deepseek-ai/deepseek-harness · error · LlmError

UNSUPPORTED_REASONING_EFFORT

UNSUPPORTED_REASONING_EFFORT

Error message

provider "${config.provider}" model "${config.model}" does not support reasoning effort "${requested}"

What it means

Error "provider "${config.provider}" model "${config.model}" does not support reasoning effort "${requested}"" thrown in deepseek-ai/deepseek-harness.

Source

Thrown at packages/llm/llm/src/index.ts:792

  ): Promise<{ config: LlmCallConfig; context?: LlmModelContext; modelInfo: LlmResolvedModelInfo }> {
    const info = await this.resolveModelInfoFor(registration, config.model, signal)
    return this.resolveCallWithInfo(config, info)
  }

  /** Validate request controls against one already-bound exact model result. */
  private resolveCallWithInfo(
    config: LlmCallConfig,
    info: LlmResolvedModelInfo,
  ): { config: LlmCallConfig; context?: LlmModelContext; modelInfo: LlmResolvedModelInfo } {
    const defaulted = config.maxTokens === undefined && info.defaultMaxTokens !== undefined
      ? { ...config, maxTokens: info.defaultMaxTokens }
      : config
    const reasoning = info.reasoning
    const requested = defaulted.reasoningEffort
    let resolvedConfig = defaulted
    if (reasoning === undefined) {
      if (requested !== undefined) {
        throw new LlmError(
          `provider "${config.provider}" model "${config.model}" does not support reasoning effort "${requested}"`,
          'UNSUPPORTED_REASONING_EFFORT',
        )
      }
    } else {
      const effective = requested ?? reasoning.defaultEffort
      if (effective !== undefined) {
        if (!reasoning.efforts.some(effort => effort.id === effective)) {
          throw new LlmError(
            `provider "${config.provider}" model "${config.model}" does not support reasoning effort "${effective}"`,
            'UNSUPPORTED_REASONING_EFFORT',
          )
        }
        if (requested !== effective) resolvedConfig = { ...defaulted, reasoningEffort: effective }
      }
    }
    return {
      config: resolvedConfig,

View on GitHub (pinned to b150a551b8)

Solutions

1. Choose a reasoning effort the provider/model supports.

When it happens

Trigger: Thrown at packages/llm/llm/src/index.ts:792 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/3b304b8f77a2b756. Report an issue: GitHub.