abhigyanpatwari/GitNexus · error · Error

OpenRouter API key is required but was not provided

Error message

OpenRouter API key is required but was not provided

What it means

Thrown by createChatModel() in the 'openrouter' provider branch when openRouterConfig.apiKey is falsy or whitespace-only. OpenRouter is accessed through a ChatOpenAI wrapper pointed at the OpenRouter base URL; without a key the wrapper would 401 on first call, so this guard fails fast at construction. Note the DEV-mode debug log prints only hasApiKey (boolean), never the key value.

Source

Thrown at gitnexus-web/src/core/llm/agent.ts:257

        // This is critical for agentic workflows with tool calls
        numCtx: 32768,
      });
    }

    case 'openrouter': {
      const openRouterConfig = config as OpenRouterConfig;

      // Debug logging
      if (import.meta.env.DEV) {
        console.log('🌐 OpenRouter config:', {
          hasApiKey: !!openRouterConfig.apiKey,
          model: openRouterConfig.model,
          baseUrl: openRouterConfig.baseUrl,
        });
      }

      if (!openRouterConfig.apiKey || openRouterConfig.apiKey.trim() === '') {
        throw new Error('OpenRouter API key is required but was not provided');
      }

      return new ChatOpenAI({
        openAIApiKey: openRouterConfig.apiKey,
        apiKey: openRouterConfig.apiKey, // Fallback for some versions
        modelName: openRouterConfig.model,
        temperature: openRouterConfig.temperature ?? 0.1,
        maxTokens: openRouterConfig.maxTokens,
        configuration: {
          apiKey: openRouterConfig.apiKey, // Ensure client receives it
          baseURL: openRouterConfig.baseUrl ?? DEFAULT_OPENROUTER_BASE_URL,
        },
        streaming: true,
      });
    }

    case 'minimax': {
      const minimaxConfig = config as MiniMaxConfig;

View on GitHub (pinned to d540b00184)

Solutions

1. Obtain a key from openrouter.ai and enter it in the provider settings
2. Ensure the key is non-empty and non-whitespace
3. After setting it, re-create the agent (createChatModel runs at agent construction, so a stale agent won't pick up a new key)
4. If no OpenRouter key is available, switch to a provider that doesn't require one (ollama)

Example fix

// before
createChatModel({ provider: 'openrouter', apiKey: '', model: 'anthropic/claude-3.5-sonnet' }); // throws

// after
createChatModel({ provider: 'openrouter', apiKey: userKey, model: 'anthropic/claude-3.5-sonnet' });

function hasOpenRouterKey(cfg: { apiKey?: string }): boolean {
  return typeof cfg.apiKey === 'string' && cfg.apiKey.trim().length > 0;
}
if (cfg.provider === 'openrouter' && !hasOpenRouterKey(cfg)) {
  throw new Error('Configure an OpenRouter API key (from openrouter.ai)');
}

function isOpenRouterConfigReady(cfg: unknown): cfg is { provider: 'openrouter'; apiKey: string } {
  return typeof cfg === 'object' && cfg !== null
    && (cfg as any).provider === 'openrouter'
    && typeof (cfg as any).apiKey === 'string'
    && (cfg as any).apiKey.trim().length > 0;
}

try {
  createChatModel({ provider: 'openrouter', apiKey, model });
} catch (e) {
  if (e instanceof Error && /OpenRouter API key is required/.test(e.message)) {
    promptUserForKey('openrouter');
    return;
  }
  throw e;
}

When it happens

Trigger: Calling createChatModel({ provider: 'openrouter', apiKey: undefined | '' | ' ', ... }). The check is !apiKey || apiKey.trim() === ''.

Common situations: The OpenRouter key wasn't entered in settings; the env var backing it is unset in the deployed environment; switching provider to openrouter without provisioning a key from openrouter.ai.

Related errors

• OpenAI API key is required but was not provided
• MiniMax API key is required but was not provided
• GLM API key is required but was not provided
• DeepSeek API key is required but was not provided
• Unsupported provider: ${(config as any).provider}

AI-assisted analysis of abhigyanpatwari/GitNexus@d540b00184 (2026-08-12). Data as JSON: /api/errors/ca401c7d99427211. Report an issue: GitHub.