v0.24.0:0 - configurable cluster topology (vllm container name, hide services, second-vllm monitor)

Make the cluster topology configurable so an adopter wired differently
(vLLM on both Sparks, port 8000, different container name, no Parakeet)
can monitor without forking. Covers the OpenClaw report P4/P5/#6.

- VLLM_CONTAINER override (default vllm_node), validated at the boundary
  and quote_arg-quoted into the swap log-tail + pre-flight validator exec.
- DISABLED_SERVICES list: hidden services show no tile and are skipped by
  status/deep-health/connectivity probes (kills the Parakeet-on-8000
  collision).
- kind: vllm custom service monitors a second Spark's vLLM via the shared
  probe_vllm_endpoint; /api/endpoints gains a disabled flag.

Swap mechanism intentionally not generalized to raw docker run (that's
coordination, roadmap item 4).
This commit is contained in:
Keysat
2026-06-17 23:03:33 -05:00
parent 90394f891b
commit 26070eb191
17 changed files with 304 additions and 26 deletions
+120
View File
@@ -0,0 +1,120 @@
"""Configurable topology: DISABLED_SERVICES, vLLM container override, and the
extra-vLLM probe. All offline — the disabled checks short-circuit before any
network call, and the probes are exercised only on the not-configured path.
"""
import asyncio
from app.config import Settings
from app.health import (
check_embeddings,
check_kokoro,
check_parakeet,
check_qdrant,
check_vllm,
probe_vllm_endpoint,
)
from app.services import services_from_settings
def _settings(monkeypatch, **env) -> Settings:
# Pin the topology env vars under test; default the rest to blank so a stray
# value in the real environment can't leak into the assertion.
keys = [
"SPARK1_HOST", "SPARK1_USER", "SPARK2_HOST", "SPARK2_USER",
"DISABLED_SERVICES", "VLLM_CONTAINER",
]
for k in keys:
monkeypatch.delenv(k, raising=False)
for k, v in env.items():
monkeypatch.setenv(k, v)
return Settings.from_env()
# ---- DISABLED_SERVICES parsing ----
def test_disabled_services_parsed_lowercased_and_trimmed(monkeypatch):
s = _settings(monkeypatch, DISABLED_SERVICES="parakeet, Kokoro ,,")
assert s.disabled_services == frozenset({"parakeet", "kokoro"})
def test_disabled_services_blank_is_empty(monkeypatch):
assert _settings(monkeypatch).disabled_services == frozenset()
# ---- vLLM container override ----
def test_vllm_container_defaults_to_vllm_node(monkeypatch):
assert _settings(monkeypatch).vllm_container == "vllm_node"
def test_vllm_container_override(monkeypatch):
assert _settings(monkeypatch, VLLM_CONTAINER="vllm-gemma4").vllm_container == "vllm-gemma4"
def test_vllm_container_invalid_falls_back(monkeypatch):
# A malformed value (space / shell metachar) is rejected at the boundary and
# falls back to the default rather than crashing startup or reaching a sink.
assert _settings(monkeypatch, VLLM_CONTAINER="bad name; rm -rf").vllm_container == "vllm_node"
# ---- services map honors the disable list ----
def test_services_from_settings_drops_disabled(monkeypatch):
s = _settings(
monkeypatch,
SPARK1_HOST="10.0.0.1", SPARK1_USER="u",
SPARK2_HOST="10.0.0.2", SPARK2_USER="u",
DISABLED_SERVICES="parakeet,qdrant",
)
svcs = services_from_settings(s)
assert "parakeet" not in svcs and "qdrant" not in svcs
assert "kokoro" in svcs and "embeddings" in svcs
def test_custom_vllm_service_registered(monkeypatch):
from app import custom_services
monkeypatch.setattr(custom_services, "load_custom_services", lambda: [
{"key": "vllm-spark2", "kind": "vllm", "host": "10.0.0.2",
"user": "u", "container": "vllm_node", "port": 8000},
])
s = _settings(monkeypatch, SPARK1_HOST="10.0.0.1", SPARK1_USER="u",
SPARK2_HOST="10.0.0.2", SPARK2_USER="u")
svc = services_from_settings(s)["vllm-spark2"]
assert svc.kind == "vllm" and svc.port == 8000 and svc.container == "vllm_node"
def test_custom_service_colliding_with_builtin_is_ignored(monkeypatch):
# A custom entry can't shadow a built-in key — the built-in wins.
from app import custom_services
monkeypatch.setattr(custom_services, "load_custom_services", lambda: [
{"key": "parakeet", "kind": "vllm", "host": "10.0.0.9", "user": "u", "port": 8000},
])
s = _settings(monkeypatch, SPARK1_HOST="10.0.0.1", SPARK1_USER="u",
SPARK2_HOST="10.0.0.2", SPARK2_USER="u")
assert services_from_settings(s)["parakeet"].kind == "stt"
# ---- disabled health checks short-circuit (no network) ----
def test_disabled_check_returns_disabled_verdict(monkeypatch):
s = _settings(
monkeypatch,
SPARK2_HOST="10.0.0.2", SPARK2_USER="u", # host set, but disable wins
DISABLED_SERVICES="parakeet,kokoro,embeddings,qdrant",
)
for check in (check_parakeet, check_kokoro, check_embeddings, check_qdrant):
r = asyncio.run(check(s))
assert r == {"ok": False, "disabled": True, "error": "disabled", "base_url": None}
# ---- vLLM probe: not-configured path is pure ----
def test_probe_vllm_endpoint_unconfigured(monkeypatch):
r = asyncio.run(probe_vllm_endpoint("", 8000))
assert r["ok"] is False and "not configured" in r["error"]
def test_check_vllm_unconfigured_without_spark1(monkeypatch):
s = _settings(monkeypatch) # no SPARK1_HOST
r = asyncio.run(check_vllm(s))
assert r["ok"] is False and "spark1 not configured" in r["error"]