Skip to main content

Provider Configuration Guide

The following configurations are recommended based on our internal use cases. The goal is to achieve minimum API cost and stable performance across a regression test suite of more than 10 test cases.

Claude​

Minimum recommended model: claude-sonnet-4-6

AI_MAX_TOKENS=8192
MAX_SNAPSHOTS_HISTORY=0
CONTEXT_COMPRESSION=true
COMPRESSION_THRESHOLD_MIN=2500
COMPRESSION_THRESHOLD_LEAP=500
LARGE_CONTENT_THRESHOLD=10000
RATE_LIMIT_RETRY=2
MAX_ITERATIONS=100
MAXIMUM_RESTRICTED_TOOL_USAGE=3

DeepSeek​

Minimum recommended model: deepseek-v4-pro

AI_MAX_TOKENS=8192
MAX_SNAPSHOTS_HISTORY=0
CONTEXT_COMPRESSION=true
COMPRESSION_THRESHOLD_MIN=12500
COMPRESSION_THRESHOLD_LEAP=5000
LARGE_CONTENT_THRESHOLD=10000
RATE_LIMIT_RETRY=2
MAX_ITERATIONS=100
MAXIMUM_RESTRICTED_TOOL_USAGE=3
important

DeepSeek performs better with a Chinese system prompt. Rename the provided system-prompt-cn.md to system.prompt.md and place it under /agent/config, replacing the existing English prompt file of the same name.

OpenAI​

Supported in code but not tested in a real environment. Please reach out on our Discord channel if you need help.

Gemini​

Supported in code but not tested in a real environment. Please reach out on our Discord channel if you need help.