Skip to main content

bma-executor-sdk (Python)

PyPI

asyncio executor (ExecutorClient), harness (Harness) and agent ends of the BMA Executor Protocol bma.executor.v1.1, the counterpart of the Go executor module. Protocol types are TypedDicts generated into bma_executor_sdk/generated.py from the contract in contracts/bma/executor, so messages are plain JSON dicts.

Version 0.4.5 (tag executor-python/v0.4.5), see CHANGELOG
Protocol bma.executor.v1.1 (contract 1.1.0, lock.json)
Python 3.10 or newer; depends on httpx and websockets
Integration guide docs/executor (中文)
pip install bma-executor-sdk==0.4.5

The REST / façade client is the separate package bma-sdk.

Executor quick start

import asyncio, os
from bma_executor_sdk import ExecutorClient

async def main() -> None:
    client = ExecutorClient(
        environment_key=os.environ["BMA_ENVIRONMENT_KEY"],
        environment_id=os.environ["BMA_ENVIRONMENT_ID"],
        executor={"name": "my-executor", "os": "linux", "arch": "arm64", "version": "0.1.0"},
    )

    async def on_tool_call(call):
        return {"session_id": call["session_id"], "tool_call_id": call["tool_call_id"],
                "outcome": "succeeded", "is_error": False, "content": [{"type": "text", "text": "ok"}]}

    client.on_tool_call(on_tool_call)
    await client.start()
    await asyncio.Event().wait()

asyncio.run(main())

A complete version that runs bash and stops the process on cancellation is examples/executor_minimal.py; set BMA_HARNESS_URL (ws://… or unix:///path.sock) to connect it to a local harness instead of BMA.

Behavior matches the Go SDK:

  • tool.cancel cancels the handler's task and reports outcome: "canceled"; duplicate tool.call ids run once.
  • tool.result retries -32009 / -32004 / retryable errors and hands a lost result to on_tool_result_lost.
  • Reconnect resumes with resume.executor_id / active_sessions; close codes 1008, 4002, 4003 and 4004 stop the client (4001 and 4005 reconnect).
  • Call session_ready after setup and session_ended after cleanup. on_request(method, handler) serves process.*, terminal.* or skill.install yourself; there is no execution Core in Python.

Harness quick start

from bma_executor_sdk import Harness

harness = Harness(authenticate=authenticate)  # authenticate(ConnectRequest) -> Principal; omit only in-process or on a private socket
server = await harness.serve("127.0.0.1", 0)   # or await harness.serve_unix(path)

executor = await harness.wait_executor()
session = await executor.assign_session({"session_id": "ses_1"})
await session.ready()
result = await session.call_tool({"tool": "bash", "input": {"command": "ls"}})
mcp = await session.mcp("echo")  # raw MCP JSON-RPC
await session.stop("done")

Semantics match the Go Harness: call_tool is idempotent by tool_call_id; sessions and pending calls survive a reconnect within the lease; lease expiry fails pending calls with ToolOutcomeUnknownError.

Transports

Chosen by the channel URL of the token source:

Transport Executor Harness
WebSocket (ws://, wss://) default await harness.serve(host, port)
WebSocket over a Unix domain socket (unix:///path.sock) token_source=static_token("unix:///path.sock", token) await harness.serve_unix(path)
In process dialer=harness.inprocess_dialer() —

The executor-listens local socket and Windows named pipes are not implemented in Python (use the Go or TypeScript SDK). See local connection.

Agent executors

client.serve_agent(handler, capability) serves the agent capability; handler implements open_turn, run_turn and close_session (async; cancellation is task cancellation), and run_turn uses turn.emit, await turn.delta(...), turn.inputs (an asyncio.Queue) and turn.request_interaction. The harness side is Harness(agent=platform) with an AgentPlatform. See agent capability.

Go ↔ Python

Go (bmaexecutor) Python (bma_executor_sdk)
NewClient(Options{...}) ExecutorClient(environment_id=..., executor=..., ...)
Options.TokenSource, StaticToken(url, token) token_source=, static_token(url, token)
Client.Start / Stop / State / ExecutorID / ConnectionID / ActiveSessions start() / stop(reason) / state / executor_id / connection_id / active_sessions
OnToolCall / OnSessionAssign / OnSessionStop / OnDrain / OnRequest / OnNotification on_tool_call / on_session_assign / on_session_stop / on_drain / on_request / on_notification
Call / Notify / ReportToolResult / SessionReady / SessionEnded / OpenMCPChannel call / notify / report_tool_result / session_ready / session_ended / open_mcp_channel
ServeAgent(handler, AgentCapability) serve_agent(handler, capability)
AgentHandler.OpenTurn / RunTurn / CloseSession open_turn / run_turn / close_session
AgentTurn.Emit / EmitWithID / NewEventID / Delta / Flush / Inputs() / RequestInteraction / CancelInteraction emit / emit_with_id / new_event_id / await delta / await flush / inputs / request_interaction / cancel_interaction
NewHarness(HarnessOptions{...}), http.Handler Harness(...), await serve(host, port) / serve_unix(path) / inprocess_dialer()
HarnessOptions.Authenticate(*http.Request) (Principal, error) authenticate(ConnectRequest) -> Principal (raise to refuse)
Harness.Executors / WaitExecutor executors() / wait_executor()
Executor.AssignSession / Drain / Capabilities / Protocol assign_session / drain / capabilities / protocol
Executor.StartTurn / SendTurnInput / CancelTurn / CloseAgentSession / RespondInteraction / AgentCapability start_turn / send_turn_input / cancel_turn / close_agent_session / respond_interaction / agent_capability()
Session.Ready / CallTool / CancelTool / Stop / MCP / Done / EndReason ready() / call_tool / cancel_tool / stop / mcp / wait_ended(), ended / end_reason
AgentPlatform AgentPlatform (Protocol: acked_sequence, agent_event, agent_delta, interaction_requested, interaction_canceled)
ErrNotConnected / ErrClientStopped / ErrSessionEnded / ErrToolOutcomeUnknown / ErrAssignRejected / *RPCError NotConnectedError / ClientStoppedError / SessionEndedError / ToolOutcomeUnknownError / AssignRejectedError / RPCError
Core, NewProcessCapability, ListenUnixSocket, Harness.DialExecutor not provided

Examples

Run from examples after uv sync (or pip install bma-executor-sdk):

Example What it shows
executor_minimal.py executor answering bash calls, against BMA or a local harness
harness_loopback.py brain and hand in one process, in-process or --unix PATH
agent_minimal.py agent capability with an in-memory platform

Tests

uv sync && uv run pytest -q

tests/test_executor_interop.py runs the Python executor against the Go harness (WebSocket and Unix socket) and the Python harness against the Go executor; it needs Go.

Metadata

Release files for bma-executor-sdk 0.4.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for bma-executor-sdk 0.4.5
File Size Uploaded Provenance Actions
bma_executor_sdk-0.4.5.tar.gz 49.6 kB With provenance Details for bma_executor_sdk-0.4.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for bma-executor-sdk 0.4.5
File Interpreter ABI Platform Actions
bma_executor_sdk-0.4.5-py3-none-any.whl Python 3 none any Details for bma_executor_sdk-0.4.5-py3-none-any.whl

Total release size: 92.3 kB

Release files / bma_executor_sdk-0.4.5.tar.gz

Download URL bma_executor_sdk-0.4.5.tar.gz
Size 49.6 kB
Tags Source
SHA-256 checksum
How to use checksums
ec4ad63774be01659695a449f050f2849de5242d95ced9f8493935a519fe9938
BLAKE2b-256 checksum
How to use checksums
47c7debb52584de618a65423e5a633456acd0c0c973d5bf10623e07394f508a5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

Release files / bma_executor_sdk-0.4.5-py3-none-any.whl

Download URL bma_executor_sdk-0.4.5-py3-none-any.whl
Size 42.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
440d2248d9e08399a329df96cfdb872889453c8e3d5657a1b4c1e6bc61eb9707
BLAKE2b-256 checksum
How to use checksums
b97a922c97cbb886187839e8d9bd2211b5b9460316c6f664418a1d2f00107b4f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

Security for bma-executor-sdk 0.4.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for bma_executor_sdk-0.4.5.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 31, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page