no-mistakes(document): Document llmuser SSH user for .8 GPU health probe
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 11s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 12s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 24s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 23s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 2s

This commit is contained in:
root
2026-09-28 07:22:13 +00:00
parent bf3a1ba523
commit e0c9852de8
3 changed files with 39 additions and 1 deletions
+33
View File
@@ -124,6 +124,39 @@ def test_tanko_ct112_is_probed_on_minipve(ahc, monkeypatch, capsys):
ahc.REPORT_ONLY.clear()
def test_gpu_rtx3090_probe_uses_llmuser_not_root(ahc, monkeypatch, capsys):
# 2026-09-28: root SSH to .8 was lost when the guest was rebuilt; llmuser
# owns llama-server and can read systemctl status and the :8080 pid. A root
# probe reads as UNREACHABLE for a healthy host (the reported bug). Execute
# check_gpu_ports() against an SSH boundary that only accepts llmuser@.8 and
# assert the .8 leg does not produce the false UNREACHABLE failure.
seen = []
def fake_ssh(host, cmd, user="root"):
seen.append((host, user))
if host == "192.168.68.8" and user != "llmuser":
return None # root SSH denied -> baseline false UNREACHABLE
if cmd.startswith("systemctl is-active"):
return "active"
if cmd.startswith("ss -tlnp"):
return "48351"
if cmd.startswith("curl"):
return '{"status":"ok"}'
return None
monkeypatch.setattr(ahc, "ssh", fake_ssh)
ahc.FAIL.clear()
try:
ahc.check_gpu_ports()
out = capsys.readouterr().out
assert "gpu-unreachable:192.168.68.8" not in ahc.FAIL
assert "\u2705 gpu-rtx3090 (.8): healthy" in out
assert ("192.168.68.8", "llmuser") in seen
assert not any(host == "192.168.68.8" and user == "root" for host, user in seen)
finally:
ahc.FAIL.clear()
def test_report_only_legs_never_count_as_failures(ahc):
for agent, report_only in (("koby", True), ("koonimo", False), ("tanko", False)):
ahc.FAIL.clear()