ruvnet/ruflo · error · Error

maxTokens exceeds limit of ${this.config.maxTokensLimit}

Error message

maxTokens exceeds limit of ${this.config.maxTokensLimit}

What it means

Request validation in SamplingManager: the requested maxTokens exceeds the server's configured maxTokensLimit. The refusal happens up front so providers never receive an over-budget completion request; lower maxTokens or raise the server limit.

Source

Thrown at v3/@claude-flow/mcp/src/sampling.ts:229

  } {
    return {
      requestCount: this.requestCount,
      totalTokens: this.totalTokens,
      providerCount: this.providers.size,
      defaultProvider: this.defaultProvider,
    };
  }

  /**
   * Validate sampling request
   */
  private validateRequest(request: CreateMessageRequest): void {
    if (!request.messages || request.messages.length === 0) {
      throw new Error('Messages are required');
    }

    if (request.maxTokens > this.config.maxTokensLimit) {
      throw new Error(`maxTokens exceeds limit of ${this.config.maxTokensLimit}`);
    }

    if (request.temperature !== undefined && (request.temperature < 0 || request.temperature > 2)) {
      throw new Error('Temperature must be between 0 and 2');
    }
  }

  /**
   * Select provider based on preferences
   */
  private selectProvider(preferences?: ModelPreferences): LLMProvider | undefined {
    // If hints provided, try to find matching provider
    if (preferences?.hints) {
      for (const hint of preferences.hints) {
        if (hint.name && this.providers.has(hint.name)) {
          return this.providers.get(hint.name);
        }
      }

View on GitHub (pinned to fa13ee4ad6)

Solutions

1. Reduce maxTokens in the request to a value at or below the server's maxTokensLimit.
2. Raise maxTokensLimit in the sampling configuration if the larger budget is legitimate.
3. Clamp maxTokens to the limit instead of rejecting when truncation is acceptable.

When it happens

Trigger: A sampling request specifies maxTokens larger than the server's configured maxTokensLimit.

Common situations: Client requests a very large completion, or the server's maxTokensLimit is set lower than the client's default.

AI-assisted analysis of ruvnet/ruflo@fa13ee4ad6 (2026-08-18). Data as JSON: /api/errors/e6ce73b59148426d. Report an issue: GitHub.