mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-16 22:05:20 +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.
48 lines
1.8 KiB
PHP
48 lines
1.8 KiB
PHP
<?php
|
|
|
|
namespace App\Providers;
|
|
|
|
use App\Services\Ai\AiToolRegistry;
|
|
use App\Services\Ai\Tools\GetCompanyStatsTool;
|
|
use App\Services\Ai\Tools\GetCustomerTool;
|
|
use App\Services\Ai\Tools\GetInvoiceTool;
|
|
use App\Services\Ai\Tools\ListExpenseCategoriesTool;
|
|
use App\Services\Ai\Tools\ListOverdueInvoicesTool;
|
|
use App\Services\Ai\Tools\ListRecentPaymentsTool;
|
|
use App\Services\Ai\Tools\SearchCustomersTool;
|
|
use App\Services\Ai\Tools\SearchInvoicesTool;
|
|
use App\Services\Ai\Tools\SearchItemsTool;
|
|
use Illuminate\Contracts\Foundation\Application;
|
|
use Illuminate\Support\ServiceProvider;
|
|
|
|
/**
|
|
* Binds the AI tool registry as a singleton and registers every built-in
|
|
* read-only tool the chat assistant can call.
|
|
*
|
|
* Modules that ship additional tools should extend the registry from their
|
|
* own ServiceProvider::boot() by resolving AiToolRegistry from the container
|
|
* and calling register() on it.
|
|
*/
|
|
class AiServiceProvider extends ServiceProvider
|
|
{
|
|
public function register(): void
|
|
{
|
|
$this->app->singleton(AiToolRegistry::class, function (Application $app): AiToolRegistry {
|
|
$registry = new AiToolRegistry;
|
|
|
|
// Built-in read-only tools (order is presentation-only; the LLM picks).
|
|
$registry->register(new SearchInvoicesTool);
|
|
$registry->register(new GetInvoiceTool);
|
|
$registry->register(new ListOverdueInvoicesTool);
|
|
$registry->register(new SearchCustomersTool);
|
|
$registry->register(new GetCustomerTool);
|
|
$registry->register(new ListRecentPaymentsTool);
|
|
$registry->register(new SearchItemsTool);
|
|
$registry->register(new ListExpenseCategoriesTool);
|
|
$registry->register(new GetCompanyStatsTool);
|
|
|
|
return $registry;
|
|
});
|
|
}
|
|
}
|