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>

hermes_cli/main.py

@@ -1645,81 +1645,8 @@ def _model_flow_named_custom(config, provider_info):
     print(f"   Provider: {name} ({base_url})")
 
 
-# Curated model lists for direct API-key providers
-_PROVIDER_MODELS = {
-    "copilot-acp": [
-        "copilot-acp",
-    ],
-    "copilot": [
-        "gpt-5.4",
-        "gpt-5.4-mini",
-        "gpt-5-mini",
-        "gpt-5.3-codex",
-        "gpt-5.2-codex",
-        "gpt-4.1",
-        "gpt-4o",
-        "gpt-4o-mini",
-        "claude-opus-4.6",
-        "claude-sonnet-4.6",
-        "claude-sonnet-4.5",
-        "claude-haiku-4.5",
-        "gemini-2.5-pro",
-        "grok-code-fast-1",
-    ],
-    "zai": [
-        "glm-5",
-        "glm-4.7",
-        "glm-4.5",
-        "glm-4.5-flash",
-    ],
-    "kimi-coding": [
-        "kimi-for-coding",
-        "kimi-k2.5",
-        "kimi-k2-thinking",
-        "kimi-k2-thinking-turbo",
-        "kimi-k2-turbo-preview",
-        "kimi-k2-0905-preview",
-    ],
-    "moonshot": [
-        "kimi-k2.5",
-        "kimi-k2-thinking",
-        "kimi-k2-turbo-preview",
-        "kimi-k2-0905-preview",
-    ],
-    "minimax": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
-        "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
-    ],
-    "minimax-cn": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
-        "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
-    ],
-    "kilocode": [
-        "anthropic/claude-opus-4.6",
-        "anthropic/claude-sonnet-4.6",
-        "openai/gpt-5.4",
-        "google/gemini-3-pro-preview",
-        "google/gemini-3-flash-preview",
-    ],
-    # Curated HF model list — only agentic models that map to OpenRouter defaults.
-    # Format: HF model ID → OpenRouter equivalent noted in comment
-    "huggingface": [
-        "Qwen/Qwen3.5-397B-A17B",                  # ↔ qwen/qwen3.5-plus
-        "Qwen/Qwen3.5-35B-A3B",                     # ↔ qwen/qwen3.5-35b-a3b
-        "deepseek-ai/DeepSeek-V3.2",                # ↔ deepseek/deepseek-chat
-        "moonshotai/Kimi-K2.5",                      # ↔ moonshotai/kimi-k2.5
-        "MiniMaxAI/MiniMax-M2.5",                    # ↔ minimax/minimax-m2.5
-        "zai-org/GLM-5",                             # ↔ z-ai/glm-5
-        "XiaomiMiMo/MiMo-V2-Flash",                 # ↔ xiaomi/mimo-v2-pro
-        "moonshotai/Kimi-K2-Thinking",               # ↔ moonshotai/kimi-k2-thinking
-    ],
-}
+# Curated model lists for direct API-key providers — single source in models.py
+from hermes_cli.models import _PROVIDER_MODELS
 
 
 def _current_reasoning_effort(config) -> str:
@@ -2188,12 +2115,13 @@ def _model_flow_kimi(config, current_model=""):
 
 
 def _model_flow_api_key_provider(config, provider_id, current_model=""):
-    """Generic flow for API-key providers (z.ai, MiniMax)."""
+    """Generic flow for API-key providers (z.ai, MiniMax, OpenCode, etc.)."""
     from hermes_cli.auth import (
         PROVIDER_REGISTRY, _prompt_model_selection, _save_model_choice,
         deactivate_provider,
     )
     from hermes_cli.config import get_env_value, save_env_value, load_config, save_config
+    from hermes_cli.models import fetch_api_models, opencode_model_api_mode, normalize_opencode_model_id
 
     pconfig = PROVIDER_REGISTRY[provider_id]
     key_env = pconfig.api_key_env_vars[0] if pconfig.api_key_env_vars else ""
@@ -2247,7 +2175,6 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         # Curated list is substantial — use it directly, skip live probe
         live_models = None
     else:
-        from hermes_cli.models import fetch_api_models
         api_key_for_probe = existing_key or (get_env_value(key_env) if key_env else "")
         live_models = fetch_api_models(api_key_for_probe, effective_base)
 
@@ -2260,6 +2187,11 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
             print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
         # else: no defaults either, will fall through to raw input
 
+    if provider_id in {"opencode-zen", "opencode-go"}:
+        model_list = [normalize_opencode_model_id(provider_id, mid) for mid in model_list]
+        current_model = normalize_opencode_model_id(provider_id, current_model)
+        model_list = list(dict.fromkeys(mid for mid in model_list if mid))
+
     if model_list:
         selected = _prompt_model_selection(model_list, current_model=current_model)
     else:
@@ -2269,9 +2201,12 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
             selected = None
 
     if selected:
+        if provider_id in {"opencode-zen", "opencode-go"}:
+            selected = normalize_opencode_model_id(provider_id, selected)
+
         _save_model_choice(selected)
 
-        # Update config with provider and base URL
+        # Update config with provider, base URL, and provider-specific API mode
         cfg = load_config()
         model = cfg.get("model")
         if not isinstance(model, dict):
@@ -2279,7 +2214,10 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
             cfg["model"] = model
         model["provider"] = provider_id
         model["base_url"] = effective_base
-        model.pop("api_mode", None)  # let runtime auto-detect from URL
+        if provider_id in {"opencode-zen", "opencode-go"}:
+            model["api_mode"] = opencode_model_api_mode(provider_id, selected)
+        else:
+            model.pop("api_mode", None)
         save_config(cfg)
         deactivate_provider()