v1.0.1

Summary

Compatibility release: migrated Groq cloud models to openai/gpt-oss-20b and openai/gpt-oss-120b before llama-3.1-8b-instant and llama-3.3-70b-versatile are decommissioned (2026-08-16). The public demo uses production Groq models only (preview/evaluation models excluded). Simulated mode — labeled mock fallback when the API is unavailable — is unchanged from v1.0.0.

Live demo: https://ethical-decision-simulator.streamlit.app/

---

What's new

Groq model migration

• Removed deprecated llama-3.1-8b-instant and llama-3.3-70b-versatile from the model picker
• Cloud lineup: openai/gpt-oss-20b (fast baseline, Explore default) and openai/gpt-oss-120b (high-reasoning tier)
• Default Compare selection: GPT-OSS 20B + GPT-OSS 120B (same two-model audit pattern as before)
• Groq’s recommended 1:1 replacements per model deprecations

Production models only

• Excluded qwen/qwen3.6-27b — Groq preview models are for evaluation, may be discontinued without notice, and are not suitable for the public Streamlit Cloud demo
• README Data Sources notes that preview models are intentionally omitted

UI & docs

• Compare model multiselect caps at available models (max_selections=len(models) — two on Groq cloud)
• Glossary and architecture docs updated for the two-model cloud lineup
• Tech stack, attribution table, and version history refreshed

Tests

• Offline tests updated for new model display names and API IDs (GPT-OSS 20B, GPT-OSS 120B)
• 46 offline tests pass in CI (no API key required)
• Live API smoke tests exercise GPT-OSS 20B single-run and 20B + 120B parallel compare when GROQ_API_KEY is set

---

Quick start

Unchanged from v1.0.0 — see README Quick Start.

Local (Groq):

git clone https://github.com/rvong65/ethical-decision-simulator.git
cd ethical-decision-simulator
python -m venv .venv
source .venv/bin/activate   # Windows: .\.venv\Scripts\activate
pip install -r requirements.txt
cp .streamlit/secrets.toml.example .streamlit/secrets.toml   # add GROQ_API_KEY
streamlit run app.py

Local Ollama (no Groq):

export LLM_PROVIDER=ollama   # Windows: $env:LLM_PROVIDER = "ollama"
streamlit run app.py

Docker:

git clone https://github.com/rvong65/ethical-decision-simulator.git
cd ethical-decision-simulator
docker compose up --build
# open http://localhost:8501

Try it: Home → Explore or Compare → pick a curated scenario → Run analysis or Run comparison.

---

Full changelog

See CHANGELOG.md#101---2026-07-13

v1.0.0

Summary

Initial public MVP: ethical decision simulator for auditing how LLMs reason through moral dilemmas — Explore single-model review, Compare multi-model audit with semantic agreement metrics, ethical lens stress tests, Compare-only JSON export, crisis guardrails, Streamlit UI, and GitHub Actions CI.

Live demo: https://ethical-decision-simulator.streamlit.app/

---

Features

Ethics pipeline

• Structured JSON verdicts (Pydantic) — decision, reasoning steps, creative alternatives, detected frameworks, confidence
• Explore — single-model walkthrough with ethical lens selection (neutral, utilitarian, deontological, care ethics); on-screen results only
• Compare — up to 3 models side-by-side with semantic decision agreement (primary) and lexical agreement (secondary)
• Framework stress test — batch run all four lenses per model to probe framework adherence
• Consistency test — rephrase variants on curated scenarios to measure framing sensitivity
• Creative alternatives first — models list escape hatches before forced tradeoff analysis
• Lens-adherence mismatch warnings when forced lens ≠ detected framework
• Compare JSON export (ethical_comparison_*.json) — full metrics, verdicts, consistency data, and run metadata

Safety & responsible AI

• Crisis keyword detector with 988 / Crisis Text Line disclaimer banner
• Simulated mode — labeled mock fallback on rate limits, auth failure, or missing API key (never silent)
• Educational framing — not moral guidance, legal advice, therapy, or crisis service
• Session-only state — no project database; Compare export is user-initiated download only
• Privacy & data expander on Home + README data-flow table

Streamlit app

• Custom indigo sidebar theme; Home / Explore / Compare navigation
• 12 curated moral dilemmas plus custom dilemma input
• In-app glossary — ethical lenses, Compare modes, metric definitions
• Provider status badge (live vs simulated); friendly LLM errors (429, auth, timeout)
• Hybrid LLM — Groq (Llama 3.3 70B, GPT-OSS 20B, Llama 3.1 8B) default; optional Ollama (gemma3:4b) for local inference

Quality & docs

• 46 offline pytest tests + 3 optional Groq API smoke tests
• GitHub Actions CI — offline tests + Docker build/health on every push/PR (no API keys required); optional API smoke on main
• README with architecture overview, quick start, privacy, and safety considerations
• docs/architecture.md, CHANGELOG, Dockerfile / docker-compose, brand assets
• Streamlit Cloud deployment

---

Quick start

git clone https://github.com/rvong65/ethical-decision-simulator.git
cd ethical-decision-simulator
pip install -r requirements.txt
cp .streamlit/secrets.toml.example .streamlit/secrets.toml   # add GROQ_API_KEY
streamlit run app.py

Try it: Home → Explore or Compare → pick a curated scenario in the sidebar → Run analysis or Run comparison.

Docker:

docker compose up --build 
# open http://localhost:8501

---

Note

This release marks the MVP baseline.