Gemini CLI
Gemini CLI errors and fixes
19 Gemini CLI error messages, quoted verbatim, each with what it means, why it happens and the fix documented in official docs, maintainer replies or release notes. Verified .
All Gemini CLI errors
- Status: Fixed in release2 fixed in release
- Status: Workaround9 workaround
- Status: By design7 by design
- Status: Open1 open
You must be a named user on your organization's Gemini Code Assist Standard edition subscription to use this service. Please contact your administrator to request an entitlement to Gemini Code Assist Standard edition.A 403 PERMISSION_DENIED returned during sign-in or on the first request: the CLI is checking for an organization (Standard edition) subscription and the signed-in account has no entitlement.Status: WorkaroundFailed to sign in. Message: Your current account is not eligible... because it is not currently available in your location.Sign in with Google was refused because Gemini Code Assist for individuals is not offered in the account's location.Status: By designFailed to sign in. Message: Request contains an invalid argumentFree-tier activation of Gemini Code Assist failed during Sign in with Google.Status: WorkaroundUNABLE_TO_GET_ISSUER_CERT_LOCALLY or unable to get local issuer certificateNode.js could not verify the TLS certificate chain of Google's endpoints, so sign-in or API requests fail.Status: WorkaroundThis account requires setting the GOOGLE_CLOUD_PROJECT or GOOGLE_CLOUD_PROJECT_ID env var. See https://geminicli.com/docs/get-started/authentication/#set-gcpSign in with Google succeeded, but the account type (Workspace, school, company, or a Code Assist license) needs a Google Cloud project for Gemini CLI to use. Older releases showed it as "Failed to login. Message: This account requires setting the GOOGLE_CLOUD_PROJECT env var".Status: By designInvalid Google Cloud Project ID: "<projectId>". The GOOGLE_CLOUD_PROJECT (or GOOGLE_CLOUD_PROJECT_ID) environment variable must be set to your string-based Project ID (e.g., "my-project-123"), not your numeric Project Number. Please update your environment variables.GOOGLE_CLOUD_PROJECT is set to the numeric Project Number instead of the string Project ID, and the CLI rejects it before sign-in.Status: By designFailed to login. Message: Precondition check failed.Code Assist onboarding rejected the login request, usually because a Google Cloud project was sent for a free-tier login.Status: Fixed in releaseYou are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license.Login found a Google Cloud project configured but no Gemini Code Assist license tied to the account.Status: WorkaroundFailed to sign in. Message: You do not have a valid license of this product. Please contact your administrator to request a license. If you are not an enterprise user and believe you are receiving this message as an error, please try using the latest version and logging in again.Google Workspace (enterprise) accounts with a Google Cloud project configured as the docs describe are blocked at sign-in.Status: OpenAPI error: 429 - Resource exhaustedThe request was rejected because a rate limit or quota was exceeded (HTTP 429 Too Many Requests / RESOURCE_EXHAUSTED).Status: WorkaroundUsage limit reached for <model>.A terminal quota error for the current model: the daily quota for that model is used up. The dialog adds the reset time when known, plus "/stats model for usage details", "/model to switch models." and, for Sign in with Google, "/auth to switch to API key."Status: Fixed in releaseWe are currently experiencing high demand for <model>.A capacity error, not a personal quota problem: the backend is out of capacity for the model. Raw API forms include 503 "The model is overloaded. Please try again later." (UNAVAILABLE) and 429 "Resource exhausted. Please try again later."Status: WorkaroundRequested entity was not found.A 404 from the API when the selected model (here, Gemini 3 at launch) is not available to the account.Status: Workaround[API Error: Model stream ended with an invalid chunk or missing finish reason.]The model's streamed response ended without a valid finish reason or content, so the turn stopped mid-task. Current source raises this as InvalidStreamError with types such as NO_FINISH_REASON and MALFORMED_FUNCTION_CALL (for example "Model stream ended without a finish reason.").Status: WorkaroundSyntaxError: Invalid regular expression flagsThe CLI crashes on startup inside a dependency (for example node_modules/string-width/index.js) because the Node.js runtime is too old for the regex syntax it uses.Status: By designnpm WARN deprecated node-domexception@1.0.0A deprecation warning printed during npm install -g or npm update -g of Gemini CLI. The install still completes. A similar warning appears for old glob versions (npm WARN deprecated glob).Status: By designMCP error -32000: Connection closedA configured MCP server process exited or closed its stdio/HTTP connection, so the server shows as DISCONNECTED and its tools are unavailable.Status: WorkaroundPlease set an Auth method in your <user settings.json path> or specify one of the following environment variables before running: GEMINI_API_KEY, GOOGLE_GENAI_USE_VERTEXAI, GOOGLE_GENAI_USE_GCANon-interactive (headless) mode found no cached credential, no configured auth type, and no auth environment variable. It exits with code 41 (FatalAuthenticationError).Status: By designSandbox image '<image>' is missing or could not be pulled. Please check the image name, your network connection, or notify gemini-cli-dev@google.com if the issue persists.Sandboxing is enabled (Docker or Podman) but the sandbox container image is not present locally and could not be pulled. The CLI exits with code 44 (FatalSandboxError).Status: By design
New to Gemini CLI? Start with Gemini CLI in the tools directory.
Newsletter
Fixes for the tools you use, weekly
One email per week. New coding agent releases, what broke, and how developers are working around it.