mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-17 06:15:20 +00:00
e861fc1fc1
Second phase of the AI feature. Users can now open a slide-in chat drawer from the SiteHeader and ask natural-language questions about their company's invoices, customers, payments, and expenses. The LLM invokes pre-defined read-only tool functions (scoped to the current company at execute time) to fetch data and synthesize answers.
**Database** — new ai_conversations and ai_messages tables. Messages are stored in OpenAI's chat format so AiAssistantService serializes a conversation into an API request with zero translation. Columns: role, content, tool_call_id, tool_calls JSON, model, tokens_in, tokens_out. Conversations are scoped (company_id, user_id) — one user's chats are invisible to everyone else, even inside the same company. Foreign-key cascade deletes.
**Tool infrastructure** — AiTool abstract base + AiToolRegistry singleton (registered in a new AiServiceProvider). The base class enforces the security rule: every tool's execute() receives companyId and userId as injected parameters; tools' JSON schemas NEVER include a company_id field. An LLM physically cannot pass a company_id and escape tenancy. Modules can register their own tools by resolving the registry from their own ServiceProvider::boot().
**Nine built-in tools**: search_invoices, get_invoice, search_customers, get_customer, list_recent_payments, list_overdue_invoices, get_company_stats (aggregates for named periods), search_items, list_expense_categories. All read-only; no mutations. Each returns JSON-encodable data the LLM can parse.
**AiAssistantService orchestration loop** — the heart of Phase 2. Flow: persist user message → build payload from system prompt + recent history (40-message window) + new user message → call driver.chatCompletion with tools → if tool_calls, execute each one via the registry (with injected scope), persist tool result, loop → if plain text, persist and return. Hard cap at 5 iterations to prevent runaway LLMs. System prompt pins the assistant to this company's data and forbids mutation.
**Controllers + policy + rate limit** — POST /api/v1/ai/chat runs the orchestration loop. GET/PATCH/DELETE /api/v1/ai/conversations for CRUD. AiConversationPolicy enforces user_id+company_id match on every action. A new 'ai' RateLimiter in RouteServiceProvider throttles to 30 req/min per (user, company). New 'use ai' Gate defined in AppServiceProvider returns true for any authenticated user — the per-company kill-switch still goes through AiConfigurationService::resolveForCompany.
**Frontend** — new features/company/ai/ folder with a Pinia store (ai-chat.store.ts) holding drawer state, current conversation, messages, and loading flags. AiChatDrawer.vue is a slide-in panel teleported to <body>, mounted globally in CompanyLayout.vue when bootstrap reports ai.enabled && ai.chat_enabled. Sub-components: AiChatMessage (user bubbles vs assistant bubbles), AiChatMessageInput (Enter submits, Shift+Enter newline), AiChatConversationList (sidebar with 'new chat' button, rename, delete). A SparklesIcon button in SiteHeader toggles the drawer.
**Driver test double** — tests use a ScriptedAiDriver registered via AiDriverFactory::register('scripted', ...) that returns pre-queued AiChatResponse objects. Feature tests cover: happy path (new conversation + message persistence), tool-call loop (multi-round-trip with search_invoices), runaway-loop cap, driver-throws path, ai_enabled=NO rejection, chat role disabled rejection, per-user conversation visibility, cross-user policy enforcement, cascade delete.
388 tests pass (was 372, +16 new). Pint clean. npm run build clean. Phase 3 (WYSIWYG text generation popup) is the remaining follow-up.
79 lines
2.5 KiB
PHP
79 lines
2.5 KiB
PHP
<?php
|
|
|
|
namespace App\Services\Ai\Tools;
|
|
|
|
use App\Models\Customer;
|
|
use App\Models\Invoice;
|
|
|
|
class GetCustomerTool extends AiTool
|
|
{
|
|
public function name(): string
|
|
{
|
|
return 'get_customer';
|
|
}
|
|
|
|
public function description(): string
|
|
{
|
|
return 'Fetch full details for a single customer by ID, including contact info, billing/shipping address, and aggregate totals (invoice count, outstanding balance).';
|
|
}
|
|
|
|
public function parameterSchema(): array
|
|
{
|
|
return [
|
|
'type' => 'object',
|
|
'properties' => [
|
|
'customer_id' => [
|
|
'type' => 'integer',
|
|
'description' => 'The customer ID.',
|
|
],
|
|
],
|
|
'required' => ['customer_id'],
|
|
];
|
|
}
|
|
|
|
public function execute(array $arguments, int $companyId, int $userId): mixed
|
|
{
|
|
$customer = Customer::query()
|
|
->where('company_id', $companyId)
|
|
->where('id', (int) ($arguments['customer_id'] ?? 0))
|
|
->with(['billingAddress', 'shippingAddress'])
|
|
->first();
|
|
|
|
if (! $customer) {
|
|
return ['error' => 'customer_not_found'];
|
|
}
|
|
|
|
// Aggregate totals — done with lightweight queries rather than loading every invoice.
|
|
$invoiceCount = Invoice::query()
|
|
->where('company_id', $companyId)
|
|
->where('customer_id', $customer->id)
|
|
->count();
|
|
|
|
$outstanding = (float) Invoice::query()
|
|
->where('company_id', $companyId)
|
|
->where('customer_id', $customer->id)
|
|
->whereIn('paid_status', ['UNPAID', 'PARTIALLY_PAID'])
|
|
->sum('due_amount');
|
|
|
|
return [
|
|
'customer' => [
|
|
'id' => $customer->id,
|
|
'name' => $customer->name,
|
|
'display_name' => $customer->display_name,
|
|
'email' => $customer->email,
|
|
'phone' => $customer->phone,
|
|
'contact_name' => $customer->contact_name,
|
|
'company_name' => $customer->company_name,
|
|
'website' => $customer->website,
|
|
'enable_portal' => (bool) $customer->enable_portal,
|
|
'billing_address' => $customer->billingAddress,
|
|
'shipping_address' => $customer->shippingAddress,
|
|
'totals' => [
|
|
'invoice_count' => $invoiceCount,
|
|
'outstanding_amount' => $outstanding,
|
|
],
|
|
],
|
|
];
|
|
}
|
|
}
|