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
+```

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,
+        default=600,
-        help="Timeout in seconds (default: 300)"
+        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 = {

state/component-registry.json

@@ -199,6 +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/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

@@ -119,72 +119,79 @@
       "cli": "opencode",
       "cli_args": ["-m", "github-copilot/gpt-5.2"],
       "use_cases": ["reasoning", "fallback"],
-      "tier": "opus-equivalent"
+      "tier": "frontier"
     },
     "github-copilot/claude-sonnet-4.5": {
       "cli": "opencode",
       "cli_args": ["-m", "github-copilot/claude-sonnet-4.5"],
       "use_cases": ["general", "fallback"],
-      "tier": "sonnet-equivalent"
+      "tier": "mid-tier"
     },
     "github-copilot/claude-haiku-4.5": {
       "cli": "opencode",
       "cli_args": ["-m", "github-copilot/claude-haiku-4.5"],
       "use_cases": ["simple"],
-      "tier": "haiku-equivalent"
+      "tier": "lightweight"
-    },
-    "zai-coding-plan/glm-4.7": {
-      "cli": "opencode",
-      "cli_args": ["-m", "zai-coding-plan/glm-4.7"],
-      "use_cases": ["code-generation"],
-      "tier": "opus-equivalent"
     },
     "github-copilot/gemini-3-pro-preview": {
       "cli": "opencode",
       "cli_args": ["-m", "github-copilot/gemini-3-pro-preview"],
       "use_cases": ["long-context", "reasoning"],
-      "tier": "opus-equivalent"
+      "tier": "frontier"
     },
     "github-copilot/gemini-3-flash-preview": {
       "cli": "opencode",
       "cli_args": ["-m", "github-copilot/gemini-3-flash-preview"],
       "use_cases": ["fast", "general"],
-      "tier": "sonnet-equivalent"
+      "tier": "mid-tier"
-    },
-    "github-copilot/o3": {
-      "cli": "opencode",
-      "cli_args": ["-m", "github-copilot/o3"],
-      "use_cases": ["complex-reasoning"],
-      "tier": "sonnet-equivalent"
-    },
-    "opencode/big-pickle": {
-      "cli": "opencode",
-      "cli_args": ["-m", "opencode/big-pickle"],
-      "use_cases": ["general"],
-      "tier": "sonnet-equivalent"
     },
     "gemini/gemini-2.5-pro": {
       "cli": "gemini",
       "cli_args": ["-m", "gemini-2.5-pro"],
       "use_cases": ["long-context", "reasoning"],
-      "tier": "sonnet-equivalent"
+      "tier": "frontier"
     },
     "gemini/gemini-2.5-flash": {
       "cli": "gemini",
       "cli_args": ["-m", "gemini-2.5-flash"],
       "use_cases": ["fast", "general"],
-      "tier": "haiku-equivalent"
+      "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"
     }
   },
-  "claude_to_external_map": {
+  "tier_to_external_map": {
-    "opus": "github-copilot/gpt-5.2",
+    "frontier": "github-copilot/gpt-5.2",
-    "sonnet": "github-copilot/claude-sonnet-4.5",
+    "mid-tier": "github-copilot/gpt-5-mini",
-    "haiku": "github-copilot/claude-haiku-4.5"
+    "lightweight": "opencode/gpt-5-nano"
   },
   "task_routing": {
     "reasoning": "github-copilot/gpt-5.2",
-    "code-generation": "zai-coding-plan/glm-4.7",
+    "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.",