Files

OpenCode Test f63172c4cf 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>

2026-01-12 03:30:51 -08:00

2.7 KiB

Raw Blame History

name, description, aliases

name

description

aliases

external

Toggle and use external LLM mode (GPT-5.2, Gemini, etc.)

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

~/.claude/mcp/llm-router/toggle.py status

Toggle On/Off

~/.claude/mcp/llm-router/toggle.py on --reason "reason"
~/.claude/mcp/llm-router/toggle.py off

Invoke

~/.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

2.7 KiB Raw Blame History