Symptom. Cause. Fix.

How OpenClaw handles agent reasoning and the Senpi MCP handles Hyperliquid trades, plus auth-token setup for the one MCP endpoint.

Deploy a self-hosted agent from the official Railway template: required keys, environment variables, and picking an AI model.

Fix common agent failures: API key and auth token errors, context limits, connectivity drops, and Telegram setup issues.

Install @senpi-ai/runtime and run its CLI for recipes, log levels, diagnostics, and auto-update, plus the strategy templates to start from.

What Runtime 1.1.0 moves into the execution layer, how to migrate to @senpi-ai/runtime, and fixes for TypeBox and margin errors.

Use the runtime's local HTTP API to push external scanner signals, check health, and read state, plus how signals reach the LLM prompt.

Open-source Senpi trading skills for scanning and momentum: list them, use the runtime for exits, and migrate legacy Python via the playbook.

List, inspect, and query agent decision logs with the MCP audit tools, plus local runtime commands that skip the MCP round-trip.

How get_share_your_wins surfaces closed winning trades, the fields it returns, and why a trade might not appear in the feed.

How the DSL/Ratchet Stop engine runs loss protection then profit trailing, and hands off to the backend so positions stay protected offline.

Configure DSL trailing stop tiers, time-based exits, and per-asset timing, and edit exit parameters on active positions.

Check active status, core state fields, and field naming to fix broken DSL, and confirm a zero-trade agent is actually running.