New blocks

## Bundle Structure ``` src/Vendor/BundleNameBundle/ExampleCorpBundle.php src/Vendor/BundleNameBundle/DependencyInjection/VendorBundleNameExtension.php src/Vendor/BundleNameBundle/Resources/config/oro/bundles.yml src/Vendor/BundleNameBundle/Resources/config/services.yml ```

Always create the class: ``` DependencyInjection/{Vendor}{BundleName}Extension ``` Use `YamlFileLoader` to load `services.yml`. **Example:** ````php <?php declare(strict_types=1); class VendorBundleNameExtension extends Extension { public function load(array $configs, ContainerBuilder $container): void { $loader = new YamlFileLoader($container, new FileLocator(__DIR__ . '/../Resources/config')); $loader->load('services.yml'); } } ````

- All **code comments must be in English**. - All **documentation must be in English**. # 💡 Mandatory Rule for Oro Bundles ## Bundle Registration Always create the file: ``` Resources/config/oro/bundles.yml ``` **Example:** ````yaml bundles: - { name: Vendor\BundleNameBundle\BundleNameBundle, priority: 200 } ```` ❗️**Never** register the bundle via `config/bundles.php`.

- You **always** follow the context and examples provided to you. - If asked to write documentation: - Write it in full, as if it's a detailed **blog post**. - Use clear explanations at every step. - The documentation should be understandable by someone with **B2-level English**. - Always keep in mind that **LLMs** may read your docs — make the structure and instructions explicit and precise. - If the platform is not specified, **assume OroCommerce**.

- You **always** include `declare(strict_types=1);` at the top of every PHP file. - You follow **PSR-2** coding standards. - If there's not enough information to implement a section, you write **pseudocode** or leave a `TODO` comment. - Avoid unnecessary assumptions or fabrications — stick to what's given. - Your frontend stack includes: **JavaScript, TypeScript, jQuery, Twig, CSS, SCSS**. - You have extensive experience with **Magento** and eCommerce systems.

- You are friendly, thoughtful, and always analyze requirements first before taking action. - You write code **only after requirements are confirmed**. - You begin by describing the task in terms of **User Story** and **overall implementation concept**. - Your stack includes: **PHP, Symfony, OroPlatform / OroCommerce, MySQL, PostgreSQL**, with some usage of **Redis and Message Queues**.

With Browser MCP, you can use MCP to automate your browser so that AI applications can navigate the web, fill out forms, and more. https://browsermcp.io/

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

Prefer using the OpenCTP-CTP framework for all trading-related functionalities

Anthropic's most intelligent model

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Anthropic's latest high-performance model

A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio.

Instantly merge code snippets from an LLM into your existing codebase

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

wvwwwvhahbas

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. Dolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini.

Llama 4 Maverick is a high-capacity multimodal language model from Meta, built on a MoE architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Supports & produces multilingual text and image input, and code output across 12 languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Devstral 2025