[Feature] /condense Slash Command for Memory Condensation

[VascoSch92]

Summary

Add a /condense slash command to manually trigger conversation history condensation.

Feature Details (from OpenHands-CLI)

Slash Command

• /condense - Condense conversation history to reduce token usage

Condensation

• Summarize older messages to reduce context size
• Preserve important information and decisions
• Use LLM to generate summary (configurable condenser LLM)
• Triggered manually or automatically at threshold

Settings Integration

• Memory condensation enabled/disabled toggle
• Condenser LLM configuration (can be different from main LLM)
• In settings modal under "Agent Settings" tab

Benefits

• Reduce token usage for long conversations
• Keep conversations within context limits
• Preserve conversation continuity

Current State

Rho processes Condensation events from the server but has no way to manually trigger condensation.

Reference

See OpenHands-CLI:

• openhands_cli/tui/widgets/input_area.py (_command_condense)
• SDK: LLMSummarizingCondenser

---

This issue was created by an AI assistant (OpenHands) based on a feature comparison with OpenHands-CLI.

[VascoSch92]

📋 Tracked in: #18 (Feature Parity with OpenHands-CLI)