Leonid PershinandCursor
03ba4cb6ed
gpu-rent now writes personas/<id>/ on the VM (not legacy personas.json), adds seed-personas/doctor checks, and shortens mid/high keep-alive now that Assistent parks the LLM before Generate. Co-authored-by: Cursor <cursoragent@cursor.com>
132 lines
4.1 KiB
Python
132 lines
4.1 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from gpu_rent.llm_runtime import (
|
|
already_have_ollama_tag,
|
|
decide_runtime,
|
|
normalize_runtime,
|
|
parse_ollama_models,
|
|
preferred_ollama_model,
|
|
write_ollama_models_preset,
|
|
)
|
|
|
|
|
|
def test_normalize_runtime():
|
|
assert normalize_runtime(None) == "none"
|
|
assert normalize_runtime("OLLAMA") == "ollama"
|
|
with pytest.raises(ValueError):
|
|
normalize_runtime("llamacpp")
|
|
with pytest.raises(ValueError):
|
|
normalize_runtime("foo")
|
|
|
|
|
|
def test_decide_runtime_flags_win():
|
|
assert (
|
|
decide_runtime(flag=None, ollama_flag=True, from_config="none") == "ollama"
|
|
)
|
|
assert (
|
|
decide_runtime(flag="ollama", ollama_flag=False, from_config="none") == "ollama"
|
|
)
|
|
assert decide_runtime(flag=None, ollama_flag=False, from_config="ollama") == "ollama"
|
|
|
|
|
|
def test_parse_ollama_models(tmp_path: Path):
|
|
path = tmp_path / "m.yaml"
|
|
path.write_text(
|
|
"models:\n - name: huihui_ai/qwen2.5-abliterate:7b\n default: true\n - qwen2.5:3b\n",
|
|
encoding="utf-8",
|
|
)
|
|
entries = parse_ollama_models(path)
|
|
assert [e.name for e in entries] == [
|
|
"huihui_ai/qwen2.5-abliterate:7b",
|
|
"qwen2.5:3b",
|
|
]
|
|
assert entries[0].default is True
|
|
|
|
|
|
def test_parse_empty_manifest(tmp_path: Path):
|
|
path = tmp_path / "empty.yaml"
|
|
path.write_text("models: []\n", encoding="utf-8")
|
|
assert parse_ollama_models(path) == []
|
|
assert parse_ollama_models(tmp_path / "missing.yaml") == []
|
|
|
|
|
|
def test_write_preset(tmp_path: Path):
|
|
path = tmp_path / "out.yaml"
|
|
write_ollama_models_preset(path, "recommended")
|
|
entries = parse_ollama_models(path)
|
|
assert entries[0].name == "huihui_ai/qwen3-vl-abliterated:8b-instruct"
|
|
assert entries[0].default is True
|
|
assert entries[1].name == "huihui_ai/qwen2.5-vl-abliterated:7b"
|
|
write_ollama_models_preset(path, "big")
|
|
assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-vl-abliterated:32b"
|
|
write_ollama_models_preset(path, "text")
|
|
assert parse_ollama_models(path)[0].name == "huihui_ai/qwen2.5-abliterate:7b"
|
|
|
|
|
|
def test_already_have_ollama_tag_exact_only():
|
|
have = {"qwen2.5:7b", "foo:latest"}
|
|
assert already_have_ollama_tag(have, "qwen2.5:7b")
|
|
assert not already_have_ollama_tag(have, "qwen2.5:3b")
|
|
assert already_have_ollama_tag(have, "foo")
|
|
assert already_have_ollama_tag(have, "foo:latest")
|
|
|
|
|
|
def test_preferred_ollama_model(tmp_path: Path):
|
|
path = tmp_path / "m.yaml"
|
|
path.write_text(
|
|
"models:\n - name: a:3b\n - name: b:7b\n default: true\n",
|
|
encoding="utf-8",
|
|
)
|
|
assert preferred_ollama_model(path) == "b:7b"
|
|
path.write_text('models:\n - "only:7b"\n', encoding="utf-8")
|
|
assert preferred_ollama_model(path) == "only:7b"
|
|
assert preferred_ollama_model(tmp_path / "missing.yaml") is None
|
|
|
|
|
|
def test_warmup_ollama_http_skips_loaded(monkeypatch):
|
|
from gpu_rent.llm_runtime import warmup_ollama_http
|
|
|
|
class Resp:
|
|
def raise_for_status(self) -> None:
|
|
return None
|
|
|
|
def json(self):
|
|
return {"models": [{"name": "foo:7b"}]}
|
|
|
|
class Client:
|
|
def __init__(self, *a, **k):
|
|
pass
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *a):
|
|
return False
|
|
|
|
def get(self, url, timeout=None):
|
|
assert url.endswith("/api/ps")
|
|
return Resp()
|
|
|
|
def post(self, *_a, **_k):
|
|
raise AssertionError("must not chat when already loaded")
|
|
|
|
monkeypatch.setattr("gpu_rent.llm_runtime.httpx.Client", Client)
|
|
msg = warmup_ollama_http("http://127.0.0.1:17811", "foo:7b")
|
|
assert "skip" in msg
|
|
|
|
|
|
def test_maybe_warmup_skips_when_runtime_none():
|
|
from gpu_rent.llm_runtime import maybe_warmup_ollama_local
|
|
|
|
logs: list[str] = []
|
|
|
|
class Cfg:
|
|
llm_runtime = "none"
|
|
ollama_models_manifest = Path("missing.yaml")
|
|
ollama_local_port = 17811
|
|
|
|
maybe_warmup_ollama_local(Cfg(), logs.append)
|
|
assert logs == []
|