What this error means
gemini --list-sessions ignores saved /auth state and strictly requires GEMINI_API_KEY env var is a Gemini CLI failure pattern reported for developers trying to fix gemini --list-sessions crashing when gemini_api_key is not set despite saved oauth auth. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Official Gemini CLI issue #26906 (2026-05-12) reports --list-sessions ignores internally saved OAuth authentication state and crashes without GEMINI_API_KEY env var. Main gemini command works fine with saved auth, but --list-sessions uses different auth resolution logic.
Common causes
- Developers who authenticated Gemini CLI via OAuth (
/authcommand) find that--list-sessionsignores the saved auth state and crashes unless GEMINI_API_KEY is explicitly set in the shell. This breaks the core workflow of session management after OAuth login. - Official Gemini CLI issue #26906 (2026-05-12) reports
--list-sessionsignores internally saved OAuth authentication state and crashes without GEMINI_API_KEY env var. Maingeminicommand works fine with saved auth, but --list-sessions uses different auth resolution logic.
Quick fixes
- Confirm the exact error signature matches
gemini --list-sessions ignores saved /auth state and strictly requires GEMINI_API_KEY env var. - Check the Gemini CLI account, local tool state, and provider configuration involved in the failing workflow.
- Verify the account session, API key, provider settings, and environment where the failing tool is running.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.