feat(dashboard): add corpus dashboard at /dashboard/

Full private corpus dashboard for tools.dobetternorge.no users — each SSO account gets an auto-provisioned CaveauAI tenant (clients row, corpus) on first visit. Includes upload (file/paste/URL), RAG chat with SSE streaming and citation chips, document CRUD, FalkorDB graph relations tab, and improved save-from-tool flow with tag/preview support. - dashboard/{index,documents,document,upload,chat,settings}.php - api/dashboard/{corpus-init,documents,upload,ingest-status,chat-stream, save-from-tool,graph}.php - includes/{CorpusProvision,layout_dashboard,layout_dashboard_footer}.php - assets/css/dashboard.css assets/js/corpus-save.js (routing upgrade) - includes/{bootstrap,layout}.php extended for dashboard provisioning Migration 141 (clients.dbn_sso_uid + import_method enum) applied on chloe. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-23 17:15:40 +02:00
parent 83fc71414f
commit 06d01a3bce
20 changed files with 2632 additions and 28 deletions
@@ -0,0 +1,110 @@
+<?php
+/**
+ * POST /api/dashboard/chat-stream.php  (SSE)
+ *
+ * Streams a RAG chat answer using the user's private corpus + the dobetter
+ * legal package. Each output token is delivered as an SSE event named "token".
+ * On completion, sources, chunks_used, model, and elapsed_ms are sent as a
+ * "done" event. Errors are sent as a "fail" event.
+ *
+ * Request body (JSON):
+ *   {
+ *     "question": "Hva sier barnevernloven § 4-12?",
+ *     "history":  [{role:"user"|"assistant", content:"..."}],  // optional, capped at 8
+ *     "category": "barnevern" (optional),
+ *     "language": "no" | "en" (optional, default no)
+ *   }
+ */
+
+declare(strict_types=1);
+
+require_once dirname(__DIR__, 2) . '/includes/bootstrap.php';
+
+dbnToolsRequireMethod('POST');
+dbnToolsRequireAuth();
+
+try {
+    $tenant = dbnToolsEnsureDashboardTenant();
+} catch (DbnToolsHttpException $e) {
+    dbnToolsError($e->getMessage(), $e->status, $e->errorCode);
+}
+$clientId = (int)$tenant['client_id'];
+
+$input    = dbnToolsJsonInput(80_000);
+$question = trim((string)($input['question'] ?? ''));
+if ($question === '') {
+    dbnToolsError('question is required.', 400, 'missing_question');
+}
+if (mb_strlen($question, 'UTF-8') > 4000) {
+    dbnToolsError('question is too long (max 4000 chars).', 422, 'question_too_long');
+}
+
+$history = is_array($input['history'] ?? null) ? $input['history'] : [];
+$history = array_slice($history, -8);
+$history = array_values(array_filter($history, fn($m) => is_array($m)
+    && in_array($m['role'] ?? '', ['user', 'assistant'], true)
+    && is_string($m['content'] ?? null)));
+
+$category = trim((string)($input['category'] ?? '')) ?: null;
+$language = in_array($input['language'] ?? 'no', ['no', 'en'], true) ? $input['language'] : 'no';
+
+// SSE setup
+header('Content-Type: text/event-stream');
+header('Cache-Control: no-cache, no-transform');
+header('X-Accel-Buffering: no');
+@ini_set('output_buffering', 'off');
+@ini_set('zlib.output_compression', '0');
+while (ob_get_level() > 0) ob_end_flush();
+ob_implicit_flush(true);
+
+function sseEmit(string $event, array $data): void {
+    echo "event: {$event}\n";
+    echo 'data: ' . json_encode($data, JSON_UNESCAPED_UNICODE | JSON_UNESCAPED_SLASHES) . "\n\n";
+    if (function_exists('flush')) @flush();
+}
+
+dbnToolsBootCaveau();
+
+try {
+    $rag = new ClientRagPipeline($clientId);
+
+    $options = [
+        'conversation_history' => $history,
+        'language'             => $language,
+        'user_id'              => (int)($tenant['client_user_id'] ?? 0),
+        'user_role'            => 'owner',
+    ];
+
+    $result = $rag->askStreaming(
+        $question,
+        null,         // model: let pipeline choose default
+        $category,
+        $options,
+        function (string $chunk): void {
+            if ($chunk !== '') sseEmit('token', ['t' => $chunk]);
+        }
+    );
+
+    $sources = [];
+    foreach (($result['fullChunks'] ?? $result['chunks'] ?? []) as $c) {
+        if (!is_array($c)) continue;
+        $sources[] = [
+            'document_id'  => (int)($c['document_id'] ?? 0),
+            'title'        => (string)($c['title'] ?? ''),
+            'section'      => (string)($c['section_title'] ?? $c['section'] ?? ''),
+            'source_url'   => (string)($c['source_url'] ?? ''),
+            'score'        => isset($c['score']) ? (float)$c['score'] : null,
+        ];
+    }
+
+    sseEmit('done', [
+        'ok'              => true,
+        'chunks_used'     => (int)($result['chunks_used'] ?? count($sources)),
+        'model'           => (string)($result['model'] ?? ''),
+        'response_time_ms'=> (int)($result['response_time_ms'] ?? 0),
+        'sources'         => $sources,
+    ]);
+} catch (Throwable $e) {
+    sseEmit('fail', ['ok' => false, 'message' => $e->getMessage()]);
+}
+exit;