Skip to main content
Claude Code is an AI coding agent by Anthropic that reads code, edits files, and runs commands in the terminal.

​
Installation

curl -fsSL https://claude.ai/install.sh | bash
Open CC Switch and add a RuoLi configuration:
FieldValue
API URLhttps://ruoli.dev
API KeyYour Key
Select Claude Code and click Apply.
The API URL for Claude Code is https://ruoli.dev, without /v1.

​
Switch Models

Beyond native Claude models, RuoLi routes to third-party models like gpt-5.5, GLM, Kimi, and DeepSeek. Open CC Switch → Edit Provider → Model Mapping, point each Claude alias at the target model, and save — no JSON editing required.
CC Switch Model Mapping
FieldPurpose
Main ModelThe default model Claude Code calls
Thinking ModelUsed when extended / reasoning mode is on
Haiku Default ModelTarget model for the haiku alias
Sonnet Default ModelTarget model for the sonnet alias
Opus Default ModelTarget model for the opus alias
Leave these blank if your provider is natively Claude — only fill them in when you want to route aliases to a different model.

​
Disable Attribution Header (Required)

Claude Code injects a dynamic attribution header (containing session ID and more) into every request by default — this completely destroys upstream prompt caching, causing cache hit rates to collapse, costs to spike, and responses to slow down.Always disable it, whether you’re using native Claude models or third-party models like GLM / Kimi / DeepSeek.
In CC Switch → Edit Provider → Config JSON, add one line to env: 
"CLAUDE_CODE_ATTRIBUTION_HEADER": "0"
Add CLAUDE_CODE_ATTRIBUTION_HEADER in CC Switch JSON
The same applies to manual ~/.claude/settings.json — see the example below.

​
Manual Configuration

Edit ~/.claude/settings.json: 
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://ruoli.dev",
    "ANTHROPIC_AUTH_TOKEN": "sk-YOUR-KEY",
    "CLAUDE_CODE_ATTRIBUTION_HEADER": "0"
  }
}
Or via environment variables: 
export ANTHROPIC_BASE_URL=https://ruoli.dev
export ANTHROPIC_AUTH_TOKEN=sk-YOUR-KEY
export CLAUDE_CODE_ATTRIBUTION_HEADER=0

​
Configure Context Compression

Claude Code auto-compresses context at about 83% of the context window by default. If you’re using a 1M context window, you can adjust when compression triggers via CLAUDE_AUTOCOMPACT_PCT_OVERRIDE. For example, to trigger compression at 180k tokens (180k / 1000k = 18%): Add to the env block in ~/.claude/settings.json: 
{
  "env": {
    "CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "18"
  }
}
Or set a temporary environment variable: 
export CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=18
ValueTrigger point (1M window)Use case
18~180k tokensKeep context clean frequently
50~500k tokensBalance performance and context
83~830k tokens (default)Maximize context utilization
You can only set the threshold below 83%. Values above 83% are silently ignored.
Official Documentation: code.claude.com/docs