@ai-sdk/harness-codex 1.0.125 → 1.0.128

package/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @ai-sdk/harness-codex
 
+## 1.0.128
+
+### Patch Changes
+
+- af9597b: Compile packages for ES2022 runtime target
+- Updated dependencies [af9597b]
+- Updated dependencies [31742b9]
+- Updated dependencies [bc49f78]
+  - @ai-sdk/harness@1.0.126
+  - @ai-sdk/provider-utils@5.0.49
+
+## 1.0.127
+
+### Patch Changes
+
+- d17ead7: feat(harness-codex): migrate adapter to use Codex app server, unlocking more granular tool call emissions, built-in tool filtering, and mid-turn steering
+- Updated dependencies [be877ff]
+  - @ai-sdk/provider-utils@5.0.48
+  - @ai-sdk/harness@1.0.125
+
+## 1.0.126
+
+### Patch Changes
+
+- Updated dependencies [40231b6]
+  - @ai-sdk/harness@1.0.124
+
 ## 1.0.125
 
 ### Patch Changes

package/README.md

@@ -1,6 +1,6 @@
 # AI SDK - Codex Harness
 
-`HarnessV1` adapter backed by [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk), which drives the `codex` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied loopback port.
+`HarnessV1` adapter backed by the [Codex CLI](https://www.npmjs.com/package/@openai/codex). The adapter runs Codex app-server inside a sandbox and communicates with it over JSON-RPC. A bridge process connects app-server to the host over a WebSocket on a sandbox-proxied loopback port.
 
 ## Setup
 
@@ -8,14 +8,14 @@
 npm i @ai-sdk/harness-codex @ai-sdk/harness @ai-sdk/sandbox-vercel
 ```
 
-The bridge installs `@openai/codex-sdk` (and the `codex` CLI it depends on) inside the sandbox the first time the session starts.
+The bridge installs the Codex CLI inside the sandbox the first time the session starts.
 
 ## Usage
 
 ```ts
 import { HarnessAgent } from '@ai-sdk/harness/agent';
 import { createCodex } from '@ai-sdk/harness-codex';
-import { createVercelSandbox } from '@ai-sdk/sandbox-vercel';
+import { createVercelNetworkSandboxSession } from '@ai-sdk/sandbox-vercel';
 import { tool } from 'ai';
 import { z } from 'zod/v4';
 
@@ -26,10 +26,6 @@ const agent = new HarnessAgent({
     },
   }),
   id: 'demo',
-  sandbox: createVercelSandbox({
-    runtime: 'node24',
-    ports: [4000],
-  }),
   tools: {
     deploy: tool({
       description: 'Deploy a service.',
@@ -60,13 +56,14 @@ const agent = new HarnessAgent({
       { name: 'haiku-mode', description: 'Answer in haikus.', content: '...' },
     ],
   }),
-  sandbox: createVercelSandbox({
-    runtime: 'node24',
-    ports: [4000],
-  }),
 });
 
-const session = await agent.createSession();
+const sandboxSession = await createVercelNetworkSandboxSession({
+  runtime: 'node24',
+  ports: [4000],
+  template: await agent.getSandboxTemplate(),
+});
+const session = await agent.createSession({ sandboxSession });
 
 try {
   const result = await agent.generate({
@@ -76,7 +73,9 @@ try {
   console.log(result.text);
 } finally {
   await session.destroy();
+  await sandboxSession.destroy();
 }
 ```
 
-The adapter requires a `HarnessV1SandboxProvider` whose handles expose at least one port — `@ai-sdk/sandbox-vercel` is the supported choice today. The agent calls `provider.createSession()` when a session starts. Use `session.detach()` to park the bridge and sandbox, `session.stop()` to save state and stop the sandbox, or `session.destroy()` to clean up without keeping resume state.
+The adapter needs a sandbox session with an exposed port. The caller ends the
+harness session and sandbox separately.