deepseek-ai/deepseek-harness · error · LlmError

UNSUPPORTED_CONTENT

UNSUPPORTED_CONTENT

Error message

compaction summary cannot contain image output

What it means

Error "compaction summary cannot contain image output" thrown in deepseek-ai/deepseek-harness.

Source

Thrown at packages/compaction/compaction-basic/src/summarizer.ts:221

      error.code = finish.failure.code
      return error
    }
    case 'max-tokens': {
      const error = new Error('summarization truncated at the token cap (incomplete checkpoint)') as Error & { code?: string }
      error.code = 'MAX_TOKENS'
      return error
    }
    default:
      return undefined
  }
}

/** Reject visual output and keep only text before synthesizing a user message. */
function summaryText(
  blocks: readonly ContentBlock[],
): Array<Extract<ContentBlock, { type: 'text' }>> {
  if (contentHasImage(blocks)) {
    throw new LlmError('compaction summary cannot contain image output', 'UNSUPPORTED_CONTENT')
  }
  return blocks.filter((block): block is Extract<ContentBlock, { type: 'text' }> => block.type === 'text')
}

View on GitHub (pinned to b150a551b8)

Solutions

1. Remove image output from the compaction summary; summaries must be text only.

When it happens

Trigger: Thrown at packages/compaction/compaction-basic/src/summarizer.ts:221 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of deepseek-ai/deepseek-harness@b150a551b8 (2026-08-24). Data as JSON: /api/errors/f1d75d27663dcbdc. Report an issue: GitHub.