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.
63 lines
1.4 KiB
Vue
63 lines
1.4 KiB
Vue
<script setup lang="ts">
|
|
import { ref } from 'vue'
|
|
|
|
const props = defineProps<{
|
|
isSending?: boolean
|
|
}>()
|
|
|
|
const emit = defineEmits<{
|
|
send: [message: string]
|
|
}>()
|
|
|
|
const text = ref<string>('')
|
|
|
|
function submit(): void {
|
|
const trimmed = text.value.trim()
|
|
if (!trimmed || props.isSending) return
|
|
|
|
emit('send', trimmed)
|
|
text.value = ''
|
|
}
|
|
|
|
/**
|
|
* Shift+Enter → newline, Enter alone → submit (standard chat UX).
|
|
*/
|
|
function onKeydown(e: KeyboardEvent): void {
|
|
if (e.key === 'Enter' && !e.shiftKey) {
|
|
e.preventDefault()
|
|
submit()
|
|
}
|
|
}
|
|
</script>
|
|
|
|
<template>
|
|
<form
|
|
class="border-t border-line-default p-3 flex items-end gap-2"
|
|
@submit.prevent="submit"
|
|
>
|
|
<textarea
|
|
v-model="text"
|
|
rows="2"
|
|
class="
|
|
flex-1 resize-none rounded-md border border-line-default
|
|
bg-surface text-body text-sm px-3 py-2
|
|
focus:outline-none focus:ring-1 focus:ring-primary-500
|
|
"
|
|
:placeholder="$t('ai.chat.input_placeholder')"
|
|
:disabled="isSending"
|
|
@keydown="onKeydown"
|
|
/>
|
|
<button
|
|
type="submit"
|
|
class="
|
|
rounded-md px-3 py-2 text-sm font-medium
|
|
bg-btn-primary text-white hover:bg-btn-primary-hover
|
|
disabled:opacity-50 disabled:cursor-not-allowed
|
|
"
|
|
:disabled="!text.trim() || isSending"
|
|
>
|
|
{{ isSending ? $t('ai.chat.sending') : $t('ai.chat.send') }}
|
|
</button>
|
|
</form>
|
|
</template>
|