Authenticate with Google Cloud APIs and Vertex AI inside OpenShell sandboxes.
The google-cloud provider gives sandboxes native GCP credentials so
any Google Cloud SDK works out of the box — Cloud Storage, BigQuery, Drive,
Maps, Discovery Engine, or any other GCP API. A GCE metadata server emulator
on loopback provides credential placeholders that the
sandbox proxy resolves to real tokens at request time. The sandbox process
never holds a real GCP credential.
Quick Start
Section titled “Quick Start”Import the google-cloud profile first; a gateway serves only the profiles you
imported:
openshell profile import --url https://raw.githubusercontent.com/NVIDIA/OpenShell/main/providers/google-cloud.yaml --globalIf you already have gcloud configured with Application Default Credentials,
create a provider with automatic credential refresh in one command:
openshell provider create \ --name my-gcp \ --type google-cloud \ --from-gcloud-adc \ --config project_id="$(gcloud config get-value project)" \ --config region=global--from-gcloud-adc reads your ADC file, configures OAuth2 refresh on the
gateway, and mints the first access token before the command returns. The
gateway rotates the token automatically — no manual refresh needed.
Authentication Flows
Section titled “Authentication Flows”Two credential flows are supported. Choose based on your environment.
Application Default Credentials (gcloud ADC)
Section titled “Application Default Credentials (gcloud ADC)”Use credentials from gcloud auth application-default login. The gateway
exchanges the refresh token for short-lived access tokens automatically.
openshell provider create \ --name my-gcp \ --type google-cloud \ --config project_id=my-project \ --config region=us-central1 \ --credential GCP_ADC_ACCESS_TOKEN=placeholderConfigure credential refresh with the ADC JSON fields:
openshell provider refresh configure my-gcp \ --credential-key GCP_ADC_ACCESS_TOKEN \ --strategy oauth2-refresh-token \ --material client_id=YOUR_CLIENT_ID \ --material client_secret=YOUR_CLIENT_SECRET \ --material refresh_token=YOUR_REFRESH_TOKEN \ --secret-material-key client_secret \ --secret-material-key refresh_tokenFind these values in your ADC file at
~/.config/gcloud/application_default_credentials.json.
Trigger the first token mint:
openshell provider refresh rotate my-gcp \ --credential-key GCP_ADC_ACCESS_TOKENService Account Key
Section titled “Service Account Key”Use a GCP service account JSON key file. The gateway signs JWTs and
exchanges them for access tokens using the google-service-account-jwt
strategy.
openshell provider create \ --name my-gcp \ --type google-cloud \ --config project_id=my-project \ --config region=us-central1 \ --credential GCP_SA_ACCESS_TOKEN=placeholderopenshell provider refresh configure my-gcp \ --credential-key GCP_SA_ACCESS_TOKEN \ --strategy google-service-account-jwt \ --material client_email=sa@my-project.iam.gserviceaccount.com \ --material private_key="$(jq -r .private_key /path/to/sa-key.json)" \ --secret-material-key private_keyopenshell provider refresh rotate my-gcp \ --credential-key GCP_SA_ACCESS_TOKENConfiguration Keys
Section titled “Configuration Keys”Set these with --config key=value during provider creation:
| Key | Description | Example |
|---|---|---|
project_id |
GCP project ID | my-project-123 |
region |
GCP region | us-central1 |
service_account_email |
Optional SA email for metadata endpoint | sa@proj.iam.gserviceaccount.com |
When service_account_email is omitted or empty, recursive metadata account
discovery returns the default identifier so SDKs can refresh repeatedly.
How It Works
Section titled “How It Works”When a sandbox starts with the google-cloud provider attached:
- The gateway mints a fresh GCP access token and stores it in the sandbox proxy’s credential resolver.
- The sandbox relays HTTP requests to the reserved
127.0.0.1:8174metadata endpoint over its authenticated supervisor connection. The supervisor emulates the GCE instance metadata API and serves credential placeholders to GCP SDKs. Real access tokens remain in the supervisor. - When the SDK makes an API call, it sends the placeholder in the
Authorizationheader. The sandbox proxy TLS-terminates the outbound connection, resolves the placeholder to the real token, and forwards the request to GCP. - When the token approaches expiry, the gateway refreshes it. The proxy’s resolver is updated atomically — subsequent API calls use the new token automatically.
Configuration values (project_id, region, service_account_email)
are visible in plain text inside the sandbox — they appear as
environment variables and are served by the metadata endpoint. These are
non-secret identifiers, not credentials. Access tokens are never exposed;
only placeholders reach the sandbox process.
The emulator supports Linux sandboxes using the Docker, Podman, Kubernetes,
and VM runtimes. Windows/MXC does not provide this metadata endpoint. SDKs must
honor the injected metadata discovery variables below. Requests require the
Metadata-Flavor: Google header; requests with X-Forwarded-For are rejected.
The endpoint serves project ID, service-account email, scopes, and token
placeholders, including recursive service-account discovery.
OpenShell reserves 127.0.0.1:8174 for this service. Connections to this
address reach the emulator even if a workload binds its own listener there.
Requests to the host’s cloud metadata service remain blocked; the emulator does not forward requests to
metadata.google.internal or 169.254.169.254.
Injected Environment Variables
Section titled “Injected Environment Variables”The provider automatically injects these into the sandbox. Non-secret vars are resolved to real values at process spawn time; token vars stay as placeholders for proxy-time resolution.
| Variable | Value | Purpose |
|---|---|---|
GCE_METADATA_HOST |
127.0.0.1:8174 |
GCP SDK metadata discovery (supervisor emulator) |
GCE_METADATA_IP |
127.0.0.1:8174 |
Python google-auth ping detection |
METADATA_SERVER_DETECTION |
assume-present |
Node.js gcp-metadata skip detection |
GCP_PROJECT_ID |
from project_id config |
GCP SDK project |
GOOGLE_CLOUD_PROJECT |
from project_id config |
Alternative project var |
CLOUD_ML_REGION |
from region config |
GCP region |
GCP_LOCATION |
from region config |
Alternative region var |
Using with GCP APIs
Section titled “Using with GCP APIs”The metadata emulator serves tokens with the cloud-platform OAuth2 scope,
which grants access to any GCP API the underlying service account has IAM
permissions for. Add the target API hosts to your sandbox network policy:
Attach my-gcp to the sandbox first. Because the google-cloud profile has no
endpoints, each API endpoint must bind to that provider instance. Without the
binding, OpenShell withholds its access token from the sandbox.
The metadata token endpoint returns HTTP 503 when no bound access token is
available or the token has expired. Attach the provider, add a credential
binding, and check openshell provider refresh status my-gcp before testing
token discovery.
network_policies: gcp_apis: name: gcp-apis endpoints: - host: "*.googleapis.com" port: 443 protocol: rest access: read-write enforcement: enforce credential_binding: provider: my-gcp binaries: - { path: /usr/bin/curl } - { path: /usr/bin/node } - { path: "/sandbox/.uv/python/**" } - { path: "/sandbox/.venv/**" }For a running sandbox, export its base policy. Remove the metadata header above
the --- line, add the endpoint and binaries shown above, then apply the file:
openshell policy get my-sandbox --base > sandbox-policy.yaml# Edit sandbox-policy.yaml to add the gcp_apis rule shown above.openshell policy set my-sandbox --policy sandbox-policy.yaml --waitNetwork Policy
Section titled “Network Policy”The google-cloud provider type does not include any network policy
endpoints by default. You must add endpoint rules to your sandbox policy
for each GCP API the sandbox needs to reach. See “Using with GCP APIs”
above for an example.
Vertex AI
Section titled “Vertex AI”The google-vertex-ai provider gives selected sandboxes access to native
Google Vertex AI endpoints. OpenShell keeps refresh bootstrap material at the
gateway, rotates short-lived access tokens, and resolves token placeholders
only at endpoints authorized by the provider profile.
OpenShell does not choose a model or transform a request. The workload uses the native Vertex endpoint and request format for its selected model.
Prerequisites
Section titled “Prerequisites”- A GCP project with the Vertex AI API enabled.
- A service account with the Vertex AI User role and a downloaded JSON key for production, or gcloud Application Default Credentials for local development.
- Access to the selected model in the intended Vertex region.
Create a Vertex AI Provider
Section titled “Create a Vertex AI Provider”Import the google-vertex-ai profile first:
openshell profile import --url https://raw.githubusercontent.com/NVIDIA/OpenShell/main/providers/google-vertex-ai.yaml --globalService Account Key
Section titled “Service Account Key”Create the provider with the JSON key as gateway-only bootstrap material:
openshell provider create \ --name vertex-prod \ --type google-vertex-ai \ --credential GOOGLE_SERVICE_ACCOUNT_KEY="$(cat /path/to/key.json)" \ --config VERTEX_AI_PROJECT_ID=my-gcp-project \ --config VERTEX_AI_REGION=us-central1Configure gateway-managed refresh:
openshell provider refresh configure vertex-prod \ --credential-key GOOGLE_VERTEX_AI_SERVICE_ACCOUNT_TOKEN \ --strategy google-service-account-jwt \ --material client_email="sa@my-gcp-project.iam.gserviceaccount.com" \ --material private_key="$(jq -r .private_key /path/to/key.json)" \ --secret-material-key private_keyThe private key remains in the gateway credential store. Sandboxes receive only an opaque placeholder for the short-lived access token.
gcloud Application Default Credentials
Section titled “gcloud Application Default Credentials”For local development:
gcloud auth application-default login
openshell provider create \ --name vertex-local \ --type google-vertex-ai \ --from-gcloud-adc \ --config VERTEX_AI_PROJECT_ID=my-gcp-project \ --config VERTEX_AI_REGION=us-central1--from-gcloud-adc reads authorized-user ADC, configures an OAuth2 refresh
grant at the gateway, and immediately mints GOOGLE_VERTEX_AI_TOKEN. The ADC
file and refresh token do not enter the sandbox.
Vertex AI Configuration Keys
Section titled “Vertex AI Configuration Keys”| Key | Required | Default | Description |
|---|---|---|---|
VERTEX_AI_PROJECT_ID |
Yes | — | GCP project ID exposed as non-secret workload configuration. |
VERTEX_AI_REGION |
No | us-central1 |
Vertex location exposed as non-secret workload configuration. |
When the provider is attached, OpenShell also projects standard project and
location aliases such as GOOGLE_CLOUD_PROJECT, ANTHROPIC_VERTEX_PROJECT_ID,
CLOUD_ML_REGION, and VERTEX_LOCATION.
Attach the Vertex AI Provider
Section titled “Attach the Vertex AI Provider”Attach it while creating a sandbox:
openshell sandbox create \ --from registry.example.com/team/agent:1.0 \ --name vertex-agent \ --provider vertex-localOr attach it to an existing sandbox:
openshell sandbox provider attach vertex-agent vertex-localLaunch a new process after runtime attachment so it receives the provider environment. Existing processes do not gain newly attached environment variables.
Call the Native Vertex API
Section titled “Call the Native Vertex API”Claude models use Vertex’s publisher-model endpoint. Run a request from a new sandbox process:
openshell sandbox exec vertex-agent -- sh -lc ' token=${GOOGLE_VERTEX_AI_SERVICE_ACCOUNT_TOKEN:-$GOOGLE_VERTEX_AI_TOKEN} curl -X POST \ -H "Authorization: Bearer $token" \ -H "Content-Type: application/json" \ -d '\''{ "anthropic_version":"vertex-2023-10-16", "max_tokens":1024, "messages":[{"role":"user","content":"Hello"}] }'\'' \ "https://${CLOUD_ML_REGION}-aiplatform.googleapis.com/v1/projects/${GOOGLE_CLOUD_PROJECT}/locations/${CLOUD_ML_REGION}/publishers/anthropic/models/claude-sonnet-4-6:rawPredict"'Use the model ID and location supported by your GCP project. For global, us,
or eu, use the corresponding Google-documented hostname instead of the
regional <location>-aiplatform.googleapis.com form.
Gemini and third-party models use their documented native or OpenAI-compatible Vertex endpoints. Configure the model, URL, streaming mode, and timeout in the client. OpenShell does not rewrite them.
Verify and Troubleshoot Vertex AI
Section titled “Verify and Troubleshoot Vertex AI”Inspect the attachment and effective policy:
openshell sandbox provider list vertex-agentopenshell policy get vertex-agent --fullopenshell provider refresh status vertex-localCommon failures:
- A missing token variable usually means the process started before provider attachment. Launch a new process.
connection not allowed by policymeans the provider endpoint or caller binary is absent from the effective policy. A gateway global policy override suppresses provider-derived entries.credential_endpoint_mismatchmeans the request destination is outside the provider profile’s endpoint binding.- A Vertex 400 or 404 usually means the model, location, publisher path, or request body does not match the native API.
- A Vertex 401 or 403 can indicate an expired refresh grant or missing GCP IAM
permission. Check
provider refresh statusand the Vertex AI User role.
Provider creation does not verify model access. The native request is the end-to-end check.
Migrate an Existing Vertex Route
Section titled “Migrate an Existing Vertex Route”An earlier managed route stored the provider and model separately and rewrote requests for the workload. After upgrading, the provider and its refresh state remain, but the route does not.
- Attach the preserved Vertex provider to each intended sandbox.
- Launch new workload processes.
- Move the route’s model and timeout into the client configuration.
- Change the client to the native Vertex endpoint and request format.
- Verify one non-streaming and one streaming native request before production rollout.
Do not attach the provider to every sandbox automatically. The old route was workspace-global; the replacement intentionally grants access per sandbox.
We are a Cloud Native Computing Foundation sandbox project.
Copyright OpenShell a Series of LF Projects, LLC
For website terms of use, trademark policy and other project policies please see lfprojects.org/policies/.