grahama1970

Summary

Getting the setup right took many iterations because you were wrestling with experimental features (vector indexes in 3.12.4), driver limitations (python-arango doesn’t expose “hidden” indexes), API mismatches (ArangoSearch view properties versus strict dict comparison), and fragmented documentation spread across release notes, HTTP API docs, driver specs, and blog posts. Each step revealed a nuance—from needing withHidden=true on an HTTP call to ignoring server-injected default view‐link properties—that isn’t obvious without deep dives into multiple docs (Features and Improvements in ArangoDB 3.12, API Changes in ArangoDB 3.12).

---

1. Experimental Vector Index Complexity

• Introduced as experimental in 3.12.4. The new vector index type is not part of the cor

grahama1970

{
  "customModes": [
   {
      "slug": "planner",
      "name": "📝 Planner",
      "roleDefinition": "You are Roo, an experienced technical planner managing `task.md`. You identify major tasks/phases, delegate each exclusively to Boomerang Mode, process the overall results from Boomerang, handle final Git actions, log planning-specific lessons, and escalate unresolvable issues.",
      "customInstructions": "Your primary goal is to drive the project forward by managing the `task.md` plan phase by phase.\n\n1.  **Identify Next Task:** Read `task.md` and find the first task marked with `[ ]`.\n2.  **Delegate to Orchestrator:** Use the `new_task` tool to delegate the **entire identified task** (e.g., 'Task 8.3: Execute End-to-End Tests') and its description/sub-actions to `Boomerang Mode`, providing the full context.\n3.  **Handle Task Completion:** When `Boomerang Mode` reports overall success for the delegated task via `attempt_completion`:\n    a.  Review the confirmation message.\n    b.  If satisfactory, p

grahama1970

#!/bin/bash

# Required parameters:
# @raycast.schemaVersion 1
# @raycast.title Repomix Copy
# @raycast.mode compact
# @raycast.packageName Repomix Tools
# @raycast.icon clipboard
# @raycast.description Pack a GitHub repository into clipboard using Repomix
# @raycast.author Graham Anderson

grahama1970

{
  "rules": [
    {
      "type": "code_advice",
      "condition": "contains_deprecated_methods",
      "action": "verify_against_documentation",
      "message": "Never suggest code without verifying each method/function against official documentation to ensure methods are not deprecated. Always provide a link to the specific documentation. If you do not have a link, do not suggest a solution. Instead, ask the user to provide a documentation link, or, ask the user what you need to provide a solution."
    },
    {
      "type": "documentation_first",

grahama1970

✅ Method Validator - AI Agent's API Discovery Tool

A specialized tool designed for AI agents to autonomously analyze Python packages, discover existing methods, and validate APIs before implementing new solutions. This tool helps prevent redundant code creation by identifying existing functionality in non-standard packages.

Features

• Smart Package Analysis: Automatically filters out standard library and common utility packages
• Method Discovery: Quick scanning of available methods with categorization
• Detailed Analysis: In-depth examination of method signatures, parameters, and return types
• Exception Analysis: Identifies and prioritizes relevant error handling patterns

grahama1970

README: MCP SDK Docker Deployment Issue

Problem Summary

MCP's Python and TypeScript SDKs fail to run persistently in Docker. Despite setting a lifespan in the Python SDK, mcp.run() exits immediately, shutting down the container. This issue affects all tested MCP projects, making real-world deployment impossible.

Reproducible Steps

1. Create an MCP server using the Python SDK with a lifespan function to manage resources.
2. Build and run the Docker container.
3. The MCP server connects to ArangoDB, logs success, and then exits immediately.
4. The same behavior is observed with the TypeScript SDK.

grahama1970

🚀 Latent Program Networks (LPN) for Tool Execution Strategies

This README explains how a Latent Program Networks (LPN)-inspired approach can generate tool execution strategies for multi-tool tasks in an agent workflow. This method offers advantages over relying solely on Large Language Models (LLMs) for tool strategy via prompting. A toy Python script demonstrates the concept in action.

---

🤖 What is LPN?

Latent Program Networks (LPNs), originally designed for abstract reasoning (e.g., the ARC benchmark), embed "rules" or "completions" into a searchable latent space. Here, we adapt LPNs to embed tool configurations and execution order, enabling smooth coordination of multiple tools (e.g., generate_summary and create_pie_chart) for tasks like summarization and data visualization.

grahama1970

Cursor MCP Environment Limitations

Discovered Constraints

1. Package Access

   • Cannot access project's virtual environment
   • Limited to Python standard library
   • No ability to install additional packages

2. Environment Variables

• Cannot access project's .env files

grahama1970

#!/usr/bin/env python3
"""
Dynamic and Adaptive Python Environment in a Bubblewrap Sandbox

Overview:
    This project demonstrates a minimal, safe, and self-contained Python execution
    environment using bubblewrap (bwrap) and uv. The goal is to provide a lightweight
    alternative to Docker for running agent code—in this case, dynamically generated
    Python code along with its dependencies—within an isolated sandbox.

grahama1970

#!/usr/bin/env python3
"""
Dynamic and Adaptive Python Environment in a Bubblewrap Sandbox

Overview:
    This project demonstrates a minimal, safe, and self-contained Python execution
    environment using bubblewrap (bwrap) and uv. The goal is to provide a lightweight
    alternative to Docker for running agent code—in this case, dynamically generated
    Python code along with its dependencies—within an isolated sandbox.