Files
openai--openai-agents-python/examples/basic/stream_function_call_args.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

88 lines
3.4 KiB
Python

import asyncio
from typing import Annotated, Any
from openai.types.responses import ResponseFunctionCallArgumentsDeltaEvent
from agents import Agent, Runner, function_tool
@function_tool
def write_file(filename: Annotated[str, "Name of the file"], content: str) -> str:
"""Write content to a file."""
return f"File {filename} written successfully"
@function_tool
def create_config(
project_name: Annotated[str, "Project name"],
version: Annotated[str, "Project version"],
dependencies: Annotated[list[str] | None, "Dependencies (list of packages)"],
) -> str:
"""Generate a project configuration file."""
return f"Config for {project_name} v{version} created"
async def main():
"""
Demonstrates real-time streaming of function call arguments.
Function arguments are streamed incrementally as they are generated,
providing immediate feedback during parameter generation.
"""
agent = Agent(
name="CodeGenerator",
instructions="You are a helpful coding assistant. Use the provided tools to create files and configurations.",
tools=[write_file, create_config],
)
print("🚀 Function Call Arguments Streaming Demo")
result = Runner.run_streamed(
agent,
input="Create a Python web project called 'my-app' with FastAPI. Version 1.0.0, dependencies: fastapi, uvicorn",
)
# Track function calls for detailed output
function_calls: dict[Any, dict[str, Any]] = {} # call_id -> {name, arguments}
current_active_call_id = None
async for event in result.stream_events():
if event.type == "raw_response_event":
# Function call started
if event.data.type == "response.output_item.added":
if getattr(event.data.item, "type", None) == "function_call":
function_name = getattr(event.data.item, "name", "unknown")
call_id = getattr(event.data.item, "call_id", "unknown")
function_calls[call_id] = {"name": function_name, "arguments": ""}
current_active_call_id = call_id
print(f"\n📞 Function call streaming started: {function_name}()")
print("📝 Arguments building...")
# Real-time argument streaming
elif isinstance(event.data, ResponseFunctionCallArgumentsDeltaEvent):
if current_active_call_id and current_active_call_id in function_calls:
function_calls[current_active_call_id]["arguments"] += event.data.delta
print(event.data.delta, end="", flush=True)
# Function call completed
elif event.data.type == "response.output_item.done":
if hasattr(event.data.item, "call_id"):
call_id = getattr(event.data.item, "call_id", "unknown")
if call_id in function_calls:
function_info = function_calls[call_id]
print(f"\n✅ Function call streaming completed: {function_info['name']}")
print()
if current_active_call_id == call_id:
current_active_call_id = None
print("Summary of all function calls:")
for call_id, info in function_calls.items():
print(f" - #{call_id}: {info['name']}({info['arguments']})")
print(f"\nResult: {result.final_output}")
if __name__ == "__main__":
asyncio.run(main())