Files
openai--openai-agents-python/docs/stylesheets/extra.css
T
Steve Coffey 2d665c9a67 Sandbox Agents (#2889)
### Sandbox Agents

This release adds **Sandbox Agents**, a beta SDK surface for running
agents with a persistent, isolated workspace. Sandbox agents keep the
normal `Agent` and `Runner` flow, but add workspace manifests,
sandbox-native capabilities, sandbox clients, snapshots, and resume
support so agents can work over real files, run commands, edit
repositories, generate artifacts, and continue work across runs.

Key pieces:

- `SandboxAgent`: an `Agent` with sandbox defaults such as
`default_manifest`, sandbox instructions, capabilities, and `run_as`.
- `Manifest`: a fresh-workspace contract for files, directories, local
files, local directories, Git repos, environment, users, groups, and
mounts.
- `SandboxRunConfig`: per-run sandbox wiring for client creation, live
session injection, serialized session resume, manifest overrides,
snapshots, and materialization concurrency limits.
- Built-in capabilities for shell access, filesystem editing and image
inspection, skills, memory, and compaction.
- Workspace snapshots and serialized sandbox session state for
reconnecting to existing work or seeding a fresh sandbox from saved
contents.

### Sandbox clients and hosted providers

Sandbox agents now support local, containerized, and hosted execution
backends:

- `UnixLocalSandboxClient` for fast local development.
- `DockerSandboxClient` for container isolation and image parity.
- Hosted sandbox clients for Blaxel, Cloudflare, Daytona, E2B, Modal,
Runloop, and Vercel through optional extras.

The release also adds provider-specific examples and mount strategies
for common storage backends, including S3, Cloudflare R2, Google Cloud
Storage, Azure Blob Storage, and S3 Files where supported by the
selected backend.

### Sandbox memory

Adds a sandbox memory capability that lets future sandbox-agent runs
learn from prior runs. Memory stores extracted lessons in the sandbox
workspace, injects a concise summary into later runs, and uses
progressive disclosure so agents can search deeper rollout summaries
only when useful.

Memory supports:

- Read-only or generate-only modes.
- Live updates when the agent discovers stale memory.
- Multi-turn grouping through `conversation_id`, SDK `Session`,
`RunConfig.group_id`, or generated run IDs.
- Separate memory layouts for isolating memory across agents or
workflows.
- S3-backed examples for persisted memory across runs.

### Workspace mounts, snapshots, and resume

This release adds a full workspace entry and mount model for sandbox
sessions:

- Local files and directories.
- Synthetic files and directories.
- Git repository entries.
- Remote storage mounts for S3, R2, GCS, Azure Blob Storage, and S3
Files.
- Provider-specific mount strategies across Docker, Modal, Cloudflare,
Blaxel, Daytona, E2B, and Runloop.
- Portable snapshots with path normalization, symlink preservation,
mount-safe snapshotting, and remote snapshot support.
- Resume paths through runner-managed `RunState`, explicit
`SandboxSessionState`, or saved snapshots.

### Examples and tutorials

Adds a large `examples/sandbox/` suite covering:

- Local Unix and Docker sandbox runners.
- Docker mount smoke tests for S3, GCS, Azure Blob Storage, and S3
Files.
- Sandbox coding tasks with skills.
- Sandbox agents as tools and handoff patterns.
- Memory examples, including multi-agent/multi-turn memory and S3-backed
memory.
- Tax-prep and healthcare-support workflows.
- Dataroom QA and metric extraction tutorials.
- Repository code review tutorial.
- Vision website clone tutorial.
- Provider examples for Blaxel, Cloudflare, Daytona, E2B, Modal,
Runloop, Temporal, and Vercel.

### Runtime, tracing, and model plumbing

The release includes the runtime plumbing needed to make sandbox agents
work naturally inside the existing SDK:

- Runner-managed sandbox preparation, capability binding, session
lifecycle, state serialization, and resume behavior.
- Sandbox-aware `RunState` serialization.
- Unified sandbox tracing with SDK spans.
- Token usage on tracing spans.
- Runner-managed prompt cache key defaults.
- OpenAI agent registration and harness ID configuration.
- Safer redaction of sensitive MCP tool outputs when sensitive tracing
is disabled.
- Additional OpenAI client/model utilities and Chat Completions
coverage.


## Documentation & Other Changes

- docs: add Asqav to external tracing processors list.
- docs: update translated document pages.

Co-authored-by: Abdulrahman Alfozan <alfozan@openai.com>
Co-authored-by: Aditya Singh <60082699+adityasingh2400@users.noreply.github.com>
Co-authored-by: Andi Liu <andi@openai.com>
Co-authored-by: Aron <263346377+aron-cf@users.noreply.github.com>
Co-authored-by: ashwinnathan-openai <ashwinnathan@openai.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: cploujoux <cploujoux@blaxel.ai>
Co-authored-by: elainegan-openai <168589666+elainegan-openai@users.noreply.github.com>
Co-authored-by: Elias Freider <freider@users.noreply.github.com>
Co-authored-by: Erik Dunteman <erik@erikds-macbook-air.local>
Co-authored-by: Jason Liu <jasonliu@openai.com>
Co-authored-by: Jason Steving <32336750+jasonsteving99@users.noreply.github.com>
Co-authored-by: Kazuhiro Sera <seratch@openai.com>
Co-authored-by: Lovre Pešut <lovre.pesut@gmail.com>
Co-authored-by: Lucas Wang <lucas_wang@lucas-futures.com>
Co-authored-by: Matt Brockman <matt.brockman@e2b.dev>
Co-authored-by: Mish Ushakov <mishushakov@users.noreply.github.com>
Co-authored-by: Naresh <ghostwriternr@gmail.com>
Co-authored-by: nicholasclark-openai <nicholasclark@openai.com>
Co-authored-by: qiyaoq-oai <qiyaoq@openai.com>
Co-authored-by: Scott Trinh <scott@scotttrinh.com>
Co-authored-by: tode-rl <tony@runloop.ai>
Co-authored-by: Wendy Jiao <wendyjiao@openai.com>
2026-04-15 10:00:40 -07:00

272 lines
5.7 KiB
CSS

@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: normal;
font-weight: 400;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-Regular.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: italic;
font-weight: 400;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-RegularItalic.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: normal;
font-weight: 500;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-Medium.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: italic;
font-weight: 500;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-MediumItalic.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: normal;
font-weight: 600;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-Semibold.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: italic;
font-weight: 600;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-SemiboldItalic.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: normal;
font-weight: 700;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-Bold.woff2")
format("woff2");
}
@font-face {
font-display: swap;
font-family: "OpenAI Sans";
font-style: italic;
font-weight: 700;
src: url("https://cdn.openai.com/common/fonts/openai-sans/OpenAISans-BoldItalic.woff2")
format("woff2");
}
/*
Root variables that apply to all color schemes.
Material for MkDocs automatically switches data-md-color-scheme
between "default" (light) and "slate" (dark) when you use the toggles.
*/
:root {
/* Font families */
--md-text-font: "OpenAI Sans", -apple-system, system-ui, Helvetica, Arial,
sans-serif;
--md-typeface-heading: "OpenAI Sans", -apple-system, system-ui, Helvetica,
Arial, sans-serif;
/* Global color variables */
--md-default-fg-color: #212121;
--md-default-bg-color: #ffffff;
--md-primary-fg-color: #000;
--md-accent-fg-color: #000;
/* Code block theming */
--md-code-fg-color: red;
--md-code-bg-color: #f5f5f5;
/* Tables, blockquotes, etc. */
--md-table-row-border-color: #e0e0e0;
--md-admonition-bg-color: #f8f8f8;
--md-admonition-title-fg-color: #373737;
--md-default-fg-color--light: #000;
--md-typeset-a-color: #000;
--md-accent-fg-color: #000;
--md-code-fg-color: #000;
}
/* Header styling */
.md-header {
background-color: #000;
}
.md-header--shadow {
box-shadow: none;
}
.md-content .md-typeset h1 {
color: #000;
}
.md-typeset p,
.md-typeset li {
font-size: 16px;
}
.md-typeset__table p {
line-height: 1em;
}
.md-nav {
font-size: 14px;
}
.md-nav__title {
color: #000;
font-weight: 600;
}
.md-typeset h1,
.md-typeset h2,
.md-typeset h3,
.md-typeset h4 {
font-weight: 600;
}
.md-typeset h1 code {
color: #000;
padding: 0;
background-color: transparent;
}
.md-footer {
display: none;
}
.md-header__title {
margin-left: 0 !important;
}
.md-typeset .admonition,
.md-typeset details {
border: none;
outline: none;
border-radius: 8px;
overflow: hidden;
}
.md-typeset pre > code {
font-size: 14px;
}
.md-typeset__table code {
font-size: 14px;
}
.md-typeset .field-table {
overflow-x: auto;
}
.md-typeset .field-table table:not([class]) {
display: table;
table-layout: fixed;
width: 100%;
}
.md-typeset .field-table table:not([class]) th:first-child,
.md-typeset .field-table table:not([class]) td:first-child {
width: 11rem;
}
.md-typeset .field-table table:not([class]) th:nth-child(2),
.md-typeset .field-table table:not([class]) td:nth-child(2) {
width: 18rem;
}
.md-typeset .field-table table:not([class]) th:first-child code,
.md-typeset .field-table table:not([class]) td:first-child code {
white-space: nowrap;
word-break: normal;
}
/* Custom link styling */
.md-content a {
text-decoration: none;
}
.md-content a:hover {
text-decoration: underline;
}
/* Code block styling */
.md-content .md-code__content {
border-radius: 8px;
}
/* Prevent grid layout from collapsing code lines on narrow viewports. */
.md-typeset .md-code__content {
display: block;
white-space: pre;
min-width: 0;
}
.md-typeset pre > code {
white-space: pre;
}
.md-clipboard.md-icon {
color: #9e9e9e;
}
/* Reset scrollbar styling to browser default with high priority */
.md-sidebar__scrollwrap {
scrollbar-color: auto !important;
}
/* Let the docs layout use more of large viewports without becoming fully fluid. */
@media screen and (min-width: 76.25em) {
.md-grid {
max-width: clamp(76rem, 92vw, 92rem);
}
}
.sandbox-nowrap-first-column-table th:first-child,
.sandbox-nowrap-first-column-table td:first-child {
white-space: nowrap;
width: 1%;
}
.sandbox-nowrap-first-column-table td:first-child code {
word-break: normal;
white-space: nowrap;
}
.sandbox-lifecycle-diagram {
text-align: center;
}
.sandbox-lifecycle-diagram .mermaid svg {
max-height: 20rem;
max-width: 100%;
width: auto !important;
}
.sandbox-harness-image {
text-align: center;
}
.sandbox-harness-image img {
display: block;
margin: 0 auto;
max-height: 28rem;
max-width: 100%;
width: auto;
}