (typeof value === 'object') {
-    if (Object.keys(value as object).length === 0) return null;
+  if (!opts?.preserveEmpty) {
+    if (Array.isArray(value)) {
+      if (value.length === 0) return null;
+    } else if (typeof value === 'object') {
+      if (Object.keys(value as object).length === 0) return null;
+    }
   }
   return sql<T>`${JSON.stringify(value)}::text::jsonb`;
 }

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

@@ -22,12 +22,10 @@ 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,
-  normalizeForeignMarkdown,
-} from '@docmost/prosemirror-markdown';
+import { markdownToProseMirror } 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

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

apps/server/src/integrations/import/utils/foreign-markdown.spec.ts

@@ -1,15 +1,12 @@
-import { describe, it, expect } from 'vitest';
-import { convertProseMirrorToMarkdown } from '../src/lib/markdown-converter.js';
-import { markdownToProseMirror } from '../src/lib/markdown-to-prosemirror.js';
 import {
-  normalizeForeignMarkdown,
-  normalizeAgentMarkdown,
-} from '../src/lib/foreign-markdown.js';
+  convertProseMirrorToMarkdown,
+  markdownToProseMirror,
+} from '@docmost/prosemirror-markdown';
+import { normalizeForeignMarkdown } from './foreign-markdown';
 
 /**
- * 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`).
+ * STEP 2 goldens for issue #345: 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
@@ -219,53 +216,3 @@ 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(/\[\^1\]:/);
-  });
-});

apps/server/src/integrations/import/utils/foreign-markdown.ts

@@ -1,14 +1,7 @@
 /**
  * Foreign-markdown normalizer — an input-liberal / output-canonical adapter that
  * runs at the IMPORT boundary, BEFORE the canonical parser
- * (`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.
+ * (`markdownToProseMirror` from `@docmost/prosemirror-markdown`).
  *
  * The canonical parser is deliberately STRICT: it only understands Docmost's
  * canonical markdown surface (Obsidian-style `> [!type]` callouts, Pandoc/Obsidian
@@ -254,18 +247,11 @@ function convertReferenceFootnotes(markdown: string): string {
 const YAML_FRONT_MATTER_RE = /^\uFEFF?---\n[\s\S]*?\n---\n?/;
 
 /**
- * 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).
+ * 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.
  */
 export function normalizeForeignMarkdown(markdown: string): string {
   if (!markdown) return markdown;
@@ -278,26 +264,3 @@ 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);
-}

apps/server/test/integration/ai-mcp-server-repo.int-spec.ts

@@ -1,5 +1,6 @@
 import { Kysely, sql } from 'kysely';
 import { randomUUID } from 'node:crypto';
+import { Logger } from '@nestjs/common';
 import { AiMcpServerRepo } from '@docmost/db/repos/ai-chat/ai-mcp-server.repo';
 import { getTestDb, destroyTestDb, createWorkspace } from './db';
 
@@ -54,7 +55,11 @@ describe('AiMcpServerRepo tool_allowlist jsonb round-trip [integration]', () =>
     expect(Array.isArray(found?.toolAllowlist)).toBe(true);
   });
 
-  it('an empty allowlist is normalized to null (no restriction), not []', async () => {
+  // #476 (deliberate behaviour change): an empty allowlist used to be
+  // normalized to SQL NULL, which downstream means "no restriction" — so an
+  // admin's deny-all `[]` silently became allow-all. It must now round-trip as
+  // a real jsonb `[]` (deny-all), distinct from NULL.
+  it('an empty allowlist round-trips as jsonb [] (deny-all), not null (#476)', async () => {
     const row = await repo.insert({
       workspaceId: ws,
       name: `srv-${randomUUID()}`,
@@ -62,7 +67,27 @@ describe('AiMcpServerRepo tool_allowlist jsonb round-trip [integration]', () =>
       url: 'https://example.com/mcp',
       toolAllowlist: [],
     });
-    // The column is SQL NULL, so jsonb_typeof returns SQL NULL (JS null).
+    // The column holds a real (empty) jsonb ARRAY, not SQL NULL.
+    expect(await jsonbTypeof(row.id)).toBe('array');
+    expect((await repo.findById(row.id, ws))?.toolAllowlist).toEqual([]);
+  });
+
+  it('update to [] persists jsonb [] and update to null clears to SQL NULL (#476)', async () => {
+    const row = await repo.insert({
+      workspaceId: ws,
+      name: `srv-${randomUUID()}`,
+      transport: 'http',
+      url: 'https://example.com/mcp',
+      toolAllowlist: ['search'],
+    });
+
+    // Deny-all via update: [] must survive as a real jsonb array.
+    await repo.update(row.id, ws, { toolAllowlist: [] });
+    expect(await jsonbTypeof(row.id)).toBe('array');
+    expect((await repo.findById(row.id, ws))?.toolAllowlist).toEqual([]);
+
+    // Explicit clear (null) still means "no restriction" = SQL NULL.
+    await repo.update(row.id, ws, { toolAllowlist: null });
     expect(await jsonbTypeof(row.id)).toBeNull();
     expect((await repo.findById(row.id, ws))?.toolAllowlist).toBeNull();
   });
@@ -92,23 +117,60 @@ describe('AiMcpServerRepo tool_allowlist jsonb round-trip [integration]', () =>
     expect(healed?.toolAllowlist).toEqual(['alpha', 'beta']);
   });
 
-  it('FAIL-OPEN: a present-but-corrupt tool_allowlist reads back as null (no restriction)', async () => {
-    // #185 re-review pt 8: normalizeRow's fail-open branch — the column is
-    // PRESENT but does not parse into a string[] (here a jsonb string scalar
-    // holding non-array JSON). The read must degrade to `null` ("no restriction"),
-    // not crash. (A warn is logged with the server id; not asserted here.)
-    const id = randomUUID();
-    await sql`
-      INSERT INTO ai_mcp_servers (id, workspace_id, name, transport, url, tool_allowlist)
-      VALUES (
-        ${id}, ${ws}, ${`srv-${id}`}, 'http', 'https://example.com/mcp',
-        to_jsonb(${'{"not":"an array"}'}::text)
-      )
-    `.execute(db);
-    // Sanity: the column is present (a jsonb string scalar), not SQL NULL.
-    expect(await jsonbTypeof(id)).toBe('string');
-    // ...yet the read degrades to null (fail-open).
-    expect((await repo.findById(id, ws))?.toolAllowlist).toBeNull();
+  // #476 (deliberate behaviour change, replaces the old FAIL-OPEN pin): a
+  // present-but-corrupt tool_allowlist used to degrade to null ("no
+  // restriction"), silently handing the agent ALL of the server's tools. It
+  // must now FAIL CLOSED to `[]` (deny-all) and log an error.
+  it('FAIL-CLOSED: a present-but-corrupt tool_allowlist reads back as [] (deny-all) + error log (#476)', async () => {
+    const errorSpy = jest
+      .spyOn(Logger.prototype, 'error')
+      .mockImplementation(() => undefined);
+    try {
+      // The column is PRESENT but does not parse into a string[] — a jsonb
+      // string scalar holding unparseable text (a truncated legacy write).
+      const id = randomUUID();
+      await sql`
+        INSERT INTO ai_mcp_servers (id, workspace_id, name, transport, url, tool_allowlist)
+        VALUES (
+          ${id}, ${ws}, ${`srv-${id}`}, 'http', 'https://example.com/mcp',
+          to_jsonb(${'{oops'}::text)
+        )
+      `.execute(db);
+      // Sanity: the column is present (a jsonb string scalar), not SQL NULL.
+      expect(await jsonbTypeof(id)).toBe('string');
+      // ...and the read degrades to [] (fail-closed deny-all), not null.
+      expect((await repo.findById(id, ws))?.toolAllowlist).toEqual([]);
+      // The narrowing is not silent: an error names the server id (never the
+      // corrupt contents).
+      expect(errorSpy).toHaveBeenCalledWith(
+        expect.stringContaining(`Corrupt tool_allowlist for MCP server ${id}`),
+      );
+      expect(
+        errorSpy.mock.calls.some((c) => String(c[0]).includes('{oops')),
+      ).toBe(false);
+    } finally {
+      errorSpy.mockRestore();
+    }
+  });
+
+  it('FAIL-CLOSED: corrupt non-array JSON (an object) also reads back as [] (#476)', async () => {
+    const errorSpy = jest
+      .spyOn(Logger.prototype, 'error')
+      .mockImplementation(() => undefined);
+    try {
+      const id = randomUUID();
+      await sql`
+        INSERT INTO ai_mcp_servers (id, workspace_id, name, transport, url, tool_allowlist)
+        VALUES (
+          ${id}, ${ws}, ${`srv-${id}`}, 'http', 'https://example.com/mcp',
+          to_jsonb(${'{"not":"an array"}'}::text)
+        )
+      `.execute(db);
+      expect(await jsonbTypeof(id)).toBe('string');
+      expect((await repo.findById(id, ws))?.toolAllowlist).toEqual([]);
+    } finally {
+      errorSpy.mockRestore();
+    }
   });
 });
 

packages/editor-ext/src/index.ts

@@ -1,5 +1,4 @@
 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

@@ -1,20 +0,0 @@
-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

@@ -72,13 +72,7 @@ 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> {
-  // 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 md1 = convertProseMirrorToMarkdown(content);
   const doc2 = await markdownToProseMirror(md1);
-  return convertProseMirrorToMarkdown(doc2, { strict: true });
+  return convertProseMirrorToMarkdown(doc2);
 }

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

@@ -4,7 +4,6 @@ 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
@@ -67,23 +66,6 @@ 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/lib/collaboration.ts

@@ -10,10 +10,7 @@ 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,
-  normalizeAgentMarkdown,
-} from "@docmost/prosemirror-markdown";
+import { markdownToProseMirror } from "@docmost/prosemirror-markdown";
 import { docmostExtensions, docmostSchema } from "./docmost-schema.js";
 import { withPageLock } from "./page-lock.js";
 import {
@@ -23,7 +20,6 @@ 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";
 
@@ -101,15 +97,6 @@ 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,
@@ -118,9 +105,7 @@ export async function markdownToProseMirrorCanonical(
   // canonicalizing, so the canonicalizer re-hangs references and drops the
   // now-orphaned duplicate definitions.
   return canonicalizeFootnotes(
-    normalizeAndMergeFootnotes(
-      await markdownToProseMirror(normalizeAgentMarkdown(markdownContent)),
-    ),
+    normalizeAndMergeFootnotes(await markdownToProseMirror(markdownContent)),
   );
 }
 
@@ -343,12 +328,6 @@ export async function updatePageContentRealtime(
     pageId,
     collabToken,
     baseUrl,
-    // #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),
+    () => tiptapJson,
   );
 }

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

@@ -312,9 +312,10 @@ export function canAnchorInDoc(doc: any, selection: string): boolean {
 function spliceCommentMark(
   blockContent: any[],
   match: AnchorMatch,
-  commentMark: any,
+  commentId: string,
 ): void {
   const { startChild, startOffset, endChild, endOffset } = match;
+  const commentMark = makeCommentMark(commentId);
   const fragments: any[] = [];
 
   for (let k = startChild; k <= endChild; k++) {
@@ -450,22 +451,6 @@ 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;
@@ -474,7 +459,7 @@ export function applyCommentMarkInDoc(
     if (!Array.isArray(node.content)) return false;
     const match = findAnchorInBlock(node.content, effective);
     if (match) {
-      spliceCommentMark(node.content, match, commentMark);
+      spliceCommentMark(node.content, match, commentId);
       return true;
     }
     for (const child of node.content) {
@@ -486,97 +471,3 @@ export function applyCommentMarkInDoc(
   };
   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

@@ -1,30 +1,64 @@
 /**
- * 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`.
+ * 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.
  *
- * 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.
+ * 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.
  */
-import {
-  stripInlineMarkdown,
-  stripWrappersAndLinks,
-} from "@docmost/prosemirror-markdown";
 
-// Re-export the canonical locator normalizer so mcp call sites keep importing it
-// from `./text-normalize.js` unchanged.
-export { stripInlineMarkdown };
+/** Maximum unwrap passes, so pathological/nested input cannot loop forever. */
+const MAX_PASSES = 8;
 
 /**
- * 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).
+ * 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).
  *
  * It exists ONLY to recognize formatting-vs-plain INTENT in `applyTextEdits`
  * (deciding whether find/replace differ purely by markdown markers). Because it
@@ -43,6 +77,44 @@ 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-e2e.mjs

@@ -434,6 +434,71 @@ async function main() {
       }
     }
 
+    // 6h. markdown converter fixpoint (#476): pins the converter fixpoint
+    // THROUGH the live server/collab path, not just the package tests. The
+    // unit corpus (docmost-md-roundtrip) proves the converter alone is a
+    // fixpoint; this asserts the property survives the real pipeline — export
+    // (REST read, PM -> MD) -> import (MD -> PM -> collab replace -> server
+    // persistence) -> export — where the server schema, the Yjs structural
+    // diff or the collab write path could still mangle the doc while every
+    // unit test stays green. importPageMarkdown is the designed inverse of
+    // exportPageMarkdown (the self-contained envelope with meta/comments
+    // blocks); updatePageMarkdown (client.updatePage) takes plain authoring
+    // markdown and would re-import the envelope blocks as literal content.
+    {
+      const FIXMD = [
+        "# Fixpoint heading",
+        "",
+        "Paragraph with **bold**, *italic* and a [link](https://example.com).",
+        "",
+        "## Second level",
+        "",
+        "- bullet one",
+        "- bullet two",
+        "",
+        "1. ordered one",
+        "2. ordered two",
+        "",
+        "```js",
+        "const answer = 42; // code block must survive byte-identically",
+        "```",
+        "",
+        "| A | B |",
+        "| --- | --- |",
+        "| one | two |",
+        "",
+        ":::info",
+        "Callout body.",
+        ":::",
+      ].join("\n");
+      const fx = await client.createPage("E2E md fixpoint " + Date.now(), FIXMD, spaceId);
+      const fxid = fx.data.id;
+      try {
+        const md1 = await client.exportPageMarkdown(fxid);
+        await client.importPageMarkdown(fxid, md1);
+        await new Promise((r) => setTimeout(r, 16000)); // wait for server persistence
+        const md2 = await client.exportPageMarkdown(fxid);
+        // On failure, name the first diverging line of the two exports.
+        const firstDiff = (a, b) => {
+          const al = a.split("\n");
+          const bl = b.split("\n");
+          for (let i = 0; i < Math.max(al.length, bl.length); i++) {
+            if (al[i] !== bl[i]) {
+              return `first diff at line ${i + 1}: ${JSON.stringify(al[i] ?? "<EOF>")} -> ${JSON.stringify(bl[i] ?? "<EOF>")}`;
+            }
+          }
+          return "same lines, different bytes (line endings?)";
+        };
+        check(
+          "markdown fixpoint: export -> import -> export is byte-identical",
+          md1 === md2,
+          md1 === md2 ? "" : firstDiff(md1, md2),
+        );
+      } finally {
+        try { await client.deletePage(fxid); } catch {}
+      }
+    }
+
     // 7. shares: create (idempotent), public access, list, unshare
     const share = await client.sharePage(pageId);
     check("sharePage: returns public URL", share.publicUrl?.startsWith(`${APP}/share/`), share.publicUrl);

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

@@ -108,17 +108,6 @@ 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.
@@ -132,8 +121,8 @@ 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: yattr2markname(type), attrs }
-              : { type: yattr2markname(type) },
+              ? { type, attrs }
+              : { type },
           );
         }
         return node;

packages/mcp/test/unit/collab-session.test.mjs

@@ -9,6 +9,7 @@ import {
   __sessionCountForTests,
 } from "../../build/lib/collab-session.js";
 import { withPageLock } from "../../build/lib/page-lock.js";
+import { DocmostClient } from "../../build/client.js";
 
 // A stand-in for HocuspocusProvider: it shares the ydoc (so the real yjs
 // read/transform/write in CollabSession.mutate runs unchanged), auto-completes
@@ -89,6 +90,7 @@ const ENV_KEYS = [
   "MCP_COLLAB_SESSION_IDLE_MS",
   "MCP_COLLAB_SESSION_MAX_AGE_MS",
   "MCP_COLLAB_SESSION_MAX_ENTRIES",
+  "MCP_COLLAB_TOKEN_TTL_MS",
 ];
 let savedEnv;
 
@@ -345,6 +347,86 @@ test("replaceImage-shaped flow: acquire under an EXTERNAL page lock does not dea
   );
 });
 
+// --- #439: the collab-token cache is what makes the session cache ACTUALLY hit ---
+//
+// WHY these two tests exist (the #435 incident): the session registry keys on
+// (wsUrl, pageId, token) for identity isolation, but BOTH production token
+// sources mint a FRESH JWT on every call (the in-app provider re-signs a JWT
+// whose iat/exp changes every second; the external MCP POSTs /auth/collab-token
+// per call). The fresh token per call made the session-registry key unstable,
+// so the prod hit-rate was 0% — connect storms, 25s timeouts, zombie sessions —
+// while every other test in this file stayed green because they pass a FIXED
+// "tok" string. The #439 fix is the per-client collab-token cache
+// (DocmostClient.getCollabTokenWithReauth + MCP_COLLAB_TOKEN_TTL_MS); these
+// tests drive the token through it with a source that returns a DIFFERENT
+// fresh JWT per mint, exactly like prod, so a regression in EITHER the token
+// cache or the registry keying turns them red.
+//
+// getCollabTokenWithReauth is TS-private, but the compiled JS exposes it; the
+// tests call it directly because that is exactly the per-op composition of the
+// production call sites (updatePage etc.: mint the token, then acquire).
+
+test("#439 token cache ON: fresh-JWT-per-mint source, two ops => ONE connect (session cache hits)", async () => {
+  process.env.MCP_COLLAB_TOKEN_TTL_MS = "300000"; // cache ON (explicit, not default-dependent)
+  let mints = 0;
+  const client = new DocmostClient({
+    apiUrl: "http://h/api",
+    getToken: async () => "user-jwt",
+    // Like both prod sources: a DIFFERENT fresh JWT on every mint.
+    getCollabToken: async () => `fresh-jwt-${++mints}`,
+  });
+
+  // Op 1: mint the collab token through the client, then acquire + mutate.
+  const tok1 = await client.getCollabTokenWithReauth();
+  const s1 = await acquireCollabSession("page-1", tok1, "http://h/api");
+  await s1.mutate(() => docWith("one"));
+
+  // Op 2: the same identity mints again — the cache must serve the SAME token.
+  const tok2 = await client.getCollabTokenWithReauth();
+  const s2 = await acquireCollabSession("page-1", tok2, "http://h/api");
+  await s2.mutate(() => docWith("two"));
+
+  assert.equal(mints, 1, "the second op is served from the token cache");
+  assert.equal(tok2, tok1, "stable token => stable session-registry key");
+  assert.equal(s2, s1, "the live session is reused");
+  assert.equal(
+    FakeProvider.connectCount,
+    1,
+    "two mutations over one identity must cost exactly ONE real connect",
+  );
+  assert.equal(__sessionCountForTests(), 1);
+});
+
+test("#439 negative control: token cache OFF (TTL=0) reproduces the #435 churn — two ops => TWO connects", async () => {
+  process.env.MCP_COLLAB_TOKEN_TTL_MS = "0"; // explicit 0 disables the cache (fetch-per-call legacy)
+  let mints = 0;
+  const client = new DocmostClient({
+    apiUrl: "http://h/api",
+    getToken: async () => "user-jwt",
+    getCollabToken: async () => `fresh-jwt-${++mints}`,
+  });
+
+  const tok1 = await client.getCollabTokenWithReauth();
+  const s1 = await acquireCollabSession("page-1", tok1, "http://h/api");
+  await s1.mutate(() => docWith("one"));
+
+  const tok2 = await client.getCollabTokenWithReauth();
+  const s2 = await acquireCollabSession("page-1", tok2, "http://h/api");
+  await s2.mutate(() => docWith("two"));
+
+  assert.equal(mints, 2, "without the cache every op mints its own token");
+  assert.notEqual(tok2, tok1, "unstable token => unstable session-registry key");
+  assert.notEqual(s2, s1, "no session reuse");
+  assert.equal(
+    FakeProvider.connectCount,
+    2,
+    "a full reconnect per op — the #435 storm in miniature",
+  );
+  // The first session lingers under its now-unreachable key until its idle
+  // TTL — the zombie-session symptom of the incident.
+  assert.equal(__sessionCountForTests(), 2);
+});
+
 test("destroyAllSessions tears down every cached session", async () => {
   await acquireCollabSession("page-1", "tok", "http://h/api");
   await acquireCollabSession("page-2", "tok", "http://h/api");

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

@@ -1,107 +0,0 @@
-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

@@ -16,7 +16,6 @@
  * `@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";
@@ -1482,20 +1481,7 @@ 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/index.ts

@@ -15,10 +15,7 @@ export {
 } from "./markdown-document.js";
 export type { DocmostMdMeta } from "./markdown-document.js";
 
-export {
-  convertProseMirrorToMarkdown,
-  ConverterLossError,
-} from "./markdown-converter.js";
+export { convertProseMirrorToMarkdown } from "./markdown-converter.js";
 export type { ConvertProseMirrorToMarkdownOptions } from "./markdown-converter.js";
 
 export {
@@ -26,19 +23,6 @@ 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.
@@ -92,17 +76,6 @@ 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

@@ -33,26 +33,6 @@ 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}.
  */
@@ -66,23 +46,6 @@ 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;
 }
 
 /**
@@ -100,70 +63,6 @@ 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";
@@ -210,26 +109,6 @@ 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
@@ -483,99 +362,6 @@ 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
@@ -626,17 +412,7 @@ export function convertProseMirrorToMarkdown(
       }
 
       case "paragraph": {
-        // 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 text = renderInlineChildren(nodeContent);
         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):
@@ -675,38 +451,154 @@ export function convertProseMirrorToMarkdown(
         return headingLine;
       }
 
-      case "text": {
+      case "text":
         let textContent = node.text || "";
-        // #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);
+        // #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, "^\\[");
         }
+        // Apply marks (bold, italic, code, etc.)
         if (node.marks) {
-          // #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.
+          // 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");
           if (hasCode) {
             textContent = `\`${textContent}\``;
+            return textContent;
           }
           for (const mark of node.marks) {
-            if (mark.type === "code") continue; // wrapped innermost above
-            textContent = applyInlineMark(textContent, mark);
+            switch (mark.type) {
+              case "bold":
+                textContent = `**${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;
+              }
+            }
           }
         }
         return textContent;
-      }
 
       case "codeBlock":
         const language = node.attrs?.language || "";
@@ -1281,11 +1173,7 @@ export function convertProseMirrorToMarkdown(
       }
 
       default:
-        // 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));
+        // Fallback: process children
         return nodeContent.map(processNode).join("");
     }
   };
@@ -1298,165 +1186,18 @@ 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 => {
-    // 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++;
-      }
-    }
-    // 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 `$…$` immediately followed by
-    // a digit-leading segment would re-tokenize as a longer math span, so emit
-    // that math node as HTML instead. A code-emphasis run never starts with a
-    // digit (it opens with a delimiter or `<`), so segment granularity is safe.
-    for (let k = 0; k < segs.length - 1; k++) {
+    const parts = nodes.map(processNode);
+    for (let i = 0; i < nodes.length - 1; i++) {
       if (
-        segs[k].firstNode?.type === "mathInline" &&
-        (segs[k].text || "").startsWith("$") &&
-        /^[0-9]/.test(segs[k + 1].text || "")
+        nodes[i]?.type === "mathInline" &&
+        parts[i].startsWith("$") &&
+        /^[0-9]/.test(parts[i + 1] || "")
       ) {
-        segs[k].text = mathInlineHtml(segs[k].firstNode.attrs?.text || "");
+        parts[i] = mathInlineHtml(nodes[i].attrs?.text || "");
       }
     }
-    return segs.map((s) => s.text).join("");
+    return parts.join("");
   };
 
   // Render inline content (text runs + their marks) to HTML. Used by the raw
@@ -1491,22 +1232,7 @@ 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>`;
@@ -1571,12 +1297,6 @@ 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

@@ -7,12 +7,13 @@
  * it is never applied to replacement text or inserted node content, so no
  * formatting is ever lost.
  *
- * 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.
+ * 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.
  */
 
 /** Maximum unwrap passes, so pathological/nested input cannot loop forever. */
@@ -43,7 +44,7 @@ const LINK_IMAGE_RE = /!?\[([^\]]*)\]\([^)]*\)/g;
  * Does NOT trim decoration, does NOT guard against an empty result — it returns
  * exactly the transformed string.
  */
-export function stripWrappersAndLinks(s: string): string {
+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

@@ -1,112 +0,0 @@
-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/generative/text-arbitraries.ts

@@ -11,11 +11,9 @@
  *
  * The corpus deliberately spans the CommonMark / canon hostile alphabet
  * (`* _ [ ] ( ) { } | < > & # ! ~ = + -`), unicode / emoji / RTL, and the legal
- * 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* ``).
+ * 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).
  */
 import fc from 'fast-check';
 
@@ -108,16 +106,16 @@ 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
- * `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.
+ * 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.
  *
- * 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).
+ * 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.
  */
 export const markedTextRunArb: fc.Arbitrary<any> = fc.oneof(
   // Plain text.
@@ -140,25 +138,6 @@ 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
@@ -233,93 +212,25 @@ 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. 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.)
+ * inline atoms (math/mention) and hard breaks interspersed. Always starts with a
+ * text run so the paragraph never opens with a block trigger. (Ported.)
  */
 export const inlineContentArb: fc.Arbitrary<any[]> = fc
   .tuple(
-    fc.oneof(
-      { weight: 5, arbitrary: markedTextRunArb },
-      { weight: 1, arbitrary: blockTriggerLeadRunArb },
-    ),
+    markedTextRunArb,
     fc.array(
       fc.oneof(
-        { 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 },
+        { weight: 5, arbitrary: markedTextRunArb },
+        { weight: 1, arbitrary: mathInlineArb },
+        { weight: 1, arbitrary: mentionArb },
+        { weight: 1, arbitrary: hardBreakArb },
       ),
       { minLength: 0, maxLength: 4 },
     ),
   )
-  .map(([first, rest]) => normalizeInline([first, ...rest.flat()]));
+  .map(([first, rest]) => normalizeInline([first, ...rest]));
 
 /**
  * Inline content for a HEADING — identical to a paragraph's, but WITHOUT hard

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

@@ -5,21 +5,32 @@ import { convertProseMirrorToMarkdown } from "../src/lib/markdown-converter.js";
 import { markdownToProseMirror } from "../src/lib/markdown-to-prosemirror.js";
 
 /**
- * #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.
+ * gitmost #377 (round-1 review, finding #1) — proof, against the REAL
+ * converter, that the transcript-insert boundary defense survives git-sync.
  *
- * 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).
+ * 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.
  */
 
+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",
@@ -32,117 +43,78 @@ const roundtrip = async (text: string) => {
   return back.content as any[];
 };
 
-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.
+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.
   const triggerLines = [
     "- dash",
     "* star",
     "+ plus",
     "> quote",
     "# hash",
-    "## two hash",
-    "###### six hash",
     "1. one",
     "1) one",
     "> [!info] note",
     "```js",
     "~~~",
-    "| a | b |",
-    // Solid + spaced thematic breaks — the text-LOSING case pre-fix.
+    // 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.
     "---",
     "***",
     "___",
-    "- - -",
+    "- - -", // spaced dash break (solid form is caught by [-*+]\s too, but this is the break)
     "_ _ _",
   ];
 
-  it("every bare trigger line round-trips as a single paragraph, text byte-preserved", async () => {
+  it("BARE trigger lines corrupt into non-paragraph blocks (root cause)", async () => {
     for (const line of triggerLines) {
       const blocks = await roundtrip(line);
-      expect(blocks, `"${line}" should be one block`).toHaveLength(1);
-      expect(blocks[0].type, `"${line}" should stay a paragraph`).toBe(
-        "paragraph",
-      );
+      // At least one produced block is NOT a paragraph — i.e. corruption.
+      const allParagraphs = blocks.every((b) => b.type === "paragraph");
       expect(
-        blocks[0].content?.[0]?.text,
-        `"${line}" text should survive byte-exact`,
-      ).toBe(line);
+        allParagraphs,
+        `expected "${line}" to corrupt when inserted bare`,
+      ).toBe(false);
     }
   });
 
-  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("\\"), `${mark} must not be block-escaped`).toBe(
-        false,
+  it("BARE solid thematic breaks corrupt into a text-LOSING horizontalRule", async () => {
+    // The severe case: no text node survives. Documents why neutralization
+    // matters more here than for list/quote (where the text survived).
+    for (const line of ["---", "***", "___"]) {
+      const blocks = await roundtrip(line);
+      expect(blocks.map((b) => b.type)).toContain("horizontalRule");
+      // No block carries the original text anywhere.
+      const flat = JSON.stringify(blocks);
+      expect(flat).not.toContain(line);
+    }
+  });
+
+  it("ZWSP-neutralized trigger lines round-trip as a single paragraph, text preserved", async () => {
+    for (const line of triggerLines) {
+      // The regex must actually classify each as a trigger.
+      expect(MD_BLOCK_TRIGGER_RE.test(line), `regex missed "${line}"`).toBe(
+        true,
       );
-      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);
+      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);
     }
   });
 
-  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 () => {
+  it("normal host-prefixed lines never match the trigger regex and round-trip byte-exact", 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

@@ -294,11 +294,10 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
     );
   });
 
-  // 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)', () => {
+  // 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)', () => {
     const out = convertProseMirrorToMarkdown(
       doc(
         para({
@@ -311,7 +310,7 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
         }),
       ),
     );
-    expect(out).toBe('[`x`](http://a?b&c"d)');
+    expect(out).toBe('`x`');
   });
 
   // 6. hardBreak inside a heading: prefix applied once, "  \n" between a and b.
@@ -431,7 +430,7 @@ describe('converter gap coverage — emission branches (specs 1–11)', () => {
   });
 });
 
-describe('converter gap coverage — formerly-lossy round-trips, now closed (specs 12–14)', () => {
+describe('converter gap coverage — documented round-trip data loss (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.
@@ -461,24 +460,25 @@ describe('converter gap coverage — formerly-lossy round-trips, now closed (spe
     expect(docsCanonicallyEqual(d, doc2)).toBe(false);
   });
 
-  // 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 () => {
+  // 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 () => {
     const d = doc({
       type: 'paragraph',
       content: [{ type: 'text', text: '1. not a list' }],
     });
     const md1 = convertProseMirrorToMarkdown(d);
-    expect(md1).toBe('1\\. not a list'); // the ordered-list delimiter is escaped
+    expect(md1).toBe('1. not a list'); // no backslash escape
 
     const doc2 = await markdownToProseMirror(md1);
-    expect(doc2.content?.[0]?.type).toBe('paragraph');
-    expect(doc2.content[0].content?.[0]).toMatchObject({
+    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({
       type: 'text',
-      text: '1. not a list', // the escape decodes back to the literal text
+      text: 'not a list', // the "1. " was consumed as a list marker
     });
-    expect(docsCanonicallyEqual(d, doc2)).toBe(true);
+    expect(docsCanonicallyEqual(d, doc2)).toBe(false);
   });
 
   // 14. #293 canon #4: the image title now round-trips via the attached

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

@@ -59,21 +59,22 @@ describe('convertProseMirrorToMarkdown', () => {
       ).toBe('`x`');
     });
 
-    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.
+    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.
       const out = convertProseMirrorToMarkdown(
         doc(para(text('x', [{ type: 'bold' }, { type: 'code' }]))),
       );
-      expect(out).toBe('**`x`**');
+      expect(out).toBe('`x`');
     });
 
-    it('code + strike nests the backtick span inside the emphasis (#515)', () => {
+    it('code + strike combo emits the backtick code form (code wins)', () => {
       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

@@ -80,7 +80,13 @@ 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. A BLOCK-level `image` placed BETWEEN other blocks. The Docmost image node
+//   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
 //      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
@@ -619,7 +625,7 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
   });
 
   // -------------------------------------------------------------------------
-  // KNOWN, DOCUMENTED non-roundtrip bug #1 (kept honest as it.fails).
+  // KNOWN, DOCUMENTED non-roundtrip bug #2 (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
@@ -649,18 +655,23 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
   });
 
   // -------------------------------------------------------------------------
-  // #515 ROUND-TRIP PIN: `code` combined with another mark.
+  // KNOWN, DOCUMENTED non-roundtrip bug #1 (kept honest as it.fails).
   //
-  // 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].
+  // 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.
   // -------------------------------------------------------------------------
   it(
-    'code combined with another mark round-trips and keeps both marks (#515)',
+    'code mark combined with another mark is byte-stable',
     async () => {
       const codeComboArb = fc
         .tuple(safeTextArb, fc.constantFrom('bold', 'italic', 'strike'))
@@ -677,90 +688,11 @@ describe('markdown <-> ProseMirror round-trip (property-based)', () => {
         }));
       await fc.assert(
         fc.asyncProperty(codeComboArb, async (doc) => {
-          const { md1, md2, doc2 } = await roundTrip(doc);
+          const { md1, md2 } = 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

@@ -16,16 +16,14 @@ 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).
 //
-// 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,
+// 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,
 // 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.
 //
@@ -87,224 +85,3 @@ 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

@@ -9,18 +9,11 @@ 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: {

scripts/ci/image-smoke.sh

@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+# Boot-smoke for the exact Docker image that is about to be pushed (issue #476).
+#
+# Retrospective class "local logic is right, the integration property was never
+# checked" (#353/#452/#361): every other CI job builds and tests code from the
+# working tree, but the IMAGE watchtower pulls was never actually started
+# anywhere before this gate. This script boots the built image against the
+# publish job's postgres/redis services and asserts four integration
+# properties end-to-end:
+#   S1  the app boots and /api/health answers (startup migrator + boot)
+#   S2  the first-run workspace setup endpoint works (API + DB writes)
+#   S3  the client dist is inside the image and served
+#   S4  hashed assets are served immutable (#452) with the precompressed
+#       brotli copy shipped in the image
+set -euo pipefail
+
+IMAGE="${1:?usage: image-smoke.sh <image>}"
+
+fail() { echo "FAIL: $*"; exit 1; }
+
+# Boot the exact image that will be pushed, wired to the job services via host
+# network (postgres on localhost:5432, redis on localhost:6379). The container
+# is deliberately NOT removed on failure so the workflow's dump-on-failure step
+# can read `docker logs gitmost-smoke`.
+docker run -d --name gitmost-smoke --network host \
+  -e DATABASE_URL=postgresql://docmost:docmost@localhost:5432/docmost \
+  -e REDIS_URL=redis://localhost:6379 \
+  -e APP_SECRET=ci-smoke-secret-change-me-min-32-characters \
+  -e APP_URL=http://localhost:3000 \
+  "$IMAGE"
+
+# S1: wait for /api/health — covers the startup migrator + boot inside the
+# shipped image (#361-boot, #353 runtime class): a migration the Kysely startup
+# migrator rejects, or a runtime module missing from the image, dies right here.
+healthy=0
+for _ in $(seq 1 60); do
+  if curl -fsS http://localhost:3000/api/health > /dev/null 2>&1; then
+    healthy=1
+    break
+  fi
+  sleep 2
+done
+[ "$healthy" -eq 1 ] || fail "S1: /api/health did not answer within 120s (boot or startup migration failed)"
+echo "OK S1: image booted and /api/health answers"
+
+# S2: the first-run workspace setup works end-to-end (controller -> service ->
+# DB write chain inside the shipped image, not just a static health probe).
+curl -fsS -X POST http://localhost:3000/api/auth/setup \
+  -H "Content-Type: application/json" \
+  -d '{"name":"Smoke","email":"smoke@example.com","password":"SmokePassword123","workspaceName":"Smoke"}' \
+  > /dev/null || fail "S2: POST /api/auth/setup failed"
+echo "OK S2: workspace setup succeeded"
+
+# S3: the client dist is actually inside the image and served — the SPA HTML
+# must reference hashed /assets/ bundles (a broken client COPY in the
+# Dockerfile would serve an empty shell that every other job stays green on).
+HTML=$(curl -fsS http://localhost:3000/) || fail "S3: fetching / failed"
+grep -q '/assets/' <<<"$HTML" || fail "S3: served HTML references no /assets/ bundle (client dist missing from the image?)"
+echo "OK S3: client dist served (HTML references /assets/)"
+
+# S4: hashed /assets/ files must be served with an immutable cache-control
+# (#452 class: static.module.ts resolveStaticAssetHeaders owns the header) AND
+# with the precompressed brotli neighbour. Both checks are mandatory — verified
+# against the code: resolveStaticAssetHeaders marks every /assets/ path
+# immutable, and the client build (vite-plugin-compression2, include covers
+# .js) emits a .br copy next to every bundle that the Dockerfile ships and
+# @fastify/static serves via preCompressed:true.
+ASSET=$(grep -oE '/assets/[A-Za-z0-9._@/-]+\.js' <<<"$HTML" | head -1 || true)
+[ -n "$ASSET" ] || fail "S4: no /assets/*.js path found in the served HTML"
+HDRS=$(curl -fsSI -H 'Accept-Encoding: br' "http://localhost:3000$ASSET") || fail "S4: HEAD $ASSET failed"
+grep -qi '^cache-control:.*immutable' <<<"$HDRS" || fail "S4: $ASSET served without an immutable cache-control (#452)"
+echo "OK S4: hashed asset served with immutable cache-control"
+grep -qi '^content-encoding:.*br' <<<"$HDRS" || fail "S4: $ASSET not served brotli-precompressed (content-encoding: br missing)"
+echo "OK S4: hashed asset served with the precompressed brotli copy"
+
+# Remove the container ONLY on success, so the failure path keeps it around for
+# the workflow's "Dump smoke container log on failure" step.
+docker rm -f gitmost-smoke > /dev/null
+echo "OK image smoke passed"