feat: Corpus Intelligence page + timeline background events

Adds /corpus.php — a data transparency page showing what powers the
legal tools: 9 coverage categories with live doc counts, a full
sources table pulled from the corpus DB, the AI stack (LLMs, Whisper,
Qdrant, Azure AI Search, embeddings, chunking), and a pipeline flow
diagram. Stats are live via a new /api/corpus-stats.php endpoint
(queries dobetter_rag + bnl_admin). The reasoning sidebar is repurposed
as a Corpus health panel on this page.

Also ships the in-progress timeline background events toggle:
API and UI wired together via include_background param.

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

api/corpus-stats.php

@@ -0,0 +1,68 @@
+<?php
+declare(strict_types=1);
+
+require_once __DIR__ . '/../includes/bootstrap.php';
+
+dbnToolsRequireMethod('GET');
+dbnToolsRequireAuth();
+
+try {
+    $bnlDb = dbnToolsDb();
+    $ragDb = dbnToolsRagDb();
+
+    // Total documents in the do-better-legal corpus (corpus_id=1)
+    $stmt = $ragDb->prepare('SELECT COUNT(*) FROM documents WHERE corpus_id = 1');
+    $stmt->execute();
+    $totalDocs = (int)$stmt->fetchColumn();
+
+    // Total chunks for corpus_id=1 documents
+    $stmt = $ragDb->prepare(
+        'SELECT COUNT(*) FROM chunks c
+         JOIN documents d ON c.document_id = d.id
+         WHERE d.corpus_id = 1'
+    );
+    $stmt->execute();
+    $totalChunks = (int)$stmt->fetchColumn();
+
+    // Doc counts by category
+    $stmt = $ragDb->prepare(
+        'SELECT category, COUNT(*) AS doc_count
+         FROM documents
+         WHERE corpus_id = 1 AND category IS NOT NULL AND category != \'\'
+         GROUP BY category
+         ORDER BY doc_count DESC'
+    );
+    $stmt->execute();
+    $byCategory = $stmt->fetchAll(PDO::FETCH_ASSOC);
+
+    // Last updated timestamp
+    $stmt = $ragDb->prepare('SELECT MAX(updated_at) FROM documents WHERE corpus_id = 1');
+    $stmt->execute();
+    $lastUpdated = $stmt->fetchColumn() ?: null;
+
+    // Active sources from bnl_admin
+    $stmt = $bnlDb->prepare(
+        'SELECT name, url, category, authority_type, language, schedule, is_active, scraper_class
+         FROM corpus_sources
+         WHERE corpus_id = 1
+         ORDER BY category, name'
+    );
+    $stmt->execute();
+    $sources = $stmt->fetchAll(PDO::FETCH_ASSOC);
+
+    $activeSources = count(array_filter($sources, fn($s) => !empty($s['is_active'])));
+
+    dbnToolsRespond([
+        'ok'    => true,
+        'stats' => [
+            'total_chunks'   => $totalChunks,
+            'total_docs'     => $totalDocs,
+            'active_sources' => $activeSources,
+            'last_updated'   => $lastUpdated,
+            'by_category'    => $byCategory,
+        ],
+        'sources' => $sources,
+    ]);
+} catch (Throwable $e) {
+    dbnToolsError('Could not load corpus statistics: ' . $e->getMessage(), 500, 'corpus_stats_error');
+}

api/timeline.php

@@ -23,6 +23,7 @@ dbnToolsWithTelemetry('timeline', $language, function () use ($input, $language)
         ? 'high_medium' : 'all';
 
     $includeRelative   = ($input['include_relative']   ?? true) !== false;
+    $includeBackground = ($input['include_background'] ?? true) !== false;
 
-    return (new DbnLegalToolsService())->timeline($text, $language, $engine, $focus, $confidenceFilter, $includeRelative);
+    return (new DbnLegalToolsService())->timeline($text, $language, $engine, $focus, $confidenceFilter, $includeRelative, $includeBackground);
 });

assets/css/tools.css

@@ -2013,6 +2013,414 @@ p {
   font-size: 0.92rem;
 }
 
+/* ============================================================
+   CORPUS PAGE
+   ============================================================ */
+
+/* Stats bar */
+.corpus-stats-bar {
+  display: flex;
+  gap: 0;
+  border: 1px solid var(--line);
+  border-radius: 8px;
+  overflow: hidden;
+  margin-bottom: 36px;
+  background: var(--panel);
+}
+
+.corpus-stat {
+  flex: 1;
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  padding: 20px 16px;
+  border-right: 1px solid var(--line);
+  text-align: center;
+}
+.corpus-stat:last-child { border-right: 0; }
+
+.corpus-stat__value {
+  display: block;
+  font-size: 2rem;
+  font-weight: 800;
+  color: var(--teal);
+  line-height: 1;
+  font-variant-numeric: tabular-nums;
+  letter-spacing: -0.02em;
+}
+
+.corpus-stat__value.is-loading {
+  color: var(--line);
+  background: linear-gradient(90deg, var(--line) 25%, #e8ecf2 50%, var(--line) 75%);
+  background-size: 200% 100%;
+  animation: shimmer 1.4s infinite;
+  border-radius: 4px;
+  min-width: 60px;
+}
+
+@keyframes shimmer {
+  0%   { background-position: 200% 0; }
+  100% { background-position: -200% 0; }
+}
+
+.corpus-stat__label {
+  display: block;
+  font-size: 0.72rem;
+  font-weight: 700;
+  text-transform: uppercase;
+  color: var(--muted);
+  margin-top: 6px;
+  letter-spacing: 0.04em;
+}
+
+/* Section headings */
+.corpus-section {
+  margin-bottom: 40px;
+}
+
+.corpus-section__title {
+  font-size: 1.05rem;
+  font-weight: 700;
+  color: var(--ink);
+  margin: 4px 0 18px;
+}
+
+/* Category cards */
+.corpus-categories {
+  display: grid;
+  grid-template-columns: repeat(3, 1fr);
+  gap: 14px;
+}
+
+.category-card {
+  background: var(--panel);
+  border: 1px solid var(--line);
+  border-radius: 8px;
+  padding: 18px;
+  transition: border-color 0.15s, box-shadow 0.15s;
+}
+
+.category-card:hover {
+  border-color: var(--teal);
+  box-shadow: 0 4px 16px rgba(15, 118, 110, 0.1);
+}
+
+.category-card__top {
+  display: flex;
+  justify-content: space-between;
+  align-items: flex-start;
+  margin-bottom: 10px;
+}
+
+.category-card__icon {
+  font-size: 1.5rem;
+  line-height: 1;
+}
+
+.category-card__count {
+  font-size: 0.72rem;
+  font-weight: 800;
+  background: var(--soft-teal);
+  color: var(--teal-dark);
+  border-radius: 999px;
+  padding: 2px 10px;
+  font-variant-numeric: tabular-nums;
+  min-width: 28px;
+  text-align: center;
+}
+
+.category-card__count.is-loading {
+  color: transparent;
+  background: linear-gradient(90deg, var(--line) 25%, #e8ecf2 50%, var(--line) 75%);
+  background-size: 200% 100%;
+  animation: shimmer 1.4s infinite;
+}
+
+.category-card h4 {
+  font-size: 0.88rem;
+  font-weight: 700;
+  color: var(--ink);
+  margin: 0 0 6px;
+}
+
+.category-card p {
+  font-size: 0.80rem;
+  color: var(--muted);
+  line-height: 1.5;
+  margin: 0;
+}
+
+/* Sources table */
+.corpus-table-wrap {
+  overflow-x: auto;
+  border: 1px solid var(--line);
+  border-radius: 8px;
+}
+
+.sources-table {
+  width: 100%;
+  border-collapse: collapse;
+  font-size: 0.84rem;
+  background: var(--panel);
+}
+
+.sources-table th {
+  background: var(--bg);
+  font-size: 0.70rem;
+  font-weight: 700;
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+  color: var(--muted);
+  padding: 10px 14px;
+  text-align: left;
+  border-bottom: 1px solid var(--line);
+  white-space: nowrap;
+}
+
+.sources-table td {
+  padding: 10px 14px;
+  border-bottom: 1px solid var(--line);
+  vertical-align: middle;
+}
+
+.sources-table tbody tr:last-child td { border-bottom: 0; }
+
+.sources-table tbody tr:hover td {
+  background: var(--soft-teal);
+}
+
+.sources-table a {
+  color: var(--teal);
+  text-decoration: none;
+  font-weight: 600;
+}
+
+.sources-table a:hover { text-decoration: underline; }
+
+.source-name { max-width: 260px; }
+
+.source-badge {
+  display: inline-block;
+  font-size: 0.68rem;
+  font-weight: 800;
+  padding: 2px 8px;
+  border-radius: 999px;
+  text-transform: uppercase;
+  letter-spacing: 0.03em;
+  white-space: nowrap;
+}
+
+.badge--teal   { background: var(--soft-teal); color: var(--teal-dark); }
+.badge--amber  { background: #fef3cd; color: var(--amber); }
+.badge--coral  { background: var(--soft-coral); color: var(--coral); }
+.badge--muted  { background: #eef0f5; color: var(--muted); }
+
+.source-cat {
+  font-size: 0.75rem;
+  color: var(--muted);
+  white-space: nowrap;
+}
+
+.status-active   { color: #15803d; font-size: 0.78rem; font-weight: 700; white-space: nowrap; }
+.status-inactive { color: var(--muted); font-size: 0.78rem; white-space: nowrap; }
+
+.sources-skeleton td {
+  color: var(--muted);
+  font-style: italic;
+  padding: 16px 14px;
+}
+
+/* AI Stack */
+.stack-grid {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
+  gap: 14px;
+}
+
+.stack-card {
+  background: var(--panel);
+  border: 1px solid var(--line);
+  border-left: 3px solid var(--teal);
+  border-radius: 0 8px 8px 0;
+  padding: 18px 20px;
+}
+
+.stack-card h3 {
+  font-size: 0.70rem;
+  font-weight: 700;
+  text-transform: uppercase;
+  letter-spacing: 0.06em;
+  color: var(--muted);
+  margin: 0 0 12px;
+}
+
+.stack-list {
+  list-style: none;
+  padding: 0;
+  margin: 0 0 10px;
+  display: flex;
+  flex-direction: column;
+  gap: 7px;
+  font-size: 0.84rem;
+  color: var(--ink);
+  line-height: 1.4;
+}
+
+.stack-badge {
+  display: inline-block;
+  font-size: 0.62rem;
+  font-weight: 800;
+  padding: 1px 6px;
+  border-radius: 4px;
+  text-transform: uppercase;
+  letter-spacing: 0.04em;
+  vertical-align: middle;
+  margin-right: 4px;
+}
+
+.stack-badge--azure { background: #dbeafe; color: #1d4ed8; }
+.stack-badge--gpu   { background: #f3e8ff; color: #7c3aed; }
+.stack-badge--api   { background: #fef3cd; color: var(--amber); }
+
+.stack-star {
+  font-size: 0.70rem;
+  font-weight: 700;
+  color: var(--amber);
+}
+
+.stack-note {
+  font-size: 0.75rem;
+  color: var(--muted);
+  margin: 8px 0 0;
+  line-height: 1.4;
+}
+
+.stack-note code {
+  background: var(--bg);
+  padding: 1px 5px;
+  border-radius: 3px;
+  font-size: 0.72rem;
+}
+
+/* Pipeline flow */
+.pipeline-flow {
+  display: flex;
+  align-items: stretch;
+  flex-wrap: wrap;
+  gap: 0;
+  background: var(--panel);
+  border: 1px solid var(--line);
+  border-radius: 8px;
+  overflow: hidden;
+}
+
+.pipeline-step {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  padding: 18px 14px;
+  text-align: center;
+  min-width: 90px;
+  flex: 1;
+  background: var(--panel);
+}
+
+.pipeline-step--end {
+  background: var(--soft-teal);
+}
+
+.pipeline-step__icon {
+  font-size: 1.4rem;
+  margin-bottom: 6px;
+  display: block;
+}
+
+.pipeline-step span:not(.pipeline-step__icon) {
+  font-size: 0.78rem;
+  font-weight: 700;
+  color: var(--ink);
+  display: block;
+}
+
+.pipeline-step small {
+  font-size: 0.67rem;
+  color: var(--muted);
+  display: block;
+  margin-top: 3px;
+}
+
+.pipeline-arrow {
+  display: flex;
+  align-items: center;
+  padding: 0 2px;
+  color: var(--muted);
+  font-size: 1.1rem;
+  background: var(--bg);
+  border-left: 1px solid var(--line);
+  border-right: 1px solid var(--line);
+}
+
+.pipeline-arrow::after {
+  content: '›';
+  font-weight: 700;
+}
+
+/* Corpus health sidebar */
+.corpus-health-dl {
+  margin: 0;
+  padding: 16px;
+  display: grid;
+  grid-template-columns: auto 1fr;
+  gap: 6px 12px;
+  font-size: 0.80rem;
+}
+
+.corpus-health-dl dt {
+  font-weight: 700;
+  color: var(--muted);
+  font-size: 0.70rem;
+  text-transform: uppercase;
+  letter-spacing: 0.04em;
+  padding-top: 2px;
+  white-space: nowrap;
+}
+
+.corpus-health-dl dd {
+  color: var(--ink);
+  margin: 0;
+  line-height: 1.5;
+}
+
+.corpus-health-dl code {
+  background: var(--bg);
+  border: 1px solid var(--line);
+  border-radius: 3px;
+  font-size: 0.70rem;
+  padding: 1px 5px;
+}
+
+/* Responsive */
+@media (max-width: 760px) {
+  .corpus-stats-bar {
+    flex-wrap: wrap;
+  }
+  .corpus-stat {
+    flex: 1 1 50%;
+    border-right: 0;
+    border-bottom: 1px solid var(--line);
+  }
+  .corpus-categories {
+    grid-template-columns: 1fr;
+  }
+  .pipeline-flow {
+    flex-direction: column;
+  }
+  .pipeline-arrow {
+    display: none;
+  }
+}
+
 /* Method trace — overrides for #traceList rendered in rich mode */
 .trace-list.is-rich {
   display: grid;

corpus.php

@@ -0,0 +1,415 @@
+<?php
+declare(strict_types=1);
+$toolName  = 'corpus';
+$toolTitle = 'Legal Knowledge Base';
+$toolKind  = 'Corpus Intelligence';
+$toolBadge = '~220 K passages';
+
+ob_start();
+?>
+            <div class="reasoning-head">
+                <p class="eyebrow">Corpus health</p>
+                <h2 id="reasoningTitle">Vector index</h2>
+            </div>
+            <dl class="corpus-health-dl">
+                <dt>Collection</dt>
+                <dd><code>bnl_chunks</code></dd>
+                <dt>Dimensions</dt>
+                <dd>768 (nomic-embed-text)</dd>
+                <dt>Similarity</dt>
+                <dd>Cosine</dd>
+                <dt>RAG strategy</dt>
+                <dd>Hybrid vector + keyword<br>Reciprocal rank fusion</dd>
+                <dt>Private boost</dt>
+                <dd>1.5×</dd>
+                <dt>Temporal mode</dt>
+                <dd>legal_conservative</dd>
+                <dt>Chunk target</dt>
+                <dd>600 words · 75 overlap</dd>
+                <dt>Vector DB</dt>
+                <dd>Qdrant on Colin Docker<br><code>10.0.2.10:6333</code></dd>
+                <dt>Hybrid search</dt>
+                <dd>Azure AI Search<br><code>bnl-legal-search</code><br>West Europe · Basic SKU</dd>
+            </dl>
+<?php
+$reasoningPanelOverride = ob_get_clean();
+
+require_once __DIR__ . '/includes/layout.php';
+?>
+
+<div class="corpus-stats-bar" id="corpusStatsBar">
+    <div class="corpus-stat" id="statChunks">
+        <span class="corpus-stat__value is-loading">—</span>
+        <span class="corpus-stat__label">Indexed passages</span>
+    </div>
+    <div class="corpus-stat" id="statDocs">
+        <span class="corpus-stat__value is-loading">—</span>
+        <span class="corpus-stat__label">Source documents</span>
+    </div>
+    <div class="corpus-stat" id="statSources">
+        <span class="corpus-stat__value is-loading">—</span>
+        <span class="corpus-stat__label">Active scrapers</span>
+    </div>
+    <div class="corpus-stat" id="statUpdated">
+        <span class="corpus-stat__value is-loading">—</span>
+        <span class="corpus-stat__label">Last ingested</span>
+    </div>
+</div>
+
+<!-- COVERAGE -->
+<div class="corpus-section">
+    <p class="eyebrow">Coverage</p>
+    <h3 class="corpus-section__title">Legal categories</h3>
+    <div class="corpus-categories" id="corpusCategories">
+        <div class="category-card" data-category="family-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">⚖</span>
+                <span class="category-card__count is-loading" id="cat-family-law">—</span>
+            </div>
+            <h4>Family Law</h4>
+            <p>Barneloven, child custody (foreldreansvar), samvær, mediation (mekling), separation and divorce proceedings.</p>
+        </div>
+        <div class="category-card" data-category="child-welfare">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🧒</span>
+                <span class="category-card__count is-loading" id="cat-child-welfare">—</span>
+            </div>
+            <h4>Child Welfare</h4>
+            <p>Barnevernloven, omsorgsovertakelse, emergency care orders, foster placement, CPS (barnevernet) case law.</p>
+        </div>
+        <div class="category-card" data-category="labour-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🏭</span>
+                <span class="category-card__count is-loading" id="cat-labour-law">—</span>
+            </div>
+            <h4>Labour Law</h4>
+            <p>Arbeidsmiljøloven, collective agreements (tariffavtaler), Arbeidsretten rulings, dismissal, sick leave obligations.</p>
+        </div>
+        <div class="category-card" data-category="social-welfare">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🛡</span>
+                <span class="category-card__count is-loading" id="cat-social-welfare">—</span>
+            </div>
+            <h4>Social Welfare</h4>
+            <p>NAV guidance on sykepenger, dagpenger, AAP, uføretrygd, alderspensjon, yrkesskade and social assistance.</p>
+        </div>
+        <div class="category-card" data-category="tax-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">📊</span>
+                <span class="category-card__count is-loading" id="cat-tax-law">—</span>
+            </div>
+            <h4>Tax Law</h4>
+            <p>Skatteetaten's Skatte-ABC, binding advance rulings (BFU), Skatteklagenemnda decisions, income and capital tax.</p>
+        </div>
+        <div class="category-card" data-category="administrative-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🏛</span>
+                <span class="category-card__count is-loading" id="cat-administrative-law">—</span>
+            </div>
+            <h4>Administrative Law</h4>
+            <p>Sivilombudet reports, Forvaltningsloven, procedural rights, official complaints, Stortinget oversight.</p>
+        </div>
+        <div class="category-card" data-category="consumer-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🏠</span>
+                <span class="category-card__count is-loading" id="cat-consumer-law">—</span>
+            </div>
+            <h4>Consumer &amp; Housing</h4>
+            <p>HTU (rental disputes), Finansklagenemnda, Forbrukertilsynet, Forbrukerrådet, Pakkereisenemnda decisions.</p>
+        </div>
+        <div class="category-card" data-category="immigration-law">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">🌐</span>
+                <span class="category-card__count is-loading" id="cat-immigration-law">—</span>
+            </div>
+            <h4>Immigration &amp; International</h4>
+            <p>UNE (Utlendingsnemnda) decisions, ECHR Art. 8 family rights, EMD case law, Hague Convention (cross-border child abduction).</p>
+        </div>
+        <div class="category-card" data-category="government-documents">
+            <div class="category-card__top">
+                <span class="category-card__icon" aria-hidden="true">📄</span>
+                <span class="category-card__count is-loading" id="cat-government-documents">—</span>
+            </div>
+            <h4>Government Documents</h4>
+            <p>NOUer, Stortingsmeldinger, government white papers and regulatory guidance from Regjeringen.no.</p>
+        </div>
+    </div>
+</div>
+
+<!-- SOURCES TABLE -->
+<div class="corpus-section">
+    <p class="eyebrow">Data sources</p>
+    <h3 class="corpus-section__title">Active scrapers</h3>
+    <div class="corpus-table-wrap">
+        <table class="sources-table" id="sourcesTable">
+            <thead>
+                <tr>
+                    <th>Source</th>
+                    <th>Type</th>
+                    <th>Category</th>
+                    <th>Lang</th>
+                    <th>Schedule</th>
+                    <th>Status</th>
+                </tr>
+            </thead>
+            <tbody id="sourcesTableBody">
+                <tr class="sources-skeleton"><td colspan="6">Loading sources…</td></tr>
+            </tbody>
+        </table>
+    </div>
+</div>
+
+<!-- AI STACK -->
+<div class="corpus-section">
+    <p class="eyebrow">Software</p>
+    <h3 class="corpus-section__title">AI stack</h3>
+    <div class="stack-grid">
+
+        <div class="stack-card">
+            <h3>Reasoning LLMs</h3>
+            <ul class="stack-list">
+                <li><span class="stack-badge stack-badge--azure">Azure</span> <strong>gpt-4o-mini</strong> <span class="stack-star">★ default</span> — fast, cost-efficient</li>
+                <li><span class="stack-badge stack-badge--azure">Azure</span> <strong>gpt-4o</strong> — highest quality</li>
+                <li><span class="stack-badge stack-badge--gpu">GPU</span> <strong>qwen2.5:14b</strong> — local, private</li>
+                <li><span class="stack-badge stack-badge--gpu">GPU</span> <strong>qwen3:14b</strong> — reasoning mode</li>
+                <li><span class="stack-badge stack-badge--gpu">GPU</span> <strong>dbn-legal-agent</strong> — Norwegian law fine-tune (QLoRA on qwen2.5:7b, NorwAI-24B distillation)</li>
+            </ul>
+            <p class="stack-note">All routed via LiteLLM on Colin · <code>10.0.1.10:4000</code></p>
+        </div>
+
+        <div class="stack-card">
+            <h3>Transcription</h3>
+            <ul class="stack-list">
+                <li><span class="stack-badge stack-badge--gpu">GPU</span> <strong>Whisper large-v3</strong> <span class="stack-star">★ primary</span><br>Cuttlefish · RTX 3060 12 GB VRAM</li>
+                <li><span class="stack-badge stack-badge--api">API</span> OpenAI Whisper API</li>
+                <li><span class="stack-badge stack-badge--azure">Azure</span> AI Speech <code>nb-NO</code> (Norway East)</li>
+            </ul>
+            <p class="stack-note">Speaker diarization · VAD silence filter · beam size 5 · vocabulary presets (barnerett, mediation)</p>
+        </div>
+
+        <div class="stack-card">
+            <h3>Embeddings</h3>
+            <ul class="stack-list">
+                <li><strong>nomic-embed-text</strong> — 768-dim dense vectors</li>
+                <li>Ollama on Chloe <code>10.0.1.11:11434</code></li>
+                <li>Cosine similarity in Qdrant</li>
+            </ul>
+            <p class="stack-note">All documents chunked and embedded before indexing; chunks stored in both Qdrant (vector) and MariaDB (keyword fallback)</p>
+        </div>
+
+        <div class="stack-card">
+            <h3>Vector &amp; Hybrid Search</h3>
+            <ul class="stack-list">
+                <li><strong>Qdrant</strong> <code>bnl_chunks</code> · ~220 K vectors<br>Colin Docker · <code>10.0.2.10:6333</code></li>
+                <li><strong>Azure AI Search</strong> <code>bnl-legal-search</code><br>Basic SKU · West Europe · hybrid keyword + semantic</li>
+                <li>Reciprocal rank fusion (vector + keyword)</li>
+                <li>Private corpus boosted 1.5×</li>
+            </ul>
+        </div>
+
+        <div class="stack-card">
+            <h3>Chunking pipeline</h3>
+            <ul class="stack-list">
+                <li>Heading-aware semantic splitting</li>
+                <li>600-word target · 75-word overlap</li>
+                <li>50-word minimum chunk</li>
+                <li>SHA-256 deduplication</li>
+                <li>PDF, DOCX, HTML text extraction</li>
+                <li>Temporal metadata (valid_from / valid_until)</li>
+            </ul>
+            <p class="stack-note">Legal temporal reranking: <code>legal_conservative</code> — surfaces current versions first</p>
+        </div>
+
+    </div>
+</div>
+
+<!-- DATA PIPELINE -->
+<div class="corpus-section">
+    <p class="eyebrow">How it works</p>
+    <h3 class="corpus-section__title">Ingestion pipeline</h3>
+    <div class="pipeline-flow" role="list" aria-label="Data pipeline steps">
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">🌐</span>
+            <span>Source</span>
+            <small>gov websites, APIs, PDFs</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">🕷</span>
+            <span>Scraper</span>
+            <small>HTTP / API / PDF</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">📝</span>
+            <span>Text extract</span>
+            <small>PDF, DOCX, HTML</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">✂</span>
+            <span>TextChunker</span>
+            <small>600w · 75w overlap</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">🔢</span>
+            <span>Embed</span>
+            <small>nomic · 768-dim</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">⚡</span>
+            <span>Qdrant</span>
+            <small>cosine upsert</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step" role="listitem">
+            <span class="pipeline-step__icon">🤖</span>
+            <span>LiteLLM</span>
+            <small>RAG + LLM</small>
+        </div>
+        <div class="pipeline-arrow" aria-hidden="true"></div>
+        <div class="pipeline-step pipeline-step--end" role="listitem">
+            <span class="pipeline-step__icon">🔍</span>
+            <span>Your tool</span>
+            <small>Ask, Search, Research…</small>
+        </div>
+    </div>
+</div>
+
+<script>
+(function () {
+    function fmt(n) {
+        if (n === null || n === undefined) return '—';
+        return Number(n).toLocaleString('en');
+    }
+
+    function fmtDate(s) {
+        if (!s) return '—';
+        try {
+            const d = new Date(s);
+            return d.toLocaleDateString('en-GB', { day: 'numeric', month: 'short', year: 'numeric' });
+        } catch (e) { return s; }
+    }
+
+    const authorityLabels = {
+        case_law:   { label: 'Case law',    cls: 'badge--teal' },
+        guidance:   { label: 'Guidance',    cls: 'badge--amber' },
+        report:     { label: 'Report',      cls: 'badge--muted' },
+        ombudsman:  { label: 'Ombudsman',   cls: 'badge--muted' },
+        tribunal:   { label: 'Tribunal',    cls: 'badge--coral' },
+        regulatory: { label: 'Regulatory',  cls: 'badge--coral' },
+        law:        { label: 'Statute',     cls: 'badge--teal' },
+        treaty:     { label: 'Treaty',      cls: 'badge--muted' },
+    };
+
+    const scheduleLabels = {
+        daily:   'Daily',
+        weekly:  'Weekly',
+        monthly: 'Monthly',
+        manual:  'Manual',
+    };
+
+    // Category slug → element id map (for live counts)
+    const catIds = {
+        'family-law':          'cat-family-law',
+        'family_law':          'cat-family-law',
+        'child-welfare':       'cat-child-welfare',
+        'child_welfare':       'cat-child-welfare',
+        'labour-law':          'cat-labour-law',
+        'labour_law':          'cat-labour-law',
+        'social-welfare':      'cat-social-welfare',
+        'social_welfare':      'cat-social-welfare',
+        'tax-law':             'cat-tax-law',
+        'tax_law':             'cat-tax-law',
+        'administrative-law':  'cat-administrative-law',
+        'administrative_law':  'cat-administrative-law',
+        'consumer-law':        'cat-consumer-law',
+        'consumer_law':        'cat-consumer-law',
+        'tenancy-law':         'cat-consumer-law',
+        'financial-law':       'cat-consumer-law',
+        'immigration-law':     'cat-immigration-law',
+        'immigration_law':     'cat-immigration-law',
+        'government-documents':'cat-government-documents',
+        'government_documents':'cat-government-documents',
+        'case-law':            'cat-administrative-law',
+        'victim-compensation': 'cat-administrative-law',
+        'procurement-law':     'cat-administrative-law',
+    };
+
+    function setLoaded(el) {
+        el.classList.remove('is-loading');
+    }
+
+    fetch('/api/corpus-stats.php', { credentials: 'same-origin' })
+        .then(r => r.json())
+        .then(data => {
+            if (!data.ok) return;
+            const s = data.stats;
+
+            const elChunks = document.querySelector('#statChunks .corpus-stat__value');
+            const elDocs   = document.querySelector('#statDocs .corpus-stat__value');
+            const elSrc    = document.querySelector('#statSources .corpus-stat__value');
+            const elUpd    = document.querySelector('#statUpdated .corpus-stat__value');
+
+            if (elChunks) { elChunks.textContent = fmt(s.total_chunks); setLoaded(elChunks); }
+            if (elDocs)   { elDocs.textContent   = fmt(s.total_docs);   setLoaded(elDocs); }
+            if (elSrc)    { elSrc.textContent    = fmt(s.active_sources); setLoaded(elSrc); }
+            if (elUpd)    { elUpd.textContent    = fmtDate(s.last_updated); setLoaded(elUpd); }
+
+            // Category counts
+            (s.by_category || []).forEach(row => {
+                const elId = catIds[row.category];
+                if (!elId) return;
+                const el = document.getElementById(elId);
+                if (!el) return;
+                const cur = parseInt(el.textContent, 10) || 0;
+                el.textContent = fmt(cur + parseInt(row.doc_count, 10));
+                setLoaded(el);
+            });
+            // Zero out remaining loading badges
+            document.querySelectorAll('.category-card__count.is-loading').forEach(el => {
+                el.textContent = '0';
+                setLoaded(el);
+            });
+
+            // Sources table
+            const tbody = document.getElementById('sourcesTableBody');
+            if (!tbody) return;
+            tbody.innerHTML = '';
+            (data.sources || []).forEach(src => {
+                const auth = authorityLabels[src.authority_type] || { label: src.authority_type || '—', cls: 'badge--muted' };
+                const sched = scheduleLabels[src.schedule] || (src.schedule || 'Manual');
+                const langFlag = src.language === 'no' ? '🇳🇴' : src.language === 'en' ? '🇬🇧' : (src.language || '—');
+                const statusHtml = src.is_active
+                    ? '<span class="status-active">● Active</span>'
+                    : '<span class="status-inactive">○ Inactive</span>';
+                const nameHtml = src.url
+                    ? `<a href="${escHtml(src.url)}" target="_blank" rel="noopener">${escHtml(src.name)}</a>`
+                    : escHtml(src.name);
+                const tr = document.createElement('tr');
+                tr.innerHTML = `
+                    <td class="source-name">${nameHtml}</td>
+                    <td><span class="source-badge ${escHtml(auth.cls)}">${escHtml(auth.label)}</span></td>
+                    <td><span class="source-cat">${escHtml(src.category || '—')}</span></td>
+                    <td>${langFlag}</td>
+                    <td>${escHtml(sched)}</td>
+                    <td>${statusHtml}</td>`;
+                tbody.appendChild(tr);
+            });
+        })
+        .catch(() => {
+            document.querySelectorAll('.corpus-stat__value').forEach(el => {
+                el.textContent = '—';
+                el.classList.remove('is-loading');
+            });
+        });
+
+    function escHtml(s) {
+        return String(s ?? '').replace(/&/g,'&amp;').replace(/</g,'&lt;').replace(/>/g,'&gt;').replace(/"/g,'&quot;');
+    }
+})();
+</script>
+
+<?php require_once __DIR__ . '/includes/layout_footer.php'; ?>

includes/layout.php

@@ -16,6 +16,7 @@ $navItems = [
     'timeline'      => ['Timeline',      'Events'],
     'redact'        => ['Redact',        'Privacy'],
     'transcribe'    => ['Transcribe',    'Audio'],
+    'corpus'        => ['Corpus',        'Data & stack'],
 ];
 $toolName  = $toolName  ?? 'ask';
 $toolTitle = $toolTitle ?? 'Legal Tools';

includes/layout_footer.php

@@ -1,6 +1,9 @@
         </section><!-- /tool-panel -->
 
         <aside class="reasoning-panel" aria-labelledby="reasoningTitle">
+<?php if (!empty($reasoningPanelOverride)): ?>
+<?= $reasoningPanelOverride ?>
+<?php else: ?>
             <div class="reasoning-head">
                 <p class="eyebrow">Evidence trail</p>
                 <h2 id="reasoningTitle">Reasoning</h2>
@@ -14,6 +17,7 @@
                     </div>
                 </li>
             </ol>
+<?php endif; ?>
         </aside>
     </section><!-- /workspace -->
 </main><!-- /appShell -->

timeline.php

@@ -42,6 +42,12 @@ require_once __DIR__ . '/includes/layout.php';
                         </div>
                         <p class="upload-hint" data-i18n="timelineConfidenceHint">Show all: includes events the model is uncertain about (shown in grey). Hide low-confidence: only returns events the model is reasonably sure of.</p>
 
+                        <div class="control-row" id="timelineBackgroundControl">
+                            <span class="control-label" data-i18n="timelineBackground">Background events</span>
+                            <label><input type="checkbox" id="includeBackgroundCheck" name="include_background" checked> <span data-i18n="timelineIncludeBackground">Include narrative / background dates</span></label>
+                        </div>
+                        <p class="upload-hint" data-i18n="timelineBackgroundHint">When checked, historical context dates are included (e.g. "born 30.07.2015", "met around 2011/2012"). Uncheck to extract only operational events and deadlines.</p>
+
                         <div class="control-row" id="timelineDatesControl">
                             <span class="control-label" data-i18n="timelineDates">Date types</span>
                             <label><input type="checkbox" id="includeRelativeCheck" name="include_relative" checked> <span data-i18n="timelineIncludeRelative">Include relative / recurring dates</span></label>