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.
74 lines
2.2 KiB
PHP
74 lines
2.2 KiB
PHP
<?php
|
|
|
|
namespace App\Services\Ai\Tools;
|
|
|
|
use App\Models\Customer;
|
|
|
|
class SearchCustomersTool extends AiTool
|
|
{
|
|
private const DEFAULT_LIMIT = 10;
|
|
|
|
private const MAX_LIMIT = 50;
|
|
|
|
public function name(): string
|
|
{
|
|
return 'search_customers';
|
|
}
|
|
|
|
public function description(): string
|
|
{
|
|
return 'Search customers for the current company by free-text query (matches name, display_name, email, company_name, contact_name). Returns a compact list with ids, names, and contact info.';
|
|
}
|
|
|
|
public function parameterSchema(): array
|
|
{
|
|
return [
|
|
'type' => 'object',
|
|
'properties' => [
|
|
'query' => [
|
|
'type' => 'string',
|
|
'description' => 'Free-text search against name, email, and related fields.',
|
|
],
|
|
'limit' => [
|
|
'type' => 'integer',
|
|
'minimum' => 1,
|
|
'maximum' => self::MAX_LIMIT,
|
|
],
|
|
],
|
|
'required' => [],
|
|
];
|
|
}
|
|
|
|
public function execute(array $arguments, int $companyId, int $userId): mixed
|
|
{
|
|
$limit = min((int) ($arguments['limit'] ?? self::DEFAULT_LIMIT), self::MAX_LIMIT);
|
|
|
|
$query = Customer::query()
|
|
->where('company_id', $companyId)
|
|
->orderBy('name')
|
|
->limit($limit);
|
|
|
|
if (! empty($arguments['query'])) {
|
|
$q = $arguments['query'];
|
|
$query->where(function ($qb) use ($q) {
|
|
$qb->where('name', 'like', "%{$q}%")
|
|
->orWhere('display_name', 'like', "%{$q}%")
|
|
->orWhere('email', 'like', "%{$q}%")
|
|
->orWhere('company_name', 'like', "%{$q}%")
|
|
->orWhere('contact_name', 'like', "%{$q}%");
|
|
});
|
|
}
|
|
|
|
return [
|
|
'customers' => $query->get()->map(fn (Customer $c): array => [
|
|
'id' => $c->id,
|
|
'name' => $c->name,
|
|
'display_name' => $c->display_name,
|
|
'email' => $c->email,
|
|
'phone' => $c->phone,
|
|
'company_name' => $c->company_name,
|
|
])->all(),
|
|
];
|
|
}
|
|
}
|