feat: OCR invoice import via Claude Vision

Upload an invoice photo → Claude extracts {supplier_name, date, currency, items, total} as JSON → auto-create a draft Purchase + PurchaseItems → redirect to edit so the user reviews before confirming/receiving. OcrInvoiceService: - Validates supported MIME (jpg/png/webp/gif) - Reads tenant Claude key (settings.ai.claude_key) — friendly error if missing - Calls /v1/messages with image content block + structured-output system prompt - Tolerant parser: strips ```json fences, falls back to first {…} block - normalize(): computes per-item total when absent, fills overall total - All return shapes: {ok:bool, data?, error?, raw?, tokens?} Filament: - "Import factură (OCR)" header action on Purchases list - Image file upload → service → matches Supplier by case-insensitive name (notes the unmapped name if no match) → creates draft Purchase + items → redirects to the Edit page Tests (6 new): - clean JSON parses; markdown fences stripped; malformed → graceful error; missing key → friendly message + no HTTP; unsupported MIME rejected; item total computed when missing Full suite: 123 passed. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-03 06:00:45 +00:00
parent 75386c354a
commit fca4f75e9c
3 changed files with 391 additions and 1 deletions
@@ -0,0 +1,165 @@
+<?php
+
+namespace App\Services\Ai;
+
+use App\Models\Central\Company;
+use App\Tenancy\TenantManager;
+use Illuminate\Support\Facades\Http;
+use Illuminate\Support\Facades\Log;
+
+/**
+ * Extracts structured invoice data from an uploaded image using Claude Vision.
+ * Output shape (when ok=true):
+ *   data => [
+ *     'supplier_name' => string|null,
+ *     'date'          => string|null (YYYY-MM-DD),
+ *     'currency'      => string|null,
+ *     'items'         => [{name, qty, unit_price, total?}],
+ *     'total'         => float|null,
+ *   ]
+ */
+class OcrInvoiceService
+{
+    public const SUPPORTED_MIME = ['image/jpeg', 'image/png', 'image/webp', 'image/gif'];
+
+    public function extract(string $absPath, ?string $mime = null): array
+    {
+        if (! is_file($absPath)) {
+            return ['ok' => false, 'error' => 'Fișierul nu există.'];
+        }
+
+        $mime ??= mime_content_type($absPath) ?: 'image/jpeg';
+        if (! in_array($mime, self::SUPPORTED_MIME, true)) {
+            return ['ok' => false, 'error' => "Tip fișier neacceptat: {$mime}. Folosește JPG/PNG/WebP."];
+        }
+
+        $company = $this->currentCompany();
+        if (! $company) {
+            return ['ok' => false, 'error' => 'Tenant nerezolvat.'];
+        }
+
+        $key = data_get($company->settings, 'ai.claude_key');
+        if (! $key) {
+            return ['ok' => false, 'error' => '⚠️ Lipsește cheia Claude în Setări → AI.'];
+        }
+
+        $b64 = base64_encode(file_get_contents($absPath));
+
+        $r = Http::withHeaders([
+                'x-api-key' => $key,
+                'anthropic-version' => '2023-06-01',
+                'content-type' => 'application/json',
+            ])
+            ->timeout(60)
+            ->post('https://api.anthropic.com/v1/messages', [
+                'model' => 'claude-sonnet-4-5',
+                'max_tokens' => 2048,
+                'system' => $this->systemPrompt(),
+                'messages' => [[
+                    'role' => 'user',
+                    'content' => [
+                        ['type' => 'image', 'source' => [
+                            'type' => 'base64', 'media_type' => $mime, 'data' => $b64,
+                        ]],
+                        ['type' => 'text', 'text' => 'Extrage datele din această factură. Răspunde DOAR cu obiectul JSON, fără text suplimentar și fără ```.'],
+                    ],
+                ]],
+            ]);
+
+        if (! $r->successful()) {
+            Log::warning('ocr.extract API error', ['status' => $r->status(), 'body' => $r->body()]);
+            return ['ok' => false, 'error' => 'API Claude: ' . ($r->json('error.message') ?? $r->status())];
+        }
+
+        $body = $r->json();
+        $text = collect($body['content'] ?? [])
+            ->where('type', 'text')->pluck('text')->implode("\n");
+        $text = trim($text);
+
+        $data = $this->parseJson($text);
+        if ($data === null) {
+            return ['ok' => false, 'error' => 'Răspuns AI ne-parsabil ca JSON.', 'raw' => $text];
+        }
+
+        return [
+            'ok' => true,
+            'data' => $this->normalize($data),
+            'raw' => $text,
+            'tokens' => [
+                'in' => $body['usage']['input_tokens'] ?? null,
+                'out' => $body['usage']['output_tokens'] ?? null,
+            ],
+        ];
+    }
+
+    private function systemPrompt(): string
+    {
+        return <<<TXT
+Ești expert OCR pentru facturi auto-service / piese auto din România/Moldova.
+Primești o imagine de factură. Extragi datele într-un obiect JSON STRICT cu schema:
+
+{
+  "supplier_name": string | null,
+  "date": string | null,        // format YYYY-MM-DD
+  "currency": string | null,    // MDL / EUR / USD / RON
+  "items": [
+    { "name": string, "qty": number, "unit_price": number, "total": number | null }
+  ],
+  "total": number | null
+}
+
+Reguli:
+- Răspunde DOAR cu JSON-ul, fără cod de ghilimele markdown.
+- Dacă o valoare nu poate fi citită clar, pune null (NU ghicești).
+- Cantitățile și prețurile sunt numere zecimale (punct, nu virgulă).
+- Numele piesei = scurt, fără TVA/observații.
+TXT;
+    }
+
+    /** Tolerate markdown code fences + leading/trailing text around the JSON object. */
+    private function parseJson(string $text): ?array
+    {
+        // Strip markdown fences if present.
+        $clean = preg_replace('/^```(?:json)?\s*|\s*```$/m', '', $text);
+        $clean = trim($clean);
+
+        $data = json_decode($clean, true);
+        if (is_array($data)) return $data;
+
+        // Fallback: find first {...} block.
+        if (preg_match('/\{.*\}/s', $clean, $m)) {
+            $data = json_decode($m[0], true);
+            if (is_array($data)) return $data;
+        }
+        return null;
+    }
+
+    private function normalize(array $d): array
+    {
+        $items = [];
+        foreach ((array) ($d['items'] ?? []) as $it) {
+            if (! is_array($it)) continue;
+            $name = trim((string) ($it['name'] ?? ''));
+            if ($name === '') continue;
+            $qty = (float) ($it['qty'] ?? 1);
+            $unit = (float) ($it['unit_price'] ?? 0);
+            $total = isset($it['total']) ? (float) $it['total'] : round($qty * $unit, 2);
+            $items[] = ['name' => $name, 'qty' => $qty, 'unit_price' => $unit, 'total' => $total];
+        }
+
+        return [
+            'supplier_name' => $d['supplier_name'] ?? null,
+            'date' => $d['date'] ?? null,
+            'currency' => $d['currency'] ?? null,
+            'items' => $items,
+            'total' => isset($d['total']) ? (float) $d['total'] : array_sum(array_column($items, 'total')),
+        ];
+    }
+
+    private function currentCompany(): ?Company
+    {
+        $id = app(TenantManager::class)->currentId();
+        if (! $id) return null;
+        return Company::withoutGlobalScopes()->find($id);
+    }
+}