mirror of
https://github.com/InvoiceShelf/InvoiceShelf.git
synced 2026-07-17 22:35:19 +00:00
Foundation for the AI chatbot + text generation feature. Phase 1 is infrastructure only: driver plumbing, configuration storage with encrypted API keys, global vs per-company resolution, admin + company UI pages, and an optional installer wizard step. The chat assistant and text-generation WYSIWYG integration come in later phases.
**Driver plumbing (app/Support/Ai/)** — AiDriver abstract, AiDriverFactory, AiException, AiChatResponse DTO, OpenRouterDriver concrete implementation. OpenRouter is the OpenAI-compatible aggregator that unlocks hundreds of models behind one API key and one request shape — ideal as the default v1 driver. Drivers are extensible the same way exchange rate drivers are: the module Registry's generic registerDriver('ai', ...) machinery plus a typed Registry::registerAiDriver() convenience wrapper (shipped in the upstream invoiceshelf/modules package in a paired commit).
**AiConfigurationService** — mirrors MailConfigurationService shape but with one deliberate deviation: API keys are encrypted at the service layer via Crypt::encryptString before persistence. OpenRouter bearer tokens have much bigger blast radius than SMTP passwords. Same settings / company_settings tables, same global-vs-per-company pattern, same use_custom_ai_config override toggle. Resolution order: global ai_enabled must be YES, then the company either overrides via use_custom_ai_config=YES (and can opt out with ai_enabled=NO inside the override) or inherits the global config.
**Controllers** — Admin/Settings/AiConfigurationController (global CRUD + driver list + test connection), Company/Settings/CompanyAiConfigurationController (per-company override + test), Setup/AiConfigurationController (installer wizard step, skippable with explicit ai_enabled=NO). API key is always masked as '********' in GET responses — the frontend submits the placeholder back on save and the backend preserves the stored value.
**Installer wizard** — new optional step 7 'AI' between Mail and Account. Default OFF with a Skip button. MailView.vue now routes to installation.ai instead of installation.account; installation.ai then routes to installation.account. Step order comment updated in routes.ts.
**Admin + Company settings pages** — AdminAiConfigView (no toggle, always global) and AiConfigView (with use_custom_ai_config BaseSwitchSection that auto-saves OFF). Both share AiConfigurationForm which renders the driver selector, API key input with show/hide, driver-specific config_fields (base_url for OpenRouter), and per-role enable toggles with free-text model inputs backed by a datalist of suggested models from driver metadata.
**Bootstrap endpoint** — adds an ai block to the response: { enabled, chat_enabled, text_generation_enabled }. All three are booleans resolved through AiConfigurationService::resolveForCompany(). Never leaks the API key. Frontend feature flags read from bootstrapData.ai to decide whether to show Phase 2/3 UI.
**Bouncer ability** 'manage ai config' added to SettingsPolicy, gated on isSuperAdmin() (same pattern as manage email config, manage pdf config).
**Tests** (22 new) — Unit: AiDriverFactory resolves built-in + Registry-contributed drivers, rejects unknown, merges availableDrivers. AiConfigurationService: encryption round-trip, resolution order (3 cases: global off, inherit global, override with company key, override with opt-out), makeDriver null/instance cases, listDrivers metadata. Feature: admin save + read with api key masking, preserve-on-placeholder behavior, company toggle ON/OFF semantics, bootstrap ai flags reflect resolution, company opt-out path.
372 tests pass (was 350, +22). Pint clean. npm run build clean. Phase 2 (chat assistant + tool calling) and Phase 3 (WYSIWYG text generation popup) are separate follow-up commits — this one is the foundation only.
86 lines
2.9 KiB
PHP
86 lines
2.9 KiB
PHP
<?php
|
|
|
|
namespace App\Support\Ai;
|
|
|
|
/**
|
|
* Abstract base for AI drivers.
|
|
*
|
|
* Concrete drivers adapt a specific AI provider (OpenRouter, Anthropic direct,
|
|
* local Ollama, etc.) into the two operations the host app needs:
|
|
*
|
|
* - `chatCompletion()` — for the chat assistant. OpenAI chat format, optional
|
|
* tool-calling support. Drivers MUST translate their provider's tool-call
|
|
* shape into the OpenAI-style `tool_calls` array on AiChatResponse so the
|
|
* AiAssistantService orchestration loop stays provider-agnostic.
|
|
*
|
|
* - `textCompletion()` — for the text generation popup on WYSIWYG editors.
|
|
* Stateless single-shot prompt → text.
|
|
*
|
|
* Drivers are registered with the host via the module Registry (see
|
|
* App\Providers\DriverRegistryProvider for built-ins and
|
|
* InvoiceShelf\Modules\Registry::registerAiDriver() for module-contributed ones).
|
|
*/
|
|
abstract class AiDriver
|
|
{
|
|
public function __construct(
|
|
protected string $apiKey,
|
|
protected array $config = [],
|
|
) {}
|
|
|
|
/**
|
|
* Perform a chat completion.
|
|
*
|
|
* @param array<int, array<string, mixed>> $messages OpenAI chat format: [['role' => 'user', 'content' => '...'], ...]
|
|
* @param string $model Provider-specific model identifier, e.g. 'openai/gpt-4o'
|
|
* @param array<int, array<string, mixed>> $tools OpenAI tools schema array (empty = no tool calling)
|
|
* @param array<string, mixed> $options Provider-specific options (temperature, max_tokens, etc.)
|
|
*
|
|
* @throws AiException
|
|
*/
|
|
abstract public function chatCompletion(
|
|
array $messages,
|
|
string $model,
|
|
array $tools = [],
|
|
array $options = [],
|
|
): AiChatResponse;
|
|
|
|
/**
|
|
* Perform a single-shot text completion.
|
|
*
|
|
* Implementations may route this through chatCompletion() with a single
|
|
* user message — it's a convenience for callers that don't need history.
|
|
*
|
|
* @throws AiException
|
|
*/
|
|
abstract public function textCompletion(
|
|
string $prompt,
|
|
string $model,
|
|
array $options = [],
|
|
): string;
|
|
|
|
/**
|
|
* Validate that the configured API key and base URL can reach the provider.
|
|
*
|
|
* Called from admin "Test connection" buttons. Should make a cheap round-trip
|
|
* (list models, short completion, etc.) and throw AiException on failure.
|
|
*
|
|
* @return array<string, mixed> Provider info the UI can display (e.g. echoed model list)
|
|
*
|
|
* @throws AiException
|
|
*/
|
|
abstract public function validateConnection(): array;
|
|
|
|
/**
|
|
* Optional: return the list of available model identifiers from the provider.
|
|
*
|
|
* Drivers that don't expose a models endpoint can leave this as an empty array.
|
|
* The UI falls back to the `suggested_models` declared in driver metadata.
|
|
*
|
|
* @return array<int, array{value: string, label: string}>
|
|
*/
|
|
public function listModels(): array
|
|
{
|
|
return [];
|
|
}
|
|
}
|