What causes "No api keys/credentials provided for models" in plandex-ai/plandex?

Configure model API keys/credentials for your account or org (dashboard integrations settings)

No api keys/credentials provided for models

Error message

No api keys/credentials provided for models

What it means

initClients returns HTTP 400 'No api keys/credentials provided for models' when authVars is empty AND the server runs in cloud mode (IS_CLOUD env set). In cloud mode, users must supply model credentials (or use integrated models); without any, LLM clients cannot be initialized, so the request is rejected as a client configuration problem. Self-hosted (IS_CLOUD unset) deployments skip this check.

Source

Thrown at app/server/handlers/client_helper.go:74

	if apiErr != nil {
		log.Printf("Error getting integrated models: %v\n", apiErr)
		http.Error(w, "Error getting integrated models", http.StatusInternalServerError)
		return initClientsResult{}
	}

	if hookResult.GetIntegratedModelsResult != nil && hookResult.GetIntegratedModelsResult.IntegratedModelsMode {
		merged := map[string]string{}
		for k, v := range hookResult.GetIntegratedModelsResult.AuthVars {
			merged[k] = v
		}
		if authVars[shared.AnthropicClaudeMaxTokenEnvVar] != "" {
			merged[shared.AnthropicClaudeMaxTokenEnvVar] = authVars[shared.AnthropicClaudeMaxTokenEnvVar]
		}
		authVars = merged
	}
	if len(authVars) == 0 && os.Getenv("IS_CLOUD") != "" {
		log.Println("No api keys/credentials provided for models")
		http.Error(w, "No api keys/credentials provided for models", http.StatusBadRequest)
		return initClientsResult{}
	}

	clients := model.InitClients(authVars, settings, orgUserConfig)

	return initClientsResult{
		clients:  clients,
		authVars: authVars,
	}
}

View on GitHub (pinned to e2d772072e)

Solutions

Configure model API keys/credentials for your account or org (dashboard integrations settings)
Ensure the client sends authVars with at least one valid credential in the request
Verify integrated models are enabled so the hook supplies authVars
If self-hosting, confirm IS_CLOUD is set only when the cloud credential requirement is intended

Example fix

// before
req := shared.TellPlanRequest{} // no authVars
// after
req := shared.TellPlanRequest{
    AuthVars: map[string]string{"OPENAI_API_KEY": os.Getenv("OPENAI_API_KEY")},
}

Defensive patterns

Strategy: validation

Validate before calling

// client: ensure credentials exist before invoking plan operations
if len(authVars) == 0 {
    return errors.New("configure model API keys in settings before running plans")
}

Type guard

func hasCredentials(authVars map[string]string) bool {
    for _, v := range authVars { if v != "" { return true } }
    return false
}

Prevention

Configure org/user API keys or integrated models before first use
Always populate authVars in API requests on cloud deployments
After revoking an integration, add a replacement credential source
Only set IS_CLOUD on deployments where enforced credentials are intended

When it happens

Trigger: Tell/Build/Apply plan or loadContexts requests in cloud deployments when: the user/org has no stored API keys or integrated models, the client sends an empty authVars map, or deprecated apiKeys field is omitted and integrated models are not enabled.

Common situations: New user account with no model credentials configured yet; API client upgraded to the authVars flow while still sending nothing; org integration revoked leaving authVars empty after the hook merge; keys stored under wrong env var names so the map ends up empty.

Understand the failure class

Background: "API key is required" / "API key not found" / "No API key was set": the missing-api-key error family across 16 libraries — this error's family across 16 libraries.

Related errors

AI-assisted analysis of plandex-ai/plandex@e2d772072e (2026-09-05). Data as JSON: /api/errors/d75b8a7d17ba3a4a. Report an issue: GitHub.