test(cli): drop lite --version subprocess regression

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

tests/test_litellm/proxy/client/cli/test_global_options.py

@@ -1,10 +1,6 @@
 # stdlib imports
 import json
 import os
-import shutil
-import subprocess
-import threading
-from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from unittest.mock import Mock, patch
 
@@ -37,58 +33,6 @@ def test_cli_version_flag(cli_runner):
     assert "LiteLLM Proxy Server Version: 1.2.3" in result.output
 
 
-def test_lite_version_does_not_fetch_model_cost_map(tmp_path: Path) -> None:
-    lite_path = shutil.which("lite")
-    if lite_path is None:
-        pytest.skip("lite executable is unavailable")
-
-    request_log: Path = tmp_path / "requests.log"
-
-    class _CostMapHandler(BaseHTTPRequestHandler):
-        def do_GET(self) -> None:
-            with request_log.open("a", encoding="utf-8") as log_file:
-                log_file.write(f"{self.path}\n")
-            body = b'{"test-model": {"litellm_provider": "openai", "mode": "chat"}}'
-            self.send_response(200)
-            self.send_header("Content-Type", "application/json")
-            self.send_header("Content-Length", str(len(body)))
-            self.end_headers()
-            self.wfile.write(body)
-
-        def log_message(self, format: str, *args: object) -> None:
-            return
-
-    server = ThreadingHTTPServer(("127.0.0.1", 0), _CostMapHandler)
-    thread = threading.Thread(target=server.serve_forever, daemon=True)
-    thread.start()
-    try:
-        env = {key: value for key, value in os.environ.items() if key != "LITELLM_LOCAL_MODEL_COST_MAP"}
-        source_root = str(Path(__file__).resolve().parents[5])
-        env["PYTHONPATH"] = os.pathsep.join(filter(None, (source_root, env.get("PYTHONPATH"))))
-        env.update(
-            {
-                "LITELLM_MODEL_COST_MAP_URL": f"http://127.0.0.1:{server.server_port}/map.json",
-                "LITELLM_PROXY_URL": "http://127.0.0.1:9",
-            }
-        )
-        result = subprocess.run(
-            [lite_path, "--version"],
-            capture_output=True,
-            text=True,
-            timeout=120,
-            env=env,
-        )
-    finally:
-        server.shutdown()
-        server.server_close()
-        thread.join(timeout=10)
-
-    assert result.returncode == 0
-    assert "LiteLLM Proxy CLI Version" in result.stdout
-    request_count: int = request_log.read_text(encoding="utf-8").count("\n") if request_log.exists() else 0
-    assert request_count == 0
-
-
 def test_cli_source_is_ascii_only():
     """Non-ASCII output (emoji, box-drawing chars) raises UnicodeEncodeError on legacy Windows
     consoles (cp1252), so the whole CLI package must stay ASCII-only."""