opencode-ai-wg 1.0.0

Walzen Group fork of the Python library for the opencode API

Opencode Python API library

The Opencode Python library provides convenient access to the Opencode REST API from any Python 3.8+ application. The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx.

The client talks to a running opencode server. By default it connects to http://localhost:54321, so start opencode serve (or point the client at another host) before making requests.

It is generated with Stainless.

Documentation

The REST API documentation can be found on opencode.ai. The full API of this library can be found in api.md.

Installation

This is the Walzen-Group fork, distributed as opencode-ai-wg:

pip install opencode-ai-wg

You can also install straight from GitHub, for example to track main or a specific commit:

pip install "git+https://github.com/Walzen-Group/opencode-sdk-python.git@main"

The distribution is named opencode-ai-wg, but you still import it as opencode_ai:

from opencode_ai import Opencode

Usage

The full API of this library can be found in api.md.

from opencode_ai import Opencode

client = Opencode()

sessions = client.session.list()

The base URL defaults to http://localhost:54321. Override it with the base_url argument or the OPENCODE_BASE_URL environment variable:

from opencode_ai import Opencode

client = Opencode(base_url="http://localhost:4096")

Resources

The client exposes one namespace per area of the opencode server. Each is available as an attribute on the client (for example client.session, client.file):

Namespace	Purpose
session	Create sessions, send prompts, run shell/commands, manage messages, share and revert
event	Stream server events (SSE)
app	Application-level info and actions
find	Search files, symbols, and text in the workspace
file	Read file contents and status
config	Read the resolved opencode configuration
project	List and inspect projects
provider	List available model providers
question	List, reply to, and reject pending questions
permission	List and reply to permission requests
mcp	Inspect configured MCP servers
path	Resolve server paths
vcs	Version-control status and operations
command	List available commands
lsp	Language-server information
formatter	Configured formatters
instance	Instance details
auth	Set and remove provider credentials (auth.set, auth.remove)
sync	Synchronization operations
pty / tui	Pseudo-terminal and TUI control

The full method list for each namespace is in api.md.

Sending a prompt to a session

Create a session, then send it a message. Message content is a list of parts; a plain text prompt is a single text part:

from opencode_ai import Opencode

client = Opencode()

session = client.session.create()

response = client.session.prompt(
    session.id,
    parts=[{"type": "text", "text": "Explain what this project does."}],
)
print(response)

session.prompt accepts an optional model, agent, tools, and more. See api.md for the full parameter set.

Directory and workspace addressing

Every v1 method accepts optional directory and workspace arguments. They are sent as query parameters and tell the server which directory or workspace the request applies to, which is useful when a single server manages more than one:

sessions = client.session.list(directory="/path/to/project")

client.session.prompt(
    session_id,
    parts=[{"type": "text", "text": "Run the tests."}],
    workspace="my-workspace",
)

Async usage

Simply import AsyncOpencode instead of Opencode and use await with each API call:

import asyncio
from opencode_ai import AsyncOpencode

client = AsyncOpencode()


async def main() -> None:
    sessions = await client.session.list()


asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

With aiohttp

By default, the async client uses httpx for HTTP requests. However, for improved concurrency performance you may also use aiohttp as the HTTP backend.

You can enable this by installing the aiohttp extra:

pip install opencode-ai-wg[aiohttp]

Then you can enable it by instantiating the client with http_client=DefaultAioHttpClient():

import asyncio
from opencode_ai import DefaultAioHttpClient
from opencode_ai import AsyncOpencode


async def main() -> None:
    async with AsyncOpencode(
        http_client=DefaultAioHttpClient(),
    ) as client:
        sessions = await client.session.list()


asyncio.run(main())

Streaming responses

We provide support for streaming responses using Server Side Events (SSE).

from opencode_ai import Opencode

client = Opencode()

stream = client.event.list()
for events in stream:
    print(events)

The async client uses the exact same interface.

from opencode_ai import AsyncOpencode

client = AsyncOpencode()

stream = await client.event.list()
async for events in stream:
    print(events)

Using types

Nested request parameters are TypedDicts. Responses are Pydantic models which also provide helper methods for things like:

• Serializing back into JSON, model.to_json()
• Converting to a dictionary, model.to_dict()

Typed requests and responses provide autocomplete and documentation within your editor. If you would like to see type errors in VS Code to help catch bugs earlier, set python.analysis.typeCheckingMode to basic.

Handling errors

When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of opencode_ai.APIConnectionError is raised.

When the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of opencode_ai.APIStatusError is raised, containing status_code and response properties.

All errors inherit from opencode_ai.APIError.

import opencode_ai
from opencode_ai import Opencode

client = Opencode()

try:
    client.session.list()
except opencode_ai.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except opencode_ai.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except opencode_ai.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

Error codes are as follows:

Status Code	Error Type
400	BadRequestError
401	AuthenticationError
403	PermissionDeniedError
404	NotFoundError
422	UnprocessableEntityError
429	RateLimitError
>=500	InternalServerError
N/A	APIConnectionError

Retries

Certain errors are automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors are all retried by default.

You can use the max_retries option to configure or disable retry settings:

from opencode_ai import Opencode

# Configure the default for all requests:
client = Opencode(
    # default is 2
    max_retries=0,
)

# Or, configure per-request:
client.with_options(max_retries=5).session.list()

Timeouts

By default requests time out after 1 minute. You can configure this with a timeout option, which accepts a float or an httpx.Timeout object:

from opencode_ai import Opencode

# Configure the default for all requests:
client = Opencode(
    # 20 seconds (default is 1 minute)
    timeout=20.0,
)

# More granular control:
client = Opencode(
    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)

# Override per-request:
client.with_options(timeout=5.0).session.list()

On timeout, an APITimeoutError is thrown.

Note that requests that time out are retried twice by default.

Advanced

Logging

We use the standard library logging module.

You can enable logging by setting the environment variable OPENCODE_LOG to info.

$ export OPENCODE_LOG=info

Or to debug for more verbose logging.

How to tell whether None means null or missing

In an API response, a field may be explicitly null, or missing entirely; in either case, its value is None in this library. You can differentiate the two cases with .model_fields_set:

if response.my_field is None:
  if 'my_field' not in response.model_fields_set:
    print('Got json like {}, without a "my_field" key present at all.')
  else:
    print('Got json like {"my_field": null}.')

Accessing raw response data (e.g. headers)

The "raw" Response object can be accessed by prefixing .with_raw_response. to any HTTP method call, e.g.,

from opencode_ai import Opencode

client = Opencode()
response = client.session.with_raw_response.list()
print(response.headers.get('X-My-Header'))

session = response.parse()  # get the object that `session.list()` would have returned
print(session)

These methods return an APIResponse object.

The async client returns an AsyncAPIResponse with the same structure, the only difference being awaitable methods for reading the response content.

.with_streaming_response

The above interface eagerly reads the full response body when you make the request, which may not always be what you want.

To stream the response body, use .with_streaming_response instead, which requires a context manager and only reads the response body once you call .read(), .text(), .json(), .iter_bytes(), .iter_text(), .iter_lines() or .parse(). In the async client, these are async methods.

with client.session.with_streaming_response.list() as response:
    print(response.headers.get("X-My-Header"))

    for line in response.iter_lines():
        print(line)

The context manager is required so that the response will reliably be closed.

Making custom/undocumented requests

This library is typed for convenient access to the documented API.

If you need to access undocumented endpoints, params, or response properties, the library can still be used.

Undocumented endpoints

To make requests to undocumented endpoints, you can make requests using client.get, client.post, and other http verbs. Options on the client will be respected (such as retries) when making this request.

import httpx

response = client.post(
    "/foo",
    cast_to=httpx.Response,
    body={"my_param": True},
)

print(response.headers.get("x-foo"))

Undocumented request params

If you want to explicitly send an extra param, you can do so with the extra_query, extra_body, and extra_headers request options.

Undocumented response properties

To access undocumented response properties, you can access the extra fields like response.unknown_prop. You can also get all the extra fields on the Pydantic model as a dict with response.model_extra.

Configuring the HTTP client

You can directly override the httpx client to customize it for your use case, including:

• Support for proxies
• Custom transports
• Additional advanced functionality

import httpx
from opencode_ai import Opencode, DefaultHttpxClient

client = Opencode(
    # Or use the `OPENCODE_BASE_URL` env var
    base_url="http://my.test.server.example.com:8083",
    http_client=DefaultHttpxClient(
        proxy="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

You can also customize the client on a per-request basis by using with_options():

client.with_options(http_client=DefaultHttpxClient(...))

Managing HTTP resources

By default the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close() method if desired, or with a context manager that closes when exiting.

from opencode_ai import Opencode

with Opencode() as client:
  # make requests here
  ...

# HTTP client is now closed

Versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

1. Changes that only affect static types, without breaking runtime behavior.
2. Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
3. Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Determining the installed version

If you've upgraded to the latest version but aren't seeing any new features you were expecting then your python environment is likely still using an older version.

You can determine the version that is being used at runtime with:

import opencode_ai
print(opencode_ai.__version__)

Requirements

Python 3.8 or higher.

Contributing

See the contributing documentation.

Publishing

See the publishing guide for how to build and release opencode-ai-wg to PyPI with uv.