dobetternorge-tools/api/deep-research.php

<?php
declare(strict_types=1);

require_once __DIR__ . '/../includes/bootstrap.php';
require_once __DIR__ . '/../includes/DeepResearchAgent.php';

dbnToolsRequireMethod('POST');
dbnToolsRequireAuth();

// Stream-friendly response — defeat output buffering so the user's browser
// receives progress events while the agent runs (can take 60-180s for
// gpt-4o synthesis or multi-file ingest).
@ini_set('output_buffering', '0');
@ini_set('zlib.output_compression', '0');
@ini_set('implicit_flush', '1');
while (ob_get_level() > 0) { @ob_end_clean(); }
ob_implicit_flush(true);

header('Content-Type: application/x-ndjson; charset=utf-8');
header('Cache-Control: no-store');
header('X-Accel-Buffering: no');

$language = 'en';
$startTime = microtime(true);

$emit = function (string $event, array $payload = []) use ($startTime): void {
    $payload['event'] = $event;
    $payload['t_ms'] = (int)round((microtime(true) - $startTime) * 1000);
    echo json_encode($payload, JSON_UNESCAPED_UNICODE | JSON_UNESCAPED_SLASHES) . "\n";
    @flush();
};

try {
    $isMultipart = stripos((string)($_SERVER['CONTENT_TYPE'] ?? ''), 'multipart/form-data') !== false;
    if ($isMultipart) {
        $payloadRaw = (string)($_POST['payload'] ?? '');
        if ($payloadRaw === '') {
            throw new DbnToolsHttpException('Multipart request missing payload.', 422, 'missing_payload');
        }
        $input = json_decode($payloadRaw, true);
        if (!is_array($input)) {
            throw new DbnToolsHttpException('Invalid payload JSON.', 422, 'invalid_payload_json');
        }
    } else {
        $raw = file_get_contents('php://input');
        if ($raw === false || strlen($raw) > 120000) {
            throw new DbnToolsHttpException('Request body unreadable or too large.', 413, 'body_too_large');
        }
        $input = json_decode((string)$raw, true);
        if (!is_array($input)) {
            throw new DbnToolsHttpException('Request body must be valid JSON.', 400, 'invalid_json');
        }
    }

    $language    = dbnToolsNormalizeLanguage($input['language'] ?? 'en');
    $seedQuery   = trim((string)($input['query'] ?? ''));
    $pastedText  = trim((string)($input['paste_text'] ?? ''));
    $sliceInput  = $input['slices'] ?? [];
    $engine      = (string)($input['engine'] ?? 'azure_mini');
    $controls    = is_array($input['controls'] ?? null) ? $input['controls'] : [];

    if (mb_strlen($seedQuery, 'UTF-8') > 4000) {
        throw new DbnToolsHttpException('Query is too long.', 422, 'query_too_long');
    }
    if (mb_strlen($pastedText, 'UTF-8') > 64000) {
        throw new DbnToolsHttpException('Pasted text is too long.', 422, 'paste_too_long');
    }

    $emit('progress', ['detail' => 'Reading upload(s)…']);

    $uploadedFiles = [];
    if (!empty($_FILES['files']) && is_array($_FILES['files']['tmp_name'] ?? null)) {
        $count = count($_FILES['files']['tmp_name']);
        if ($count > 5) {
            throw new DbnToolsHttpException('At most 5 files can be uploaded per request.', 413, 'too_many_files');
        }
        for ($i = 0; $i < $count; $i++) {
            $file = [
                'name'     => $_FILES['files']['name'][$i]     ?? '',
                'type'     => $_FILES['files']['type'][$i]     ?? '',
                'tmp_name' => $_FILES['files']['tmp_name'][$i] ?? '',
                'error'    => $_FILES['files']['error'][$i]    ?? UPLOAD_ERR_NO_FILE,
                'size'     => $_FILES['files']['size'][$i]     ?? 0,
            ];
            $extracted = dbnToolsExtractUploadedFile($file);
            $uploadedFiles[] = [
                'filename'  => $extracted['filename'],
                'text'      => $extracted['text'],
                'chars'     => $extracted['chars'],
                'truncated' => $extracted['truncated'],
            ];
            $emit('progress', [
                'detail' => sprintf('Extracted %s (%d chars%s)',
                    $extracted['filename'],
                    $extracted['chars'],
                    !empty($extracted['truncated']) ? ', truncated' : ''
                ),
            ]);
        }
    }

    $emit('start', [
        'engine' => $engine,
        'language' => $language,
        'upload_count' => count($uploadedFiles),
    ]);

    $result = (new DbnDeepResearchAgent())->run(
        $seedQuery,
        $pastedText,
        $uploadedFiles,
        is_array($sliceInput) ? $sliceInput : [],
        $engine,
        $language,
        $controls,
        $emit
    );

    $result['ok'] = true;
    $result['latency_ms'] = (int)round((microtime(true) - $startTime) * 1000);

    dbnToolsLogMetadata([
        'tool'         => 'deep_research',
        'language'     => $language,
        'ok'           => true,
        'latency_ms'   => $result['latency_ms'],
        'chunk_count'  => (int)($result['trace_metadata']['chunk_count'] ?? 0),
        'source_count' => (int)($result['trace_metadata']['source_count'] ?? 0),
        'deployment'   => $result['trace_metadata']['deployment'] ?? null,
    ]);

    $emit('final', ['result' => $result]);

} catch (DbnToolsHttpException $e) {
    $latency = (int)round((microtime(true) - $startTime) * 1000);
    dbnToolsLogMetadata([
        'tool'       => 'deep_research',
        'language'   => $language,
        'ok'         => false,
        'latency_ms' => $latency,
        'error_code' => $e->errorCode,
    ]);
    $emit('error', ['code' => $e->errorCode, 'message' => $e->getMessage(), 'status' => $e->status]);
} catch (Throwable $e) {
    error_log('DBN deep research fatal: ' . $e->getMessage());
    $latency = (int)round((microtime(true) - $startTime) * 1000);
    dbnToolsLogMetadata([
        'tool'       => 'deep_research',
        'language'   => $language,
        'ok'         => false,
        'latency_ms' => $latency,
        'error_code' => 'internal_error',
    ]);
    $emit('error', ['code' => 'internal_error', 'message' => 'The agent could not complete this request.']);
}