Merge remote-tracking branch 'origin/main' into hf-deploy

docs(harness,readme): two re-review must-fix items

docs+build: judge-layer v1 coupled-artifact updates

docs(readme): correct test count 444 → 443

Merge origin/main into hf-deploy: Part A (OWASP) + cold-wake README

docs: update README cold-start timing to measured values (~2 min cold / ~5s warm)

docs(readme): link SECURITY.md OWASP mapping from Security Architecture tail

docs(readme): update cold-wake number with measured range

deploy(hf): inject HF Spaces frontmatter into README for hf-deploy branch

docs: defer HF Space rename — outstanding applications reference current URL

docs: step 8.1 — tagline reframe + README honest-scope + rename closure

docs: sharpen zero-hallucination claim, explain Mistral-7B row

docs: fix test count in Testing section, add auth decision, reorder entries

docs: refine README per review — scope boundary, config block, DECISIONS link

docs: add security architecture section to README and DECISIONS.md

docs: sharpen README narrative for clarity

feat: infrastructure sprint — vLLM/Modal, Helm, Terraform (#8)

docs: restructure README for clarity

fix: comparison framing, mock-specific failure analysis, stale test counts

docs: add langchain baseline comparison to README

docs: add provider comparison report (OpenAI vs Anthropic Haiku)

Revert "fix: restore HF Spaces frontmatter"

fix: restore HF Spaces frontmatter

Clean up README by removing metadata

feat: Anthropic Haiku benchmark + README with provider comparison

feat: implement Anthropic Claude provider

feat: add SQLite conversation sessions with session_id

fix: update live demo URL to actual HF Spaces deployment

feat: switch deployment to Hugging Face Spaces (16GB free tier)

feat: Render deployment config, startup warmup, README update

feat: upgrade GitHub Actions CI with pip cache, type check, Docker build

fix: move gpt-4o-mini to benchmark context, highlight provider abstraction

feat: rewrite README for recruiter impact

feat: sharpen README for recruiter readability

feat: real benchmark numbers from OpenAI gpt-4o-mini evaluation

fix: README dataset breakdown matches actual corpus, quick start uses make targets

feat: Day 8 — README with architecture, API docs, eval guide + DECISIONS.md