openai-agents-python/examples/sandbox/misc/workspace_apply_patch.py
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

78 lines
3 KiB
Python

from __future__ import annotations
import io
from pathlib import Path
from agents import ApplyPatchTool, apply_diff
from agents.editor import ApplyPatchOperation, ApplyPatchResult
from agents.sandbox import Capability, Manifest
from agents.sandbox.session.base_sandbox_session import BaseSandboxSession
from agents.tool import Tool
def _read_text(handle: io.IOBase) -> str:
payload = handle.read()
if isinstance(payload, str):
return payload
if isinstance(payload, bytes | bytearray):
return bytes(payload).decode("utf-8", errors="replace")
return str(payload)
class _SandboxWorkspaceEditor:
def __init__(self, session: BaseSandboxSession) -> None:
self._session = session
async def create_file(self, operation: ApplyPatchOperation) -> ApplyPatchResult:
target = self._resolve_path(operation.path)
content = apply_diff("", operation.diff or "", mode="create")
await self._session.mkdir(target.parent, parents=True)
await self._session.write(target, io.BytesIO(content.encode("utf-8")))
return ApplyPatchResult(output=f"Created {self._display_path(target)}")
async def update_file(self, operation: ApplyPatchOperation) -> ApplyPatchResult:
target = self._resolve_path(operation.path)
handle = await self._session.read(target)
try:
original = _read_text(handle)
finally:
handle.close()
updated = apply_diff(original, operation.diff or "")
await self._session.write(target, io.BytesIO(updated.encode("utf-8")))
return ApplyPatchResult(output=f"Updated {self._display_path(target)}")
async def delete_file(self, operation: ApplyPatchOperation) -> ApplyPatchResult:
target = self._resolve_path(operation.path)
await self._session.rm(target)
return ApplyPatchResult(output=f"Deleted {self._display_path(target)}")
def _resolve_path(self, raw_path: str) -> Path:
return self._session.normalize_path(raw_path)
def _display_path(self, path: Path) -> str:
root = Path(self._session.state.manifest.root)
return path.relative_to(root).as_posix()
class WorkspaceApplyPatchCapability(Capability):
"""Expose the hosted apply_patch tool against the active sandbox workspace."""
def __init__(self) -> None:
super().__init__(type="workspace_apply_patch")
self._session: BaseSandboxSession | None = None
def bind(self, session: BaseSandboxSession) -> None:
self._session = session
def tools(self) -> list[Tool]:
if self._session is None:
return []
return [ApplyPatchTool(editor=_SandboxWorkspaceEditor(self._session))]
async def instructions(self, manifest: Manifest) -> str | None:
_ = manifest
return (
"Use the `apply_patch` tool for workspace text edits when you need to create or "
"update files inside the sandbox. Prefer saving final outputs in the requested "
"workspace directories instead of describing edits without writing them."
)