eonist

Based on my extensive research, I need to share an important finding: very few animals meet both criteria of living 75+ years AND sleeping long hours. Most animals with extreme longevity (75+ years) are either marine creatures with unique sleep patterns, or land animals that sleep very little. Here are the animals I found that genuinely meet both requirements:

Animals That Live 75+ Years AND Sleep Long Hours

1. Giant Tortoises (Galapagos, Aldabra, Seychelles)

• Lifespan: 100-175+ years[1][2][3][4]
• Daily Sleep: 12 hours[5][6][7]

Jonathan, a Seychelles giant tortoise living on St. Helena, is currently 192 years old and holds the record as the oldest known living land animal. These tortoises sleep approximately 12 hours per day, with juveniles sleeping even more (19-22 hours).[3][8][6][5]

eonist

is it possible to interact with GitHub release via cli. like GitHub CLI api library? or smth like that?

Yes—GitHub releases can be fully managed from the command line using GitHub CLI (gh), and for anything not covered by built-in commands you can call the GitHub REST API from the CLI as well.[^1_1][^1_3]

Using GitHub CLI for releases

GitHub CLI has a dedicated gh release command group for managing releases.[^1_3] Common operations include creating, listing, viewing, and deleting releases, plus uploading/deleting assets.[^1_15][^1_3]

eonist

Here's how the terminal-only flow would work, following patterns similar to git add -p and git rebase -i:[1][2]

Initial Invocation

$ git add .
$ omni --segment

Interactive Terminal Flow

eonist

Based on my research, when calling Apple Intelligence from Swift APIs using the Foundation Models framework, only on-device AFM (Apple Foundation Models) is available. Neither PCC (Private Cloud Compute) nor ChatGPT can be accessed programmatically through Apple's APIs.

Foundation Models Framework: On-Device Only

The Foundation Models framework provides developers with access exclusively to the on-device ~3B parameter language model. According to Apple's official developer forums, inference is entirely on-device and PCC is never used when calling the Foundation Models framework.[1][2][3]

Key characteristics:

• Zero cloud communication: No user data is transferred to PCC when using the Foundation Models API[3]
• Enhanced privacy: Apple doesn't log input prompts or outputs - only counts that your app called the model[3]
• Swift-native access: Available through a clean, type-safe Swift API with features like @Generable macros, guided generation, and tool calling[2][4][1]

eonist

The GitHub API limit of 5,000 requests is per hour, not per day. This rate limit applies to authenticated users making API requests with a personal access token, or through authorized GitHub Apps or OAuth apps.[1][2]

Rate Limits by Authentication Type

The specific limits vary based on how you authenticate:

• Unauthenticated requests: 60 requests per hour[5][9]
• Authenticated users (personal access tokens): 5,000 requests per hour[2][5]
• GitHub Enterprise Cloud organizations: 15,000 requests per hour for GitHub Apps or OAuth apps owned by or approved by the organization[2][5]
• GITHUB_TOKEN in GitHub Actions: 1,000 requests per hour per repository (15,000 per hour for Enterprise Cloud accounts)[8][2]

eonist

Based on the available documentation about Apple Intelligence, the statement that "AFM cannot vectorize data" appears to be partially true in a specific context.[1]

Apple Foundation Models (AFM) are primarily designed for text generation, summarization, extraction, and other language understanding tasks rather than generating embedding vectors for use in vector databases. The Foundation Models framework provides capabilities for generating text content, creating Swift data structures, and tool calling, but does not explicitly include functionality for generating text embeddings or vectorizing data for retrieval augmented generation (RAG) applications.[1]

Alternative Vectorization Options

For developers needing to vectorize data on Apple devices, separate solutions are available:

• NLEmbedding: Apple provides the NLEmbedding framework from Natural Language, which can generate embeddings entirely offline on-device, though the quality may not match cloud-based embedding models[2]
• **Third-party s

eonist

For a terminal binary executable app in Go, you do not need AppKit unless you're building GUI elements. AppKit is macOS's graphical user interface framework, which is unnecessary for command-line applications.[1][2][3]

Accessing AppKit from Go (if needed)

If you do need AppKit for some reason, Go can access it through bindings like DarwinKit (formerly MacDriver), which provides native Mac API access. DarwinKit offers bindings for 33 frameworks including AppKit, with over 2,353 classes and 23,822 methods. It works by wrapping Objective-C runtime calls in Go APIs, allowing you to write native macOS code without CGO in many cases.[2][4][1]

Apple Intelligence API Access

Apple Intelligence and the Foundation Models framework are currently primarily accessible through Swift. The Foundation Models framework provides on-device access to Apple's LLMs with as few as three lines of Swift code. There's no official Go API for Apple Intelligence yet.[5][6][7]

eonist

Based on your context, I can suggest the optimal solution for your situation. You discovered that shields.io provides JSON endpoints, which is the key insight here.[1][2]

Recommended Solution: Use Shields.io JSON API as Primary

Instead of parsing SVG, shields.io provides a .json endpoint that returns structured data. Here's the cleanest approach:[1]

async function getBadgeValue(owner, repo, metric) {
  try {
    const response = await fetch(`https://img.shields.io/github/${metric}/${owner}/${repo}/total.json`);

eonist

Based on the context from your attached files and the issue discussion, I can suggest specific edits to solve the rate limiting problem by using the Shields.io JSON API as the primary approach with GitHub API as fallback.

Recommended Solution

Use Shields.io's JSON endpoint (which provides instant cached results with no rate limit concerns) as your primary data source, with GitHub API as fallback. This approach:[1]

• Eliminates the SVG parsing hack that was initially considered[1]
• Provides faster response times than GitHub API[1]
• Avoids the rate limiting issues with high traffic[2]
• Requires no additional dependencies or cron jobs[1]

eonist

Potential Issues with High Traffic

Your JavaScript implementation makes client-side API calls to GitHub's API, which will likely cause problems with high traffic due to GitHub's strict rate limits.[^1_1]

Critical Rate Limit Constraints

GitHub enforces a 60 requests per hour limit for unauthenticated requests, shared per originating IP address. With your current implementation, every visitor triggers three API calls (repo stats and releases), meaning you'll hit the limit after just 20 visitors per hour from the same IP address or network.[^1_2][^1_1]