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>

README.md

@@ -45,8 +45,34 @@ ietf viz all
 
 # Open the interactive browser
 xdg-open data/figures/browser.html
+
+# Launch the web dashboard
+./scripts/run-webui.sh
 ```
 
+## Web Dashboard
+
+A full interactive dashboard at `http://127.0.0.1:5000` with 8 pages:
+
+```bash
+# Start the dashboard
+./scripts/run-webui.sh
+# or: python src/webui/app.py
+```
+
+| Page | What it shows |
+|------|---------------|
+| **Overview** | Stat cards, score histogram, category donut, submission timeline, category radar |
+| **Draft Explorer** | Searchable/filterable/sortable table of all drafts with category pills and score badges |
+| **Draft Detail** | Individual draft view with score ring, dimension bars, ideas, references, and linked authors |
+| **Ratings** | Score distributions, dimension box plots, category radar, novelty vs maturity scatter, top-20 leaderboard |
+| **Landscape** | t-SNE embedding map, quality quadrants, violin plots by category |
+| **Authors** | Co-authorship force-directed graph, organization charts, cross-org collaboration |
+| **Ideas** | Extracted ideas grouped by type with search |
+| **Gaps** | Gap cards sorted by severity with links to related drafts |
+
+Charts are interactive (Plotly.js) — click data points to navigate to draft details, click categories to filter.
+
 ## CLI Commands
 
 ### Core Pipeline
@@ -182,6 +208,7 @@ The safety deficit is the most striking finding — only **12.3%** of categorize
 - **SQLite** with FTS5 full-text search and WAL mode
 - **Anthropic Claude** (Sonnet 4) for analysis, rating, idea extraction, gap analysis
 - **Ollama** (nomic-embed-text) for local embeddings and similarity
+- **Flask** with Jinja2 for the interactive web dashboard
 - **Plotly** for interactive HTML visualizations
 - **Matplotlib/Seaborn** for publication-ready static figures
 - **NetworkX** for author collaboration graph analysis
@@ -203,6 +230,11 @@ src/ietf_analyzer/
     draftgen.py     # Internet-Draft generation from gap analysis
     config.py       # Configuration with defaults
 
+src/webui/
+    app.py          # Flask application with all routes
+    data.py         # Data access layer (stats, filtering, t-SNE, network graphs)
+    templates/      # Jinja2 templates (base + 8 page templates)
+
 data/
     drafts.db       # SQLite database (all analysis data)
     reports/        # Generated markdown reports