feat: harden and extend the CLI (security, UX, robustness, tests)

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>

tests/test_http_ops.py

@@ -64,7 +64,9 @@ def test_chat_completion_text_success():
         mock_resp = MagicMock(status_code=200)
         mock_resp.json.return_value = {"choices": [{"message": {"content": "ok"}}]}
         mock_post.return_value = mock_resp
-        assert chat_completion_text(cfg, prompt_cfg) == "ok"
+        reply = chat_completion_text(cfg, prompt_cfg)
+        assert reply.content == "ok"
+        assert reply.finish_reason == ""
 
 
 def test_chat_completion_text_honors_chat_endpoint():
@@ -116,6 +118,53 @@ def test_chat_completion_text_malformed_response():
             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)