Skip to content

docs: align Vercel S3 mount documentation with implementation #3988

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ShawnSiao wants to merge 2 commits into from
Closed

docs: align Vercel S3 mount documentation with implementation #3988

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0929093
docs: document Vercel S3 mounts
ShawnSiao Jul 27, 2026
20562b5
docs: clarify Vercel S3 mount constraints
ShawnSiao Jul 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 44 additions & 2 deletions docs/sandbox/clients.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ Hosted sandbox clients expose provider-specific mount strategies. Choose the bac
| `DaytonaSandboxClient` | Supports rclone-backed cloud storage mounts with `DaytonaCloudBucketMountStrategy`; use it with `S3Mount`, `GCSMount`, `R2Mount`, `AzureBlobMount`, and `BoxMount`. |
| `E2BSandboxClient` | Supports rclone-backed cloud storage mounts with `E2BCloudBucketMountStrategy`; use it with `S3Mount`, `GCSMount`, `R2Mount`, `AzureBlobMount`, and `BoxMount`. |
| `RunloopSandboxClient` | Supports rclone-backed cloud storage mounts with `RunloopCloudBucketMountStrategy`; use it with `S3Mount`, `GCSMount`, `R2Mount`, `AzureBlobMount`, and `BoxMount`. |
| `VercelSandboxClient` | No hosted-specific mount strategy is currently exposed. Use manifest files, repos, or other workspace inputs instead. |
| `VercelSandboxClient` | Supports create-time `S3Mount` entries through `VercelCloudBucketMountStrategy`. |

</div>

Expand All @@ -130,8 +130,50 @@ The table below summarizes which remote storage entries each backend can mount d
| `DaytonaSandboxClient` | ✓ | ✓ | ✓ | ✓ | ✓ | - |
| `E2BSandboxClient` | ✓ | ✓ | ✓ | ✓ | ✓ | - |
| `RunloopSandboxClient` | ✓ | ✓ | ✓ | ✓ | ✓ | - |
| `VercelSandboxClient` | - | - | - | - | - | - |
| `VercelSandboxClient` | ✓ | - | - | - | - | - |

</div>

### Vercel S3 mounts

Vercel supports create-time `S3Mount` entries through
`VercelCloudBucketMountStrategy`. Declare the mount in the manifest passed to
`VercelSandboxClient.create`. The mount topology is fixed for the lifetime of
the sandbox session.

```python
import os

from agents.extensions.sandbox.vercel import (
VercelCloudBucketMountStrategy,
VercelSandboxClient,
VercelSandboxClientOptions,
)
from agents.sandbox import Manifest
from agents.sandbox.entries import S3Mount

manifest = Manifest(
root="/workspace",
entries={
"data": S3Mount(
bucket="my-data-bucket",
region="us-east-1",
access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
ephemeral=True,
mount_strategy=VercelCloudBucketMountStrategy(),
)
},
)

session = await VercelSandboxClient().create(
manifest=manifest,
options=VercelSandboxClientOptions(allow_s3_credential_exposure=True),
)
```

- Inline credentials are exposed to code running in the sandbox. Set `allow_s3_credential_exposure=True` only for credentials scoped to that sandbox and bucket.
- Credentials are removed from serialized session state. Sessions containing Vercel S3 mounts cannot be resumed; create a new sandbox from a trusted manifest instead.
- Workspace persistence temporarily unmounts S3 buckets, so persisted workspace data excludes remote bucket contents. Native snapshot hydration is not supported while S3 mounts are active.

For more runnable examples, browse [examples/sandbox/](https://github.com/openai/openai-agents-python/tree/main/examples/sandbox) for local, coding, memory, handoff, and agent-composition patterns, and [examples/sandbox/extensions/](https://github.com/openai/openai-agents-python/tree/main/examples/sandbox/extensions) for hosted sandbox clients.