This commit is contained in:
Dobromir Popov
2026-07-07 18:49:32 +03:00
parent e9a094b620
commit b1f08c45cd
6 changed files with 541 additions and 26 deletions

View File

@@ -1116,7 +1116,7 @@ def test_real_model_startup_summary_shows_total_layers(tmp_path, monkeypatch, ca
assert captured_registration["vram_bytes"] == 6144 * 1024 * 1024
assert captured_registration["max_loaded_shards"] == 2
output = capsys.readouterr().out
assert "Shard: layers 023; 24 of 24" in output
assert "Shard: layers 023 (24 of 24)" in output
assert "Node ID: node-test-123" in output

View File

@@ -5,6 +5,7 @@ import json
import threading
import time
import urllib.error
import urllib.parse
import urllib.request
import pytest
@@ -501,6 +502,100 @@ def test_tracker_logs_stream_progress_before_request_completes():
node_thread.join(timeout=1.0)
def test_tracker_dashboard_can_cancel_inflight_proxy():
chunk_sent = threading.Event()
release = threading.Event()
class StreamingChatHandler(http.server.BaseHTTPRequestHandler):
def log_message(self, fmt, *args):
pass
def do_POST(self):
if self.path != "/v1/chat/completions":
self.send_response(404)
self.end_headers()
return
self.rfile.read(int(self.headers.get("Content-Length", 0)))
self.send_response(200)
self.send_header("Content-Type", "text/event-stream; charset=utf-8")
self.end_headers()
payload = json.dumps({
"choices": [{"delta": {"content": "hello world"}}],
}).encode()
self.wfile.write(b"data: " + payload + b"\n\n")
self.wfile.flush()
chunk_sent.set()
release.wait(timeout=3.0)
self.wfile.write(b"data: [DONE]\n\n")
self.wfile.flush()
node = http.server.HTTPServer(("127.0.0.1", 0), StreamingChatHandler)
node_thread = threading.Thread(target=node.serve_forever, daemon=True)
node_thread.start()
tracker = TrackerServer(heartbeat_timeout=60.0)
tracker_port = tracker.start()
response = None
request_id = None
try:
_post_json(
f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
{"endpoint": f"http://127.0.0.1:{node.server_address[1]}",
"model": "cancel-proxy-model", "num_layers": 1,
"shard_start": 0, "shard_end": 0,
"hardware_profile": {}, "score": 1.0},
)
req = urllib.request.Request(
f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
data=json.dumps({
"model": "cancel-proxy-model",
"stream": True,
"messages": [{"role": "user", "content": "hi"}],
}).encode(),
headers={"Content-Type": "application/json"},
method="POST",
)
response = urllib.request.urlopen(req, timeout=3.0)
first_line = response.readline()
assert first_line.startswith(b"data:")
assert chunk_sent.wait(timeout=1.0)
console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
selected = [
event for event in console["events"]
if event["message"] == "proxy route selected"
]
assert selected
request_id = selected[-1]["fields"]["request_id"]
cancel = _post_json(
f"http://127.0.0.1:{tracker_port}/v1/proxy/requests/{urllib.parse.quote(request_id, safe='')}/cancel",
{},
)
assert cancel["status"] == "canceled"
deadline = time.time() + 5.0
canceled_events = []
while time.time() < deadline:
console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
canceled_events = [
event for event in console["events"]
if event["message"] == "proxy canceled"
and event["fields"].get("request_id") == request_id
]
if canceled_events:
break
time.sleep(0.05)
assert canceled_events
finally:
release.set()
if response is not None:
response.close()
tracker.stop()
node.shutdown()
node.server_close()
node_thread.join(timeout=1.0)
def test_tracker_routes_hf_model_alias_from_quickstart():
"""The documented qwen2.5-0.5b alias resolves a full HF repo registration."""
tracker = TrackerServer()