feat(server): add document write tools for mcp (#14245)

## Summary

This PR adds write capabilities to AFFiNE's MCP (Model Context Protocol)
integration, enabling external tools (Claude, GPT, etc.) to create and
modify documents programmatically.

**New MCP Tools:**
- `create_document` - Create new documents from markdown content
- `update_document` - Update document content using structural diffing
for minimal changes (preserves document history and enables real-time
collaboration)

**Implementation:**
- `markdown_to_ydoc.rs` - Converts markdown to AFFiNE-compatible y-octo
binary format
- `markdown_utils.rs` - Shared markdown parsing utilities (used by both
ydoc-to-md and md-to-ydoc)
- `update_ydoc.rs` - Structural diffing implementation for updating
existing documents
- `DocWriter` service - TypeScript service for document operations
- Exposes `markdownToDocBinary` and `updateDocBinary` via napi bindings

**Supported Markdown Elements:**
- Headings (H1-H6)
- Paragraphs
- Bullet lists and numbered lists
- Code blocks (with language detection)
- Blockquotes
- Horizontal dividers
- Todo items (checkboxes)

**y-octo Changes:**
This PR reverts the y-octo sync (ca2462f, a5b60cf) which introduced a
concurrency bug causing hangs when creating documents with many nested
block structures. It also ports the improved `get_node_index` binary
search fix from upstream that prevents divide-by-zero panics when
decoding documents.

## Test Results 

### Unit Tests (47/47 passing)

| Test Suite | Tests | Status |
|------------|-------|--------|
| markdown_to_ydoc | 16/16 |  Pass |
| markdown_utils | 11/11 |  Pass |
| update_ydoc | 13/13 |  Pass |
| delta_markdown | 2/2 |  Pass |
| affine (doc parser) | 5/5 |  Pass |

### End-to-End MCP Testing 

Tested against local AFFiNE server with real MCP client requests:

| Tool | Result | Notes |
|------|--------|-------|
| `tools/list` |  Pass | Returns all 5 tools with correct schemas |
| `create_document` |  Pass | Successfully created test documents |
| `update_document` |  Pass | Successfully updated documents with
structural diffing |
| `read_document` |  Pass | Existing tool, works correctly |
| `keyword_search` |  Pass | Existing tool, works correctly |

**E2E Test Details:**
- Started local AFFiNE server with PostgreSQL, Redis, and Manticore
- Created test user and workspace via seed/GraphQL
- Verified MCP endpoint at `/api/workspaces/:workspaceId/mcp`
- Tested JSON-RPC calls with proper SSE streaming
- Confirmed documents are stored and indexed correctly (verified via
server logs)

## Test Plan
- [x] All Rust unit tests pass (47 tests)
- [x] Native bindings build successfully (release mode)
- [x] Document creation via MCP works end-to-end
- [x] Document update via MCP works end-to-end
- [x] CodeRabbit feedback addressed
- [ ] Integration testing with Claude/GPT MCP clients

Closes #14161

---

**Requested by:** @realies  
**Key guidance from:** @darkskygit (use y-octo instead of yjs for memory
efficiency)

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Create documents from Markdown: generate new documents directly from
Markdown content with automatic title extraction
* Update documents with Markdown: modify existing documents using
Markdown as the source with automatic diff calculation for efficient
updates
* Copilot integration: new tools for document creation and updates
through Copilot's interface

<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
realies
2026-01-16 14:57:24 +02:00
committed by GitHub
parent 2c5559ed0b
commit 0da91e406e
14 changed files with 2585 additions and 4 deletions

View File

@@ -4,6 +4,20 @@ export declare class Tokenizer {
count(content: string, allowedSpecial?: Array<string> | undefined | null): number
}
/**
* Adds a document ID to the workspace root doc's meta.pages array.
* This registers the document in the workspace so it appears in the UI.
*
* # Arguments
* * `root_doc_bin` - The current root doc binary (workspaceId doc)
* * `doc_id` - The document ID to add
* * `title` - Optional title for the document
*
* # Returns
* A Buffer containing the y-octo update binary to apply to the root doc
*/
export declare function addDocToRootDoc(rootDocBin: Buffer, docId: string, title?: string | undefined | null): Buffer
export const AFFINE_PRO_LICENSE_AES_KEY: string | undefined | null
export const AFFINE_PRO_PUBLIC_KEY: string | undefined | null
@@ -19,6 +33,18 @@ export declare function getMime(input: Uint8Array): string
export declare function htmlSanitize(input: string): string
/**
* Converts markdown content to AFFiNE-compatible y-octo document binary.
*
* # Arguments
* * `markdown` - The markdown content to convert
* * `doc_id` - The document ID to use for the y-octo doc
*
* # Returns
* A Buffer containing the y-octo document update binary
*/
export declare function markdownToDocBinary(markdown: string, docId: string): Buffer
/**
* Merge updates in form like `Y.applyUpdate(doc, update)` way and return the
* result binary.
@@ -77,4 +103,18 @@ export declare function parseWorkspaceDoc(docBin: Buffer): NativeWorkspaceDocCon
export declare function readAllDocIdsFromRootDoc(docBin: Buffer, includeTrash?: boolean | undefined | null): Array<string>
/**
* Updates an existing document with new markdown content.
* Uses structural and text-level diffing to apply minimal changes.
*
* # Arguments
* * `existing_binary` - The current document binary
* * `new_markdown` - The new markdown content to apply
* * `doc_id` - The document ID
*
* # Returns
* A Buffer containing only the delta (changes) as a y-octo update binary
*/
export declare function updateDocWithMarkdown(existingBinary: Buffer, newMarkdown: string, docId: string): Buffer
export declare function verifyChallengeResponse(response: string, bits: number, resource: string): Promise<boolean>

View File

@@ -132,3 +132,52 @@ pub fn read_all_doc_ids_from_root_doc(doc_bin: Buffer, include_trash: Option<boo
.map_err(|e| Error::new(Status::GenericFailure, e.to_string()))?;
Ok(result)
}
/// Converts markdown content to AFFiNE-compatible y-octo document binary.
///
/// # Arguments
/// * `markdown` - The markdown content to convert
/// * `doc_id` - The document ID to use for the y-octo doc
///
/// # Returns
/// A Buffer containing the y-octo document update binary
#[napi]
pub fn markdown_to_doc_binary(markdown: String, doc_id: String) -> Result<Buffer> {
let result =
doc_parser::markdown_to_ydoc(&markdown, &doc_id).map_err(|e| Error::new(Status::GenericFailure, e.to_string()))?;
Ok(Buffer::from(result))
}
/// Updates an existing document with new markdown content.
/// Uses structural and text-level diffing to apply minimal changes.
///
/// # Arguments
/// * `existing_binary` - The current document binary
/// * `new_markdown` - The new markdown content to apply
/// * `doc_id` - The document ID
///
/// # Returns
/// A Buffer containing only the delta (changes) as a y-octo update binary
#[napi]
pub fn update_doc_with_markdown(existing_binary: Buffer, new_markdown: String, doc_id: String) -> Result<Buffer> {
let result = doc_parser::update_ydoc(&existing_binary, &new_markdown, &doc_id)
.map_err(|e| Error::new(Status::GenericFailure, e.to_string()))?;
Ok(Buffer::from(result))
}
/// Adds a document ID to the workspace root doc's meta.pages array.
/// This registers the document in the workspace so it appears in the UI.
///
/// # Arguments
/// * `root_doc_bin` - The current root doc binary (workspaceId doc)
/// * `doc_id` - The document ID to add
/// * `title` - Optional title for the document
///
/// # Returns
/// A Buffer containing the y-octo update binary to apply to the root doc
#[napi]
pub fn add_doc_to_root_doc(root_doc_bin: Buffer, doc_id: String, title: Option<String>) -> Result<Buffer> {
let result = doc_parser::add_doc_to_root_doc(root_doc_bin.into(), &doc_id, title.as_deref())
.map_err(|e| Error::new(Status::GenericFailure, e.to_string()))?;
Ok(Buffer::from(result))
}