mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-17 14:25:21 +00:00
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.
99 lines
3.0 KiB
PHP
99 lines
3.0 KiB
PHP
<?php
|
|
|
|
namespace App\Http\Controllers\Company\Ai;
|
|
|
|
use App\Http\Controllers\Controller;
|
|
use App\Models\AiConversation;
|
|
use App\Services\Ai\AiAssistantService;
|
|
use App\Support\Ai\AiException;
|
|
use Illuminate\Http\JsonResponse;
|
|
use Illuminate\Http\Request;
|
|
use Illuminate\Validation\ValidationException;
|
|
|
|
class ChatController extends Controller
|
|
{
|
|
public function __construct(
|
|
private readonly AiAssistantService $assistant,
|
|
) {}
|
|
|
|
/**
|
|
* Send a message into a conversation and get the assistant's reply.
|
|
*
|
|
* If `conversation_id` is omitted (or belongs to a conversation the user
|
|
* doesn't own), we start a fresh conversation scoped to the current
|
|
* (company_id, user_id). This matches the "new chat" UX where the user
|
|
* opens the drawer and starts typing immediately.
|
|
*
|
|
* @throws ValidationException
|
|
*/
|
|
public function __invoke(Request $request): JsonResponse
|
|
{
|
|
$this->authorize('use ai');
|
|
|
|
$validated = $this->validate($request, [
|
|
'conversation_id' => 'nullable|integer',
|
|
'message' => 'required|string|max:10000',
|
|
]);
|
|
|
|
$companyId = (int) $request->header('company');
|
|
$userId = (int) $request->user()->id;
|
|
|
|
$conversation = $this->resolveConversation(
|
|
$validated['conversation_id'] ?? null,
|
|
$companyId,
|
|
$userId,
|
|
$validated['message'],
|
|
);
|
|
|
|
try {
|
|
$assistantMessage = $this->assistant->chat($conversation, $validated['message']);
|
|
} catch (AiException $e) {
|
|
return response()->json([
|
|
'error' => $e->errorKey,
|
|
'message' => $e->getMessage(),
|
|
], 422);
|
|
}
|
|
|
|
$conversation->refresh();
|
|
|
|
return response()->json([
|
|
'conversation' => [
|
|
'id' => $conversation->id,
|
|
'title' => $conversation->title,
|
|
'model' => $conversation->model,
|
|
'updated_at' => $conversation->updated_at,
|
|
],
|
|
'message' => [
|
|
'id' => $assistantMessage->id,
|
|
'role' => $assistantMessage->role,
|
|
'content' => $assistantMessage->content,
|
|
'created_at' => $assistantMessage->created_at,
|
|
],
|
|
]);
|
|
}
|
|
|
|
/**
|
|
* Pick an existing conversation the user owns, or create a new one.
|
|
*/
|
|
protected function resolveConversation(
|
|
?int $conversationId,
|
|
int $companyId,
|
|
int $userId,
|
|
string $firstMessage,
|
|
): AiConversation {
|
|
if ($conversationId !== null) {
|
|
$existing = AiConversation::query()
|
|
->where('id', $conversationId)
|
|
->where('company_id', $companyId)
|
|
->where('user_id', $userId)
|
|
->first();
|
|
|
|
if ($existing) {
|
|
return $existing;
|
|
}
|
|
}
|
|
|
|
return $this->assistant->startConversation($companyId, $userId, $firstMessage);
|
|
}
|
|
}
|