Run python nodes out of process, with modules of their own

User code no longer execs in the engine. A pool of persistent worker
subprocesses speaks one JSON object per line; the controller installs a
proxy as the node's function, so every execution path funnels through it
and the pipeline is untouched. A crash costs one subprocess, a per-node
timeout is a kill, and cancelling from the canvas is that same kill.

The workers run a venv of the user's own on the data volume, filled from
a pip manifest versioned beside the flows. Applying it retires the
workers and rebuilds, so a package lands without restarting the engine.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017MeiWk3Yq12n2pTvnQWYvt
This commit is contained in:
2026-08-16 21:43:36 +02:00
co-authored by Claude Fable 5
parent 979c9d3c1f
commit f300c43f3a
27 changed files with 1536 additions and 46 deletions
+11
View File
@@ -13,6 +13,7 @@ from app.core.config import settings
from app.core.db import engine
from app.flow.controller import FlowController
from app.flow.dashboards import DashboardStore
from app.flow.workers import PythonWorkerPool
from app.models import TokenPayload, User
reusable_oauth2 = OAuth2PasswordBearer(
@@ -113,6 +114,16 @@ def get_dashboard_store(request: Request) -> DashboardStore:
DashboardStoreDep = Annotated[DashboardStore, Depends(get_dashboard_store)]
def get_worker_pool(request: Request) -> PythonWorkerPool:
pool: PythonWorkerPool | None = getattr(request.app.state, "worker_pool", None)
if pool is None:
raise HTTPException(status_code=503, detail="The flow engine is not running")
return pool
WorkerPoolDep = Annotated[PythonWorkerPool, Depends(get_worker_pool)]
def get_current_active_superuser(current_user: CurrentUser) -> User:
if not current_user.is_superuser:
raise HTTPException(
+2
View File
@@ -6,6 +6,7 @@ from app.api.routes import (
flows,
login,
messages,
modules,
oauth,
private,
secrets,
@@ -23,6 +24,7 @@ api_router.include_router(secrets.router)
api_router.include_router(alerts.router)
api_router.include_router(dashboards.router)
api_router.include_router(messages.router)
api_router.include_router(modules.router)
# Always mounted so the generated SDK stays the same shape; the endpoints
# themselves refuse to work unless MCP is switched on.
api_router.include_router(oauth.router)
+13
View File
@@ -606,6 +606,19 @@ async def trigger_node(
return _flow_state(controller, name)
@router.post("/{name}/nodes/{node_id}/cancel", response_model=Message)
def cancel_node(name: str, node_id: str, controller: FlowControllerDep) -> Any:
"""Stop a node that is running right now, by killing the worker running it.
Idempotent on purpose: by the time a click reaches here the node may well
have finished, and that is the outcome that was asked for.
"""
pool = controller.workers
if pool is not None and pool.cancel(f"{name}.{node_id}"):
return Message(message=f"Stopped '{node_id}'")
return Message(message=f"'{node_id}' was not running")
@router.get("/{name}/state", response_model=FlowStatePublic)
def read_flow_state(name: str, controller: FlowControllerDep) -> Any:
"""The last value seen on every message of this flow."""
+50
View File
@@ -0,0 +1,50 @@
"""The python packages node code may import.
A manifest in the flow store, a venv on the data volume, and one button that
brings the second in line with the first. Nothing here restarts the engine:
the worker pool retires its processes, and the next node call picks up the new
packages.
"""
from typing import Any
from fastapi import APIRouter, Depends, HTTPException
from fastapi.concurrency import run_in_threadpool
from app.api.deps import FlowControllerDep, WorkerPoolDep, get_current_user
from app.flow import modules
from app.flow.schemas import ApplyRequest, ApplyResult, ModulesInfo
router = APIRouter(
prefix="/modules", tags=["modules"], dependencies=[Depends(get_current_user)]
)
@router.get("/", response_model=ModulesInfo)
async def read_modules(controller: FlowControllerDep) -> Any:
"""What node code can import, and whether it matches the manifest."""
return await run_in_threadpool(modules.info, controller.store)
@router.post("/apply", response_model=ApplyResult)
async def apply_modules(
body: ApplyRequest, controller: FlowControllerDep, pool: WorkerPoolDep
) -> Any:
"""Install exactly these requirements, then hand them to the workers.
A manifest that does not resolve changes nothing: the venv is left as it
was and the stored manifest is only written once the install succeeded.
"""
ok, output = await run_in_threadpool(modules.sync, body.requirements)
if not ok:
raise HTTPException(
status_code=400,
detail=output or "These requirements could not be installed",
)
await run_in_threadpool(controller.store.write_requirements, body.requirements)
# Retire the workers first, so the rebuild compiles every node against the
# packages that were just installed — a node that could not import one is
# the reason this was called, and it stays red until it is built again.
pool.respawn_all()
await controller.reload()
return ApplyResult(ok=True, output=output)