feat(custom): prompt and persist explicit api_mode for custom providers

Adds an explicit API compatibility mode prompt to the `hermes model -> custom`
flow so Codex-compatible third-party endpoints (and any other non-default
backend whose URL doesn't match the existing heuristics in
`_detect_api_mode_for_url`) can be selected explicitly instead of silently
falling back to chat_completions.

Choices: Auto-detect / chat_completions / codex_responses / anthropic_messages.

Persists `api_mode` to:
  - `model.api_mode` (active session config)
  - the matching `custom_providers[*]` entry (so re-activating the named
    provider next time replays the same transport)

Salvaged from PR #6125 onto current main: kept the new prompt and the
`_save_custom_provider(api_mode=...)` plumbing; the named-custom flow
already extracts and applies `api_mode` from the saved entry on current
main so those changes are preserved as-is. Test fixtures updated for the
new prompt and the existing display-name prompt.

Co-authored-by: littlewwwhite <1095245867@qq.com>

tests/cli/test_cli_provider_resolution.py

@@ -531,8 +531,8 @@ def test_model_flow_custom_saves_verified_v1_base_url(monkeypatch, capsys):
 
     # After the probe detects a single model ("llm"), the flow asks
     # "Use this model? [Y/n]:" — confirm with Enter, then context length,
-    # then display name.
-    answers = iter(["http://localhost:8000", "local-key", "", "", "", ""])
+    # then display name. The api_mode prompt also runs before model selection.
+    answers = iter(["http://localhost:8000", "local-key", "", "", "", "", ""])
     monkeypatch.setattr("builtins.input", lambda _prompt="": next(answers))
     monkeypatch.setattr("getpass.getpass", lambda _prompt="": next(answers))
 
@@ -546,6 +546,63 @@ def test_model_flow_custom_saves_verified_v1_base_url(monkeypatch, capsys):
     assert saved_env["MODEL"] == "llm"
 
 
+def test_model_flow_custom_persists_selected_api_mode(monkeypatch):
+    saved_cfg = {"model": {"default": "", "provider": "custom", "base_url": ""}}
+    captured_provider = {}
+
+    monkeypatch.setattr(
+        "hermes_cli.config.get_env_value",
+        lambda key: "" if key in {"OPENAI_BASE_URL", "OPENAI_API_KEY"} else "",
+    )
+    monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
+    monkeypatch.setattr("hermes_cli.auth.deactivate_provider", lambda: None)
+    monkeypatch.setattr(
+        "hermes_cli.models.probe_api_models",
+        lambda api_key, base_url: {
+            "models": [],
+            "probed_url": f"{base_url.rstrip('/')}/models",
+            "resolved_base_url": None,
+            "suggested_base_url": None,
+            "used_fallback": False,
+        },
+    )
+    monkeypatch.setattr("hermes_cli.config.load_config", lambda: saved_cfg)
+    monkeypatch.setattr("hermes_cli.config.save_config", lambda cfg: saved_cfg.update(cfg))
+    monkeypatch.setattr(
+        "hermes_cli.main._save_custom_provider",
+        lambda base_url, api_key="", model="", context_length=None, name=None, api_mode=None: captured_provider.update(
+            {
+                "base_url": base_url,
+                "api_key": api_key,
+                "model": model,
+                "context_length": context_length,
+                "name": name,
+                "api_mode": api_mode,
+            }
+        ),
+    )
+
+    answers = iter(
+        [
+            "https://codex.example.com/v1",
+            "3",
+            "chosen-model",
+            "",
+            "",
+        ]
+    )
+    monkeypatch.setattr("builtins.input", lambda _prompt="": next(answers))
+    monkeypatch.setattr("getpass.getpass", lambda _prompt="": "test-key")
+
+    hermes_main._model_flow_custom({"model": {"provider": "custom"}})
+
+    assert saved_cfg["model"]["provider"] == "custom"
+    assert saved_cfg["model"]["base_url"] == "https://codex.example.com/v1"
+    assert saved_cfg["model"]["api_key"] == "test-key"
+    assert saved_cfg["model"]["api_mode"] == "codex_responses"
+    assert captured_provider["api_mode"] == "codex_responses"
+
+
 def test_cmd_model_forwards_nous_login_tls_options(monkeypatch):
     monkeypatch.setattr(hermes_main, "_require_tty", lambda *a: None)
     monkeypatch.setattr(

tests/hermes_cli/test_model_provider_persistence.py

@@ -177,6 +177,40 @@ class TestProviderPersistsAfterModelSave:
         assert model.get("api_mode") == "codex_responses"
         assert config["agent"]["reasoning_effort"] == "high"
 
+    def test_named_custom_provider_preserves_explicit_api_mode(self, config_home):
+        """Named custom providers should re-activate with their saved api_mode."""
+        import yaml
+
+        from hermes_cli.main import _model_flow_named_custom
+
+        provider_info = {
+            "name": "Packy",
+            "base_url": "https://packy.example.com/v1",
+            "api_key": "sk-test",
+            "model": "gpt-5.4",
+            "api_mode": "codex_responses",
+        }
+
+        # Patch fetch_api_models so the named custom flow returns one model;
+        # patch simple_term_menu to force the input() fallback; patch input to
+        # auto-select the first model from the fallback prompt.
+        from unittest.mock import MagicMock
+        fake_menu_module = MagicMock()
+        fake_menu_module.TerminalMenu.side_effect = OSError("no tty in test")
+        with patch("hermes_cli.auth._save_model_choice"), \
+             patch("hermes_cli.auth.deactivate_provider"), \
+             patch("hermes_cli.models.fetch_api_models", return_value=["gpt-5.4"]), \
+             patch.dict("sys.modules", {"simple_term_menu": fake_menu_module}), \
+             patch("builtins.input", return_value="1"):
+            _model_flow_named_custom({}, provider_info)
+
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict)
+        assert model.get("provider") == "custom"
+        assert model.get("base_url") == "https://packy.example.com/v1"
+        assert model.get("api_mode") == "codex_responses"
+
     def test_copilot_acp_provider_saved_when_selected(self, config_home):
         """_model_flow_copilot_acp should persist provider/base_url/model together."""
         from hermes_cli.main import _model_flow_copilot_acp