Fast Apply

AI agents edit files using // ... existing code ... markers instead of sending full files. Morph merges server-side at 10,500 tokens/s. Why this matters: Traditional search-replace uses 40% more tokens and takes more turns. Fast Apply is instant.

Installation

npm install @morphllm/morphsdk

Quick Start

import Anthropic from '@anthropic-ai/sdk';
import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });
const anthropic = new Anthropic();

// Tool inherits API key from MorphClient
const tool = morph.anthropic.createEditFileTool();

const response = await anthropic.messages.create({
  model: "claude-sonnet-4-5-20250929",
  max_tokens: 12000,
  tools: [tool],
  messages: [{ 
    role: "user", 
    content: "Add error handling to src/auth.ts" 
  }]
});

import OpenAI from 'openai';
import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });
const openai = new OpenAI();

// Tool inherits API key from MorphClient
const tool = morph.openai.createEditFileTool();

const response = await openai.chat.completions.create({
  model: "gpt-5-high",
  tools: [tool],
  messages: [{ 
    role: "user", 
    content: "Add error handling to src/auth.ts" 
  }]
});

OpenAI high thinking models often output in patch format—Morph handles this automatically. If you see patch-style outputs, tune your system prompt to prefer // ... existing code ... markers for better results.

import { generateText, stepCountIs } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';
import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });

// Create the tool that is compatible with the Vercel AI SDK
const editFileTool = morph.vercel.createEditFileTool();

const result = await generateText({
  model: anthropic('claude-sonnet-4-5-20250929'),
  tools: { editFile: editFileTool },
  prompt: "Add error handling to src/auth.ts",
  stopWhen: stepCountIs(5)
});

import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });

// Direct execution
const result = await morph.fastApply.execute({
  target_filepath: 'src/auth.ts',
  instructions: 'I will add null check',
  code_edit: '// ... existing code ...\nif (!user) throw new Error("Not found");\n// ... existing code ...'
});

console.log(result.success); // true
console.log(`+${result.changes.linesAdded} -${result.changes.linesRemoved}`);

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.morphllm.com/v1",
)

original_code = open("src/auth.ts").read()
code_edit = "// ... existing code ...\nif (!user) throw new Error('Not found');\n// ... existing code ..."
instruction = "I will add null check"

response = client.chat.completions.create(
    model="morph-v3-fast",
    messages=[
        {
            "role": "user",
            "content": f"<instruction>{instruction}</instruction>\n<code>{original_code}</code>\n<update>{code_edit}</update>"
        }
    ],
)

merged_code = response.choices[0].message.content

with open("src/auth.ts", "w") as f:
    f.write(merged_code)

curl -X POST "https://api.morphllm.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "morph-v3-fast",
    "messages": [
      {
        "role": "user",
        "content": "<instruction>I will add null check</instruction>\n<code>async function login(email: string, password: string) {\n  const user = await db.findUser(email);\n  return createSession(user);\n}</code>\n<update>// ... existing code ...\nif (!user) throw new Error(\"Not found\");\n// ... existing code ...</update>"
      }
    ]
  }'

The response is an OpenAI-compatible chat completion. The merged code is in choices[0].message.content.

The instructions parameter provides crucial context for ambiguous edits, helping the apply model make correct decisions and achieve near perfect accuracy. Have the parent model generate the instructions.

How It Works

Add an edit_file tool to your agent

Add the edit_file tool to your agent. Use one of the formats below.

General Prompt
JSON Tool (Claude)
Output Parsing (No Tool)

When editing files, use the edit_file tool with these parameters:
- target_filepath: Path of the file to modify
- instructions: Brief first-person description of what you're changing
- code_edit: Only the changed lines with // ... existing code ... markers

Use "// ... existing code ..." to represent unchanged code blocks. Include
just enough surrounding context to locate each edit precisely.

Example format:
// ... existing code ...
FIRST_EDIT
// ... existing code ...
SECOND_EDIT
// ... existing code ...

Rules:
- ALWAYS use "// ... existing code ..." for unchanged sections (omitting
  this marker will cause deletions)
- Include minimal context around edits only when needed for disambiguation
- Preserve exact indentation
- For deletions: show context before and after, omit the deleted lines
- Batch multiple edits to the same file in one call

Pass this tool definition directly to Claude or any model that supports JSON tool schemas.

{
  "name": "edit_file",
  "description": "Edit an existing file by showing only the changed lines. Use // ... existing code ... to represent unchanged sections. Include just enough surrounding context to locate each edit precisely. ALWAYS use the marker for unchanged sections (omitting it will cause deletions). Preserve exact indentation. For deletions, show context before and after. Batch multiple edits to the same file in one call.",
  "input_schema": {
    "type": "object",
    "properties": {
      "target_filepath": {
        "type": "string",
        "description": "Path of the file to modify"
      },
      "instructions": {
        "type": "string",
        "description": "A single sentence written in the first person describing what the agent is changing. Used to help disambiguate uncertainty in the edit."
      },
      "code_edit": {
        "type": "string",
        "description": "Specify ONLY the precise lines of code that you wish to edit. Use // ... existing code ... for unchanged sections."
      }
    },
    "required": ["target_filepath", "instructions", "code_edit"]
  }
}

If your model doesn’t support tool use, have it output edits in a structured format you parse yourself.

When editing files, output a fenced code block with the filepath as the language tag:

```src/auth.ts
// ... existing code ...
if (!user) throw new Error("Not found");
// ... existing code ...
```

Before each block, write a one-line instruction starting with "I will":
I will add a null check before creating the session.

Parse the filepath from the code fence, the instruction from the preceding line, and the code edit from the block contents. Then send all three to Morph.

Parameters:

Parameter	Type	Required	Description
`target_filepath`	string	yes	Path of the file to modify
`instructions`	string	yes	Brief first-person description of what you’re changing (helps disambiguate uncertainty in the edit)
`code_edit`	string	yes	Only the changed lines with `// ... existing code ...` markers for unchanged sections

The instructions param should be generated by the model, not hardcoded. Example: “I am adding error handling to the user auth and removing the old auth functions”

Why do I need the instructions to be generated by the model?

The instructions parameter provides crucial context for ambiguous edits, helping the apply model make correct decisions and achieve near 100% accuracy even in edge cases.

Merge with Morph Fast Apply

When the agent calls your tool, send the original file + the edit snippet to Morph’s API. It returns the merged file. Write it to disk.

What to add to your System Prompt

When editing code, use the edit_file tool. Output only the changed sections and use
`// ... existing code ...` markers to skip over unchanged code. Do not reread a file
before editing. The edit is applied semantically, so you do not need the file's exact
current contents to make a correct edit.

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.morphllm.com/v1",
});

const originalCode = await fs.readFile(toolCall.target_filepath, "utf-8");

const response = await openai.chat.completions.create({
  model: "morph-v3-fast",
  messages: [
    {
      role: "user",
      content: `<instruction>${toolCall.instructions}</instruction>\n<code>${originalCode}</code>\n<update>${toolCall.code_edit}</update>`,
    },
  ],
});

const mergedCode = response.choices[0].message.content;

Handle the Response

The merged code is in response.choices[0].message.content. Write it to the target file.

const finalCode = response.choices[0].message.content;
await fs.writeFile(toolCall.target_filepath, finalCode);

Verifying Edits (Optional but Recommended)

Pass the diff back to the agent so it can verify the changes match its intent. To save tokens, you can limit this to cases where the linter reports errors.

import { createTwoFilesPatch } from 'diff';

const udiff = createTwoFilesPatch(
  toolCall.target_filepath,
  toolCall.target_filepath,
  originalCode,
  mergedCode,
  '',
  ''
);

// Send back to agent for verification
console.log("Changes applied:", udiff);

This catches unexpected changes before they hit disk.

Direct Usage

Use without an agent:

TypeScript
Python
cURL

const result = await morph.fastApply.execute({
  target_filepath: 'src/auth.ts',
  instructions: 'I will add null check',
  code_edit: '// ... existing code ...\nif (!user) throw new Error("Not found");\n// ... existing code ...'
});

console.log(result.success); // true
console.log(`+${result.changes.linesAdded} -${result.changes.linesRemoved}`);

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.morphllm.com/v1",
)

original_code = open("src/auth.ts").read()

response = client.chat.completions.create(
    model="morph-v3-fast",
    messages=[
        {
            "role": "user",
            "content": f"<instruction>I will add null check</instruction>\n<code>{original_code}</code>\n<update>// ... existing code ...\nif (!user) throw new Error('Not found');\n// ... existing code ...</update>"
        }
    ],
)

merged_code = response.choices[0].message.content
with open("src/auth.ts", "w") as f:
    f.write(merged_code)

curl -X POST "https://api.morphllm.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "morph-v3-fast",
    "messages": [
      {
        "role": "user",
        "content": "<instruction>I will add null check</instruction>\n<code>async function login(email, password) {\n  const user = await db.findUser(email);\n  return createSession(user);\n}</code>\n<update>// ... existing code ...\nif (!user) throw new Error(\"Not found\");\n// ... existing code ...</update>"
      }
    ]
  }'

Code-in/Code-out (Sandbox Support)

Use applyEdit when you manage your own filesystem or work in sandboxes like E2B, Modal, or Daytona:

applyEdit Function
MorphClient Method
Python
cURL

import { applyEdit } from '@morphllm/morphsdk';

// Read file yourself (from sandbox, memory, etc.)
const originalCode = await sandbox.readFile('src/auth.ts');

const result = await applyEdit({
  originalCode,
  codeEdit: '// ... existing code ...\nif (!user) throw new Error("Not found");\n// ... existing code ...',
  instructions: 'Add null check',
});

if (result.success) {
  // Write file yourself
  await sandbox.writeFile('src/auth.ts', result.mergedCode);
  console.log(result.udiff);  // View the diff
}

import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });

const result = await morph.fastApply.applyEdit({
  originalCode: 'function hello() { return "world"; }',
  codeEdit: 'function hello() { return "universe"; }',
  instructions: 'Change return value'
});

console.log(result.mergedCode);
// function hello() { return "universe"; }

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.morphllm.com/v1",
)

original_code = sandbox.read_file("src/auth.ts")
code_edit = "// ... existing code ...\nif (!user) throw new Error('Not found');\n// ... existing code ..."

response = client.chat.completions.create(
    model="morph-v3-fast",
    messages=[
        {
            "role": "user",
            "content": f"<instruction>Add null check</instruction>\n<code>{original_code}</code>\n<update>{code_edit}</update>"
        }
    ],
)

merged_code = response.choices[0].message.content
sandbox.write_file("src/auth.ts", merged_code)

curl -X POST "https://api.morphllm.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "morph-v3-fast",
    "messages": [
      {
        "role": "user",
        "content": "<instruction>Add null check</instruction>\n<code>async function login(email, password) {\n  const user = await db.findUser(email);\n  return createSession(user);\n}</code>\n<update>// ... existing code ...\nif (!user) throw new Error(\"Not found\");\n// ... existing code ...</update>"
      }
    ]
  }'

Parse choices[0].message.content for the merged code, then write it back to your sandbox filesystem.

applyEdit returns mergedCode instead of writing to disk—perfect for sandbox environments where you control file I/O.

Configuration

import { MorphClient } from '@morphllm/morphsdk';

const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });

const tool = morph.openai.createEditFileTool({
  baseDir: './src',       // Default: process.cwd()
  autoWrite: true,        // Auto-write files (default: true)
  generateUdiff: true     // Return diff (default: true)
});

API

execute (file-based)
applyEdit (code-based)

Input (EditFileInput):

{
  target_filepath: string,  // Relative to baseDir
  instructions: string,     // What the model is changing
  code_edit: string         // Code with // ... existing code ...
}

Returns (EditFileResult):

{
  success: boolean,
  filepath: string,
  changes: { linesAdded, linesRemoved, linesModified },
  udiff?: string,
  error?: string
}

Input (ApplyEditInput):

{
  originalCode: string,     // Current file contents
  codeEdit: string,         // Code with // ... existing code ...
  instructions: string      // What the model is changing
}

Returns (ApplyEditResult):

{
  success: boolean,
  mergedCode?: string,      // The merged result
  changes: { linesAdded, linesRemoved, linesModified },
  udiff?: string,
  error?: string
}

All types are exported from the SDK root:

import type { 
  EditFileInput, 
  EditFileResult, 
  ApplyEditInput, 
  ApplyEditResult,
  EditChanges 
} from '@morphllm/morphsdk';

Edge / Cloudflare Workers

Use @morphllm/morphsdk/edge for edge environments (Cloudflare Workers, Vercel Edge, Deno):

import { applyEdit } from '@morphllm/morphsdk/edge';

export default {
  async fetch(request: Request, env: Env) {
    const { originalCode, codeEdit, instructions } = await request.json();

    const result = await applyEdit({
      originalCode,
      codeEdit,
      instructions,
    }, {
      morphApiKey: env.MORPH_API_KEY
    });

    return Response.json({
      success: result.success,
      mergedCode: result.mergedCode,
      udiff: result.udiff
    });
  }
};

The edge entry point has zero Node.js dependencies. It exports applyEdit, generateUdiff, countChanges, and callMorphAPI.

Error Handling

if (!result.success) {
  console.error(result.error);
  // "File not found" | "Invalid filepath" | "API error"
}

Get Started

Products

API Reference

Integrations

Installation

Quick Start

How It Works

Direct Usage

Code-in/Code-out (Sandbox Support)

Configuration

API

Edge / Cloudflare Workers

Error Handling

Get Started

Products

API Reference

Integrations

​Installation

​Quick Start

​How It Works

​Direct Usage

​Code-in/Code-out (Sandbox Support)

​Configuration

​API

​Edge / Cloudflare Workers

​Error Handling

Installation

Quick Start

How It Works

Direct Usage

Code-in/Code-out (Sandbox Support)

Configuration

API

Edge / Cloudflare Workers

Error Handling