fix(cli): address greptile review feedback on autoroute PR

- terminate the ephemeral proxy child process when its health check
  fails, instead of leaking an orphaned, unrecoverable process bound
  to the port
- replace bare assert isinstance checks (no-ops under python -O) with
  click.ClickException in the model-groups list and configure wizard
  code paths
- close launch_proxy's log file handle once the child process has
  inherited its fd, instead of leaking it
- add build_generated_proxy_config to config.py's __all__

litellm/proxy/client/cli/commands/autoroute/commands.py

@@ -92,6 +92,7 @@ def up() -> None:
     try:
         poll_liveliness(base_url, LOG_PATH, process)
     except ProcessLaunchError as e:
+        terminate(process.pid)
         clear_pid_record()
         raise click.ClickException(str(e))
 

litellm/proxy/client/cli/commands/autoroute/config.py

@@ -229,6 +229,7 @@ __all__ = [
     "SemanticMatching",
     "SemanticMatchingChoice",
     "build_generated_model_list",
+    "build_generated_proxy_config",
     "chat_models",
     "embedding_models",
     "parse_discovered_models",

litellm/proxy/client/cli/commands/autoroute/process.py

@@ -66,12 +66,12 @@ def allocate_free_port() -> int:
 
 def launch_proxy(config_path: Path, port: int, log_path: Path) -> "subprocess.Popen[bytes]":
     log_path.parent.mkdir(parents=True, exist_ok=True)
-    log_file = open(log_path, "w")
-    return subprocess.Popen(
-        [sys.executable, "-m", "litellm.proxy.proxy_cli", "--config", str(config_path), "--port", str(port)],
-        stdout=log_file,
-        stderr=subprocess.STDOUT,
-    )
+    with open(log_path, "w") as log_file:
+        return subprocess.Popen(
+            [sys.executable, "-m", "litellm.proxy.proxy_cli", "--config", str(config_path), "--port", str(port)],
+            stdout=log_file,
+            stderr=subprocess.STDOUT,
+        )
 
 
 def _tail(log_path: Path, lines: int = 40) -> str:

litellm/proxy/client/cli/commands/autoroute/wizard.py

@@ -70,7 +70,10 @@ def run_configure_wizard(ctx: click.Context) -> Path:
     client = Client(base_url=base_url, api_key=api_key)
 
     raw_groups = client.model_groups.info()
-    assert isinstance(raw_groups, list)
+    if not isinstance(raw_groups, list):
+        raise click.ClickException(
+            f"Unexpected response from /model_group/info: expected a list, got {type(raw_groups).__name__}"
+        )
     discovered = parse_discovered_models(raw_groups)
     chat_pool = chat_models(discovered)
     embedding_pool = embedding_models(discovered)

litellm/proxy/client/cli/commands/model_groups.py

@@ -29,7 +29,10 @@ def list_model_groups(ctx: click.Context, output_format: Literal["table", "json"
     """List model groups accessible to your key, with mode and pricing"""
     client = create_client(ctx)
     groups = client.model_groups.info()
-    assert isinstance(groups, list)
+    if not isinstance(groups, list):
+        raise click.ClickException(
+            f"Unexpected response from /model_group/info: expected a list, got {type(groups).__name__}"
+        )
 
     if output_format == "json":
         rich.print_json(data=groups)

tests/test_litellm/proxy/client/cli/autoroute/test_commands.py

@@ -122,6 +122,7 @@ class TestUpCommand:
         claude_settings_path.write_text(json.dumps(original_settings))
 
         fake_process = FakeProcess(pid=555)
+        terminate_calls = []
 
         def _raise_launch_error(*args, **kwargs):
             raise ProcessLaunchError("boom: proxy never became healthy")
@@ -129,12 +130,14 @@ class TestUpCommand:
         monkeypatch.setattr(commands_module, "launch_proxy", lambda *a, **k: fake_process)
         monkeypatch.setattr(commands_module, "poll_liveliness", _raise_launch_error)
         monkeypatch.setattr(commands_module, "allocate_free_port", lambda: 12345)
+        monkeypatch.setattr(commands_module, "terminate", lambda pid, **k: terminate_calls.append(pid))
         monkeypatch.setattr(commands_module.secrets, "token_urlsafe", lambda n: "fixed-master-key")
 
         result = self.runner.invoke(up)
 
         assert result.exit_code != 0
         assert "boom" in result.output
+        assert terminate_calls == [555]
         assert not pid_record_path.exists()
         assert not backup_path.exists()
         assert json.loads(claude_settings_path.read_text()) == original_settings

tests/test_litellm/proxy/client/cli/autoroute/test_wizard.py

@@ -183,6 +183,14 @@ class TestRunConfigureWizardNoChatModels:
         assert "no chat-capable models" in result.output.lower()
         assert not config_path.exists()
 
+    def test_surfaces_clean_error_when_response_is_not_a_list(self, tmp_path):
+        result, config_path = _run(tmp_path, {"data": CHAT_AND_EMBEDDING_GROUPS}, {}, input_str="")
+
+        assert result.exit_code != 0
+        assert result.exception is None or not isinstance(result.exception, AssertionError)
+        assert "Unexpected response from /model_group/info" in result.output
+        assert not config_path.exists()
+
 
 class TestRunConfigureWizardNotInteractive:
     def test_fails_cleanly_when_not_a_tty(self, tmp_path):

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

@@ -102,3 +102,13 @@ def test_list_error_handling(mock_client, cli_runner):
 
     assert result.exit_code != 0
     assert "API Error" in str(result.exception)
+
+
+def test_list_surfaces_clean_error_when_response_is_not_a_list(mock_client, cli_runner):
+    mock_client.return_value.model_groups.info.return_value = {"data": SAMPLE_MODEL_GROUPS}
+
+    result = cli_runner.invoke(cli, ["model-groups", "list"])
+
+    assert result.exit_code != 0
+    assert result.exception is None or not isinstance(result.exception, AssertionError)
+    assert "Unexpected response from /model_group/info" in result.output