### 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>
## Background
Currently, the `RunHooks` lifecycle (`on_tool_start`, `on_tool_end`)
exposes the `Tool` and `ToolContext`, but does not include the actual
arguments passed to the tool call.
resolves https://github.com/openai/openai-agents-python/issues/939
## Solution
This implementation is inspired by [PR
#1598](https://github.com/openai/openai-agents-python/pull/1598).
* Add a new `tool_arguments` field to `ToolContext` and populate it via
from_agent_context with tool_call.arguments.
* Update `lifecycle_example.py` to demonstrate tool_arguments in hooks
* Unlike the proposal in [PR
#253](https://github.com/openai/openai-agents-python/issues/253), this
solution is not expected to introduce breaking changes, making it easier
to adopt.
This is a follow-up to pr #1043 The original changes were reverted due
to missing updates in RealtimeSession, which caused runtime test
failures.
This PR:
- Reapplies the `tool_name` and `tool_call_id` additions to
`ToolContext`.
- Updates `RealtimeSession._handle_tool_call` to instantiate
`ToolContext` with `tool_name=event.name` and
`tool_call_id=event.call_id`.
- Adjusts tests as needed so that all 533 tests (including old-version
Python 3.9) pass cleanly.
Closes#1030
---------
Co-authored-by: Kazuhiro Sera <seratch@openai.com>
This adds a `tool_name` field to `ToolContext`, which gets passed into
the `on_invoke_tool` handler. Helpful for scenarios where we dynamically
register multiple tools that all share a single generic handler e.g.in
multi-agent setups.
As such, by including the name of the tool that was invoked, the handler
can now easily branch logic or route requests accordingly.
Resolves #1030
All tests pass. and here is a script to test it out
https://gist.github.com/vrtnis/ca354244f7a5ecd9a73c0a2d34cb194b
---------
Co-authored-by: Kazuhiro Sera <seratch@openai.com>
This PR fixes issue:
https://github.com/openai/openai-agents-python/issues/559
By adding the tool_call_id to the RunContextWrapper prior to calling
tools. This gives the ability to access the tool_call_id in the
implementation of the tool.
Summary:
1. Use <2 for MCP version so it doesn't break if the MCP sdk upgrades.
2. Test the func schema extraction logic.
3. Fix the logic to get the version nuber of the framework
Test Plan:
unit tests
Kazuhiro Sera