fix: repair OpenCode model routing and selection (#4508)

OpenCode Zen and Go are mixed-API-surface providers — different models
behind them use different API surfaces (GPT on Zen uses codex_responses,
Claude on Zen uses anthropic_messages, MiniMax on Go uses
anthropic_messages, GLM/Kimi on Go use chat_completions).

Changes:
- Add normalize_opencode_model_id() and opencode_model_api_mode() to
  models.py for model ID normalization and API surface routing
- Add _provider_supports_explicit_api_mode() to runtime_provider.py
  to prevent stale api_mode from leaking across provider switches
- Wire opencode routing into all three api_mode resolution paths:
  pool entry, api_key provider, and explicit runtime
- Add api_mode field to ModelSwitchResult for propagation through the
  switch pipeline
- Consolidate _PROVIDER_MODELS from main.py into models.py (single
  source of truth, eliminates duplicate dict)
- Add opencode normalization to setup wizard and model picker flows
- Add opencode block to _normalize_model_for_provider in CLI
- Add opencode-zen/go fallback model lists to setup.py

Tests: 160 targeted tests pass (26 new tests covering normalization,
api_mode routing per provider/model, persistence, and setup wizard
normalization).

Based on PR #3017 by SaM13997.

Co-authored-by: SaM13997 <139419381+SaM13997@users.noreply.github.com>

tests/test_model_provider_persistence.py

@@ -210,3 +210,50 @@ class TestProviderPersistsAfterModelSave:
         assert model.get("base_url") == "acp://copilot"
         assert model.get("default") == "gpt-5.4"
         assert model.get("api_mode") == "chat_completions"
+
+    def test_opencode_go_models_are_selectable_and_persist_normalized(self, config_home, monkeypatch):
+        from hermes_cli.main import _model_flow_api_key_provider
+        from hermes_cli.config import load_config
+
+        monkeypatch.setenv("OPENCODE_GO_API_KEY", "test-key")
+
+        with patch("hermes_cli.models.fetch_api_models", return_value=["opencode-go/kimi-k2.5", "opencode-go/minimax-m2.7"]), \
+             patch("hermes_cli.auth._prompt_model_selection", return_value="kimi-k2.5"), \
+             patch("hermes_cli.auth.deactivate_provider"), \
+             patch("builtins.input", return_value=""):
+            _model_flow_api_key_provider(load_config(), "opencode-go", "opencode-go/kimi-k2.5")
+
+        import yaml
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict)
+        assert model.get("provider") == "opencode-go"
+        assert model.get("default") == "kimi-k2.5"
+        assert model.get("api_mode") == "chat_completions"
+
+    def test_opencode_go_same_provider_switch_recomputes_api_mode(self, config_home, monkeypatch):
+        from hermes_cli.main import _model_flow_api_key_provider
+        from hermes_cli.config import load_config
+
+        monkeypatch.setenv("OPENCODE_GO_API_KEY", "test-key")
+        (config_home / "config.yaml").write_text(
+            "model:\n"
+            "  default: kimi-k2.5\n"
+            "  provider: opencode-go\n"
+            "  base_url: https://opencode.ai/zen/go/v1\n"
+            "  api_mode: chat_completions\n"
+        )
+
+        with patch("hermes_cli.models.fetch_api_models", return_value=["opencode-go/kimi-k2.5", "opencode-go/minimax-m2.5"]), \
+             patch("hermes_cli.auth._prompt_model_selection", return_value="minimax-m2.5"), \
+             patch("hermes_cli.auth.deactivate_provider"), \
+             patch("builtins.input", return_value=""):
+            _model_flow_api_key_provider(load_config(), "opencode-go", "kimi-k2.5")
+
+        import yaml
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict)
+        assert model.get("provider") == "opencode-go"
+        assert model.get("default") == "minimax-m2.5"
+        assert model.get("api_mode") == "anthropic_messages"