Skip to content

Gemini onboard process could not handle key expiration properly #1942

@xiaoming-nv

Description

@xiaoming-nv

Description

Description:
nemoclaw onboard should ask for new key if the gemini key user provided is expired

[Environment]
Device: Ubuntu 24.04
Node.js:v22.22.2
npm: 10.9.7
Docker: Docker version 29.1.3
OpenShell CLI: 0.0.26
NemoClaw: v0.0.14
OpenClaw 2026.3.11 (29dc654)

[Steps to Reproduce]

install Nemoclaw: curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash
select Google Gemini
input an expired key
select "3) gemini-3-flash-preview" for the model

[Expected Result]

Wizard should ask user to input a new key to replace the expired one

[Actual Result]

Wizard does not give the user the opportunity to input a new key

[Log]
user@xxxxx:~$ nemoclaw onboard

NemoClaw Onboarding

[1/8] Preflight checks
──────────────────────────────────────────────────
✓ Docker is running
✓ Container runtime: docker
✓ openshell CLI: openshell 0.0.26
✓ Port 8080 already owned by healthy NemoClaw runtime (OpenShell gateway)
✓ Port 18789 already owned by healthy NemoClaw runtime (NemoClaw dashboard)
✓ NVIDIA GPU detected: 1 GPU(s), 124610 MB VRAM
✓ Memory OK: 124610 MB RAM + 16383 MB swap

[2/8] Starting OpenShell gateway
──────────────────────────────────────────────────
[reuse] Skipping gateway (running)
Reusing healthy NemoClaw gateway.

[3/8] Configuring inference (NIM)
──────────────────────────────────────────────────
Detected local inference option: Ollama

Inference options:
1) NVIDIA Endpoints
2) OpenAI
3) Other OpenAI-compatible endpoint
4) Anthropic
5) Other Anthropic-compatible endpoint
6) Google Gemini
7) Local Ollama (localhost:11434) — running (suggested)

Choose [1]: 6

Get your Google Gemini API key from: https://aistudio.google.com/app/apikey

Google Gemini API key: ***************************************

Key saved to ~/.nemoclaw/credentials.json (mode 600)

Google Gemini models:
1) gemini-3.1-pro-preview
2) gemini-3.1-flash-lite-preview
3) gemini-3-flash-preview
4) gemini-2.5-pro
5) gemini-2.5-flash
6) gemini-2.5-flash-lite
7) Other...

Choose model [5]: 3
Google Gemini endpoint validation failed.
Responses API with tool calling: HTTP 404 with no response body | Chat Completions API: HTTP 400: [{ "error": { "code": 400, "message": "API key expired. Please renew the API key.", "status": "INVALID_ARGUMENT", "details": [ { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "API_KEY
Please choose a provider/model again.

Please choose a provider/model again.

Detected local inference option: Ollama

Inference options:
1) NVIDIA Endpoints
2) OpenAI
3) Other OpenAI-compatible endpoint
4) Anthropic
5) Other Anthropic-compatible endpoint
6) Google Gemini
7) Local Ollama (localhost:11434) — running (suggested)

Choose [1]: 6

Google Gemini models:
1) gemini-3.1-pro-preview
2) gemini-3.1-flash-lite-preview
3) gemini-3-flash-preview
4) gemini-2.5-pro
5) gemini-2.5-flash
6) gemini-2.5-flash-lite
7) Other...

Choose model [5]: 3
Google Gemini endpoint validation failed.
Responses API with tool calling: HTTP 404 with no response body | Chat Completions API: HTTP 400: [{ "error": { "code": 400, "message": "API key expired. Please renew the API key.", "status": "INVALID_ARGUMENT", "details": [ { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "API_KEY
Please choose a provider/model again.

Please choose a provider/model again.

Detected local inference option: Ollama

Inference options:
1) NVIDIA Endpoints
2) OpenAI
3) Other OpenAI-compatible endpoint
4) Anthropic
5) Other Anthropic-compatible endpoint
6) Google Gemini
7) Local Ollama (localhost:11434) — running (suggested)

Choose [1]: 6

Google Gemini models:
1) gemini-3.1-pro-preview
2) gemini-3.1-flash-lite-preview
3) gemini-3-flash-preview
4) gemini-2.5-pro
5) gemini-2.5-flash
6) gemini-2.5-flash-lite
7) Other...

Choose model [5]: 3
Google Gemini endpoint validation failed.
Responses API with tool calling: HTTP 404 with no response body | Chat Completions API: HTTP 400: [{ "error": { "code": 400, "message": "API key expired. Please renew the API key.", "status": "INVALID_ARGUMENT", "details": [ { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "API_KEY
Please choose a provider/model again.

Please choose a provider/model again.

Detected local inference option: Ollama

Inference options:
1) NVIDIA Endpoints
2) OpenAI
3) Other OpenAI-compatible endpoint
4) Anthropic
5) Other Anthropic-compatible endpoint
6) Google Gemini
7) Local Ollama (localhost:11434) — running (suggested)

Choose [1]:

Reproduction Steps

install Nemoclaw: curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash
select Google Gemini
input an expired key
select "3) gemini-3-flash-preview" for the model

Environment

Device: Ubuntu 24.04
Node.js:v22.22.2
npm: 10.9.7
Docker: Docker version 29.1.3
OpenShell CLI: 0.0.26
NemoClaw: v0.0.14
OpenClaw 2026.3.11 (29dc654)

Debug Output

Logs

Checklist

  • I confirmed this bug is reproducible
  • I searched existing issues and this is not a duplicate

Metadata

Metadata

Assignees

Labels

NV QABugs found by the NVIDIA QA Teamarea: providersInference provider integrations and provider behaviorplatform: ubuntuAffects Ubuntu Linux environments

Type

No fields configured for Bug.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions