Platform upgrade: semantic search, citations, readiness, tests, Docker

Major features added by 5 parallel agent teams:
- Semantic "Ask" (NL queries via FTS5 + embeddings + Claude synthesis)
- Global search across drafts, ideas, authors, gaps
- REST API expansion (14 endpoints, up from 3) with CSV/JSON export
- Citation graph visualization (D3.js, 440 nodes, 2422 edges)
- Standards readiness scoring (0-100 composite from 6 factors)
- Side-by-side draft comparison view with shared/unique analysis
- Annotation system (notes + tags per draft, DB-persisted)
- Docker deployment (Dockerfile + docker-compose with Ollama)
- Scheduled updates (cron script with log rotation)
- Pipeline health dashboard (stage progress bars, cost tracking)
- Test suite foundation (54 pytest tests covering DB, models, web data)

Fixes: compare_drafts() stubbed→working, get_authors_for_draft() bug,
source-aware analysis prompts, config env var overrides + validation,
resilient batch error handling with --retry-failed, observatory --dry-run

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

pyproject.toml

@@ -22,10 +22,17 @@ dependencies = [
     "scikit-learn>=1.3",
     "networkx>=3.2",
     "markdown>=3.5",
+    "flask>=3.0",
 ]
 
+[project.optional-dependencies]
+test = ["pytest", "pytest-cov"]
+
 [project.scripts]
 ietf = "ietf_analyzer.cli:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]