Dominik Oswald d-oit

Log LLM API Post from Roo Code

1. Capturing with Postman’s Built-In Proxy

Postman Desktop includes a simple “HTTP proxy” you can enable in seconds.

Open Settings → Proxy
Under Capture traffic click Start Proxy Session
Default port is 5559 (you can edit it with the little pencil icon)
Configure your client or system to use http://localhost:5559

Optimized Image Creation Prompt: "Visualize a surreal, hyper-detained universe where symbolic mathematics defines physical laws. Design an ethereal landscape using these guidelines:

Core Visual Metaphors:

Fractal Time: Depict time as interlocking geometric lattices (e.g., recursive tetrahedrons or Penrose tiling) where past/present/future coexist.
Topological Gravity: Show gravity as warped, glowing manifolds (think Klein bottle-like distortions) pulling celestial bodies into Möbius strip orbits.

Symbolic Architecture:

Render primal symbols (e.g., Δ, ⨀) as glowing hieroglyphs etched into floating monoliths or encoded in particle trails.
Use hyperdimensional geometry: Merge 4D Calabi-Yau shapes with adversarial neural network patterns (modular, tessellated grids).

When developing a prompt-only coding web app, several common challenges arise:

Selecting an appropriate language model: Choosing a powerful and accurate model capable of understanding and generating code is crucial[1][2].
Prompt engineering: Crafting effective prompts that yield accurate code responses is challenging and requires ongoing optimization[5].
Ensuring code quality and security: Generated code may contain errors or security vulnerabilities, necessitating robust validation and review processes[2][3].
Managing performance and scalability: Handling potentially high volumes of requests and ensuring quick response times can be technically demanding[2][3].

Here’s the reusable initial prompt with placeholders for [Country], [Year], [Total Seats], and customizable inputs. It includes explicit data references, mathematical notation, and modular coalition logic:

Role

You are an analyst for the [Germany] [2025] election with [630] seats. Prioritize current polling, economic context, and party red lines.

Input Requirements

Winget Not Recognized After Windows Update

If you're experiencing issues with Winget not being recognized after a Windows update, you can try reinstalling it using the following PowerShell script from PSGallery.

Reinstall Winget using PowerShell

Open PowerShell as Administrator.
Run the following commands:

	{
	"customModes": [
	{
	"slug": "roo-diagnose",
	"name": "Roo Issue Diagnoser",
	"roleDefinition": "You are Roo, a specialized diagnostic assistant. Your primary function is to guide users through a structured, wizard-like process to collect detailed information about issues encountered with Roo or its extensions. You will systematically gather information using scripts where possible, ask targeted follow-up questions, and use a scoring system to analyze if the collected information is sufficient to provide an answer or fix.",
	"whenToUse": "Select this mode when you encounter an issue with Roo tools or extensions and need to generate a detailed diagnostic report. This mode is ideal for systematically collecting all relevant information to help troubleshoot and resolve problems through a guided, wizard-like process.",
	"groups": [
	"read",
	"command"

	#!/bin/bash

	# AI Git Commit Helper
	# A script to generate commit messages using Mistral's Codestral API

	# Colors for output
	GREEN='\033[0;32m'
	RED='\033[0;31m'
	YELLOW='\033[1;33m'
	NC='\033[0m' # No Color

	# Role Mappings Configuration

	# File Pattern Based Mappings
	file_patterns:
	- pattern: "\.(spec\|test)\\.(ts\|tsx\|js\|jsx)$"
	role: playwright
	description: "End-to-end test files"
	priority: 1

	- pattern: "(__tests__/.\|__mocks__/.\|\\.test\\.(ts\|tsx\|js\|jsx)$)"

	import os
	from dotenv import load_dotenv
	from imagepig import ImagePig

	# Load environment variables from .env file
	load_dotenv()

	# Get the API key from environment variables
	API_KEY = os.getenv('IMAGEPIG_API_KEY')

	{
	"messages": [
	{
	"role": "system",
	"content": "You are an AI programming assistant.\nWhen asked for your name, you must respond with \"GitHub Copilot\".\nFollow the user's requirements carefully & to the letter.\nFollow Microsoft content policies.\nAvoid content that violates copyrights.\nIf you are asked to generate content that is harmful, hateful, racist, sexist, lewd, or violent, only respond with \"Sorry, I can't assist with that.\"\nKeep your answers short and impersonal.\nYou can answer general programming questions and perform the following tasks: \n* Ask a question about the files in your current workspace\n* Explain how the code in your active editor works\n* Make changes to existing code\n* Review the selected code in your active editor\n* Generate unit tests for the selected code\n* Propose a fix for the problems in the selected code\n* Scaffold code for a new file or project in a workspace\n* Create a new Jupyter Notebook\n* Ask questions about VS Code\n* Gene