docs: Add LLM profiles documentation

[VascoSch92]

Summary

This PR adds documentation for the LLM profiles feature to the Language Model (LLM) Settings page.

Changes

Added a new "LLM Profiles" section that documents:

• Creating LLM Profiles: How profiles are automatically created when saving LLM configurations, and how to manually add profiles
• Managing LLM Profiles: How to edit, rename, delete, and set profiles as active from the settings page
• Switching Profiles During a Conversation: How to switch between different LLM models mid-conversation using the profile selector button in the chat input area
• How Profile Switching Works: Technical explanation of what happens when switching profiles (context preservation, metadata updates)
• Best Practices: Tips for naming profiles, creating task-specific configurations, and testing after switching

Why This Change

The LLM profiles feature allows users to:

• Save up to 10 different LLM configurations
• Switch between models during active conversations without losing context
• Use different models for different types of tasks (e.g., faster models for exploration, more powerful models for complex reasoning)

This powerful feature was not previously documented, making it difficult for users to discover and use effectively.

References

• Frontend implementation: frontend/src/components/features/settings/llm-profiles-manager.tsx
• Backend implementation: openhands/app_server/settings/llm_profiles.py
• Conversation profile switching: openhands/app_server/app_conversation/app_conversation_router.py

---

This PR was created by an AI agent (OpenHands) on behalf of the user.

@VascoSch92 can click here to continue refining the PR

[mintlify]

Preview deployment for your docs. Learn more about Mintlify Previews.

Project	Status	Preview	Updated (UTC)
all-hands-ai	🟢 Ready	View Preview	May 6, 2026, 2:08 PM

💡 Tip: Enable Workflows to automatically generate PRs for you.

[all-hands-bot]

🟢 Good taste - Well-structured documentation that solves a real problem.

This PR documents the previously undocumented LLM profiles feature with clear, actionable information. The documentation:

• Follows existing Mintlify patterns and uses appropriate components (, )
• Provides complete coverage: creation, management, switching, slash commands, and best practices
• Has been verified against source code by previous reviews
• Maintains logical flow and appropriate detail level

[RISK ASSESSMENT]

• [Overall PR] ⚠️ Risk Assessment: 🟢 LOW

Documentation-only change with no code modifications, breaking changes, or security implications.

VERDICT:
✅ Worth merging - Addresses real user need with quality documentation.

KEY INSIGHT:
Documents a powerful feature (mid-conversation model switching) that enables users to optimize cost and performance by leveraging different models for different tasks.