Third and final phase of the AI feature. A SparklesIcon button is added to every Tiptap WYSIWYG editor (invoice notes, email body compose, note templates — ~6 places where RichEditor is used) that opens a modal with a prompt input, optional 'use current content as context' toggle, preview area, and Insert / Replace / Regenerate actions.
**Backend (thin)** — AiTextGenerationService is stateless: resolve config → check text_generation_enabled → instantiate driver → call textCompletion() with a system-prompt-wrapped user instruction. The system prompt is terse and opinionated: 'Return only the requested text. No preamble, no explanation, no markdown code fences.' When context is provided, it's included as a separate framed block ('Context (current content the user is working with):') so the model knows it's operating on existing copy.
**GenerationController** — POST /api/v1/ai/generate with {prompt, context?}. Validates prompt required (max 4000 chars) and context optional (max 20000 chars). Rate-limited via the same 'ai' RateLimiter from Phase 2 (30/min per user/company). Gated by 'use ai' Bouncer ability + AiConfigurationService resolution. Returns {text} on success or {error, message} with 422 on any AiException.
**Frontend modal (AiTextGenerationModal.vue)** — mounted globally in CompanyLayout when bootstrap reports ai.enabled && text_generation_enabled. Uses the existing modalStore pattern: self-registers on componentName='AiTextGenerationModal'. Modal state includes prompt, useContext toggle, generatedText preview. Callers (currently RichEditor) pass onInsert/onReplace callbacks via modalStore.data; the modal invokes them with the final text and closes — it knows nothing about tiptap or ProseMirror.
**RichEditor integration** — the Sparkles toolbar button is pushed onto the existing editorButtons ref at setup time, gated on globalStore.ai.enabled && text_generation_enabled. The button opens the modal with the editor's current getHTML() as context and callbacks that use the tiptap chain API: insertContent for Insert, selectAll().deleteSelection().insertContent for Replace. No reactivity on the flag check — it's set once at bootstrap and doesn't change during a session.
**Tests** (7 new) — AiGenerationTest with a dedicated TextGenDriver test double that tracks the exact prompt passed to textCompletion(). Covers: happy path, context inclusion/omission, AI globally disabled rejection, text_generation role disabled rejection, prompt/context length validation, response whitespace trimming.
395 tests pass (was 388, +7 new). Pint clean. npm run build clean. The AI feature is now complete end-to-end: provider configuration (Phase 1), chat assistant with DB tool-calling (Phase 2), and text generation popup (Phase 3).
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.
Every main_menu entry moves from numeric group (1/2/3) to string-based group + group_label + priority. Groups now carry their own i18n label and child entries are sorted by an explicit priority field instead of config-array order, so module-contributed menu items can slot into any existing group at any position.
BootstrapController merges module-registered menu items into main_menu (previously they lived in a separate module_menu response key) and introduces a user_menu response key for items modules want to place in the avatar dropdown. The global store follows suit: moduleMenu becomes userMenu, menuGroups is a computed that sorts by priority, and hasActiveModules drops out.
New admin Appearance setting page with a single toggle for whether sidebar group labels render — so instances that prefer a compact sidebar can hide the Documents/Administration/Modules headings without losing the grouping itself. CompanyLayout watches route meta and re-bootstraps when the admin-mode flag flips so the sidebar repaints with the right menu on navigation across the admin boundary.
Test suites updated: module menu merging is asserted against main_menu (name: 'module-{slug}') rather than the old module_menu response; HelloWorldIntegrationTest verifies the schema translation path; CompanyModulesIndexTest covers the display_name attachment.
Now that the legacy v1 frontend (commit 064bdf53) is gone, the v2 directory is the only frontend and the v2 suffix is just noise. Renames resources/scripts-v2 to resources/scripts via git mv (so git records the move as renames, preserving blame and log --follow), then bulk-rewrites the 152 files that imported via @v2/... to use @/scripts/... instead. The existing @ alias (resources/) covers the new path with no extra config needed.
Drops the now-unused @v2 alias from vite.config.js and points the laravel-vite-plugin entry at resources/scripts/main.ts. Updates the only blade reference (resources/views/app.blade.php) to match. The package.json test script (eslint ./resources/scripts) automatically targets the right place after the rename without any edit.
Verified: npm run build exits clean and the Vite warning lines now reference resources/scripts/plugins/i18n.ts, confirming every import resolved through the new path. git log --follow on any moved file walks back through its scripts-v2 history.
