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>

commands/README.md

@@ -28,6 +28,7 @@ Slash commands for quick actions. User-invoked (type `/command` to trigger).
 | `/programmer` | | Code development tasks |
 | `/gcal` | `/calendar`, `/cal` | Google Calendar access |
 | `/usage` | `/stats` | View usage statistics |
+| `/external` | `/llm`, `/ext` | Toggle and use external LLM mode |
 
 ### Kubernetes (`/k8s:*`)
 

commands/external.md

@@ -0,0 +1,89 @@
+---
+name: external
+description: Toggle and use external LLM mode (GPT-5.2, Gemini, etc.)
+aliases: [llm, ext, external-llm]
+---
+
+# External LLM Mode
+
+Route requests to external LLMs via opencode or gemini CLI.
+
+## Usage
+
+```
+/external                   # Show current status
+/external on [reason]       # Enable external mode
+/external off               # Disable external mode
+/external invoke <prompt>   # Send prompt to default model
+/external invoke --model <model> <prompt>   # Send to specific model
+/external invoke --task <task> <prompt>     # Route by task type
+/external models            # List available models
+```
+
+## Implementation
+
+### Status
+```bash
+~/.claude/mcp/llm-router/toggle.py status
+```
+
+### Toggle On/Off
+```bash
+~/.claude/mcp/llm-router/toggle.py on --reason "reason"
+~/.claude/mcp/llm-router/toggle.py off
+```
+
+### Invoke
+```bash
+~/.claude/mcp/llm-router/invoke.py --model MODEL -p "prompt" [--json]
+~/.claude/mcp/llm-router/invoke.py --task TASK -p "prompt" [--json]
+```
+
+## Available Models by Tier
+
+### Frontier (strongest)
+| Model | Provider | Best For |
+|-------|----------|----------|
+| `github-copilot/gpt-5.2` | opencode | reasoning, fallback |
+| `github-copilot/gemini-3-pro-preview` | opencode | long context, reasoning |
+| `gemini/gemini-2.5-pro` | gemini | long context, reasoning |
+
+### Mid-tier (general purpose)
+| Model | Provider | Best For |
+|-------|----------|----------|
+| `github-copilot/claude-sonnet-4.5` | opencode | general, fallback |
+| `github-copilot/gemini-3-flash-preview` | opencode | fast |
+| `zai-coding-plan/glm-4.7` | opencode | code generation |
+| `opencode/big-pickle` | opencode | general |
+| `gemini/gemini-2.5-flash` | gemini | fast |
+
+### Lightweight (simple tasks)
+| Model | Provider | Best For |
+|-------|----------|----------|
+| `github-copilot/claude-haiku-4.5` | opencode | simple tasks |
+
+## Task Routing
+
+| Task | Routes To | Tier |
+|------|-----------|------|
+| `reasoning` | github-copilot/gpt-5.2 | frontier |
+| `code-generation` | github-copilot/gemini-3-pro-preview | frontier |
+| `long-context` | gemini/gemini-2.5-pro | frontier |
+| `fast` | github-copilot/gemini-3-flash-preview | mid-tier |
+| `general` (default) | github-copilot/claude-sonnet-4.5 | mid-tier |
+
+## State Files
+
+- Mode state: `~/.claude/state/external-mode.json`
+- Model policy: `~/.claude/state/model-policy.json`
+
+## Examples
+
+```
+/external on testing        # Enable for testing
+/external invoke "Explain k8s pods"   # Use default model (mid-tier)
+/external invoke --model github-copilot/gpt-5.2 "Complex analysis"  # frontier
+/external invoke --task code-generation "Write a Python function"   # routes to frontier
+/external invoke --task fast "Quick question"                       # routes to mid-tier
+/external off               # Back to Claude
+```

hooks/scripts/session-start.sh

@@ -32,12 +32,24 @@ with open('${PA_DIR}/memory/decisions.json') as f:
 " 2>/dev/null || echo "0")
 fi
 
+# Check external mode
+EXTERNAL_MODE="disabled"
+if [[ -f "${STATE_DIR}/external-mode.json" ]]; then
+    EXTERNAL_ENABLED=$(jq -r '.enabled // false' "${STATE_DIR}/external-mode.json" 2>/dev/null || echo "false")
+    if [[ "${EXTERNAL_ENABLED}" == "true" ]]; then
+        EXTERNAL_MODE="enabled"
+    fi
+fi
+
 # Output context as system reminder format
-echo "SessionStart:Callback hook success: Success"
+echo "SessionStart:resume hook success: Success"
 
 # Add additional context if there's something noteworthy
-if [[ "${UNSUMMARIZED}" -gt 0 || "${PENDING_DECISIONS}" -gt 0 ]]; then
+if [[ "${UNSUMMARIZED}" -gt 0 || "${PENDING_DECISIONS}" -gt 0 || "${EXTERNAL_MODE}" == "enabled" ]]; then
     echo "SessionStart hook additional context: "
+    if [[ "${EXTERNAL_MODE}" == "enabled" ]]; then
+        echo "- EXTERNAL MODE ACTIVE: All requests routed to external LLMs"
+    fi
     if [[ "${UNSUMMARIZED}" -gt 0 ]]; then
         echo "- ${UNSUMMARIZED} unsummarized session(s) available for review"
     fi

mcp/llm-router/delegate.py

@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+"""
+Agent delegation helper. Routes to external or Claude based on mode.
+
+Usage:
+    delegate.py --tier sonnet -p "prompt"
+    delegate.py --tier opus -p "complex reasoning task" --json
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+STATE_DIR = Path.home() / ".claude/state"
+ROUTER_DIR = Path(__file__).parent
+
+
+def is_external_mode() -> bool:
+    """Check if external-only mode is enabled."""
+    mode_file = STATE_DIR / "external-mode.json"
+    if mode_file.exists():
+        with open(mode_file) as f:
+            data = json.load(f)
+            return data.get("enabled", False)
+    return False
+
+
+def get_external_model(tier: str) -> str:
+    """Get the external model equivalent for a Claude tier."""
+    policy_file = STATE_DIR / "model-policy.json"
+    with open(policy_file) as f:
+        policy = json.load(f)
+    mapping = policy.get("claude_to_external_map", {})
+    if tier not in mapping:
+        raise ValueError(f"No external mapping for tier: {tier}")
+    return mapping[tier]
+
+
+def delegate(tier: str, prompt: str, use_json: bool = False) -> str:
+    """
+    Delegate to appropriate model based on mode.
+
+    Args:
+        tier: Claude tier (opus, sonnet, haiku)
+        prompt: The prompt text
+        use_json: Return JSON output
+
+    Returns:
+        Model response as string
+    """
+    if is_external_mode():
+        # Use external model
+        model = get_external_model(tier)
+        invoke_script = ROUTER_DIR / "invoke.py"
+
+        cmd = [sys.executable, str(invoke_script), "--model", model, "-p", prompt]
+        if use_json:
+            cmd.append("--json")
+
+        result = subprocess.run(cmd, capture_output=True, text=True)
+
+        if result.returncode != 0:
+            raise RuntimeError(f"External invoke failed: {result.stderr}")
+
+        return result.stdout.strip()
+    else:
+        # Use Claude
+        cmd = ["claude", "--print", "--model", tier, prompt]
+
+        result = subprocess.run(cmd, capture_output=True, text=True)
+
+        if result.returncode != 0:
+            raise RuntimeError(f"Claude failed: {result.stderr}")
+
+        response = result.stdout.strip()
+
+        if use_json:
+            return json.dumps({
+                "model": f"claude/{tier}",
+                "response": response,
+                "success": True
+            }, indent=2)
+
+        return response
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Delegate to Claude or external model based on mode"
+    )
+    parser.add_argument(
+        "--tier",
+        required=True,
+        choices=["opus", "sonnet", "haiku"],
+        help="Claude tier (maps to external equivalent when in external mode)"
+    )
+    parser.add_argument(
+        "-p", "--prompt",
+        required=True,
+        help="Prompt text"
+    )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        help="Output as JSON"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        result = delegate(args.tier, args.prompt, args.json)
+        print(result)
+    except Exception as e:
+        if args.json:
+            print(json.dumps({"error": str(e), "success": False}, indent=2))
+            sys.exit(1)
+        else:
+            print(f"Error: {e}", file=sys.stderr)
+            sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

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, timeout: int = 600) -> 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, 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, timeout=timeout)
+    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=600,
+        help="Timeout in seconds (default: 600)"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        policy = load_policy()
+        model = resolve_model(args, policy)
+        result = invoke(model, args.prompt, policy, timeout=args.timeout)
+
+        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()

mcp/llm-router/providers/gemini.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+"""Gemini CLI wrapper for Google models."""
+
+import subprocess
+from typing import List
+
+
+def invoke(cli_args: List[str], prompt: str, timeout: int = 300) -> str:
+    """
+    Invoke gemini CLI with given args and prompt.
+
+    Args:
+        cli_args: Model args like ["-m", "gemini-3-pro"]
+        prompt: The prompt text
+        timeout: Timeout in seconds (default 5 minutes)
+
+    Returns:
+        Model response as string
+
+    Raises:
+        RuntimeError: If gemini CLI fails
+        TimeoutError: If request exceeds timeout
+    """
+    cmd = ["gemini"] + cli_args + ["-p", prompt]
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout
+        )
+    except subprocess.TimeoutExpired:
+        raise TimeoutError(f"gemini timed out after {timeout}s")
+
+    if result.returncode != 0:
+        raise RuntimeError(f"gemini failed (exit {result.returncode}): {result.stderr}")
+
+    return result.stdout.strip()
+
+
+if __name__ == "__main__":
+    # Quick test
+    import sys
+    if len(sys.argv) > 1:
+        response = invoke(["-m", "gemini-3-pro"], sys.argv[1])
+        print(response)
+    else:
+        print("Usage: gemini.py 'prompt'")

mcp/llm-router/providers/opencode.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""OpenCode CLI wrapper for GitHub Copilot, Z.AI, and other providers."""
+
+import subprocess
+from typing import List
+
+# OpenCode binary path (linuxbrew installation)
+OPENCODE_BIN = "/home/linuxbrew/.linuxbrew/bin/opencode"
+
+
+def invoke(cli_args: List[str], prompt: str, timeout: int = 300) -> str:
+    """
+    Invoke opencode CLI with given args and prompt.
+
+    Args:
+        cli_args: Model args like ["-m", "github-copilot/gpt-5.2"]
+        prompt: The prompt text
+        timeout: Timeout in seconds (default 5 minutes)
+
+    Returns:
+        Model response as string
+
+    Raises:
+        RuntimeError: If opencode CLI fails
+        TimeoutError: If request exceeds timeout
+
+    Example invocation:
+        opencode run -m github-copilot/gpt-5.2 "Hello world"
+    """
+    # Build command: opencode run -m MODEL "prompt"
+    cmd = [OPENCODE_BIN, "run"] + cli_args + [prompt]
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout
+        )
+    except subprocess.TimeoutExpired:
+        raise TimeoutError(f"opencode timed out after {timeout}s")
+
+    if result.returncode != 0:
+        raise RuntimeError(f"opencode failed (exit {result.returncode}): {result.stderr}")
+
+    return result.stdout.strip()
+
+
+if __name__ == "__main__":
+    # Quick test
+    import sys
+    if len(sys.argv) > 1:
+        response = invoke(["-m", "github-copilot/gpt-5.2"], sys.argv[1])
+        print(response)
+    else:
+        print("Usage: opencode.py 'prompt'")

mcp/llm-router/toggle.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""
+Toggle external-only mode.
+
+Usage:
+    toggle.py on [--reason "user requested"]
+    toggle.py off
+    toggle.py status
+"""
+
+import argparse
+import json
+from datetime import datetime
+from pathlib import Path
+from typing import Optional
+
+STATE_FILE = Path.home() / ".claude/state/external-mode.json"
+
+
+def load_state() -> dict:
+    """Load current state."""
+    if STATE_FILE.exists():
+        with open(STATE_FILE) as f:
+            return json.load(f)
+    return {"enabled": False, "activated_at": None, "reason": None}
+
+
+def save_state(state: dict):
+    """Save state to file."""
+    with open(STATE_FILE, "w") as f:
+        json.dump(state, f, indent=2)
+
+
+def enable(reason: Optional[str] = None):
+    """Enable external-only mode."""
+    state = {
+        "enabled": True,
+        "activated_at": datetime.now().isoformat(),
+        "reason": reason or "user-requested"
+    }
+    save_state(state)
+    print("External-only mode ENABLED")
+    print(f"  Activated: {state['activated_at']}")
+    print(f"  Reason: {state['reason']}")
+    print("\nAll agent requests will now use external LLMs.")
+    print("Run 'toggle.py off' or '/pa --external off' to disable.")
+
+
+def disable():
+    """Disable external-only mode."""
+    state = {
+        "enabled": False,
+        "activated_at": None,
+        "reason": None
+    }
+    save_state(state)
+    print("External-only mode DISABLED")
+    print("\nAll agent requests will now use Claude.")
+
+
+def status():
+    """Show current mode status."""
+    state = load_state()
+    if state.get("enabled"):
+        print("External-only mode: ENABLED")
+        print(f"  Activated: {state.get('activated_at', 'unknown')}")
+        print(f"  Reason: {state.get('reason', 'unknown')}")
+    else:
+        print("External-only mode: DISABLED")
+        print("  Using Claude for all requests.")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Toggle external-only mode")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    # on command
+    on_parser = subparsers.add_parser("on", help="Enable external-only mode")
+    on_parser.add_argument("--reason", help="Reason for enabling")
+
+    # off command
+    subparsers.add_parser("off", help="Disable external-only mode")
+
+    # status command
+    subparsers.add_parser("status", help="Show current mode")
+
+    args = parser.parse_args()
+
+    if args.command == "on":
+        enable(args.reason)
+    elif args.command == "off":
+        disable()
+    elif args.command == "status":
+        status()
+
+
+if __name__ == "__main__":
+    main()

plans/gleaming-routing-mercury-impl.md

@@ -0,0 +1,903 @@
+# External LLM Integration Implementation Plan
+
+> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
+
+**Goal:** Enable agents to use external LLMs (Copilot, Z.AI, Gemini) via CLI tools with a session toggle.
+
+**Architecture:** Python router reads model-policy.json, invokes appropriate CLI (opencode/gemini), returns response. State file controls Claude vs external mode. PA exposes toggle commands.
+
+**Tech Stack:** Python 3, subprocess, JSON state files, opencode CLI, gemini CLI
+
+---
+
+## Task 1: Create External Mode State File
+
+**Files:**
+- Create: `~/.claude/state/external-mode.json`
+
+**Step 1: Create state file**
+
+```bash
+cat > ~/.claude/state/external-mode.json << 'EOF'
+{
+  "enabled": false,
+  "activated_at": null,
+  "reason": null
+}
+EOF
+```
+
+**Step 2: Verify file**
+
+Run: `cat ~/.claude/state/external-mode.json | jq .`
+Expected: Valid JSON with `enabled: false`
+
+**Step 3: Commit**
+
+```bash
+git -C ~/.claude add state/external-mode.json
+git -C ~/.claude commit -m "feat(external-llm): add external-mode state file"
+```
+
+---
+
+## Task 2: Extend Model Policy
+
+**Files:**
+- Modify: `~/.claude/state/model-policy.json`
+
+**Step 1: Read current file**
+
+Run: `cat ~/.claude/state/model-policy.json | jq .`
+
+**Step 2: Add external_models section**
+
+Add to model-policy.json (after `skill_delegation` section):
+
+```json
+"external_models": {
+  "copilot/gpt-5.2": {
+    "cli": "opencode",
+    "cli_args": ["--provider", "copilot", "--model", "gpt-5.2"],
+    "use_cases": ["reasoning", "fallback"],
+    "tier": "opus-equivalent"
+  },
+  "copilot/sonnet-4.5": {
+    "cli": "opencode",
+    "cli_args": ["--provider", "copilot", "--model", "sonnet-4.5"],
+    "use_cases": ["general", "fallback"],
+    "tier": "sonnet-equivalent"
+  },
+  "copilot/haiku-4.5": {
+    "cli": "opencode",
+    "cli_args": ["--provider", "copilot", "--model", "haiku-4.5"],
+    "use_cases": ["simple"],
+    "tier": "haiku-equivalent"
+  },
+  "zai/glm-4.7": {
+    "cli": "opencode",
+    "cli_args": ["--provider", "zai", "--model", "glm-4.7"],
+    "use_cases": ["code-generation"],
+    "tier": "sonnet-equivalent"
+  },
+  "gemini/gemini-3-pro": {
+    "cli": "gemini",
+    "cli_args": ["-m", "gemini-3-pro"],
+    "use_cases": ["long-context"],
+    "tier": "opus-equivalent"
+  }
+},
+"claude_to_external_map": {
+  "opus": "copilot/gpt-5.2",
+  "sonnet": "copilot/sonnet-4.5",
+  "haiku": "copilot/haiku-4.5"
+},
+"task_routing": {
+  "reasoning": "copilot/gpt-5.2",
+  "code-generation": "zai/glm-4.7",
+  "long-context": "gemini/gemini-3-pro",
+  "default": "copilot/sonnet-4.5"
+}
+```
+
+**Step 3: Validate JSON**
+
+Run: `cat ~/.claude/state/model-policy.json | jq .`
+Expected: Valid JSON, no errors
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add state/model-policy.json
+git -C ~/.claude commit -m "feat(external-llm): add external model definitions to policy"
+```
+
+---
+
+## Task 3: Create Router Directory Structure
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/`
+- Create: `~/.claude/mcp/llm-router/providers/`
+- Create: `~/.claude/mcp/llm-router/providers/__init__.py`
+
+**Step 1: Create directories**
+
+```bash
+mkdir -p ~/.claude/mcp/llm-router/providers
+```
+
+**Step 2: Create __init__.py**
+
+```bash
+touch ~/.claude/mcp/llm-router/providers/__init__.py
+```
+
+**Step 3: Verify structure**
+
+Run: `ls -la ~/.claude/mcp/llm-router/`
+Expected: `providers/` directory exists
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/
+git -C ~/.claude commit -m "feat(external-llm): create llm-router directory structure"
+```
+
+---
+
+## Task 4: Create OpenCode Provider
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/providers/opencode.py`
+
+**Step 1: Write provider**
+
+```python
+#!/usr/bin/env python3
+"""OpenCode CLI wrapper for Copilot, Z.AI, and other providers."""
+
+import subprocess
+from typing import List
+
+
+def invoke(cli_args: List[str], prompt: str, timeout: int = 300) -> str:
+    """
+    Invoke opencode CLI with given args and prompt.
+
+    Args:
+        cli_args: Provider/model args like ["--provider", "copilot", "--model", "gpt-5.2"]
+        prompt: The prompt text
+        timeout: Timeout in seconds (default 5 minutes)
+
+    Returns:
+        Model response as string
+
+    Raises:
+        RuntimeError: If opencode CLI fails
+        TimeoutError: If request exceeds timeout
+    """
+    cmd = ["opencode", "--print"] + cli_args + ["-p", prompt]
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout
+        )
+    except subprocess.TimeoutExpired:
+        raise TimeoutError(f"opencode timed out after {timeout}s")
+
+    if result.returncode != 0:
+        raise RuntimeError(f"opencode failed (exit {result.returncode}): {result.stderr}")
+
+    return result.stdout.strip()
+
+
+if __name__ == "__main__":
+    # Quick test
+    import sys
+    if len(sys.argv) > 1:
+        response = invoke(["--provider", "copilot", "--model", "gpt-5.2"], sys.argv[1])
+        print(response)
+    else:
+        print("Usage: opencode.py 'prompt'")
+```
+
+**Step 2: Make executable**
+
+```bash
+chmod +x ~/.claude/mcp/llm-router/providers/opencode.py
+```
+
+**Step 3: Verify syntax**
+
+Run: `python3 -m py_compile ~/.claude/mcp/llm-router/providers/opencode.py`
+Expected: No output (success)
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/providers/opencode.py
+git -C ~/.claude commit -m "feat(external-llm): add opencode provider wrapper"
+```
+
+---
+
+## Task 5: Create Gemini Provider
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/providers/gemini.py`
+
+**Step 1: Write provider**
+
+```python
+#!/usr/bin/env python3
+"""Gemini CLI wrapper for Google models."""
+
+import subprocess
+from typing import List
+
+
+def invoke(cli_args: List[str], prompt: str, timeout: int = 300) -> str:
+    """
+    Invoke gemini CLI with given args and prompt.
+
+    Args:
+        cli_args: Model args like ["-m", "gemini-3-pro"]
+        prompt: The prompt text
+        timeout: Timeout in seconds (default 5 minutes)
+
+    Returns:
+        Model response as string
+
+    Raises:
+        RuntimeError: If gemini CLI fails
+        TimeoutError: If request exceeds timeout
+    """
+    cmd = ["gemini"] + cli_args + ["-p", prompt]
+
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            timeout=timeout
+        )
+    except subprocess.TimeoutExpired:
+        raise TimeoutError(f"gemini timed out after {timeout}s")
+
+    if result.returncode != 0:
+        raise RuntimeError(f"gemini failed (exit {result.returncode}): {result.stderr}")
+
+    return result.stdout.strip()
+
+
+if __name__ == "__main__":
+    # Quick test
+    import sys
+    if len(sys.argv) > 1:
+        response = invoke(["-m", "gemini-3-pro"], sys.argv[1])
+        print(response)
+    else:
+        print("Usage: gemini.py 'prompt'")
+```
+
+**Step 2: Make executable**
+
+```bash
+chmod +x ~/.claude/mcp/llm-router/providers/gemini.py
+```
+
+**Step 3: Verify syntax**
+
+Run: `python3 -m py_compile ~/.claude/mcp/llm-router/providers/gemini.py`
+Expected: No output (success)
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/providers/gemini.py
+git -C ~/.claude commit -m "feat(external-llm): add gemini provider wrapper"
+```
+
+---
+
+## Task 6: Create Main Router (invoke.py)
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/invoke.py`
+
+**Step 1: Write router**
+
+```python
+#!/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()
+```
+
+**Step 2: Make executable**
+
+```bash
+chmod +x ~/.claude/mcp/llm-router/invoke.py
+```
+
+**Step 3: Verify syntax**
+
+Run: `python3 -m py_compile ~/.claude/mcp/llm-router/invoke.py`
+Expected: No output (success)
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/invoke.py
+git -C ~/.claude commit -m "feat(external-llm): add main router invoke.py"
+```
+
+---
+
+## Task 7: Create Delegation Helper
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/delegate.py`
+
+**Step 1: Write delegation helper**
+
+```python
+#!/usr/bin/env python3
+"""
+Agent delegation helper. Routes to external or Claude based on mode.
+
+Usage:
+    delegate.py --tier sonnet -p "prompt"
+    delegate.py --tier opus -p "complex reasoning task" --json
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+STATE_DIR = Path.home() / ".claude/state"
+ROUTER_DIR = Path(__file__).parent
+
+
+def is_external_mode() -> bool:
+    """Check if external-only mode is enabled."""
+    mode_file = STATE_DIR / "external-mode.json"
+    if mode_file.exists():
+        with open(mode_file) as f:
+            data = json.load(f)
+            return data.get("enabled", False)
+    return False
+
+
+def get_external_model(tier: str) -> str:
+    """Get the external model equivalent for a Claude tier."""
+    policy_file = STATE_DIR / "model-policy.json"
+    with open(policy_file) as f:
+        policy = json.load(f)
+    mapping = policy.get("claude_to_external_map", {})
+    if tier not in mapping:
+        raise ValueError(f"No external mapping for tier: {tier}")
+    return mapping[tier]
+
+
+def delegate(tier: str, prompt: str, use_json: bool = False) -> str:
+    """
+    Delegate to appropriate model based on mode.
+
+    Args:
+        tier: Claude tier (opus, sonnet, haiku)
+        prompt: The prompt text
+        use_json: Return JSON output
+
+    Returns:
+        Model response as string
+    """
+    if is_external_mode():
+        # Use external model
+        model = get_external_model(tier)
+        invoke_script = ROUTER_DIR / "invoke.py"
+
+        cmd = [sys.executable, str(invoke_script), "--model", model, "-p", prompt]
+        if use_json:
+            cmd.append("--json")
+
+        result = subprocess.run(cmd, capture_output=True, text=True)
+
+        if result.returncode != 0:
+            raise RuntimeError(f"External invoke failed: {result.stderr}")
+
+        return result.stdout.strip()
+    else:
+        # Use Claude
+        cmd = ["claude", "--print", "--model", tier, prompt]
+
+        result = subprocess.run(cmd, capture_output=True, text=True)
+
+        if result.returncode != 0:
+            raise RuntimeError(f"Claude failed: {result.stderr}")
+
+        response = result.stdout.strip()
+
+        if use_json:
+            return json.dumps({
+                "model": f"claude/{tier}",
+                "response": response,
+                "success": True
+            }, indent=2)
+
+        return response
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Delegate to Claude or external model based on mode"
+    )
+    parser.add_argument(
+        "--tier",
+        required=True,
+        choices=["opus", "sonnet", "haiku"],
+        help="Claude tier (maps to external equivalent when in external mode)"
+    )
+    parser.add_argument(
+        "-p", "--prompt",
+        required=True,
+        help="Prompt text"
+    )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        help="Output as JSON"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        result = delegate(args.tier, args.prompt, args.json)
+        print(result)
+    except Exception as e:
+        if args.json:
+            print(json.dumps({"error": str(e), "success": False}, indent=2))
+            sys.exit(1)
+        else:
+            print(f"Error: {e}", file=sys.stderr)
+            sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()
+```
+
+**Step 2: Make executable**
+
+```bash
+chmod +x ~/.claude/mcp/llm-router/delegate.py
+```
+
+**Step 3: Verify syntax**
+
+Run: `python3 -m py_compile ~/.claude/mcp/llm-router/delegate.py`
+Expected: No output (success)
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/delegate.py
+git -C ~/.claude commit -m "feat(external-llm): add delegation helper"
+```
+
+---
+
+## Task 8: Create Toggle Script
+
+**Files:**
+- Create: `~/.claude/mcp/llm-router/toggle.py`
+
+**Step 1: Write toggle script**
+
+```python
+#!/usr/bin/env python3
+"""
+Toggle external-only mode.
+
+Usage:
+    toggle.py on [--reason "user requested"]
+    toggle.py off
+    toggle.py status
+"""
+
+import argparse
+import json
+import sys
+from datetime import datetime
+from pathlib import Path
+
+STATE_FILE = Path.home() / ".claude/state/external-mode.json"
+
+
+def load_state() -> dict:
+    """Load current state."""
+    if STATE_FILE.exists():
+        with open(STATE_FILE) as f:
+            return json.load(f)
+    return {"enabled": False, "activated_at": None, "reason": None}
+
+
+def save_state(state: dict):
+    """Save state to file."""
+    with open(STATE_FILE, "w") as f:
+        json.dump(state, f, indent=2)
+
+
+def enable(reason: str = None):
+    """Enable external-only mode."""
+    state = {
+        "enabled": True,
+        "activated_at": datetime.now().isoformat(),
+        "reason": reason or "user-requested"
+    }
+    save_state(state)
+    print("External-only mode ENABLED")
+    print(f"  Activated: {state['activated_at']}")
+    print(f"  Reason: {state['reason']}")
+    print("\nAll agent requests will now use external LLMs.")
+    print("Run 'toggle.py off' or '/pa --external off' to disable.")
+
+
+def disable():
+    """Disable external-only mode."""
+    state = {
+        "enabled": False,
+        "activated_at": None,
+        "reason": None
+    }
+    save_state(state)
+    print("External-only mode DISABLED")
+    print("\nAll agent requests will now use Claude.")
+
+
+def status():
+    """Show current mode status."""
+    state = load_state()
+    if state.get("enabled"):
+        print("External-only mode: ENABLED")
+        print(f"  Activated: {state.get('activated_at', 'unknown')}")
+        print(f"  Reason: {state.get('reason', 'unknown')}")
+    else:
+        print("External-only mode: DISABLED")
+        print("  Using Claude for all requests.")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Toggle external-only mode")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    # on command
+    on_parser = subparsers.add_parser("on", help="Enable external-only mode")
+    on_parser.add_argument("--reason", help="Reason for enabling")
+
+    # off command
+    subparsers.add_parser("off", help="Disable external-only mode")
+
+    # status command
+    subparsers.add_parser("status", help="Show current mode")
+
+    args = parser.parse_args()
+
+    if args.command == "on":
+        enable(args.reason)
+    elif args.command == "off":
+        disable()
+    elif args.command == "status":
+        status()
+
+
+if __name__ == "__main__":
+    main()
+```
+
+**Step 2: Make executable**
+
+```bash
+chmod +x ~/.claude/mcp/llm-router/toggle.py
+```
+
+**Step 3: Test toggle**
+
+Run: `~/.claude/mcp/llm-router/toggle.py status`
+Expected: Shows "External-only mode: DISABLED"
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add mcp/llm-router/toggle.py
+git -C ~/.claude commit -m "feat(external-llm): add toggle script"
+```
+
+---
+
+## Task 9: Update Session Start Hook
+
+**Files:**
+- Modify: `~/.claude/hooks/scripts/session-start.sh`
+
+**Step 1: Read current hook**
+
+Run: `cat ~/.claude/hooks/scripts/session-start.sh`
+
+**Step 2: Add external mode check**
+
+Add before the final output section:
+
+```bash
+# Check external mode
+if [ -f ~/.claude/state/external-mode.json ]; then
+  EXTERNAL_ENABLED=$(jq -r '.enabled // false' ~/.claude/state/external-mode.json)
+  if [ "$EXTERNAL_ENABLED" = "true" ]; then
+    echo "external-mode:enabled"
+  fi
+fi
+```
+
+**Step 3: Verify hook**
+
+Run: `bash -n ~/.claude/hooks/scripts/session-start.sh`
+Expected: No output (success)
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add hooks/scripts/session-start.sh
+git -C ~/.claude commit -m "feat(external-llm): announce external mode in session-start"
+```
+
+---
+
+## Task 10: Add Component Registry Triggers
+
+**Files:**
+- Modify: `~/.claude/state/component-registry.json`
+
+**Step 1: Read current registry**
+
+Run: `cat ~/.claude/state/component-registry.json | jq '.skills'`
+
+**Step 2: Add external-mode skill entry**
+
+Add to skills array:
+
+```json
+{
+  "id": "external-mode-toggle",
+  "name": "External Mode Toggle",
+  "description": "Toggle between Claude and external LLMs",
+  "path": "mcp/llm-router/toggle.py",
+  "triggers": [
+    "use external",
+    "switch to external",
+    "external models",
+    "external only",
+    "use copilot",
+    "use opencode",
+    "back to claude",
+    "use claude again",
+    "disable external",
+    "external mode"
+  ]
+}
+```
+
+**Step 3: Validate JSON**
+
+Run: `cat ~/.claude/state/component-registry.json | jq .`
+Expected: Valid JSON
+
+**Step 4: Commit**
+
+```bash
+git -C ~/.claude add state/component-registry.json
+git -C ~/.claude commit -m "feat(external-llm): add external-mode triggers to registry"
+```
+
+---
+
+## Task 11: Integration Test
+
+**Step 1: Test toggle**
+
+```bash
+~/.claude/mcp/llm-router/toggle.py status
+~/.claude/mcp/llm-router/toggle.py on --reason "testing"
+~/.claude/mcp/llm-router/toggle.py status
+~/.claude/mcp/llm-router/toggle.py off
+```
+
+Expected: Status changes correctly
+
+**Step 2: Test router (mock - will fail without actual CLIs)**
+
+```bash
+~/.claude/mcp/llm-router/invoke.py --model copilot/gpt-5.2 -p "Say hello" --json 2>&1 || echo "Expected: CLI not found (normal if opencode not installed)"
+```
+
+**Step 3: Test delegation helper status check**
+
+```bash
+python3 -c "
+import sys
+sys.path.insert(0, '$HOME/.claude/mcp/llm-router')
+from delegate import is_external_mode
+print(f'External mode: {is_external_mode()}')
+"
+```
+
+Expected: "External mode: False"
+
+**Step 4: Final commit**
+
+```bash
+git -C ~/.claude commit --allow-empty -m "feat(external-llm): integration complete - gleaming-routing-mercury"
+```
+
+---
+
+## Summary
+
+After completing all tasks:
+
+| Component | Status |
+|-----------|--------|
+| `state/external-mode.json` | Created |
+| `state/model-policy.json` | Extended |
+| `mcp/llm-router/invoke.py` | Created |
+| `mcp/llm-router/delegate.py` | Created |
+| `mcp/llm-router/toggle.py` | Created |
+| `mcp/llm-router/providers/opencode.py` | Created |
+| `mcp/llm-router/providers/gemini.py` | Created |
+| `hooks/scripts/session-start.sh` | Updated |
+| `state/component-registry.json` | Updated |
+
+**To use:**
+```bash
+# Enable external mode
+~/.claude/mcp/llm-router/toggle.py on
+
+# Or via PA
+/pa --external on
+/pa switch to external models
+
+# Invoke directly
+~/.claude/mcp/llm-router/invoke.py --task reasoning -p "Explain quantum computing"
+
+# Delegate (respects mode)
+~/.claude/mcp/llm-router/delegate.py --tier sonnet -p "Check disk space"
+```

plans/gleaming-routing-mercury.md

@@ -0,0 +1,375 @@
+# Plan: External LLM Integration
+
+## Summary
+
+Integrate external LLMs (via subscription-based access) into the agent system for cost optimization, specialized capabilities, and redundancy. Uses `opencode` CLI for Copilot/Z.AI models and `gemini` CLI for Google models.
+
+## Motivation
+
+- **Cost optimization** — Use cheaper models for simple tasks
+- **Specialized capabilities** — Access models with unique strengths (GPT-5.2 for reasoning, GLM 4.7 for code)
+- **Redundancy** — Fallback when Claude is unavailable
+
+## Design Decisions
+
+| Decision | Choice |
+|----------|--------|
+| Provider type | Cloud APIs via subscription (not local) |
+| Providers | GitHub Copilot, Z.AI, Google Gemini |
+| CLIs | `opencode` (Copilot, Z.AI), `gemini` (Google) |
+| Integration | Task-specific routing + agent-level assignment |
+| Toggle | State file (persists across sessions) |
+| Toggle scope | All agents switch when enabled |
+
+## Task Routing
+
+| Task Type | Model |
+|-----------|-------|
+| Reasoning chains | copilot/gpt-5.2 |
+| Code generation | zai/glm-4.7 |
+| Long context | gemini/gemini-3-pro |
+| General/fallback | copilot/sonnet-4.5 |
+
+## Claude-to-External Mapping
+
+| Claude Tier | External Equivalent |
+|-------------|---------------------|
+| opus | copilot/gpt-5.2 |
+| sonnet | copilot/sonnet-4.5 |
+| haiku | copilot/haiku-4.5 |
+
+## Files to Create
+
+### `~/.claude/state/external-mode.json`
+
+```json
+{
+  "enabled": false,
+  "activated_at": null,
+  "reason": null
+}
+```
+
+### `~/.claude/mcp/llm-router/invoke.py`
+
+Main entry point for invoking external LLMs.
+
+```python
+#!/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"
+"""
+
+import argparse
+import json
+import subprocess
+from pathlib import Path
+
+STATE_DIR = Path.home() / ".claude/state"
+
+def load_policy():
+    with open(STATE_DIR / "model-policy.json") as f:
+        return json.load(f)
+
+def resolve_model(args, policy):
+    if args.model:
+        return args.model
+    if args.task and args.task in policy["task_routing"]:
+        return policy["task_routing"][args.task]
+    return policy["task_routing"]["default"]
+
+def invoke(model: str, prompt: str, policy: dict) -> str:
+    model_config = policy["external_models"][model]
+    cli = model_config["cli"]
+    cli_args = model_config["cli_args"]
+
+    if cli == "opencode":
+        from providers.opencode import invoke as opencode_invoke
+        return opencode_invoke(cli_args, prompt)
+    elif cli == "gemini":
+        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()
+    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", help="Task type for routing")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    args = parser.parse_args()
+
+    policy = load_policy()
+    model = resolve_model(args, policy)
+    result = invoke(args.prompt, model, policy)
+
+    if args.json:
+        print(json.dumps({"model": model, "response": result}))
+    else:
+        print(result)
+
+if __name__ == "__main__":
+    main()
+```
+
+### `~/.claude/mcp/llm-router/providers/opencode.py`
+
+```python
+#!/usr/bin/env python3
+"""OpenCode CLI wrapper."""
+
+import subprocess
+
+def invoke(cli_args: list, prompt: str) -> str:
+    cmd = ["opencode", "--print"] + cli_args + ["-p", prompt]
+
+    result = subprocess.run(
+        cmd,
+        capture_output=True,
+        text=True,
+        timeout=300
+    )
+
+    if result.returncode != 0:
+        raise RuntimeError(f"opencode failed: {result.stderr}")
+
+    return result.stdout.strip()
+```
+
+### `~/.claude/mcp/llm-router/providers/gemini.py`
+
+```python
+#!/usr/bin/env python3
+"""Gemini CLI wrapper."""
+
+import subprocess
+
+def invoke(cli_args: list, prompt: str) -> str:
+    cmd = ["gemini"] + cli_args + ["-p", prompt]
+
+    result = subprocess.run(
+        cmd,
+        capture_output=True,
+        text=True,
+        timeout=300
+    )
+
+    if result.returncode != 0:
+        raise RuntimeError(f"gemini failed: {result.stderr}")
+
+    return result.stdout.strip()
+```
+
+### `~/.claude/mcp/llm-router/delegate.py`
+
+```python
+#!/usr/bin/env python3
+"""
+Agent delegation helper. Routes to external or Claude based on mode.
+
+Usage:
+  delegate.py --tier sonnet -p "prompt"
+"""
+
+import argparse
+import json
+import subprocess
+from pathlib import Path
+
+STATE_DIR = Path.home() / ".claude/state"
+
+def is_external_mode():
+    mode_file = STATE_DIR / "external-mode.json"
+    if mode_file.exists():
+        with open(mode_file) as f:
+            return json.load(f).get("enabled", False)
+    return False
+
+def delegate(tier: str, prompt: str) -> str:
+    if is_external_mode():
+        policy = json.loads((STATE_DIR / "model-policy.json").read_text())
+        model = policy["claude_to_external_map"][tier]
+
+        result = subprocess.run(
+            [str(Path.home() / ".claude/mcp/llm-router/invoke.py"),
+             "--model", model, "-p", prompt],
+            capture_output=True, text=True
+        )
+        return result.stdout
+    else:
+        result = subprocess.run(
+            ["claude", "--print", "--model", tier, prompt],
+            capture_output=True, text=True
+        )
+        return result.stdout
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--tier", required=True, choices=["opus", "sonnet", "haiku"])
+    parser.add_argument("-p", "--prompt", required=True)
+    args = parser.parse_args()
+
+    print(delegate(args.tier, args.prompt))
+
+if __name__ == "__main__":
+    main()
+```
+
+## Files to Modify
+
+### `~/.claude/state/model-policy.json`
+
+Add sections:
+
+```json
+{
+  "external_models": {
+    "copilot/gpt-5.2": {
+      "cli": "opencode",
+      "cli_args": ["--provider", "copilot", "--model", "gpt-5.2"],
+      "use_cases": ["reasoning", "fallback"],
+      "tier": "opus-equivalent"
+    },
+    "copilot/sonnet-4.5": {
+      "cli": "opencode",
+      "cli_args": ["--provider", "copilot", "--model", "sonnet-4.5"],
+      "use_cases": ["general", "fallback"],
+      "tier": "sonnet-equivalent"
+    },
+    "copilot/haiku-4.5": {
+      "cli": "opencode",
+      "cli_args": ["--provider", "copilot", "--model", "haiku-4.5"],
+      "use_cases": ["simple"],
+      "tier": "haiku-equivalent"
+    },
+    "zai/glm-4.7": {
+      "cli": "opencode",
+      "cli_args": ["--provider", "zai", "--model", "glm-4.7"],
+      "use_cases": ["code-generation"],
+      "tier": "sonnet-equivalent"
+    },
+    "gemini/gemini-3-pro": {
+      "cli": "gemini",
+      "cli_args": ["-m", "gemini-3-pro"],
+      "use_cases": ["long-context"],
+      "tier": "opus-equivalent"
+    }
+  },
+  "claude_to_external_map": {
+    "opus": "copilot/gpt-5.2",
+    "sonnet": "copilot/sonnet-4.5",
+    "haiku": "copilot/haiku-4.5"
+  },
+  "task_routing": {
+    "reasoning": "copilot/gpt-5.2",
+    "code-generation": "zai/glm-4.7",
+    "long-context": "gemini/gemini-3-pro",
+    "default": "copilot/sonnet-4.5"
+  }
+}
+```
+
+### `~/.claude/state/component-registry.json`
+
+Add trigger for external mode:
+
+```json
+{
+  "id": "external-mode-toggle",
+  "type": "skill",
+  "triggers": [
+    "use external", "switch to external", "external models",
+    "stop using claude", "external only", "use copilot",
+    "back to claude", "use claude again", "disable external"
+  ],
+  "action": "toggle-external-mode"
+}
+```
+
+### `~/.claude/hooks/scripts/session-start.sh`
+
+Add external mode announcement:
+
+```bash
+# Check external mode
+if [ -f ~/.claude/state/external-mode.json ]; then
+  if [ "$(jq -r '.enabled' ~/.claude/state/external-mode.json)" = "true" ]; then
+    echo "external-mode:enabled"
+  fi
+fi
+```
+
+## Toggle Interface
+
+### Command-based
+
+```
+/pa --external on       # Enable external-only mode
+/pa --external off      # Disable, return to Claude
+/pa --external status   # Show current mode
+```
+
+### Natural language
+
+| User says | Action |
+|-----------|--------|
+| "switch to external models" | Enable |
+| "use copilot for everything" | Enable |
+| "go back to claude" | Disable |
+| "are we using external?" | Status |
+| "use external for this" | One-shot (no persist) |
+
+### Visual indicator
+
+When external mode active, PA prefixes responses:
+
+```
+🔌 [External: copilot/gpt-5.2]
+
+<response>
+```
+
+## Implementation Order
+
+1. Create `external-mode.json` state file
+2. Extend `model-policy.json` with external models
+3. Create `llm-router/` directory and scripts
+4. Add provider wrappers (opencode, gemini)
+5. Create delegation helper
+6. Update PA with toggle commands
+7. Add component-registry triggers
+8. Update session-start hook
+9. Test each provider
+
+## Validation
+
+```bash
+# Test router directly
+~/.claude/mcp/llm-router/invoke.py --model copilot/gpt-5.2 -p "Say hello"
+
+# Test delegation
+~/.claude/mcp/llm-router/delegate.py --tier sonnet -p "What is 2+2?"
+
+# Test toggle
+/pa --external on
+/pa what time is it?
+/pa --external off
+```
+
+## Rollback
+
+If issues arise:
+1. Set `external-mode.json` → `enabled: false`
+2. All operations revert to Claude immediately
+
+## Future Considerations
+
+- Auto-fallback to external when Claude rate-limited
+- Cost tracking per external model
+- Response quality comparison metrics
+- Additional providers (Mistral, local Ollama)

plans/index.json

@@ -121,6 +121,14 @@
       "implemented": "2026-01-07",
       "category": "enhancement",
       "notes": "This plan - meta!"
+    },
+    "gleaming-routing-mercury": {
+      "title": "External LLM integration",
+      "status": "implemented",
+      "created": "2026-01-08",
+      "implemented": "2026-01-08",
+      "category": "feature",
+      "notes": "fc-004 - Cloud API integration via opencode/gemini CLIs with session toggle"
     }
   }
 }

state/component-registry.json

@@ -143,6 +143,23 @@
         "block dangerous",
         "protect"
       ]
+    },
+    "external-mode": {
+      "description": "Toggle between Claude and external LLMs (Copilot, Z.AI, Gemini)",
+      "script": "~/.claude/mcp/llm-router/toggle.py",
+      "triggers": [
+        "external",
+        "use external",
+        "switch to external",
+        "external models",
+        "external only",
+        "use copilot",
+        "use opencode",
+        "back to claude",
+        "use claude again",
+        "disable external",
+        "external mode"
+      ]
     }
   },
   "commands": {
@@ -182,6 +199,15 @@
       ],
       "invokes": "skill:usage"
     },
+    "/external": {
+      "description": "Toggle and use external LLM mode (GPT-5.2, Gemini, etc.)",
+      "aliases": [
+        "/llm",
+        "/ext",
+        "/external-llm"
+      ],
+      "invokes": "command:external"
+    },
     "/README": {
       "description": "TODO",
       "aliases": [],

state/external-mode.json

@@ -0,0 +1,5 @@
+{
+  "enabled": false,
+  "activated_at": null,
+  "reason": null
+}

state/future-considerations.json

@@ -37,10 +37,12 @@
       "category": "integration",
       "title": "External LLM integration",
       "description": "Support for non-Claude models in the agent system",
-      "priority": "low",
-      "status": "deferred",
+      "priority": "medium",
+      "status": "resolved",
       "created": "2024-12-28",
-      "notes": "For specialized tasks or cost optimization"
+      "resolved": "2026-01-08",
+      "plan": "gleaming-routing-mercury",
+      "notes": "Implemented via opencode CLI. Models: github-copilot/gpt-5.2, zai-coding-plan/glm-4.7, etc. Toggle via /pa --external or natural language."
     },
     {
       "id": "fc-005",

state/kb.json

@@ -1 +1,171 @@
-{"infra":{"cluster":"k0s","nodes":3,"arch":"arm64"},"svc":{"gitops":"argocd","mon":"prometheus","alerts":"alertmanager"},"net":{},"hw":{"pi5_8gb":2,"pi3_1gb":1}}
+{
+  "infra": {
+    "cluster": "k0s",
+    "nodes": 3,
+    "arch": "arm64",
+    "storage": "longhorn",
+    "storage_class": "longhorn",
+    "backup": "longhorn-backup + minio-to-mega"
+  },
+  "hw": {
+    "pi5_8gb": 2,
+    "pi3_1gb": 1,
+    "roles": {
+      "control_plane": "pi5",
+      "workers": ["pi5", "pi3"]
+    }
+  },
+  "net": {
+    "metallb_pool": "192.168.153.240-192.168.153.254",
+    "ingress_nginx_ip": "192.168.153.240",
+    "ingress_haproxy_ip": "192.168.153.241",
+    "tailnet": "taildb3494.ts.net",
+    "dns_pattern": "<app>.<ns>.<ip>.nip.io"
+  },
+  "svc": {
+    "gitops": "argocd",
+    "monitoring": {
+      "metrics": "kube-prometheus-stack",
+      "logs": "loki-stack",
+      "alerts": "alertmanager",
+      "dashboards": "grafana"
+    },
+    "ingress": ["nginx-ingress-controller", "haproxy-ingress"],
+    "storage": ["longhorn", "local-path-storage", "minio"],
+    "networking": ["metallb", "tailscale-operator"]
+  },
+  "apps": {
+    "ai_stack": {
+      "namespace": "ai-stack",
+      "components": ["open-webui", "ollama", "litellm", "searxng", "n8n", "vllm"],
+      "models": ["gpt-oss:120b", "qwen3-coder"],
+      "ollama_host": "100.85.116.57:11434"
+    },
+    "home": ["home-assistant", "pihole", "plex"],
+    "infra": ["gitea", "docker-registry", "kubernetes-dashboard"],
+    "other": ["ghost", "tor-controller", "speedtest-tracker"]
+  },
+  "namespaces": [
+    "ai-stack", "argocd", "monitoring", "loki-system", "longhorn-system",
+    "metallb-system", "minio", "nginx-ingress-controller", "tailscale-operator",
+    "gitea", "home-assistant", "pihole", "pihole2", "plex", "ghost",
+    "kubernetes-dashboard", "docker-registry", "k8s-agent", "tools", "vpa"
+  ],
+  "urls": {
+    "grafana": "grafana.monitoring.192.168.153.240.nip.io",
+    "longhorn": "ui.longhorn-system.192.168.153.240.nip.io",
+    "open_webui": "oi.ai-stack.192.168.153.240.nip.io",
+    "searxng": "sx.ai-stack.192.168.153.240.nip.io",
+    "n8n": "n8n.ai-stack.192.168.153.240.nip.io",
+    "minio_console": "console.minio.192.168.153.240.nip.io",
+    "pihole": "pihole.192.168.153.240.nip.io",
+    "k8s_dashboard": "dashboard.kubernetes-dashboards.192.168.153.240.nip.io",
+    "home_assistant": "ha.home-assistant.192.168.153.241.nip.io",
+    "plex": "player.plex.192.168.153.246.nip.io"
+  },
+  "external_llm": {
+    "description": "Route requests to external LLMs via opencode or gemini CLI",
+    "state_file": "~/.claude/state/external-mode.json",
+    "router_dir": "~/.claude/mcp/llm-router/",
+    "commands": {
+      "toggle_on": "~/.claude/mcp/llm-router/toggle.py on --reason 'reason'",
+      "toggle_off": "~/.claude/mcp/llm-router/toggle.py off",
+      "status": "~/.claude/mcp/llm-router/toggle.py status",
+      "invoke": "~/.claude/mcp/llm-router/invoke.py --model MODEL -p 'prompt'"
+    },
+    "providers": ["opencode", "gemini"],
+    "tiers": {
+      "frontier": ["github-copilot/gpt-5.2", "github-copilot/gemini-3-pro-preview", "gemini/gemini-2.5-pro"],
+      "mid-tier": ["github-copilot/gpt-5-mini", "github-copilot/claude-sonnet-4.5", "github-copilot/gemini-3-flash-preview", "opencode/grok-code", "gemini/gemini-2.5-flash"],
+      "lightweight": ["opencode/gpt-5-nano", "zai-coding-plan/glm-4.5-air", "github-copilot/claude-haiku-4.5"]
+    },
+    "task_routing": {
+      "reasoning": "github-copilot/gpt-5.2",
+      "code-generation": "github-copilot/gemini-3-pro-preview",
+      "long-context": "gemini/gemini-2.5-pro",
+      "fast": "github-copilot/gemini-3-flash-preview",
+      "default": "github-copilot/claude-sonnet-4.5"
+    },
+    "notes": {
+      "opencode_path": "/home/linuxbrew/.linuxbrew/bin/opencode (NOT /usr/bin/opencode which crashes)",
+      "o3_removed": "github-copilot/o3 not available via GitHub Copilot"
+    }
+  },
+  "workstation": {
+    "hostname": "willlaptop",
+    "ip": "192.168.153.117",
+    "os": "Arch Linux",
+    "desktop": "GNOME",
+    "shell": "fish",
+    "terminal": ["ghostty", "alacritty", "gnome-console"],
+    "network": "systemd-networkd + iwd",
+    "theme": "Dracula",
+    "editors": ["vscode", "zed", "vim"],
+    "browsers": ["firefox", "chromium", "google-chrome", "zen-browser", "epiphany"],
+    "virtualization": ["docker", "podman", "distrobox", "virt-manager", "virtualbox", "gnome-boxes"],
+    "k8s_tools": ["k9s", "k0s-bin", "k0sctl-bin", "argocd", "krew", "kubecolor"],
+    "dev_langs": ["go", "rust", "python", "typescript", "zig", "bun", "node/npm/pnpm"],
+    "ai_local": {
+      "ollama": true,
+      "llama_swap": true,
+      "models": ["Qwen3-4b", "Gemma3-4b"]
+    },
+    "backup": ["restic", "timeshift", "btrbk", "chezmoi"],
+    "dotfiles": "chezmoi"
+  },
+  "repos": {
+    "willlaptop": {
+      "path": "~/Code/active/devops/willlaptop",
+      "remote": "git@gitea-gitea-ssh.taildb3494.ts.net:will/willlaptop.git",
+      "purpose": "Workstation provisioning and config",
+      "structure": {
+        "ansible/": "Machine provisioning playbooks",
+        "ansible/roles/common/": "Hostname, network, users, SSH config",
+        "ansible/roles/packages/": "Package installation (pacman, AUR, flatpak, appimage)",
+        "ansible/roles/packages/files/": "Package lists (pkglist.txt, aur_pkglist.txt, etc)",
+        "docker/": "Local Docker stacks",
+        "scripts/": "Utility scripts (backup, sync, networking)",
+        "MCP/": "MCP server configs",
+        "local_ollama/": "Local Ollama data"
+      },
+      "ansible_tags": ["network", "wifi", "ethernet", "users", "sshd", "pacman", "aur", "flatpak", "appimage"],
+      "docker_stacks": ["file_browser", "minio-longhorn-backup", "rancher-cleanup"],
+      "scripts": ["bridge-up.sh", "chezmoi-sync.sh", "curl-s3.sh", "kvm-bridge-setup.sh",
+                  "rclone-sync.sh", "restic-backup.sh", "restic-clean.sh"]
+    },
+    "homelab": {
+      "path": "~/Code/active/devops/homelab/homelab",
+      "remote": "git@github.com:will666/homelab.git",
+      "symlink": "~/.claude/repos/homelab",
+      "structure": {
+        "ansible/": "Ansible playbooks and templates for node provisioning",
+        "argocd/": "ArgoCD Application manifests (one per service)",
+        "charts/": "Helm values and raw manifests per service",
+        "charts/<svc>/values.yaml": "Helm chart values override",
+        "charts/<svc>/manifests/": "Raw K8s manifests (non-Helm resources)",
+        "docker/": "Docker Compose stacks for non-K8s workloads"
+      },
+      "charts": [
+        "ai-stack", "argocd", "argo-workflow", "cdi-operator",
+        "cloudflare-tunnel-ingress-controller", "docker-registry", "ghost",
+        "gitea", "haproxy-ingress", "harbor", "home-assistant", "k0s-backup",
+        "k8s-agent-dashboard", "kube-prometheus-stack", "kubernetes-dashboard",
+        "kubevirt", "local-path-storage", "loki-stack", "longhorn",
+        "longhorn-backup", "metallb", "minio", "minio-to-mega-backup",
+        "nfs-server-longhorn", "nginx-ingress-controller", "pihole", "pihole2",
+        "plex", "speedtest-tracker", "squareffect", "squareserver",
+        "tailscale-operator", "tools", "tor-controller", "traefik-ingress-controller",
+        "willlaptop-backup", "willlaptop-monitoring", "wills-portal"
+      ],
+      "docker_stacks": [
+        "protonvpn-proxy", "squareffect", "squareserver", "stable-diffusion-webui"
+      ],
+      "conventions": {
+        "argocd_app": "argocd/<name>.yaml points to charts/<name>/",
+        "helm_values": "charts/<name>/values.yaml for Helm overrides",
+        "raw_manifests": "charts/<name>/manifests/ for non-Helm K8s resources",
+        "naming": "ArgoCD app name = namespace name (usually)"
+      }
+    }
+  }
+}

state/model-policy.json

@@ -113,5 +113,85 @@
       "default": "haiku",
       "escalate_on": ["insufficient_context", "reasoning_required", "user_dissatisfied"]
     }
+  },
+  "external_models": {
+    "github-copilot/gpt-5.2": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/gpt-5.2"],
+      "use_cases": ["reasoning", "fallback"],
+      "tier": "frontier"
+    },
+    "github-copilot/claude-sonnet-4.5": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/claude-sonnet-4.5"],
+      "use_cases": ["general", "fallback"],
+      "tier": "mid-tier"
+    },
+    "github-copilot/claude-haiku-4.5": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/claude-haiku-4.5"],
+      "use_cases": ["simple"],
+      "tier": "lightweight"
+    },
+    "github-copilot/gemini-3-pro-preview": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/gemini-3-pro-preview"],
+      "use_cases": ["long-context", "reasoning"],
+      "tier": "frontier"
+    },
+    "github-copilot/gemini-3-flash-preview": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/gemini-3-flash-preview"],
+      "use_cases": ["fast", "general"],
+      "tier": "mid-tier"
+    },
+    "gemini/gemini-2.5-pro": {
+      "cli": "gemini",
+      "cli_args": ["-m", "gemini-2.5-pro"],
+      "use_cases": ["long-context", "reasoning"],
+      "tier": "frontier"
+    },
+    "gemini/gemini-2.5-flash": {
+      "cli": "gemini",
+      "cli_args": ["-m", "gemini-2.5-flash"],
+      "use_cases": ["fast", "general"],
+      "tier": "mid-tier"
+    },
+    "github-copilot/gpt-5-mini": {
+      "cli": "opencode",
+      "cli_args": ["-m", "github-copilot/gpt-5-mini"],
+      "use_cases": ["fast", "general"],
+      "tier": "mid-tier"
+    },
+    "opencode/gpt-5-nano": {
+      "cli": "opencode",
+      "cli_args": ["-m", "opencode/gpt-5-nano"],
+      "use_cases": ["fast", "simple"],
+      "tier": "lightweight"
+    },
+    "zai-coding-plan/glm-4.5-air": {
+      "cli": "opencode",
+      "cli_args": ["-m", "zai-coding-plan/glm-4.5-air"],
+      "use_cases": ["simple", "fast"],
+      "tier": "lightweight"
+    },
+    "opencode/grok-code": {
+      "cli": "opencode",
+      "cli_args": ["-m", "opencode/grok-code"],
+      "use_cases": ["code-generation", "general"],
+      "tier": "mid-tier"
+    }
+  },
+  "tier_to_external_map": {
+    "frontier": "github-copilot/gpt-5.2",
+    "mid-tier": "github-copilot/gpt-5-mini",
+    "lightweight": "opencode/gpt-5-nano"
+  },
+  "task_routing": {
+    "reasoning": "github-copilot/gpt-5.2",
+    "code-generation": "github-copilot/gemini-3-pro-preview",
+    "long-context": "gemini/gemini-2.5-pro",
+    "fast": "github-copilot/gemini-3-flash-preview",
+    "default": "github-copilot/claude-sonnet-4.5"
   }
 }

state/personal-assistant/general-instructions.json

@@ -20,6 +20,18 @@
       "status": "active",
       "added": "2026-01-04"
     },
+    {
+      "id": "f6a7b8c9-0123-45fa-1234-666666666666",
+      "instruction": "After reinstalling gmail-mcp package, run ~/.claude/patches/apply-gmail-auth-patch.sh to restore auto re-auth on token expiry.",
+      "status": "active",
+      "added": "2026-01-09"
+    },
+    {
+      "id": "a7b8c9d0-1234-56ab-2345-777777777777",
+      "instruction": "Homelab repo is at ~/Code/active/devops/homelab/homelab (canonical). ~/.claude/repos/homelab is a symlink to it. Always use the canonical path for new work.",
+      "status": "active",
+      "added": "2026-01-09"
+    },
     {
       "id": "b2c3d4e5-6789-01bc-def0-222222222222",
       "instruction": "Git workflow: See CLAUDE.md for full process. Use rebase merges, not merge commits.",