docs: отразить ключ error в заглавной секции reading-ai-logs (устранить противоречие)

Ревью #426: секция «How tool calls are stored — READ THIS» всё ещё утверждала,
что единственные ключи элемента — toolName/input/output и «нет error», хотя этот
же PR добавляет error и подробно описывает его ниже. Заглавный абзац приведён в
соответствие: error — возможный ключ для брошенных ошибок на строках после #407;
подсчёт инвокаций и пайринг учитывают error как парный результат.

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

apps/server/src/core/ai-chat/ai-chat.service.spec.ts

@@ -148,6 +148,53 @@ describe('assistantParts', () => {
     expect(toolPart).not.toHaveProperty('output');
   });
 
+  it('replays the REAL error text for a THROWN tool (tool-error part)', () => {
+    const steps = [
+      {
+        text: '',
+        toolCalls: [
+          { toolCallId: 'c7', toolName: 'editPageText', input: { id: 'p1' } },
+        ],
+        // A thrown tool is a `tool-error` content part; toolResults holds only
+        // successes and stays empty for this call.
+        toolResults: [],
+        content: [
+          {
+            type: 'tool-error',
+            toolCallId: 'c7',
+            toolName: 'editPageText',
+            input: { id: 'p1' },
+            error: new Error('page is locked'),
+          },
+        ],
+      },
+    ];
+    const parts = assistantParts(steps, '') as AnyPart[];
+    const toolPart = parts.find((p) => p.type === 'tool-editPageText');
+    expect(toolPart).toBeDefined();
+    expect(toolPart!.state).toBe('output-error');
+    // The REAL error is replayed, NOT the 'Tool call did not complete.' placeholder.
+    expect(toolPart!.errorText).toBe('page is locked');
+    expect(toolPart).not.toHaveProperty('output');
+  });
+
+  it('keeps the placeholder ONLY for a call with neither result nor tool-error', () => {
+    const steps = [
+      {
+        text: '',
+        toolCalls: [
+          { toolCallId: 'c8', toolName: 'insertNode', input: { node: {} } },
+        ],
+        toolResults: [],
+        content: [], // aborted mid-step: no result AND no tool-error
+      },
+    ];
+    const parts = assistantParts(steps, '') as AnyPart[];
+    const toolPart = parts.find((p) => p.type === 'tool-insertNode');
+    expect(toolPart!.state).toBe('output-error');
+    expect(toolPart!.errorText).toBe('Tool call did not complete.');
+  });
+
   it('skips malformed tool-calls (missing toolName or toolCallId)', () => {
     const steps = [
       {
@@ -195,6 +242,45 @@ describe('serializeSteps', () => {
     expect(trace[0]).toEqual({ toolName: 'getPage', input: { id: 'p1' } });
     expect(trace[1]).toEqual({ toolName: 'getPage', output: { title: 'T' } });
   });
+
+  it('records a THROWN tool failure (tool-error part) with its error message', () => {
+    const trace = serializeSteps([
+      {
+        toolCalls: [{ toolName: 'editPageText', input: { id: 'p1' } }],
+        toolResults: [],
+        content: [
+          {
+            type: 'tool-error',
+            toolName: 'editPageText',
+            error: new Error('page is locked'),
+          },
+        ],
+      },
+    ]) as Array<Record<string, unknown>>;
+    // The call element is followed by a paired error element (mirroring how a
+    // successful result is appended), so the failure survives in the trace.
+    expect(trace).toHaveLength(2);
+    expect(trace[0]).toEqual({ toolName: 'editPageText', input: { id: 'p1' } });
+    expect(trace[1]).toEqual({
+      toolName: 'editPageText',
+      error: 'page is locked',
+    });
+  });
+
+  it('truncates a very long tool-error message to the tool-output limit', () => {
+    const long = 'x'.repeat(5000);
+    const trace = serializeSteps([
+      {
+        toolCalls: [{ toolName: 'editPageText', input: {} }],
+        toolResults: [],
+        content: [{ type: 'tool-error', toolName: 'editPageText', error: long }],
+      },
+    ]) as Array<Record<string, unknown>>;
+    const errorText = trace[1].error as string;
+    // Truncated (not the full 5000 chars) and carries the omission marker.
+    expect(errorText.length).toBeLessThan(long.length);
+    expect(errorText).toContain('chars omitted');
+  });
 });
 
 describe('rowToUiMessage', () => {

apps/server/src/core/ai-chat/ai-chat.service.ts

@@ -1637,6 +1637,17 @@ type StepLike = {
     toolName?: string;
     output?: unknown;
   }>;
+  // ai@6.0.134: a tool that THREW surfaces as a `tool-error` content part
+  // ({ type:'tool-error', toolCallId, toolName, input, error }), NOT as a
+  // `toolResults` entry (which holds only successes). Read from here so failed
+  // calls are persisted with their real error instead of being dropped.
+  content?: ReadonlyArray<{
+    type?: string;
+    toolCallId?: string;
+    toolName?: string;
+    input?: unknown;
+    error?: unknown;
+  }>;
 };
 
 /**
@@ -1739,6 +1750,26 @@ function compactValue(value: unknown, depth: number): unknown {
   return value;
 }
 
+/**
+ * Extract a bounded string message from a `tool-error` part's `error` field for
+ * persistence and history replay. The field may be an `Error`, a string, or an
+ * arbitrary object, so pull a message robustly. The result is passed through
+ * `compactValue` so a very long error honors the SAME truncation limits the file
+ * already applies to tool outputs (no new limit is introduced here).
+ */
+function normalizeToolError(error: unknown): string {
+  const message =
+    error instanceof Error
+      ? error.message
+      : typeof error === 'string'
+        ? error
+        : error != null &&
+            typeof (error as { message?: unknown }).message === 'string'
+          ? (error as { message: string }).message
+          : String(error);
+  return compactValue(message, 0) as string;
+}
+
 /**
  * Rebuild the FULL UIMessage `parts` for an assistant turn from the SDK steps,
  * so multi-turn history replays prior tool-calls/results to the model (not just
@@ -1771,6 +1802,14 @@ export function assistantParts(
     for (const r of step.toolResults ?? []) {
       if (r.toolCallId) resultsById.set(r.toolCallId, r.output);
     }
+    // Index this step's THROWN tool failures (ai@6 `tool-error` content parts)
+    // by tool call id, so a call that failed replays with its real error text.
+    const errorsById = new Map<string, unknown>();
+    for (const part of step.content ?? []) {
+      if (part.type === 'tool-error' && part.toolCallId) {
+        errorsById.set(part.toolCallId, part.error);
+      }
+    }
     for (const call of step.toolCalls ?? []) {
       if (!call.toolName || !call.toolCallId) continue;
       const hasResult = resultsById.has(call.toolCallId);
@@ -1783,9 +1822,21 @@ export function assistantParts(
           input: call.input,
           output: compactToolOutput(resultsById.get(call.toolCallId)),
         });
+      } else if (errorsById.has(call.toolCallId)) {
+        // The tool THREW: replay the REAL error so the model on the next turn
+        // knows WHY the call failed (and does not blindly repeat it). An
+        // output-error round-trips through convertToModelMessages as a balanced
+        // tool-call + tool-result, keeping the rebuilt history valid.
+        parts.push({
+          type: `tool-${call.toolName}`,
+          toolCallId: call.toolCallId,
+          state: 'output-error',
+          input: call.input,
+          errorText: normalizeToolError(errorsById.get(call.toolCallId)),
+        });
       } else {
-        // No paired result (e.g. aborted mid-step). Persisting a bare
+        // No paired result AND no tool-error (e.g. aborted mid-step). Persisting
-        // tool-call (input-available) would replay as an unpaired call and
+        // a bare tool-call (input-available) would replay as an unpaired call and
         // throw MissingToolResultsError on the next turn (convertToModelMessages
         // emits no tool-result for it). Emit a SYNTHETIC paired result instead:
         // an output-error round-trips through convertToModelMessages as a
@@ -2021,10 +2072,19 @@ export function serializeSteps(
   steps: ReadonlyArray<{
     toolCalls?: ReadonlyArray<{ toolName?: string; input?: unknown }>;
     toolResults?: ReadonlyArray<{ toolName?: string; output?: unknown }>;
+    content?: ReadonlyArray<{
+      type?: string;
+      toolName?: string;
+      error?: unknown;
+    }>;
   }>,
 ): unknown {
-  const calls: Array<{ toolName?: string; input?: unknown; output?: unknown }> =
+  const calls: Array<{
-    [];
+    toolName?: string;
+    input?: unknown;
+    output?: unknown;
+    error?: string;
+  }> = [];
   for (const step of steps ?? []) {
     for (const call of step.toolCalls ?? []) {
       calls.push({ toolName: call.toolName, input: call.input });
@@ -2032,6 +2092,18 @@ export function serializeSteps(
     for (const r of step.toolResults ?? []) {
       calls.push({ toolName: r.toolName, output: compactToolOutput(r.output) });
     }
+    // ai@6 surfaces a THROWN tool failure as a `tool-error` content part, NOT as
+    // a `toolResults` entry. Record it as its own paired element (mirroring how a
+    // successful result is appended) so the failure and its reason survive in the
+    // trace instead of leaving an orphaned call with no result.
+    for (const part of step.content ?? []) {
+      if (part.type === 'tool-error') {
+        calls.push({
+          toolName: part.toolName,
+          error: normalizeToolError(part.error),
+        });
+      }
+    }
   }
   return calls.length > 0 ? calls : null;
 }

apps/server/src/core/ai-chat/tools/ai-chat-tools.service.ts

@@ -17,7 +17,7 @@ import {
   resolveCurrentPageResult,
   type SelectionContext,
 } from './current-page.util';
-import { parseNodeArg } from '@docmost/prosemirror-markdown';
+import { parseNodeArg } from './parse-node-arg';
 import { modelFriendlyInput } from './model-friendly-input';
 import { SandboxStore } from '../../../integrations/sandbox/sandbox.store';
 import {

apps/server/src/core/ai-chat/tools/parse-node-arg.spec.ts

@@ -1,10 +1,10 @@
-import { parseNodeArg } from '@docmost/prosemirror-markdown';
+import { parseNodeArg } from './parse-node-arg';
 
 /**
- * Unit tests for the shared `parseNodeArg` helper (#414: now the single copy in
+ * Unit tests for the in-app `parseNodeArg` helper. It mirrors the standalone
- * `@docmost/prosemirror-markdown`, imported by both the server tool adapters and
+ * MCP helper (packages/mcp/src/lib/parse-node-arg.ts) and is used by the
- * `@docmost/mcp`). Used by the patchNode / insertNode / updatePageJson adapters.
+ * patchNode / insertNode / updatePageJson tool adapters. Behavior must be
- * Behavior: object passthrough, valid-string parse, invalid-string throw.
+ * byte-identical: object passthrough, valid-string parse, invalid-string throw.
  */
 describe('parseNodeArg', () => {
   it('passes an object through unchanged', () => {

apps/server/src/core/ai-chat/tools/parse-node-arg.ts

@@ -0,0 +1,26 @@
+// The model sometimes serializes a ProseMirror node arg as a JSON string
+// instead of an object. Normalize: parse a string to an object (throwing on
+// invalid JSON), pass an object through unchanged. Shared by patchNode /
+// insertNode (and the analogous updatePageJson content parsing).
+//
+// This is behaviorally identical to `packages/mcp/src/lib/parse-node-arg.ts`
+// (the function logic, default/explicit throw messages and branch order match;
+// only comments and quote style differ). We cannot import that helper here:
+// `@docmost/mcp` is ESM-only and this server
+// compiles with module:commonjs, so it is loaded at runtime via the
+// `new Function('import()')` trick (see docmost-client.loader.ts). Sharing
+// runtime code across that ESM/CJS boundary by a normal import is impossible,
+// hence the mirrored copy.
+export function parseNodeArg(
+  node: unknown,
+  errMsg = 'node was a string but not valid JSON',
+): unknown {
+  if (typeof node === 'string') {
+    try {
+      return JSON.parse(node);
+    } catch {
+      throw new Error(errMsg);
+    }
+  }
+  return node;
+}

docs/reading-ai-logs.md

@@ -13,12 +13,14 @@ Read the **Gotchas** section before you trust any error count.
 - Agent chats live in Postgres, DB `docmost`, tables `ai_chat_*`.
 - Each tool invocation is stored as **two** array elements (a `tool-call` part and
   a `tool-result` part), so naive counting double-counts.
-- **A tool that *throws* writes no result part at all.** Its error text is nowhere
+- **A tool that *throws* writes no result part.** Since the #407 fix its error is
-  in the DB — not in `tool_calls`, `content`, or `metadata`. It is shown live in
+  persisted as a dedicated `{toolName, error}` element in `tool_calls` (queryable +
-  the UI only. So `isError` / `success=false` scans under-report by design.
+  replayed to the model). **Rows written before #407 still drop it** — the error is
-- To find where agents fail you need **three** sources: (1) soft-failure markers in
+  nowhere in the DB and shows only in the live UI. So `isError` / `success=false`
-  `tool_calls`, (2) the orphan-gap proxy for thrown errors, (3) server logs / the
+  scans under-report by design, and pre-#407 thrown errors are invisible.
-  live UI for the actual error text.
+- To find where agents fail: (1) soft-failure markers in `tool_calls`, (2) the new
+  `error` field for thrown errors (new rows) / the orphan-gap proxy (old rows),
+  (3) server logs / the live UI for full stack traces beyond the truncated message.
 
 ## Where the data lives
 
@@ -61,13 +63,17 @@ index 0: { "toolName": "getPage",  "input":  { "pageId": "…" } }   ← tool-ca
 index 1: { "toolName": "getPage",  "output": { … } }                ← tool-result (has output, NO input)
 ```
 
-The **only** keys that ever appear on an element are `toolName`, `input`, `output`.
+The keys that appear on an element are `toolName`, `input`, `output`, and — for a
-There is no `state`, no `errorText`, no `type`. Consequences:
+**thrown** failure on rows written after the #407 fix — `error` (the tool's error
+message; see the "Hard failures" section below). There is no `state`, no `errorText`,
+no `type`. On pre-#407 rows a thrown failure has NO paired result element at all
+(silent orphan). Consequences:
 
-1. **Real invocation count = elements that have `output`.** Counting every element
+1. **Real invocation count = elements that have `output` or `error`.** Counting every
-   double-counts (you get ~2× and a spurious "~50% of every tool has no output").
+   element double-counts (you get ~2× and a spurious "~50% of every tool has no output").
-2. **Pairing:** a successful call = a `tool-call` part followed by its `tool-result`
+2. **Pairing:** a call = a `tool-call` part followed by its result part. A success
-   part. Both carry `toolName`, so you can group by tool on either.
+   carries `output`; a thrown failure (post-#407) carries `error` instead. Both carry
+   `toolName`, so you can group by tool on either.
 
 ## The two classes of failure (and which the DB can see)
 
@@ -85,25 +91,37 @@ These are visible in the `tool-result` `output`. The marker differs per tool:
 Note `editPageText` returns `failed: []` on success — filtering on the *presence*
 of the key gives false positives; filter on **non-empty**.
 
-### 2. Hard failures — tool THREW → NOT PERSISTED ❌ (the trap)
+### 2. Hard failures — tool THREW → NOW PERSISTED ✅ (since the #407 fix)
 
 When a tool throws (the classic one is `patchNode` / `insertNode` / `tableUpdateCell`
 → `Failed to encode document to Yjs (fromJSON): Unknown node type: undefined`), the
-runtime writes **no `tool-result` part**. The orphaned `tool-call` part stays, but
+runtime still writes **no `tool-result` part** — the failure is an ai@6 `tool-error`
-the error text is **nowhere in the DB**. It is streamed to the UI live and (until
+content part instead. **Since the #407 fix, that error is persisted**: `serializeSteps`
-rotation) to server logs — that is it.
+appends a dedicated element `{toolName, error: "<message>"}` right after the failed
+call, mirroring how a successful `{toolName, output}` element is appended. So a thrown
+error now leaves a queryable `error` field carrying its (truncated) reason, and the
+same real text is replayed to the model on the next turn (an `output-error` part with
+the real `errorText`, no longer the `'Tool call did not complete.'` placeholder).
 
-So any query like `count(*) FILTER (WHERE output.success = false)` will happily
+**Cutover caveat — old rows keep the old blind shape.** Rows written **before** this
-return **0** for `patchNode` even when the chat is visibly full of red failures.
+change have the two-part shape (`call` + `output` only) and simply **drop** thrown
-That is survivorship bias, not reliability.
+errors, leaving a silent **orphan** (a `call` with no `output` *and* no `error`). Rows
+written **after** the fix additionally carry the `error` element. So:
 
-The only DB-side proxy for a thrown error is an **orphan**: a `tool-call` part with
+- **New rows:** query the `error` field directly (see the hard-error query below) — no
-no matching `tool-result`. Caveat: orphans also appear when a run is **aborted**
+  orphan heuristic needed for thrown failures.
-mid-flight (server restart), so a high-volume tool (`createComment`, `searchInPage`,
+- **Old rows (pre-#407):** the only DB-side proxy is still an **orphan**: a `tool-call`
-`Search_web_search`) shows orphans from aborts, not from real errors. Treat the
+  part with no matching `tool-result` *and* no `error`. Orphans also appear when a run
-orphan gap as an *upper bound* on hard errors, and cross-check the tool: a gap on a
+  is **aborted** mid-flight (server restart), so a high-volume tool (`createComment`,
-structural editor (`patchNode`, `insertNode`, `updatePageJson`, `transformPage`) is
+  `searchInPage`, `Search_web_search`) shows orphans from aborts, not real errors on
-almost certainly a thrown Yjs-encode error; a gap on `createComment` is mostly aborts.
+  old rows. Treat the orphan gap as an *upper bound*, and cross-check the tool: a gap on
+  a structural editor (`patchNode`, `insertNode`, `updatePageJson`, `transformPage`) is
+  almost certainly a thrown Yjs-encode error; a gap on `createComment` is mostly aborts.
+
+A note on the aborted-call fallback: a call with **neither** a result **nor** a
+`tool-error` (genuinely interrupted mid-step) still replays with the
+`'Tool call did not complete.'` placeholder and persists as an orphan — that path is
+unchanged, and is distinct from a real thrown error, which now carries `error`.
 
 ### 3. Run-level failures → `ai_chat_runs`
 
@@ -164,14 +182,28 @@ WHERE jsonb_typeof(o->'failed') = 'array'
 GROUP BY 1 ORDER BY 2 DESC;
 ```
 
-**Hard-error proxy — orphan gap per tool, WITH a spread column** (call parts minus
+**Hard errors — persisted `error` field per tool (NEW rows, since #407)** — thrown
-result parts, plus how many distinct chats the gap is spread across):
+tool failures now carry their real reason, so query them directly:
+
+```sql
+SELECT elem->>'toolName' AS tool, count(*) AS thrown_errors,
+       min(elem->>'error') AS sample_error
+FROM ai_chat_messages m, jsonb_array_elements(m.tool_calls) elem
+WHERE jsonb_typeof(m.tool_calls) = 'array' AND elem ? 'error'
+GROUP BY 1 ORDER BY 2 DESC;
+```
+
+**Hard-error proxy for OLD rows (pre-#407) — orphan gap per tool, WITH a spread column**
+(call parts minus result parts, plus how many distinct chats the gap is spread across).
+This covers rows written before thrown errors were persisted; on new rows a thrown
+failure now has its own `error` element (use the query above) and an orphan means only
+a genuinely aborted mid-step call:
 
 ```sql
 WITH parts AS (
   SELECT m.chat_id, elem->>'toolName' AS tool,
          (elem ? 'input' AND NOT (elem ? 'output')) AS is_call,
-         (elem ? 'output')                          AS is_result
+         (elem ? 'output' OR elem ? 'error')        AS is_result
   FROM ai_chat_messages m, jsonb_array_elements(m.tool_calls) elem
   WHERE jsonb_typeof(m.tool_calls) = 'array' AND m.role = 'assistant'
 ),
@@ -188,8 +220,12 @@ HAVING sum(gap) FILTER (WHERE gap > 0) > 0
 ORDER BY missing_results DESC;
 ```
 
-**`missing_results` mixes thrown errors AND aborted/interrupted runs — you cannot
+The `is_result` predicate counts an `error` element as a paired result too, so on new
-split them from `output` alone** (a positional "what follows the orphan" heuristic
+rows a persisted thrown error no longer inflates the orphan gap; a remaining gap is an
+aborted/interrupted call.
+
+**On OLD rows, `missing_results` mixes thrown errors AND aborted/interrupted runs — you
+cannot split them from `output` alone** (a positional "what follows the orphan" heuristic
 breaks on parallel tool batches, which persist as `call,call,…,result,result`). Use
 `chats_spread` to disambiguate:
 
@@ -244,18 +280,20 @@ docker compose -p gitmost logs -f --tail=100 # whole stack
 ```
 
 Logging is `json-file`, `max-size=10m max-file=5` → ~50 MB retained, then rotated,
-and **wiped on container recreate**. So thrown-tool error text is only reliably
+and **wiped on container recreate**. Since the #407 fix, thrown-tool error text is
-caught **in real time** (or in the live chat UI, which renders the failed part with
+**persisted in the `error` field** of `tool_calls` (see the hard-error query above), so
-its message). There is no durable, queryable store of hard tool errors today — if you
+you no longer depend on live logs for it. Logs/live UI remain useful for **pre-#407
-need one, that is a feature to add (persist `output-error` parts, or emit a
+rows** (whose thrown errors were dropped) and for full stack traces beyond the
-`tool_calls_total{tool,status}` metric to VictoriaMetrics).
+truncated stored message. A per-tool `tool_calls_total{tool,status}` metric to
+VictoriaMetrics is still a possible future add for aggregate dashboards.
 
 ## Gotchas checklist
 
-- [ ] Counting every `tool_calls` element → **2× overcount**. Count elements with `output`.
+- [ ] Counting every `tool_calls` element → **overcount**. Count `output` elements; add `error` elements for thrown failures (new rows), but don't count both as invocations.
-- [ ] `isError` / `success=false` ≈ 0 does **not** mean "no errors" — thrown errors aren't persisted.
+- [ ] `isError` / `success=false` ≈ 0 does **not** mean "no errors" — thrown errors are a separate `error` element (new rows) or dropped entirely (pre-#407 rows).
+- [ ] Thrown errors persist only on rows written **after the #407 fix** — pre-#407 rows still drop them (orphan only). Mind the cutover when trending over time.
 - [ ] `editPageText.failed` is `[]` on success — test for **non-empty**, not presence.
-- [ ] Orphan gap mixes thrown errors **and** aborted runs — split by tool before concluding.
+- [ ] Orphan gap on OLD rows mixes thrown errors **and** aborted runs — split by tool. On NEW rows a thrown error is its own `error` element, so a gap ≈ aborted call.
 - [ ] `aborted` runs = server restarts, `failed` runs = provider overload — not agent mistakes.
 - [ ] Never dump a raw `tool_calls` cell — it can be hundreds of KB.
 - [ ] Logs are ephemeral (≤50 MB, wiped on recreate) — grab hard-error text live.

packages/mcp/src/client.ts

@@ -46,7 +46,7 @@ import {
   insertTableRow,
   deleteTableRow,
   updateTableCell,
-} from "@docmost/prosemirror-markdown";
+} from "./lib/node-ops.js";
 import { searchInDoc, SearchOptions } from "./lib/page-search.js";
 import { withPageLock } from "./lib/page-lock.js";
 import {

packages/mcp/src/index.ts

@@ -4,7 +4,7 @@ import { readFileSync } from "fs";
 import { fileURLToPath } from "url";
 import { dirname, join } from "path";
 import { DocmostClient, DocmostMcpConfig } from "./client.js";
-import { parseNodeArg } from "@docmost/prosemirror-markdown";
+import { parseNodeArg } from "./lib/parse-node-arg.js";
 import { SHARED_TOOL_SPECS, SharedToolSpec } from "./tool-specs.js";
 
 // Re-export the client and its config type so embedding hosts (e.g. the gitmost

packages/mcp/src/lib/collaboration.ts

@@ -14,7 +14,7 @@ import { JSDOM } from "jsdom";
 import { markdownToProseMirror } from "@docmost/prosemirror-markdown";
 import { docmostExtensions, docmostSchema } from "./docmost-schema.js";
 import { withPageLock } from "./page-lock.js";
-import { sanitizeForYjs, findUnstorableAttr } from "@docmost/prosemirror-markdown";
+import { sanitizeForYjs, findUnstorableAttr } from "./node-ops.js";
 import { canonicalizeFootnotes } from "./footnote-canonicalize.js";
 import { summarizeChange, VerifyReport } from "./diff.js";
 

packages/mcp/src/lib/footnote-analyze.ts

@@ -1,62 +1,136 @@
 /**
- * Legacy footnote advisory for imported Markdown (issue #166, reduced in #414).
+ * Legacy footnote diagnostics for imported Markdown (issue #166).
  *
- * Since #293 STEP 5 the canonical import form is inline `^[body]` footnotes
+ * A PURE, fence-aware text scan (independent of the Markdown->ProseMirror
- * (handled by `@docmost/prosemirror-markdown`). LEGACY reference-style
+ * conversion path, so it reports the same problems for `create_page`,
- * `[^id]: …` definition markup is now INERT on import — the importer leaves it as
+ * `update_page` and `import_page_markdown`). It never changes the document — the
- * literal text — so authoring it silently produces broken footnotes (the #410
+ * importer still creates the page; this only surfaces footnote problems to the
- * incident class). Rather than the old, elaborate diagnostics of every problem
+ * caller so an agent can fix its own markup instead of shipping broken footnotes.
- * SHAPE (dangling/duplicate/empty/in-table) that no longer describe what the
- * importer builds, this module surfaces ONE advisory warning whenever legacy
- * reference-style definition syntax is present, nudging the author to the inline
- * form. It never changes the document — the importer still creates the page.
  *
- * The scan is fence-aware: a `[^id]:` line inside a ``` / ~~~ code block is
+ * SCOPE after #293 STEP 5: the canonical import form is now inline `^[body]`
- * example text, not markup, so it never triggers the warning.
+ * footnotes (handled by `@docmost/prosemirror-markdown`), where these problems
+ * cannot arise. This scan therefore targets the LEGACY reference-style
+ * (`[^id]` / `[^id]:`) markup, which is now inert on import (left as literal
+ * text). The warnings remain useful as an advisory nudge when an agent still
+ * authors the old syntax, but they no longer describe what the importer builds.
+ *
+ * Detected problems:
+ *  - danglingReferences: a `[^id]` reference with no `[^id]:` definition.
+ *  - emptyDefinitions:   a `[^id]:` whose (kept) text is empty/whitespace.
+ *  - duplicateDefinitions: an id defined by two or more `[^id]:` lines (only the
+ *    first would have been kept under the old first-wins import).
+ *  - referencesInTables: a `[^id]` marker found in a GFM table row (heuristic:
+ *    the line, trimmed, starts with `|`) — footnotes in table cells often do not
+ *    render as expected.
  */
 
-/** A legacy footnote DEFINITION line: `[^id]:` at the start of a (non-fenced) line. */
+import {
-const FOOTNOTE_DEF_RE = /^\[\^[^\]\s]+\]:/;
+  lexFootnoteLines,
-/** Opening/closing code fence marker (``` or ~~~). */
+  forEachFootnoteReference,
-const FENCE_RE = /^\s*(`{3,}|~{3,})/;
+} from "./footnote-lex.js";
 
-/** The single advisory shown when legacy reference-style footnotes are present. */
+export interface FootnoteDiagnostics {
-export const LEGACY_FOOTNOTE_WARNING =
+  /** Reference ids (distinct, document order) with no matching definition. */
-  "Reference-style footnotes (`[^id]: …`) are not parsed on import and will " +
+  danglingReferences: string[];
-  "appear as literal text. Use inline footnotes instead: `^[footnote text]`.";
+  /** Definition ids whose first (kept) text is empty/whitespace. */
+  emptyDefinitions: string[];
+  /** Ids defined by two or more `[^id]:` lines (only the first is kept). */
+  duplicateDefinitions: string[];
+  /** Reference ids found inside a GFM table row (heuristic). */
+  referencesInTables: string[];
+  /** Human-readable warning lines for the tool result (one per problem class). */
+  warnings: string[];
+}
 
 /**
- * True when `markdown` contains a legacy `[^id]:` definition line OUTSIDE any
+ * Analyze the footnotes in a Markdown string. Pure; safe to call on any body.
- * code fence. Pure; safe to call on any body.
  */
-export function hasLegacyFootnoteDefinition(markdown: string): boolean {
+export function analyzeFootnotes(markdown: string): FootnoteDiagnostics {
-  if (typeof markdown !== "string" || !markdown.includes("[^")) return false;
+  // Distinct reference ids in first-appearance order, plus the set of ids seen
-  let fence: string | null = null;
+  // inside a table row.
-  for (const line of markdown.split("\n")) {
+  const refIds: string[] = [];
-    const fenceMatch = FENCE_RE.exec(line);
+  const refIdSet = new Set<string>();
-    if (fenceMatch) {
+  const referencesInTables = new Set<string>();
-      const marker = fenceMatch[1][0];
+  const addRef = (id: string, inTable: boolean) => {
-      if (fence === null) fence = marker; // opening fence
+    if (!refIdSet.has(id)) {
-      else if (marker === fence) fence = null; // matching closing fence
+      refIdSet.add(id);
+      refIds.push(id);
+    }
+    if (inTable) referencesInTables.add(id);
+  };
+
+  // Definition texts per id, in first-appearance order of the id.
+  const defTextsById = new Map<string, string[]>();
+
+  // Same lexer the importer uses, so the analysis matches exactly what import
+  // keeps/strips (#166): fenced lines are inert, definition lines are pulled.
+  for (const tok of lexFootnoteLines(markdown)) {
+    if (tok.inFence) continue;
+    if (tok.definition) {
+      const { id, text } = tok.definition;
+      const arr = defTextsById.get(id);
+      if (arr) arr.push(text);
+      else defTextsById.set(id, [text]);
+      // A definition's TEXT can itself reference another footnote (`[^a]: see
+      // [^b]`); count those so such a `[^b]` is not falsely reported dangling.
+      forEachFootnoteReference(text, (rid) => addRef(rid, false));
       continue;
     }
-    if (fence !== null) continue; // inside a fence: inert example text
+    const inTable = tok.line.trimStart().startsWith("|");
-    if (FOOTNOTE_DEF_RE.test(line)) return true;
+    forEachFootnoteReference(tok.line, (id) => addRef(id, inTable));
   }
-  return false;
+
+  const danglingReferences = refIds.filter((id) => !defTextsById.has(id));
+  const duplicateDefinitions: string[] = [];
+  const emptyDefinitions: string[] = [];
+  for (const [id, texts] of defTextsById) {
+    if (texts.length >= 2) duplicateDefinitions.push(id);
+    // First-wins: the kept definition is the first one; flag it if it is blank.
+    if ((texts[0] ?? "").trim().length === 0) emptyDefinitions.push(id);
+  }
+  const tableRefs = [...referencesInTables];
+
+  const warnings: string[] = [];
+  const list = (ids: string[]) => ids.map((id) => `[^${id}]`).join(", ");
+  if (danglingReferences.length > 0) {
+    warnings.push(
+      `Footnote reference(s) with no matching definition: ${list(danglingReferences)} (each will render as an empty footnote in the editor).`,
+    );
+  }
+  if (emptyDefinitions.length > 0) {
+    warnings.push(
+      `Footnote definition(s) with empty text: ${list(emptyDefinitions)}.`,
+    );
+  }
+  if (duplicateDefinitions.length > 0) {
+    warnings.push(
+      `Footnote id(s) defined more than once (only the first definition was kept): ${list(duplicateDefinitions)}.`,
+    );
+  }
+  if (tableRefs.length > 0) {
+    warnings.push(
+      `Footnote marker(s) inside a table row (footnotes in table cells may not render as expected): ${list(tableRefs)}.`,
+    );
+  }
+
+  return {
+    danglingReferences,
+    emptyDefinitions,
+    duplicateDefinitions,
+    referencesInTables: tableRefs,
+    warnings,
+  };
 }
 
 /**
  * The optional `footnoteWarnings` field for a page-write tool result: present
- * (with the single advisory) only when `markdown` uses legacy reference-style
+ * (with the warning lines) only when `markdown` has footnote problems, omitted
- * footnote syntax, omitted otherwise. One helper so all three call sites
+ * otherwise. One helper so all three call sites (create/update/import) attach the
- * (create/update/import) attach the field identically. Spread into the result:
+ * field identically. Spread into the result: `{ ...result, ...footnoteWarningsField(text) }`.
- * `{ ...result, ...footnoteWarningsField(text) }`.
  */
 export function footnoteWarningsField(markdown: string): {
   footnoteWarnings?: string[];
 } {
-  return hasLegacyFootnoteDefinition(markdown)
+  const { warnings } = analyzeFootnotes(markdown);
-    ? { footnoteWarnings: [LEGACY_FOOTNOTE_WARNING] }
+  return warnings.length > 0 ? { footnoteWarnings: warnings } : {};
-    : {};
 }

packages/mcp/src/lib/footnote-authoring.ts

@@ -0,0 +1,91 @@
+/**
+ * Inline-authoring helpers for footnotes (MCP).
+ *
+ * These build/identify footnote DEFINITION nodes for the author-inline tool
+ * (`insertInlineFootnote` in transforms.ts): a content key to de-duplicate notes
+ * by text, a definition-node factory, and a fresh uuidv7-style id generator.
+ *
+ * Split out of `footnote-canonicalize.ts` so that module stays a pure MIRROR of
+ * the editor-ext canonicalizer (compositionally symmetric to the editor-ext
+ * copy, which keeps its authoring helpers in `footnote-util.ts`). The pure
+ * canonicalizer has no dependency on these.
+ */
+
+const FOOTNOTE_DEFINITION_NAME = "footnoteDefinition";
+
+function cloneJson<T>(v: T): T {
+  if (typeof structuredClone === "function") return structuredClone(v);
+  return JSON.parse(JSON.stringify(v)) as T;
+}
+
+/**
+ * Normalized content key for de-duplicating footnote DEFINITIONS by their text.
+ *
+ * Two definitions with the same key are the SAME footnote — so the inline
+ * authoring tool reuses one id (one number, one definition, several references)
+ * instead of minting a second definition. Key = plaintext (whitespace-collapsed,
+ * trimmed) PLUS a signature of the inline mark types in order, so two notes that
+ * read the same but differ in formatting (one bold, one plain) are NOT merged.
+ * Conservative: only an exact match merges.
+ */
+export function footnoteContentKey(defNode: any): string {
+  const parts: string[] = [];
+  const visit = (n: any): void => {
+    if (!n || typeof n !== "object") return;
+    if (n.type === "text" && typeof n.text === "string") {
+      const marks = Array.isArray(n.marks)
+        ? n.marks.map((m: any) => m?.type).filter(Boolean).sort().join(",")
+        : "";
+      parts.push(`${n.text}${marks}`);
+    }
+    if (Array.isArray(n.content)) for (const c of n.content) visit(c);
+  };
+  visit(defNode);
+  // Collapse the assembled text's whitespace and trim, keeping the mark
+  // signature attached so formatting differences still distinguish notes.
+  return parts
+    .join("")
+    .replace(/[ \t\r\n]+/g, " ")
+    .trim();
+}
+
+/**
+ * Build a footnoteDefinition node from inline ProseMirror nodes, keyed by id.
+ */
+export function makeFootnoteDefinition(id: string, inlineNodes: any[]): any {
+  const content = Array.isArray(inlineNodes) ? cloneJson(inlineNodes) : [];
+  return {
+    type: FOOTNOTE_DEFINITION_NAME,
+    attrs: { id },
+    content: [{ type: "paragraph", content }],
+  };
+}
+
+/**
+ * Generate a uuidv7-style id (time-ordered), matching editor-ext's
+ * `generateFootnoteId`. Used for a genuinely-new inline footnote id.
+ */
+export function generateFootnoteId(): string {
+  const now = Date.now();
+  const timeHex = now.toString(16).padStart(12, "0");
+  const rand = (length: number) => {
+    let s = "";
+    for (let i = 0; i < length; i++)
+      s += Math.floor(Math.random() * 16).toString(16);
+    return s;
+  };
+  const versioned = "7" + rand(3);
+  const variantNibble = (8 + Math.floor(Math.random() * 4)).toString(16);
+  const variant = variantNibble + rand(3);
+  return (
+    timeHex.slice(0, 8) +
+    "-" +
+    timeHex.slice(8, 12) +
+    "-" +
+    versioned +
+    "-" +
+    variant +
+    "-" +
+    rand(12)
+  );
+}

packages/mcp/src/lib/footnote-canonicalize.ts

@@ -4,8 +4,8 @@
  * `canonicalizeFootnotes(doc)` is a pure ProseMirror-JSON port of the editor's
  * `footnoteSyncPlugin` end-state, identical in behaviour to
  * `@docmost/editor-ext`'s `canonicalizeFootnotes`. It is mirrored here — rather
- * than imported from editor-ext — for the SAME reason the `docmost-schema.ts`
+ * than imported from editor-ext — for the SAME reason `footnote-lex.ts` and the
- * nodes are mirrored: the MCP package is deliberately
+ * `docmost-schema.ts` nodes are mirrored: the MCP package is deliberately
  * decoupled from the browser/React-heavy editor barrel and operates on plain
  * JSON. The editor-ext copy owns the golden test against the live plugin; this
  * copy must stay behaviourally identical (a SHARED golden corpus, exercised by
@@ -13,8 +13,8 @@
  *
  * This module is the pure MIRROR only. The inline-authoring helpers
  * (`footnoteContentKey`, `makeFootnoteDefinition`, `generateFootnoteId`) used by
- * `insertInlineFootnote` live in `@docmost/prosemirror-markdown` (next to the
+ * `insertInlineFootnote` live in the sibling `footnote-authoring.ts`, so this
- * importer's `assembleFootnotes`, #414), so this file stays a pure mirror.
+ * file is compositionally symmetric to the editor-ext copy.
  *
  * Why it exists: every NON-editor write path (markdown import, update_page_json,
  * docmost_transform, insert_footnote) builds ProseMirror JSON directly, so the

packages/mcp/src/lib/footnote-lex.ts

@@ -0,0 +1,73 @@
+/**
+ * Shared, fence-aware line lexer for legacy footnote markdown (MCP-internal).
+ *
+ * Since #293 STEP 5 the markdown -> ProseMirror IMPORT path lives in the shared
+ * `@docmost/prosemirror-markdown` package (inline `^[body]` footnotes), so this
+ * lexer no longer backs an mcp importer. It now backs ONLY the import-time
+ * diagnostics (`analyzeFootnotes` in footnote-analyze.ts), which still scan the
+ * raw markdown for legacy reference-style `[^id]:` definition lines and surface
+ * advisory warnings (duplicate/orphan definitions) about content that is now
+ * inert on import. Fence-awareness (a `[^id]:` line inside a ``` / ~~~ block is
+ * NOT a definition) is the property the analyzer relies on.
+ *
+ * NOTE: this is deliberately NOT shared with editor-ext's
+ * `extractFootnoteDefinitions` — that lives in a different package and the
+ * decoupling between the editor and the MCP mirror is intentional.
+ */
+
+/** A footnote DEFINITION line: `[^id]: text` (id + text captured). */
+export const FOOTNOTE_DEF_RE = /^\[\^([^\]\s]+)\]:[ \t]*(.*)$/;
+/** Every footnote REFERENCE `[^id]` in a line (global; id captured). */
+export const FOOTNOTE_REF_RE_G = /\[\^([^\]\s]+)\]/g;
+/** Opening/closing code fence marker (``` or ~~~). */
+const FENCE_RE = /^(\s*)(`{3,}|~{3,})/;
+
+export interface FootnoteLine {
+  /** The raw line, verbatim. */
+  line: string;
+  /**
+   * True for a code-fence marker line AND every line inside a fence — footnote
+   * syntax on such lines is inert (example text, not real markup). The importer
+   * keeps these in the body; the analyzer skips them.
+   */
+  inFence: boolean;
+  /** The parsed definition, when this is a `[^id]: text` line OUTSIDE any fence. */
+  definition: { id: string; text: string } | null;
+}
+
+/** Classify every line of `markdown`, tracking fenced-code state. Pure. */
+export function lexFootnoteLines(markdown: string): FootnoteLine[] {
+  const out: FootnoteLine[] = [];
+  let fence: string | null = null;
+  for (const line of markdown.split("\n")) {
+    const fenceMatch = FENCE_RE.exec(line);
+    if (fenceMatch) {
+      const marker = fenceMatch[2][0];
+      if (fence === null) fence = marker; // opening fence
+      else if (marker === fence) fence = null; // matching closing fence
+      out.push({ line, inFence: true, definition: null });
+      continue;
+    }
+    if (fence !== null) {
+      out.push({ line, inFence: true, definition: null });
+      continue;
+    }
+    const m = FOOTNOTE_DEF_RE.exec(line);
+    out.push({
+      line,
+      inFence: false,
+      definition: m ? { id: m[1], text: m[2] } : null,
+    });
+  }
+  return out;
+}
+
+/** Scan a line for every `[^id]` reference, invoking `onRef(id)` for each. */
+export function forEachFootnoteReference(
+  line: string,
+  onRef: (id: string) => void,
+): void {
+  FOOTNOTE_REF_RE_G.lastIndex = 0;
+  let m: RegExpExecArray | null;
+  while ((m = FOOTNOTE_REF_RE_G.exec(line)) !== null) onRef(m[1]);
+}

packages/mcp/src/lib/node-ops.ts

@@ -0,0 +1,963 @@
+/**
+ * Pure, network-free helpers for manipulating a ProseMirror/TipTap document
+ * tree by node id.
+ *
+ * A ProseMirror node here is a plain JSON object of the shape produced by
+ * Docmost: `{ type, attrs?, content?, text?, marks? }`. Children live in the
+ * `content` array; a node carries a stable id in `attrs.id`. Callouts and
+ * table cells hold their children in `content` just like any other block, so a
+ * single recursive walk reaches them all.
+ *
+ * Every exported function operates on a DEEP CLONE of the input document and
+ * returns the new document. The input doc and any `newNode`/`node` argument are
+ * never mutated. All functions are defensively null-safe: missing/!Array
+ * `content`, non-object nodes, and absent `attrs` are tolerated.
+ */
+
+import { stripInlineMarkdown } from "./text-normalize.js";
+
+/** Deep-clone a JSON-serializable value without mutating the original. */
+function clone<T>(value: T): T {
+  if (typeof structuredClone === "function") {
+    return structuredClone(value);
+  }
+  // Fallback for environments without structuredClone.
+  return JSON.parse(JSON.stringify(value)) as T;
+}
+
+/** True if `value` is a non-null object (and not an array). */
+function isObject(value: any): value is Record<string, any> {
+  return value != null && typeof value === "object" && !Array.isArray(value);
+}
+
+/** True if `node` carries the given id in `node.attrs.id`. */
+function matchesId(node: any, nodeId: string): boolean {
+  return isObject(node) && isObject(node.attrs) && node.attrs.id === nodeId;
+}
+
+/**
+ * Recursively concatenate all text contained in a node.
+ *
+ * Text nodes contribute their `text` string; container nodes contribute the
+ * joined `blockPlainText` of their `content` children. Returns "" for nullish
+ * or non-object inputs.
+ */
+export function blockPlainText(node: any): string {
+  if (!isObject(node)) return "";
+  let out = "";
+  if (typeof node.text === "string") {
+    out += node.text;
+  }
+  if (Array.isArray(node.content)) {
+    for (const child of node.content) {
+      out += blockPlainText(child);
+    }
+  }
+  return out;
+}
+
+/** Truncate `text` to at most `n` chars, appending an ellipsis when cut. */
+function truncate(text: string, n: number): string {
+  return text.length > n ? text.slice(0, n) + "…" : text;
+}
+
+/** One compact outline entry for a single top-level block. */
+export interface OutlineEntry {
+  index: number;
+  type: string | undefined;
+  id: string | null;
+  firstText: string;
+  /** Present for headings only. */
+  level?: number | null;
+  /** Present for tables only. */
+  rows?: number;
+  cols?: number;
+  header?: string[];
+  /** Present for list blocks only (bulletList/orderedList/taskList). */
+  items?: number;
+}
+
+/**
+ * Build a COMPACT outline of the TOP-LEVEL blocks of `doc` (the entries in
+ * `doc.content`). Deliberately does NOT recurse into paragraphs, list items, or
+ * table cells — compactness is the point; use `getNodeByRef` to drill into a
+ * specific block.
+ *
+ * Each entry carries `{ index, type, id, firstText }`, plus type-specific
+ * extras: headings add `level`; tables add `rows`/`cols` and the first row's
+ * cell texts as `header`; list blocks (types ending in "List") add `items`.
+ * `firstText` is the block's plain text truncated to 100 chars. Null-safe:
+ * a missing or non-object doc/content yields `[]`.
+ */
+export function buildOutline(doc: any): OutlineEntry[] {
+  if (!isObject(doc) || !Array.isArray(doc.content)) return [];
+
+  const out: OutlineEntry[] = [];
+  for (let i = 0; i < doc.content.length; i++) {
+    const block = doc.content[i];
+    const type = isObject(block) ? block.type : undefined;
+    const entry: OutlineEntry = {
+      index: i,
+      type,
+      id:
+        isObject(block) && isObject(block.attrs)
+          ? (block.attrs.id ?? null)
+          : null,
+      firstText: truncate(blockPlainText(block), 100),
+    };
+
+    if (type === "heading") {
+      entry.level = isObject(block.attrs) ? (block.attrs.level ?? null) : null;
+    } else if (type === "table") {
+      const headerRow = block.content?.[0]?.content ?? [];
+      entry.rows = block.content?.length ?? 0;
+      entry.cols = block.content?.[0]?.content?.length ?? 0;
+      entry.header = headerRow.map((cell: any) =>
+        truncate(blockPlainText(cell), 40),
+      );
+    } else if (typeof type === "string" && type.endsWith("List")) {
+      entry.items = block.content?.length ?? 0;
+    }
+
+    out.push(entry);
+  }
+  return out;
+}
+
+/**
+ * Resolve a single node by reference and return `{ node, path, type }`, or
+ * `null` when nothing matches.
+ *
+ * - `ref` of the form `#<n>` (e.g. `#2`) selects the TOP-LEVEL block at index
+ *   `n` in `doc.content`. This is the only way to address table/tableRow/
+ *   tableCell nodes, which carry no `attrs.id`.
+ * - Otherwise `ref` is treated as a block id: the FIRST node anywhere in the
+ *   tree with `attrs.id === ref` is returned.
+ *
+ * `path` is the array of child indices from the doc root down to the node
+ * (so a top-level block is `[index]`). The returned `node` is a DEEP CLONE,
+ * so callers can mutate it without touching the input doc. Null-safe.
+ */
+export function getNodeByRef(
+  doc: any,
+  ref: string,
+): { node: any; path: number[]; type: string | undefined } | null {
+  if (!isObject(doc)) return null;
+
+  // "#<n>": index into the top-level content array.
+  const indexMatch = typeof ref === "string" ? ref.match(/^#(\d+)$/) : null;
+  if (indexMatch) {
+    const index = Number(indexMatch[1]);
+    const block = Array.isArray(doc.content) ? doc.content[index] : undefined;
+    if (!isObject(block)) return null;
+    return { node: clone(block), path: [index], type: block.type };
+  }
+
+  // Otherwise: depth-first search for the first node with attrs.id === ref.
+  const search = (
+    node: any,
+    trail: number[],
+  ): { node: any; path: number[]; type: string } | null => {
+    if (!isObject(node)) return null;
+    if (Array.isArray(node.content)) {
+      for (let i = 0; i < node.content.length; i++) {
+        const child = node.content[i];
+        const path = [...trail, i];
+        if (matchesId(child, ref)) {
+          return { node: clone(child), path, type: child.type };
+        }
+        const hit = search(child, path);
+        if (hit != null) return hit;
+      }
+    }
+    return null;
+  };
+
+  return search(doc, []);
+}
+
+/**
+ * Replace EVERY node whose `attrs.id === nodeId` with a deep clone of
+ * `newNode`, anywhere in the tree (including inside callouts and table cells).
+ *
+ * Operates on a clone of `doc`; returns `{ doc, replaced }` where `replaced`
+ * is the number of nodes substituted. A fresh clone of `newNode` is used for
+ * each match so they do not share references.
+ */
+export function replaceNodeById(
+  doc: any,
+  nodeId: string,
+  newNode: any,
+): { doc: any; replaced: number } {
+  const out = clone(doc);
+  let replaced = 0;
+
+  // Walk a content array, replacing direct matches and recursing into the
+  // (possibly new) children of non-matching nodes.
+  const walkContent = (content: any[]): void => {
+    for (let i = 0; i < content.length; i++) {
+      const child = content[i];
+      if (matchesId(child, nodeId)) {
+        content[i] = clone(newNode);
+        replaced++;
+        // Do not recurse into a freshly substituted node.
+        continue;
+      }
+      if (isObject(child) && Array.isArray(child.content)) {
+        walkContent(child.content);
+      }
+    }
+  };
+
+  if (isObject(out) && Array.isArray(out.content)) {
+    walkContent(out.content);
+  }
+  return { doc: out, replaced };
+}
+
+/**
+ * Remove EVERY node whose `attrs.id === nodeId` from its parent `content`
+ * array, anywhere in the tree (recursive, including callouts and tables).
+ *
+ * Operates on a clone of `doc`; returns `{ doc, deleted }` where `deleted` is
+ * the number of nodes removed.
+ */
+export function deleteNodeById(
+  doc: any,
+  nodeId: string,
+): { doc: any; deleted: number } {
+  const out = clone(doc);
+  let deleted = 0;
+
+  // Filter a content array in place, dropping matches and recursing into the
+  // surviving children.
+  const walkContent = (content: any[]): any[] => {
+    const kept: any[] = [];
+    for (const child of content) {
+      if (matchesId(child, nodeId)) {
+        deleted++;
+        continue;
+      }
+      if (isObject(child) && Array.isArray(child.content)) {
+        child.content = walkContent(child.content);
+      }
+      kept.push(child);
+    }
+    return kept;
+  };
+
+  if (isObject(out) && Array.isArray(out.content)) {
+    out.content = walkContent(out.content);
+  }
+  return { doc: out, deleted };
+}
+
+/**
+ * Throw a clear, model-actionable error when a node-id write op did NOT match
+ * exactly one node (#159). `count === 0` -> "no node found"; `count > 1` ->
+ * "ambiguous, refused" — Docmost duplicates block ids on copy/paste, so a write
+ * by id could clobber/remove EVERY duplicate. The caller skips the write for any
+ * `count !== 1` (the transform returns null), so this only REPORTS; nothing was
+ * changed. No-op for the unambiguous single-match case.
+ */
+export function assertUnambiguousMatch(
+  op: "patch_node" | "delete_node",
+  verb: "replace" | "delete",
+  count: number,
+  nodeId: string,
+  pageId: string,
+): void {
+  if (count === 0) {
+    throw new Error(
+      `${op}: no node with id "${nodeId}" found on page ${pageId}`,
+    );
+  }
+  if (count > 1) {
+    throw new Error(
+      `${op}: id "${nodeId}" is ambiguous — ${count} nodes on page ${pageId} share it (block ids are duplicated on copy/paste). Refusing to ${verb} all of them; nothing was changed. Re-target with a more specific anchor.`,
+    );
+  }
+}
+
+/**
+ * Deep-clone `doc` and strip every node/mark attribute whose value is strictly
+ * `undefined`, so the result is safe to hand to Yjs (which throws an opaque
+ * "Unexpected content type" when asked to store an `undefined` attribute value).
+ *
+ * Only `undefined` keys are removed; `null`, `false`, `0`, and `""` are all
+ * legitimate JSON-storable values and are preserved. Operates on a clone and
+ * returns it; the input is never mutated. Defensively null-safe like the rest
+ * of the file.
+ */
+export function sanitizeForYjs(doc: any): any {
+  const out = clone(doc);
+
+  // Drop every key whose value is strictly `undefined` from an attrs object.
+  const stripUndefined = (attrs: any): void => {
+    if (!isObject(attrs)) return;
+    for (const key of Object.keys(attrs)) {
+      if (attrs[key] === undefined) {
+        delete attrs[key];
+      }
+    }
+  };
+
+  const walk = (node: any): void => {
+    if (!isObject(node)) return;
+    stripUndefined(node.attrs);
+    if (Array.isArray(node.marks)) {
+      for (const mark of node.marks) {
+        if (isObject(mark)) stripUndefined(mark.attrs);
+      }
+    }
+    if (Array.isArray(node.content)) {
+      for (const child of node.content) {
+        walk(child);
+      }
+    }
+  };
+
+  walk(out);
+  return out;
+}
+
+/**
+ * Diagnostics helper: walk the tree and return a human-readable path string for
+ * the FIRST attribute value (in any `node.attrs` or `mark.attrs`) that Yjs
+ * cannot store — i.e. `undefined`, a `function`, a `symbol`, or a `bigint`
+ * (e.g. `content[3].content[0].attrs.indent (undefined)`). Returns `null` when
+ * every attribute is storable. Null-safe.
+ */
+export function findUnstorableAttr(doc: any): string | null {
+  const isUnstorable = (value: any): string | null => {
+    if (value === undefined) return "undefined";
+    const t = typeof value;
+    if (t === "function") return "function";
+    if (t === "symbol") return "symbol";
+    if (t === "bigint") return "bigint";
+    return null;
+  };
+
+  // Check an attrs object; return the offending sub-path or null.
+  const checkAttrs = (attrs: any, basePath: string): string | null => {
+    if (!isObject(attrs)) return null;
+    for (const key of Object.keys(attrs)) {
+      const kind = isUnstorable(attrs[key]);
+      if (kind != null) return `${basePath}.${key} (${kind})`;
+    }
+    return null;
+  };
+
+  const walk = (node: any, path: string): string | null => {
+    if (!isObject(node)) return null;
+    const attrHit = checkAttrs(node.attrs, `${path}.attrs`);
+    if (attrHit != null) return attrHit;
+    if (Array.isArray(node.marks)) {
+      for (let i = 0; i < node.marks.length; i++) {
+        const markHit = checkAttrs(
+          node.marks[i]?.attrs,
+          `${path}.marks[${i}].attrs`,
+        );
+        if (markHit != null) return markHit;
+      }
+    }
+    if (Array.isArray(node.content)) {
+      for (let i = 0; i < node.content.length; i++) {
+        const childHit = walk(node.content[i], `${path}.content[${i}]`);
+        if (childHit != null) return childHit;
+      }
+    }
+    return null;
+  };
+
+  // The root doc node carries no useful index, so start the path at "doc".
+  if (!isObject(doc)) return null;
+  const attrHit = checkAttrs(doc.attrs, "attrs");
+  if (attrHit != null) return attrHit;
+  if (Array.isArray(doc.content)) {
+    for (let i = 0; i < doc.content.length; i++) {
+      const childHit = walk(doc.content[i], `content[${i}]`);
+      if (childHit != null) return childHit;
+    }
+  }
+  return null;
+}
+
+/**
+ * Table structural node types and the container each must live directly inside.
+ * Used by `insertNodeRelative` to splice rows/cells into the correct ancestor
+ * rather than blindly into the anchor's direct parent (which would corrupt the
+ * table's nesting).
+ */
+const STRUCTURAL_TYPES = new Set(["tableRow", "tableCell", "tableHeader"]);
+const REQUIRED_CONTAINER: Record<string, string> = {
+  tableRow: "table",
+  tableCell: "tableRow",
+  tableHeader: "tableRow",
+};
+
+/**
+ * Find the index of the first TOP-LEVEL block whose plain text includes the
+ * anchor, with a markdown-stripping FALLBACK. Returns -1 when none matches.
+ *
+ * Two passes preserve "exact wins globally":
+ *  - Pass 1: first block containing the verbatim `anchorText`.
+ *  - Pass 2 (only if pass 1 found nothing): first block containing the
+ *    markdown-stripped anchor, when stripping actually changed it.
+ */
+function findAnchorTextIndex(content: any[], anchorText: string): number {
+  if (!Array.isArray(content)) return -1;
+  // Pass 1: exact.
+  for (let i = 0; i < content.length; i++) {
+    if (blockPlainText(content[i]).includes(anchorText)) return i;
+  }
+  // Pass 2: markdown-stripped fallback.
+  const a = stripInlineMarkdown(anchorText);
+  if (a !== anchorText && a.length > 0) {
+    for (let i = 0; i < content.length; i++) {
+      if (blockPlainText(content[i]).includes(a)) return i;
+    }
+  }
+  return -1;
+}
+
+/**
+ * Locate an anchor and return its ancestor chain (from `doc` down to and
+ * including the matched node). Each chain entry is `{ node, index }` where
+ * `index` is the node's position inside its parent's `content` array (the root
+ * doc has index -1). Returns `null` when the anchor cannot be resolved.
+ */
+function findAnchorChain(
+  doc: any,
+  opts: InsertOptions,
+): { node: any; index: number }[] | null {
+  if (!isObject(doc)) return null;
+
+  // DFS by id anywhere in the tree, accumulating the path.
+  if (opts.anchorNodeId != null) {
+    const targetId = opts.anchorNodeId;
+    const search = (
+      node: any,
+      index: number,
+      trail: { node: any; index: number }[],
+    ): { node: any; index: number }[] | null => {
+      if (!isObject(node)) return null;
+      const here = [...trail, { node, index }];
+      if (matchesId(node, targetId)) return here;
+      if (Array.isArray(node.content)) {
+        for (let i = 0; i < node.content.length; i++) {
+          const hit = search(node.content[i], i, here);
+          if (hit != null) return hit;
+        }
+      }
+      return null;
+    };
+    return search(doc, -1, []);
+  }
+
+  // By text: only top-level blocks are scanned (same rule as the JSON path).
+  // Exact match wins; a markdown-stripped fallback is tried only on a miss.
+  if (opts.anchorText != null && Array.isArray(doc.content)) {
+    const i = findAnchorTextIndex(doc.content, opts.anchorText);
+    if (i !== -1) {
+      return [
+        { node: doc, index: -1 },
+        { node: doc.content[i], index: i },
+      ];
+    }
+  }
+
+  return null;
+}
+
+/** Options controlling where `insertNodeRelative` places the new node. */
+export interface InsertOptions {
+  position: "before" | "after" | "append";
+  /** Resolve the anchor by node id anywhere in the tree (preferred). */
+  anchorNodeId?: string;
+  /** Fallback: first TOP-LEVEL block whose plain text includes this string. */
+  anchorText?: string;
+}
+
+/**
+ * Insert a deep clone of `node` relative to an anchor.
+ *
+ * - position "append": push the node onto the top-level `doc.content`.
+ * - position "before"/"after": locate the anchor and splice the node into the
+ *   anchor's parent `content` array immediately before / after it.
+ *
+ * Anchor resolution for before/after:
+ *   - if `anchorNodeId` is given, find the node with `attrs.id === anchorNodeId`
+ *     anywhere in the tree (recursive);
+ *   - otherwise, if `anchorText` is given, scan only TOP-LEVEL `doc.content`
+ *     blocks and pick the first whose `blockPlainText` includes `anchorText`.
+ *
+ * Operates on a clone of `doc`; returns `{ doc, inserted }`. `inserted` is
+ * false when the anchor could not be resolved (the doc is returned unchanged
+ * apart from being cloned).
+ */
+export function insertNodeRelative(
+  doc: any,
+  node: any,
+  opts: InsertOptions,
+): { doc: any; inserted: boolean } {
+  const out = clone(doc);
+  const fresh = clone(node);
+
+  // Defensive: stay null-safe like the other exports — a missing opts means
+  // there is nothing actionable to do.
+  if (!isObject(opts)) return { doc: out, inserted: false };
+
+  const isStructural = isObject(node) && STRUCTURAL_TYPES.has(node.type);
+
+  // "append": top-level push.
+  if (opts.position === "append") {
+    // Structural table nodes (tableRow/tableCell/tableHeader) cannot live at the
+    // top level — appending one would produce invalid nesting.
+    if (isStructural) {
+      throw new Error(
+        `insert_node: cannot append a ${node.type} at the top level; use ` +
+          `position before/after with an anchor inside the target table`,
+      );
+    }
+    if (isObject(out)) {
+      if (!Array.isArray(out.content)) out.content = [];
+      out.content.push(fresh);
+      return { doc: out, inserted: true };
+    }
+    return { doc: out, inserted: false };
+  }
+
+  const offset = opts.position === "after" ? 1 : 0;
+
+  // Structural insert (before/after a tableRow/tableCell/tableHeader): splice
+  // into the nearest enclosing table/tableRow rather than the anchor's direct
+  // parent, so the row/cell lands at the correct level of the table.
+  if (isStructural) {
+    const containerType = REQUIRED_CONTAINER[node.type];
+    const chain = findAnchorChain(out, opts);
+    // Anchor not resolved at all — keep the existing "anchor not found" path.
+    if (chain == null) return { doc: out, inserted: false };
+
+    // Find the DEEPEST ancestor (including the anchor itself) of the required
+    // container type.
+    let containerIdx = -1;
+    for (let i = chain.length - 1; i >= 0; i--) {
+      if (isObject(chain[i].node) && chain[i].node.type === containerType) {
+        containerIdx = i;
+        break;
+      }
+    }
+
+    if (containerIdx === -1) {
+      throw new Error(
+        `insert_node: cannot insert a ${node.type} here — the anchor is not ` +
+          `inside a ${containerType}. Anchor on a cell's text or a block id ` +
+          `that lives inside the target table.`,
+      );
+    }
+
+    const container = chain[containerIdx].node;
+    if (!Array.isArray(container.content)) container.content = [];
+
+    if (containerIdx === chain.length - 1) {
+      // The matched container IS the anchor node itself (e.g. anchorText
+      // resolved to the table block): append/prepend within it.
+      const at = opts.position === "after" ? container.content.length : 0;
+      container.content.splice(at, 0, fresh);
+    } else {
+      // The immediate child on the path leading to the anchor is the row/cell
+      // to splice next to.
+      const enclosingChildIndex = chain[containerIdx + 1].index;
+      container.content.splice(enclosingChildIndex + offset, 0, fresh);
+    }
+    return { doc: out, inserted: true };
+  }
+
+  // Resolve by id anywhere in the tree: splice into the parent content array.
+  if (opts.anchorNodeId != null) {
+    let inserted = false;
+    const walkContent = (content: any[]): void => {
+      for (let i = 0; i < content.length; i++) {
+        const child = content[i];
+        if (matchesId(child, opts.anchorNodeId as string)) {
+          content.splice(i + offset, 0, fresh);
+          inserted = true;
+          return;
+        }
+        if (isObject(child) && Array.isArray(child.content)) {
+          walkContent(child.content);
+          if (inserted) return;
+        }
+      }
+    };
+    if (isObject(out) && Array.isArray(out.content)) {
+      walkContent(out.content);
+    }
+    return { doc: out, inserted };
+  }
+
+  // Resolve by text: only top-level doc.content blocks are scanned. Exact
+  // match wins; a markdown-stripped fallback is tried only on a miss.
+  if (opts.anchorText != null && isObject(out) && Array.isArray(out.content)) {
+    const i = findAnchorTextIndex(out.content, opts.anchorText);
+    if (i !== -1) {
+      out.content.splice(i + offset, 0, fresh);
+      return { doc: out, inserted: true };
+    }
+  }
+
+  return { doc: out, inserted: false };
+}
+
+// ===========================================================================
+// Table editing helpers
+//
+// A Docmost table is a ProseMirror subtree with NO ids on the structural nodes:
+//   table   -> { type:"table",     content:[tableRow...] }
+//   row     -> { type:"tableRow",  content:[tableCell|tableHeader...] }
+//   cell    -> { type:"tableCell"|"tableHeader", attrs:{colspan,rowspan,colwidth},
+//                content:[paragraph...] }
+//   para    -> { type:"paragraph", attrs:{id,indent}, content:[textNode...] }
+// Only paragraphs/headings carry an `attrs.id`, so a cell is addressed via the
+// id of the paragraph inside it. The helpers below all operate on a DEEP CLONE
+// of the input doc (via `clone`) and never mutate their inputs.
+// ===========================================================================
+
+/**
+ * Collect EVERY `attrs.id` present anywhere in `node` into `used`. Used to seed
+ * `makeFreshId` so generated paragraph ids never collide with existing ones.
+ */
+function collectIds(node: any, used: Set<string>): void {
+  if (!isObject(node)) return;
+  if (isObject(node.attrs) && typeof node.attrs.id === "string") {
+    used.add(node.attrs.id);
+  }
+  if (Array.isArray(node.content)) {
+    for (const child of node.content) collectIds(child, used);
+  }
+}
+
+/**
+ * Fresh-id generator: returns a random Docmost-style id (12 chars from
+ * lowercase `a-z0-9`) that is not already in `used`, and records it. On the
+ * rare collision the id is regenerated. Callers rely on uniqueness, not on the
+ * exact string, so randomness is fine — and unlike a module-local counter it
+ * needs no reset and cannot become predictable across calls.
+ */
+function makeFreshId(used: Set<string>): string {
+  const alphabet = "abcdefghijklmnopqrstuvwxyz0123456789";
+  let id: string;
+  do {
+    id = "";
+    for (let i = 0; i < 12; i++) {
+      id += alphabet[Math.floor(Math.random() * alphabet.length)];
+    }
+  } while (used.has(id) || id === "");
+  used.add(id);
+  return id;
+}
+
+/**
+ * Resolve a table reference against an ALREADY-CLONED doc and return the LIVE
+ * table node (a reference inside `rootClone`, so the caller may mutate it) plus
+ * its index path. Returns null when no table matches.
+ *
+ * - `#<n>`: the top-level block at index `n`, only if its `type === "table"`.
+ * - otherwise: DFS for the node with `attrs.id === tableRef`, then walk UP its
+ *   ancestor chain to the nearest `type === "table"` ancestor.
+ */
+function locateTable(
+  rootClone: any,
+  tableRef: string,
+): { table: any; path: number[] } | null {
+  if (!isObject(rootClone)) return null;
+
+  // "#<n>": index into the top-level content array; must be a table.
+  const indexMatch =
+    typeof tableRef === "string" ? tableRef.match(/^#(\d+)$/) : null;
+  if (indexMatch) {
+    const index = Number(indexMatch[1]);
+    const block = Array.isArray(rootClone.content)
+      ? rootClone.content[index]
+      : undefined;
+    if (isObject(block) && block.type === "table") {
+      return { table: block, path: [index] };
+    }
+    return null;
+  }
+
+  // Otherwise: DFS for attrs.id === tableRef, tracking the ancestor chain, then
+  // climb to the nearest enclosing table.
+  const search = (
+    node: any,
+    trail: { node: any; index: number }[],
+  ): { table: any; path: number[] } | null => {
+    if (!isObject(node)) return null;
+    if (Array.isArray(node.content)) {
+      for (let i = 0; i < node.content.length; i++) {
+        const child = node.content[i];
+        const here = [...trail, { node: child, index: i }];
+        if (matchesId(child, tableRef)) {
+          // Walk UP to the nearest table ancestor (including the match itself).
+          for (let j = here.length - 1; j >= 0; j--) {
+            if (isObject(here[j].node) && here[j].node.type === "table") {
+              return {
+                table: here[j].node,
+                path: here.slice(0, j + 1).map((e) => e.index),
+              };
+            }
+          }
+          return null; // id found but no enclosing table
+        }
+        const hit = search(child, here);
+        if (hit != null) return hit;
+      }
+    }
+    return null;
+  };
+
+  return search(rootClone, []);
+}
+
+/** Build the plain-text → single-paragraph cell content used by all writers. */
+function makeCellParagraph(id: string, text: string): any {
+  return {
+    type: "paragraph",
+    attrs: { id, indent: 0 },
+    // Empty string → a paragraph with an empty content array.
+    content: text ? [{ type: "text", text }] : [],
+  };
+}
+
+/**
+ * Read a table as a matrix. Returns null when `tableRef` resolves to no table.
+ *
+ * - `rows`/`cols`: the table's row count and the column count of its FIRST row.
+ *   Tables may be ragged (rows of differing length), so `cols` reflects only
+ *   row 0; use the per-row length of `cells`/`cellIds` for each row's actual
+ *   width.
+ * - `cells`: `string[][]` of each cell's `blockPlainText`.
+ * - `cellIds`: `(string|null)[][]` of each cell's FIRST paragraph id (or null),
+ *   so callers can `patch_node` a cell for rich-formatted edits.
+ * - `path`: index path of the table within the doc.
+ */
+export function readTable(
+  doc: any,
+  tableRef: string,
+): {
+  rows: number;
+  cols: number;
+  cells: string[][];
+  cellIds: (string | null)[][];
+  path: number[];
+} | null {
+  const root = clone(doc);
+  const located = locateTable(root, tableRef);
+  if (located == null) return null;
+  const { table, path } = located;
+
+  const rowNodes = Array.isArray(table.content) ? table.content : [];
+  const rows = rowNodes.length;
+  const cols = rowNodes[0]?.content?.length ?? 0;
+
+  const cells: string[][] = [];
+  const cellIds: (string | null)[][] = [];
+  for (const rowNode of rowNodes) {
+    const cellNodes = Array.isArray(rowNode?.content) ? rowNode.content : [];
+    const rowText: string[] = [];
+    const rowIds: (string | null)[] = [];
+    for (const cellNode of cellNodes) {
+      rowText.push(blockPlainText(cellNode));
+      // The cell's first paragraph carries the id used for patch_node.
+      const firstPara = Array.isArray(cellNode?.content)
+        ? cellNode.content[0]
+        : undefined;
+      const id =
+        isObject(firstPara) && isObject(firstPara.attrs)
+          ? (firstPara.attrs.id ?? null)
+          : null;
+      rowIds.push(id);
+    }
+    cells.push(rowText);
+    cellIds.push(rowIds);
+  }
+
+  return { rows, cols, cells, cellIds, path };
+}
+
+/**
+ * Insert a row of plain-text cells into a table. Returns `{ doc, inserted }`.
+ *
+ * The row is padded to the table's column count (`cells[i] ?? ""`); supplying
+ * MORE cells than columns throws. Each new cell copies `colwidth` for its
+ * column from the header row when present, gets a fresh-id paragraph, and a
+ * `colspan:1, rowspan:1` attrs. `index` (when an integer in `[0, rows]`) splices
+ * the row there; otherwise the row is appended at the end.
+ */
+export function insertTableRow(
+  doc: any,
+  tableRef: string,
+  cells: string[],
+  index?: number,
+): { doc: any; inserted: boolean } {
+  const out = clone(doc);
+  const located = locateTable(out, tableRef);
+  if (located == null) return { doc: out, inserted: false };
+  const { table } = located;
+
+  if (!Array.isArray(table.content)) table.content = [];
+  const rows = table.content.length;
+  const headerRow = table.content[0];
+  const headerCells = Array.isArray(headerRow?.content)
+    ? headerRow.content
+    : [];
+
+  // Column count is the WIDEST existing row, so the guard below stays
+  // meaningful for ragged tables and the new row matches the table's width.
+  // Fall back to the supplied cell count only when the table has no rows.
+  let colCount = 0;
+  for (const r of table.content) {
+    if (isObject(r) && Array.isArray(r.content))
+      colCount = Math.max(colCount, r.content.length);
+  }
+  if (colCount === 0) colCount = Array.isArray(cells) ? cells.length : 0;
+
+  if (Array.isArray(cells) && cells.length > colCount) {
+    throw new Error(
+      `table_insert_row: got ${cells.length} cell(s) but the table has ${colCount} column(s)`,
+    );
+  }
+
+  // Resolve the landing index up front so the cell-type decision and the splice
+  // below agree: a valid integer in [0, rows] splices there, else we append.
+  const landingIndex =
+    typeof index === "number" &&
+    Number.isInteger(index) &&
+    index >= 0 &&
+    index <= rows
+      ? index
+      : rows;
+
+  // Seed the id generator with every id already in the doc so the new cell
+  // paragraph ids are unique within the whole document.
+  const used = new Set<string>();
+  collectIds(out, used);
+
+  const newCells: any[] = [];
+  for (let i = 0; i < colCount; i++) {
+    const text = (Array.isArray(cells) ? cells[i] : undefined) ?? "";
+    const attrs: Record<string, any> = { colspan: 1, rowspan: 1 };
+    // Copy this column's colwidth from the header row's cell when present.
+    const colwidth = headerCells[i]?.attrs?.colwidth;
+    if (colwidth !== undefined) attrs.colwidth = colwidth;
+    // A row landing at index 0 becomes the new header row, so inherit the
+    // current header cell's type per column (Docmost uses "tableHeader" there);
+    // every other position is a plain data cell.
+    const cellType =
+      landingIndex === 0 ? (headerCells[i]?.type ?? "tableCell") : "tableCell";
+    newCells.push({
+      type: cellType,
+      attrs,
+      content: [makeCellParagraph(makeFreshId(used), text)],
+    });
+  }
+
+  const newRow = { type: "tableRow", content: newCells };
+
+  // Splice at the resolved landing index (append when index was omitted/invalid).
+  table.content.splice(landingIndex, 0, newRow);
+
+  return { doc: out, inserted: true };
+}
+
+/**
+ * Delete the row at 0-based `index` from a table. Returns `{ doc, deleted }`.
+ * `deleted` is false only when the table cannot be located. Throws on an
+ * out-of-range index, and refuses to delete the table's only row.
+ */
+export function deleteTableRow(
+  doc: any,
+  tableRef: string,
+  index: number,
+): { doc: any; deleted: boolean } {
+  const out = clone(doc);
+  const located = locateTable(out, tableRef);
+  if (located == null) return { doc: out, deleted: false };
+  const { table } = located;
+
+  if (!Array.isArray(table.content)) table.content = [];
+  const rows = table.content.length;
+
+  if (!Number.isInteger(index) || index < 0 || index >= rows) {
+    throw new Error(
+      `table_delete_row: row index ${index} out of range (table has ${rows} row(s))`,
+    );
+  }
+  if (rows <= 1) {
+    throw new Error(
+      "table_delete_row: refusing to delete the only row of the table",
+    );
+  }
+
+  table.content.splice(index, 1);
+  return { doc: out, deleted: true };
+}
+
+/**
+ * Set the plain-text content of cell `[row, col]` (0-based) to `text`. Returns
+ * `{ doc, updated }`; `updated` is false only when the table cannot be located.
+ * Throws when `row`/`col` is out of range. The cell's own attrs (colspan/
+ * rowspan/colwidth) are preserved; its content becomes a single text paragraph
+ * that reuses the cell's existing first-paragraph id when present, else a fresh
+ * one.
+ */
+export function updateTableCell(
+  doc: any,
+  tableRef: string,
+  row: number,
+  col: number,
+  text: string,
+): { doc: any; updated: boolean } {
+  const out = clone(doc);
+  const located = locateTable(out, tableRef);
+  if (located == null) return { doc: out, updated: false };
+  const { table } = located;
+
+  const rowNodes = Array.isArray(table.content) ? table.content : [];
+  const rows = rowNodes.length;
+  const rowNode = rowNodes[row];
+  const cols =
+    isObject(rowNode) && Array.isArray(rowNode.content)
+      ? rowNode.content.length
+      : 0;
+
+  if (
+    !Number.isInteger(row) ||
+    row < 0 ||
+    row >= rows ||
+    !Number.isInteger(col) ||
+    col < 0 ||
+    col >= cols
+  ) {
+    throw new Error(`table_update_cell: cell [${row},${col}] out of range`);
+  }
+
+  const cellNode = rowNode.content[col];
+  // Reuse the cell's existing first-paragraph id, or mint a fresh unique one.
+  const existingPara = Array.isArray(cellNode?.content)
+    ? cellNode.content[0]
+    : undefined;
+  let id =
+    isObject(existingPara) && isObject(existingPara.attrs)
+      ? existingPara.attrs.id
+      : undefined;
+  if (typeof id !== "string" || id.length === 0) {
+    const used = new Set<string>();
+    collectIds(out, used);
+    id = makeFreshId(used);
+  }
+
+  cellNode.content = [makeCellParagraph(id, text)];
+  return { doc: out, updated: true };
+}

packages/mcp/src/lib/page-search.ts

@@ -33,7 +33,7 @@
 
 import RE2 from "re2";
 
-import { blockPlainText } from "@docmost/prosemirror-markdown";
+import { blockPlainText } from "./node-ops.js";
 
 /** An RE2 regex instance (RE2 extends `RegExp`, so it is usable as one). */
 type Re2Regex = InstanceType<typeof RE2>;

packages/mcp/src/lib/parse-node-arg.ts

@@ -2,11 +2,6 @@
 // instead of an object. Normalize: parse a string to an object (throwing on
 // invalid JSON), pass an object through unchanged. Shared by patch_node /
 // insert_node (and the analogous update_page_json content parsing).
-//
-// This lives in the converter package (#414) so BOTH consumers import the ONE
-// copy: `@docmost/mcp` (ESM) and the CommonJS server app. The server cannot
-// import `@docmost/mcp` directly (ESM-only, no declaration files), but it does
-// import `@docmost/prosemirror-markdown` natively — so this is the shared home.
 export function parseNodeArg(
   node: unknown,
   errMsg = "node was a string but not valid JSON",

packages/mcp/src/lib/transforms.ts

@@ -14,13 +14,13 @@
  *  - `marks` arrays are preserved verbatim when fragments are split/reordered.
  */
 
+import { blockPlainText } from "./node-ops.js";
+import { canonicalizeFootnotes } from "./footnote-canonicalize.js";
 import {
-  blockPlainText,
   footnoteContentKey,
   makeFootnoteDefinition,
   generateFootnoteId,
-} from "@docmost/prosemirror-markdown";
+} from "./footnote-authoring.js";
-import { canonicalizeFootnotes } from "./footnote-canonicalize.js";
 
 export { canonicalizeFootnotes } from "./footnote-canonicalize.js";
 
@@ -365,7 +365,7 @@ export function noteItem(inlineNodes: any[]): any {
  *   { type:"footnoteDefinition", attrs:{id}, content:[{ type:"paragraph", content }] }
  * (mirrors the editor-ext / docmost-schema FootnoteDefinition node).
  *
- * Built on the shared `makeFootnoteDefinition` factory (`@docmost/prosemirror-markdown`);
+ * Built on the shared `makeFootnoteDefinition` factory (footnote-authoring.ts);
  * the only extra is a fresh block id on the inner paragraph (Docmost stamps one,
  * and the canonicalizer preserves attrs as-is). Single factory, one place to
  * change the definition shape.

packages/mcp/test/mock/footnote-warnings.test.mjs

@@ -1,7 +1,7 @@
 // Mock-HTTP test for the footnoteWarnings plumbing (#166). createPage is the
 // representative path that is fully plain-HTTP (import + getPage) and so is
 // mockable here; updatePage / importPageMarkdown attach footnoteWarnings with the
-// IDENTICAL wiring (`footnoteWarningsField(...)` spread-when-non-empty) but run their
+// IDENTICAL wiring (`analyzeFootnotes(...)` + spread-when-non-empty) but run their
 // mutation over the Hocuspocus collab WebSocket, which this plain-HTTP harness
 // does not stand up. The analyzer itself is unit-tested in footnote-analyze.test.
 import { test, after } from "node:test";
@@ -76,29 +76,35 @@ function pageHandler() {
   };
 }
 
-test("createPage attaches footnoteWarnings when the content uses legacy footnote syntax", async () => {
+test("createPage attaches footnoteWarnings when the content has footnote problems", async () => {
   const baseURL = await spawn(pageHandler());
   const client = new DocmostClient(baseURL, "user@example.com", "pw");
-  // Legacy reference-style `[^id]:` definitions — inert on import since #293.
+  // A dangling reference + a duplicate definition + a table marker.
-  const content = ["Intro[^a].", "", "[^a]: a definition"].join("\n");
+  const content = [
+    "Intro[^missing] and| cell[^t] |.",
+    "",
+    "[^d]: one",
+    "[^d]: two",
+    "[^t]: in table",
+  ].join("\n");
   const result = await client.createPage("T", content, "sp-1");
   assert.ok(Array.isArray(result.footnoteWarnings), "footnoteWarnings present");
   const joined = result.footnoteWarnings.join("\n");
-  assert.match(joined, /reference-style footnotes/i);
+  assert.match(joined, /no matching definition/); // dangling [^missing]
-  assert.match(joined, /\^\[footnote text\]/); // nudge to the inline form
+  assert.match(joined, /defined more than once/); // duplicate [^d]
   // The page itself is still returned.
   assert.equal(result.success, true);
 });
 
-test("createPage omits footnoteWarnings when the content uses the inline form", async () => {
+test("createPage omits footnoteWarnings when the content is clean", async () => {
   const baseURL = await spawn(pageHandler());
   const client = new DocmostClient(baseURL, "user@example.com", "pw");
-  const content = "A note.^[the body] and reuse.^[the body]";
+  const content = ["A[^a] and reuse[^a].", "", "[^a]: fine"].join("\n");
   const result = await client.createPage("T", content, "sp-1");
   assert.equal(
     "footnoteWarnings" in result,
     false,
-    "no footnoteWarnings field on inline-footnote input",
+    "no footnoteWarnings field on clean input",
   );
   assert.equal(result.success, true);
 });

packages/mcp/test/unit/footnote-analyze.test.mjs

@@ -1,45 +1,64 @@
 import { test } from "node:test";
 import assert from "node:assert/strict";
 
-import {
+import { analyzeFootnotes } from "../../build/lib/footnote-analyze.js";
-  footnoteWarningsField,
-  hasLegacyFootnoteDefinition,
-} from "../../build/lib/footnote-analyze.js";
 
-// #414: the legacy footnote diagnostics were reduced to ONE advisory that fires
+test("clean footnotes produce no diagnostics", () => {
-// on the PRESENCE of legacy reference-style `[^id]:` definition syntax (inert on
+  const md = ["A[^a] and B[^b].", "", "[^a]: first", "[^b]: second"].join("\n");
-// import since #293), nudging the author to inline `^[...]` footnotes.
+  const d = analyzeFootnotes(md);
-
+  assert.deepEqual(d.danglingReferences, []);
-test("inline `^[...]` footnotes produce no warning", () => {
+  assert.deepEqual(d.emptyDefinitions, []);
-  const md = "A note here.^[the body] and reuse elsewhere.^[the body]";
+  assert.deepEqual(d.duplicateDefinitions, []);
-  assert.equal(hasLegacyFootnoteDefinition(md), false);
+  assert.deepEqual(d.referencesInTables, []);
-  assert.deepEqual(footnoteWarningsField(md), {});
+  assert.deepEqual(d.warnings, []);
 });
 
-test("no footnotes at all produce no warning", () => {
+test("reuse (repeated references to one definition) is NOT a warning", () => {
-  const md = "Just a paragraph with [a link](https://x) and no footnotes.";
+  const md = ["A[^a] B[^a] C[^a].", "", "[^a]: shared"].join("\n");
-  assert.equal(hasLegacyFootnoteDefinition(md), false);
+  const d = analyzeFootnotes(md);
-  assert.deepEqual(footnoteWarningsField(md), {});
+  assert.deepEqual(d.danglingReferences, []);
+  assert.deepEqual(d.warnings, []);
 });
 
-test("a legacy `[^id]:` definition triggers the single advisory", () => {
+test("dangling reference (no definition) is reported", () => {
-  const md = ["See[^a].", "", "[^a]: defined"].join("\n");
+  const md = ["See[^missing] and[^a].", "", "[^a]: defined"].join("\n");
-  assert.equal(hasLegacyFootnoteDefinition(md), true);
+  const d = analyzeFootnotes(md);
-  const field = footnoteWarningsField(md);
+  assert.deepEqual(d.danglingReferences, ["missing"]);
-  assert.equal(field.footnoteWarnings.length, 1);
+  assert.equal(d.warnings.length, 1);
-  assert.match(field.footnoteWarnings[0], /reference-style footnotes/i);
+  assert.match(d.warnings[0], /no matching definition/);
-  assert.match(field.footnoteWarnings[0], /\^\[footnote text\]/);
+  assert.match(d.warnings[0], /\[\^missing\]/);
 });
 
-test("a bare `[^id]` reference (no definition line) is not flagged", () => {
+test("empty definition text is reported", () => {
-  // Only the definition syntax `[^id]:` is a reliable signal of legacy authoring;
+  const md = ["See[^a].", "", "[^a]:   "].join("\n");
-  // a lone `[^x]` in prose is too ambiguous to warn on.
+  const d = analyzeFootnotes(md);
-  const md = "A sentence mentioning [^x] with no definition.";
+  assert.deepEqual(d.emptyDefinitions, ["a"]);
-  assert.equal(hasLegacyFootnoteDefinition(md), false);
+  assert.match(d.warnings.join("\n"), /empty text/);
-  assert.deepEqual(footnoteWarningsField(md), {});
 });
 
-test("legacy syntax inside a code fence is ignored (fence-aware)", () => {
+test("duplicate definition id is reported (first-wins)", () => {
+  const md = ["See[^d].", "", "[^d]: first", "[^d]: second"].join("\n");
+  const d = analyzeFootnotes(md);
+  assert.deepEqual(d.duplicateDefinitions, ["d"]);
+  assert.match(d.warnings.join("\n"), /defined more than once/);
+});
+
+test("reference inside a GFM table row is reported (heuristic)", () => {
+  const md = [
+    "| Col |",
+    "| --- |",
+    "| cell[^t] |",
+    "",
+    "[^t]: table note",
+  ].join("\n");
+  const d = analyzeFootnotes(md);
+  assert.deepEqual(d.referencesInTables, ["t"]);
+  assert.match(d.warnings.join("\n"), /table/);
+  // It is defined, so it is NOT also dangling.
+  assert.deepEqual(d.danglingReferences, []);
+});
+
+test("footnote syntax inside a code fence is ignored", () => {
   const md = [
     "Intro.",
     "",
@@ -48,22 +67,40 @@ test("legacy syntax inside a code fence is ignored (fence-aware)", () => {
     "[^demo]: not a real definition",
     "```",
     "",
-    "Outro with an inline note.^[real]",
+    "Outro[^a].",
+    "",
+    "[^a]: real",
   ].join("\n");
-  assert.equal(hasLegacyFootnoteDefinition(md), false);
+  const d = analyzeFootnotes(md);
-  assert.deepEqual(footnoteWarningsField(md), {});
+  // `[^demo]` lives only in the fenced block, so it is neither a reference nor a
+  // dangling one, and `[^demo]:` is not counted as a definition.
+  assert.deepEqual(d.danglingReferences, []);
+  assert.deepEqual(d.duplicateDefinitions, []);
+  assert.deepEqual(d.warnings, []);
 });
 
-test("a legacy definition OUTSIDE a fence still warns even with a fenced sample", () => {
+test("a reference that only appears inside a definition's text is not dangling", () => {
-  const md = [
+  // `[^b]` is referenced from within [^a]'s text and has its own definition.
-    "```",
+  const md = ["See[^a].", "", "[^a]: see also [^b]", "[^b]: the other"].join(
-    "[^demo]: example inside a fence",
+    "\n",
-    "```",
+  );
-    "",
+  const d = analyzeFootnotes(md);
-    "See[^a].",
+  assert.deepEqual(d.danglingReferences, []);
-    "",
+});
-    "[^a]: real definition outside the fence",
+
-  ].join("\n");
+test("multiple problem classes accumulate distinct warnings", () => {
-  assert.equal(hasLegacyFootnoteDefinition(md), true);
+  const md = [
-  assert.equal(footnoteWarningsField(md).footnoteWarnings.length, 1);
+    "Ref[^x] and[^dup].",
+    "",
+    "[^dup]: one",
+    "[^dup]: two",
+    "[^empty]:",
+  ].join("\n");
+  const d = analyzeFootnotes(md);
+  // x has no definition; dup is defined twice; empty is empty AND has no ref.
+  assert.ok(d.danglingReferences.includes("x"));
+  assert.deepEqual(d.duplicateDefinitions, ["dup"]);
+  assert.deepEqual(d.emptyDefinitions, ["empty"]);
+  // One warning line per problem class present.
+  assert.ok(d.warnings.length >= 3);
 });

packages/mcp/test/unit/footnote-canonicalize.test.mjs

@@ -5,7 +5,7 @@ import { canonicalizeFootnotes } from "../../build/lib/footnote-canonicalize.js"
 import {
   footnoteContentKey,
   generateFootnoteId,
-} from "@docmost/prosemirror-markdown";
+} from "../../build/lib/footnote-authoring.js";
 import { insertInlineFootnote } from "../../build/lib/transforms.js";
 import { markdownToProseMirrorCanonical } from "../../build/lib/collaboration.js";
 

packages/mcp/test/unit/footnote-warnings-import.test.mjs

@@ -1,37 +1,39 @@
 import { test } from "node:test";
 import assert from "node:assert/strict";
 
-import { footnoteWarningsField } from "../../build/lib/footnote-analyze.js";
+import {
+  analyzeFootnotes,
+  footnoteWarningsField,
+} from "../../build/lib/footnote-analyze.js";
 import {
   serializeDocmostMarkdown,
   parseDocmostMarkdown,
 } from "../../build/lib/markdown-document.js";
 
-// Pins the footnoteWarnings PLUMBING contract (#169 review; reduced in #414): the
+// Pins the footnoteWarnings PLUMBING contract (#169 review): the field is
-// field is present only when legacy reference-style `[^id]:` syntax is used and
+// present only on problems and omitted on clean input, AND `import_page_markdown`
-// omitted otherwise, AND `import_page_markdown` analyzes the BODY (after the
+// analyzes the BODY (after the docmost:meta / docmost:comments blocks) — so a
-// docmost:meta / docmost:comments blocks) — so a footnote-like token inside those
+// footnote-like token inside those JSON blocks never warns, while a real marker
-// JSON blocks never warns, while a real definition in the body does.
+// in the body does. importPageMarkdown does exactly
-// importPageMarkdown does exactly `footnoteWarningsField(parseDocmostMarkdown(full).body)`
+// `footnoteWarningsField(parseDocmostMarkdown(full).body)` over a collab socket
-// over a collab socket this harness does not stand up, so we test the same pure
+// this harness does not stand up, so we test the same pure composition directly.
-// composition directly.
 
-test("footnoteWarningsField is present on legacy syntax and omitted on the inline form", () => {
+test("footnoteWarningsField is present on problems and omitted on clean input", () => {
-  const legacy = footnoteWarningsField("See[^a].\n\n[^a]: defined");
+  const problem = footnoteWarningsField("See[^missing].\n\n[^a]: defined");
-  assert.ok(Array.isArray(legacy.footnoteWarnings));
+  assert.ok(Array.isArray(problem.footnoteWarnings));
-  assert.match(legacy.footnoteWarnings.join("\n"), /reference-style footnotes/i);
+  assert.match(problem.footnoteWarnings.join("\n"), /no matching definition/);
 
-  const inline = footnoteWarningsField("A note.^[the body] reused.^[the body]");
+  const clean = footnoteWarningsField("A[^a] and reuse[^a].\n\n[^a]: fine");
-  assert.deepEqual(inline, {}); // no key at all on inline-footnote input
+  assert.deepEqual(clean, {}); // no key at all on clean input
 });
 
 test("import analyzes the BODY only — tokens inside meta/comments never warn", () => {
-  // meta + comments JSON carry `[^metaonly]:` / `[^commentonly]:`-looking text;
+  // meta + comments JSON carry `[^metaonly]` / `[^commentonly]`-looking text; the
-  // the BODY has a genuine legacy `[^bodyref]:` definition.
+  // BODY has a genuinely dangling `[^bodyref]`.
   const full = serializeDocmostMarkdown(
-    { pageId: "p1", note: "front-matter mentions [^metaonly]: in text" },
+    { pageId: "p1", note: "front-matter mentions [^metaonly] in text" },
-    "Body with a legacy[^bodyref] marker.\n\n[^bodyref]: the definition",
+    "Body with a dangling[^bodyref] marker.",
-    [{ id: "c1", content: "a comment that says [^commentonly]: text" }],
+    [{ id: "c1", content: "a comment that says [^commentonly]" }],
   );
 
   const { body } = parseDocmostMarkdown(full);
@@ -40,19 +42,20 @@ test("import analyzes the BODY only — tokens inside meta/comments never warn",
   assert.ok(!body.includes("[^commentonly]"));
 
   const field = footnoteWarningsField(body);
-  // ONLY the body's legacy definition triggers the advisory.
+  const joined = (field.footnoteWarnings ?? []).join("\n");
-  assert.ok(Array.isArray(field.footnoteWarnings));
+  // ONLY the body's dangling reference is flagged.
-  assert.match(field.footnoteWarnings.join("\n"), /reference-style footnotes/i);
+  assert.match(joined, /\[\^bodyref\]/);
+  assert.ok(!joined.includes("metaonly"));
+  assert.ok(!joined.includes("commentonly"));
 
-  // The meta/comments tokens, analyzed on their own, would NOT have warned in a
+  // Cross-check against analyzeFootnotes directly (same composition the importer uses).
-  // way that leaks here — the field is computed over the body only.
+  assert.deepEqual(analyzeFootnotes(body).danglingReferences, ["bodyref"]);
-  assert.deepEqual(footnoteWarningsField("front-matter mentions text"), {});
 });
 
-test("import on an inline-footnote body yields no footnoteWarnings field", () => {
+test("import on a clean body yields no footnoteWarnings field", () => {
   const full = serializeDocmostMarkdown(
     { pageId: "p1" },
-    "Clean body.^[a note] reusing.^[a note]",
+    "Clean body[^a] reusing[^a].\n\n[^a]: ok",
     [],
   );
   const { body } = parseDocmostMarkdown(full);

packages/mcp/test/unit/node-ops-table.test.mjs

@@ -5,7 +5,7 @@ import {
   insertNodeRelative,
   sanitizeForYjs,
   findUnstorableAttr,
-} from "@docmost/prosemirror-markdown";
+} from "../../build/lib/node-ops.js";
 
 // ProseMirror builders. Blocks carry a stable id in attrs.id.
 const textNode = (text) => ({ type: "text", text });

packages/mcp/test/unit/node-ops.test.mjs

@@ -7,7 +7,7 @@ import {
   deleteNodeById,
   assertUnambiguousMatch,
   insertNodeRelative,
-} from "@docmost/prosemirror-markdown";
+} from "../../build/lib/node-ops.js";
 
 // ProseMirror builders. Blocks carry a stable id in attrs.id.
 const textNode = (text) => ({ type: "text", text });

packages/mcp/test/unit/outline.test.mjs

@@ -1,7 +1,7 @@
 import { test } from "node:test";
 import assert from "node:assert/strict";
 
-import { buildOutline, getNodeByRef } from "@docmost/prosemirror-markdown";
+import { buildOutline, getNodeByRef } from "../../build/lib/node-ops.js";
 
 // Helpers to build the small fixture doc.
 const textNode = (text) => ({ type: "text", text });

packages/mcp/test/unit/page-search.test.mjs

@@ -2,7 +2,7 @@ import { test } from "node:test";
 import assert from "node:assert/strict";
 
 import { searchInDoc } from "../../build/lib/page-search.js";
-import { getNodeByRef } from "@docmost/prosemirror-markdown";
+import { getNodeByRef } from "../../build/lib/node-ops.js";
 
 // ---------------------------------------------------------------------------
 // Document builders. Mirror the Docmost ProseMirror shape: paragraphs/headings

packages/mcp/test/unit/parse-node-arg.test.mjs

@@ -1,7 +1,7 @@
 import { test } from "node:test";
 import assert from "node:assert/strict";
 
-import { parseNodeArg } from "@docmost/prosemirror-markdown";
+import { parseNodeArg } from "../../build/lib/parse-node-arg.js";
 
 test("parseNodeArg passes an object through unchanged", () => {
   const obj = { type: "paragraph", content: [] };

packages/mcp/test/unit/table-ops.test.mjs

@@ -6,7 +6,7 @@ import {
   insertTableRow,
   deleteTableRow,
   updateTableCell,
-} from "@docmost/prosemirror-markdown";
+} from "../../build/lib/node-ops.js";
 
 // ---------------------------------------------------------------------------
 // Builders. Tables/rows/cells carry NO attrs.id — only the paragraph inside a

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

@@ -59,89 +59,3 @@ export function splitFootnoteParagraphs(encoded: string): string[] {
   paragraphs.push(current);
   return paragraphs;
 }
-
-// ---------------------------------------------------------------------------
-// Inline-authoring helpers (#414: moved here from the mcp `footnote-authoring.ts`
-// fork so the dedup convention — content-key + definition factory + id gen —
-// has ONE home next to the importer that shares the convention). Used by the
-// mcp author-inline tool (`insertInlineFootnote` in transforms.ts).
-// ---------------------------------------------------------------------------
-
-const FOOTNOTE_DEFINITION_NAME = "footnoteDefinition";
-
-function cloneJson<T>(v: T): T {
-  if (typeof structuredClone === "function") return structuredClone(v);
-  return JSON.parse(JSON.stringify(v)) as T;
-}
-
-/**
- * Normalized content key for de-duplicating footnote DEFINITIONS by their text.
- *
- * Two definitions with the same key are the SAME footnote — so the inline
- * authoring tool reuses one id (one number, one definition, several references)
- * instead of minting a second definition. Key = plaintext (whitespace-collapsed,
- * trimmed) PLUS a signature of the inline mark types in order, so two notes that
- * read the same but differ in formatting (one bold, one plain) are NOT merged.
- * Conservative: only an exact match merges.
- */
-export function footnoteContentKey(defNode: any): string {
-  const parts: string[] = [];
-  const visit = (n: any): void => {
-    if (!n || typeof n !== "object") return;
-    if (n.type === "text" && typeof n.text === "string") {
-      const marks = Array.isArray(n.marks)
-        ? n.marks.map((m: any) => m?.type).filter(Boolean).sort().join(",")
-        : "";
-      parts.push(`${n.text}${marks}`);
-    }
-    if (Array.isArray(n.content)) for (const c of n.content) visit(c);
-  };
-  visit(defNode);
-  // Collapse the assembled text's whitespace and trim, keeping the mark
-  // signature attached so formatting differences still distinguish notes.
-  return parts
-    .join("")
-    .replace(/[ \t\r\n]+/g, " ")
-    .trim();
-}
-
-/**
- * Build a footnoteDefinition node from inline ProseMirror nodes, keyed by id.
- */
-export function makeFootnoteDefinition(id: string, inlineNodes: any[]): any {
-  const content = Array.isArray(inlineNodes) ? cloneJson(inlineNodes) : [];
-  return {
-    type: FOOTNOTE_DEFINITION_NAME,
-    attrs: { id },
-    content: [{ type: "paragraph", content }],
-  };
-}
-
-/**
- * Generate a uuidv7-style id (time-ordered), matching editor-ext's
- * `generateFootnoteId`. Used for a genuinely-new inline footnote id.
- */
-export function generateFootnoteId(): string {
-  const now = Date.now();
-  const timeHex = now.toString(16).padStart(12, "0");
-  const rand = (length: number) => {
-    let s = "";
-    for (let i = 0; i < length; i++)
-      s += Math.floor(Math.random() * 16).toString(16);
-    return s;
-  };
-  const versioned = "7" + rand(3);
-  const variantNibble = (8 + Math.floor(Math.random() * 4)).toString(16);
-  const variant = variantNibble + rand(3);
-  return (
-    timeHex.slice(0, 8) +
-    "-" +
-    timeHex.slice(8, 12) +
-    "-" +
-    versioned +
-    "-" +
-    variant +
-    "-" +
-    rand(12)
-  );
-}

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

@@ -44,35 +44,3 @@ export {
   docsCanonicallyEqual,
 } from "./canonicalize.js";
 export { parsePageFile, serializePageFile } from "./page-file.js";
-
-// Pure, network-free helpers for manipulating a ProseMirror/TipTap document
-// tree by node id (#414: the single canonical copy, formerly forked into mcp).
-// Consumed by `@docmost/mcp` (patch/insert/delete node, table tools, outline).
-export {
-  blockPlainText,
-  buildOutline,
-  getNodeByRef,
-  replaceNodeById,
-  deleteNodeById,
-  sanitizeForYjs,
-  findUnstorableAttr,
-  insertNodeRelative,
-  readTable,
-  insertTableRow,
-  deleteTableRow,
-  updateTableCell,
-  assertUnambiguousMatch,
-} from "./node-ops.js";
-export type { OutlineEntry } from "./node-ops.js";
-
-// Normalize a ProseMirror node arg that the model may have serialized as a JSON
-// string (#414: single copy shared by mcp and the CommonJS server app).
-export { parseNodeArg } from "./parse-node-arg.js";
-
-// Inline-footnote authoring convention (#414: single copy, formerly the mcp
-// `footnote-authoring.ts` fork), shared with the importer's `assembleFootnotes`.
-export {
-  footnoteContentKey,
-  makeFootnoteDefinition,
-  generateFootnoteId,
-} from "./footnote.js";

packages/prosemirror-markdown/src/lib/node-ops.ts

@@ -14,8 +14,6 @@
  * `content`, non-object nodes, and absent `attrs` are tolerated.
  */
 
-import { stripInlineMarkdown } from "./text-normalize.js";
-
 /** Deep-clone a JSON-serializable value without mutating the original. */
 function clone<T>(value: T): T {
   if (typeof structuredClone === "function") {
@@ -99,15 +97,12 @@ export function buildOutline(doc: any): OutlineEntry[] {
     const entry: OutlineEntry = {
       index: i,
       type,
-      id:
+      id: isObject(block) && isObject(block.attrs) ? block.attrs.id ?? null : null,
-        isObject(block) && isObject(block.attrs)
-          ? (block.attrs.id ?? null)
-          : null,
       firstText: truncate(blockPlainText(block), 100),
     };
 
     if (type === "heading") {
-      entry.level = isObject(block.attrs) ? (block.attrs.level ?? null) : null;
+      entry.level = isObject(block.attrs) ? block.attrs.level ?? null : null;
     } else if (type === "table") {
       const headerRow = block.content?.[0]?.content ?? [];
       entry.rows = block.content?.length ?? 0;
@@ -252,33 +247,6 @@ export function deleteNodeById(
   return { doc: out, deleted };
 }
 
-/**
- * Throw a clear, model-actionable error when a node-id write op did NOT match
- * exactly one node (#159). `count === 0` -> "no node found"; `count > 1` ->
- * "ambiguous, refused" — Docmost duplicates block ids on copy/paste, so a write
- * by id could clobber/remove EVERY duplicate. The caller skips the write for any
- * `count !== 1` (the transform returns null), so this only REPORTS; nothing was
- * changed. No-op for the unambiguous single-match case.
- */
-export function assertUnambiguousMatch(
-  op: "patch_node" | "delete_node",
-  verb: "replace" | "delete",
-  count: number,
-  nodeId: string,
-  pageId: string,
-): void {
-  if (count === 0) {
-    throw new Error(
-      `${op}: no node with id "${nodeId}" found on page ${pageId}`,
-    );
-  }
-  if (count > 1) {
-    throw new Error(
-      `${op}: id "${nodeId}" is ambiguous — ${count} nodes on page ${pageId} share it (block ids are duplicated on copy/paste). Refusing to ${verb} all of them; nothing was changed. Re-target with a more specific anchor.`,
-    );
-  }
-}
-
 /**
  * Deep-clone `doc` and strip every node/mark attribute whose value is strictly
  * `undefined`, so the result is safe to hand to Yjs (which throws an opaque
@@ -396,31 +364,6 @@ const REQUIRED_CONTAINER: Record<string, string> = {
   tableHeader: "tableRow",
 };
 
-/**
- * Find the index of the first TOP-LEVEL block whose plain text includes the
- * anchor, with a markdown-stripping FALLBACK. Returns -1 when none matches.
- *
- * Two passes preserve "exact wins globally":
- *  - Pass 1: first block containing the verbatim `anchorText`.
- *  - Pass 2 (only if pass 1 found nothing): first block containing the
- *    markdown-stripped anchor, when stripping actually changed it.
- */
-function findAnchorTextIndex(content: any[], anchorText: string): number {
-  if (!Array.isArray(content)) return -1;
-  // Pass 1: exact.
-  for (let i = 0; i < content.length; i++) {
-    if (blockPlainText(content[i]).includes(anchorText)) return i;
-  }
-  // Pass 2: markdown-stripped fallback.
-  const a = stripInlineMarkdown(anchorText);
-  if (a !== anchorText && a.length > 0) {
-    for (let i = 0; i < content.length; i++) {
-      if (blockPlainText(content[i]).includes(a)) return i;
-    }
-  }
-  return -1;
-}
-
 /**
  * Locate an anchor and return its ancestor chain (from `doc` down to and
  * including the matched node). Each chain entry is `{ node, index }` where
@@ -456,14 +399,14 @@ function findAnchorChain(
   }
 
   // By text: only top-level blocks are scanned (same rule as the JSON path).
-  // Exact match wins; a markdown-stripped fallback is tried only on a miss.
   if (opts.anchorText != null && Array.isArray(doc.content)) {
-    const i = findAnchorTextIndex(doc.content, opts.anchorText);
+    for (let i = 0; i < doc.content.length; i++) {
-    if (i !== -1) {
+      if (blockPlainText(doc.content[i]).includes(opts.anchorText)) {
-      return [
+        return [
-        { node: doc, index: -1 },
+          { node: doc, index: -1 },
-        { node: doc.content[i], index: i },
+          { node: doc.content[i], index: i },
-      ];
+        ];
+      }
     }
   }
 
@@ -597,13 +540,13 @@ export function insertNodeRelative(
     return { doc: out, inserted };
   }
 
-  // Resolve by text: only top-level doc.content blocks are scanned. Exact
+  // Resolve by text: only top-level doc.content blocks are scanned.
-  // match wins; a markdown-stripped fallback is tried only on a miss.
   if (opts.anchorText != null && isObject(out) && Array.isArray(out.content)) {
-    const i = findAnchorTextIndex(out.content, opts.anchorText);
+    for (let i = 0; i < out.content.length; i++) {
-    if (i !== -1) {
+      if (blockPlainText(out.content[i]).includes(opts.anchorText)) {
-      out.content.splice(i + offset, 0, fresh);
+        out.content.splice(i + offset, 0, fresh);
-      return { doc: out, inserted: true };
+        return { doc: out, inserted: true };
+      }
     }
   }
 
@@ -674,8 +617,7 @@ function locateTable(
   if (!isObject(rootClone)) return null;
 
   // "#<n>": index into the top-level content array; must be a table.
-  const indexMatch =
+  const indexMatch = typeof tableRef === "string" ? tableRef.match(/^#(\d+)$/) : null;
-    typeof tableRef === "string" ? tableRef.match(/^#(\d+)$/) : null;
   if (indexMatch) {
     const index = Number(indexMatch[1]);
     const block = Array.isArray(rootClone.content)
@@ -775,7 +717,7 @@ export function readTable(
         : undefined;
       const id =
         isObject(firstPara) && isObject(firstPara.attrs)
-          ? (firstPara.attrs.id ?? null)
+          ? firstPara.attrs.id ?? null
           : null;
       rowIds.push(id);
     }
@@ -809,17 +751,14 @@ export function insertTableRow(
   if (!Array.isArray(table.content)) table.content = [];
   const rows = table.content.length;
   const headerRow = table.content[0];
-  const headerCells = Array.isArray(headerRow?.content)
+  const headerCells = Array.isArray(headerRow?.content) ? headerRow.content : [];
-    ? headerRow.content
-    : [];
 
   // Column count is the WIDEST existing row, so the guard below stays
   // meaningful for ragged tables and the new row matches the table's width.
   // Fall back to the supplied cell count only when the table has no rows.
   let colCount = 0;
   for (const r of table.content) {
-    if (isObject(r) && Array.isArray(r.content))
+    if (isObject(r) && Array.isArray(r.content)) colCount = Math.max(colCount, r.content.length);
-      colCount = Math.max(colCount, r.content.length);
   }
   if (colCount === 0) colCount = Array.isArray(cells) ? cells.length : 0;
 
@@ -832,10 +771,7 @@ export function insertTableRow(
   // Resolve the landing index up front so the cell-type decision and the splice
   // below agree: a valid integer in [0, rows] splices there, else we append.
   const landingIndex =
-    typeof index === "number" &&
+    typeof index === "number" && Number.isInteger(index) && index >= 0 && index <= rows
-    Number.isInteger(index) &&
-    index >= 0 &&
-    index <= rows
       ? index
       : rows;
 
@@ -854,8 +790,7 @@ export function insertTableRow(
     // A row landing at index 0 becomes the new header row, so inherit the
     // current header cell's type per column (Docmost uses "tableHeader" there);
     // every other position is a plain data cell.
-    const cellType =
+    const cellType = landingIndex === 0 ? headerCells[i]?.type ?? "tableCell" : "tableCell";
-      landingIndex === 0 ? (headerCells[i]?.type ?? "tableCell") : "tableCell";
     newCells.push({
       type: cellType,
       attrs,
@@ -927,10 +862,9 @@ export function updateTableCell(
   const rowNodes = Array.isArray(table.content) ? table.content : [];
   const rows = rowNodes.length;
   const rowNode = rowNodes[row];
-  const cols =
+  const cols = isObject(rowNode) && Array.isArray(rowNode.content)
-    isObject(rowNode) && Array.isArray(rowNode.content)
+    ? rowNode.content.length
-      ? rowNode.content.length
+    : 0;
-      : 0;
 
   if (
     !Number.isInteger(row) ||

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

@@ -1,99 +0,0 @@
-/**
- * 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.
- *
- * 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.
- *
- * 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. */
-const MAX_PASSES = 8;
-
-/**
- * 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 the two balanced/link passes: 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, "$1");
-    }
-    if (out === before) break;
-  }
-  return out;
-}
-
-/**
- * Conservatively strip inline markdown from a locator string.
- *
- * Deterministic, order-fixed steps:
- *  1. Links/images: `[text](url)` -> `text`, `![alt](src)` -> `alt`.
- *  2. Balanced inline wrappers (strong before emphasis, code, strikethrough),
- *     applied repeatedly until stable for nested cases.
- *  3. Trim leading/trailing decoration only: whitespace, leftover marker chars
- *     (`* _ ~ \``) and emoji. Letters/digits and sentence punctuation (`.`/`,`
- *     etc.) are NEVER trimmed.
- *
- * If the result is empty (e.g. the input was only markers like `***`), the
- * ORIGINAL string is returned so a locator can never normalize down to "" and
- * match everything.
- */
-export function stripInlineMarkdown(s: string): string {
-  if (typeof s !== "string" || s.length === 0) return s;
-
-  // 1 + 2. Shared link/image and balanced-wrapper passes.
-  let out = stripWrappersAndLinks(s);
-
-  // 3. Trim leading/trailing decoration: whitespace, leftover markdown markers,
-  //    and emoji (Extended_Pictographic plus the VS16 / ZWJ joiners, plus the
-  //    regional-indicator range U+1F1E6–U+1F1FF for flag emoji, which are NOT
-  //    Extended_Pictographic). The `u` flag enables the Unicode property escape.
-  //    Anchored runs only — interior text and sentence punctuation are untouched.
-  const DECORATION =
-    "[\\s*_~\\x60\\p{Extended_Pictographic}\\u{1F1E6}-\\u{1F1FF}\\u{FE0F}\\u{200D}]+";
-  out = out
-    .replace(new RegExp("^" + DECORATION, "u"), "")
-    .replace(new RegExp(DECORATION + "$", "u"), "");
-
-  // 4. Never normalize a locator down to nothing.
-  if (out.length === 0) return s;
-
-  return out;
-}