Patrick Plate
155d56e8e8
- Move bigmind/ -> mcp/bigmind/ - Move webscraper/ -> mcp/webscraper/ - Move mss-failsafe/ -> java/mss-failsafe/ - Move Wellmann-Shop/ -> java/wellmann-shop/ (normalize to kebab-case) - Add .roo/ IDE config files to tracking - Add plans/REPO_STRATEGY.md (monorepo strategy document) - Expand .gitignore: Java/Maven, Node/TS, coverage, uv.lock - Rewrite README.md as navigation index - Update .roo/mcp.json webscraper path to mcp/webscraper/
1.2 KiB
1.2 KiB
Code Mode Behavior — Roo Code
Before Writing Code
- Search Memory:
memory_search_facts("codebase [project]")+memory_search_chunks("similar code") - Form Hypothesis:
memory_add_hypothesis(session_id, "I predict X will fix Y with confidence 0.8") - Announce Focus:
memory_announce_focus(session_id, "Implementing Z in file.py", files=["file.py"], ide_hint="VS Code")
Coding Patterns
- Python: Use uv for dependencies, FastMCP for MCP servers, pytest for tests
- Java: Maven for Paisy projects, Spring Boot patterns
- Testing: Always write tests first, mock external calls
- Token Efficiency: Use
memory_log_token_savewhen reusing code from memory
After Code Changes
- Store Fact:
memory_store_fact("codebase", "New function X in file.py does Y") - Flag Important:
memory_flag_important(session_id, "Code review: implemented Z", role="assistant") - Resolve Hypothesis:
memory_resolve_hypothesis(hypothesis_id, "confirmed", "Worked as predicted")
Error Handling
- If code fails, form new hypothesis: "Bug might be in dependency version"
- Search:
memory_search_chunks("similar error") - Debug systematically, log token savings from targeted searches