mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-17 22:35:19 +00:00
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).
89 lines
3.6 KiB
PHP
89 lines
3.6 KiB
PHP
<?php
|
|
|
|
namespace App\Services\Ai;
|
|
|
|
use App\Services\AiConfigurationService;
|
|
use App\Support\Ai\AiException;
|
|
|
|
/**
|
|
* Stateless one-shot text generation for the WYSIWYG popup.
|
|
*
|
|
* Much simpler than the chat assistant — no conversation state, no tool calls,
|
|
* no history. Takes a user-authored instruction plus optional surrounding
|
|
* context (e.g. "here's the current editor content") and returns a single
|
|
* generated text blob the frontend can insert into the editor.
|
|
*
|
|
* The text-generation role is distinct from chat in two places:
|
|
* - AiConfigurationService.text_generation_enabled gates availability
|
|
* - ai_text_generation_model picks which model to use
|
|
*
|
|
* That means an instance can use a cheap fast model for one-shot writing
|
|
* (openai/gpt-4o-mini) while pointing chat at a smarter model
|
|
* (openai/gpt-4o) without config gymnastics.
|
|
*/
|
|
class AiTextGenerationService
|
|
{
|
|
public function __construct(
|
|
private readonly AiConfigurationService $aiConfiguration,
|
|
) {}
|
|
|
|
/**
|
|
* Generate text from a user instruction, optionally grounded in a context blob.
|
|
*
|
|
* @param int $companyId Current company — resolves config and model selection
|
|
* @param string $prompt User's instruction (e.g. "write a polite late-payment reminder")
|
|
* @param string|null $context Optional surrounding content — usually the editor's
|
|
* current HTML/text, passed when the user wants the AI
|
|
* to work from existing copy
|
|
*
|
|
* @throws AiException When AI is disabled, text generation is off, or the driver call fails
|
|
*/
|
|
public function generate(int $companyId, string $prompt, ?string $context = null): string
|
|
{
|
|
$driver = $this->aiConfiguration->makeDriver($companyId);
|
|
|
|
if ($driver === null) {
|
|
throw new AiException('AI is not enabled for this company', 'ai_disabled');
|
|
}
|
|
|
|
$resolved = $this->aiConfiguration->resolveForCompany($companyId);
|
|
if (empty($resolved['text_generation_enabled'])) {
|
|
throw new AiException('Text generation is not enabled for this company', 'text_generation_disabled');
|
|
}
|
|
|
|
$model = (string) ($resolved['ai_text_generation_model'] ?? '');
|
|
if ($model === '') {
|
|
throw new AiException('No text generation model configured', 'missing_model');
|
|
}
|
|
|
|
$fullPrompt = $this->buildPrompt($prompt, $context);
|
|
|
|
return trim($driver->textCompletion($fullPrompt, $model));
|
|
}
|
|
|
|
/**
|
|
* Compose the final prompt sent to the model.
|
|
*
|
|
* Keep the framing terse — text-generation output should not be padded
|
|
* with "Here is the text you requested:" preambles. The instruction is
|
|
* always placed last so the model gives it the most weight.
|
|
*/
|
|
protected function buildPrompt(string $prompt, ?string $context): string
|
|
{
|
|
$system = "You are a helpful writing assistant embedded in an invoicing application. Generate text based on the user's instruction. Rules:\n"
|
|
.'- Return only the requested text. No preamble, no explanation, no markdown code fences.'."\n"
|
|
.'- Match the tone and language implied by the instruction.'."\n"
|
|
.'- Be concise unless explicitly asked for length.';
|
|
|
|
if ($context !== null && trim($context) !== '') {
|
|
return $system."\n\n"
|
|
."Context (current content the user is working with):\n"
|
|
.trim($context)
|
|
."\n\n"
|
|
."Instruction: {$prompt}";
|
|
}
|
|
|
|
return $system."\n\nInstruction: {$prompt}";
|
|
}
|
|
}
|