feat: render health endpoint + test script + pipeline fixes

- GET /api/worker/health/render: checks render-worker (thumbnail_rendering
  queue), Blender availability via active_queues inspect, queue depth,
  last render recency — returns ok/degraded/down status
- scripts/test_render_pipeline.py: integration test for full pipeline
  (--health, --sample, --full modes)
- PLAN.md: appended Render Pipeline Fixes section with all B-Fixes
- LEARNINGS.md: documented 5 new learnings (queue mismatch, circular
  import, 307 redirect, worker capability detection)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-06 19:34:12 +01:00
parent 979b0082ec
commit 381f44bc8b
4 changed files with 703 additions and 1 deletions
+464
View File
@@ -0,0 +1,464 @@
#!/usr/bin/env python3
"""Render pipeline integration test.
Tests the full pipeline: STEP upload → CAD processing → thumbnail rendering →
order creation → submit → dispatch renders → wait for completed.
Usage:
# Quick smoke test (1 STEP file, 1 output type)
python scripts/test_render_pipeline.py --sample
# Full test — all output types, waits for all renders
python scripts/test_render_pipeline.py --full
# Only check render health endpoint
python scripts/test_render_pipeline.py --health
# Custom credentials / host
python scripts/test_render_pipeline.py --sample --host http://localhost:8888 \
--email admin@schaeffler.com --password Admin1234!
Environment variables (alternative to flags):
TEST_HOST, TEST_EMAIL, TEST_PASSWORD
"""
import argparse
import os
import sys
import time
import json
import requests
from pathlib import Path
# ---------------------------------------------------------------------------
# Config
# ---------------------------------------------------------------------------
DEFAULT_HOST = os.environ.get("TEST_HOST", "http://localhost:8888")
DEFAULT_EMAIL = os.environ.get("TEST_EMAIL", "admin@schaeffler.com")
DEFAULT_PASSWORD = os.environ.get("TEST_PASSWORD", "Admin1234!")
SAMPLE_STEP = Path(__file__).parent.parent / "step-sample-file" / "81113-l_cut.stp"
RENDER_TIMEOUT_SECONDS = 300 # 5 minutes per render
POLL_INTERVAL_SECONDS = 5
CAD_PROCESSING_TIMEOUT = 120 # 2 minutes for STEP processing
GREEN = "\033[92m"
RED = "\033[91m"
YELLOW = "\033[93m"
BLUE = "\033[94m"
RESET = "\033[0m"
passed = []
failed = []
warnings = []
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def ok(msg: str):
print(f" {GREEN}{RESET} {msg}")
passed.append(msg)
def fail(msg: str):
print(f" {RED}{RESET} {msg}")
failed.append(msg)
def warn(msg: str):
print(f" {YELLOW}{RESET} {msg}")
warnings.append(msg)
def info(msg: str):
print(f" {BLUE}{RESET} {msg}")
def section(title: str):
print(f"\n{BLUE}{'='*60}{RESET}")
print(f"{BLUE} {title}{RESET}")
print(f"{BLUE}{'='*60}{RESET}")
class APIClient:
def __init__(self, host: str, email: str, password: str):
self.host = host.rstrip("/")
self.session = requests.Session()
self.token: str | None = None
self._login(email, password)
def _login(self, email: str, password: str):
resp = self.session.post(
f"{self.host}/api/auth/login",
data={"username": email, "password": password},
)
resp.raise_for_status()
data = resp.json()
self.token = data["access_token"]
self.session.headers["Authorization"] = f"Bearer {self.token}"
def get(self, path: str, **kwargs) -> requests.Response:
return self.session.get(f"{self.host}/api{path}", **kwargs)
def post(self, path: str, **kwargs) -> requests.Response:
return self.session.post(f"{self.host}/api{path}", **kwargs)
def delete(self, path: str, **kwargs) -> requests.Response:
return self.session.delete(f"{self.host}/api{path}", **kwargs)
# ---------------------------------------------------------------------------
# Test: Render health endpoint
# ---------------------------------------------------------------------------
def test_health(client: APIClient) -> bool:
section("1. Render Health Check")
resp = client.get("/worker/health/render")
if resp.status_code != 200:
fail(f"GET /worker/health/render → {resp.status_code}: {resp.text[:200]}")
return False
data = resp.json()
info(f"Overall status: {data['status']}")
info(f"Render worker connected: {data['render_worker_connected']}")
info(f"Blender available: {data['blender_available']}")
info(f"thumbnail_rendering queue depth: {data['thumbnail_queue_depth']}")
if data.get("last_render_at"):
info(f"Last render: {data['last_render_at']} ({'success' if data['last_render_success'] else 'FAILED'}, {data['last_render_age_minutes']}m ago)")
if data["render_worker_connected"]:
ok("Render worker connected")
else:
fail("Render worker NOT connected — renders will fail")
if data["blender_available"]:
ok("Blender renderer reachable (port 8100)")
else:
fail("Blender renderer NOT reachable — thumbnail/order renders will fail")
if data["thumbnail_queue_ok"]:
ok(f"thumbnail_rendering queue healthy (depth={data['thumbnail_queue_depth']})")
else:
warn(f"thumbnail_rendering queue DEEP ({data['thumbnail_queue_depth']} tasks) — renders may be slow")
return data["status"] != "down"
# ---------------------------------------------------------------------------
# Test: STEP upload + CAD processing
# ---------------------------------------------------------------------------
def test_step_upload(client: APIClient, step_file: Path) -> str | None:
"""Upload STEP file, wait for completed processing. Returns cad_file_id or None."""
section("2. STEP Upload + CAD Processing")
if not step_file.exists():
fail(f"Sample STEP file not found: {step_file}")
return None
info(f"Uploading {step_file.name} ({step_file.stat().st_size // 1024} KB)")
with open(step_file, "rb") as f:
resp = client.post(
"/uploads/step",
files={"file": (step_file.name, f, "application/octet-stream")},
)
if resp.status_code not in (200, 201):
fail(f"STEP upload failed: {resp.status_code} {resp.text[:300]}")
return None
data = resp.json()
cad_file_id = data["cad_file_id"]
ok(f"STEP uploaded → cad_file_id={cad_file_id[:8]}... status={data.get('status')}")
# Poll for completed processing
info(f"Waiting for CAD processing (timeout={CAD_PROCESSING_TIMEOUT}s)...")
deadline = time.time() + CAD_PROCESSING_TIMEOUT
last_status = None
while time.time() < deadline:
resp = client.get(f"/cad/{cad_file_id}")
if resp.status_code == 200:
cad = resp.json()
status = cad.get("processing_status")
if status != last_status:
info(f" CAD status: {status}")
last_status = status
if status == "completed":
ok(f"CAD processing completed (thumbnail rendered)")
return cad_file_id
if status == "failed":
fail(f"CAD processing FAILED: {cad.get('error_message', 'unknown error')}")
return None
time.sleep(POLL_INTERVAL_SECONDS)
fail(f"CAD processing timed out after {CAD_PROCESSING_TIMEOUT}s (last status: {last_status})")
return None
# ---------------------------------------------------------------------------
# Test: Order creation + submit + dispatch + wait
# ---------------------------------------------------------------------------
def test_order_render(
client: APIClient,
cad_file_id: str,
output_type_ids: list[str],
test_label: str,
) -> bool:
"""Create a minimal order, submit, dispatch renders, wait for completion."""
section(f"3. Order Render — {test_label}")
info(f"Output types: {len(output_type_ids)}")
# Get a product that uses this CAD file
resp = client.get(f"/cad/{cad_file_id}")
if resp.status_code != 200:
fail(f"CAD file lookup failed: {resp.status_code}")
return False
# Find or create a product linked to this CAD file
product_id = None
resp_products = client.get("/products/?limit=100")
if resp_products.status_code == 200:
products = resp_products.json()
if isinstance(products, dict):
products = products.get("items", [])
for p in products:
if str(p.get("cad_file_id")) == cad_file_id:
product_id = str(p["id"])
info(f"Using existing product: {p.get('name', p['id'])[:40]}")
break
if not product_id:
# Create a minimal test product
resp_create = client.post("/products/", json={
"name": f"Test Product {cad_file_id[:8]}",
"pim_id": f"TEST-{cad_file_id[:8]}",
"is_active": True,
"cad_file_id": cad_file_id,
})
if resp_create.status_code not in (200, 201):
fail(f"Product creation failed: {resp_create.status_code} {resp_create.text[:200]}")
return False
product_id = resp_create.json()["id"]
ok(f"Created test product: {product_id[:8]}...")
# Build output_type_selections for one product
ot_selections = [{"product_id": product_id, "output_type_id": ot_id} for ot_id in output_type_ids]
# Create order via wizard endpoint
resp_order = client.post("/orders/product-order", json={
"product_id": product_id,
"output_type_selections": [
{"output_type_id": ot_id}
for ot_id in output_type_ids
],
})
if resp_order.status_code not in (200, 201):
# Fallback: try to find existing submitted order
warn(f"Product order wizard not available ({resp_order.status_code}), looking for existing order lines...")
return _test_existing_renders(client, product_id, output_type_ids)
order = resp_order.json()
order_id = order["id"]
ok(f"Order created: {order.get('order_number')} (id={order_id[:8]}...)")
return _submit_and_wait(client, order_id, output_type_ids)
def _test_existing_renders(client: APIClient, product_id: str, output_type_ids: list[str]) -> bool:
"""Find existing order lines for a product and wait for completion."""
resp = client.get(f"/orders/?limit=20")
if resp.status_code != 200:
fail("Could not list orders")
return False
orders = resp.json()
if isinstance(orders, dict):
orders = orders.get("items", [])
for order in orders:
if order.get("status") in ("submitted", "processing", "rendering"):
return _submit_and_wait(client, order["id"], output_type_ids)
warn("No suitable existing orders found for render test")
return True # non-blocking warning
def _submit_and_wait(client: APIClient, order_id: str, output_type_ids: list[str]) -> bool:
# Submit
resp_sub = client.post(f"/orders/{order_id}/submit")
if resp_sub.status_code not in (200, 201, 204):
if resp_sub.status_code == 409:
info("Order already submitted")
else:
fail(f"Order submit failed: {resp_sub.status_code} {resp_sub.text[:200]}")
return False
else:
ok("Order submitted")
# Dispatch renders
resp_disp = client.post(f"/orders/{order_id}/dispatch-renders")
if resp_disp.status_code not in (200, 201, 204):
fail(f"Dispatch renders failed: {resp_disp.status_code} {resp_disp.text[:200]}")
return False
dispatch_data = resp_disp.json() if resp_disp.content else {}
dispatched = dispatch_data.get("dispatched", "?")
ok(f"Renders dispatched ({dispatched} lines)")
# Poll for order completion
info(f"Waiting for renders to complete (timeout={RENDER_TIMEOUT_SECONDS}s per OT)...")
deadline = time.time() + RENDER_TIMEOUT_SECONDS * max(len(output_type_ids), 1)
last_summary = ""
while time.time() < deadline:
resp_ord = client.get(f"/orders/{order_id}")
if resp_ord.status_code != 200:
fail(f"Order poll failed: {resp_ord.status_code}")
return False
order = resp_ord.json()
order_status = order.get("status")
lines = order.get("lines", order.get("order_lines", []))
statuses = [l.get("render_status") for l in lines]
summary = f"order={order_status} lines={statuses}"
if summary != last_summary:
info(f" {summary}")
last_summary = summary
if order_status == "completed":
ok(f"Order completed — all {len(lines)} render(s) done")
# Check individual line results
all_success = True
for line in lines:
rs = line.get("render_status")
ot_name = line.get("output_type_name") or line.get("output_type", {}).get("name", "?")
if rs == "completed":
ok(f" Line [{ot_name}]: completed")
elif rs == "failed":
fail(f" Line [{ot_name}]: FAILED")
all_success = False
else:
warn(f" Line [{ot_name}]: {rs}")
return all_success
if order_status == "failed":
fail(f"Order FAILED — check render logs")
return False
time.sleep(POLL_INTERVAL_SECONDS)
fail(f"Render timed out after {(time.time() - deadline + RENDER_TIMEOUT_SECONDS * max(len(output_type_ids), 1)):.0f}s")
return False
# ---------------------------------------------------------------------------
# Get output types
# ---------------------------------------------------------------------------
def get_output_types(client: APIClient) -> list[dict]:
resp = client.get("/output-types/")
if resp.status_code != 200:
resp = client.get("/output-types")
if resp.status_code != 200:
return []
data = resp.json()
if isinstance(data, dict):
data = data.get("items", [])
return [ot for ot in data if ot.get("is_active", True)]
# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------
def main():
parser = argparse.ArgumentParser(description="Render pipeline integration tests")
parser.add_argument("--host", default=DEFAULT_HOST)
parser.add_argument("--email", default=DEFAULT_EMAIL)
parser.add_argument("--password", default=DEFAULT_PASSWORD)
parser.add_argument("--health", action="store_true", help="Only run health check")
parser.add_argument("--sample", action="store_true", help="Quick sample test (1 STEP, 1 OT)")
parser.add_argument("--full", action="store_true", help="Full test (all output types)")
parser.add_argument("--step", default=str(SAMPLE_STEP), help="Path to STEP file")
args = parser.parse_args()
if not any([args.health, args.sample, args.full]):
parser.print_help()
sys.exit(0)
print(f"\n{BLUE}Render Pipeline Test{RESET}")
print(f"Host: {args.host}")
print(f"Mode: {'health' if args.health else 'sample' if args.sample else 'full'}")
# Login
try:
client = APIClient(args.host, args.email, args.password)
ok(f"Authenticated as {args.email}")
except Exception as exc:
fail(f"Authentication failed: {exc}")
sys.exit(1)
# Health check
health_ok = test_health(client)
if args.health:
_print_summary()
sys.exit(0 if not failed else 1)
if not health_ok:
warn("Health check failed — render tests may not work. Continuing anyway...")
# STEP upload
step_path = Path(args.step)
cad_file_id = test_step_upload(client, step_path)
if not cad_file_id:
fail("STEP processing failed — cannot proceed to render tests")
_print_summary()
sys.exit(1)
# Get output types
output_types = get_output_types(client)
if not output_types:
fail("No active output types found")
_print_summary()
sys.exit(1)
info(f"Found {len(output_types)} active output types: {[ot['name'] for ot in output_types]}")
if args.sample:
# Pick the first non-animation output type (fastest)
ot = next(
(ot for ot in output_types if not ot.get("is_animation") and "LQ" in ot["name"].upper()),
output_types[0],
)
info(f"Sample test using output type: {ot['name']}")
test_order_render(client, cad_file_id, [ot["id"]], f"Sample [{ot['name']}]")
elif args.full:
# Test each output type individually
for ot in output_types:
if ot.get("is_animation"):
warn(f"Skipping animation output type: {ot['name']} (too slow for full test)")
continue
test_order_render(client, cad_file_id, [ot["id"]], ot["name"])
_print_summary()
sys.exit(0 if not failed else 1)
def _print_summary():
section("Test Summary")
print(f" {GREEN}Passed:{RESET} {len(passed)}")
print(f" {RED}Failed:{RESET} {len(failed)}")
print(f" {YELLOW}Warnings:{RESET} {len(warnings)}")
if failed:
print(f"\n{RED}FAILURES:{RESET}")
for f_ in failed:
print(f" - {f_}")
if not failed:
print(f"\n{GREEN}All tests passed!{RESET}")
else:
print(f"\n{RED}Tests FAILED{RESET}")
if __name__ == "__main__":
main()