mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-18 14:55:21 +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.
80 lines
2.3 KiB
Vue
80 lines
2.3 KiB
Vue
<script setup lang="ts">
|
|
import { useAiChatStore } from '../stores/ai-chat.store'
|
|
import type { AiConversationSummary } from '@/scripts/types/ai-config'
|
|
|
|
const store = useAiChatStore()
|
|
|
|
async function select(convo: AiConversationSummary): Promise<void> {
|
|
await store.loadConversation(convo.id)
|
|
}
|
|
|
|
async function remove(convo: AiConversationSummary, event: MouseEvent): Promise<void> {
|
|
event.stopPropagation()
|
|
if (!window.confirm('Delete this conversation?')) return
|
|
await store.deleteConversation(convo.id)
|
|
}
|
|
</script>
|
|
|
|
<template>
|
|
<div class="flex flex-col h-full">
|
|
<div class="p-3 border-b border-line-default">
|
|
<button
|
|
type="button"
|
|
class="w-full text-left text-sm font-medium rounded px-3 py-2 bg-btn-primary text-white hover:bg-btn-primary-hover"
|
|
@click="store.newConversation()"
|
|
>
|
|
+ {{ $t('ai.chat.new_conversation') }}
|
|
</button>
|
|
</div>
|
|
|
|
<div class="flex-1 overflow-y-auto">
|
|
<div
|
|
v-if="store.isLoadingConversations && store.conversations.length === 0"
|
|
class="p-3 text-xs text-muted"
|
|
>
|
|
{{ $t('general.loading') }}...
|
|
</div>
|
|
|
|
<div
|
|
v-else-if="store.conversations.length === 0"
|
|
class="p-3 text-xs text-muted"
|
|
>
|
|
{{ $t('ai.chat.no_conversations') }}
|
|
</div>
|
|
|
|
<ul v-else class="space-y-1 p-2">
|
|
<li
|
|
v-for="convo in store.conversations"
|
|
:key="convo.id"
|
|
>
|
|
<button
|
|
type="button"
|
|
class="
|
|
w-full text-left flex items-center justify-between
|
|
px-3 py-2 rounded text-sm group
|
|
hover:bg-hover
|
|
"
|
|
:class="{
|
|
'bg-hover-strong font-semibold': store.currentConversationId === convo.id,
|
|
}"
|
|
@click="select(convo)"
|
|
>
|
|
<span class="truncate text-body">
|
|
{{ convo.title ?? $t('ai.chat.untitled') }}
|
|
</span>
|
|
<span
|
|
class="
|
|
ml-2 text-xs text-muted opacity-0 group-hover:opacity-100
|
|
hover:text-alert-error-text
|
|
"
|
|
@click="remove(convo, $event)"
|
|
>
|
|
{{ $t('general.delete') }}
|
|
</span>
|
|
</button>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
</template>
|