Steuert einen llama.cpp-Server als Docker-Container: --start/--check/--stop/
--change/--chat, INI-Konfiguration (builtin defaults -> [default] ->
[model.<profile>] -> CLI), SSRF-gehärtete Prompt-Eingabe (Datei/HTTPS-URL),
File-Locking für --start/--change und ein OpenAI-kompatibler HTTP-Layer.
Enthält u. a.:
- Env-Var-Expansion in hf_home (hf_home = ${HF_HOME})
- konfigurierbares Chat-Antwortbudget (max_tokens/chat_temperature,
CLI: --max-tokens/--chat-temp); temperature defer an Server-Default
- DNS-Pinning gegen DNS-Rebinding bei URL-Quellen
- dry-run als nebenwirkungsfreie Vorschau (kein Lock/Removal/Modell-Check)
- 98 Tests (pytest)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
154 lines
4.6 KiB
Python
154 lines
4.6 KiB
Python
import sys
|
|
from pathlib import Path
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
|
|
|
|
from llamacppctl.docker_ops import ( # noqa: E402
|
|
build_run_command,
|
|
container_exists,
|
|
container_running,
|
|
docker_available,
|
|
format_command_for_display,
|
|
inspect_container,
|
|
)
|
|
from llamacppctl.schema import ServerConfig # noqa: E402
|
|
|
|
|
|
def make_cfg(**overrides) -> ServerConfig:
|
|
base = dict(
|
|
image="ghcr.io/ggml-org/llama.cpp:server-cuda",
|
|
hf_home=Path("/srv/models"),
|
|
model_path="qwen3/default.gguf",
|
|
container_name="test_llm",
|
|
host_port=8001,
|
|
container_port=8000,
|
|
model_alias="default_llm",
|
|
gpu_device="0",
|
|
restart_policy="unless-stopped",
|
|
ctx_size=262144,
|
|
n_predict=16384,
|
|
temp=0.65,
|
|
top_p=0.80,
|
|
top_k=20,
|
|
min_p=0.01,
|
|
repeat_penalty=1.05,
|
|
main_gpu=0,
|
|
ngl=999,
|
|
batch_size=1024,
|
|
ubatch_size=512,
|
|
parallel=1,
|
|
cache_type_k="q4_0",
|
|
cache_type_v="q4_0",
|
|
reasoning="on",
|
|
jinja=True,
|
|
fa=True,
|
|
kv_unified=True,
|
|
cont_batching=True,
|
|
no_context_shift=True,
|
|
host="0.0.0.0",
|
|
health_endpoint="/health",
|
|
models_endpoint="/v1/models",
|
|
chat_endpoint="/v1/chat/completions",
|
|
timeout=300,
|
|
poll_interval=2.0,
|
|
lock_file=Path("/tmp/llamacppctl.test_llm.lock"),
|
|
)
|
|
base.update(overrides)
|
|
return ServerConfig(**base)
|
|
|
|
|
|
def test_docker_available_true():
|
|
with patch("subprocess.run") as mock_run:
|
|
mock_run.return_value = MagicMock(returncode=0)
|
|
assert docker_available() is True
|
|
|
|
|
|
def test_docker_available_false_when_missing():
|
|
with patch("subprocess.run", side_effect=FileNotFoundError()):
|
|
assert docker_available() is False
|
|
|
|
|
|
def test_container_exists_true():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="test_llm\nother\n")
|
|
assert container_exists("test_llm") is True
|
|
|
|
|
|
def test_container_exists_false():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="other\n")
|
|
assert container_exists("test_llm") is False
|
|
|
|
|
|
def test_container_running_true():
|
|
with patch("llamacppctl.docker_ops._run") as mock_run:
|
|
mock_run.return_value = MagicMock(stdout="test_llm\n")
|
|
assert container_running("test_llm") is True
|
|
|
|
|
|
def test_inspect_container_missing():
|
|
with patch("llamacppctl.docker_ops.container_exists", return_value=False):
|
|
info = inspect_container("ghost")
|
|
assert info.status == "missing"
|
|
assert info.health == "none"
|
|
|
|
|
|
def test_inspect_container_running():
|
|
fake_json = (
|
|
'[{"State": {"Status": "running", "Health": {"Status": "healthy"}}}]'
|
|
)
|
|
with patch("llamacppctl.docker_ops.container_exists", return_value=True), patch(
|
|
"llamacppctl.docker_ops._run"
|
|
) as mock_run:
|
|
mock_run.return_value = MagicMock(stdout=fake_json)
|
|
info = inspect_container("test_llm")
|
|
assert info.status == "running"
|
|
assert info.health == "healthy"
|
|
|
|
|
|
def test_build_run_command_contains_key_flags():
|
|
cfg = make_cfg()
|
|
cmd = build_run_command(cfg)
|
|
assert cmd[0:2] == ["docker", "run"]
|
|
assert "--gpus" in cmd
|
|
assert "device=0" in cmd
|
|
assert "--name" in cmd
|
|
assert "test_llm" in cmd
|
|
assert "-p" in cmd
|
|
assert "8001:8000" in cmd
|
|
assert "--jinja" in cmd
|
|
assert "--reasoning" in cmd
|
|
assert "on" in cmd
|
|
assert "--no-context-shift" in cmd
|
|
assert "--kv-unified" in cmd
|
|
assert "--cont-batching" in cmd
|
|
|
|
|
|
def test_build_run_command_respects_disabled_flags():
|
|
cfg = make_cfg(jinja=False, kv_unified=False, cont_batching=False, no_context_shift=False, fa=False)
|
|
cmd = build_run_command(cfg)
|
|
assert "--jinja" not in cmd
|
|
assert "--kv-unified" not in cmd
|
|
assert "--cont-batching" not in cmd
|
|
assert "--no-context-shift" not in cmd
|
|
|
|
|
|
def test_build_run_command_absolute_model_path():
|
|
cfg = make_cfg(model_path="/abs/path/model.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("-m")
|
|
assert cmd[idx + 1] == "/abs/path/model.gguf"
|
|
|
|
|
|
def test_build_run_command_relative_model_path():
|
|
cfg = make_cfg(model_path="qwen3/default.gguf")
|
|
cmd = build_run_command(cfg)
|
|
idx = cmd.index("-m")
|
|
assert cmd[idx + 1] == "/hf_home/qwen3/default.gguf"
|
|
|
|
|
|
def test_format_command_for_display_quotes_properly():
|
|
cmd = ["docker", "run", "--name", "has space"]
|
|
out = format_command_for_display(cmd)
|
|
assert "'has space'" in out
|