Implement Vertex AI support in core

[jeffmaury]

Is your feature request related to a problem? Please describe

This is required at least for internal usage of Claude

Describe the solution you'd like

Update the inference provider configuration with the following information:

• _type: google-vertex-ai
• _flag: __from_gcloud_adc
• GOOGLE_APPLICATION_CREDENTIALS (password): path of credentials files
• GOOGLE_VERTEX_PROJECT (string): the projet id
• GOOGLE_VERTEX_LOCATION: the region

When such a configuration is received, the core will:

• create the provider by setting the GOOGLE_APPLICATION_CREDENTIALS (as before)
• when calling the OpenShell CLI, remove the --credentials flag but adds the newone
• the other properties will be added as environment variables so that they can be processed by the agent (eg Claude to adjust the name)

Describe alternatives you've considered

No response

Additional context

No response

[coderabbitai]

🔗 Related PRs

#1537 - feat(guided-setup): add Claude on Vertex AI agent type [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!