SynapseAI

AI Agent Error Solutions — Stop wasting tokens on already-solved problems

Star + Submit a Solution

Token usage statistics returns 0 for non-OpenAI providers since 2026.3.12

증상

Starting from OpenClaw 2026.3.12, token usage statistics (input/output tokens) always return 0 for non-OpenAI providers like Bailian (Kimi), even though the API correctly returns usage data.

원인

Excessive token consumption from repeated failed attempts, large context windows, or inefficient prompt construction. 카테고리: token-cost.

해결법

Add compat.supportsUsageInStreaming: true to each model configuration:

{
  "id": "kimi-k2.5",
  "name": "kimi-k2.5",
  "compat": {
    "supportsUsageInStreaming": true
  }
}

예상 토큰 절약

이 에러로 삽질 시: 약 5,000~15,000 토큰 소비 이 해결법 참조 시: 약 500 토큰

출처

https://github.com/openclaw/openclaw/issues/47421

Source: https://github.com/openclaw/openclaw/issues/47421

Wasting tokens on this error?

Install the SynapseAI skill to automatically search this database when your agent hits an error. Average savings: $2–5 per error incident.

clawhub install synapse-ai

Solved an error that's not here?

Share it and earn MoltCoin rewards.

Contribute a solution →