feat(external-llm): add external LLM integration (fc-004)

Implements external LLM routing via opencode CLI for:
- GitHub Copilot (gpt-5.2, claude-sonnet-4.5, claude-haiku-4.5, o3, gemini-3-pro)
- Z.AI (glm-4.7 for code generation)
- OpenCode native (big-pickle)

Components:
- mcp/llm-router/invoke.py: Main router with task-based model selection
- mcp/llm-router/delegate.py: Agent delegation helper (respects external mode)
- mcp/llm-router/toggle.py: Enable/disable external-only mode
- mcp/llm-router/providers/: CLI wrappers for opencode and gemini

Features:
- Persistent toggle via state/external-mode.json
- Task routing: reasoning -> gpt-5.2, code-gen -> glm-4.7, long-context -> gemini
- Claude tier mapping: opus -> gpt-5.2, sonnet -> claude-sonnet-4.5, haiku -> claude-haiku-4.5
- Session-start hook announces when external mode is active
- Natural language toggle support via component registry

Plan: gleaming-routing-mercury

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

mcp/llm-router/invoke.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+"""
+Invoke external LLM via configured provider.
+
+Usage:
+    invoke.py --model copilot/gpt-5.2 -p "prompt"
+    invoke.py --task reasoning -p "prompt"
+    invoke.py --task code-generation -p "prompt" --json
+
+Model selection priority:
+    1. Explicit --model flag
+    2. Task-based routing (--task flag)
+    3. Default from policy
+"""
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+STATE_DIR = Path.home() / ".claude/state"
+ROUTER_DIR = Path(__file__).parent
+
+
+def load_policy() -> dict:
+    """Load model policy from state file."""
+    policy_file = STATE_DIR / "model-policy.json"
+    with open(policy_file) as f:
+        return json.load(f)
+
+
+def resolve_model(args: argparse.Namespace, policy: dict) -> str:
+    """Determine which model to use based on args and policy."""
+    if args.model:
+        return args.model
+    if args.task and args.task in policy.get("task_routing", {}):
+        return policy["task_routing"][args.task]
+    return policy.get("task_routing", {}).get("default", "copilot/sonnet-4.5")
+
+
+def invoke(model: str, prompt: str, policy: dict) -> str:
+    """Invoke the appropriate provider for the given model."""
+    external_models = policy.get("external_models", {})
+
+    if model not in external_models:
+        raise ValueError(f"Unknown model: {model}. Available: {list(external_models.keys())}")
+
+    model_config = external_models[model]
+    cli = model_config["cli"]
+    cli_args = model_config.get("cli_args", [])
+
+    # Import and invoke appropriate provider
+    if cli == "opencode":
+        sys.path.insert(0, str(ROUTER_DIR))
+        from providers.opencode import invoke as opencode_invoke
+        return opencode_invoke(cli_args, prompt)
+    elif cli == "gemini":
+        sys.path.insert(0, str(ROUTER_DIR))
+        from providers.gemini import invoke as gemini_invoke
+        return gemini_invoke(cli_args, prompt)
+    else:
+        raise ValueError(f"Unknown CLI: {cli}")
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Invoke external LLM via configured provider"
+    )
+    parser.add_argument(
+        "-p", "--prompt",
+        required=True,
+        help="Prompt text"
+    )
+    parser.add_argument(
+        "--model",
+        help="Explicit model (e.g., copilot/gpt-5.2)"
+    )
+    parser.add_argument(
+        "--task",
+        choices=["reasoning", "code-generation", "long-context", "general"],
+        help="Task type for automatic model routing"
+    )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        help="Output as JSON with model info"
+    )
+    parser.add_argument(
+        "--timeout",
+        type=int,
+        default=300,
+        help="Timeout in seconds (default: 300)"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        policy = load_policy()
+        model = resolve_model(args, policy)
+        result = invoke(model, args.prompt, policy)
+
+        if args.json:
+            output = {
+                "model": model,
+                "response": result,
+                "success": True
+            }
+            print(json.dumps(output, indent=2))
+        else:
+            print(result)
+
+    except Exception as e:
+        if args.json:
+            output = {
+                "model": args.model or "unknown",
+                "error": str(e),
+                "success": False
+            }
+            print(json.dumps(output, indent=2))
+            sys.exit(1)
+        else:
+            print(f"Error: {e}", file=sys.stderr)
+            sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()