fix: update Gemini model catalog + wire models.dev as live model source

Follow-up for salvaged PR #5494:
- Update model catalog to Gemini 3.x + Gemma 4 (drop deprecated 2.0)
- Add list_agentic_models() to models_dev.py with noise filter
- Wire models.dev into _model_flow_api_key_provider as primary source
  (static curated list serves as offline fallback)
- Add gemini -> google mapping in PROVIDER_TO_MODELS_DEV
- Fix Gemma 4 context lengths to 256K (models.dev values)
- Update auxiliary model to gemini-3-flash-preview
- Expand tests: 3.x catalog, context lengths, models.dev integration

hermes_cli/main.py

@@ -2211,24 +2211,37 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         save_env_value(base_url_env, override)
         effective_base = override
 
-    # Model selection — try live /models endpoint first, fall back to defaults.
-    # Providers with large live catalogs (100+ models) use a curated list instead
-    # so users see familiar model names rather than an overwhelming dump.
+    # Model selection — resolution order:
+    #   1. models.dev registry (cached, filtered for agentic/tool-capable models)
+    #   2. Curated static fallback list (offline insurance)
+    #   3. Live /models endpoint probe (small providers without models.dev data)
     curated = _PROVIDER_MODELS.get(provider_id, [])
-    if curated and len(curated) >= 8:
+
+    # Try models.dev first — returns tool-capable models, filtered for noise
+    mdev_models: list = []
+    try:
+        from agent.models_dev import list_agentic_models
+        mdev_models = list_agentic_models(provider_id)
+    except Exception:
+        pass
+
+    if mdev_models:
+        model_list = mdev_models
+        print(f"  Found {len(model_list)} model(s) from models.dev registry")
+    elif curated and len(curated) >= 8:
         # Curated list is substantial — use it directly, skip live probe
-        live_models = None
+        model_list = curated
+        print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
     else:
         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)
-
-    if live_models and len(live_models) >= len(curated):
-        model_list = live_models
-        print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
-    else:
-        model_list = curated
-        if model_list:
-            print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
+        if live_models and len(live_models) >= len(curated):
+            model_list = live_models
+            print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
+        else:
+            model_list = curated
+            if model_list:
+                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"}:

hermes_cli/models.py

@@ -112,15 +112,15 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "grok-code-fast-1",
     ],
     "gemini": [
+        "gemini-3.1-pro-preview",
+        "gemini-3-flash-preview",
+        "gemini-3.1-flash-lite-preview",
         "gemini-2.5-pro",
         "gemini-2.5-flash",
-        "gemini-2.0-flash",
-        "gemini-2.0-flash-lite",
+        "gemini-2.5-flash-lite",
         # Gemma open models (also served via AI Studio)
         "gemma-4-31b-it",
-        "gemma-4-26b-a4b-it",
-        "gemma-4-e4b-it",
-        "gemma-4-e2b-it",
+        "gemma-4-26b-it",
     ],
     "zai": [
         "glm-5",

hermes_cli/setup.py

@@ -112,8 +112,9 @@ _DEFAULT_PROVIDER_MODELS = {
         "grok-code-fast-1",
     ],
     "gemini": [
-        "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.0-flash", "gemini-2.0-flash-lite",
-        "gemma-4-31b-it", "gemma-4-26b-a4b-it", "gemma-4-e4b-it", "gemma-4-e2b-it",
+        "gemini-3.1-pro-preview", "gemini-3-flash-preview", "gemini-3.1-flash-lite-preview",
+        "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite",
+        "gemma-4-31b-it", "gemma-4-26b-it",
     ],
     "zai": ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
     "kimi-coding": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],