Add portfolio documentation, demo script, and CI workflow

[Copilot]

Makes Arrowhead demonstrable without external LLM access by adding documentation, a deterministic demo, and CI smoke tests.

Changes

Documentation

• README.md: Added TL;DR, problem statement, Ollama/OpenAI quickstart, env vars config, expected output example
• docs/SCREENSHOT_README.md: Instructions for adding CLI screenshot

Demo

• demo/sample_note.md: Sample Obsidian journal with hashtags (#meeting, #work, etc.)
• demo/run_summary_demo.py: TextRank-based extractive summarizer via networkx—no external API calls

# Deterministic summarization for CI
summary = textrank_summarize(note_content, num_sentences=5)

# LLM integration points clearly marked:
# def summarize_with_llm(text, model="llama2"): ...
# def summarize_with_openai(text): ...

CI

• requirements.txt: numpy, nltk, networkx, pytest
• tests/smoke_test.py: 9 tests validating demo execution, output content, determinism
• .github/workflows/ci.yml: Python 3.12, installs deps, downloads NLTK punkt, runs smoke tests

---

⚠️ Do not merge without owner approval.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• https://api.github.com//advisories
  • Triggering command: /home/REDACTED/work/_temp/ghcca-node/node/bin/node /home/REDACTED/work/_temp/ghcca-node/node/bin/node --enable-source-maps /home/REDACTED/work/_temp/copilot-developer-action-main/dist/index.js (http block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

Goal: Prepare the arrowhead LLM-powered Obsidian summarizer to be portfolio-ready by adding a clear README with quickstart, an example smoke-test demo script that runs a small summarization locally using a simple heuristic or a local small model placeholder, and a CI workflow to run the smoke test. Create branch portfolio/docs-arrowhead and open PR to main. Do not merge.

Required changes:

1. README.md - TL;DR, problem summary (Obsidian automated summarizer), features, quickstart (how to configure local LLM or Ollama, env variables), example usage and expected outputs, license, and screenshot placeholder.
2. demo/sample_note.md - sample obsidian note content used by demo.
3. demo/run_summary_demo.py - lightweight script that reads sample_note.md and produces a summary using a simple heuristic (e.g., extract first 3 lines + simple sentence-rank using TextRank via networkx or sumy if available) to avoid external LLM calls in CI. Include clear comments where to plug LLM calls (OLLAMA/OpenAI) and how to configure API keys.
4. tests/smoke_test.py - runs demo/run_summary_demo.py and asserts non-empty output.
5. .github/workflows/ci.yml - installs python deps from requirements.txt and runs tests/smoke_test.py.
6. requirements.txt - minimal dependencies: "numpy", "nltk", "networkx", "sumy" (or alternatives) and instructions to download NLTK punkt in CI.

PR description: Adds documentation, a safe demo using deterministic heuristics for CI, and a smoke-test CI workflow to make arrowhead demonstrable without external LLM access. Do not merge without owner approval.

Notes: Keep CI deterministic and offline; include instructions for enabling real LLM usage locally in README.

This pull request was created as a result of the following prompt from Copilot chat.

Goal: Prepare the arrowhead LLM-powered Obsidian summarizer to be portfolio-ready by adding a clear README with quickstart, an example smoke-test demo script that runs a small summarization locally using a simple heuristic or a local small model placeholder, and a CI workflow to run the smoke test. Create branch portfolio/docs-arrowhead and open PR to main. Do not merge.

Required changes:

1. README.md - TL;DR, problem summary (Obsidian automated summarizer), features, quickstart (how to configure local LLM or Ollama, env variables), example usage and expected outputs, license, and screenshot placeholder.
2. demo/sample_note.md - sample obsidian note content used by demo.
3. demo/run_summary_demo.py - lightweight script that reads sample_note.md and produces a summary using a simple heuristic (e.g., extract first 3 lines + simple sentence-rank using TextRank via networkx or sumy if available) to avoid external LLM calls in CI. Include clear comments where to plug LLM calls (OLLAMA/OpenAI) and how to configure API keys.
4. tests/smoke_test.py - runs demo/run_summary_demo.py and asserts non-empty output.
5. .github/workflows/ci.yml - installs python deps from requirements.txt and runs tests/smoke_test.py.
6. requirements.txt - minimal dependencies: "numpy", "nltk", "networkx", "sumy" (or alternatives) and instructions to download NLTK punkt in CI.

PR description: Adds documentation, a safe demo using deterministic heuristics for CI, and a smoke-test CI workflow to make arrowhead demonstrable without external LLM access. Do not merge without owner approval.

Notes: Keep CI deterministic and offline; include instructions for enabling real LLM usage locally in README.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.