feat(external-llm): standardize tiers and optimize model selection

- Rename tiers: opus/sonnet/haiku → frontier/mid-tier/lightweight
- Align with industry benchmarks (MMLU, GPQA, Chatbot Arena)
- Add /external command for LLM mode control
- Fix invoke.py timeout passthrough (now 600s default)

Tier changes:
- Promote gemini-2.5-pro to frontier (benchmark-validated)
- Demote glm-4.7 to mid-tier then removed (unreliable)
- Promote gemini-2.5-flash to mid-tier

New models added:
- gpt-5-mini, gpt-5-nano (GPT family coverage)
- grok-code (Grok/X family)
- glm-4.5-air (lightweight GLM)

Removed (redundant/unreliable):
- o3 (not available)
- glm-4.7 (timeouts)
- gpt-4o, big-pickle, glm-4.5-flash (redundant)

Final: 11 models across 3 tiers, 4 model families

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

mcp/llm-router/invoke.py

@@ -38,7 +38,7 @@ def resolve_model(args: argparse.Namespace, policy: dict) -> str:
     return policy.get("task_routing", {}).get("default", "copilot/sonnet-4.5")
 
 
-def invoke(model: str, prompt: str, policy: dict) -> str:
+def invoke(model: str, prompt: str, policy: dict, timeout: int = 600) -> str:
     """Invoke the appropriate provider for the given model."""
     external_models = policy.get("external_models", {})
 
@@ -53,11 +53,11 @@ def invoke(model: str, prompt: str, policy: dict) -> str:
     if cli == "opencode":
         sys.path.insert(0, str(ROUTER_DIR))
         from providers.opencode import invoke as opencode_invoke
-        return opencode_invoke(cli_args, prompt)
+        return opencode_invoke(cli_args, prompt, timeout=timeout)
     elif cli == "gemini":
         sys.path.insert(0, str(ROUTER_DIR))
         from providers.gemini import invoke as gemini_invoke
-        return gemini_invoke(cli_args, prompt)
+        return gemini_invoke(cli_args, prompt, timeout=timeout)
     else:
         raise ValueError(f"Unknown CLI: {cli}")
 
@@ -88,8 +88,8 @@ def main():
     parser.add_argument(
         "--timeout",
         type=int,
-        default=300,
-        help="Timeout in seconds (default: 300)"
+        default=600,
+        help="Timeout in seconds (default: 600)"
     )
 
     args = parser.parse_args()
@@ -97,7 +97,7 @@ def main():
     try:
         policy = load_policy()
         model = resolve_model(args, policy)
-        result = invoke(model, args.prompt, policy)
+        result = invoke(model, args.prompt, policy, timeout=args.timeout)
 
         if args.json:
             output = {