@cloudflare/codemode v0.1.0: modular, runtime-agnostic architecture
The codemode package has been rewritten as a modular, runtime-agnostic SDK that enables LLMs to write and execute code orchestrating tools more efficiently. It now features a new Executor interface and DynamicWorkerExecutor with network isolation, console capture, and configurable timeouts.
The @cloudflare/codemode ↗ package has been rewritten into a modular, runtime-agnostic SDK.
Code Mode ↗ enables LLMs to write and execute code that orchestrates your tools, instead of calling them one at a time. This can (and does) yield significant token savings, reduces context window pressure and improves overall model performance on a task.
The new Executor interface is runtime agnostic and comes with a prebuilt DynamicWorkerExecutor to run generated code in a Dynamic Worker Loader.
Breaking changes
- Removed
experimental_codemode()andCodeModeProxy— the package no longer owns an LLM call or model choice - New import path:
createCodeTool()is now exported from@cloudflare/codemode/ai
New features
createCodeTool()— Returns a standard AI SDKToolto use in your AI agents.Executorinterface — Minimalexecute(code, fns)contract. Implement for any code sandboxing primitive or runtime.
DynamicWorkerExecutor
Runs code in a Dynamic Worker. It comes with the following features:
- Network isolation —
fetch()andconnect()blocked by default (globalOutbound: null) when usingDynamicWorkerExecutor - Console capture —
console.log/warn/errorcaptured and returned inExecuteResult.logs - Execution timeout — Configurable via
timeoutoption (default 30s)
Usage
import { createCodeTool } from "@cloudflare/codemode/ai";
import { DynamicWorkerExecutor } from "@cloudflare/codemode";
import { streamText } from "ai";
const executor = new DynamicWorkerExecutor({ loader: env.LOADER });
const codemode = createCodeTool({ tools: myTools, executor });
const result = streamText({
model,
tools: { codemode },
messages,
});import { createCodeTool } from "@cloudflare/codemode/ai";
import { DynamicWorkerExecutor } from "@cloudflare/codemode";
import { streamText } from "ai";
const executor = new DynamicWorkerExecutor({ loader: env.LOADER });
const codemode = createCodeTool({ tools: myTools, executor });
const result = streamText({
model,
tools: { codemode },
messages,
});
Wrangler configuration
{
"worker_loaders": [{ "binding": "LOADER" }],
}[[worker_loaders]]
binding = "LOADER"
See the Code Mode documentation for full API reference and examples.
Upgrade
npm i @cloudflare/codemode@latestSource: original entry ↗
More from Cloudflare
Follow Cloudflare to get its new changes in your feed and email digest.
Cloudflare One Client for macOS 2026.8.2100.0
GA release for macOS Cloudflare One Client with improved split tunnel handling that no longer briefly blocks traffic during reconnects, support for non-RFC 1918 local IPv4 networks, faster connects with lower memory use, and numerous reliability fixes across DNS, reauthentication, and client stability.
Cloudflare One Client for Windows 2026.8.2100.0
This GA release improves split tunnel reliability, adds support for non-RFC 1918 local networks, optimizes connection performance with faster reconnections and lower memory usage, and includes numerous bug fixes for DNS, registration, and network handling. The client now features a service recovery mechanism that automatically restarts on system unlock and better handles large hosts files without blocking traffic.
Cloudflare One Client for Linux 2026.8.2100.0
New GA release for Linux with improved split tunnel handling that no longer briefly blocks traffic during reconnects, support for non-RFC 1918 local IPv4 networks, faster tunnel reconnections, and lower memory usage. Includes numerous stability and reliability fixes for DNS, reconnection behavior, and crash issues.