smooai-smooth-operator — the native, fully-async Python client for the smooth-operator service.
Streaming agent turns, HITL resume, pydantic v2 models. One of five native SDKs over one schema-driven WebSocket protocol.
What is this?
The native async Python client for the smooth-operator WebSocket protocol. It connects to a running smooth-operator service (create a session, send a message, stream the agent's events back) — not the agent engine itself. The pydantic v2 models in smooth_operator._generated are generated from the language-neutral JSON Schemas in spec/ (and committed), using pydantic discriminated unions so events deserialize to the right concrete type. The wire is camelCase; you work in idiomatic snake_case.
30-second quickstart
uv add smooai-smooth-operator # or: pip install smooai-smooth-operator
The PyPI distribution name is smooai-smooth-operator (the import package stays
smooth_operator) — don't pip install smooth-operator from the public index until
the SmooAI release lands.
import asyncio
from smooth_operator import SmoothAgentClient
async def main():
client = SmoothAgentClient(url="ws://127.0.0.1:8787/ws")
await client.connect()
session = await client.create_conversation_session(agent_id=agent_id, user_name="Alice")
turn = client.send_message(session_id=session.session_id, message="How long is your return window?")
final = await turn # the terminal eventual_response
print(final.data.payload.message_id)
asyncio.run(main())
(Point url at your own smooth-operator-server or the hosted endpoint.)
Watch it stream
send_message returns a turn you can async for over for live events and await for the authoritative terminal response.
turn = client.send_message(session_id=session.session_id, message="Where is my order?")
async for event in turn:
if event.type == "stream_chunk":
print(f"\n ↳ node: {event.node}") # workflow node boundary
elif event.type == "stream_token":
print(event.token, end="", flush=True) # tokens, live
elif event.type == "write_confirmation_required":
# HITL: approve, and the resumed stream flows back into this same turn.
await client.confirm_tool_action(
session_id=session.session_id, request_id=turn.request_id, approved=True
)
final = await turn # the terminal eventual_response
print("\nmessageId:", final.data.payload.message_id)
%%{init: {'theme':'base','themeVariables':{'background':'#020618','primaryColor':'#0b1426','primaryTextColor':'#e6edf6','primaryBorderColor':'#2b3a52','lineColor':'#7c8aa0','actorBkg':'#0b1426','actorBorder':'#2b3a52','actorTextColor':'#e6edf6','signalColor':'#7c8aa0','signalTextColor':'#e6edf6','noteBkgColor':'#f49f0a','noteTextColor':'#1a0f00','noteBorderColor':'#ff6b6c','fontFamily':'ui-sans-serif, system-ui, sans-serif'}}}%%
sequenceDiagram
participant App
participant C as SmoothAgentClient
participant S as Service
App->>C: send_message(...)
C->>S: { action: send_message }
S-->>C: immediate_response (202)
S-->>C: stream_token / stream_chunk …
S-->>C: eventual_response (200)
C-->>App: async-for yields events · await resolves final
camelCase wire, snake_case Python
The JSON wire form is camelCase (requestId, sessionId); the pydantic models use snake_case attributes with camelCase aliases and populate_by_name = True. So you construct/access with session.session_id, and model_dump(by_alias=True) emits the camelCase wire form.
Polyglot — one spec, five clients
%%{init: {'theme':'base','themeVariables':{'background':'#020618','primaryColor':'#0b1426','primaryTextColor':'#e6edf6','primaryBorderColor':'#2b3a52','lineColor':'#7c8aa0','secondaryColor':'#0b1426','tertiaryColor':'#0b1426','fontFamily':'ui-sans-serif, system-ui, sans-serif','clusterBkg':'#0b1426','clusterBorder':'#22304a'}}}%%
flowchart LR
SPEC["spec/ (JSON Schema)"] --> PY["Python<br/>smooth_operator"]
SPEC --> TS["TypeScript"]
SPEC --> GO["Go"]
SPEC --> NET[".NET (+ MEAI IChatClient facade)"]
SPEC --> RS["Rust"]
Test-driven by default
Nothing here is vibe-coded — it's verified against a real LLM gateway.
%%{init: {'theme':'base','themeVariables':{'background':'#020618','primaryColor':'#0b1426','primaryTextColor':'#e6edf6','primaryBorderColor':'#2b3a52','lineColor':'#7c8aa0','secondaryColor':'#0b1426','tertiaryColor':'#0b1426','fontFamily':'ui-sans-serif, system-ui, sans-serif','clusterBkg':'#0b1426','clusterBorder':'#22304a'}}}%%
flowchart TD
J["🎯 LLM-as-judge quality evals (Rust harness)"]
E["🌐 Live cross-language E2E — this client boots the real server + drives a real claude-haiku-4-5 turn"]
C["🧪 Conformance fixtures (shared across all 5 clients)"]
U["⚡ Unit tests (discriminated-union parsing, alias round-trip, correlation)"]
J --> E --> C --> U
26 tests. The live cross-language E2E boots a real smooth-operator-server subprocess (KB seeded) and drives a real claude-haiku-4-5 turn over WebSocket: ≥1 streamed event, a knowledge-grounded "17", per-session memory.
A real bug the live E2E caught (mocks masked it): agentId is UUID-typed in spec/, so pydantic rejected a bare string the lenient Go/TS clients accepted — surfacing a real cross-client string-vs-UUID alignment gap. A mock fixture using a valid UUID would have hidden it.
The proof story: an LLM-as-judge scored a multi-turn answer 1/5 (the runtime forgot turn 1's context); the failing eval drove a per-session-memory fix; it now scores 5/5 — a regression a substring test would have missed. See docs/EVALS.md.
Live tests are gated, never silently skipped — SMOOTH_AGENT_E2E=1 + SMOOAI_GATEWAY_KEY to run; skip cleanly otherwise.
uv run pytest # no creds
SMOOTH_AGENT_E2E=1 uv run pytest -m e2e # live cross-language E2E
Develop & regenerate
uv sync
uv run python -c "import smooth_operator"
uv run python scripts/generate.py # regen pydantic models from ../spec via datamodel-code-generator
Smoo-powered or bring-your-own
Point url at your own self-hosted smooth-operator-server — same protocol, same client.
🧩 Part of Smoo AI
smooai-smooth-operator is built and open-sourced by Smoo AI — the AI-powered business platform with AI built into every product. It's the Python member of the polyglot SDK set (TypeScript · Python · Go · .NET · Rust) for the smooth-operator service.
- 🌐 The service — smooth-operator (protocol, server, the five clients, AWS/k8s deploy)
- 🧰 More open source from Smoo AI — smoo.ai/open-source
- ☁️ Hosted by Smoo — smooth-operator runs the Smoo AI platform in production
🔗 Links
- 📦 PyPI —
smooai-smooth-operator - 🛰️ Protocol —
docs/PROTOCOL.md - 🧪 Evals —
docs/EVALS.md - 💬 Issues — github.com/SmooAI/smooth-operator/issues
📄 License
MIT © 2026 Smoo AI. See LICENSE.
Built by Smoo AI — AI built into every product.
1 maintainer
Metadata
1 maintainer
Release files for smooai-smooth-operator 1.49.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| smooai_smooth_operator-1.49.1.tar.gz | 296.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| smooai_smooth_operator-1.49.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 327.6 kB
Release files / smooai_smooth_operator-1.49.1.tar.gz
| Download URL | smooai_smooth_operator-1.49.1.tar.gz |
|---|---|
| Size | 296.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c956fd85d74042c2f600a67c19f6d0f3b30cc5cd0efad3c12e60544618c41132
|
|
BLAKE2b-256 checksum How to use checksums |
e96a4feb580eca38f0ec3cf0f69c990fbb214b6b7c72577964286e4acf6a1e82
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Release files / smooai_smooth_operator-1.49.1-py3-none-any.whl
| Download URL | smooai_smooth_operator-1.49.1-py3-none-any.whl |
|---|---|
| Size | 31.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
157a0a34c82b4f1f60f1035ae66d8ce3476265e05dd7bcfddf82b0a7621c5088
|
|
BLAKE2b-256 checksum How to use checksums |
5ead40e54a2aef3254bab7ae03eb3da2231c82bc015fb2095ae246ac8ddbc9a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
