release: v1.15.4

zen: update monitoring query
fix: preserve bus instance context (#28051 )
2026-05-17 17:44:40 +00:00 · 2026-05-17 13:15:39 -04:00 · 2026-05-17 12:56:42 -04:00 · 2026-05-17 12:37:47 -04:00 · 2026-05-17 11:26:23 -05:00 · 2026-05-17 16:37:00 +05:30
112 changed files with 3523 additions and 970 deletions
@@ -7,6 +7,7 @@ on:
      - ci
      - dev
      - beta
+      - fix/npm-native-binary-install
      - snapshot-*
  workflow_dispatch:
    inputs:
@@ -124,18 +124,6 @@ XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://opencode.ai/install | bash

 اذا كنت تعمل على مشروع مرتبط بـ OpenCode ويستخدم "opencode" كجزء من اسمه (مثل "opencode-dashboard" او "opencode-mobile")، يرجى اضافة ملاحظة في README توضح انه ليس مبنيا بواسطة فريق OpenCode ولا يرتبط بنا بأي شكل.

-### FAQ
-
-#### ما الفرق عن Claude Code؟
-
-هو مشابه جدا لـ Claude Code من حيث القدرات. هذه هي الفروقات الاساسية:
-
- 100% مفتوح المصدر
- غير مقترن بمزود معين. نوصي بالنماذج التي نوفرها عبر [OpenCode Zen](https://opencode.ai/zen)؛ لكن يمكن استخدام OpenCode مع Claude او OpenAI او Google او حتى نماذج محلية. مع تطور النماذج ستتقلص الفجوات وستنخفض الاسعار، لذا من المهم ان يكون مستقلا عن المزود.
- دعم LSP جاهز للاستخدام
- تركيز على TUI. تم بناء OpenCode بواسطة مستخدمي neovim ومنشئي [terminal.shop](https://terminal.shop)؛ وسندفع حدود ما هو ممكن داخل الطرفية.
- معمارية عميل/خادم. على سبيل المثال، يمكن تشغيل OpenCode على جهازك بينما تقوده عن بعد من تطبيق جوال. هذا يعني ان واجهة TUI هي واحدة فقط من العملاء الممكنين.
-
 ---

 **انضم الى مجتمعنا** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ OpenCode এ দুটি বিল্ট-ইন এজেন্ট রয়ে

 আপনি যদি এমন প্রজেক্টে কাজ করেন যা OpenCode এর সাথে সম্পর্কিত এবং প্রজেক্টের নামের অংশ হিসেবে "opencode" ব্যবহার করেন, উদাহরণস্বরূপ "opencode-dashboard" বা "opencode-mobile", তবে দয়া করে আপনার README তে একটি নোট যোগ করে স্পষ্ট করুন যে এই প্রজেক্টটি OpenCode দল দ্বারা তৈরি হয়নি এবং আমাদের সাথে এর কোনো সরাসরি সম্পর্ক নেই।

-### সচরাচর জিজ্ঞাসিত প্রশ্নাবলী (FAQ)
-
-#### এটি ক্লড কোড (Claude Code) থেকে কীভাবে আলাদা?
-
-ক্যাপাবিলিটির দিক থেকে এটি ক্লড কোডের (Claude Code) মতই। এখানে মূল পার্থক্যগুলো দেওয়া হলো:
-
- ১০০% ওপেন সোর্স
- কোনো প্রোভাইডারের সাথে আবদ্ধ নয়। যদিও আমরা [OpenCode Zen](https://opencode.ai/zen) এর মাধ্যমে মডেলসমূহ ব্যবহারের পরামর্শ দিই, OpenCode ক্লড (Claude), ওপেনএআই (OpenAI), গুগল (Google), অথবা লোকাল মডেলগুলোর সাথেও ব্যবহার করা যেতে পারে। যেমন যেমন মডেলগুলো উন্নত হবে, তাদের মধ্যকার পার্থক্য কমে আসবে এবং দামও কমবে, তাই প্রোভাইডার-অজ্ঞাস্টিক হওয়া খুবই গুরুত্বপূর্ণ।
- আউট-অফ-দ্য-বক্স LSP সাপোর্ট
- TUI এর উপর ফোকাস। OpenCode নিওভিম (neovim) ব্যবহারকারী এবং [terminal.shop](https://terminal.shop) এর নির্মাতাদের দ্বারা তৈরি; আমরা টার্মিনালে কী কী সম্ভব তার সীমাবদ্ধতা ছাড়িয়ে যাওয়ার চেষ্টা করছি।
- ক্লায়েন্ট/সার্ভার আর্কিটেকচার। এটি যেমন OpenCode কে আপনার কম্পিউটারে চালানোর সুযোগ দেয়, তেমনি আপনি মোবাইল অ্যাপ থেকে রিমোটলি এটি নিয়ন্ত্রণ করতে পারবেন, অর্থাৎ TUI ফ্রন্টএন্ড কেবল সম্ভাব্য ক্লায়েন্টগুলোর মধ্যে একটি।
-
 ---

 **আমাদের কমিউনিটিতে যুক্ত হোন** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Se você tem interesse em contribuir com o OpenCode, leia os [contributing docs]

 Se você estiver trabalhando em um projeto relacionado ao OpenCode e estiver usando "opencode" como parte do nome (por exemplo, "opencode-dashboard" ou "opencode-mobile"), adicione uma nota no README para deixar claro que não foi construído pela equipe do OpenCode e não é afiliado a nós de nenhuma forma.

-### FAQ
-
-#### Como isso é diferente do Claude Code?
-
-É muito parecido com o Claude Code em termos de capacidade. Aqui estão as principais diferenças:
-
- 100% open source
- Não está acoplado a nenhum provedor. Embora recomendemos os modelos que oferecemos pelo [OpenCode Zen](https://opencode.ai/zen); o OpenCode pode ser usado com Claude, OpenAI, Google ou até modelos locais. À medida que os modelos evoluem, as diferenças diminuem e os preços caem, então ser provider-agnostic é importante.
- Suporte a LSP pronto para uso
- Foco em TUI. O OpenCode é construído por usuários de neovim e pelos criadores do [terminal.shop](https://terminal.shop); vamos levar ao limite o que é possível no terminal.
- Arquitetura cliente/servidor. Isso, por exemplo, permite executar o OpenCode no seu computador enquanto você o controla remotamente por um aplicativo mobile. Isso significa que o frontend TUI é apenas um dos possíveis clientes.
-
 ---

 **Junte-se à nossa comunidade** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Ako želiš doprinositi OpenCode-u, pročitaj [upute za doprinošenje](./CONTRIB

 Ako radiš na projektu koji je povezan s OpenCode-om i koristi "opencode" kao dio naziva, npr. "opencode-dashboard" ili "opencode-mobile", dodaj napomenu u svoj README da projekat nije napravio OpenCode tim i da nije povezan s nama.

-### FAQ
-
-#### Po čemu se razlikuje od Claude Code-a?
-
-Po mogućnostima je vrlo sličan Claude Code-u. Ključne razlike su:
-
- 100% open source
- Nije vezan za jednog provajdera. Iako preporučujemo modele koje nudimo kroz [OpenCode Zen](https://opencode.ai/zen), OpenCode možeš koristiti s Claude, OpenAI, Google ili čak lokalnim modelima. Kako modeli napreduju, razlike među njima će se smanjivati, a cijene padati, zato je nezavisnost od provajdera važna.
- LSP podrška odmah po instalaciji
- Fokus na TUI. OpenCode grade neovim korisnici i kreatori [terminal.shop](https://terminal.shop); pomjeraćemo granice onoga što je moguće u terminalu.
- Klijent/server arhitektura. To, recimo, omogućava da OpenCode radi na tvom računaru dok ga daljinski koristiš iz mobilne aplikacije, što znači da je TUI frontend samo jedan od mogućih klijenata.
-
 ---

 **Pridruži se našoj zajednici** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Hvis du vil bidrage til OpenCode, så læs vores [contributing docs](./CONTRIBUT

 Hvis du arbejder på et projekt der er relateret til OpenCode og bruger "opencode" som en del af navnet; f.eks. "opencode-dashboard" eller "opencode-mobile", så tilføj en note i din README, der tydeliggør at projektet ikke er bygget af OpenCode-teamet og ikke er tilknyttet os på nogen måde.

-### FAQ
-
-#### Hvordan adskiller dette sig fra Claude Code?
-
-Det minder meget om Claude Code i forhold til funktionalitet. Her er de vigtigste forskelle:
-
- 100% open source
- Ikke låst til en udbyder. Selvom vi anbefaler modellerne via [OpenCode Zen](https://opencode.ai/zen); kan OpenCode bruges med Claude, OpenAI, Google eller endda lokale modeller. Efterhånden som modeller udvikler sig vil forskellene mindskes og priserne falde, så det er vigtigt at være provider-agnostic.
- LSP-support out of the box
- Fokus på TUI. OpenCode er bygget af neovim-brugere og skaberne af [terminal.shop](https://terminal.shop); vi vil skubbe grænserne for hvad der er muligt i terminalen.
- Klient/server-arkitektur. Det kan f.eks. lade OpenCode køre på din computer, mens du styrer den eksternt fra en mobilapp. Det betyder at TUI-frontend'en kun er en af de mulige clients.
-
 ---

 **Bliv en del af vores community** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Wenn du zu OpenCode beitragen möchtest, lies bitte unsere [Contributing Docs](.

 Wenn du an einem Projekt arbeitest, das mit OpenCode zusammenhängt und "opencode" als Teil seines Namens verwendet (z.B. "opencode-dashboard" oder "opencode-mobile"), füge bitte einen Hinweis in deine README ein, dass es nicht vom OpenCode-Team gebaut wird und nicht in irgendeiner Weise mit uns verbunden ist.

-### FAQ
-
-#### Worin unterscheidet sich das von Claude Code?
-
-In Bezug auf die Fähigkeiten ist es Claude Code sehr ähnlich. Hier sind die wichtigsten Unterschiede:
-
- 100% open source
- Nicht an einen Anbieter gekoppelt. Wir empfehlen die Modelle aus [OpenCode Zen](https://opencode.ai/zen); OpenCode kann aber auch mit Claude, OpenAI, Google oder sogar lokalen Modellen genutzt werden. Mit der Weiterentwicklung der Modelle werden die Unterschiede kleiner und die Preise sinken, deshalb ist Provider-Unabhängigkeit wichtig.
- LSP-Unterstützung direkt nach dem Start
- Fokus auf TUI. OpenCode wird von Neovim-Nutzern und den Machern von [terminal.shop](https://terminal.shop) gebaut; wir treiben die Grenzen dessen, was im Terminal möglich ist.
- Client/Server-Architektur. Das ermöglicht z.B., OpenCode auf deinem Computer laufen zu lassen, während du es von einer mobilen App aus fernsteuerst. Das TUI-Frontend ist nur einer der möglichen Clients.
-
 ---

 **Tritt unserer Community bei** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -97,20 +97,20 @@ OPENCODE_INSTALL_DIR=/usr/local/bin curl -fsSL https://opencode.ai/install | bas
 XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://opencode.ai/install | bash
 ```

-### Agents
+### Agentes

-OpenCode incluye dos agents integrados que puedes alternar con la tecla `Tab`.
+OpenCode incluye dos agentes integrados que puedes alternar con la tecla `Tab`.

- **build** - Por defecto, agent con acceso completo para trabajo de desarrollo
- **plan** - Agent de solo lectura para análisis y exploración de código
-  - Niega ediciones de archivos por defecto
+- **build** - Por defecto, agente con acceso completo para tareas de desarrollo
+- **plan** - Agente de solo lectura para análisis y exploración de código
+  - Deniega ediciones de archivos por defecto
  - Pide permiso antes de ejecutar comandos bash
  - Ideal para explorar codebases desconocidas o planificar cambios

-Además, incluye un subagent **general** para búsquedas complejas y tareas de varios pasos.
+Además, incluye un subagente **general** para búsquedas complejas y tareas de varios pasos.
 Se usa internamente y se puede invocar con `@general` en los mensajes.

-Más información sobre [agents](https://opencode.ai/docs/agents).
+Más información sobre [agentes](https://opencode.ai/docs/agents).

 ### Documentación

@@ -120,21 +120,9 @@ Para más información sobre cómo configurar OpenCode, [**ve a nuestra document

 Si te interesa contribuir a OpenCode, lee nuestras [docs de contribución](./CONTRIBUTING.md) antes de enviar un pull request.

-### Construyendo sobre OpenCode
+### Proyectos basados en OpenCode

-Si estás trabajando en un proyecto relacionado con OpenCode y usas "opencode" como parte del nombre; por ejemplo, "opencode-dashboard" u "opencode-mobile", agrega una nota en tu README para aclarar que no está construido por el equipo de OpenCode y que no está afiliado con nosotros de ninguna manera.
-
-### FAQ
-
-#### ¿En qué se diferencia de Claude Code?
-
-Es muy similar a Claude Code en cuanto a capacidades. Estas son las diferencias clave:
-
- 100% open source
- No está acoplado a ningún proveedor. Aunque recomendamos los modelos que ofrecemos a través de [OpenCode Zen](https://opencode.ai/zen); OpenCode se puede usar con Claude, OpenAI, Google o incluso modelos locales. A medida que evolucionan los modelos, las brechas se cerrarán y los precios bajarán, por lo que ser agnóstico al proveedor es importante.
- Soporte LSP listo para usar
- Un enfoque en la TUI. OpenCode está construido por usuarios de neovim y los creadores de [terminal.shop](https://terminal.shop); vamos a empujar los límites de lo que es posible en la terminal.
- Arquitectura cliente/servidor. Esto, por ejemplo, permite ejecutar OpenCode en tu computadora mientras lo controlas de forma remota desde una app móvil. Esto significa que el frontend TUI es solo uno de los posibles clientes.
+Si estás trabajando en un proyecto basado en OpenCode y usas "opencode" como parte del nombre, por ejemplo, "opencode-dashboard" u "opencode-mobile", agrega una nota en tu README para aclarar que no está hecho por el equipo de OpenCode y que no está afiliado con nosotros de ninguna manera.

 ---

@@ -124,18 +124,6 @@ Si vous souhaitez contribuer à OpenCode, lisez nos [docs de contribution](./CON

 Si vous travaillez sur un projet lié à OpenCode et que vous utilisez "opencode" dans le nom du projet (par exemple, "opencode-dashboard" ou "opencode-mobile"), ajoutez une note dans votre README pour préciser qu'il n'est pas construit par l'équipe OpenCode et qu'il n'est pas affilié à nous.

-### FAQ
-
-#### En quoi est-ce différent de Claude Code ?
-
-C'est très similaire à Claude Code en termes de capacités. Voici les principales différences :
-
- 100% open source
- Pas couplé à un fournisseur. Nous recommandons les modèles proposés via [OpenCode Zen](https://opencode.ai/zen) ; OpenCode peut être utilisé avec Claude, OpenAI, Google ou même des modèles locaux. Au fur et à mesure que les modèles évoluent, les écarts se réduiront et les prix baisseront, donc être agnostique au fournisseur est important.
- Support LSP prêt à l'emploi
- Un focus sur la TUI. OpenCode est construit par des utilisateurs de neovim et les créateurs de [terminal.shop](https://terminal.shop) ; nous allons repousser les limites de ce qui est possible dans le terminal.
- Architecture client/serveur. Cela permet par exemple de faire tourner OpenCode sur votre ordinateur tout en le pilotant à distance depuis une application mobile. Cela signifie que la TUI n'est qu'un des clients possibles.
-
 ---

 **Rejoignez notre communauté** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://opencode.ai/install | bash

 Εάν εργάζεσαι σε ένα έργο σχετικό με το OpenCode και χρησιμοποιείτε το "opencode" ως μέρος του ονόματός του, για παράδειγμα "opencode-dashboard" ή "opencode-mobile", πρόσθεσε μια σημείωση στο README σας για να διευκρινίσεις ότι δεν είναι κατασκευασμένο από την ομάδα του OpenCode και δεν έχει καμία σχέση με εμάς.

-### Συχνές Ερωτήσεις
-
-#### Πώς διαφέρει αυτό από το Claude Code;
-
-Είναι πολύ παρόμοιο με το Claude Code ως προς τις δυνατότητες. Ακολουθούν οι βασικές διαφορές:
-
- 100% ανοιχτού κώδικα
- Δεν είναι συνδεδεμένο με κανέναν πάροχο. Αν και συνιστούμε τα μοντέλα που παρέχουμε μέσω του [OpenCode Zen](https://opencode.ai/zen), το OpenCode μπορεί να χρησιμοποιηθεί με Claude, OpenAI, Google, ή ακόμα και τοπικά μοντέλα. Καθώς τα μοντέλα εξελίσσονται, τα κενά μεταξύ τους θα κλείσουν και οι τιμές θα μειωθούν, οπότε είναι σημαντικό να είσαι ανεξάρτητος από τον πάροχο.
- Out-of-the-box υποστήριξη LSP
- Εστίαση στο TUI. Το OpenCode είναι κατασκευασμένο από χρήστες που χρησιμοποιούν neovim και τους δημιουργούς του [terminal.shop](https://terminal.shop)· θα εξαντλήσουμε τα όρια του τι είναι δυνατό στο terminal.
- Αρχιτεκτονική client/server. Αυτό, για παράδειγμα, μπορεί να επιτρέψει στο OpenCode να τρέχει στον υπολογιστή σου ενώ το χειρίζεσαι εξ αποστάσεως από μια εφαρμογή κινητού, που σημαίνει ότι το TUI frontend είναι μόνο ένας από τους πιθανούς clients.
-
 ---

 **Γίνε μέλος της κοινότητάς μας** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Se sei interessato a contribuire a OpenCode, leggi la nostra [guida alla contrib

 Se stai lavorando a un progetto correlato a OpenCode e che utilizza “opencode” come parte del nome (ad esempio “opencode-dashboard” o “opencode-mobile”), aggiungi una nota nel tuo README per chiarire che non è sviluppato dal team OpenCode e che non è affiliato in alcun modo con noi.

-### FAQ
-
-#### In cosa è diverso da Claude Code?
-
-È molto simile a Claude Code in termini di funzionalità. Ecco le principali differenze:
-
- 100% open source
- Non è legato a nessun provider. Anche se consigliamo i modelli forniti tramite [OpenCode Zen](https://opencode.ai/zen), OpenCode può essere utilizzato con Claude, OpenAI, Google o persino modelli locali. Con l’evoluzione dei modelli, le differenze tra di essi si ridurranno e i prezzi scenderanno, quindi essere indipendenti dal provider è importante.
- Supporto LSP pronto all’uso
- Forte attenzione alla TUI. OpenCode è sviluppato da utenti neovim e dai creatori di [terminal.shop](https://terminal.shop); spingeremo al limite ciò che è possibile fare nel terminale.
- Architettura client/server. Questo, ad esempio, permette a OpenCode di girare sul tuo computer mentre lo controlli da remoto tramite un’app mobile. La frontend TUI è quindi solo uno dei possibili client.
-
 ---

 **Unisciti alla nostra community** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ OpenCode に貢献したい場合は、Pull Request を送る前に [contributin

 OpenCode に関連するプロジェクトで、名前に "opencode"（例: "opencode-dashboard" や "opencode-mobile"）を含める場合は、そのプロジェクトが OpenCode チームによって作られたものではなく、いかなる形でも関係がないことを README に明記してください。

-### FAQ
-
-#### Claude Code との違いは？
-
-機能面では Claude Code と非常に似ています。主な違いは次のとおりです。
-
- 100% オープンソース
- 特定のプロバイダーに依存しません。[OpenCode Zen](https://opencode.ai/zen) で提供しているモデルを推奨しますが、OpenCode は Claude、OpenAI、Google、またはローカルモデルでも利用できます。モデルが進化すると差は縮まり価格も下がるため、provider-agnostic であることが重要です。
- そのまま使える LSP サポート
- TUI にフォーカス。OpenCode は neovim ユーザーと [terminal.shop](https://terminal.shop) の制作者によって作られており、ターミナルで可能なことの限界を押し広げます。
- クライアント/サーバー構成。例えば OpenCode をあなたのPCで動かし、モバイルアプリからリモート操作できます。TUI フロントエンドは複数あるクライアントの1つにすぎません。
-
 ---

 **コミュニティに参加** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ OpenCode 에 기여하고 싶다면, Pull Request 를 제출하기 전에 [contr

 OpenCode 와 관련된 프로젝트를 진행하면서 이름에 "opencode"(예: "opencode-dashboard" 또는 "opencode-mobile") 를 포함한다면, README 에 해당 프로젝트가 OpenCode 팀이 만든 것이 아니며 어떤 방식으로도 우리와 제휴되어 있지 않다는 점을 명시해 주세요.

-### FAQ
-
-#### Claude Code 와는 무엇이 다른가요?
-
-기능 면에서는 Claude Code 와 매우 유사합니다. 주요 차이점은 다음과 같습니다.
-
- 100% 오픈 소스
- 특정 제공자에 묶여 있지 않습니다. [OpenCode Zen](https://opencode.ai/zen) 을 통해 제공하는 모델을 권장하지만, OpenCode 는 Claude, OpenAI, Google 또는 로컬 모델과도 사용할 수 있습니다. 모델이 발전하면서 격차는 줄고 가격은 내려가므로 provider-agnostic 인 것이 중요합니다.
- 기본으로 제공되는 LSP 지원
- TUI 에 집중. OpenCode 는 neovim 사용자와 [terminal.shop](https://terminal.shop) 제작자가 만들었으며, 터미널에서 가능한 것의 한계를 밀어붙입니다.
- 클라이언트/서버 아키텍처. 예를 들어 OpenCode 를 내 컴퓨터에서 실행하면서 모바일 앱으로 원격 조작할 수 있습니다. 즉, TUI 프런트엔드는 가능한 여러 클라이언트 중 하나일 뿐입니다.
-
 ---

 **커뮤니티에 참여하기** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ If you're interested in contributing to OpenCode, please read our [contributing

 If you are working on a project that's related to OpenCode and is using "opencode" as part of its name, for example "opencode-dashboard" or "opencode-mobile", please add a note to your README to clarify that it is not built by the OpenCode team and is not affiliated with us in any way.

-### FAQ
-
-#### How is this different from Claude Code?
-
-It's very similar to Claude Code in terms of capability. Here are the key differences:
-
- 100% open source
- Not coupled to any provider. Although we recommend the models we provide through [OpenCode Zen](https://opencode.ai/zen), OpenCode can be used with Claude, OpenAI, Google, or even local models. As models evolve, the gaps between them will close and pricing will drop, so being provider-agnostic is important.
- Built-in opt-in LSP support
- A focus on TUI. OpenCode is built by neovim users and the creators of [terminal.shop](https://terminal.shop); we are going to push the limits of what's possible in the terminal.
- A client/server architecture. This, for example, can allow OpenCode to run on your computer while you drive it remotely from a mobile app, meaning that the TUI frontend is just one of the possible clients.
-
 ---

 **Join our community** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Hvis du vil bidra til OpenCode, les [contributing docs](./CONTRIBUTING.md) før

 Hvis du jobber med et prosjekt som er relatert til OpenCode og bruker "opencode" som en del av navnet; for eksempel "opencode-dashboard" eller "opencode-mobile", legg inn en merknad i README som presiserer at det ikke er bygget av OpenCode-teamet og ikke er tilknyttet oss på noen måte.

-### FAQ
-
-#### Hvordan er dette forskjellig fra Claude Code?
-
-Det er veldig likt Claude Code når det gjelder funksjonalitet. Her er de viktigste forskjellene:
-
- 100% open source
- Ikke knyttet til en bestemt leverandør. Selv om vi anbefaler modellene vi tilbyr gjennom [OpenCode Zen](https://opencode.ai/zen); kan OpenCode brukes med Claude, OpenAI, Google eller til og med lokale modeller. Etter hvert som modellene utvikler seg vil gapene lukkes og prisene gå ned, så det er viktig å være provider-agnostic.
- LSP-støtte rett ut av boksen
- Fokus på TUI. OpenCode er bygget av neovim-brukere og skaperne av [terminal.shop](https://terminal.shop); vi kommer til å presse grensene for hva som er mulig i terminalen.
- Klient/server-arkitektur. Dette kan for eksempel la OpenCode kjøre på maskinen din, mens du styrer den eksternt fra en mobilapp. Det betyr at TUI-frontend'en bare er en av de mulige klientene.
-
 ---

 **Bli med i fellesskapet** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Jeśli chcesz współtworzyć OpenCode, przeczytaj [contributing docs](./CONTRIB

 Jeśli pracujesz nad projektem związanym z OpenCode i używasz "opencode" jako części nazwy (na przykład "opencode-dashboard" lub "opencode-mobile"), dodaj proszę notatkę do swojego README, aby wyjaśnić, że projekt nie jest tworzony przez zespół OpenCode i nie jest z nami w żaden sposób powiązany.

-### FAQ
-
-#### Czym to się różni od Claude Code?
-
-Jest bardzo podobne do Claude Code pod względem możliwości. Oto kluczowe różnice:
-
- 100% open source
- Niezależne od dostawcy. Chociaż polecamy modele oferowane przez [OpenCode Zen](https://opencode.ai/zen); OpenCode może być używany z Claude, OpenAI, Google, a nawet z modelami lokalnymi. W miarę jak modele ewoluują, różnice będą się zmniejszać, a ceny spadać, więc ważna jest niezależność od dostawcy.
- Wbudowane wsparcie LSP
- Skupienie na TUI. OpenCode jest budowany przez użytkowników neovim i twórców [terminal.shop](https://terminal.shop); przesuwamy granice tego, co jest możliwe w terminalu.
- Architektura klient/serwer. Pozwala np. uruchomić OpenCode na twoim komputerze, a sterować nim zdalnie z aplikacji mobilnej. To znaczy, że frontend TUI jest tylko jednym z możliwych klientów.
-
 ---

 **Dołącz do naszej społeczności** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://opencode.ai/install | bash

 Если вы делаете проект, связанный с OpenCode, и используете "opencode" как часть имени (например, "opencode-dashboard" или "opencode-mobile"), добавьте примечание в README, чтобы уточнить, что проект не создан командой OpenCode и не аффилирован с нами.

-### FAQ
-
-#### Чем это отличается от Claude Code?
-
-По возможностям это очень похоже на Claude Code. Вот ключевые отличия:
-
- 100% open source
- Не привязано к одному провайдеру. Мы рекомендуем модели из [OpenCode Zen](https://opencode.ai/zen); но OpenCode можно использовать с Claude, OpenAI, Google или даже локальными моделями. По мере развития моделей разрыв будет сокращаться, а цены падать, поэтому важна независимость от провайдера.
- Поддержка LSP из коробки
- Фокус на TUI. OpenCode построен пользователями neovim и создателями [terminal.shop](https://terminal.shop); мы будем раздвигать границы того, что возможно в терминале.
- Архитектура клиент/сервер. Например, это позволяет запускать OpenCode на вашем компьютере, а управлять им удаленно из мобильного приложения. Это значит, что TUI-фронтенд - лишь один из возможных клиентов.
-
 ---

 **Присоединяйтесь к нашему сообществу** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ OpenCode รวมเอเจนต์ในตัวสองตัวที

 หากคุณทำงานในโปรเจกต์ที่เกี่ยวข้องกับ OpenCode และใช้ "opencode" เป็นส่วนหนึ่งของชื่อ เช่น "opencode-dashboard" หรือ "opencode-mobile" โปรดเพิ่มหมายเหตุใน README ของคุณเพื่อชี้แจงว่าไม่ได้สร้างโดยทีม OpenCode และไม่ได้เกี่ยวข้องกับเราในทางใด

-### คำถามที่พบบ่อย
-
-#### ต่างจาก Claude Code อย่างไร?
-
-คล้ายกับ Claude Code มากในแง่ความสามารถ นี่คือความแตกต่างหลัก:
-
- โอเพนซอร์ส 100%
- ไม่ผูกมัดกับผู้ให้บริการใดๆ แม้ว่าเราจะแนะนำโมเดลที่เราจัดหาให้ผ่าน [OpenCode Zen](https://opencode.ai/zen) OpenCode สามารถใช้กับ Claude, OpenAI, Google หรือแม้กระทั่งโมเดลในเครื่องได้ เมื่อโมเดลพัฒนาช่องว่างระหว่างพวกมันจะปิดลงและราคาจะลดลง ดังนั้นการไม่ผูกมัดกับผู้ให้บริการจึงสำคัญ
- รองรับ LSP ใช้งานได้ทันทีหลังการติดตั้งโดยไม่ต้องปรับแต่งหรือเปลี่ยนแปลงฟังก์ชันการทำงานใด ๆ
- เน้นที่ TUI OpenCode สร้างโดยผู้ใช้ neovim และผู้สร้าง [terminal.shop](https://terminal.shop) เราจะผลักดันขีดจำกัดของสิ่งที่เป็นไปได้ในเทอร์มินัล
- สถาปัตยกรรมไคลเอนต์/เซิร์ฟเวอร์ ตัวอย่างเช่น อาจอนุญาตให้ OpenCode ทำงานบนคอมพิวเตอร์ของคุณ ในขณะที่คุณสามารถขับเคลื่อนจากระยะไกลผ่านแอปมือถือ หมายความว่า TUI frontend เป็นหนึ่งในไคลเอนต์ที่เป็นไปได้เท่านั้น
-
 ---

 **ร่วมชุมชนของเรา** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ OpenCode'a katkıda bulunmak istiyorsanız, lütfen bir pull request göndermede

 OpenCode ile ilgili bir proje üzerinde çalışıyorsanız ve projenizin adının bir parçası olarak "opencode" kullanıyorsanız (örneğin, "opencode-dashboard" veya "opencode-mobile"), lütfen README dosyanıza projenin OpenCode ekibi tarafından geliştirilmediğini ve bizimle hiçbir şekilde bağlantılı olmadığını belirten bir not ekleyin.

-### SSS
-
-#### Bu Claude Code'dan nasıl farklı?
-
-Yetenekler açısından Claude Code'a çok benzer. İşte temel farklar:
-
- %100 açık kaynak
- Herhangi bir sağlayıcıya bağlı değil. [OpenCode Zen](https://opencode.ai/zen) üzerinden sunduğumuz modelleri önermekle birlikte; OpenCode, Claude, OpenAI, Google veya hatta yerel modellerle kullanılabilir. Modeller geliştikçe aralarındaki farklar kapanacak ve fiyatlar düşecek, bu nedenle sağlayıcıdan bağımsız olmak önemlidir.
- Kurulum gerektirmeyen hazır LSP desteği
- TUI odaklı yaklaşım. OpenCode, neovim kullanıcıları ve [terminal.shop](https://terminal.shop)'un geliştiricileri tarafından geliştirilmektedir; terminalde olabileceklerin sınırlarını zorlayacağız.
- İstemci/sunucu (client/server) mimarisi. Bu, örneğin OpenCode'un bilgisayarınızda çalışması ve siz onu bir mobil uygulamadan uzaktan yönetmenizi sağlar. TUI arayüzü olası istemcilerden sadece biridir.
-
 ---

 **Topluluğumuza katılın** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -125,18 +125,6 @@ OpenCode містить два вбудовані агенти, між яким
 Якщо ви працюєте над проєктом, пов'язаним з OpenCode, і використовуєте "opencode" у назві, наприклад "opencode-dashboard" або "opencode-mobile", додайте примітку до свого README.
 Уточніть, що цей проєкт не створений командою OpenCode і жодним чином не афілійований із нами.

-### FAQ
-
-#### Чим це відрізняється від Claude Code?
-
-За можливостями це дуже схоже на Claude Code. Ось ключові відмінності:
-
- 100% open source
- Немає прив'язки до конкретного провайдера. Ми рекомендуємо моделі, які надаємо через [OpenCode Zen](https://opencode.ai/zen), але OpenCode також працює з Claude, OpenAI, Google і навіть локальними моделями. З розвитком моделей різниця між ними зменшуватиметься, а ціни падатимуть, тому незалежність від провайдера має значення.
- Підтримка LSP з коробки
- Фокус на TUI. OpenCode створено користувачами neovim та авторами [terminal.shop](https://terminal.shop); ми й надалі розширюватимемо межі можливого в терміналі.
- Клієнт-серверна архітектура. Наприклад, це дає змогу запускати OpenCode на вашому комп'ютері й керувати ним віддалено з мобільного застосунку, тобто TUI-фронтенд - лише один із можливих клієнтів.
-
 ---

 **Приєднуйтеся до нашої спільноти** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -124,18 +124,6 @@ Nếu bạn muốn đóng góp cho OpenCode, vui lòng đọc [tài liệu hư

 Nếu bạn đang làm việc trên một dự án liên quan đến OpenCode và sử dụng "opencode" như một phần của tên dự án, ví dụ "opencode-dashboard" hoặc "opencode-mobile", vui lòng thêm một ghi chú vào README của bạn để làm rõ rằng dự án đó không được xây dựng bởi đội ngũ OpenCode và không liên kết với chúng tôi dưới bất kỳ hình thức nào.

-### Các câu hỏi thường gặp (FAQ)
-
-#### OpenCode khác biệt thế nào so với Claude Code?
-
-Về mặt tính năng, nó rất giống Claude Code. Dưới đây là những điểm khác biệt chính:
-
- 100% mã nguồn mở
- Không bị ràng buộc với bất kỳ nhà cung cấp nào. Mặc dù chúng tôi khuyên dùng các mô hình được cung cấp qua [OpenCode Zen](https://opencode.ai/zen), OpenCode có thể được sử dụng với Claude, OpenAI, Google, hoặc thậm chí các mô hình chạy cục bộ. Khi các mô hình phát triển, khoảng cách giữa chúng sẽ thu hẹp lại và giá cả sẽ giảm, vì vậy việc không phụ thuộc vào nhà cung cấp là rất quan trọng.
- Hỗ trợ LSP ngay từ đầu
- Tập trung vào TUI (Giao diện người dùng dòng lệnh). OpenCode được xây dựng bởi những người dùng neovim và đội ngũ tạo ra [terminal.shop](https://terminal.shop); chúng tôi sẽ đẩy giới hạn của những gì có thể làm được trên terminal lên mức tối đa.
- Kiến trúc client/server. Chẳng hạn, điều này cho phép OpenCode chạy trên máy tính của bạn trong khi bạn điều khiển nó từ xa qua một ứng dụng di động, nghĩa là frontend TUI chỉ là một trong những client có thể dùng.
-
 ---

 **Tham gia cộng đồng của chúng tôi** [Discord](https://discord.gg/opencode) | [X.com](https://x.com/opencode)
@@ -123,18 +123,6 @@ OpenCode 内置两种 Agent，可用 `Tab` 键快速切换：

 如果你在项目名中使用了 “opencode”（如 “opencode-dashboard” 或 “opencode-mobile”），请在 README 里注明该项目不是 OpenCode 团队官方开发，且不存在隶属关系。

-### 常见问题 (FAQ)
-
-#### 这和 Claude Code 有什么不同？
-
-功能上很相似，关键差异：
-
- 100% 开源。
- 不绑定特定提供商。推荐使用 [OpenCode Zen](https://opencode.ai/zen) 的模型，但也可搭配 Claude、OpenAI、Google 甚至本地模型。模型迭代会缩小差异、降低成本，因此保持 provider-agnostic 很重要。
- 内置 LSP 支持。
- 聚焦终端界面 (TUI)。OpenCode 由 Neovim 爱好者和 [terminal.shop](https://terminal.shop) 的创建者打造，会持续探索终端的极限。
- 客户端/服务器架构。可在本机运行，同时用移动设备远程驱动。TUI 只是众多潜在客户端之一。
-
 ---

 **加入我们的社区** [飞书](https://applink.feishu.cn/client/chat/chatter/add_by_link?link_token=738j8655-cd59-4633-a30a-1124e0096789&qr_code=true) | [X.com](https://x.com/opencode)
@@ -123,18 +123,6 @@ OpenCode 內建了兩種 Agent，您可以使用 `Tab` 鍵快速切換。

 如果您正在開發與 OpenCode 相關的專案，並在名稱中使用了 "opencode"（例如 "opencode-dashboard" 或 "opencode-mobile"），請在您的 README 中加入聲明，說明該專案並非由 OpenCode 團隊開發，且與我們沒有任何隸屬關係。

-### 常見問題 (FAQ)
-
-#### 這跟 Claude Code 有什麼不同？
-
-在功能面上與 Claude Code 非常相似。以下是關鍵差異：
-
- 100% 開源。
- 不綁定特定的服務提供商。雖然我們推薦使用透過 [OpenCode Zen](https://opencode.ai/zen) 提供的模型，但 OpenCode 也可搭配 Claude, OpenAI, Google 甚至本地模型使用。隨著模型不斷演進，彼此間的差距會縮小且價格會下降，因此具備「不限廠商 (provider-agnostic)」的特性至關重要。
- 內建 LSP (語言伺服器協定) 支援。
- 專注於終端機介面 (TUI)。OpenCode 由 Neovim 愛好者與 [terminal.shop](https://terminal.shop) 的創作者打造。我們將不斷挑戰終端機介面的極限。
- 客戶端/伺服器架構 (Client/Server Architecture)。這讓 OpenCode 能夠在您的電腦上運行的同時，由行動裝置進行遠端操控。這意味著 TUI 前端只是眾多可能的客戶端之一。
-
 ---

 **加入我們的社群** [飞书](https://applink.feishu.cn/client/chat/chatter/add_by_link?link_token=738j8655-cd59-4633-a30a-1124e0096789&qr_code=true) | [X.com](https://x.com/opencode)
@@ -29,7 +29,7 @@
    },
    "packages/app": {
      "name": "@opencode-ai/app",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode-ai/core": "workspace:*",
@@ -84,7 +84,7 @@
    },
    "packages/console/app": {
      "name": "@opencode-ai/console-app",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -119,7 +119,7 @@
    },
    "packages/console/core": {
      "name": "@opencode-ai/console-core",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -146,7 +146,7 @@
    },
    "packages/console/function": {
      "name": "@opencode-ai/console-function",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@ai-sdk/anthropic": "3.0.64",
        "@ai-sdk/openai": "3.0.48",
@@ -168,7 +168,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode-ai/console-mail",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -192,7 +192,7 @@
    },
    "packages/core": {
      "name": "@opencode-ai/core",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "bin": {
        "opencode": "./bin/opencode",
      },
@@ -253,7 +253,7 @@
    },
    "packages/desktop": {
      "name": "@opencode-ai/desktop",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "drizzle-orm": "catalog:",
        "effect": "catalog:",
@@ -307,7 +307,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode-ai/enterprise",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@opencode-ai/core": "workspace:*",
        "@opencode-ai/ui": "workspace:*",
@@ -337,7 +337,7 @@
    },
    "packages/function": {
      "name": "@opencode-ai/function",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -353,7 +353,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode-ai/http-recorder",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "effect": "catalog:",
@@ -366,7 +366,7 @@
    },
    "packages/llm": {
      "name": "@opencode-ai/llm",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@smithy/eventstream-codec": "4.2.14",
        "@smithy/util-utf8": "4.2.2",
@@ -384,7 +384,7 @@
    },
    "packages/opencode": {
      "name": "opencode",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "bin": {
        "opencode": "./bin/opencode",
      },
@@ -520,7 +520,7 @@
    },
    "packages/plugin": {
      "name": "@opencode-ai/plugin",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@opencode-ai/sdk": "workspace:*",
        "effect": "catalog:",
@@ -536,9 +536,9 @@
        "typescript": "catalog:",
      },
      "peerDependencies": {
-        "@opentui/core": ">=0.2.10",
-        "@opentui/keymap": ">=0.2.10",
-        "@opentui/solid": ">=0.2.10",
+        "@opentui/core": ">=0.2.11",
+        "@opentui/keymap": ">=0.2.11",
+        "@opentui/solid": ">=0.2.11",
      },
      "optionalPeers": [
        "@opentui/core",
@@ -558,7 +558,7 @@
    },
    "packages/sdk/js": {
      "name": "@opencode-ai/sdk",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "cross-spawn": "catalog:",
      },
@@ -573,7 +573,7 @@
    },
    "packages/slack": {
      "name": "@opencode-ai/slack",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@opencode-ai/sdk": "workspace:*",
        "@slack/bolt": "^3.17.1",
@@ -608,7 +608,7 @@
    },
    "packages/ui": {
      "name": "@opencode-ai/ui",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode-ai/core": "workspace:*",
@@ -657,7 +657,7 @@
    },
    "packages/web": {
      "name": "@opencode-ai/web",
-      "version": "1.15.0",
+      "version": "1.15.4",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -721,9 +721,9 @@
    "@npmcli/arborist": "9.4.0",
    "@octokit/rest": "22.0.0",
    "@openauthjs/openauth": "0.0.0-20250322224806",
-    "@opentui/core": "0.2.10",
-    "@opentui/keymap": "0.2.10",
-    "@opentui/solid": "0.2.10",
+    "@opentui/core": "0.2.11",
+    "@opentui/keymap": "0.2.11",
+    "@opentui/solid": "0.2.11",
    "@pierre/diffs": "1.1.0-beta.18",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.36.0",
@@ -1590,23 +1590,23 @@

    "@opentelemetry/semantic-conventions": ["@opentelemetry/semantic-conventions@1.40.0", "", {}, "sha512-cifvXDhcqMwwTlTK04GBNeIe7yyo28Mfby85QXFe1Yk8nmi36Ab/5UQwptOx84SsoGNRg+EVSjwzfSZMy6pmlw=="],

-    "@opentui/core": ["@opentui/core@0.2.10", "", { "dependencies": { "bun-ffi-structs": "0.2.2", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2", "yoga-layout": "3.2.1" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.2.10", "@opentui/core-darwin-x64": "0.2.10", "@opentui/core-linux-arm64": "0.2.10", "@opentui/core-linux-x64": "0.2.10", "@opentui/core-win32-arm64": "0.2.10", "@opentui/core-win32-x64": "0.2.10" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-oviCtx0jYjc7F8X2b8+0IkQLg6WH47Nwl6CFeZo5dU0k6OpSbTbi07ZleObaiECAp+S1YLhAtVdgzHU7hBZlaw=="],
+    "@opentui/core": ["@opentui/core@0.2.11", "", { "dependencies": { "bun-ffi-structs": "0.2.2", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2", "yoga-layout": "3.2.1" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.2.11", "@opentui/core-darwin-x64": "0.2.11", "@opentui/core-linux-arm64": "0.2.11", "@opentui/core-linux-x64": "0.2.11", "@opentui/core-win32-arm64": "0.2.11", "@opentui/core-win32-x64": "0.2.11" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-X0zLmcDEvMrPzWYp769I7VEVb+og38vaete9tGZXu9HnJgu/paPUUplUT+6denBQccr2qx1rBYV6EtgbBpLEyw=="],

-    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.2.10", "", { "os": "darwin", "cpu": "arm64" }, "sha512-+lbDDj42Og+UtTZEwlHhGXichmOlkxSqn0J+Jqjat5/Tt5oZykj1NZjFIQ7ZSz4Miz7EmZwgYKE2CyOmmm9MoQ=="],
+    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.2.11", "", { "os": "darwin", "cpu": "arm64" }, "sha512-h2MXtE2Cu3XlKVoQMXthnbhleO68zGXkoh/r1Q5pCoZh6RuXqns5/94D/aZThXBWwzPuEoyarMlxxR9OqrpvHw=="],

-    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.2.10", "", { "os": "darwin", "cpu": "x64" }, "sha512-5iAoA0aqMWWAQ93nh8Bb0ipwt9h+tvEFc88+YO9St43uUJ+XrXcmMj3T8wtl6dSu/SN0UoDWNaUMHUmtykiPtg=="],
+    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.2.11", "", { "os": "darwin", "cpu": "x64" }, "sha512-Y0jbPClnOBTPSIy+2THG86MTqIG/jGFlOOKuw4JfCDqEjPBM3pLWIHnJb3WxHRi2LlvfyBxvrUTXWlW6JpI0QQ=="],

-    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.2.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-EnrkxgH5K76Oi/Br1UHPZblXG5P60snmtySfnxuVaeECNZrbTkV6BV/A0WoBeWshJweGbx1D+eTF+sEEjQCi8w=="],
+    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.2.11", "", { "os": "linux", "cpu": "arm64" }, "sha512-blQyyuTaW4q/OQ3whs7Kt7GCXhBUR5EQHHDdjOqQAr0HYpohUa6sbHMbiBcX2Ehc9ZWwtiaOoWiyZ5YXy2SAvg=="],

-    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.2.10", "", { "os": "linux", "cpu": "x64" }, "sha512-fI+r3kCPqIxsWwPVGpKUQy4zHK8y+jkDRCwa3UbaUy48RQ44jMuf2RhVhmi4xmCvSc8UPJBbYsw1tLuh9kmXjg=="],
+    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.2.11", "", { "os": "linux", "cpu": "x64" }, "sha512-0nEB5+MgzQRYiVcQd1vHXPWNPWGh4JEmQTJKyG3OHnTzPaJ1FVSQ/V71ECyRSl3ymY3F+U0eW9cFgw1hCieK2w=="],

-    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.2.10", "", { "os": "win32", "cpu": "arm64" }, "sha512-8F4z2hIRgkVWcr6CMVeJ9N4+1rmURPt2Pq2GBPko8ch6rxHR+a//KD1MfphyuLTHBS1tJ4vfZSWSoiaESImtrA=="],
+    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.2.11", "", { "os": "win32", "cpu": "arm64" }, "sha512-+KKH77fzm0qF8py9G2pU32DzB1bAgDMfBajrs7gKL5NtSEnknrwfh7hIs/tq41aF6j9zvIzgtykByh26tcjFog=="],

-    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.2.10", "", { "os": "win32", "cpu": "x64" }, "sha512-Ki+qNBlIFW5K2wcG/RHrlPp7yEQKXeiNX3mlje25iwX62Ac5w391HBpOmUjbPoq20McPyDRnhbLfbXQSPtickg=="],
+    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.2.11", "", { "os": "win32", "cpu": "x64" }, "sha512-dMmb9DX0W0HWadLdgciMbonqIc1xdcKiVmaQSYxw5eGCzFRPZIOrKHByesP+2ipkMuLx85W/MJUFal/lW8XSNg=="],

-    "@opentui/keymap": ["@opentui/keymap@0.2.10", "", { "dependencies": { "@opentui/core": "0.2.10" }, "peerDependencies": { "@opentui/react": "0.2.10", "@opentui/solid": "0.2.10", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-80fU3Lr/98sNIpVYd8PApAeQw8A8D9BemyOGi6jGvTQCl0rxKgvaVBviDRGKxl1INTVjZy9By8UPncc2KJOuWQ=="],
+    "@opentui/keymap": ["@opentui/keymap@0.2.11", "", { "dependencies": { "@opentui/core": "0.2.11" }, "peerDependencies": { "@opentui/react": "0.2.11", "@opentui/solid": "0.2.11", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-pCrJrY3mTuXdDaaRneId1JsJCtGE+7prTtWihzOLZzVJTJYyYtT38gMI7MpyAoloVDfEL5cTe8C+v7wv+IYREw=="],

-    "@opentui/solid": ["@opentui/solid@0.2.10", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.2.10", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-+4/MB90yIQiPwg8Y4wY092yva9BvRTsJeeeEO3e2H7P8k8zxYk4G9bzuhqYLxA9mTVQ+zVDlrmFoPQhT7vpIRw=="],
+    "@opentui/solid": ["@opentui/solid@0.2.11", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.2.11", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-M3WHxBFORHVE0yqMJYpi9PfjXWlnRTw/LYuBhZaJv0HTo+zTs60P/ukGcwnHDWnMpTGf3BH9x0Yi2dIqjHRY6Q=="],

    "@oslojs/asn1": ["@oslojs/asn1@1.0.0", "", { "dependencies": { "@oslojs/binary": "1.0.0" } }, "sha512-zw/wn0sj0j0QKbIXfIlnEcTviaCzYOY3V5rAyjR6YtOByFtJiT574+8p9Wlach0lZH9fddD4yb9laEAIl4vXQA=="],

@@ -37,16 +37,14 @@
            node_modules = final.callPackage ./nix/node_modules.nix {
              inherit rev;
            };
+          in
+          rec {
            opencode = final.callPackage ./nix/opencode.nix {
              inherit node_modules;
            };
-            desktop = final.callPackage ./nix/desktop.nix {
+            opencode-desktop = final.callPackage ./nix/desktop.nix {
              inherit opencode;
            };
-          in
-          {
-            inherit opencode;
-            opencode-desktop = desktop;
          };
      };

@@ -56,16 +54,15 @@
          node_modules = pkgs.callPackage ./nix/node_modules.nix {
            inherit rev;
          };
+        in
+        rec {
+          default = opencode;
          opencode = pkgs.callPackage ./nix/opencode.nix {
            inherit node_modules;
          };
-          desktop = pkgs.callPackage ./nix/desktop.nix {
+          opencode-desktop = pkgs.callPackage ./nix/desktop.nix {
            inherit opencode;
          };
-        in
-        {
-          default = opencode;
-          inherit opencode desktop;
          # Updater derivation with fakeHash - build fails and reveals correct hash
          node_modules_updater = node_modules.override {
            hash = pkgs.lib.fakeHash;
@@ -46,10 +46,24 @@ const modelHttpErrorsQuery = (product: "go" | "zen") => {
  ]
  const failedHttpStatus = calculatedField({
    name: "is_failed_http_status",
-    expression:
-      product === "go"
-        ? `IF(AND(GTE($status, "400"), NOT(EQUALS($status, "401")), NOT(EQUALS($status, "429"))), 1, 0)`
-        : `IF(AND(EQUALS($status, "429"), $isFreeTier), 0, AND(GTE($status, "400"), NOT(EQUALS($status, "401"))), 1, 0)`,
+    expression: `
+IF(
+  AND(
+    GTE($status, "400"),
+    NOT(EQUALS($status, "401")),
+    NOT(
+      AND(
+        EQUALS($status, "429"),
+        OR(
+          EQUALS($error.type, "GoUsageLimitError"),
+          EQUALS($error.type, "FreeUsageLimitError")
+        )
+      )
+    )
+  ),
+  1,
+  0
+)`,
  })

  return honeycomb.getQuerySpecificationOutput({
@@ -65,7 +79,7 @@ const modelHttpErrorsQuery = (product: "go" | "zen") => {
        filters,
      },
    ],
-    formulas: [{ name: "ERROR", expression: "IF(GTE($TOTAL, 100), DIV($FAILED, $TOTAL), 0)" }],
+    formulas: [{ name: "ERROR", expression: "IF(GTE($TOTAL, 200), DIV($FAILED, $TOTAL), 0)" }],
    timeRange: 900,
  }).json
 }
@@ -1,100 +1,101 @@
 {
  lib,
  stdenv,
-  rustPlatform,
-  pkg-config,
-  cargo-tauri,
  bun,
  nodejs,
-  cargo,
-  rustc,
-  jq,
-  wrapGAppsHook4,
+  electron_41,
  makeWrapper,
-  dbus,
-  glib,
-  gtk4,
-  libsoup_3,
-  librsvg,
-  libappindicator,
-  glib-networking,
-  openssl,
-  webkitgtk_4_1,
-  gst_all_1,
+  writableTmpDirAsHomeHook,
+  autoPatchelfHook,
  opencode,
 }:
-rustPlatform.buildRustPackage (finalAttrs: {
+let
+  electron = electron_41;
+in
+stdenv.mkDerivation (finalAttrs: {
  pname = "opencode-desktop";
-  inherit (opencode)
-    version
-    src
-    node_modules
-    patches
-    ;
-
-  cargoRoot = "packages/desktop/src-tauri";
-  cargoLock.lockFile = ../packages/desktop/src-tauri/Cargo.lock;
-  buildAndTestSubdir = finalAttrs.cargoRoot;
+  inherit (opencode) version src node_modules;

  nativeBuildInputs = [
-    pkg-config
-    cargo-tauri.hook
    bun
-    nodejs # for patchShebangs node_modules
-    cargo
-    rustc
-    jq
+    nodejs
    makeWrapper
-  ] ++ lib.optionals stdenv.hostPlatform.isLinux [ wrapGAppsHook4 ];
-
-  buildInputs = lib.optionals stdenv.isLinux [
-    dbus
-    glib
-    gtk4
-    libsoup_3
-    librsvg
-    libappindicator
-    glib-networking
-    openssl
-    webkitgtk_4_1
-    gst_all_1.gstreamer
-    gst_all_1.gst-plugins-base
-    gst_all_1.gst-plugins-good
-    gst_all_1.gst-plugins-bad
+    writableTmpDirAsHomeHook
+  ] ++ lib.optionals stdenv.hostPlatform.isLinux [
+    autoPatchelfHook
  ];

-  strictDeps = true;
+  buildInputs = lib.optionals stdenv.hostPlatform.isLinux [
+    (lib.getLib stdenv.cc.cc)
+  ];
+
+  env = opencode.env // {
+    ELECTRON_SKIP_BINARY_DOWNLOAD = "1";
+  };
+
+  # https://github.com/electron/electron/issues/31121
+  # mac builds use a .app bundle which doesnt have this issue
+  postPatch = lib.optionalString stdenv.isLinux ''
+    BASE_PATH=packages/desktop
+    FILES=(src/main/windows.ts)
+    for file in "''${FILES[@]}"; do
+      substituteInPlace $BASE_PATH/$file \
+        --replace-fail "process.resourcesPath" "'$out/opt/opencode-desktop/resources'"
+    done
+  '';

  preBuild = ''
-    cp -a ${finalAttrs.node_modules}/{node_modules,packages} .
-    chmod -R u+w node_modules packages
+    cp -r "${electron.dist}" $HOME/.electron-dist
+    chmod -R u+w $HOME/.electron-dist
+
+    cp -R ${finalAttrs.node_modules}/. .
    patchShebangs node_modules
-    patchShebangs packages/desktop/node_modules
-
-    mkdir -p packages/desktop/src-tauri/sidecars
-    cp ${opencode}/bin/opencode packages/desktop/src-tauri/sidecars/opencode-cli-${stdenv.hostPlatform.rust.rustcTarget}
+    patchShebangs packages/*/node_modules
  '';

-  # see publish-tauri job in .github/workflows/publish.yml
-  tauriBuildFlags = [
-    "--config"
-    "tauri.prod.conf.json"
-    "--no-sign" # no code signing or auto updates
+  buildPhase = ''
+    runHook preBuild
+
+    cd packages/desktop
+
+    bun run build
+    npx electron-builder --dir \
+      --config electron-builder.config.ts \
+      --config.mac.identity=null \
+      --config.electronDist="$HOME/.electron-dist"
+
+    runHook postBuild
+  '';
+
+  installPhase =
+    ''
+      runHook preInstall
+    ''
+    + lib.optionalString stdenv.hostPlatform.isDarwin ''
+      mkdir -p $out/Applications
+      mv dist/mac*/*.app $out/Applications
+      makeWrapper "$out/Applications/OpenCode.app/Contents/MacOS/OpenCode" $out/bin/opencode-desktop
+    ''
+    + lib.optionalString stdenv.hostPlatform.isLinux ''
+      mkdir -p $out/opt/opencode-desktop
+      cp -r dist/linux*-unpacked/{resources,LICENSE*} $out/opt/opencode-desktop
+      makeWrapper ${lib.getExe electron} $out/bin/opencode-desktop \
+        --inherit-argv0 \
+        --set ELECTRON_FORCE_IS_PACKAGED 1 \
+        --add-flags $out/opt/opencode-desktop/resources/app.asar \
+        --add-flags "\''${NIXOS_OZONE_WL:+\''${WAYLAND_DISPLAY:+--ozone-platform-hint=auto --enable-features=WaylandWindowDecorations --enable-wayland-ime=true}}"
+    ''
+    + ''
+      runHook postInstall
+    '';
+
+  autoPatchelfIgnoreMissingDeps = [
+    "libc.musl-x86_64.so.1"
  ];

-  # FIXME: workaround for concerns about case insensitive filesystems
-  # should be removed once binary is renamed or decided otherwise
-  # darwin output is a .app bundle so no conflict
-  postFixup = lib.optionalString stdenv.hostPlatform.isLinux ''
-    mv $out/bin/OpenCode $out/bin/opencode-desktop
-    sed -i 's|^Exec=OpenCode$|Exec=opencode-desktop|' $out/share/applications/OpenCode.desktop
-  '';
-
  meta = {
    description = "OpenCode Desktop App";
-    homepage = "https://opencode.ai";
-    license = lib.licenses.mit;
    mainProgram = "opencode-desktop";
-    inherit (opencode.meta) platforms;
+    inherit (opencode.meta) homepage license platforms;
  };
 })
@@ -1,8 +1,8 @@
 {
  "nodeModules": {
-    "x86_64-linux": "sha256-Hw7sVV9rTm6qBMtdwfLIV2QvxvLQY5qrywXzuyYbhcs=",
-    "aarch64-linux": "sha256-++oXnY7YqrYt0Qv7ZISmoHliARM9qEP8FacqLxGZH1c=",
-    "aarch64-darwin": "sha256-kZVa0R1YbuvtTzpETqK6ddj4ISje5jBFHBdlynkhW7Q=",
-    "x86_64-darwin": "sha256-94eagNDa8GGJxF8BsMX2BF5Pa+QTl48lXL1+6HgEn0I="
+    "x86_64-linux": "sha256-Ucvyzyq+oYvWglkeowSvb0LgDzkAvaSdq0CdA6jgN6U=",
+    "aarch64-linux": "sha256-SERwZvvN6P8/OwNolHmC0KU9H5laVQm+FD/NNKauZA8=",
+    "aarch64-darwin": "sha256-I1ABwMHkTAntlYyg43w0cW8iPYfZa9MT0In2C7plB5g=",
+    "x86_64-darwin": "sha256-degJTL0RG7QQO8/USgIF//ya7oNmwChTmAoJcpXbIp0="
  }
 }
@@ -40,7 +40,7 @@ stdenvNoCC.mkDerivation (finalAttrs: {
  env.MODELS_DEV_API_JSON = "${models-dev}/dist/_api.json";
  env.OPENCODE_DISABLE_MODELS_FETCH = true;
  env.OPENCODE_VERSION = finalAttrs.version;
-  env.OPENCODE_CHANNEL = "local";
+  env.OPENCODE_CHANNEL = "prod";

  buildPhase = ''
    runHook preBuild
@@ -89,11 +89,12 @@ stdenvNoCC.mkDerivation (finalAttrs: {

  passthru = {
    jsonschema = "${placeholder "out"}/share/opencode/schema.json";
+    env = finalAttrs.env;
  };

  meta = {
    description = "The open source coding agent";
-    homepage = "https://opencode.ai/";
+    homepage = "https://opencode.ai";
    license = lib.licenses.mit;
    mainProgram = "opencode";
    inherit (node_modules.meta) platforms;
@@ -35,9 +35,9 @@
      "@types/cross-spawn": "6.0.6",
      "@octokit/rest": "22.0.0",
      "@hono/zod-validator": "0.4.2",
-      "@opentui/core": "0.2.10",
-      "@opentui/keymap": "0.2.10",
-      "@opentui/solid": "0.2.10",
+      "@opentui/core": "0.2.11",
+      "@opentui/keymap": "0.2.11",
+      "@opentui/solid": "0.2.11",
      "ulid": "3.0.1",
      "@kobalte/core": "0.13.11",
      "@types/luxon": "3.7.1",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/app",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "description": "",
  "type": "module",
  "exports": {
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/console-app",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -161,7 +161,9 @@ export async function POST(input: APIEvent) {
            })

            if (userEmail) {
-              if (coupon === LiteData.firstMonth100Coupon) {
+              if (coupon === LiteData.firstMonth50Coupon) {
+                await Billing.redeemCoupon(userEmail, "GO1MONTH50")
+              } else if (coupon === LiteData.firstMonth100Coupon) {
                await Billing.redeemCoupon(userEmail, "GOFREEMONTH")
              } else if (coupon === LiteData.threeMonths100Coupon) {
                await Billing.redeemCoupon(userEmail, "GO3MONTHS100")
@@ -10,8 +10,11 @@ export function createRateLimiter(modelId: string, rateLimit: number | undefined
  const dict = i18n(localeFromRequest(request))

  const limits = Subscription.getFreeLimits()
-  const dailyLimit = rateLimit ?? limits.dailyRequests
-  const isDefaultModel = !rateLimit
+  const headersExist = Object.entries(limits.checkHeaders).every(
+    ([name, value]) => request.headers.get(name)?.toLowerCase().includes(value) ?? false,
+  )
+  const dailyLimit = !headersExist ? limits.dailyRequestsFallback : (rateLimit ?? limits.dailyRequests)
+  const isDefaultModel = headersExist && !rateLimit

  const ip = !rawIp.length ? "unknown" : rawIp
  const now = Date.now()
@@ -0,0 +1 @@
+ALTER TABLE `coupon` MODIFY COLUMN `type` enum('BUILDATHON','GO1MONTH50','GOFREEMONTH','GO3MONTHS100','GO6MONTHS100','GO12MONTHS100') NOT NULL;
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode-ai/console-core",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -10,7 +10,7 @@ if (!stage) throw new Error("Stage is required")
 const root = path.resolve(process.cwd(), "..", "..", "..")

 // read the secret
-const ret = await $`bun sst secret list --stage frank`.cwd(root).text()
+const ret = await $`bun sst secret list --fallback`.cwd(root).text()
 const lines = ret.split("\n")
 const value = lines.find((line) => line.startsWith("ZEN_LIMITS"))?.split("=")[1]
 if (!value) throw new Error("ZEN_LIMITS not found")
@@ -6,7 +6,7 @@ import os from "os"
 import { Subscription } from "../src/subscription"

 const root = path.resolve(process.cwd(), "..", "..", "..")
-const secrets = await $`bun sst secret list --stage frank`.cwd(root).text()
+const secrets = await $`bun sst secret list --fallback`.cwd(root).text()

 // read value
 const lines = secrets.split("\n")
@@ -25,4 +25,6 @@ const newValue = JSON.stringify(JSON.parse(await tempFile.text()))
 Subscription.validate(JSON.parse(newValue))

 // update the secret
-await $`bun sst secret set ZEN_LIMITS ${newValue} --stage frank`.cwd(root)
+const envFile = Bun.file(path.join(os.tmpdir(), `limits-${Date.now()}.env`))
+await envFile.write(`ZEN_LIMITS="${newValue.replace(/"/g, '\\"')}"`)
+await $`bun sst secret load ${envFile.name} --fallback`.cwd(root)
@@ -156,33 +156,32 @@ export namespace Billing {
  }

  export const redeemCoupon = async (email: string, type: (typeof CouponType)[number]) => {
-    const coupon = await Database.use((tx) =>
-      tx
-        .select()
-        .from(CouponTable)
-        .where(and(eq(CouponTable.email, email), eq(CouponTable.type, type)))
-        .then((rows) => rows[0]),
-    )
-    if (!coupon) throw new Error("Invalid coupon code")
-    if (coupon.timeRedeemed) throw new Error("Coupon already redeemed")
+    // validate coupon type
+    await (async () => {
+      if (type === "GO1MONTH50") return
+      const coupon = await Database.use((tx) =>
+        tx
+          .select()
+          .from(CouponTable)
+          .where(and(eq(CouponTable.email, email), eq(CouponTable.type, type)))
+          .then((rows) => rows[0]),
+      )
+      if (!coupon) throw new Error("Invalid coupon code")
+      if (coupon.timeRedeemed) throw new Error("Coupon already redeemed")
+    })()

+    // handle coupon type
    if (type === "BUILDATHON") await grantCredit(Actor.workspace(), 500)

    await Database.use((tx) =>
      tx
-        .update(CouponTable)
-        .set({ timeRedeemed: sql`now()` })
-        .where(and(eq(CouponTable.email, email), eq(CouponTable.type, type))),
-    )
-  }
-
-  export const getCoupons = async (email: string) => {
-    return await Database.use((tx) =>
-      tx
-        .select({ type: CouponTable.type, timeRedeemed: CouponTable.timeRedeemed })
-        .from(CouponTable)
-        .where(and(eq(CouponTable.email, email), isNull(CouponTable.timeRedeemed)))
-        .then((rows) => rows.map((row) => row.type)),
+        .insert(CouponTable)
+        .values({ email, type, timeRedeemed: sql`now()` })
+        .onDuplicateKeyUpdate({
+          set: {
+            timeRedeemed: sql`now()`,
+          },
+        }),
    )
  }

@@ -290,20 +289,29 @@ export namespace Billing {
      if (billing.subscriptionID) throw new Error("Already subscribed to Black")
      if (billing.liteSubscriptionID) throw new Error("Already subscribed to Lite")

-      const coupons = await Billing.getCoupons(email)
-      const coupon = coupons.includes("GO12MONTHS100")
-        ? LiteData.twelveMonths100Coupon
-        : coupons.includes("GO6MONTHS100")
-          ? LiteData.sixMonths100Coupon
-          : coupons.includes("GO3MONTHS100")
-            ? LiteData.threeMonths100Coupon
-            : coupons.includes("GOFREEMONTH")
-              ? LiteData.firstMonth100Coupon
-              : LiteData.firstMonth50Coupon
+      const coupons = await Database.use((tx) =>
+        tx
+          .select({ type: CouponTable.type, timeRedeemed: CouponTable.timeRedeemed })
+          .from(CouponTable)
+          .where(eq(CouponTable.email, email)),
+      )
+
+      const coupon = (() => {
+        if (coupons.some((coupon) => coupon.type === "GO12MONTHS100" && !coupon.timeRedeemed))
+          return LiteData.twelveMonths100Coupon
+        if (coupons.some((coupon) => coupon.type === "GO6MONTHS100" && !coupon.timeRedeemed))
+          return LiteData.sixMonths100Coupon
+        if (coupons.some((coupon) => coupon.type === "GO3MONTHS100" && !coupon.timeRedeemed))
+          return LiteData.threeMonths100Coupon
+        if (coupons.some((coupon) => coupon.type === "GOFREEMONTH" && !coupon.timeRedeemed))
+          return LiteData.firstMonth100Coupon
+        if (!coupons.some((coupon) => coupon.type === "GO1MONTH50")) return LiteData.firstMonth50Coupon
+        return undefined
+      })()
      const createSession = () =>
        Billing.stripe().checkout.sessions.create({
          mode: "subscription",
-          discounts: [{ coupon }],
+          discounts: coupon ? [{ coupon }] : undefined,
          ...(billing.customerID
            ? {
                customer: billing.customerID,
@@ -133,7 +133,14 @@ export const UsageTable = mysqlTable(
  (table) => [...workspaceIndexes(table), index("usage_time_created").on(table.workspaceID, table.timeCreated)],
 )

-export const CouponType = ["BUILDATHON", "GOFREEMONTH", "GO3MONTHS100", "GO6MONTHS100", "GO12MONTHS100"] as const
+export const CouponType = [
+  "BUILDATHON",
+  "GO1MONTH50",
+  "GOFREEMONTH",
+  "GO3MONTHS100",
+  "GO6MONTHS100",
+  "GO12MONTHS100",
+] as const
 export const CouponTable = mysqlTable(
  "coupon",
  {
@@ -9,6 +9,8 @@ export namespace Subscription {
    free: z.object({
      promoTokens: z.number().int(),
      dailyRequests: z.number().int(),
+      dailyRequestsFallback: z.number().int(),
+      checkHeaders: z.record(z.string(), z.string()),
    }),
    lite: z.object({
      rollingLimit: z.number().int(),
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/console-function",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "$schema": "https://json.schemastore.org/package.json",
  "private": true,
  "type": "module",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/console-mail",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "dependencies": {
    "@jsx-email/all": "2.2.3",
    "@jsx-email/cli": "1.4.3",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "name": "@opencode-ai/core",
  "type": "module",
  "license": "MIT",
@@ -38,7 +38,6 @@ export const Flag = {
  ),
  OPENCODE_EXPERIMENTAL_DISABLE_COPY_ON_SELECT:
    copy === undefined ? process.platform === "win32" : truthy("OPENCODE_EXPERIMENTAL_DISABLE_COPY_ON_SELECT"),
-  OPENCODE_EXPERIMENTAL_MINIMAL_THINKING: truthy("OPENCODE_EXPERIMENTAL_MINIMAL_THINKING"),
  OPENCODE_MODELS_URL: process.env["OPENCODE_MODELS_URL"],
  OPENCODE_MODELS_PATH: process.env["OPENCODE_MODELS_PATH"],
  OPENCODE_DB: process.env["OPENCODE_DB"],
@@ -1,7 +1,7 @@
 {
  "name": "@opencode-ai/desktop",
  "private": true,
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "homepage": "https://opencode.ai",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/enterprise",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 id = "opencode"
 name = "OpenCode"
 description = "The open source coding agent."
-version = "1.15.0"
+version = "1.15.4"
 schema_version = 1
 authors = ["Anomaly"]
 repository = "https://github.com/anomalyco/opencode"
@@ -11,26 +11,26 @@ name = "OpenCode"
 icon = "./icons/opencode.svg"

 [agent_servers.opencode.targets.darwin-aarch64]
-archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.0/opencode-darwin-arm64.zip"
+archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.4/opencode-darwin-arm64.zip"
 cmd = "./opencode"
 args = ["acp"]

 [agent_servers.opencode.targets.darwin-x86_64]
-archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.0/opencode-darwin-x64.zip"
+archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.4/opencode-darwin-x64.zip"
 cmd = "./opencode"
 args = ["acp"]

 [agent_servers.opencode.targets.linux-aarch64]
-archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.0/opencode-linux-arm64.tar.gz"
+archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.4/opencode-linux-arm64.tar.gz"
 cmd = "./opencode"
 args = ["acp"]

 [agent_servers.opencode.targets.linux-x86_64]
-archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.0/opencode-linux-x64.tar.gz"
+archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.4/opencode-linux-x64.tar.gz"
 cmd = "./opencode"
 args = ["acp"]

 [agent_servers.opencode.targets.windows-x86_64]
-archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.0/opencode-windows-x64.zip"
+archive = "https://github.com/anomalyco/opencode/releases/download/v1.15.4/opencode-windows-x64.zip"
 cmd = "./opencode.exe"
 args = ["acp"]
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/function",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "$schema": "https://json.schemastore.org/package.json",
  "private": true,
  "type": "module",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "name": "@opencode-ai/http-recorder",
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "name": "@opencode-ai/llm",
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "name": "opencode",
  "type": "module",
  "license": "MIT",
@@ -37,9 +37,16 @@ await $`cp ./script/postinstall.mjs ./dist/${pkg.name}/postinstall.mjs`
 await Bun.file(`./dist/${pkg.name}/LICENSE`).write(await Bun.file("../../LICENSE").text())
 await Bun.file(`./dist/${pkg.name}/bin/${pkg.name}.exe`).write(
  [
-    "#!/usr/bin/env node",
-    "console.error('The opencode native binary was not installed. Run `node postinstall.mjs` from the opencode-ai package directory to finish setup.')",
-    "process.exit(1)",
+    `echo "Error: ${pkg.name}-ai's postinstall script was not run." >&2`,
+    'echo "" >&2',
+    'echo "This occurs when using --ignore-scripts during installation, or when using a" >&2',
+    'echo "package manager like pnpm that does not run postinstall scripts by default." >&2',
+    'echo "" >&2',
+    'echo "To fix this, run the postinstall script manually:" >&2',
+    `echo "  cd node_modules/${pkg.name}-ai && node postinstall.mjs" >&2`,
+    'echo "" >&2',
+    `echo "Or reinstall ${pkg.name}-ai without the --ignore-scripts flag." >&2`,
+    "exit 1",
    "",
  ].join("\n"),
 )
@@ -70,11 +70,54 @@ Endpoint definitions declare which public errors can be emitted. Public
 HTTP error schemas carry their response status with `httpApiStatus` or the
 equivalent HttpApi schema annotation.

+Effect's own HttpApi examples follow this pattern:
+
+```ts
+export class Unauthorized extends Schema.TaggedErrorClass<Unauthorized>()(
+  "Unauthorized",
+  { message: Schema.String },
+  { httpApiStatus: 401 },
+) {}
+
+export class Authorization extends HttpApiMiddleware.Service<
+  Authorization,
+  {
+    provides: CurrentUser
+  }
+>()("app/Authorization", {
+  security: { bearer: HttpApiSecurity.bearer },
+  error: Unauthorized,
+}) {}
+```
+
+Endpoint-level errors use the same idea:
+
+```ts
+export class ConfigApiError extends Schema.ErrorClass<ConfigApiError>("ConfigApiError")(
+  {
+    name: Schema.Union(Schema.Literal("ConfigInvalidError"), Schema.Literal("ConfigJsonError")),
+    data: Schema.Struct({ message: Schema.optional(Schema.String), path: Schema.String }),
+  },
+  { httpApiStatus: 400 },
+) {}
+
+HttpApiEndpoint.get("get", "/config", {
+  success: Config.Info,
+  error: ConfigApiError,
+})
+```
+
 The service error and HTTP error may be the same class only when the wire
 shape is intentionally public. Use separate HTTP error schemas when the
 service error contains internals, low-level causes, retry hints, or data
 that should not be exposed to API clients.

+Do not map every domain error into one universal HTTP error class. Prefer a
+small public error vocabulary by route group: shared shapes like
+`ApiNotFoundError`, route-specific shapes like `ConfigApiError`, and built-in
+empty `HttpApiError.*` only when an empty/no-content body is the intended SDK
+contract.
+
 ## Mapping Guidance

 - Keep one-off translations inline in the handler.
@@ -86,6 +129,35 @@ that should not be exposed to API clients.
  breaking API change.
 - Use built-in `HttpApiError.*` only when its generated body and SDK
  surface are intentionally the public contract.
+- Prefer `Schema.ErrorClass` for public HTTP error bodies whose wire shape is
+  not the same as the internal domain error shape.
+- Prefer `Schema.TaggedErrorClass` for service/domain errors and middleware
+  errors that are naturally tagged by `_tag`.
+- If preserving a legacy `{ name, data }` body, model that shape explicitly in
+  the public API error schema instead of relying on `NamedError.toObject()` in
+  generic middleware.
+
+## User-Facing Rendering
+
+HTTP serialization and user rendering are separate boundaries. The server
+should send structured public errors; CLI and TUI code should format those
+structures through one shared formatter.
+
+For SDK calls using `{ throwOnError: true }`, the generated client may wrap the
+decoded response body in an `Error`. The original body should remain available
+under `error.cause.body`; `FormatError` is the right place to unwrap and render
+that body. TUI aggregation helpers should call `FormatError` first, then fall
+back to generic `Error.message` / string rendering.
+
+When several parallel startup requests fail from the same underlying issue,
+group identical rendered messages and list the affected request names once.
+For example:
+
+```text
+Configuration is invalid at /path/to/opencode.json
+↳ Expected object, got "not-object" provider.bad.options
+Affected startup requests: config.providers, provider.list, app.agents, config.get
+```

 ## Middleware Guidance

@@ -99,6 +171,15 @@ middleware should shrink. It should not gain new name checks.
 Unknown `500` responses should log full details server-side with
 `Cause.pretty(cause)` and return a safe public body.

+The config startup regression in #27056 is the failure mode this rule is meant
+to avoid: a user-authored invalid `opencode.json` crossed the HttpApi boundary
+as a defect, so middleware replaced a useful `ConfigInvalidError` with a safe
+generic `UnknownError`. The compatibility fix is to preserve config parse and
+validation errors as client-visible `400`s. The target architecture is better:
+config loading should fail on the typed error channel, config HTTP handlers
+should map those errors to declared `ConfigApiError` responses, and the generic
+middleware should never see them.
+
 ## Migration Order

 Prefer small vertical slices:
@@ -113,6 +194,9 @@ Prefer small vertical slices:
 Good early domains are storage not-found, worktree errors, and provider
 auth validation errors because they currently drive HTTP behavior.

+Config parse and validation errors are also a good early slice because they
+are startup-blocking and must be rendered clearly in both CLI and TUI flows.
+
 ## Checklist For A PR

 - [ ] Expected failures are typed errors, not defects.
@@ -6,6 +6,8 @@ import { GlobalBus } from "./global"
 import { InstanceState } from "@/effect/instance-state"
 import { makeRuntime } from "@/effect/run-service"
 import { Identifier } from "@/id/id"
+import type { InstanceContext } from "@/project/instance-context"
+import { InstanceRef } from "@/effect/instance-ref"

 const log = Log.create({ service: "bus" })

@@ -185,11 +187,12 @@ export function createID() {
 }

 export async function publish<D extends BusEvent.Definition>(
+  ctx: InstanceContext,
  def: D,
  properties: BusProperties<D>,
  options?: { id?: string },
 ) {
-  return runPromise((svc) => svc.publish(def, properties, options))
+  return runPromise((svc) => svc.publish(def, properties, options).pipe(Effect.provideService(InstanceRef, ctx)))
 }

 export function subscribe<D extends BusEvent.Definition>(def: D, callback: (event: Payload<D>) => unknown) {
@@ -66,6 +66,8 @@ const AgentCreateCommand = effectCmd({
    if (!maybeCtx) return yield* Effect.die("InstanceRef not provided")
    const ctx = maybeCtx
    const agentSvc = yield* Agent.Service
+    const runLocalEffect = <A, E>(effect: Effect.Effect<A, E>) =>
+      Effect.runPromise(effect.pipe(Effect.provideService(InstanceRef, ctx)))
    yield* Effect.promise(async () => {
      const cliPath = args.path
      const cliDescription = args.description
@@ -127,7 +129,7 @@ const AgentCreateCommand = effectCmd({
      const spinner = prompts.spinner()
      spinner.start("Generating agent configuration...")
      const model = args.model ? Provider.parseModel(args.model) : undefined
-      const generated = await Effect.runPromise(agentSvc.generate({ description, model })).catch((error) => {
+      const generated = await runLocalEffect(agentSvc.generate({ description, model })).catch((error) => {
        spinner.stop(`LLM failed to generate agent: ${error.message}`, 1)
        if (isFullyNonInteractive) process.exit(1)
        throw new UI.CancelledError()
@@ -435,6 +435,9 @@ export const GithubRunCommand = effectCmd({
    const sessionSvc = yield* Session.Service
    const sessionShare = yield* SessionShare.Service
    const sessionPrompt = yield* SessionPrompt.Service
+    const busSvc = yield* Bus.Service
+    const runLocalEffect = <A, E>(effect: Effect.Effect<A, E>) =>
+      Effect.runPromise(effect.pipe(Effect.provideService(InstanceRef, ctx)))
    yield* Effect.promise(async () => {
      const isMock = args.token || args.event

@@ -548,7 +551,7 @@ export const GithubRunCommand = effectCmd({

        // Setup opencode session
        const repoData = await fetchRepo()
-        session = await Effect.runPromise(
+        session = await runLocalEffect(
          sessionSvc.create({
            permission: [
              {
@@ -559,11 +562,11 @@ export const GithubRunCommand = effectCmd({
            ],
          }),
        )
-        subscribeSessionEvents()
+        await subscribeSessionEvents()
        shareId = await (async () => {
          if (share === false) return
          if (!share && repoData.data.private) return
-          await Effect.runPromise(sessionShare.share(session.id))
+          await runLocalEffect(sessionShare.share(session.id))
          return session.id.slice(-8)
        })()
        console.log("opencode session", session.id)
@@ -870,7 +873,7 @@ export const GithubRunCommand = effectCmd({
        return { userPrompt: prompt, promptFiles: imgData }
      }

-      function subscribeSessionEvents() {
+      async function subscribeSessionEvents() {
        const TOOL: Record<string, [string, string]> = {
          todowrite: ["Todo", UI.Style.TEXT_WARNING_BOLD],
          bash: ["Shell", UI.Style.TEXT_DANGER_BOLD],
@@ -893,33 +896,35 @@ export const GithubRunCommand = effectCmd({
        }

        let text = ""
-        Bus.subscribe(MessageV2.Event.PartUpdated, (evt) => {
-          if (evt.properties.part.sessionID !== session.id) return
-          //if (evt.properties.part.messageID === messageID) return
-          const part = evt.properties.part
+        await runLocalEffect(
+          busSvc.subscribeCallback(MessageV2.Event.PartUpdated, (evt) => {
+            if (evt.properties.part.sessionID !== session.id) return
+            //if (evt.properties.part.messageID === messageID) return
+            const part = evt.properties.part

-          if (part.type === "tool" && part.state.status === "completed") {
-            const [tool, color] = TOOL[part.tool] ?? [part.tool, UI.Style.TEXT_INFO_BOLD]
-            const title =
-              part.state.title || Object.keys(part.state.input).length > 0
-                ? JSON.stringify(part.state.input)
-                : "Unknown"
-            console.log()
-            printEvent(color, tool, title)
-          }
-
-          if (part.type === "text") {
-            text = part.text
-
-            if (part.time?.end) {
-              UI.empty()
-              UI.println(UI.markdown(text))
-              UI.empty()
-              text = ""
-              return
+            if (part.type === "tool" && part.state.status === "completed") {
+              const [tool, color] = TOOL[part.tool] ?? [part.tool, UI.Style.TEXT_INFO_BOLD]
+              const title =
+                part.state.title || Object.keys(part.state.input).length > 0
+                  ? JSON.stringify(part.state.input)
+                  : "Unknown"
+              console.log()
+              printEvent(color, tool, title)
            }
-          }
-        })
+
+            if (part.type === "text") {
+              text = part.text
+
+              if (part.time?.end) {
+                UI.empty()
+                UI.println(UI.markdown(text))
+                UI.empty()
+                text = ""
+                return
+              }
+            }
+          }),
+        )
      }

      async function summarize(response: string) {
@@ -936,7 +941,7 @@ export const GithubRunCommand = effectCmd({
      async function chat(message: string, files: PromptFiles = []) {
        console.log("Sending message to opencode...")

-        return Effect.runPromise(
+        return runLocalEffect(
          Effect.gen(function* () {
            const prompt = sessionPrompt
            const result = yield* prompt.prompt({
@@ -24,6 +24,7 @@ import { createOpencodeClient, type OpencodeClient, type ToolPart } from "@openc
 import { Agent } from "@/agent/agent"
 import { Permission } from "@/permission"
 import { RuntimeFlags } from "@/effect/runtime-flags"
+import { InstanceRef } from "@/effect/instance-ref"
 import { FormatError, FormatUnknownError } from "../error"
 import { INTERACTIVE_INPUT_ERROR, resolveInteractiveStdin } from "./run/runtime.stdin"

@@ -236,6 +237,7 @@ export const RunCommand = effectCmd({
  handler: Effect.fn("Cli.run")(function* (args) {
    const agentSvc = yield* Agent.Service
    const flags = yield* RuntimeFlags.Service
+    const localInstance = yield* InstanceRef
    yield* Effect.promise(async () => {
      const rawMessage = [...args.message, ...(args["--"] || [])].join(" ")
      const thinking = args.interactive ? (args.thinking ?? true) : (args.thinking ?? false)
@@ -508,7 +510,9 @@ export const RunCommand = effectCmd({
        if (!args.agent) return undefined
        const name = args.agent

-        const entry = await Effect.runPromise(agentSvc.get(name))
+        const entry = await Effect.runPromise(
+          agentSvc.get(name).pipe(Effect.provideService(InstanceRef, localInstance)),
+        )
        if (!entry) {
          UI.println(
            UI.Style.TEXT_WARNING_BOLD + "!",
@@ -859,6 +859,7 @@ function App(props: { onSnapshot?: () => Promise<string[]> }) {
  })

  event.on("installation.update-available", async (evt) => {
+    console.log("installation.update-available", evt)
    const version = evt.properties.version

    const skipped = kv.get("skipped_version")
@@ -27,6 +27,11 @@ export type PromptInfo = {

 const MAX_HISTORY_ENTRIES = 50

+export function isDuplicateEntry(previous: PromptInfo | undefined, next: PromptInfo): boolean {
+  if (!previous) return false
+  return JSON.stringify(previous) === JSON.stringify(next)
+}
+
 export const { use: usePromptHistory, provider: PromptHistoryProvider } = createSimpleContext({
  name: "PromptHistory",
  init: () => {
@@ -83,6 +88,10 @@ export const { use: usePromptHistory, provider: PromptHistoryProvider } = create
      },
      append(item: PromptInfo) {
        const entry = structuredClone(unwrap(item))
+        if (isDuplicateEntry(store.history.at(-1), entry)) {
+          setStore("index", 0)
+          return
+        }
        let trimmed = false
        setStore(
          produce((draft) => {
@@ -1,3 +1,5 @@
+import { FormatError } from "@/cli/error"
+
 /**
 * Aggregate Promise.allSettled results into a single Error that names every
 * failed endpoint, or return null when all fulfilled. Used at TUI bootstrap
@@ -15,7 +17,19 @@ export function aggregateFailures(labeled: LabeledSettled[]): Error | null {
  )
  if (failed.length === 0) return null

-  const reasons = failed.map((f) => `${f.name}: ${reasonMessage(f.result.reason)}`).join("; ")
+  const reasons = Array.from(
+    failed
+      .map((f) => ({ name: f.name, message: reasonMessage(f.result.reason) }))
+      .reduce((grouped, failure) => {
+        grouped.set(failure.message, [...(grouped.get(failure.message) ?? []), failure.name])
+        return grouped
+      }, new Map<string, string[]>())
+      .entries(),
+  )
+    .map(([message, names]) =>
+      names.length === 1 ? `${names[0]}: ${message}` : `${message}\nAffected startup requests: ${names.join(", ")}`,
+    )
+    .join("; ")
  const summary = `${failed.length} of ${labeled.length} requests failed: ${reasons}`
  const err = new Error(summary)
  err.cause = { failures: failed.map((f) => ({ name: f.name, reason: f.result.reason })) }
@@ -23,6 +37,9 @@ export function aggregateFailures(labeled: LabeledSettled[]): Error | null {
 }

 function reasonMessage(reason: unknown): string {
+  const formatted = FormatError(reason)
+  if (formatted) return formatted
+
  if (reason instanceof Error) return reason.message
  if (typeof reason === "string") return reason
  if (reason && typeof reason === "object") {
@@ -457,7 +457,7 @@ export const { use: useLocal, provider: LocalProvider } = createSimpleContext({
            const exists = sessionStore.pinned.includes(sessionID)
            const next = exists
              ? sessionStore.pinned.filter((x) => x !== sessionID)
-              : [sessionID, ...sessionStore.pinned]
+              : [...sessionStore.pinned, sessionID]
            setSessionStore("pinned", next)
            save()
          })
@@ -962,6 +962,7 @@ function getSyntaxRules(theme: Theme) {
      style: {
        foreground: theme.markdownHeading,
        bold: true,
+        underline: true,
      },
    },
    {
@@ -1,10 +1,9 @@
 import { createMemo, type Setter } from "solid-js"
-import { Flag } from "@opencode-ai/core/flag/flag"
 import { useKV } from "./kv"

-export type ThinkingMode = "show" | "minimal" | "hide"
+export type ThinkingMode = "show" | "hide"

-const MODES: readonly ThinkingMode[] = ["show", "minimal", "hide"] as const
+const MODES: readonly ThinkingMode[] = ["show", "hide"] as const

 // OpenAI's Responses API surfaces reasoning summaries that start with a bolded
 // title line: "**Inspecting PR workflow**\n\n<body>". GitHub Copilot routes
@@ -20,7 +19,7 @@ export function isThinkingMode(value: unknown): value is ThinkingMode {
  return typeof value === "string" && (MODES as readonly string[]).includes(value)
 }

-// Cycle order matches the slash command: show → minimal → hide → show.
+// Cycle order matches the slash command: show → hide → show.
 export function nextThinkingMode(current: ThinkingMode): ThinkingMode {
  const idx = MODES.indexOf(current)
  return MODES[(idx + 1) % MODES.length] ?? "show"
@@ -33,7 +32,7 @@ export function useThinkingMode() {
  // The KVProvider only renders children once kv.ready, so reads here are safe.
  const hadStored = kv.get("thinking_mode") !== undefined
  const legacy = kv.get("thinking_visibility")
-  const [stored, setStored] = kv.signal<ThinkingMode>("thinking_mode", "minimal")
+  const [stored, setStored] = kv.signal<ThinkingMode>("thinking_mode", "hide")

  // The kv signal exposes its setter typed as `Setter<T>` which carries Solid's
  // overload set; passing an updater fn through a property access loses the
@@ -47,21 +46,21 @@ export function useThinkingMode() {

  // Preserve previous experience for users who had explicitly toggled the
  // legacy `thinking_visibility` boolean. First-time users (no legacy key)
-  // get the new "minimal" default.
+  // get the new "hide" default (collapsed thinking).
  if (!hadStored) {
    if (legacy === true) set("show")
    else if (legacy === false) set("hide")
  }

+  if ((stored() as string) === "minimal") set("hide")
+
  const mode = createMemo<ThinkingMode>(() => {
-    if (Flag.OPENCODE_EXPERIMENTAL_MINIMAL_THINKING) return "minimal"
    const value = stored()
-    return isThinkingMode(value) ? value : "minimal"
+    return isThinkingMode(value) ? value : "hide"
  })

  return {
    mode,
    set,
-    locked: () => Flag.OPENCODE_EXPERIMENTAL_MINIMAL_THINKING === true,
  }
 }
@@ -392,7 +392,7 @@ function AssistantReasoning(props: {
  const thinking = useThinkingMode()
  const [expanded, setExpanded] = createSignal(false)
  const content = createMemo(() => props.part.text.replace("[REDACTED]", "").trim())
-  const inMinimal = createMemo(() => thinking.mode() === "minimal")
+  const inMinimal = createMemo(() => thinking.mode() === "hide")
  // v2 reasoning parts have no per-part `time.end` (see SessionMessageAssistantReasoning
  // in the v2 SDK); we settle on parent-message completion instead.
  const isDone = createMemo(() => props.completedAt() !== undefined)
@@ -404,7 +404,7 @@ function AssistantReasoning(props: {
  }

  return (
-    <Show when={content() && thinking.mode() !== "hide"}>
+    <Show when={content()}>
      <Switch>
        <Match when={!inMinimal() || expanded()}>
          <box
@@ -218,7 +218,7 @@ export function Session() {
  const [conceal, setConceal] = createSignal(true)
  const thinking = useThinkingMode()
  const thinkingMode = thinking.mode
-  const showThinking = createMemo(() => thinkingMode() !== "hide")
+  const showThinking = createMemo(() => true)
  const [timestamps, setTimestamps] = kv.signal<"hide" | "show">("timestamps", "hide")
  const [showDetails, setShowDetails] = kv.signal("tool_details_visibility", true)
  const [showAssistantMetadata, _setShowAssistantMetadata] = kv.signal("assistant_metadata_visibility", true)
@@ -689,9 +689,8 @@ export function Session() {
    {
      title: (() => {
        const next = nextThinkingMode(thinkingMode())
-        if (next === "minimal") return "Switch thinking to minimal"
-        if (next === "hide") return "Hide thinking"
-        return "Show thinking"
+        if (next === "hide") return "Collapse thinking"
+        return "Expand thinking"
      })(),
      value: "session.toggle.thinking",
      category: "Session",
@@ -700,16 +699,6 @@ export function Session() {
        aliases: ["toggle-thinking"],
      },
      run: () => {
-        // Env override forces minimal for the process. Updating KV here would
-        // silently diverge from what's rendered; tell the user instead.
-        if (thinking.locked()) {
-          toast.show({
-            message: "Thinking mode is locked to minimal by OPENCODE_EXPERIMENTAL_MINIMAL_THINKING",
-            variant: "info",
-          })
-          dialog.clear()
-          return
-        }
        thinking.set(nextThinkingMode(thinkingMode()))
        dialog.clear()
      },
@@ -1512,7 +1501,7 @@ const PART_MAPPING = {
 function ReasoningPart(props: { last: boolean; part: ReasoningPart; message: AssistantMessage }) {
  const { theme, subtleSyntax } = useTheme()
  const ctx = use()
-  // Collapsed by default in minimal mode: a single line throughout, so the
+  // Collapsed by default in hide mode: a single line throughout, so the
  // layout never shifts. Click to open the full markdown block, click to close.
  const [expanded, setExpanded] = createSignal(false)

@@ -1523,7 +1512,7 @@ function ReasoningPart(props: { last: boolean; part: ReasoningPart; message: Ass
  // Reasoning is finalized when the server sets `time.end` (see processor.ts).
  // Flips independently of the parent message completing.
  const isDone = createMemo(() => props.part.time.end !== undefined)
-  const inMinimal = createMemo(() => ctx.thinkingMode() === "minimal")
+  const inMinimal = createMemo(() => ctx.thinkingMode() === "hide")
  const duration = createMemo(() => {
    const end = props.part.time.end
    return end === undefined ? 0 : Math.max(0, end - props.part.time.start)
@@ -1539,10 +1528,10 @@ function ReasoningPart(props: { last: boolean; part: ReasoningPart; message: Ass
  }

  return (
-    <Show when={content() && ctx.thinkingMode() !== "hide"}>
+    <Show when={content()}>
      <Switch>
        <Match when={!inMinimal() || expanded()}>
-          {/* Full markdown block: `show` mode, or `minimal` after the user opens it. */}
+          {/* Full markdown block: `show` mode, or `hide` after the user opens it. */}
          <box
            id={"text-" + props.part.id}
            paddingLeft={2}
@@ -1558,7 +1547,7 @@ function ReasoningPart(props: { last: boolean; part: ReasoningPart; message: Ass
              drawUnstyledText={false}
              streaming={true}
              syntaxStyle={subtleSyntax()}
-              content={(inMinimal() ? "▼ " : "") + "_Thinking:_ " + content()}
+              content={(inMinimal() ? "▼ " : "") + (isDone() ? "_Thought:_ " : "_Thinking:_ ") + content()}
              conceal={ctx.conceal()}
              fg={theme.textMuted}
            />
@@ -2,16 +2,9 @@ import { NamedError } from "@opencode-ai/core/util/error"
 import { errorFormat } from "@/util/error"
 import { isRecord } from "@/util/record"

-interface ErrorLike {
-  name?: string
-  _tag?: string
-  message?: string
-  data?: Record<string, unknown>
-}
-
 type ConfigIssue = { message: string; path: string[] }

-function isTaggedError(error: unknown, tag: string): boolean {
+function isTaggedError(error: unknown, tag: string): error is Record<string, unknown> {
  return isRecord(error) && error._tag === tag
 }

@@ -39,22 +32,27 @@ function configIssues(input: Record<string, unknown>): ConfigIssue[] {
    : []
 }

-export function FormatError(input: unknown) {
+export function FormatError(input: unknown): string | undefined {
+  if (input instanceof Error && isRecord(input.cause) && "body" in input.cause) {
+    const formatted = FormatError(input.cause.body)
+    if (formatted) return formatted
+  }
+
  // CliError: domain failure surfaced from an effectCmd handler via fail("...")
  if (isTaggedError(input, "CliError")) {
-    const data = input as ErrorLike & { exitCode?: number }
-    if (data.exitCode != null) process.exitCode = data.exitCode
-    return data.message ?? ""
+    if (typeof input.exitCode === "number") process.exitCode = input.exitCode
+    return stringField(input, "message") ?? ""
  }

  // MCPFailed: { name: string }
  if (NamedError.hasName(input, "MCPFailed")) {
-    return `MCP server "${(input as ErrorLike).data?.name}" failed. Note, opencode does not support MCP authentication yet.`
+    const data = isRecord(input) && isRecord(input.data) ? stringField(input.data, "name") : undefined
+    return `MCP server "${data}" failed. Note, opencode does not support MCP authentication yet.`
  }

  // AccountServiceError, AccountTransportError: TaggedErrorClass
  if (isTaggedError(input, "AccountServiceError") || isTaggedError(input, "AccountTransportError")) {
-    return (input as ErrorLike).message ?? ""
+    return stringField(input, "message") ?? ""
  }

  // ProviderModelNotFoundError: { providerID: string, modelID: string, suggestions?: string[] }
@@ -64,7 +62,7 @@ export function FormatError(input: unknown) {
      ? providerModelNotFound.suggestions.filter((x) => typeof x === "string")
      : []
    return [
-      `Model not found: ${providerModelNotFound.providerID}/${providerModelNotFound.modelID}`,
+      `Model not found: ${stringField(providerModelNotFound, "providerID")}/${stringField(providerModelNotFound, "modelID")}`,
      ...(suggestions.length ? ["Did you mean: " + suggestions.join(", ")] : []),
      `Try: \`opencode models\` to list available models`,
      `Or check your config (opencode.json) provider/model names`,
@@ -112,6 +110,7 @@ export function FormatError(input: unknown) {
  if (isTaggedError(input, "UICancelledError") || NamedError.hasName(input, "UICancelledError")) {
    return ""
  }
+  return undefined
 }

 export function FormatUnknownError(input: unknown): string {
@@ -1,9 +1,9 @@
-import { Bus } from "@/bus"
 import { Config } from "@/config/config"
 import { AppRuntime } from "@/effect/app-runtime"
 import { Flag } from "@opencode-ai/core/flag/flag"
 import { Installation } from "@/installation"
 import { InstallationVersion } from "@opencode-ai/core/installation/version"
+import { GlobalBus } from "@/bus/global"

 export async function upgrade() {
  const config = await AppRuntime.runPromise(Config.Service.use((cfg) => cfg.getGlobal()))
@@ -13,7 +13,13 @@ export async function upgrade() {
  if (!latest) return

  if (Flag.OPENCODE_ALWAYS_NOTIFY_UPDATE) {
-    await Bus.publish(Installation.Event.UpdateAvailable, { version: latest })
+    GlobalBus.emit("event", {
+      directory: "global",
+      payload: {
+        type: Installation.Event.UpdateAvailable.type,
+        properties: { version: latest },
+      },
+    })
    return
  }

@@ -22,12 +28,26 @@ export async function upgrade() {
  const kind = Installation.getReleaseType(InstallationVersion, latest)

  if (config.autoupdate === "notify" || kind !== "patch") {
-    await Bus.publish(Installation.Event.UpdateAvailable, { version: latest })
+    GlobalBus.emit("event", {
+      directory: "global",
+      payload: {
+        type: Installation.Event.UpdateAvailable.type,
+        properties: { version: latest },
+      },
+    })
    return
  }

  if (method === "unknown") return
  await Installation.upgrade(method, latest)
-    .then(() => Bus.publish(Installation.Event.Updated, { version: latest }))
+    .then(() =>
+      GlobalBus.emit("event", {
+        directory: "global",
+        payload: {
+          type: Installation.Event.Updated.type,
+          properties: { version: latest },
+        },
+      }),
+    )
    .catch(() => {})
 }
@@ -1,10 +1,8 @@
 export * as ConfigAgent from "./agent"

 import { Exit, Schema, SchemaGetter } from "effect"
-import { Bus } from "@/bus"
 import { PositiveInt } from "@opencode-ai/core/schema"
 import * as Log from "@opencode-ai/core/util/log"
-import { NamedError } from "@opencode-ai/core/util/error"
 import { Glob } from "@opencode-ai/core/util/glob"
 import { configEntryNameFromPath } from "./entry-name"
 import * as ConfigMarkdown from "./markdown"
@@ -112,12 +110,7 @@ export async function load(dir: string) {
    dot: true,
    symlink: true,
  })) {
-    const md = await ConfigMarkdown.parse(item).catch(async (err) => {
-      const message = ConfigMarkdown.FrontmatterError.isInstance(err)
-        ? err.data.message
-        : `Failed to parse agent ${item}`
-      const { Session } = await import("@/session/session")
-      void Bus.publish(Session.Event.Error, { error: new NamedError.Unknown({ message }).toObject() })
+    const md = await ConfigMarkdown.parse(item).catch((err) => {
      log.error("failed to load agent", { agent: item, err })
      return undefined
    })
@@ -144,12 +137,7 @@ export async function loadMode(dir: string) {
    dot: true,
    symlink: true,
  })) {
-    const md = await ConfigMarkdown.parse(item).catch(async (err) => {
-      const message = ConfigMarkdown.FrontmatterError.isInstance(err)
-        ? err.data.message
-        : `Failed to parse mode ${item}`
-      const { Session } = await import("@/session/session")
-      void Bus.publish(Session.Event.Error, { error: new NamedError.Unknown({ message }).toObject() })
+    const md = await ConfigMarkdown.parse(item).catch((err) => {
      log.error("failed to load mode", { mode: item, err })
      return undefined
    })
@@ -2,9 +2,7 @@ export * as ConfigCommand from "./command"

 import * as Log from "@opencode-ai/core/util/log"
 import { Cause, Exit, Schema } from "effect"
-import { NamedError } from "@opencode-ai/core/util/error"
 import { Glob } from "@opencode-ai/core/util/glob"
-import { Bus } from "@/bus"
 import { configEntryNameFromPath } from "./entry-name"
 import { InvalidError } from "./error"
 import * as ConfigMarkdown from "./markdown"
@@ -32,12 +30,7 @@ export async function load(dir: string) {
    dot: true,
    symlink: true,
  })) {
-    const md = await ConfigMarkdown.parse(item).catch(async (err) => {
-      const message = ConfigMarkdown.FrontmatterError.isInstance(err)
-        ? err.data.message
-        : `Failed to parse command ${item}`
-      const { Session } = await import("@/session/session")
-      void Bus.publish(Session.Event.Error, { error: new NamedError.Unknown({ message }).toObject() })
+    const md = await ConfigMarkdown.parse(item).catch((err) => {
      log.error("failed to load command", { command: item, err })
      return undefined
    })
@@ -96,11 +96,11 @@ export const layer = Layer.effect(
          )

          const cb: ParcelWatcher.SubscribeCallback = bridge.bind((err, evts) => {
-            if (err) return
+            // if (err) return
            for (const evt of evts) {
-              if (evt.type === "create") void Bus.publish(Event.Updated, { file: evt.path, event: "add" })
-              if (evt.type === "update") void Bus.publish(Event.Updated, { file: evt.path, event: "change" })
-              if (evt.type === "delete") void Bus.publish(Event.Updated, { file: evt.path, event: "unlink" })
+              if (evt.type === "create") void Bus.publish(ctx, Event.Updated, { file: evt.path, event: "add" })
+              if (evt.type === "update") void Bus.publish(ctx, Event.Updated, { file: evt.path, event: "change" })
+              if (evt.type === "delete") void Bus.publish(ctx, Event.Updated, { file: evt.path, event: "unlink" })
            }
          })

@@ -291,7 +291,7 @@ export const layer = Layer.effect(
          if (!client) continue

          result.push(client)
-          Bus.publish(Event.Updated, {})
+          await Bus.publish(ctx, Event.Updated, {})
        }

        return result
@@ -1,5 +1,6 @@
 import { NamedError } from "@opencode-ai/core/util/error"
 import * as Log from "@opencode-ai/core/util/log"
+import { ConfigError } from "@/config/error"
 import { Cause, Effect } from "effect"
 import { HttpRouter, HttpServerError, HttpServerRespondable, HttpServerResponse } from "effect/unstable/http"

@@ -18,6 +19,13 @@ export const errorLayer = HttpRouter.middleware<{ handles: unknown }>()((effect)
      if (!defect) return Effect.failCause(cause)

      const error = defect.defect
+      if (
+        error instanceof NamedError &&
+        (ConfigError.InvalidError.isInstance(error) || ConfigError.JsonError.isInstance(error))
+      ) {
+        return Effect.succeed(HttpServerResponse.jsonUnsafe(error.toObject(), { status: 400 }))
+      }
+
      log.error("failed", { error, cause: Cause.pretty(cause) })

      return Effect.succeed(
@@ -16,10 +16,8 @@ import { Effect, Layer, Context, Schema } from "effect"
 import * as DateTime from "effect/DateTime"
 import { InstanceState } from "@/effect/instance-state"
 import { isOverflow as overflow, usable } from "./overflow"
-import { makeRuntime } from "@/effect/run-service"
 import { serviceUse } from "@/effect/service-use"
 import { RuntimeFlags } from "@/effect/runtime-flags"
-import { EventV2 } from "@opencode-ai/core/event"
 import { EventV2Bridge } from "@/event-v2-bridge"
 import { SessionEvent } from "@opencode-ai/core/session-event"

@@ -638,14 +636,4 @@ export const defaultLayer = Layer.suspend(() =>
  ),
 )

-const { runPromise } = makeRuntime(Service, defaultLayer)
-
-export async function isOverflow(input: { tokens: MessageV2.Assistant["tokens"]; model: Provider.Model }) {
-  return runPromise((svc) => svc.isOverflow(input))
-}
-
-export async function prune(input: { sessionID: SessionID }) {
-  return runPromise((svc) => svc.prune(input))
-}
-
 export * as SessionCompaction from "./compaction"
@@ -17,11 +17,6 @@ Only use emojis if the user explicitly requests it. Avoid using emojis in all co
 IMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.
 IMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.
 IMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as "The answer is <answer>.", "Here is the content of the file..." or "Based on the information provided, the answer is..." or "Here is what I will do next...". Here are some examples to demonstrate appropriate verbosity:
-<example>
-user: 2 + 2
-assistant: 4
-</example>
-
 <example>
 user: what is 2+2?
 assistant: 4
@@ -43,11 +38,6 @@ assistant: [use the ls tool to list the files in the current directory, then rea
 npm run dev
 </example>

-<example>
-user: How many golf balls fit inside a jetta?
-assistant: 150000
-</example>
-
 <example>
 user: what files are in the directory src/?
 assistant: [runs ls and sees foo.c, bar.c, baz.c]
@@ -17,6 +17,7 @@ import { EventV2 } from "@opencode-ai/core/event"
 import { serviceUse } from "@/effect/service-use"
 import { InstanceState } from "@/effect/instance-state"
 import { RuntimeFlags } from "@/effect/runtime-flags"
+import { attachWith } from "@/effect/run-service"

 // Keep `Event["data"]` mutable because projectors mutate the persisted shape
 // when writing to the database. Bus payloads (`Properties`) stay readonly —
@@ -75,6 +76,7 @@ export class Service extends Context.Service<Service, Interface>()("@opencode/Sy
 export const layer = Layer.effect(Service)(
  Effect.gen(function* () {
    const flags = yield* RuntimeFlags.Service
+    const bus = yield* ProjectBus.Service

    const replay: Interface["replay"] = Effect.fn("SyncEvent.replay")(function* (event, options) {
      const def = registry.get(event.type)
@@ -112,6 +114,7 @@ export const layer = Layer.effect(Service)(
          }
        : undefined
      process(def, event, {
+        bus,
        publish,
        context,
        ownerID: options?.ownerID,
@@ -172,7 +175,7 @@ export const layer = Layer.effect(Service)(
          const seq = row?.seq != null ? row.seq + 1 : 0

          const event = { id, seq, aggregateID: agg, data }
-          process(def, event, { publish, context, experimentalWorkspaces: flags.experimentalWorkspaces })
+          process(def, event, { bus, publish, context, experimentalWorkspaces: flags.experimentalWorkspaces })
        },
        {
          behavior: "immediate",
@@ -209,7 +212,7 @@ export const layer = Layer.effect(Service)(
  }),
 )

-export const defaultLayer = layer.pipe(Layer.provide(RuntimeFlags.defaultLayer))
+export const defaultLayer = layer.pipe(Layer.provide([ProjectBus.defaultLayer, RuntimeFlags.defaultLayer]))

 export const use = serviceUse(Service)

@@ -303,7 +306,13 @@ function register(def: Definition) {
 function process<Def extends Definition>(
  def: Def,
  event: Event<Def>,
-  options: { publish: boolean; context?: PublishContext; ownerID?: string; experimentalWorkspaces: boolean },
+  options: {
+    bus: ProjectBus.Interface
+    publish: boolean
+    context?: PublishContext
+    ownerID?: string
+    experimentalWorkspaces: boolean
+  },
 ) {
  if (projectors == null) {
    throw new Error("No projectors available. Call `SyncEvent.init` to install projectors")
@@ -348,7 +357,13 @@ function process<Def extends Definition>(
        }

        const result = convertEvent(def.type, event.data)
-        const publish = (data: unknown) => ProjectBus.publish(def, data as Properties<Def>, { id: event.id })
+        const publish = (data: unknown) =>
+          Effect.runPromise(
+            attachWith(options.bus.publish(def, data as Properties<Def>, { id: event.id }), {
+              instance: options.context?.instance,
+              workspace: options.context?.workspace,
+            }),
+          )
        if (result instanceof Promise) {
          void result.then(publish)
        } else {
@@ -19,6 +19,8 @@ const MAX_BYTES_LABEL = `${MAX_BYTES / 1024} KB`
 const SAMPLE_BYTES = 4096
 const SUPPORTED_IMAGE_MIMES = new Set(["image/jpeg", "image/png", "image/gif", "image/webp"])

+class ReadStop extends Schema.TaggedErrorClass<ReadStop>()("ReadStop", {}) {}
+
 // `offset` and `limit` were originally `z.coerce.number()` — the runtime
 // coercion was useful when the tool was called from a shell but serves no
 // purpose in the LLM tool-call path (the model emits typed JSON). The JSON
@@ -111,15 +113,15 @@ export const ReadTool = Tool.define(
      // Note: prefer manual TextDecoder over Stream.decodeText — when the source stream
      // ends without flushing, decodeText drops the final unterminated line. We also
      // avoid Stream.runForEachWhile (it currently swallows the final unterminated
-      // line of the upstream splitLines pipeline) and instead toggle a `done` flag
-      // and ignore subsequent lines.
+      // line of the upstream splitLines pipeline) and use a tagged error to stop the
+      // upstream file stream as soon as the byte cap is reached.
      const decoder = new TextDecoder("utf-8")
      yield* fs.stream(filepath).pipe(
        Stream.map((bytes) => decoder.decode(bytes, { stream: true })),
        Stream.splitLines,
        Stream.runForEach((text) =>
-          Effect.sync(() => {
-            if (flags.done) return
+          Effect.gen(function* () {
+            if (flags.done) return yield* new ReadStop()
            flags.count += 1
            if (flags.count <= start) return

@@ -130,17 +132,19 @@ export const ReadTool = Tool.define(

            const line = text.length > MAX_LINE_LENGTH ? text.substring(0, MAX_LINE_LENGTH) + MAX_LINE_SUFFIX : text
            const size = Buffer.byteLength(line, "utf-8") + (raw.length > 0 ? 1 : 0)
-            if (flags.bytes + size > MAX_BYTES) {
-              flags.cut = true
-              flags.more = true
-              flags.done = true
+            if (flags.bytes + size <= MAX_BYTES) {
+              raw.push(line)
+              flags.bytes += size
              return
            }

-            raw.push(line)
-            flags.bytes += size
+            flags.cut = true
+            flags.more = true
+            flags.done = true
+            return yield* new ReadStop()
          }),
        ),
+        Effect.catchTag("ReadStop", () => Effect.void),
      )

      return { raw, count: flags.count, cut: flags.cut, more: flags.more, offset: opts.offset }
@@ -10,68 +10,12 @@ IMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO N

 ${commandSection}

-# Committing changes with git
-
-Only create commits when requested by the user. If unclear, ask first. When the user asks you to create a new git commit, follow these steps carefully:
-
-Git Safety Protocol:
- NEVER update the git config
- NEVER run destructive/irreversible git commands (like push --force, hard reset, etc) unless the user explicitly requests them
- NEVER skip hooks (--no-verify, --no-gpg-sign, etc) unless the user explicitly requests it
- NEVER run force push to main/master, warn the user if they request it
- Avoid git commit --amend. ONLY use --amend when ALL conditions are met:
-  (1) User explicitly requested amend, OR the commit succeeded and pre-commit hooks auto-modified files that need including — verify by checking `git log` that HEAD is the new commit before amending
-  (2) HEAD commit was created by you in this conversation (verify: git log -1 --format='%an %ae')
-  (3) Commit has NOT been pushed to remote (verify: git status shows "Your branch is ahead")
- CRITICAL: If commit FAILED or was REJECTED by hook, NEVER amend - fix the issue and create a NEW commit
- CRITICAL: If you already pushed to remote, NEVER amend unless user explicitly requests it (requires force push)
- NEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.
-
-1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following ${gitCommands} in parallel, each using the ${toolName} tool:
-  - Run a git status command to see all untracked files.
-  - Run a git diff command to see both staged and unstaged changes that will be committed.
-  - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
-2. Analyze all staged changes (both previously staged and newly added) and draft a commit message:
-  - Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.). Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.).
-  - Do not commit files that likely contain secrets (.env, credentials.json, etc.). Warn the user if they specifically request to commit those files
-  - Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
-  - Ensure it accurately reflects the changes and their purpose
-3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands:
-   - Add relevant untracked files to the staging area.
-   - Create the commit with a message
-   - Run git status after the commit completes to verify success.
-   Note: git status depends on the commit completing, so run it sequentially after the commit.
-4. If the commit fails due to pre-commit hook, fix the issue and create a NEW commit (see amend rules above)
-
-Important notes:
- NEVER run additional commands to read or explore code, besides ${gitCommandRestriction}
- NEVER use the TodoWrite or Task tools
- DO NOT push to the remote repository unless the user explicitly asks you to do so
- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
-
-# Creating pull requests
-Use the gh command via the ${toolName} tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a GitHub URL use the gh command to get the information needed.
-
-IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
-
-1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following ${gitCommands} in parallel using the ${toolName} tool, in order to understand the current state of the branch since it diverged from the main branch:
-   - Run a git status command to see all untracked files
-   - Run a git diff command to see both staged and unstaged changes that will be committed
-   - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
-   - Run a git log command and `git diff [base-branch]...HEAD` to understand the full commit history for the current branch (from the time it diverged from the base branch)
-2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary
-3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:
-   - Create new branch if needed
-   - Push to remote with -u flag if needed
-   - ${createPrInstruction}
-<example>
-${createPrExample}
-</example>
-
-Important:
- DO NOT use the TodoWrite or Task tools
- Return the PR URL when you're done, so the user can see it
-
-# Other common operations
- View comments on a GitHub PR: gh api repos/foo/bar/pulls/123/comments
+# Git and GitHub
+- Only commit, amend, push, or create PRs when explicitly requested.
+- Before committing, inspect `git status`, `git diff`, and `git log --oneline -10`; stage only intended files and never commit secrets.
+- Write a concise commit message that matches the repo style.
+- Do not update git config, skip hooks, use interactive `-i`, force-push, or create empty commits unless explicitly requested.
+- If a commit fails or hooks reject it, fix the issue and create a new commit; do not amend the failed commit.
+- Before creating a PR, inspect status, diff, remote tracking, recent commits, and the diff from the base branch.
+- Review all commits included in the PR, not just the latest commit.
+- Use `gh` for GitHub tasks, including PRs, issues, checks, and releases; return the PR URL when done.
@@ -24,6 +24,14 @@ export interface TaskPromptOps {
 }

 const id = "task"
+const BACKGROUND_DESCRIPTION = [
+  "",
+  "",
+  [
+    "Background mode: background=true launches the subagent asynchronously.",
+    "Use task_status(task_id=..., wait=false) to poll, or wait=true to block until done.",
+  ].join(" "),
+].join("\n")

 const BaseParameters = Schema.Struct({
  description: Schema.String.annotate({ description: "A short (3-5 words) description of the task" }),
@@ -327,7 +335,7 @@ export const TaskTool = Tool.define(
    })

    return {
-      description: DESCRIPTION,
+      description: flags.experimentalBackgroundSubagents ? DESCRIPTION + BACKGROUND_DESCRIPTION : DESCRIPTION,
      parameters: Parameters,
      jsonSchema: flags.experimentalBackgroundSubagents ? undefined : ToolJsonSchema.fromSchema(BaseParameters),
      execute: (params: Schema.Schema.Type<typeof Parameters>, ctx: Tool.Context) =>
@@ -2,57 +2,17 @@ Launch a new agent to handle complex, multistep tasks autonomously.

 When using the Task tool, you must specify a subagent_type parameter to select which agent type to use.

-When to use the Task tool:
- When you are instructed to execute custom slash commands. Use the Task tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description="Check the file", prompt="/check-file path/to/file.py")
-
 When NOT to use the Task tool:
 - If you want to read a specific file path, use the Read or Glob tool instead of the Task tool, to find the match more quickly
- If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
+- If you are searching for a specific class definition like "class Foo", use the Grep tool instead, to find the match more quickly
 - If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Task tool, to find the match more quickly
- Other tasks that are not related to the agent descriptions above
+- If no available agent is a good fit for the task, use other tools directly


 Usage notes:
 1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
 2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result. The output includes a task_id you can reuse later to continue the same subagent session.
-3. If OPENCODE_EXPERIMENTAL_BACKGROUND_SUBAGENTS is enabled, background=true launches the subagent asynchronously. Use task_status(task_id=..., wait=false) to poll, or wait=true to block until done.
-4. Each agent invocation starts with a fresh context unless you provide task_id to resume the same subagent session (which continues with its previous messages and tool outputs). When starting fresh, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
-5. The agent's outputs should generally be trusted
-6. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent. Tell it how to verify its work if possible (e.g., relevant test commands).
-7. If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.
-
-Example usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):
-
-<example_agent_descriptions>
-"code-reviewer": use this agent after you are done writing a significant piece of code
-"greeting-responder": use this agent when to respond to user greetings with a friendly joke
-</example_agent_description>
-
-<example>
-user: "Please write a function that checks if a number is prime"
-assistant: Sure let me write a function that checks if a number is prime
-assistant: First let me use the Write tool to write a function that checks if a number is prime
-assistant: I'm going to use the Write tool to write the following code:
-<code>
-function isPrime(n) {
-  if (n <= 1) return false
-  for (let i = 2; i * i <= n; i++) {
-    if (n % i === 0) return false
-  }
-  return true
-}
-</code>
-<commentary>
-Since a significant piece of code was written and the task was completed, now use the code-reviewer agent to review the code
-</commentary>
-assistant: Now let me use the code-reviewer agent to review the code
-assistant: Uses the Task tool to launch the code-reviewer agent
-</example>
-
-<example>
-user: "Hello"
-<commentary>
-Since the user is greeting, use the greeting-responder agent to respond with a friendly joke
-</commentary>
-assistant: "I'm going to use the Task tool to launch the with the greeting-responder agent"
-</example>
+3. Each agent invocation starts with a fresh context unless you provide task_id to resume the same subagent session (which continues with its previous messages and tool outputs). When starting fresh, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
+4. The agent's outputs should generally be trusted
+5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent. Tell it how to verify its work if possible (e.g., relevant test commands).
+6. If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.
@@ -1,167 +1,44 @@
-Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.
-It also helps the user understand the progress of the task and overall progress of their requests.
+Create and maintain a structured task list for the current coding session. Tracks progress, organizes multi-step work, and surfaces status to the user.

-## When to Use This Tool
-Use this tool proactively in these scenarios:
+## When to use
+Use proactively when:
+- The task requires 3+ distinct steps or actions (not just 3 tool calls for a single conceptual step)
+- The work is non-trivial and benefits from planning
+- The user provides multiple tasks (numbered or comma-separated) or explicitly asks for a todo list
+- New instructions arrive - capture them as todos
+- You start a task - mark it `in_progress` (only one at a time) before working
+- You finish a task - mark it `completed` and add any follow-ups discovered during the work

-1. Complex multistep tasks - When a task requires 3 or more distinct steps or actions
-2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
-3. User explicitly requests todo list - When the user directly asks you to use the todo list
-4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
-5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.
-6. After completing a task - Mark it complete and add any new follow-up tasks
-7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.
+## When NOT to use
+Skip when:
+- The work is a single, straightforward task (or <3 trivial steps)
+- The request is purely informational or conversational
+- Tracking adds no organizational value

-## When NOT to Use This Tool
+## States
+- `pending` - not started
+- `in_progress` - actively working (exactly ONE at a time)
+- `completed` - finished successfully
+- `cancelled` - no longer needed

-Skip using this tool when:
-1. There is only a single, straightforward task
-2. The task is trivial and tracking it provides no organizational benefit
-3. The task can be completed in less than 3 trivial steps
-4. The task is purely conversational or informational
+## Rules
+- Update status in real time; don't batch completions
+- Mark `completed` only after the required work is actually done, including any required verification. Never based on intent.
+- Keep exactly one `in_progress` while work remains
+- If blocked or partial, keep it `in_progress` and add a follow-up todo describing the blocker
+- Preserve user-provided commands verbatim (flags, args, order)
+- Items should be specific and actionable; break large work into smaller steps

-NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
+## Examples

-## Examples of When to Use the Todo List
+Use it:
+- "Add a dark mode toggle and run the tests" -> multi-step feature + explicit verification
+- "Rename getCwd -> getCurrentWorkingDirectory across the repo" -> grep reveals 15 occurrences in 8 files
+- "Implement registration, catalog, cart, checkout" -> multiple complex features

-<example>
-User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
-Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
-*Creates todo list with the following items:*
-1. Create dark mode toggle component in Settings page
-2. Add dark mode state management (context/store)
-3. Implement CSS-in-JS styles for dark theme
-4. Update existing components to support theme switching
-5. Run tests and build process, addressing any failures or errors that occur
-*Begins working on the first task*
-
-<reasoning>
-The assistant used the todo list because:
-1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
-2. The user explicitly requested tests and build be run afterward
-3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
-</reasoning>
-</example>
-
-<example>
-User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
-Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
-*Uses grep or search tools to locate all instances of getCwd in the codebase*
-Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
-*Creates todo list with specific items for each file that needs updating*
-
-<reasoning>
-The assistant used the todo list because:
-1. First, the assistant searched to understand the scope of the task
-2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
-3. The todo list helps ensure every instance is tracked and updated systematically
-4. This approach prevents missing any occurrences and maintains code consistency
-</reasoning>
-</example>
-
-
-<example>
-User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
-Assistant: I'll help implement these features. First, let's add all the features to the todo list.
-*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
-Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
-
-<reasoning>
-The assistant used the todo list because:
-1. The user provided multiple complex features to implement in a comma separated list
-2. The todo list helps organize these large features into manageable tasks
-3. This approach allows for tracking progress across the entire implementation
-</reasoning>
-</example>
-
-<example>
-User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
-Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
-*Reviews component structure, render patterns, state management, and data fetching*
-Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
-*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*
-Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
-
-<reasoning>
-The assistant used the todo list because:
-1. First, the assistant examined the codebase to identify specific performance issues
-2. Based on this analysis, it identified multiple optimization opportunities
-3. Performance optimization is a non-trivial task requiring multiple steps
-4. The todo list helps methodically track improvements across different components
-5. This systematic approach ensures all performance bottlenecks are addressed
-</reasoning>
-</example>
-
-## Examples of When NOT to Use the Todo List
-
-<example>
-User: How do I print 'Hello World' in Python?
-Assistant: In Python, you can print "Hello World" with this simple code:
-
-python
-print("Hello World")
-
-This will output the text "Hello World" to the console when executed.</assistant>
-
-<reasoning>
-The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
-</reasoning>
-</example>
-
-<example>
-User: What does the git status command do?
-Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
-
-<reasoning>
-The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
-</reasoning>
-</example>
-
-<example>
-User: Can you add a comment to the calculateTotal function to explain what it does?
-Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
-* Uses the Edit tool to add a comment to the calculateTotal function *
-
-<reasoning>
-The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
-</reasoning>
-</example>
-
-<example>
-User: Run npm install for me and tell me what happens.
-Assistant: I'll run the npm install command for you.
-
-*Executes: npm install*
-
-The command completed successfully. Here's the output:
-[Output of npm install command]
-
-All dependencies have been installed according to your package.json file.
-
-<reasoning>
-The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
-</reasoning>
-</example>
-
-## Task States and Management
-
-1. **Task States**: Use these states to track progress:
-   - pending: Task not yet started
-   - in_progress: Currently working on (limit to ONE task at a time)
-   - completed: Task finished successfully
-   - cancelled: Task no longer needed
-
-2. **Task Management**:
-   - Update task status in real-time as you work
-   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
-   - Only have ONE task in_progress at any time
-   - Complete current tasks before starting new ones
-   - Cancel tasks that become irrelevant
-
-3. **Task Breakdown**:
-   - Create specific, actionable items
-   - Break complex tasks into smaller, manageable steps
-   - Use clear, descriptive task names
-
-When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.
+Skip it:
+- "How do I print Hello World in Python?" -> informational
+- "Add a comment to calculateTotal" -> single edit
+- "Run npm install and tell me what happened" -> one command

+When in doubt, use it.
@@ -5,6 +5,7 @@
 */
 import { describe, expect, test } from "bun:test"
 import { aggregateFailures } from "@/cli/cmd/tui/context/aggregate-failures"
+import { ConfigError } from "@/config/error"

 describe("aggregateFailures", () => {
  test("returns null when every result is fulfilled", () => {
@@ -41,11 +42,48 @@ describe("aggregateFailures", () => {
    expect(err!.message).toContain("agents: boom")
  })

+  test("formats structured config errors hidden inside SDK error causes", () => {
+    const configError = new ConfigError.InvalidError({
+      path: "/tmp/opencode.json",
+      issues: [{ message: "Expected object", path: ["provider", "anthropic", "options"] }],
+    })
+    const err = aggregateFailures([
+      {
+        name: "config.get",
+        result: {
+          status: "rejected",
+          reason: new Error("ConfigInvalidError", {
+            cause: {
+              body: configError.toObject(),
+            },
+          }),
+        },
+      },
+    ])
+
+    expect(err!.message).toContain("config.get: Configuration is invalid at /tmp/opencode.json")
+    expect(err!.message).toContain("Expected object provider.anthropic.options")
+  })
+
+  test("deduplicates identical failure messages across startup requests", () => {
+    const reason = new Error("same config problem")
+    const err = aggregateFailures([
+      { name: "config.providers", result: { status: "rejected", reason } },
+      { name: "provider.list", result: { status: "rejected", reason } },
+      { name: "app.agents", result: { status: "rejected", reason } },
+      { name: "config.get", result: { status: "rejected", reason } },
+      { name: "project.sync", result: { status: "fulfilled", value: undefined } },
+    ])
+
+    expect(err!.message).toContain("4 of 5 requests failed: same config problem")
+    expect(err!.message).toContain("Affected startup requests: config.providers, provider.list, app.agents, config.get")
+    expect(err!.message.match(/same config problem/g)?.length).toBe(1)
+  })
+
  test("attaches structured failure list under .cause", () => {
    const reason = new Error("nope")
    const err = aggregateFailures([{ name: "providers", result: { status: "rejected", reason } }])
-    const cause = err!.cause as { failures: Array<{ name: string; reason: unknown }> }
-    expect(cause.failures).toEqual([{ name: "providers", reason }])
+    expect(err!.cause).toEqual({ failures: [{ name: "providers", reason }] })
  })

  test("falls back to String() for opaque reasons", () => {
@@ -0,0 +1,44 @@
+import { describe, expect, test } from "bun:test"
+import { isDuplicateEntry, type PromptInfo } from "../../../../src/cli/cmd/tui/component/prompt/history"
+
+const entry = (input: string, parts: PromptInfo["parts"] = []): PromptInfo => ({ input, parts })
+
+describe("prompt history dedupe", () => {
+  test("returns false when there is no previous entry", () => {
+    expect(isDuplicateEntry(undefined, entry("hello"))).toBe(false)
+  })
+
+  test("dedupes identical consecutive entries", () => {
+    const a = entry("hello world this is over twenty chars")
+    const b = entry("hello world this is over twenty chars")
+    expect(isDuplicateEntry(a, b)).toBe(true)
+  })
+
+  test("does not dedupe when input text differs", () => {
+    expect(isDuplicateEntry(entry("foo"), entry("bar"))).toBe(false)
+  })
+
+  test("does not dedupe when parts differ", () => {
+    const a = entry("describe this", [
+      {
+        type: "file",
+        mime: "image/png",
+        filename: "a.png",
+        url: "data:image/png;base64,AAA",
+      },
+    ])
+    const b = entry("describe this", [
+      {
+        type: "file",
+        mime: "image/png",
+        filename: "b.png",
+        url: "data:image/png;base64,BBB",
+      },
+    ])
+    expect(isDuplicateEntry(a, b)).toBe(false)
+  })
+
+  test("does not dedupe when mode differs", () => {
+    expect(isDuplicateEntry({ ...entry("ls"), mode: "normal" }, { ...entry("ls"), mode: "shell" })).toBe(false)
+  })
+})
@@ -1,13 +1,14 @@
 import { describe, expect, spyOn } from "bun:test"
 import path from "path"
-import { Effect, Layer } from "effect"
+import { Deferred, Effect, Layer } from "effect"
+import { Bus } from "@/bus"
 import { Config } from "@/config/config"
 import { RuntimeFlags } from "@/effect/runtime-flags"
 import { LSP } from "@/lsp/lsp"
 import * as LSPServer from "@/lsp/server"
 import { CrossSpawnSpawner } from "@opencode-ai/core/cross-spawn-spawner"
 import { provideTmpdirInstance } from "../fixture/fixture"
-import { testEffect } from "../lib/effect"
+import { awaitWithTimeout, testEffect } from "../lib/effect"

 const it = testEffect(Layer.mergeAll(LSP.defaultLayer, CrossSpawnSpawner.defaultLayer))
 const experimentalTyIt = testEffect(
@@ -16,6 +17,7 @@ const experimentalTyIt = testEffect(
    CrossSpawnSpawner.defaultLayer,
  ),
 )
+const fakeServerPath = path.join(__dirname, "../fixture/lsp/fake-lsp-server.js")
 const disabledDownloadIt = testEffect(
  Layer.mergeAll(
    LSP.layer.pipe(Layer.provide(Config.defaultLayer), Layer.provide(RuntimeFlags.layer({ disableLspDownload: true }))),
@@ -92,6 +94,35 @@ describe("lsp.spawn", () => {
    ),
  )

+  it.live("publishes lsp.updated after custom LSP initialization", () =>
+    provideTmpdirInstance(
+      (dir) =>
+        Effect.gen(function* () {
+          const lsp = yield* LSP.Service
+          const updated = yield* Deferred.make<void>()
+          const unsubscribe = Bus.subscribe(LSP.Event.Updated, () =>
+            Effect.runSync(Deferred.succeed(updated, undefined)),
+          )
+          yield* Effect.addFinalizer(() => Effect.sync(unsubscribe))
+
+          const file = path.join(dir, "sample.repro")
+          yield* Effect.promise(() => Bun.write(file, "sample\n"))
+          yield* lsp.touchFile(file)
+          yield* awaitWithTimeout(Deferred.await(updated), "lsp.updated event was not published")
+        }),
+      {
+        config: {
+          lsp: {
+            fake: {
+              command: [process.execPath, fakeServerPath],
+              extensions: [".repro"],
+            },
+          },
+        },
+      },
+    ),
+  )
+
  it.live("would spawn builtin LSP for files inside instance when config object is provided", () =>
    provideTmpdirInstance(
      (dir) =>
@@ -1,6 +1,7 @@
 import { NodeHttpServer, NodeServices } from "@effect/platform-node"
 import { NamedError } from "@opencode-ai/core/util/error"
 import { describe, expect } from "bun:test"
+import { ConfigError } from "../../src/config/error"
 import { Effect, Layer } from "effect"
 import { HttpClient, HttpClientRequest, HttpRouter } from "effect/unstable/http"
 import { errorLayer } from "../../src/server/routes/instance/httpapi/middleware/error"
@@ -50,6 +51,27 @@ describe("HttpApi error middleware", () => {
    }),
  )

+  it.live("preserves config defects as client-visible bad requests", () =>
+    Effect.gen(function* () {
+      const configError = new ConfigError.InvalidError({
+        path: "/tmp/opencode.json",
+        issues: [{ message: "Expected object", path: ["provider", "anthropic", "options"] }],
+      })
+
+      yield* HttpRouter.add("GET", "/config-error", Effect.die(configError)).pipe(
+        Layer.provide(errorLayer),
+        HttpRouter.serve,
+        Layer.build,
+      )
+
+      const response = yield* HttpClientRequest.get("/config-error").pipe(HttpClient.execute)
+      const body = yield* response.json
+
+      expect(response.status).toBe(400)
+      expect(JSON.stringify(body)).toBe(JSON.stringify(configError.toObject()))
+    }),
+  )
+
  it.live("does not map storage not-found defects to 404", () =>
    Effect.gen(function* () {
      yield* HttpRouter.add(
@@ -13,7 +13,10 @@ import { RuntimeFlags } from "@/effect/runtime-flags"

 const it = testEffect(
  Layer.mergeAll(
-    SyncEvent.layer.pipe(Layer.provide(RuntimeFlags.layer({ experimentalWorkspaces: true }))),
+    SyncEvent.layer.pipe(
+      Layer.provide(RuntimeFlags.layer({ experimentalWorkspaces: true })),
+      Layer.provideMerge(Bus.layer),
+    ),
    CrossSpawnSpawner.defaultLayer,
  ),
 )
@@ -114,7 +117,8 @@ describe("SyncEvent", () => {
          const received = new Promise<void>((done) => {
            resolve = done
          })
-          const dispose = Bus.subscribeAll((event) => {
+          const bus = yield* Bus.Service
+          const dispose = yield* bus.subscribeAllCallback((event) => {
            events.push(event)
            resolve()
          })
@@ -1,5 +1,5 @@
 import { afterEach, describe, expect } from "bun:test"
-import { Cause, Effect, Exit, Layer } from "effect"
+import { Cause, Effect, Exit, Layer, Stream } from "effect"
 import path from "path"
 import { Agent } from "../../src/agent/agent"
 import { CrossSpawnSpawner } from "@opencode-ai/core/cross-spawn-spawner"
@@ -366,6 +366,38 @@ describe("tool.read truncation", () => {
    }),
  )

+  it.instance("stops streaming after the byte cap", () =>
+    Effect.gen(function* () {
+      const test = yield* TestInstance
+      const filepath = path.join(test.directory, "huge.txt")
+      const content = `${"x".repeat(80)}\n`.repeat(50_000)
+      yield* put(filepath, content)
+
+      const fs = yield* AppFileSystem.Service
+      const counter = { bytes: 0 }
+      const result = yield* run({ filePath: filepath }).pipe(
+        Effect.provideService(
+          AppFileSystem.Service,
+          AppFileSystem.Service.of({
+            ...fs,
+            stream: (file, options) =>
+              fs.stream(file, options).pipe(
+                Stream.tap((chunk) =>
+                  Effect.sync(() => {
+                    counter.bytes += chunk.length
+                  }),
+                ),
+              ),
+          }),
+        ),
+      )
+
+      expect(result.metadata.truncated).toBe(true)
+      expect(result.output).toContain("Output capped at")
+      expect(counter.bytes).toBeLessThan(Buffer.byteLength(content, "utf-8") / 2)
+    }),
+  )
+
  it.instance("truncates by line count when limit is specified", () =>
    Effect.gen(function* () {
      const test = yield* TestInstance
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode-ai/plugin",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -22,9 +22,9 @@
    "zod": "catalog:"
  },
  "peerDependencies": {
-    "@opentui/core": ">=0.2.10",
-    "@opentui/keymap": ">=0.2.10",
-    "@opentui/solid": ">=0.2.10"
+    "@opentui/core": ">=0.2.11",
+    "@opentui/keymap": ">=0.2.11",
+    "@opentui/solid": ">=0.2.11"
  },
  "peerDependenciesMeta": {
    "@opentui/core": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode-ai/sdk",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/slack",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,6 +1,6 @@
 {
  "name": "@opencode-ai/ui",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "type": "module",
  "license": "MIT",
  "exports": {
@@ -2,7 +2,7 @@
  "name": "@opencode-ai/web",
  "type": "module",
  "license": "MIT",
-  "version": "1.15.0",
+  "version": "1.15.4",
  "scripts": {
    "dev": "astro dev",
    "dev:remote": "VITE_API_URL=https://api.opencode.ai astro dev",
@@ -98,7 +98,6 @@ OpenCode Zen هي بوابة AI تتيح لك الوصول إلى هذه الن
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 يستخدم [معرّف النموذج](/docs/config/#models) في إعدادات OpenCode الصيغة `opencode/<model-id>`. على سبيل المثال، بالنسبة إلى GPT 5.5، ستستخدم `opencode/gpt-5.5` في إعداداتك.
@@ -124,7 +123,6 @@ https://opencode.ai/zen/v1/models
 | Big Pickle                        | Free    | Free    | Free            | -               |
 | DeepSeek V4 Flash Free            | Free    | Free    | Free            | -               |
 | MiniMax M2.5 Free                 | Free    | Free    | Free            | -               |
-| Ring 2.6 1T Free                  | Free    | Free    | Free            | -               |
 | Nemotron 3 Super Free             | Free    | Free    | Free            | -               |
 | MiniMax M2.7                      | $0.30   | $1.20   | $0.06           | $0.375          |
 | MiniMax M2.5                      | $0.30   | $1.20   | $0.06           | $0.375          |
@@ -177,7 +175,6 @@ https://opencode.ai/zen/v1/models

 - DeepSeek V4 Flash Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
 - MiniMax M2.5 Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
- Ring 2.6 1T Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
 - Nemotron 3 Super Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
 - Big Pickle نموذج خفي ومتاح مجانا على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.

@@ -230,7 +227,6 @@ https://opencode.ai/zen/v1/models
 - Big Pickle: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج.
 - DeepSeek V4 Flash Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج.
 - MiniMax M2.5 Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج.
- Ring 2.6 1T Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج.
 - Nemotron 3 Super Free (نقاط نهاية NVIDIA المجانية): يُقدَّم بموجب [شروط خدمة النسخة التجريبية من واجهة NVIDIA API](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). للاستخدام التجريبي فقط، وليس للإنتاج أو البيانات الحساسة. تقوم NVIDIA بتسجيل المطالبات والمخرجات لتحسين نماذجها وخدماتها. لا ترسل بيانات شخصية أو سرية.
 - OpenAI APIs: يتم الاحتفاظ بالطلبات لمدة 30 يوما وفقا لـ [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: يتم الاحتفاظ بالطلبات لمدة 30 يوما وفقا لـ [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
@@ -103,7 +103,6 @@ Našim modelima možete pristupiti i preko sljedećih API endpointa.
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 [model id](/docs/config/#models) u vašoj OpenCode konfiguraciji koristi format
@@ -131,7 +130,6 @@ Podržavamo pay-as-you-go model. Ispod su cijene **po 1M tokena**.
 | Big Pickle                        | Free   | Free    | Free        | -            |
 | DeepSeek V4 Flash Free            | Free   | Free    | Free        | -            |
 | MiniMax M2.5 Free                 | Free   | Free    | Free        | -            |
-| Ring 2.6 1T Free                  | Free   | Free    | Free        | -            |
 | Nemotron 3 Super Free             | Free   | Free    | Free        | -            |
 | MiniMax M2.7                      | $0.30  | $1.20   | $0.06       | $0.375       |
 | MiniMax M2.5                      | $0.30  | $1.20   | $0.06       | $0.375       |
@@ -184,7 +182,6 @@ Besplatni modeli:

 - DeepSeek V4 Flash Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
 - MiniMax M2.5 Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
- Ring 2.6 1T Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
 - Nemotron 3 Super Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
 - Big Pickle je stealth model koji je besplatan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.

@@ -242,7 +239,6 @@ i ne koriste vaše podatke za treniranje modela, uz sljedeće izuzetke:
 - Big Pickle: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela.
 - DeepSeek V4 Flash Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela.
 - MiniMax M2.5 Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela.
- Ring 2.6 1T Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela.
 - Nemotron 3 Super Free (besplatni NVIDIA endpointi): Dostupan je prema [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Samo za probnu upotrebu, nije za produkciju niti osjetljive podatke. NVIDIA bilježi promptove i izlaze radi poboljšanja svojih modela i usluga. Nemojte slati lične ili povjerljive podatke.
 - OpenAI APIs: Requests are retained for 30 days in accordance with [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Requests are retained for 30 days in accordance with [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
@@ -103,7 +103,6 @@ Du kan også få adgang til vores modeller gennem følgende API-endpoints.
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 [model id](/docs/config/#models) i din OpenCode-konfiguration
@@ -131,7 +130,6 @@ Vi understøtter en pay-as-you-go-model. Nedenfor er priserne **pr. 1M tokens**.
 | Big Pickle                        | Free   | Free    | Free        | -            |
 | DeepSeek V4 Flash Free            | Free   | Free    | Free        | -            |
 | MiniMax M2.5 Free                 | Free   | Free    | Free        | -            |
-| Ring 2.6 1T Free                  | Free   | Free    | Free        | -            |
 | Nemotron 3 Super Free             | Free   | Free    | Free        | -            |
 | MiniMax M2.7                      | $0.30  | $1.20   | $0.06       | $0.375       |
 | MiniMax M2.5                      | $0.30  | $1.20   | $0.06       | $0.375       |
@@ -184,7 +182,6 @@ De gratis modeller:

 - DeepSeek V4 Flash Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
 - MiniMax M2.5 Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
- Ring 2.6 1T Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
 - Nemotron 3 Super Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
 - Big Pickle er en stealth-model, som er gratis på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.

@@ -240,7 +237,6 @@ Alle vores modeller hostes i US. Vores udbydere følger en nul-opbevaringspoliti
 - Big Pickle: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen.
 - DeepSeek V4 Flash Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen.
 - MiniMax M2.5 Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen.
- Ring 2.6 1T Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen.
 - Nemotron 3 Super Free (gratis NVIDIA-endpoints): Leveres under [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Kun til prøvebrug, ikke til produktion eller følsomme data. Prompts og outputs logges af NVIDIA for at forbedre deres modeller og tjenester. Indsend ikke personlige eller fortrolige data.
 - OpenAI APIs: Anmodninger opbevares i 30 dage i overensstemmelse med [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Anmodninger opbevares i 30 dage i overensstemmelse med [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
@@ -94,7 +94,6 @@ Du kannst auch über die folgenden API-Endpunkte auf unsere Modelle zugreifen.
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 Die [Model-ID](/docs/config/#models) in deiner OpenCode-Konfiguration verwendet das Format `opencode/<model-id>`. Für GPT 5.5 würdest du zum Beispiel `opencode/gpt-5.5` in deiner Konfiguration verwenden.
@@ -120,7 +119,6 @@ Wir unterstützen ein Pay-as-you-go-Modell. Unten findest du die Preise **pro 1M
 | Big Pickle                        | Free   | Free    | Free        | -            |
 | DeepSeek V4 Flash Free            | Free   | Free    | Free        | -            |
 | MiniMax M2.5 Free                 | Free   | Free    | Free        | -            |
-| Ring 2.6 1T Free                  | Free   | Free    | Free        | -            |
 | Nemotron 3 Super Free             | Free   | Free    | Free        | -            |
 | MiniMax M2.7                      | $0.30  | $1.20   | $0.06       | $0.375       |
 | MiniMax M2.5                      | $0.30  | $1.20   | $0.06       | $0.375       |
@@ -173,7 +171,6 @@ Die kostenlosen Modelle:

 - DeepSeek V4 Flash Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
 - MiniMax M2.5 Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
- Ring 2.6 1T Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
 - Nemotron 3 Super Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
 - Big Pickle ist ein Stealth-Modell, das für begrenzte Zeit kostenlos auf OpenCode verfügbar ist. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.

@@ -226,7 +223,6 @@ Alle unsere Modelle werden in den USA gehostet. Unsere Provider folgen einer Zer
 - Big Pickle: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden.
 - DeepSeek V4 Flash Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden.
 - MiniMax M2.5 Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden.
- Ring 2.6 1T Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden.
 - Nemotron 3 Super Free (kostenlose NVIDIA-Endpunkte): Bereitgestellt gemäß den [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Nur für Testzwecke, nicht für Produktion oder sensible Daten. Eingaben und Ausgaben werden von NVIDIA protokolliert, um seine Modelle und Dienste zu verbessern. Übermitteln Sie keine personenbezogenen oder vertraulichen Daten.
 - OpenAI APIs: Anfragen werden in Übereinstimmung mit [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) 30 Tage lang gespeichert.
 - Anthropic APIs: Anfragen werden in Übereinstimmung mit [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) 30 Tage lang gespeichert.
@@ -103,7 +103,6 @@ También puedes acceder a nuestros modelos a través de los siguientes endpoints
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 El [identificador del modelo](/docs/config/#models) en tu configuración de OpenCode
@@ -131,7 +130,6 @@ Admitimos un modelo de pago por uso. A continuación se muestran los precios **p
 | Big Pickle                        | Free    | Free    | Free             | -                  |
 | DeepSeek V4 Flash Free            | Free    | Free    | Free             | -                  |
 | MiniMax M2.5 Free                 | Free    | Free    | Free             | -                  |
-| Ring 2.6 1T Free                  | Free    | Free    | Free             | -                  |
 | Nemotron 3 Super Free             | Free    | Free    | Free             | -                  |
 | MiniMax M2.7                      | $0.30   | $1.20   | $0.06            | $0.375             |
 | MiniMax M2.5                      | $0.30   | $1.20   | $0.06            | $0.375             |
@@ -184,7 +182,6 @@ Los modelos gratuitos:

 - DeepSeek V4 Flash Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
 - MiniMax M2.5 Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
- Ring 2.6 1T Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
 - Nemotron 3 Super Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
 - Big Pickle es un modelo stealth que es gratuito en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.

@@ -240,7 +237,6 @@ Todos nuestros modelos están alojados en US. Nuestros proveedores siguen una po
 - Big Pickle: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo.
 - DeepSeek V4 Flash Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo.
 - MiniMax M2.5 Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo.
- Ring 2.6 1T Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo.
 - Nemotron 3 Super Free (endpoints gratuitos de NVIDIA): Se ofrece bajo los [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Solo para uso de prueba, no para producción ni datos sensibles. NVIDIA registra los prompts y las salidas para mejorar sus modelos y servicios. No envíes datos personales ni confidenciales.
 - OpenAI APIs: Las solicitudes se conservan durante 30 días de acuerdo con [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Las solicitudes se conservan durante 30 días de acuerdo con [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
@@ -94,7 +94,6 @@ Vous pouvez également accéder à nos modèles via les points de terminaison AP
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 Le [model id](/docs/config/#models) dans votre configuration OpenCode utilise le format `opencode/<model-id>`. Par exemple, pour GPT 5.5, vous utiliseriez `opencode/gpt-5.5` dans votre configuration.
@@ -120,7 +119,6 @@ Nous prenons en charge un modèle de paiement à l'utilisation. Vous trouverez c
 | Big Pickle                        | Free   | Free    | Free        | -            |
 | DeepSeek V4 Flash Free            | Free   | Free    | Free        | -            |
 | MiniMax M2.5 Free                 | Free   | Free    | Free        | -            |
-| Ring 2.6 1T Free                  | Free   | Free    | Free        | -            |
 | Nemotron 3 Super Free             | Free   | Free    | Free        | -            |
 | MiniMax M2.7                      | $0.30  | $1.20   | $0.06       | $0.375       |
 | MiniMax M2.5                      | $0.30  | $1.20   | $0.06       | $0.375       |
@@ -173,7 +171,6 @@ Les modèles gratuits :

 - DeepSeek V4 Flash Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
 - MiniMax M2.5 Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
- Ring 2.6 1T Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
 - Nemotron 3 Super Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
 - Big Pickle est un modèle stealth gratuit sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.

@@ -226,7 +223,6 @@ Tous nos modèles sont hébergés aux US. Nos fournisseurs suivent une politique
 - Big Pickle : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle.
 - DeepSeek V4 Flash Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle.
 - MiniMax M2.5 Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle.
- Ring 2.6 1T Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle.
 - Nemotron 3 Super Free (endpoints NVIDIA gratuits) : Fourni dans le cadre des [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Réservé à un usage d'essai, pas à la production ni aux données sensibles. Les prompts et les sorties sont journalisés par NVIDIA pour améliorer ses modèles et services. N'envoyez pas de données personnelles ou confidentielles.
 - OpenAI APIs : Les requêtes sont conservées pendant 30 jours conformément à [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs : Les requêtes sont conservées pendant 30 jours conformément à [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
@@ -103,7 +103,6 @@ Puoi anche accedere ai nostri modelli tramite i seguenti endpoint API.
 | Kimi K2.6              | kimi-k2.6              | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Big Pickle             | big-pickle             | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | DeepSeek V4 Flash Free | deepseek-v4-flash-free | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
-| Ring 2.6 1T            | ring-2.6-1t-free       | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Super Free  | nemotron-3-super-free  | `https://opencode.ai/zen/v1/chat/completions`      | `@ai-sdk/openai-compatible` |

 Il [model id](/docs/config/#models) nella config di OpenCode
@@ -131,7 +130,6 @@ Supportiamo un modello pay-as-you-go. Qui sotto trovi i prezzi **per 1M token**.
 | Big Pickle                        | Free   | Free    | Free        | -            |
 | DeepSeek V4 Flash Free            | Free   | Free    | Free        | -            |
 | MiniMax M2.5 Free                 | Free   | Free    | Free        | -            |
-| Ring 2.6 1T Free                  | Free   | Free    | Free        | -            |
 | Nemotron 3 Super Free             | Free   | Free    | Free        | -            |
 | MiniMax M2.7                      | $0.30  | $1.20   | $0.06       | $0.375       |
 | MiniMax M2.5                      | $0.30  | $1.20   | $0.06       | $0.375       |
@@ -184,7 +182,6 @@ I modelli gratuiti:

 - DeepSeek V4 Flash Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
 - MiniMax M2.5 Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
- Ring 2.6 1T Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
 - Nemotron 3 Super Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
 - Big Pickle è un modello stealth che è gratuito su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.

@@ -240,7 +237,6 @@ Tutti i nostri modelli sono ospitati negli US. I nostri provider seguono una pol
 - Big Pickle: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello.
 - DeepSeek V4 Flash Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello.
 - MiniMax M2.5 Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello.
- Ring 2.6 1T Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello.
 - Nemotron 3 Super Free (endpoint NVIDIA gratuiti): fornito secondo i [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Solo per uso di prova, non per produzione o dati sensibili. NVIDIA registra prompt e output per migliorare i propri modelli e servizi. Non inviare dati personali o riservati.
 - OpenAI APIs: le richieste vengono conservate per 30 giorni in conformità con [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: le richieste vengono conservate per 30 giorni in conformità con [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
opencode	2b92c5677e	release: v1.15.4	2026-05-17 17:44:40 +00:00
Frank	468eb68878	zen: update monitoring query	2026-05-17 13:15:39 -04:00
DaxandGitHub	23b594de6e	fix: preserve bus instance context (#28051 )	2026-05-17 12:56:42 -04:00
Frank	5060577ee1	sync	2026-05-17 12:37:47 -04:00
Aiden Cline GitHubopencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>rekram1-node	d3ebb1f7c0	ignore: cleanup readme (#28049 ) Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com> Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-05-17 11:26:23 -05:00
Shoubhit DashandGitHub	e4cc4e1682	fix(lsp): preserve instance ref for update events (#28016 )	2026-05-17 16:37:00 +05:30
opencode-agent[bot]	53e89f9d52	chore: generate	2026-05-17 08:06:12 +00:00
Frank	de247b7aae	sync	2026-05-17 04:04:39 -04:00
Frank	0b8050d453	sync	2026-05-17 01:59:20 -04:00
Gustavo Viana GitHub Victor Navarro	be6a89a3b8	docs: update README.es.md (#27739 ) Co-authored-by: Victor Navarro <vn4varro@gmail.com>	2026-05-16 19:33:24 +02:00
Kit LangtonandGitHub	c0a8b509c7	style(tui): distinguish markdown h1 headings (#27814 )	2026-05-16 11:18:17 -04:00
opencode	f80651fa91	sync release versions for v1.15.3	2026-05-16 14:07:33 +00:00
Shoubhit DashandGitHub	68af95390d	fix: hide task background instructions by default (#27872 )	2026-05-16 19:18:15 +05:30
opencode-agent[bot]	321db7a819	chore: generate	2026-05-16 13:27:23 +00:00
Dax Raad	6d2219e001	fix(cli): preserve instance context in async commands	2026-05-16 09:25:45 -04:00
opencode-agent[bot]	dd432e3cde	chore: generate	2026-05-16 13:21:57 +00:00
Dax Raad	77db212a0a	fix read stream byte cap	2026-05-16 09:20:35 -04:00
opencode	f56263791c	sync release versions for v1.15.2	2026-05-16 12:53:10 +00:00
Dax Raad	88363f1ed9	fixed issue in opencode run	2026-05-16 08:27:25 -04:00
JackandGitHub	c5db39f626	Remove Ring 2.6 1T from Zen docs (#27849 )	2026-05-16 17:55:32 +08:00
vimtor	b5aed287ca	chore: reduce alerts noise	2026-05-16 09:39:13 +02:00
DaxandGitHub	53849bd866	fix(sync): publish events on injected project bus (#27825 )	2026-05-16 05:56:49 +00:00
opencode	e33912bfee	sync release versions for v1.15.1	2026-05-16 05:44:44 +00:00
Aiden ClineandGitHub	548648a3d9	core: reduce prompts for shell, todowrite, and task tools (#26821 )	2026-05-16 00:18:47 -05:00
Caleb NortonandGitHub	4643e13170	feat(nix): add opencode-electron derivation (#16163 )	2026-05-15 23:20:48 -05:00
Dax Raad	042e6a5c86	tui: newly pinned sessions now append to the end of the list instead of jumping to the top	2026-05-15 23:57:40 -04:00
Dax Raad	e36d6a0cbe	core: clarify postinstall error message when binary is missing Users installing with pnpm or --ignore-scripts now see a clear explanation of why the native binary is missing and exact steps to fix it. The shell script wrapper provides more actionable guidance than the previous Node.js fallback that only suggested running the postinstall script without context about why it wasn't run automatically.	2026-05-15 23:12:00 -04:00
SebastianandGitHub	cc9c0b15c7	Revert "add dialog prompt submit keybind (#27807 )" (#27815 )	2026-05-16 04:44:32 +02:00
Kit LangtonandGitHub	f3b0d3d7ac	fix(tui): dedupe consecutive prompt history entries (#27816 )	2026-05-16 02:36:35 +00:00
opencode-agent[bot]	764c6bc517	chore: update nix node_modules hashes	2026-05-16 01:20:56 +00:00
SebastianandGitHub	d441e931f9	add dialog prompt submit keybind (#27807 )	2026-05-16 03:11:46 +02:00
SebastianandGitHub	ad79ad9ea8	upgrade opentui to 0.2.11 (#27808 )	2026-05-16 03:05:54 +02:00
opencode-agent[bot]	d6b23fd8f6	chore: generate	2026-05-16 00:44:10 +00:00
Kit LangtonandGitHub	5911bd532d	fix(tui): show config error details on startup (#27803 )	2026-05-15 20:42:56 -04:00
Dax Raad	2385123f03	Fix thinking toggle defaults	2026-05-15 20:27:36 -04:00
DaxandGitHub	09549661e1	Fix npm CLI binary installation (#27801 )	2026-05-15 18:43:37 -04:00
				`@@ -0,0 +1 @@`
				ALTER TABLE `coupon` MODIFY COLUMN `type` enum('BUILDATHON','GO1MONTH50','GOFREEMONTH','GO3MONTHS100','GO6MONTHS100','GO12MONTHS100') NOT NULL;