[FEATURE] Offline Mode Requires Manual Export of `CORTEX_PROVIDER=ollama`

[Suyashd999]

What happened?

Description

When using offline mode, users currently must manually export

CORTEX_PROVIDER=ollama

However, this isn’t handled automatically during the Cortex wizard setup. Users selecting offline mode should have this environment variable exported (or set in their config) automatically.

Expected Behavior

When a user selects offline mode in the wizard:

The wizard should automatically configure CORTEX_PROVIDER=ollama

Current Behavior

Users must manually run:

export CORTEX_PROVIDER=ollama

Proposed Solution

During the offline mode selection step in the wizard:

Automatically set CORTEX_PROVIDER=ollama when user selects offline

[coderabbitai]

📝 CodeRabbit Plan Mode

Generate an implementation plan and prompts that you can use with your favorite coding agent.

• Create Plan

Examples

• Example 1
• Example 2

---

🔗 Similar Issues

Possible Duplicates

• cortex config: Interactive Setup Wizard #247

Related Issues

• [UX] Offline mode with cached suggestions #261
• [FEATURE] Ollama Integration - Local LLM Support #357
• [BUG] Cortex wizard stops even when API key is already set in ENV #355
• Bug: Cortex attempts Ollama connection when not configured #316
• Bug: API keys in .env file not loaded reliably at runtime #317

👤 Suggested Assignees

• mikejmorgan-ai
• Suyashd999
• jaysurse

---

🧪 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!

[dominitas]

Hi @Suyashd999 ,

I noticed this issue. We at Roxonn help teams and developers pay for completed GitHub tasks without hiring full-time contractors.

If this is useful, I’d be happy to show how it works.

– Domantas