f9111eea11
- AGENTS.md: workspace conventions and guidelines - SOUL.md: personality and principles - USER.md: about William - IDENTITY.md: who I am - TOOLS.md: local notes and infrastructure details - MEMORY.md: long-term memory - HEARTBEAT.md: periodic task config - LLM-ROUTING.md: model selection guide - memory/2026-01-26.md: daily log - .gitignore: exclude runtime state and secrets
112 lines
3.9 KiB
Markdown
112 lines
3.9 KiB
Markdown
# LLM Routing Guide
|
|
|
|
Use the right model for the job. Cost and speed matter.
|
|
|
|
## Available CLIs
|
|
|
|
| CLI | Auth | Best For |
|
|
|-----|------|----------|
|
|
| `claude` | Pro subscription | Complex reasoning, this workspace |
|
|
| `opencode` | GitHub Copilot subscription | Code, free Copilot models |
|
|
| `gemini` | Google account (free tier available) | Long context, multimodal |
|
|
|
|
## Model Tiers
|
|
|
|
### ⚡ Fast & Cheap (Simple Tasks)
|
|
```bash
|
|
# Quick parsing, extraction, formatting, simple questions
|
|
opencode run -m github-copilot/claude-haiku-4.5 "parse this JSON and extract emails"
|
|
opencode run -m zai-coding-plan/glm-4.5-flash "summarize in 2 sentences"
|
|
gemini -m gemini-2.0-flash "quick question here"
|
|
```
|
|
|
|
**Use for:** Log parsing, data extraction, simple formatting, yes/no questions, summarization
|
|
|
|
### 🔧 Balanced (Standard Work)
|
|
```bash
|
|
# Code review, analysis, standard coding tasks
|
|
opencode run -m github-copilot/claude-sonnet-4.5 "review this code"
|
|
opencode run -m github-copilot/gpt-5-mini "explain this error"
|
|
gemini -m gemini-2.5-pro "analyze this architecture"
|
|
```
|
|
|
|
**Use for:** Code generation, debugging, analysis, documentation
|
|
|
|
### 🧠 Powerful (Complex Reasoning)
|
|
```bash
|
|
# Complex reasoning, multi-step planning, difficult problems
|
|
claude -p --model opus "design a system for X"
|
|
opencode run -m github-copilot/gpt-5.2 "complex reasoning task"
|
|
opencode run -m github-copilot/gemini-3-pro-preview "architectural decision"
|
|
```
|
|
|
|
**Use for:** Architecture decisions, complex debugging, multi-step planning
|
|
|
|
### 📚 Long Context
|
|
```bash
|
|
# Large codebases, long documents, big context windows
|
|
gemini -m gemini-2.5-pro "analyze this entire codebase" < large_file.txt
|
|
opencode run -m github-copilot/gemini-3-pro-preview "summarize all these files"
|
|
```
|
|
|
|
**Use for:** Analyzing large files, long documents, full codebase understanding
|
|
|
|
## Quick Reference
|
|
|
|
| Task | Model | CLI Command |
|
|
|------|-------|-------------|
|
|
| Parse JSON/logs | haiku | `opencode run -m github-copilot/claude-haiku-4.5 "..."` |
|
|
| Simple summary | flash | `gemini -m gemini-2.0-flash "..."` |
|
|
| Code review | sonnet | `opencode run -m github-copilot/claude-sonnet-4.5 "..."` |
|
|
| Write code | codex | `opencode run -m github-copilot/gpt-5.1-codex "..."` |
|
|
| Debug complex issue | sonnet/opus | `claude -p --model sonnet "..."` |
|
|
| Architecture design | opus | `claude -p --model opus "..."` |
|
|
| Analyze large file | gemini-pro | `gemini -m gemini-2.5-pro "..." < file` |
|
|
| Quick kubectl help | flash | `opencode run -m zai-coding-plan/glm-4.5-flash "..."` |
|
|
|
|
## Cost Optimization Rules
|
|
|
|
1. **Start small** — Try haiku/flash first, escalate only if needed
|
|
2. **Batch similar tasks** — One opus call > five haiku calls for complex work
|
|
3. **Use subscriptions** — GitHub Copilot models are "free" with subscription
|
|
4. **Cache results** — Don't re-ask the same question
|
|
5. **Context matters** — Smaller context = faster + cheaper
|
|
|
|
## Example Workflows
|
|
|
|
### Triage emails (cheap)
|
|
```bash
|
|
opencode run -m github-copilot/claude-haiku-4.5 "categorize these emails as urgent/normal/spam"
|
|
```
|
|
|
|
### Code review (balanced)
|
|
```bash
|
|
opencode run -m github-copilot/claude-sonnet-4.5 "review this PR for issues"
|
|
```
|
|
|
|
### Architectural decision (powerful)
|
|
```bash
|
|
claude -p --model opus "given these constraints, design the best approach for..."
|
|
```
|
|
|
|
### Summarize long doc (long context)
|
|
```bash
|
|
cat huge_document.md | gemini -m gemini-2.5-pro "summarize key points"
|
|
```
|
|
|
|
## For Flynn (Clawdbot)
|
|
|
|
When spawning sub-agents or doing background work:
|
|
- Use `sessions_spawn` with appropriate model hints
|
|
- For simple extraction: spawn with default (cheaper model)
|
|
- For complex analysis: explicitly request opus
|
|
|
|
When using exec to call CLIs:
|
|
- Prefer `opencode run` for one-shot tasks (GitHub Copilot = included)
|
|
- Use `claude -p` when you need Claude-specific capabilities
|
|
- Use `gemini` for very long context or multimodal
|
|
|
|
---
|
|
|
|
*Principle: Don't use a sledgehammer to hang a picture.*
|