Sieben Verbesserungen; die Dateien überschneiden sich thematisch, daher ein Commit (jeder Commit bleibt grün: 115 Tests). - #1 --check ist scriptbar: Exit 0 wenn Container läuft und erreichbar, sonst 5 (check_exit_code / CheckResult). - #2 --force implementiert: Bypass eines belegten Locks mit Warnung (_container_lock) und stop_container(force=…) schluckt Inkonsistenzen. - #3 stille Trunkierung behoben: chat_completion_text liefert ChatReply (content + finish_reason); bei finish_reason=length Hinweis auf stderr, --chat gibt Exit 1 bei leerem Content zurück. - #4 keine vermeidbare Downtime: --change validiert den Modellpfad VOR dem Entfernen des laufenden Containers. - #5 Netzwerk dicht: Port-Publish standardmäßig nur auf 127.0.0.1 (--expose/expose für alle Interfaces), optionaler --api-key/api_key (Server --api-key + Bearer-Token auf allen Requests). - #6 --stream: Chat-Reply token-weise via SSE auf stdout (stream_chat). - #7 tests/test_actions.py: Orchestrierungs-Ebene (dry-run-Nebenwirkungen, Lock, validate-before-remove, chat/stream/exit-codes). Doku aktualisiert (Manpage, README, llama.cpp.config.example). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
181 lines
6.3 KiB
Python
181 lines
6.3 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"))
|
|
|
|
import requests # noqa: E402
|
|
|
|
from llamacppctl.http_ops import ( # noqa: E402
|
|
HttpError,
|
|
base_url,
|
|
chat_completion,
|
|
chat_completion_text,
|
|
check_health,
|
|
check_models,
|
|
wait_until_ready,
|
|
)
|
|
from llamacppctl.schema import PromptConfig, ServerConfig # noqa: E402
|
|
from tests.test_docker_ops import make_cfg # noqa: E402
|
|
|
|
|
|
def test_base_url():
|
|
cfg = make_cfg(host_port=8001)
|
|
assert base_url(cfg) == "http://127.0.0.1:8001/v1"
|
|
|
|
|
|
def test_check_health_ok():
|
|
cfg = make_cfg()
|
|
with patch("requests.get") as mock_get:
|
|
mock_get.return_value = MagicMock(ok=True)
|
|
assert check_health(cfg) is True
|
|
|
|
|
|
def test_check_health_exception_returns_false():
|
|
cfg = make_cfg()
|
|
with patch("requests.get", side_effect=requests.RequestException("boom")):
|
|
assert check_health(cfg) is False
|
|
|
|
|
|
def test_check_models_ok():
|
|
cfg = make_cfg()
|
|
with patch("requests.get") as mock_get:
|
|
mock_get.return_value = MagicMock(ok=True)
|
|
assert check_models(cfg) is True
|
|
|
|
|
|
def test_chat_completion_posts_expected_payload():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(system_prompt="sys", user_prompt="hi", max_tokens=32, temperature=0.1)
|
|
with patch("requests.post") as mock_post:
|
|
mock_post.return_value = MagicMock(status_code=200)
|
|
chat_completion(cfg, prompt_cfg)
|
|
_, kwargs = mock_post.call_args
|
|
payload = kwargs["json"]
|
|
assert payload["messages"][0] == {"role": "system", "content": "sys"}
|
|
assert payload["messages"][1] == {"role": "user", "content": "hi"}
|
|
assert payload["max_tokens"] == 32
|
|
|
|
|
|
def test_chat_completion_text_success():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.json.return_value = {"choices": [{"message": {"content": "ok"}}]}
|
|
mock_post.return_value = mock_resp
|
|
reply = chat_completion_text(cfg, prompt_cfg)
|
|
assert reply.content == "ok"
|
|
assert reply.finish_reason == ""
|
|
|
|
|
|
def test_chat_completion_text_honors_chat_endpoint():
|
|
cfg = make_cfg(host_port=8001, chat_endpoint="/custom/chat")
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.json.return_value = {"choices": [{"message": {"content": "ok"}}]}
|
|
mock_post.return_value = mock_resp
|
|
chat_completion_text(cfg, prompt_cfg)
|
|
args, _ = mock_post.call_args
|
|
assert args[0] == "http://127.0.0.1:8001/custom/chat"
|
|
|
|
|
|
def test_chat_completion_text_http_error():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_post.return_value = MagicMock(status_code=500, text="server error")
|
|
try:
|
|
chat_completion_text(cfg, prompt_cfg)
|
|
assert False, "expected HttpError"
|
|
except HttpError:
|
|
pass
|
|
|
|
|
|
def test_chat_completion_text_transport_error():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post", side_effect=requests.RequestException("down")):
|
|
try:
|
|
chat_completion_text(cfg, prompt_cfg)
|
|
assert False, "expected HttpError"
|
|
except HttpError:
|
|
pass
|
|
|
|
|
|
def test_chat_completion_text_malformed_response():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.json.return_value = {"unexpected": True}
|
|
mock_post.return_value = mock_resp
|
|
try:
|
|
chat_completion_text(cfg, prompt_cfg)
|
|
assert False, "expected HttpError"
|
|
except HttpError:
|
|
pass
|
|
|
|
|
|
def test_chat_completion_text_reports_finish_reason():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.json.return_value = {
|
|
"choices": [{"finish_reason": "length", "message": {"content": ""}}]
|
|
}
|
|
mock_post.return_value = mock_resp
|
|
reply = chat_completion_text(cfg, prompt_cfg)
|
|
assert reply.content == ""
|
|
assert reply.finish_reason == "length"
|
|
|
|
|
|
def test_api_key_sent_as_bearer():
|
|
cfg = make_cfg(api_key="secret123")
|
|
prompt_cfg = PromptConfig(user_prompt="hi")
|
|
with patch("requests.post") as mock_post:
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.json.return_value = {"choices": [{"message": {"content": "x"}}]}
|
|
mock_post.return_value = mock_resp
|
|
chat_completion_text(cfg, prompt_cfg)
|
|
_, kwargs = mock_post.call_args
|
|
assert kwargs["headers"]["Authorization"] == "Bearer secret123"
|
|
|
|
|
|
def test_stream_chat_yields_content_and_finish():
|
|
cfg = make_cfg()
|
|
prompt_cfg = PromptConfig(user_prompt="hi", stream=True)
|
|
lines = [
|
|
'data: {"choices":[{"delta":{"content":"Hal"}}]}',
|
|
'data: {"choices":[{"delta":{"content":"lo"}}]}',
|
|
'data: {"choices":[{"delta":{},"finish_reason":"stop"}]}',
|
|
"data: [DONE]",
|
|
]
|
|
mock_resp = MagicMock(status_code=200)
|
|
mock_resp.iter_lines.return_value = iter(lines)
|
|
with patch("requests.post", return_value=mock_resp):
|
|
from llamacppctl.http_ops import stream_chat
|
|
|
|
events = list(stream_chat(cfg, prompt_cfg))
|
|
contents = [v for k, v in events if k == "content"]
|
|
finishes = [v for k, v in events if k == "finish"]
|
|
assert "".join(contents) == "Hallo"
|
|
assert finishes == ["stop"]
|
|
|
|
|
|
def test_wait_until_ready_succeeds_immediately():
|
|
cfg = make_cfg(timeout=5, poll_interval=0.01)
|
|
probe = PromptConfig(user_prompt="ping", max_tokens=1)
|
|
with patch("llamacppctl.http_ops.chat_completion") as mock_chat:
|
|
mock_chat.return_value = MagicMock(status_code=200)
|
|
assert wait_until_ready(cfg, probe) is True
|
|
|
|
|
|
def test_wait_until_ready_times_out():
|
|
cfg = make_cfg(timeout=0, poll_interval=0.01)
|
|
probe = PromptConfig(user_prompt="ping", max_tokens=1)
|
|
with patch("llamacppctl.http_ops.chat_completion") as mock_chat:
|
|
mock_chat.return_value = MagicMock(status_code=500)
|
|
assert wait_until_ready(cfg, probe) is False
|