Bug: Cortex attempts Ollama connection when not configured

[mikejmorgan-ai]

Description

Cortex attempts to connect to Ollama at http://localhost:11434/ even when no local LLM is installed or configured.

Expected Behavior

• If Ollama is not configured, Cortex should skip the connection attempt
• Should fail gracefully with a clear message, not an unexpected error
• Should proceed directly to configured cloud providers (OpenAI/Anthropic)

Actual Behavior

• Cortex tries localhost:11434 regardless of configuration
• Causes confusion when users have cloud API keys configured but no local LLM

Steps to Reproduce

1. Configure OpenAI or Anthropic API key
2. Do NOT install Ollama
3. Run any cortex command
4. Observe connection attempt to localhost:11434

Suggested Fix

Check for Ollama configuration before attempting connection. If not explicitly enabled, skip local LLM detection.

Environment

• Cortex v0.1.0
• Ubuntu (Effiti team testing)

Reporter

Effiti team via Discord

[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

Related Issues

• [BUG] Logo Path error in Readme.md #308

👤 Suggested Assignees

• Sahilbhatane

---

🧪 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 or schedule a call!

[Zafeeruddin]

Can I work on this?

[Kesavaraja67]

Can i work on this
/assign