oh-my-opencode 4.19.0 → 4.19.2

package/.agents/command/omomomo.md

@@ -17,7 +17,7 @@ Print the following message to the user EXACTLY as written (in a friendly, celeb
 
 **Oh My OpenCode** is a powerful OpenCode plugin that transforms your AI agent into a full development team:
 
-- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.5), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
+- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.6 Sol), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
 - 🔧 **LSP Tools**: Full IDE capabilities for your agents - hover, goto definition, find references, rename, code actions
 - 🔍 **AST-Grep**: Structural code search and replace across 25 languages
 - 📚 **Built-in MCPs**: Context7 for docs, Exa for web search, grep.app for GitHub code search

package/.agents/skills/omomomo/SKILL.md

@@ -17,7 +17,7 @@ Print the following message to the user EXACTLY as written (in a friendly, celeb
 
 **Oh My OpenCode** is a powerful OpenCode plugin that transforms your AI agent into a full development team:
 
-- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.5), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
+- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.6 Sol), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
 - 🔧 **LSP Tools**: Full IDE capabilities for your agents - hover, goto definition, find references, rename, code actions
 - 🔍 **AST-Grep**: Structural code search and replace across 25 languages
 - 📚 **Built-in MCPs**: Context7 for docs, Exa for web search, grep.app for GitHub code search

package/.opencode/command/omomomo.md

@@ -17,7 +17,7 @@ Print the following message to the user EXACTLY as written (in a friendly, celeb
 
 **Oh My OpenCode** is a powerful OpenCode plugin that transforms your AI agent into a full development team:
 
-- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.5), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
+- 🤖 **Multi-Agent Orchestration**: Oracle (GPT-5.6 Sol), Librarian & Explore (GPT-5.4 Mini Fast), Frontend Engineer (Gemini), and more
 - 🔧 **LSP Tools**: Full IDE capabilities for your agents - hover, goto definition, find references, rename, code actions
 - 🔍 **AST-Grep**: Structural code search and replace across 25 languages
 - 📚 **Built-in MCPs**: Context7 for docs, Exa for web search, grep.app for GitHub code search

package/README.ja.md

@@ -49,7 +49,7 @@
 
 </div>
 
-> これは oh-my-openagent の Team Mode 実行中の様子です。Kimi K2.6 と GPT-5.5 で動いています。
+> これは oh-my-openagent の Team Mode 実行中の様子です。Kimi K3 と GPT-5.6 Sol で動いています。
 
 > Anthropic は [**私たちのせいで OpenCode をブロックしました。**](https://x.com/thdxr/status/2010149530486911014) **これは本当の話です。**
 > 彼らはあなたを囲い込みたいのです。Claude Code は居心地の良い牢獄ですが、牢獄であることには変わりありません。
@@ -193,17 +193,17 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
 </tr></table>
 
-**Sisyphus** (`claude-opus-4-8` / `claude-opus-4-7` / **`kimi-k3`** / **`kimi-k2.6`** / **`glm-5`**) はあなたのメインオーケストレーターです。計画を立て、専門家に委任し、攻撃的な並列実行でタスクを完了まで推進します。途中で投げ出すことはありません。thinking token のコストを許容できる場合は **Kimi K3** を、そうでなければ **Claude Opus 4.8 / 4.7** または **Kimi K2.6** を推奨します。
+**Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**) はあなたのメインオーケストレーターです。計画を立て、専門家に委任し、攻撃的な並列実行でタスクを完了まで推進します。途中で投げ出すことはありません。Claude Opus 5 と Kimi K3 が推奨デフォルトです。
 
-**Hephaestus** (OpenAI または Vercel では `gpt-5.6-sol`、その次に `gpt-5.5`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを調査し、エンドツーエンドで実行します。*正当なる職人 (The Legitimate Craftsman).*
+**Hephaestus** (OpenAI、GitHub Copilot、Vercel、または OpenCode 経由で medium effort の `gpt-5.6-sol` のみを使う) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを調査し、エンドツーエンドで実行します。*正当なる職人 (The Legitimate Craftsman).*
 
-**Prometheus** (`claude-opus-4-7` / **`gpt-5.5`** / **`glm-5.2`**) はあなたの戦略プランナーです。インタビューモードで質問を投げ、スコープを特定し、コードに一行触れる前に詳細な計画を構築します。
+**Prometheus** (`claude-fable-5` / **`kimi-k3`**) はあなたの戦略プランナーです。インタビューモードで質問を投げ、スコープを特定し、コードに一行触れる前に詳細な計画を構築します。
 
 すべてのエージェントは、それぞれのモデルの強みに合わせてチューニングされています。手動でモデルを切り替える必要はありません。[詳しくはこちら →](docs/guide/overview.md)
 
 > Anthropic が [私たちのせいで OpenCode をブロックしました。](https://x.com/thdxr/status/2010149530486911014) だからこそ Hephaestus は「正当なる職人 (The Legitimate Craftsman)」と呼ばれているのです。皮肉を込めています。
 >
-> Opus または Kimi K3 で最もよく動きますが、Kimi K2.6 + GPT-5.5 の組み合わせだけでも、バニラの Claude Code を軽く凌駕します。設定は一切不要です。
+> Opus または Kimi K3 で最もよく動きますが、Kimi K3 + GPT-5.6 Sol の組み合わせだけでも、バニラの Claude Code を軽く凌駕します。設定は一切不要です。
 
 ### Team Mode (v4.0)
 
@@ -240,7 +240,7 @@ Sisyphus がサブエージェントにタスクを委任する際、モデル
 | `quick`              | 単一ファイルの変更、タイポの修正     |
 | `ultrabrain`         | ハードロジック、アーキテクチャの決定 |
 
-エージェントは作業の種類を伝えるだけで、ハーネスが適切なモデルを選びます。`ultrabrain` は OpenAI または Vercel で利用可能な場合は GPT-5.6 Sol xhigh に、その次に GPT-5.5 xhigh にルーティングされます。あなたが触るものは何もありません。
+エージェントは作業の種類を伝えるだけで、ハーネスが適切なモデルを選びます。`ultrabrain` は OpenAI または Vercel で利用可能な場合は GPT-5.6 Sol xhigh に、その次に GPT-5.6 Sol xhigh にルーティングされます。あなたが触るものは何もありません。
 
 ### Claude Code 互換性
 

package/README.ko.md

@@ -48,7 +48,7 @@
 
 </div>
 
-> 이건 oh-my-openagent의 Team Mode 동작 장면입니다. Kimi K2.6과 GPT-5.5로요.
+> 이건 oh-my-openagent의 Team Mode 동작 장면입니다. Kimi K3과 GPT-5.6 Sol로요.
 
 > Anthropic은 [**우리 때문에 OpenCode를 차단했습니다.**](https://x.com/thdxr/status/2010149530486911014) **진짜입니다.**
 > 그들은 당신을 가둬두고 싶어 합니다. Claude Code는 좋은 감옥이지만, 여전히 감옥입니다.
@@ -194,17 +194,17 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
 </tr></table>
 
-**Sisyphus** (`claude-opus-4-8` / `claude-opus-4-7` / **`kimi-k3`** / **`kimi-k2.6`** / **`glm-5`**)는 메인 오케스트레이터입니다. 계획을 세우고, 전문가에게 위임하고, 공격적인 병렬 실행으로 작업을 끝까지 밀어붙입니다. 중간에 멈추지 않습니다. thinking token 비용을 감수할 수 있다면 **Kimi K3**를, 그렇지 않으면 **Claude Opus 4.8 / 4.7** 또는 **Kimi K2.6**을 권장합니다.
+**Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**)는 메인 오케스트레이터입니다. 계획을 세우고, 전문가에게 위임하고, 공격적인 병렬 실행으로 작업을 끝까지 밀어붙입니다. 중간에 멈추지 않습니다. Claude Opus 5와 Kimi K3가 권장 기본값입니다.
 
-**Hephaestus** (OpenAI 또는 Vercel에서 `gpt-5.6-sol`, 그다음 `gpt-5.5`)는 자율적으로 깊게 파는 작업자입니다. 레시피가 아니라 목표를 주세요. 코드베이스를 탐색하고, 패턴을 조사하고, 손을 잡아주지 않아도 엔드투엔드로 실행합니다. *The Legitimate Craftsman.*
+**Hephaestus** (OpenAI, GitHub Copilot, Vercel 또는 OpenCode에서 medium effort의 `gpt-5.6-sol`만 사용하는)는 자율적으로 깊게 파는 작업자입니다. 레시피가 아니라 목표를 주세요. 코드베이스를 탐색하고, 패턴을 조사하고, 손을 잡아주지 않아도 엔드투엔드로 실행합니다. *The Legitimate Craftsman.*
 
-**Prometheus** (`claude-opus-4-7` / **`gpt-5.5`** / **`glm-5.2`**)는 전략 플래너입니다. 인터뷰 모드: 질문으로 스코프를 파악하고, 코드에 손대기 전에 상세한 계획을 만듭니다.
+**Prometheus** (`claude-fable-5` / **`kimi-k3`**)는 전략 플래너입니다. 인터뷰 모드: 질문으로 스코프를 파악하고, 코드에 손대기 전에 상세한 계획을 만듭니다.
 
 모든 에이전트는 자기 모델의 강점에 맞춰 튜닝되어 있습니다. 수동으로 모델을 돌려가며 쓸 필요가 없습니다. [더 알아보기 →](docs/guide/overview.md)
 
 > Anthropic은 [우리 때문에 OpenCode를 차단했습니다.](https://x.com/thdxr/status/2010149530486911014) 그래서 Hephaestus에게 "The Legitimate Craftsman"이라는 별명이 붙었습니다. 의도된 아이러니입니다.
 >
-> Opus나 Kimi K3에서 가장 잘 돌지만, Kimi K2.6 + GPT-5.5 조합만으로도 이미 바닐라 Claude Code를 이깁니다. 별도 설정 없이요.
+> Opus나 Kimi K3에서 가장 잘 돌지만, Kimi K3 + GPT-5.6 Sol 조합만으로도 이미 바닐라 Claude Code를 이깁니다. 별도 설정 없이요.
 
 ### Team Mode (v4.0)
 
@@ -241,7 +241,7 @@ Sisyphus가 서브에이전트에 위임할 때는 모델을 직접 고르지
 | `quick`              | 단일 파일 변경, 오타 수정            |
 | `ultrabrain`         | 어려운 로직, 아키텍처 결정           |
 
-에이전트는 필요한 작업 종류만 말하고, 하네스가 적합한 모델을 고릅니다. `ultrabrain`은 OpenAI 또는 Vercel에서 사용 가능하면 GPT-5.6 Sol xhigh로, 그다음 GPT-5.5 xhigh로 라우팅됩니다. 당신이 건드릴 건 없습니다.
+에이전트는 필요한 작업 종류만 말하고, 하네스가 적합한 모델을 고릅니다. `ultrabrain`은 OpenAI 또는 Vercel에서 사용 가능하면 GPT-5.6 Sol xhigh로, 그다음 GPT-5.6 Sol xhigh로 라우팅됩니다. 당신이 건드릴 건 없습니다.
 
 ### Claude Code 호환성
 

package/README.md

@@ -48,7 +48,7 @@
 
 </div>
 
-> This is oh-my-openagent, running Team Mode. With Kimi K2.6 and GPT-5.5.
+> This is oh-my-openagent, running Team Mode. With Kimi K3 and GPT-5.6 Sol.
 
 > Anthropic [**blocked OpenCode because of us.**](https://x.com/thdxr/status/2010149530486911014) **Yes, this is true.**
 > They want you locked in. Claude Code is a nice prison, but it's still a prison.
@@ -241,17 +241,17 @@ Even with only the following subscriptions, `ultrawork` works well (this project
 <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
 </tr></table>
 
-**Sisyphus** (`claude-opus-4-8` / `claude-opus-4-7` / **`kimi-k3`** / **`kimi-k2.6`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway. Use **Kimi K3** when you can accept its thinking-token cost; otherwise **Claude Opus 4.8 / 4.7** or **Kimi K2.6** are the recommended defaults.
+**Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway. Claude Opus 5 and Kimi K3 are the recommended defaults.
 
-**Hephaestus** (`gpt-5.6-sol` on OpenAI or Vercel, then `gpt-5.5`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
+**Hephaestus** (`gpt-5.6-sol` through OpenAI, GitHub Copilot, Vercel, or OpenCode at medium effort) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
 
-**Prometheus** (`claude-opus-4-7` / **`gpt-5.5`** / **`glm-5.2`** ) is your strategic planner. Interview mode: he asks questions, identifies scope, and builds a detailed plan before a single line of code is touched.
+**Prometheus** (`claude-fable-5` / **`kimi-k3`**) is your strategic planner. Interview mode: he asks questions, identifies scope, and builds a detailed plan before a single line of code is touched.
 
 Every agent is tuned to its model's specific strengths. No manual model juggling. [Learn more →](docs/guide/overview.md)
 
 > Anthropic [blocked OpenCode because of us.](https://x.com/thdxr/status/2010149530486911014) That's why Hephaestus is called "The Legitimate Craftsman." The irony is intentional.
 >
-> We run best on Opus or Kimi K3, but Kimi K2.6 + GPT-5.5 already beats vanilla Claude Code. Zero config needed.
+> We run best on Opus or Kimi K3, but Kimi K3 + GPT-5.6 Sol already beats vanilla Claude Code. Zero config needed.
 
 ### Team Mode (v4.0)
 
@@ -288,7 +288,7 @@ When Sisyphus delegates to a subagent, it doesn't pick a model. It picks a **cat
 | `quick`              | Single-file changes, typos         |
 | `ultrabrain`         | Hard logic, architecture decisions |
 
-The agent says what kind of work it needs; the harness picks the right model. `ultrabrain` now routes to GPT-5.6 Sol xhigh through OpenAI or Vercel when available, then GPT-5.5 xhigh. You touch nothing.
+The agent says what kind of work it needs; the harness picks the right model. `ultrabrain` now routes to GPT-5.6 Sol xhigh through OpenAI or Vercel when available, then GPT-5.6 Sol xhigh. You touch nothing.
 
 ### Claude Code Compatibility
 

package/README.ru.md

@@ -49,7 +49,7 @@
 
 </div>
 
-> Это oh-my-openagent в режиме Team Mode. С Kimi K2.6 и GPT-5.5.
+> Это oh-my-openagent в режиме Team Mode. С Kimi K3 и GPT-5.6 Sol.
 
 > Anthropic [**заблокировал OpenCode из-за нас.**](https://x.com/thdxr/status/2010149530486911014) **Да, это правда.**
 > Они хотят держать вас в замкнутой системе. Claude Code — красивая тюрьма, но всё равно тюрьма.
@@ -192,17 +192,17 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
 </tr></table>
 
-**Sisyphus** (`claude-opus-4-8` / `claude-opus-4-7` / **`kimi-k3`** / **`kimi-k2.6`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути. Используйте **Kimi K3**, если готовы оплатить повышенный расход thinking-токенов; иначе рекомендуем **Claude Opus 4.8 / 4.7** или **Kimi K2.6**.
+**Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути. Claude Opus 5 и Kimi K3 — рекомендуемые значения по умолчанию.
 
-**Hephaestus** (`gpt-5.6-sol` через OpenAI или Vercel, затем `gpt-5.5`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
+**Hephaestus** (использует только `gpt-5.6-sol` с medium effort через OpenAI, GitHub Copilot, Vercel или OpenCode) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
 
-**Prometheus** (`claude-opus-4-7` / **`gpt-5.5`** / **`glm-5.2`**) — стратегический планировщик. Режим интервью: он задаёт вопросы, определяет объём работ и формирует детальный план до того, как написана хотя бы одна строка кода.
+**Prometheus** (`claude-fable-5` / **`kimi-k3`**) — стратегический планировщик. Режим интервью: он задаёт вопросы, определяет объём работ и формирует детальный план до того, как написана хотя бы одна строка кода.
 
 Каждый агент настроен под сильные стороны своей модели. Никакого ручного переключения между моделями. [Подробнее →](docs/guide/overview.md)
 
 > Anthropic [заблокировал OpenCode из-за нас.](https://x.com/thdxr/status/2010149530486911014) Именно поэтому Hephaestus зовётся «Законным Мастером». Ирония намеренная.
 >
-> Мы работаем лучше всего на Opus или Kimi K3, но Kimi K2.6 + GPT-5.5 уже превосходят ванильный Claude Code. Никакой настройки не требуется.
+> Мы работаем лучше всего на Opus или Kimi K3, но Kimi K3 + GPT-5.6 Sol уже превосходят ванильный Claude Code. Никакой настройки не требуется.
 
 ### Team Mode (v4.0)
 
@@ -239,7 +239,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 | `quick`              | Изменения в одном файле, опечатки     |
 | `ultrabrain`         | Сложная логика, архитектурные решения |
 
-Агент сообщает тип задачи, а обвязка подбирает нужную модель. `ultrabrain` направляется в GPT-5.6 Sol xhigh через OpenAI или Vercel, когда они доступны, затем в GPT-5.5 xhigh. Вы ни к чему не прикасаетесь.
+Агент сообщает тип задачи, а обвязка подбирает нужную модель. `ultrabrain` направляется в GPT-5.6 Sol xhigh через OpenAI или Vercel, когда они доступны, затем в GPT-5.6 Sol xhigh. Вы ни к чему не прикасаетесь.
 
 ### Совместимость с Claude Code
 

package/README.zh-cn.md

@@ -49,7 +49,7 @@
 
 </div>
 
-> 这是 oh-my-openagent 运行 Team Mode 的画面。搭配 Kimi K2.6 和 GPT-5.5。
+> 这是 oh-my-openagent 运行 Team Mode 的画面。搭配 Kimi K3 和 GPT-5.6 Sol。
 
 > Anthropic [**因为我们屏蔽了 OpenCode。**](https://x.com/thdxr/status/2010149530486911014) **这是真的。**
 > 他们想把你锁住。Claude Code 是个漂亮的牢笼，但仍然是牢笼。
@@ -199,17 +199,17 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 <td align="center"><img src=".github/assets/hephaestus.png" height="300" /></td>
 </tr></table>
 
-**Sisyphus** (`claude-opus-4-8` / `claude-opus-4-7` / **`kimi-k3`** / **`kimi-k2.6`** / **`glm-5`**) 是你的主指挥官。他负责制定计划、分配任务给专家团队，并以极其激进的并行策略推动任务直至完成。他从不半途而废。如果你能接受 thinking token 的成本，请使用 **Kimi K3**；否则推荐使用 **Claude Opus 4.8 / 4.7** 或 **Kimi K2.6**。
+**Sisyphus** (`claude-opus-5` / **`kimi-k3`** / **`glm-5`**) 是你的主指挥官。他负责制定计划、分配任务给专家团队，并以极其激进的并行策略推动任务直至完成。他从不半途而废。Claude Opus 5 和 Kimi K3 是推荐默认值。
 
-**Hephaestus** (在 OpenAI 或 Vercel 上优先 `gpt-5.6-sol`，其次 `gpt-5.5`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
+**Hephaestus** (仅通过 OpenAI、GitHub Copilot、Vercel 或 OpenCode 使用 medium effort 的 `gpt-5.6-sol`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
 
-**Prometheus** (`claude-opus-4-7` / **`gpt-5.5`** / **`glm-5.2`**) 是你的战略规划师。他通过访谈模式，在动一行代码之前，先通过提问确定范围并构建详尽的执行计划。
+**Prometheus** (`claude-fable-5` / **`kimi-k3`**) 是你的战略规划师。他通过访谈模式，在动一行代码之前，先通过提问确定范围并构建详尽的执行计划。
 
 每一个 Agent 都针对其底层模型的特点进行了专门调优。你无需手动来回切换模型。[阅读背景设定了解更多 →](docs/guide/overview.md)
 
 > Anthropic [因为我们屏蔽了 OpenCode](https://x.com/thdxr/status/2010149530486911014)。这就是为什么我们将 Hephaestus 命名为"正牌工匠 (The Legitimate Craftsman)"。这是一个故意的讽刺。
 >
-> 我们在 Opus 或 Kimi K3 上运行得最好，但仅仅使用 Kimi K2.6 + GPT-5.5 就足以碾压原版的 Claude Code。完全不需要配置。
+> 我们在 Opus 或 Kimi K3 上运行得最好，但仅仅使用 Kimi K3 + GPT-5.6 Sol 就足以碾压原版的 Claude Code。完全不需要配置。
 
 ### Team Mode (v4.0)
 
@@ -246,7 +246,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 | `quick`              | 单文件修改、修错字     |
 | `ultrabrain`         | 复杂硬核逻辑、架构决策 |
 
-智能体只需要说明要做什么类型的工作，框架就会挑选出最合适的模型去干。`ultrabrain` 在 OpenAI 或 Vercel 可用时优先路由到 GPT-5.6 Sol xhigh，其次是 GPT-5.5 xhigh。你完全不需要操心。
+智能体只需要说明要做什么类型的工作，框架就会挑选出最合适的模型去干。`ultrabrain` 在 OpenAI 或 Vercel 可用时优先路由到 GPT-5.6 Sol xhigh，其次是 GPT-5.6 Sol xhigh。你完全不需要操心。
 
 ### 完全兼容 Claude Code
 

package/dist/agents/atlas/agent.d.ts

@@ -5,7 +5,7 @@
  *
  * Prompt routing (`getAtlasPromptSource`, evaluated by prompts-core variant order):
  * 1. Claude Opus 4.7       → opus-4-7.md   (literal-following + explicit fan-out push)
- * 2. GPT family            → gpt.md        (calibrated for GPT-5.5)
+ * 2. GPT family            → gpt.md        (shared GPT-family calibration)
  * 3. Gemini family         → gemini.md
  * 4. Kimi K3              → kimi-k3.md    (K3-native; checked first among Kimi)
  * 5. Kimi K2.7             → kimi-k2-7.md  (restrained, outcome-first; checked before generic kimi)
@@ -14,9 +14,10 @@
  * 8. Default (Claude 4.6 family: opus-4-6, sonnet-4-6, haiku-4-5, etc.) → default.md
  */
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "../types";
+import type { AgentMode, AgentPromptMetadata } from "../types";
 import type { AvailableAgent, AvailableSkill } from "../dynamic-agent-prompt-builder";
 import type { CategoryConfig } from "../../config/schema";
+declare const MODE: AgentMode;
 export type AtlasPromptSource = "default" | "gpt" | "gemini" | "kimi" | "kimi-k3" | "kimi-k2-7" | "opus-4-7" | "glm";
 export declare function getAtlasPromptSource(model?: string): AtlasPromptSource;
 export interface OrchestratorContext {
@@ -28,6 +29,7 @@ export interface OrchestratorContext {
 export declare function getAtlasPrompt(model?: string): string;
 export declare function createAtlasAgent(ctx: OrchestratorContext): AgentConfig;
 export declare namespace createAtlasAgent {
-    var mode: "primary";
+    export { MODE as mode };
 }
 export declare const atlasPromptMetadata: AgentPromptMetadata;
+export {};

package/dist/agents/explore.d.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 export declare const EXPLORE_PROMPT_METADATA: AgentPromptMetadata;
 export declare function createExploreAgent(model: string): AgentConfig;
 export declare namespace createExploreAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/gpt-prompt-identity.d.ts

@@ -0,0 +1,3 @@
+export type GptPromptIdentityKey = "gpt-5.5" | "gpt-5.6-sol" | "gpt-family";
+export declare function getGptPromptIdentityKey(model?: string): GptPromptIdentityKey;
+export declare function getGptPromptIdentity(model?: string): string;

package/dist/agents/hephaestus/agent.d.ts

@@ -1,6 +1,7 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "../types";
+import type { AgentMode, AgentPromptMetadata } from "../types";
 import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder";
+declare const MODE: AgentMode;
 export type HephaestusPromptSource = "gpt-5-6" | "gpt-5-5" | "gpt-5-4" | "gpt";
 export declare class UnsupportedHephaestusModelError extends Error {
     readonly model: string | undefined;
@@ -19,6 +20,7 @@ export interface HephaestusContext {
 export declare function getHephaestusPrompt(model?: string, useTaskSystem?: boolean): string;
 export declare function createHephaestusAgent(model: string, availableAgents?: AvailableAgent[], availableToolNames?: string[], availableSkills?: AvailableSkill[], availableCategories?: AvailableCategory[], useTaskSystem?: boolean): AgentConfig;
 export declare namespace createHephaestusAgent {
-    var mode: "primary";
+    export { MODE as mode };
 }
 export declare const hephaestusPromptMetadata: AgentPromptMetadata;
+export {};

package/dist/agents/librarian.d.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 export declare const LIBRARIAN_PROMPT_METADATA: AgentPromptMetadata;
 export declare function createLibrarianAgent(model: string): AgentConfig;
 export declare namespace createLibrarianAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/metis.d.ts

@@ -1,5 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 /**
  * Metis - Plan Consultant Agent
  *
@@ -17,6 +18,7 @@ export declare const METIS_SYSTEM_PROMPT: string;
 export declare const METIS_K2_7_SYSTEM_PROMPT: string;
 export declare function createMetisAgent(model: string): AgentConfig;
 export declare namespace createMetisAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
 export declare const metisPromptMetadata: AgentPromptMetadata;
+export {};

package/dist/agents/momus.d.ts

@@ -1,5 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 /**
  * Momus - Plan Reviewer Agent
  *
@@ -20,6 +21,6 @@ declare const MOMUS_DEFAULT_PROMPT = "You are a **practical** work plan reviewer
 export { MOMUS_DEFAULT_PROMPT as MOMUS_SYSTEM_PROMPT };
 export declare function createMomusAgent(model: string): AgentConfig;
 export declare namespace createMomusAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
 export declare const momusPromptMetadata: AgentPromptMetadata;

package/dist/agents/multimodal-looker.d.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 export declare const MULTIMODAL_LOOKER_PROMPT_METADATA: AgentPromptMetadata;
 export declare function createMultimodalLookerAgent(model: string): AgentConfig;
 export declare namespace createMultimodalLookerAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/oracle.d.ts

@@ -1,7 +1,9 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import type { AgentPromptMetadata } from "./types";
+import type { AgentMode, AgentPromptMetadata } from "./types";
+declare const MODE: AgentMode;
 export declare const ORACLE_PROMPT_METADATA: AgentPromptMetadata;
 export declare function createOracleAgent(model: string): AgentConfig;
 export declare namespace createOracleAgent {
-    var mode: "subagent";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/sisyphus/claude-opus-5.d.ts

@@ -0,0 +1,33 @@
+/**
+ * Claude Opus 5-native Sisyphus prompt - tuned for Opus 5 behaviors.
+ *
+ * Design principles (Anthropic "Prompting Claude Opus 5" guidance, applied to
+ * the Opus 4.8 skeleton - Opus 5 runs well on 4.8 prompts, so only the
+ * documented behavior deltas are tuned):
+ * - SCOPE CONSTRAINT replaces 4.8's over-asking counter: Opus 5 does not
+ *   under-ask, it over-does - it expands scope and adds unrequested steps.
+ *   Explicit "deliver what was asked, at the scope intended" calibration.
+ * - DELEGATION CAP replaces 4.8's capability under-reach counter: Opus 5
+ *   delegates to subagents MORE readily than prior models, so the 4.8
+ *   "DEFAULT BIAS: DELEGATE" push is inverted into domain-and-size gating,
+ *   with an explicit ban on verify-my-own-work subagents.
+ * - OVER-VERIFICATION REMOVAL: Opus 5 self-verifies without being told.
+ *   Evidence gates stay (they define WHAT counts as done) but run ONCE;
+ *   repeat-verification scaffolding is removed per Anthropic guidance.
+ * - NARRATION CADENCE: Opus 5 narrates readily and writes long responses;
+ *   effort controls thinking volume, not response length. One-sentence
+ *   opener, silence between tool calls, outcome-first wrap-ups, and a
+ *   closing <tone_preference> reminder (Anthropic-recommended for long
+ *   system prompts).
+ * - CORRECTION NARRATION limited to corrections that change the user's
+ *   code, conclusions, or decisions.
+ * - WRITTEN DELIVERABLE length calibrated: no filler sections or boilerplate.
+ * - LITERAL instruction following inherited from 4.7/4.8: state scope
+ *   explicitly.
+ * - XML-tagged anchors, Phase 0/1/2A/2B/2C/3 mental model, and shared dynamic
+ *   helpers identical to the other Claude variants so content stays in sync.
+ */
+import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder";
+import { categorizeTools } from "../dynamic-agent-prompt-builder";
+export declare function buildClaudeOpus5SisyphusPrompt(model: string, availableAgents: AvailableAgent[], availableTools?: AvailableTool[], availableSkills?: AvailableSkill[], availableCategories?: AvailableCategory[], useTaskSystem?: boolean): string;
+export { categorizeTools };

package/dist/agents/sisyphus/gpt-5-5.d.ts

@@ -1,5 +1,5 @@
 /**
- * GPT-5.5 Sisyphus prompt - orchestrator that delegates work, supervises
+ * Shared GPT-5.5/GPT-5.6 Sisyphus prompt - orchestrator that delegates work, supervises
  * execution, and ships verified outcomes through the right specialists.
  */
 import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "../dynamic-agent-prompt-builder";

package/dist/agents/sisyphus/gpt-task-system-guide.d.ts

@@ -0,0 +1 @@
+export declare function buildTaskSystemGuide(useTaskSystem: boolean): string;

package/dist/agents/sisyphus/index.d.ts

@@ -5,6 +5,7 @@
  * - default.ts: Base implementation for Claude and general models
  * - claude-opus-4-7.ts: Native Claude Opus 4.7 prompt with literal-instruction tuning
  * - claude-opus-4-8.ts: Native Claude Opus 4.8 prompt with silence-default + autonomy tuning
+ * - claude-opus-5.ts: Native Claude Opus 5 prompt with scope/delegation/verification caps
  * - claude-fable-5.ts: Native Claude Fable 5 prompt (Opus 4.8 direction, top-tier model)
  * - gemini.ts: Corrective overlays for Gemini's aggressive tendencies
  * - gpt-5-4.ts: Native GPT-5.4 prompt with block-structured guidance
@@ -16,6 +17,7 @@
 export { buildDefaultSisyphusPrompt, buildTaskManagementSection } from "./default";
 export { buildClaudeOpus47SisyphusPrompt } from "./claude-opus-4-7";
 export { buildClaudeOpus48SisyphusPrompt } from "./claude-opus-4-8";
+export { buildClaudeOpus5SisyphusPrompt } from "./claude-opus-5";
 export { buildClaudeFable5SisyphusPrompt } from "./claude-fable-5";
 export { buildGeminiToolMandate, buildGeminiDelegationOverride, buildGeminiVerificationOverride, buildGeminiIntentGateEnforcement, buildGeminiToolGuide, buildGeminiToolCallExamples, } from "./gemini";
 export { buildGpt54SisyphusPrompt } from "./gpt-5-4";

package/dist/agents/sisyphus-agent-factory.d.ts

@@ -1,5 +1,7 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
 import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder";
+import type { AgentMode } from "./types";
+declare const MODE: AgentMode;
 /**
  * Identifies which prompt body `createSisyphusAgent` bakes for a given model.
  * The whole Sisyphus prompt is model-family-specific and selected here, so this
@@ -7,9 +9,10 @@ import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynami
  * runtime model resolves to a different family than the configured one, the baked
  * body is the wrong family and must be rebuilt (issue #5297/#5316).
  */
-export type SisyphusPromptFamily = "kimi-k3" | "kimi-k2-7" | "kimi-k2-6" | "gpt-5-5" | "gpt-5-4" | "claude-fable-5" | "claude-opus-4-8" | "claude-opus-4-7" | "glm-5-2" | "fallback";
+export type SisyphusPromptFamily = "kimi-k3" | "kimi-k2-7" | "kimi-k2-6" | "gpt-5-5" | "gpt-5-4" | "claude-fable-5" | "claude-opus-5" | "claude-opus-4-8" | "claude-opus-4-7" | "glm-5-2" | "fallback";
 export declare function resolveSisyphusPromptFamily(model: string): SisyphusPromptFamily;
 export declare function createSisyphusAgent(model: string, availableAgents?: AvailableAgent[], availableToolNames?: string[], availableSkills?: AvailableSkill[], availableCategories?: AvailableCategory[], useTaskSystem?: boolean): AgentConfig;
 export declare namespace createSisyphusAgent {
-    var mode: "primary";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/sisyphus-junior/agent.d.ts

@@ -14,7 +14,9 @@
  * 7. Default (Claude, etc.) -> default.ts (Claude-optimized)
  */
 import type { AgentConfig } from "@opencode-ai/sdk";
+import type { AgentMode } from "../types";
 import type { AgentOverrideConfig } from "../../config/schema";
+declare const MODE: AgentMode;
 export declare const SISYPHUS_JUNIOR_DEFAULTS: {
     readonly model: "anthropic/claude-sonnet-4-6";
     readonly temperature: 0.1;
@@ -27,5 +29,6 @@ export declare function getSisyphusJuniorPromptSource(model?: string): SisyphusJ
 export declare function buildSisyphusJuniorPrompt(model: string | undefined, useTaskSystem: boolean, promptAppend?: string): string;
 export declare function createSisyphusJuniorAgentWithOverrides(override: AgentOverrideConfig | undefined, systemDefaultModel?: string, useTaskSystem?: boolean): AgentConfig;
 export declare namespace createSisyphusJuniorAgentWithOverrides {
-    var mode: "subagent";
+    export { MODE as mode };
 }
+export {};

package/dist/agents/sisyphus-junior/gpt-5-5.d.ts

@@ -1,5 +1,5 @@
 /**
- * GPT-5.5 Sisyphus-Junior prompt - focused executor for orchestrator-routed
+ * Shared GPT-5.5/GPT-5.6 Sisyphus-Junior prompt - focused executor for orchestrator-routed
  * categorized tasks, gated on personal manual QA of the artifact's surface.
  */
-export declare function buildGpt55SisyphusJuniorPrompt(useTaskSystem: boolean, promptAppend?: string): string;
+export declare function buildGpt55SisyphusJuniorPrompt(useTaskSystem: boolean, promptAppend?: string, model?: string): string;

package/dist/agents/types.d.ts

@@ -1,6 +1,6 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-import { isClaudeFable5Model, isClaudeFableOrMythosModel, isClaudeOpus46Model, isClaudeOpus47Model, isClaudeOpus47OrLaterModel, isClaudeOpus48Model, isGeminiModel, isGlmModel, isGptModel, isKimiK2Model, isKimiK27Model, isKimiK3Model, isMiniMaxModel } from "@oh-my-opencode/model-core";
-export { isClaudeFable5Model, isClaudeFableOrMythosModel, isClaudeOpus46Model, isClaudeOpus47Model, isClaudeOpus47OrLaterModel, isClaudeOpus48Model, isGeminiModel, isGlmModel, isGptModel, isKimiK2Model, isKimiK27Model, isKimiK3Model, isMiniMaxModel, };
+import { isClaudeFable5Model, isClaudeFableOrMythosModel, isClaudeOpus46Model, isClaudeOpus47Model, isClaudeOpus47OrLaterModel, isClaudeOpus48Model, isClaudeOpus5Model, isGeminiModel, isGlmModel, isGptModel, isKimiK2Model, isKimiK27Model, isKimiK3Model, isMiniMaxModel } from "@oh-my-opencode/model-core";
+export { isClaudeFable5Model, isClaudeFableOrMythosModel, isClaudeOpus46Model, isClaudeOpus47Model, isClaudeOpus47OrLaterModel, isClaudeOpus48Model, isClaudeOpus5Model, isGeminiModel, isGlmModel, isGptModel, isKimiK2Model, isKimiK27Model, isKimiK3Model, isMiniMaxModel, };
 /**
  * Anthropic Opus 4.7+, Fable, and Mythos models reject thinking.type "enabled";
  * they require adaptive thinking plus an effort, which OpenCode core derives from