mirror of
https://github.com/harivansh-afk/sandbox-agent.git
synced 2026-04-16 17:01:06 +00:00
feat: add interactive permission prompt UI to Inspector
Add permission request handling to the Inspector UI so users can Allow, Always Allow, or Reject tool calls that require permissions instead of having them auto-cancelled. Wires up SDK onPermissionRequest/respondPermission through App → ChatPanel → ChatMessages with proper toolCallId-to-pendingId mapping. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
1720b6d0ba
commit
e8ffd78ac0
27 changed files with 812 additions and 563 deletions
|
|
@ -96,14 +96,6 @@ const session = await sdk.createSession({
|
|||
});
|
||||
```
|
||||
|
||||
```ts
|
||||
// Claude permission modes are exposed as a first-class helper.
|
||||
const claude = await sdk.createSession({
|
||||
agent: "claude",
|
||||
permissionMode: "default",
|
||||
});
|
||||
```
|
||||
|
||||
```ts
|
||||
// After creation
|
||||
await session.setModel("gpt-5.2-codex");
|
||||
|
|
@ -111,10 +103,6 @@ await session.setMode("full-access");
|
|||
await session.setThoughtLevel("medium");
|
||||
```
|
||||
|
||||
```ts
|
||||
await claude.setPermissionMode("acceptEdits");
|
||||
```
|
||||
|
||||
Query available modes:
|
||||
|
||||
```ts
|
||||
|
|
@ -139,26 +127,41 @@ await session.setConfigOption("some-agent-option", "value");
|
|||
|
||||
## Handle permission requests
|
||||
|
||||
For agents that use ACP `session/request_permission` (for example Claude in `default` mode), register a permission listener and reply with `once`, `always`, or `reject`:
|
||||
For agents that request tool-use permissions, register a permission listener and reply with `once`, `always`, or `reject`:
|
||||
|
||||
```ts
|
||||
const claude = await sdk.createSession({
|
||||
const session = await sdk.createSession({
|
||||
agent: "claude",
|
||||
permissionMode: "default",
|
||||
mode: "default",
|
||||
});
|
||||
|
||||
claude.onPermissionRequest((request) => {
|
||||
session.onPermissionRequest((request) => {
|
||||
console.log(request.toolCall.title, request.availableReplies);
|
||||
void claude.replyPermission(request.id, "once");
|
||||
void session.respondPermission(request.id, "once");
|
||||
});
|
||||
|
||||
await claude.prompt([
|
||||
await session.prompt([
|
||||
{ type: "text", text: "Create ./permission-example.txt with the text hello." },
|
||||
]);
|
||||
```
|
||||
|
||||
|
||||
### Auto-approving permissions
|
||||
|
||||
To auto-approve all permission requests, respond with `"once"` or `"always"` in your listener:
|
||||
|
||||
```ts
|
||||
session.onPermissionRequest((request) => {
|
||||
void session.respondPermission(request.id, "always");
|
||||
});
|
||||
```
|
||||
|
||||
See `examples/permissions/src/index.ts` for a complete permissions example that works with Claude and Codex.
|
||||
|
||||
<Info>
|
||||
Some agents like Claude allow configuring permission behavior through modes (e.g. `bypassPermissions`, `acceptEdits`). We recommend leaving the mode as `default` and handling permission decisions explicitly in `onPermissionRequest` instead.
|
||||
</Info>
|
||||
|
||||
## Destroy a session
|
||||
|
||||
```ts
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue