Files
robertvoy-ComfyUI-Distributed/tests/test_image_list_integration_gaps.py
T
Robert Wojciechowski 7ed60b93ca feat: dynamically distribute image lists across direct workers (#98)
* feat: add Runpod serverless image collector pools

* fix: prevent worker settings clipping and remove preview copy

* fix: initialize worker settings before mounting the form

* fix: validate complete serverless requests against 10 MB limit

* fix: simplify serverless cards and keep status dots circular

* fix: match serverless endpoint box to master card

* fix: preserve serverless capacity and recovery across job failures

Retain durable reservations until provider termination or explicit recovery, protect unresolved pools and credentials, and add scoped reconciliation. Consolidate lifecycle and secret policies and split prompt/media stages with regression coverage.

* feat: add dynamic per-image list queue with Start and End nodes

* fix(image-list): reject upstream data bypasses around Start

* fix(image-list): make optional End text a connection-only input

* fix(image-list): isolate unavailable workers during preflight

* fix(image-list): bound acknowledgements and configure run deadline

* fix(media-sync): preserve output and temp source roots

* fix(image-list): own job lifecycle and preserve worker preparation

* feat(image-list): let master participate unless orchestrator-only

* feat(image-list)!: replace fixed Start extras with growable value_N slots

Distributed Image List Start no longer has reference_image, text,
strength, seed or per-slot mode dropdowns. It now takes images, mask and
up to 10 generic value_N inputs (IMAGE, MASK, STRING, INT, FLOAT,
BOOLEAN) that grow via native V3 Autogrow, each with a matching output.

- One value is shared by every image; one per image pairs in order; any
  other count fails before dispatch. Only images is split into frames.
- Outputs are declared up front (image, mask, item_index, context,
  value_1..value_10). web/imageListStart.js hides unused value outputs,
  mirrors input types, and follows Autogrow compaction so downstream
  links keep their value.
- Image-list protocol bumped to v2; older workers fail preflight.

Breaking: saved workflows using the old Start inputs must recreate Start.

* fix(serverless): disable Clear saved API key while the worker is enabled

The checkbox read "Clear saved API key (disable pool first)", but the
panel never defines "pool" and saving with it ticked on an enabled worker
was rejected by the backend.

- Disable the checkbox while the worker is enabled, with a tooltip saying
  to turn the worker off first. Also disable it when no key is saved.
- Use "worker" instead of "pool" in user-facing serverless errors, the
  serverless guide and the README entry.

* feat(serverless): replace Concurrent jobs with a single Images per run setting

- Remove the separate Concurrent jobs field; rename Jobs per run to
  Images per run (1-16) with a tooltip explaining that Runpod's max
  workers decides how many GPUs run them.
- Backend uses a fixed per-worker limit of 16 outstanding jobs, so all
  images of a run are submitted at once. Unresolved jobs still count
  against it. The limit is constant, so it never has to change while
  jobs are unresolved.
- Legacy 'concurrency' in saved configs and older browser tabs is
  accepted and ignored/dropped; it no longer triggers the busy guard.
- Revert the enable toggle and show the reason when the backend rejects it.
- Trim a pasted api.runpod.ai/v2/<id> URL to the endpoint ID; plainer
  endpoint-ID error otherwise.
- Confirm before a type change deletes a saved Runpod API key.
- Update docs and tests.
2026-10-13 15:20:05 -07:00

181 lines
8.0 KiB
Python

"""Regression coverage at the scheduler and real HTTP transport boundaries."""
import asyncio
import importlib.util
import json
from pathlib import Path
import sys
import types
import unittest
from unittest.mock import patch
import torch
from aiohttp import web
from aiohttp.test_utils import TestClient, TestServer
from image_list import runtime
from test_image_list import graph_two_sequential_regions, start_node
def load_routes():
root = Path(__file__).resolve().parents[1]
name = '_image_list_transport_tests'
routes = web.RouteTableDef()
modules = {
name: types.ModuleType(name),
name + '.api': types.ModuleType(name + '.api'),
name + '.image_list': types.ModuleType(name + '.image_list'),
name + '.image_list.runtime': runtime,
'server': types.SimpleNamespace(PromptServer=types.SimpleNamespace(
instance=types.SimpleNamespace(routes=routes))),
}
spec = importlib.util.spec_from_file_location(name + '.api.image_list_routes', root / 'api/image_list_routes.py')
module = importlib.util.module_from_spec(spec)
with patch.dict(sys.modules, modules):
spec.loader.exec_module(module)
return module, routes
class TransportTests(unittest.IsolatedAsyncioTestCase):
async def asyncSetUp(self):
self.module, routes = load_routes()
app = web.Application()
app.add_routes(routes)
self.client = TestClient(TestServer(app))
await self.client.start_server()
async def asyncTearDown(self):
await self.client.close()
runtime._WORKER_ITEMS.clear()
async def test_fragmented_chunked_item_upload_is_consumable(self):
token = runtime.create_worker_task_token()
item = {'image': torch.full((1, 2, 3, 3), 0.25), 'index': 2}
data = json.dumps({'token': token, 'context_id': 'context', 'item': runtime.encode_item(item)}).encode()
async def chunks():
yield data[:8]
await asyncio.sleep(0.02)
yield data[8:]
response = await self.client.post('/distributed/image-list/item', data=chunks())
self.assertEqual(response.status, 200, await response.text())
result = runtime.consume_worker_item(token)
self.assertTrue(torch.equal(result['image'], item['image']))
self.assertEqual(result['index'], 2)
async def test_complete_item_upload_and_replay_rejection(self):
token = runtime.create_worker_task_token()
data = {'token': token, 'context_id': 'context', 'item': runtime.encode_item(
{'image': torch.zeros((1, 2, 3, 3)), 'index': 0})}
response = await self.client.post('/distributed/image-list/item', json=data)
self.assertEqual(response.status, 200, await response.text())
response = await self.client.post('/distributed/image-list/item', json=data)
self.assertEqual(response.status, 400)
runtime.consume_worker_item(token)
with self.assertRaisesRegex(RuntimeError, 'already consumed'):
runtime.consume_worker_item(token)
async def test_chunked_body_limit_is_aggregate(self):
async def chunks():
yield b'{"context_id":"'
await asyncio.sleep(0.01)
yield b'x' * 60
yield b'"}'
with patch.object(self.module, 'MAX_REQUEST_BYTES', 64):
response = await self.client.post('/distributed/image-list/item', data=chunks())
self.assertEqual(response.status, 400)
self.assertIn('exceeds', await response.text())
async def test_invalid_result_shapes_are_rejected(self):
for kind, shape in [('image', (1, 2, 3)), ('mask', (1, 2, 3, 1))]:
result = runtime.encode_result({'image': torch.zeros((1, 2, 3, 3)),
'mask': torch.zeros((1, 2, 3))})
result[kind]['shape'] = list(shape)
with self.assertRaises(ValueError):
runtime.decode_result(result)
class SchedulingBoundaryTests(unittest.IsolatedAsyncioTestCase):
async def test_user_interrupt_during_result_wait_cleans_up_promptly(self):
entered = asyncio.Event()
cancelled = asyncio.Event()
wait_cancelled = asyncio.Event()
dispatches, cleanups = [], []
async def dispatch(worker, index):
dispatches.append(index)
return {'index': index}
async def wait_next(_inflight):
entered.set()
try:
await asyncio.Event().wait()
finally:
wait_cancelled.set()
async def cleanup(worker, handle):
cleanups.append((worker, handle['index']))
task = asyncio.create_task(runtime.dynamic_schedule(
3, ['one'], dispatch, wait_next, cleanup, cancelled.is_set))
await entered.wait()
cancelled.set()
with self.assertRaises(runtime.ImageListCancelledError):
await asyncio.wait_for(task, timeout=1)
self.assertTrue(wait_cancelled.is_set())
self.assertEqual(dispatches, [0])
self.assertEqual(cleanups, [('one', 0)])
async def test_already_interrupted_does_not_submit_any_work(self):
async def unused(*args):
self.fail('pre-cancelled job must not dispatch or wait')
with self.assertRaises(runtime.ImageListCancelledError):
await runtime.dynamic_schedule(2, ['one'], unused, unused, unused, lambda: True)
async def test_task_cancel_during_submit_waits_for_owned_handle(self):
entered, release = asyncio.Event(), asyncio.Event()
cleanups = []
async def dispatch(worker, index):
entered.set()
await release.wait()
return {'index': index, 'prompt_id': 'owned'}
async def unused(*args):
self.fail('cancelled dispatch must not enter result wait')
async def cleanup(worker, handle):
cleanups.append(handle['prompt_id'])
task = asyncio.create_task(runtime.dynamic_schedule(2, ['one'], dispatch, unused, cleanup))
await entered.wait()
task.cancel()
release.set()
with self.assertRaises(asyncio.CancelledError):
await task
self.assertEqual(cleanups, ['owned'])
def test_output_nodes_inside_region_are_rejected(self):
prompt = graph_two_sequential_regions()
output_class = type('OutputOperation', (), {'OUTPUT_NODE': True})
registry = types.SimpleNamespace(NODE_CLASS_MAPPINGS={'FirstFrameOperation': output_class})
with patch.dict(sys.modules, {'nodes': registry}):
with self.assertRaisesRegex(ValueError, 'must be placed after'):
runtime.validate_image_list_regions(prompt)
def test_shared_scalars_are_validated_before_dispatch(self):
for value in (float('nan'), object(), torch.zeros(2, dtype=torch.int32)):
with self.assertRaises(TypeError):
runtime.normalize_image_list_inputs(torch.zeros((1, 2, 2, 3)), values={'value_1': [value]})
def test_three_sequential_regions_can_share_worker_loader(self):
prompt = graph_two_sequential_regions()
prompt.pop('8')
prompt.update({
'8': start_node(['7', 0]),
'9': {'class_type': 'ThirdOperation', 'inputs': {'image': ['8', 0]}},
'10': {'class_type': runtime.END_CLASS,
'inputs': {'images': ['9', 0], 'context': ['8', runtime.CONTEXT_OUT]}},
'11': {'class_type': 'GenericModelLoader', 'inputs': {}},
})
for node_id in ['3', '6', '9']:
prompt[node_id]['inputs']['model'] = ['11', 0]
# Shared dependencies are verified against the registered output schema.
loader = type('GenericModelLoader', (), {'RETURN_TYPES': ('MODEL',)})
registry = types.SimpleNamespace(NODE_CLASS_MAPPINGS={'GenericModelLoader': loader})
with patch.dict(sys.modules, {'nodes': registry}):
regions = runtime.validate_image_list_regions(prompt)
self.assertEqual(len(regions), 3)
for region in regions:
self.assertIn('11', region['node_ids'])