diff options
| author | Shoubhit Dash <[email protected]> | 2026-04-16 17:30:14 +0530 |
|---|---|---|
| committer | Shoubhit Dash <[email protected]> | 2026-04-16 17:30:14 +0530 |
| commit | 2e18a603f0ea24154908e748493fd4bfaa74fc00 (patch) | |
| tree | b723e00af2821b213573b16fa199b64babd5f1f5 /packages/web/src | |
| parent | 9819eb04614fd607cacb07d754052f1531a82331 (diff) | |
| parent | 7341718f9234b0cf3a8758c87e91d2006b71bff6 (diff) | |
| download | opencode-2e18a603f0ea24154908e748493fd4bfaa74fc00.tar.gz opencode-2e18a603f0ea24154908e748493fd4bfaa74fc00.zip | |
merge dev
Diffstat (limited to 'packages/web/src')
91 files changed, 495 insertions, 616 deletions
diff --git a/packages/web/src/components/share/part.tsx b/packages/web/src/components/share/part.tsx index c7d177df7..34cfe3f42 100644 --- a/packages/web/src/components/share/part.tsx +++ b/packages/web/src/components/share/part.tsx @@ -730,7 +730,13 @@ export function FallbackTool(props: ToolProps) { <> <div></div> <div>{arg[0]}</div> - <div>{String(arg[1] ?? "")}</div> + <div> + {typeof arg[1] === "string" || typeof arg[1] === "number" || typeof arg[1] === "boolean" + ? String(arg[1]) + : arg[1] == null + ? "" + : JSON.stringify(arg[1])} + </div> </> )} </For> diff --git a/packages/web/src/content/docs/ar/go.mdx b/packages/web/src/content/docs/ar/go.mdx index 34ae96eaa..655749eea 100644 --- a/packages/web/src/content/docs/ar/go.mdx +++ b/packages/web/src/content/docs/ar/go.mdx @@ -59,6 +59,8 @@ OpenCode Go حاليًا في المرحلة التجريبية. - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** قد تتغير قائمة النماذج مع استمرارنا في اختبار نماذج جديدة وإضافتها. @@ -77,17 +79,25 @@ OpenCode Go حاليًا في المرحلة التجريبية. يوضح الجدول أدناه عددًا تقديريًا للطلبات بناءً على أنماط استخدام Go المعتادة: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| الطلبات لكل 5 ساعات | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| الطلبات في الأسبوع | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| الطلبات في الشهر | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | الطلبات لكل 5 ساعات | الطلبات في الأسبوع | الطلبات في الشهر | +| ------------ | ------------------- | ------------------ | ---------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | تستند التقديرات إلى متوسطات أنماط الطلبات المرصودة: - GLM-5/5.1 — 700 input، و52,000 cached، و150 output tokens لكل طلب - Kimi K2.5 — 870 input، و55,000 cached، و200 output tokens لكل طلب - MiniMax M2.7/M2.5 — 300 input، و55,000 cached، و125 output tokens لكل طلب +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 input، و41,000 cached، و250 output tokens لكل طلب - MiMo-V2-Omni — 1000 input، و60,000 cached، و140 output tokens لكل طلب @@ -120,6 +130,8 @@ OpenCode Go حاليًا في المرحلة التجريبية. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | يستخدم [model id](/docs/config/#models) في إعدادات OpenCode لديك التنسيق `opencode-go/<model-id>`. على سبيل المثال، بالنسبة إلى Kimi K2.5، ستستخدم `opencode-go/kimi-k2.5` في إعداداتك. diff --git a/packages/web/src/content/docs/ar/modes.mdx b/packages/web/src/content/docs/ar/modes.mdx index ac57b98e9..ed17670a5 100644 --- a/packages/web/src/content/docs/ar/modes.mdx +++ b/packages/web/src/content/docs/ar/modes.mdx @@ -233,7 +233,6 @@ Provide constructive feedback without making direct changes. | `read` | قراءة محتويات الملفات | | `grep` | البحث في محتويات الملفات | | `glob` | العثور على الملفات حسب نمط | -| `list` | سرد محتويات الدليل | | `patch` | تطبيق تصحيحات على الملفات | | `todowrite` | إدارة قوائم المهام | | `webfetch` | جلب محتوى الويب | diff --git a/packages/web/src/content/docs/ar/permissions.mdx b/packages/web/src/content/docs/ar/permissions.mdx index 4391514b4..bb21d00b2 100644 --- a/packages/web/src/content/docs/ar/permissions.mdx +++ b/packages/web/src/content/docs/ar/permissions.mdx @@ -88,7 +88,7 @@ description: تحكّم في الإجراءات التي تتطلب موافقة ### الأدلة الخارجية -استخدم `external_directory` للسماح باستدعاءات الأدوات التي تلمس مسارات خارج دليل العمل الذي بدأ منه OpenCode. ينطبق ذلك على أي أداة تأخذ مسارًا كمدخل (مثل `read` و`edit` و`list` و`glob` و`grep` والعديد من أوامر `bash`). +استخدم `external_directory` للسماح باستدعاءات الأدوات التي تلمس مسارات خارج دليل العمل الذي بدأ منه OpenCode. ينطبق ذلك على أي أداة تأخذ مسارًا كمدخل (مثل `read` و`edit` و`glob` و`grep` والعديد من أوامر `bash`). توسيع المنزل (مثل `~/...`) يؤثر فقط على طريقة كتابة النمط. لا يجعل ذلك المسار الخارجي جزءًا من مساحة العمل الحالية، لذا يجب السماح بالمسارات خارج دليل العمل عبر `external_directory` أيضًا. @@ -133,7 +133,6 @@ description: تحكّم في الإجراءات التي تتطلب موافقة - `edit` — جميع تعديلات الملفات (يشمل `edit` و`write` و`patch` و`multiedit`) - `glob` — مطابقة أسماء الملفات (يطابق نمط الـ glob) - `grep` — البحث في المحتوى (يطابق نمط regex) -- `list` — سرد الملفات في دليل (يطابق مسار الدليل) - `bash` — تشغيل أوامر shell (يطابق الأوامر المُحلَّلة مثل `git status --porcelain`) - `task` — تشغيل وكلاء فرعيين (يطابق نوع الوكيل الفرعي) - `skill` — تحميل مهارة (يطابق اسم المهارة) diff --git a/packages/web/src/content/docs/ar/tools.mdx b/packages/web/src/content/docs/ar/tools.mdx index d820778b4..3f3c9ee06 100644 --- a/packages/web/src/content/docs/ar/tools.mdx +++ b/packages/web/src/content/docs/ar/tools.mdx @@ -151,23 +151,6 @@ description: إدارة الأدوات التي يمكن لـ LLM استخدام --- -### list - -اعرض قائمة بالملفات والمجلدات في مسار محدد. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -تعرض هذه الأداة محتويات المجلد. وتقبل أنماط glob لتصفية النتائج. - ---- - ### lsp (experimental) تفاعل مع خوادم LSP التي قمت بتهيئتها للحصول على ميزات ذكاء الشفرة مثل التعاريف والمراجع ومعلومات التحويم وتسلسل الاستدعاءات. @@ -341,7 +324,7 @@ OPENCODE_ENABLE_EXA=1 opencode ## التفاصيل الداخلية -داخليا، تستخدم أدوات مثل `grep` و`glob` و`list` أداة [ripgrep](https://github.com/BurntSushi/ripgrep) في الخلفية. افتراضيا، يحترم ripgrep أنماط `.gitignore`، ما يعني أن الملفات والمجلدات المدرجة في `.gitignore` ستُستبعد من عمليات البحث وعرض القوائم. +داخليا، تستخدم أدوات مثل `grep` و`glob` [ripgrep](https://github.com/BurntSushi/ripgrep) في الخلفية. افتراضيا، يحترم ripgrep أنماط `.gitignore`، ما يعني أن الملفات والمجلدات المدرجة في `.gitignore` ستُستبعد من عمليات البحث وعرض القوائم. --- diff --git a/packages/web/src/content/docs/ar/zen.mdx b/packages/web/src/content/docs/ar/zen.mdx index 27a2c8132..7a3931c85 100644 --- a/packages/web/src/content/docs/ar/zen.mdx +++ b/packages/web/src/content/docs/ar/zen.mdx @@ -84,6 +84,8 @@ OpenCode Zen هي بوابة AI تتيح لك الوصول إلى هذه الن� | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -92,7 +94,6 @@ OpenCode Zen هي بوابة AI تتيح لك الوصول إلى هذه الن� | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 5.3 Codex، ستستخدم `opencode/gpt-5.3-codex` في إعداداتك. @@ -118,7 +119,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -166,7 +168,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج. - MiMo V2 Pro Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج. - MiMo V2 Omni Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج. -- Qwen3.6 Plus 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. @@ -212,8 +213,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج. - MiMo V2 Pro Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج. - MiMo V2 Omni Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج. -- Qwen3.6 Plus Free: خلال فترته المجانية، قد تُستخدم البيانات المجمعة لتحسين النموذج. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/bs/go.mdx b/packages/web/src/content/docs/bs/go.mdx index 1e4371c12..3dabedf6a 100644 --- a/packages/web/src/content/docs/bs/go.mdx +++ b/packages/web/src/content/docs/bs/go.mdx @@ -69,6 +69,8 @@ Trenutna lista modela uključuje: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Lista modela se može mijenjati dok testiramo i dodajemo nove. @@ -87,17 +89,25 @@ Ograničenja su definisana u dolarskoj vrijednosti. To znači da vaš stvarni br Tabela ispod pruža procijenjeni broj zahtjeva na osnovu tipičnih obrazaca korištenja Go pretplate: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------ | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| zahtjeva na 5 sati | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| zahtjeva sedmično | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| zahtjeva mjesečno | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | zahtjeva na 5 sati | zahtjeva sedmično | zahtjeva mjesečno | +| ------------ | ------------------ | ----------------- | ----------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Procjene se zasnivaju na zapaženim prosječnim obrascima zahtjeva: - GLM-5/5.1 — 700 ulaznih (input), 52,000 keširanih, 150 izlaznih (output) tokena po zahtjevu - Kimi K2.5 — 870 ulaznih, 55,000 keširanih, 200 izlaznih tokena po zahtjevu - MiniMax M2.7/M2.5 — 300 ulaznih, 55,000 keširanih, 125 izlaznih tokena po zahtjevu +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 ulaznih, 41,000 keširanih, 250 izlaznih tokena po zahtjevu - MiMo-V2-Omni — 1000 ulaznih, 60,000 keširanih, 140 izlaznih tokena po zahtjevu @@ -132,6 +142,8 @@ Također možete pristupiti Go modelima putem sljedećih API endpointa. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | [Model id](/docs/config/#models) u vašoj OpenCode konfiguraciji koristi format `opencode-go/<model-id>`. Na primjer, za Kimi K2.5, koristili biste diff --git a/packages/web/src/content/docs/bs/modes.mdx b/packages/web/src/content/docs/bs/modes.mdx index 6bf4bd27c..d5f92a9f6 100644 --- a/packages/web/src/content/docs/bs/modes.mdx +++ b/packages/web/src/content/docs/bs/modes.mdx @@ -219,7 +219,6 @@ Ovdje su svi alati koji se mogu kontrolirati kroz konfiguraciju načina rada. | `read` | Pročitajte sadržaj datoteke | | `grep` | Pretraži sadržaj datoteke | | `glob` | Pronađite datoteke po uzorku | -| `list` | Lista sadržaja direktorija | | `patch` | Primijenite zakrpe na datoteke | | `todowrite` | Upravljanje listama zadataka | | `webfetch` | Dohvati web sadržaj | diff --git a/packages/web/src/content/docs/bs/permissions.mdx b/packages/web/src/content/docs/bs/permissions.mdx index b6a194ad2..e27fa130b 100644 --- a/packages/web/src/content/docs/bs/permissions.mdx +++ b/packages/web/src/content/docs/bs/permissions.mdx @@ -87,7 +87,7 @@ Možete koristiti `~` ili `$HOME` na početku obrasca da referencirate svoj poč ### Vanjski direktoriji -Koristite `external_directory` da dozvolite pozive alata koji dodiruju putanje izvan radnog direktorija gdje je OpenCode pokrenut. Ovo se odnosi na bilo koji alat koji uzima putanju kao ulaz (na primjer `read`, `edit`, `list`, `glob`, `grep` i mnoge `bash` komande). +Koristite `external_directory` da dozvolite pozive alata koji dodiruju putanje izvan radnog direktorija gdje je OpenCode pokrenut. Ovo se odnosi na bilo koji alat koji uzima putanju kao ulaz (na primjer `read`, `edit`, `glob`, `grep` i mnoge `bash` komande). Proširenje kuće (poput `~/...`) utiče samo na način na koji je obrazac napisan. Ne čini vanjsku stazu dijelom trenutnog radnog prostora, tako da staze izvan radnog direktorija i dalje moraju biti dozvoljene preko `external_directory`. Na primjer, ovo omogućava pristup svemu pod `~/projects/personal/`: @@ -128,7 +128,6 @@ Dozvole OpenCode su označene imenom alata, plus nekoliko sigurnosnih mjera: - `edit` — sve izmjene fajlova (pokriva `edit`, `write`, `patch`, `multiedit`) - `glob` — globbiranje fajla (odgovara glob uzorku) - `grep` — pretraga sadržaja (podudara se sa regularnim izrazom) -- `list` — lista fajlova u direktorijumu (podudara se sa putanjom direktorijuma) - `bash` — izvođenje komandi ljuske (podudara se s raščlanjenim komandama kao što je `git status --porcelain`) - `task` — pokretanje subagenta (odgovara tipu podagenta) - `skill` — učitavanje vještine (odgovara nazivu vještine) diff --git a/packages/web/src/content/docs/bs/tools.mdx b/packages/web/src/content/docs/bs/tools.mdx index d0ae9a446..db04295fd 100644 --- a/packages/web/src/content/docs/bs/tools.mdx +++ b/packages/web/src/content/docs/bs/tools.mdx @@ -151,23 +151,6 @@ Trazi datoteke koristeci glob obrasce kao `**/*.js` ili `src/**/*.ts`. Vraca put --- -### list - -Ispisuje datoteke i direktorije na zadanoj putanji. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Ovaj alat ispisuje sadrzaj direktorija. Prihvata glob obrasce za filtriranje rezultata. - ---- - ### lsp (eksperimentalno) Komunicira sa konfigurisanim LSP serverima za funkcije inteligencije koda kao definicije, reference, hover info i hijerarhija poziva. @@ -341,7 +324,7 @@ MCP (Model Context Protocol) serveri omogucavaju integraciju eksternih alata i s ## Interno -Interno, alati kao `grep`, `glob` i `list` koriste [ripgrep](https://github.com/BurntSushi/ripgrep). Po defaultu, ripgrep postuje `.gitignore` obrasce, pa se fajlovi i direktoriji iz `.gitignore` izostavljaju iz pretraga i listinga. +Interno, alati kao `grep` i `glob` koriste [ripgrep](https://github.com/BurntSushi/ripgrep). Po defaultu, ripgrep postuje `.gitignore` obrasce, pa se fajlovi i direktoriji iz `.gitignore` izostavljaju iz pretraga i listinga. --- diff --git a/packages/web/src/content/docs/bs/zen.mdx b/packages/web/src/content/docs/bs/zen.mdx index d8b258f47..76a25e5f6 100644 --- a/packages/web/src/content/docs/bs/zen.mdx +++ b/packages/web/src/content/docs/bs/zen.mdx @@ -89,6 +89,8 @@ Našim modelima možete pristupiti i preko sljedećih API endpointa. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ Našim modelima možete pristupiti i preko sljedećih API endpointa. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 @@ -125,7 +126,8 @@ Podržavamo pay-as-you-go model. Ispod su cijene **po 1M tokena**. | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ Besplatni modeli: - MiniMax M2.5 Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model. - MiMo V2 Pro Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model. - MiMo V2 Omni Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model. -- Qwen3.6 Plus 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. @@ -224,8 +225,7 @@ i ne koriste vaše podatke za treniranje modela, uz sljedeće izuzetke: - MiniMax M2.5 Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela. - MiMo V2 Pro Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela. - MiMo V2 Omni Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela. -- Qwen3.6 Plus Free: Tokom besplatnog perioda, prikupljeni podaci mogu se koristiti za poboljšanje modela. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/da/go.mdx b/packages/web/src/content/docs/da/go.mdx index 9cc45443e..54f17bd77 100644 --- a/packages/web/src/content/docs/da/go.mdx +++ b/packages/web/src/content/docs/da/go.mdx @@ -69,6 +69,8 @@ Den nuværende liste over modeller inkluderer: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Listen over modeller kan ændre sig, efterhånden som vi tester og tilføjer nye. @@ -87,17 +89,25 @@ Grænserne er defineret i dollarværdi. Det betyder, at dit faktiske antal anmod Tabellen nedenfor giver et estimeret antal anmodninger baseret på typiske Go-forbrugsmønstre: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ----------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| anmodninger pr. 5 timer | 880 | 1.150 | 1.850 | 1.290 | 2.150 | 14.000 | 20.000 | -| anmodninger pr. uge | 2.150 | 2.880 | 4.630 | 3.225 | 5.450 | 35.000 | 50.000 | -| anmodninger pr. måned | 4.300 | 5.750 | 9.250 | 6.450 | 10.900 | 70.000 | 100.000 | +| Model | anmodninger pr. 5 timer | anmodninger pr. uge | anmodninger pr. måned | +| ------------ | ----------------------- | ------------------- | --------------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Estimaterne er baseret på observerede gennemsnitlige anmodningsmønstre: - GLM-5/5.1 — 700 input, 52.000 cachelagrede, 150 output-tokens pr. anmodning - Kimi K2.5 — 870 input, 55.000 cachelagrede, 200 output-tokens pr. anmodning - MiniMax M2.7/M2.5 — 300 input, 55.000 cachelagrede, 125 output-tokens pr. anmodning +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 input, 41.000 cachelagrede, 250 output-tokens pr. anmodning - MiMo-V2-Omni — 1000 input, 60.000 cachelagrede, 140 output-tokens pr. anmodning @@ -132,6 +142,8 @@ Du kan også få adgang til Go-modeller gennem følgende API-endpoints. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | Dit [model id](/docs/config/#models) i din OpenCode config bruger formatet `opencode-go/<model-id>`. For eksempel for Kimi K2.5, vil du diff --git a/packages/web/src/content/docs/da/modes.mdx b/packages/web/src/content/docs/da/modes.mdx index 34fb2b359..a0fb87a86 100644 --- a/packages/web/src/content/docs/da/modes.mdx +++ b/packages/web/src/content/docs/da/modes.mdx @@ -233,7 +233,6 @@ Her er alle de værktøjer, der kan styres gennem tilstandskonfigurationen. | `read` | Læs filindhold | | `grep` | Søg filindhold | | `glob` | Find filer efter mønster | -| `list` | Liste biblioteksindhold | | `patch` | Anvend patches til filer | | `todowrite` | Administrer todo-lister | | `webfetch` | Hent webindhold | diff --git a/packages/web/src/content/docs/da/permissions.mdx b/packages/web/src/content/docs/da/permissions.mdx index 72ebff606..176dd568e 100644 --- a/packages/web/src/content/docs/da/permissions.mdx +++ b/packages/web/src/content/docs/da/permissions.mdx @@ -88,7 +88,7 @@ Du kan bruge `~` eller `$HOME` i starten af et mønster til at referere ti ### Eksterne mapper -Brug `external_directory` til at tillade værktøjsopkald, der berører stier uden for den arbejdsmappe, hvor OpenCode blev startet. Dette gælder for ethvert værktøj, der tager en sti som input (for eksempel `read`, `edit`, `list`, `glob`, `grep` og mange `bash` kommandoer). +Brug `external_directory` til at tillade værktøjsopkald, der berører stier uden for den arbejdsmappe, hvor OpenCode blev startet. Dette gælder for ethvert værktøj, der tager en sti som input (for eksempel `read`, `edit`, `glob`, `grep` og mange `bash` kommandoer). Hjemmeudvidelse (som `~/...`) påvirker kun, hvordan et mønster skrives. Det gør ikke en ekstern sti til en del af det aktuelle arbejdsområde, så stier uden for arbejdsbiblioteket skal stadig være tilladt via `external_directory`. @@ -133,7 +133,6 @@ OpenCode tilladelser indtastes efter værktøjsnavn plus et par sikkerhedsafskæ - `edit` — alle filændringer (dækker `edit`, `write`, `patch`, `multiedit`) - `glob` — fil-globing (matcher glob-mønsteret) - `grep` — indholdssøgning (matcher regex-mønsteret) -- `list` — viser filer i en mappe (matcher mappestien) - `bash` — kører shell-kommandoer (matcher parsede kommandoer som `git status --porcelain`) - `task` — lancering af underagenter (matcher underagenttypen) - `skill` — indlæsning af en færdighed (matcher færdighedsnavnet) diff --git a/packages/web/src/content/docs/da/tools.mdx b/packages/web/src/content/docs/da/tools.mdx index a610e8cc3..6f6f95c9c 100644 --- a/packages/web/src/content/docs/da/tools.mdx +++ b/packages/web/src/content/docs/da/tools.mdx @@ -151,23 +151,6 @@ Søk etter filer ved at bruge glob-mønstre som `**/*.js` eller `src/**/*.ts`. R --- -### list - -List filer og kataloger i en gitt bane. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Dette verktøyet viser kataloginnhold. Den aksepterer glob-mønstre for at filtrere resultater. - ---- - ### lsp (experimental) Samhandle med dine konfigurerte LSP-servere for at få kodeintelligensfunksjoner som definisjoner, referanser, sveveinformasjon og anropshierarki. @@ -341,7 +324,7 @@ MCP (Model Context Protocol) servere lar deg integrere eksterne verktøy og tjen ## Interne -Internt bruger verktøy som `grep`, `glob` og `list` [ripgrep](https://github.com/BurntSushi/ripgrep) under panseret. Som standard respekterer ripgrep `.gitignore`-mønstre, noe som betyr at filer og kataloger som er oppført i `.gitignore` vil bli ekskludert fra søk og lister. +Internt bruger verktøy som `grep` og `glob` [ripgrep](https://github.com/BurntSushi/ripgrep) under panseret. Som standard respekterer ripgrep `.gitignore`-mønstre, noe som betyr at filer og kataloger som er oppført i `.gitignore` vil bli ekskludert fra søk og lister. --- diff --git a/packages/web/src/content/docs/da/zen.mdx b/packages/web/src/content/docs/da/zen.mdx index 3660e528d..146fa0280 100644 --- a/packages/web/src/content/docs/da/zen.mdx +++ b/packages/web/src/content/docs/da/zen.mdx @@ -89,6 +89,8 @@ Du kan også få adgang til vores modeller gennem følgende API-endpoints. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ Du kan også få adgang til vores modeller gennem følgende API-endpoints. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 @@ -125,7 +126,8 @@ Vi understøtter en pay-as-you-go-model. Nedenfor er priserne **pr. 1M tokens**. | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ De gratis modeller: - MiniMax M2.5 Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen. - MiMo V2 Pro Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen. - MiMo V2 Omni Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen. -- Qwen3.6 Plus 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. @@ -222,8 +223,7 @@ Alle vores modeller hostes i US. Vores udbydere følger en nul-opbevaringspoliti - MiniMax M2.5 Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen. - MiMo V2 Pro Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen. - MiMo V2 Omni Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen. -- Qwen3.6 Plus Free: I den gratis periode kan indsamlede data blive brugt til at forbedre modellen. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/de/go.mdx b/packages/web/src/content/docs/de/go.mdx index 95237ea82..0c5ec931a 100644 --- a/packages/web/src/content/docs/de/go.mdx +++ b/packages/web/src/content/docs/de/go.mdx @@ -61,6 +61,8 @@ Die aktuelle Liste der Modelle umfasst: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Die Liste der Modelle kann sich ändern, während wir neue testen und hinzufügen. @@ -79,17 +81,25 @@ Limits sind in Dollarwerten definiert. Das bedeutet, dass die tatsächliche Anza Die folgende Tabelle zeigt eine geschätzte Anzahl von Anfragen basierend auf typischen Go-Nutzungsmustern: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ---------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| Anfragen pro 5 Stunden | 880 | 1.150 | 1.850 | 1.290 | 2.150 | 14.000 | 20.000 | -| Anfragen pro Woche | 2.150 | 2.880 | 4.630 | 3.225 | 5.450 | 35.000 | 50.000 | -| Anfragen pro Monat | 4.300 | 5.750 | 9.250 | 6.450 | 10.900 | 70.000 | 100.000 | +| Model | Anfragen pro 5 Stunden | Anfragen pro Woche | Anfragen pro Monat | +| ------------ | ---------------------- | ------------------ | ------------------ | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Die Schätzungen basieren auf beobachteten durchschnittlichen Anfragemustern: - GLM-5/5.1 — 700 Input-, 52.000 Cached-, 150 Output-Tokens pro Anfrage - Kimi K2.5 — 870 Input-, 55.000 Cached-, 200 Output-Tokens pro Anfrage - MiniMax M2.7/M2.5 — 300 Input-, 55.000 Cached-, 125 Output-Tokens pro Anfrage +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 Input-, 41.000 Cached-, 250 Output-Tokens pro Anfrage - MiMo-V2-Omni — 1.000 Input-, 60.000 Cached-, 140 Output-Tokens pro Anfrage @@ -122,6 +132,8 @@ Du kannst auf die Go-Modelle auch über die folgenden API-Endpunkte zugreifen. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | Die [Modell-ID](/docs/config/#models) in deiner OpenCode Config verwendet das Format `opencode-go/<model-id>`. Für Kimi K2.5 würdest du beispielsweise `opencode-go/kimi-k2.5` in deiner Config verwenden. diff --git a/packages/web/src/content/docs/de/modes.mdx b/packages/web/src/content/docs/de/modes.mdx index 38a2e34b3..11a010d6b 100644 --- a/packages/web/src/content/docs/de/modes.mdx +++ b/packages/web/src/content/docs/de/modes.mdx @@ -233,7 +233,6 @@ Hier sind alle Tools aufgeführt, die über den Konfigurationsmodus gesteuert we | `read` | Dateiinhalt lesen | | `grep` | Dateiinhalte durchsuchen | | `glob` | Dateien nach Muster suchen | -| `list` | Verzeichnisinhalte auflisten | | `patch` | Patches auf Dateien anwenden | | `todowrite` | Aufgabenlisten verwalten | | `webfetch` | Webinhalte abrufen | diff --git a/packages/web/src/content/docs/de/permissions.mdx b/packages/web/src/content/docs/de/permissions.mdx index ba7c80204..6b647ca36 100644 --- a/packages/web/src/content/docs/de/permissions.mdx +++ b/packages/web/src/content/docs/de/permissions.mdx @@ -88,7 +88,7 @@ Sie können `~` oder `$HOME` am Anfang eines Musters verwenden, um auf Ihr Home- ### Externe Verzeichnisse -Verwenden Sie `external_directory`, um Toolaufrufe zuzulassen, die Pfade außerhalb des Arbeitsverzeichnisses berühren, in dem OpenCode gestartet wurde. Dies gilt für jedes Werkzeug, das einen Pfad als Eingabe verwendet (z. B. `read`, `edit`, `list`, `glob`, `grep` und viele `bash`-Befehle). +Verwenden Sie `external_directory`, um Toolaufrufe zuzulassen, die Pfade außerhalb des Arbeitsverzeichnisses berühren, in dem OpenCode gestartet wurde. Dies gilt für jedes Werkzeug, das einen Pfad als Eingabe verwendet (z. B. `read`, `edit`, `glob`, `grep` und viele `bash`-Befehle). Die Home-Erweiterung (wie `~/...`) wirkt sich nur darauf aus, wie ein Muster geschrieben wird. Dadurch wird ein externer Pfad nicht zum Teil des aktuellen Arbeitsbereichs, daher müssen Pfade außerhalb des Arbeitsverzeichnisses weiterhin über `external_directory` zulässig sein. @@ -133,7 +133,6 @@ OpenCode-Berechtigungen basieren auf Tool-Namen sowie einigen Sicherheitsvorkehr - `edit` – alle Dateiänderungen (umfasst `edit`, `write`, `patch`, `multiedit`) - `glob` – Datei-Globbing (entspricht dem Glob-Muster) - `grep` – Inhaltssuche (entspricht dem Regex-Muster) -- `list` – Auflistung der Dateien in einem Verzeichnis (entspricht dem Verzeichnispfad) - `bash` – Ausführen von Shell-Befehlen (entspricht analysierten Befehlen wie `git status --porcelain`) - `task` – Subagenten starten (entspricht dem Subagententyp) - `skill` – Laden einer Fertigkeit (entspricht dem Fertigkeitsnamen) diff --git a/packages/web/src/content/docs/de/tools.mdx b/packages/web/src/content/docs/de/tools.mdx index b33163df8..6012148c6 100644 --- a/packages/web/src/content/docs/de/tools.mdx +++ b/packages/web/src/content/docs/de/tools.mdx @@ -158,23 +158,6 @@ Sucht nach Dateien mit Glob-Mustern wie `**/*.js` oder `src/**/*.ts`. Gibt passe --- -### list - -Listet Dateien und Verzeichnisse in einem Pfad auf. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Dieses Tool listet Verzeichnisinhalte auf. Es akzeptiert Glob-Muster zum Filtern der Ergebnisse. - ---- - ### lsp (experimentell) Interagiere mit deinen konfigurierten LSP-Servern fuer Code-Intelligence-Features wie Definitionen, Referenzen, Hover-Infos und Call-Hierarchien. @@ -350,7 +333,7 @@ Dazu gehoeren Datenbanken, API-Integrationen und Drittanbieter-Services. ## Interna -Intern verwenden Tools wie `grep`, `glob` und `list` [ripgrep](https://github.com/BurntSushi/ripgrep). +Intern verwenden Tools wie `grep` und `glob` [ripgrep](https://github.com/BurntSushi/ripgrep). Standardmaessig beachtet ripgrep `.gitignore`, daher werden dort aufgefuehrte Dateien und Ordner nicht durchsucht. --- diff --git a/packages/web/src/content/docs/de/zen.mdx b/packages/web/src/content/docs/de/zen.mdx index 4e94788ee..bc9438672 100644 --- a/packages/web/src/content/docs/de/zen.mdx +++ b/packages/web/src/content/docs/de/zen.mdx @@ -80,6 +80,8 @@ Du kannst auch über die folgenden API-Endpunkte auf unsere Modelle zugreifen. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ Du kannst auch über die folgenden API-Endpunkte auf unsere Modelle zugreifen. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 5.3 Codex würdest du zum Beispiel `opencode/gpt-5.3-codex` in deiner Konfiguration verwenden. @@ -114,7 +115,8 @@ Wir unterstützen ein Pay-as-you-go-Modell. Unten findest du die Preise **pro 1M | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ Die kostenlosen Modelle: - 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. - MiMo V2 Pro Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern. - MiMo V2 Omni Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern. -- Qwen3.6 Plus 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. @@ -208,8 +209,7 @@ Alle unsere Modelle werden in den USA gehostet. Unsere Provider folgen einer Zer - MiniMax M2.5 Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden. - MiMo V2 Pro Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden. - MiMo V2 Omni Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden. -- Qwen3.6 Plus Free: Während des kostenlosen Zeitraums können gesammelte Daten zur Verbesserung des Modells verwendet werden. -- Nemotron 3 Super 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. diff --git a/packages/web/src/content/docs/es/go.mdx b/packages/web/src/content/docs/es/go.mdx index 5d38ee900..86ddbe81e 100644 --- a/packages/web/src/content/docs/es/go.mdx +++ b/packages/web/src/content/docs/es/go.mdx @@ -69,6 +69,8 @@ La lista actual de modelos incluye: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** La lista de modelos puede cambiar a medida que probamos y agregamos otros nuevos. @@ -87,17 +89,25 @@ Los límites se definen en valor en dólares. Esto significa que tu cantidad rea La siguiente tabla proporciona una cantidad estimada de peticiones basada en los patrones típicos de uso de Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ---------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| peticiones por 5 horas | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| peticiones por semana | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| peticiones por mes | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | peticiones por 5 horas | peticiones por semana | peticiones por mes | +| ------------ | ---------------------- | --------------------- | ------------------ | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Las estimaciones se basan en los patrones de peticiones promedio observados: - GLM-5/5.1 — 700 tokens de entrada, 52,000 en caché, 150 tokens de salida por petición - Kimi K2.5 — 870 tokens de entrada, 55,000 en caché, 200 tokens de salida por petición - MiniMax M2.7/M2.5 — 300 tokens de entrada, 55,000 en caché, 125 tokens de salida por petición +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 tokens de entrada, 41,000 en caché, 250 tokens de salida por petición - MiMo-V2-Omni — 1000 tokens de entrada, 60,000 en caché, 140 tokens de salida por petición @@ -132,6 +142,8 @@ También puedes acceder a los modelos de Go a través de los siguientes endpoint | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | El [ID del modelo](/docs/config/#models) en tu configuración de OpenCode usa el formato `opencode-go/<model-id>`. Por ejemplo, para Kimi K2.5, usarías diff --git a/packages/web/src/content/docs/es/modes.mdx b/packages/web/src/content/docs/es/modes.mdx index cefc4a4e2..dca900dff 100644 --- a/packages/web/src/content/docs/es/modes.mdx +++ b/packages/web/src/content/docs/es/modes.mdx @@ -233,7 +233,6 @@ Aquí están todas las herramientas que se pueden controlar a través del modo d | `read` | Leer el contenido del archivo | | `grep` | Buscar contenido del archivo | | `glob` | Buscar archivos por patrón | -| `list` | Listar el contenido del directorio | | `patch` | Aplicar parches a archivos | | `todowrite` | Administrar listas de tareas pendientes | | `webfetch` | Obtener contenido web | diff --git a/packages/web/src/content/docs/es/permissions.mdx b/packages/web/src/content/docs/es/permissions.mdx index 603b3bdb3..6923368e4 100644 --- a/packages/web/src/content/docs/es/permissions.mdx +++ b/packages/web/src/content/docs/es/permissions.mdx @@ -88,7 +88,7 @@ Puede usar `~` o `$HOME` al comienzo de un patrón para hacer referencia a su di ### Directorios externos -Utilice `external_directory` para permitir llamadas a herramientas que toquen rutas fuera del directorio de trabajo donde se inició OpenCode. Esto se aplica a cualquier herramienta que tome una ruta como entrada (por ejemplo, `read`, `edit`, `list`, `glob`, `grep` y muchos comandos `bash`). +Utilice `external_directory` para permitir llamadas a herramientas que toquen rutas fuera del directorio de trabajo donde se inició OpenCode. Esto se aplica a cualquier herramienta que tome una ruta como entrada (por ejemplo, `read`, `edit`, `glob`, `grep` y muchos comandos `bash`). La expansión del hogar (como `~/...`) solo afecta la forma en que se escribe un patrón. No hace que una ruta externa forme parte del espacio de trabajo actual, por lo que las rutas fuera del directorio de trabajo aún deben permitirse a través de `external_directory`. @@ -133,7 +133,6 @@ Los permisos OpenCode están codificados por el nombre de la herramienta, ademá - `edit` — todas las modificaciones de archivos (cubre `edit`, `write`, `patch`, `multiedit`) - `glob` — globalización de archivos (coincide con el patrón global) - `grep` — búsqueda de contenido (coincide con el patrón de expresiones regulares) -- `list` — enumerar archivos en un directorio (coincide con la ruta del directorio) - `bash`: ejecuta comandos de shell (coincide con comandos analizados como `git status --porcelain`) - `task` — lanzamiento de subagentes (coincide con el tipo de subagente) - `skill` — cargar una habilidad (coincide con el nombre de la habilidad) diff --git a/packages/web/src/content/docs/es/tools.mdx b/packages/web/src/content/docs/es/tools.mdx index f3a050c03..83d61f532 100644 --- a/packages/web/src/content/docs/es/tools.mdx +++ b/packages/web/src/content/docs/es/tools.mdx @@ -151,23 +151,6 @@ Busque archivos usando patrones globales como `**/*.js` o `src/**/*.ts`. Devuelv --- -### list - -Enumere archivos y directorios en una ruta determinada. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Esta herramienta enumera el contenido del directorio. Acepta patrones globales para filtrar resultados. - ---- - ### lsp (experimental) Interactúe con sus servidores LSP configurados para obtener funciones de inteligencia de código como definiciones, referencias, información de desplazamiento y jerarquía de llamadas. @@ -341,7 +324,7 @@ Los servidores MCP (Model Context Protocol) le permiten integrar herramientas y ## Internos -Internamente, herramientas como `grep`, `glob` y `list` usan [ripgrep](https://github.com/BurntSushi/ripgrep) bajo el capó. De forma predeterminada, ripgrep respeta los patrones `.gitignore`, lo que significa que los archivos y directorios enumerados en su `.gitignore` se excluirán de las búsquedas y listados. +Internamente, herramientas como `grep` y `glob` usan [ripgrep](https://github.com/BurntSushi/ripgrep) bajo el capó. De forma predeterminada, ripgrep respeta los patrones `.gitignore`, lo que significa que los archivos y directorios enumerados en su `.gitignore` se excluirán de las búsquedas y listados. --- diff --git a/packages/web/src/content/docs/es/zen.mdx b/packages/web/src/content/docs/es/zen.mdx index b6acd296a..6fc0fb13e 100644 --- a/packages/web/src/content/docs/es/zen.mdx +++ b/packages/web/src/content/docs/es/zen.mdx @@ -89,6 +89,8 @@ También puedes acceder a nuestros modelos a través de los siguientes endpoints | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ También puedes acceder a nuestros modelos a través de los siguientes endpoints | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 @@ -125,7 +126,8 @@ Admitimos un modelo de pago por uso. A continuación se muestran los precios **p | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ Los modelos gratuitos: - MiniMax M2.5 Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo. - MiMo V2 Pro Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo. - MiMo V2 Omni Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo. -- Qwen3.6 Plus 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. @@ -222,8 +223,7 @@ Todos nuestros modelos están alojados en US. Nuestros proveedores siguen una po - MiniMax M2.5 Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo. - MiMo V2 Pro Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo. - MiMo V2 Omni Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo. -- Qwen3.6 Plus Free: Durante su período gratuito, los datos recopilados pueden usarse para mejorar el modelo. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/fr/go.mdx b/packages/web/src/content/docs/fr/go.mdx index 2b819438f..b10cf9141 100644 --- a/packages/web/src/content/docs/fr/go.mdx +++ b/packages/web/src/content/docs/fr/go.mdx @@ -59,6 +59,8 @@ La liste actuelle des modèles comprend : - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** La liste des modèles peut changer au fur et à mesure que nous en testons et en ajoutons de nouveaux. @@ -77,17 +79,25 @@ Les limites sont définies en valeur monétaire (dollars). Cela signifie que vot Le tableau ci-dessous fournit une estimation du nombre de requêtes basée sur des modèles d'utilisation typiques de Go : -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| --------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| requêtes par 5 heures | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| requêtes par semaine | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| requêtes par mois | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | requêtes par 5 heures | requêtes par semaine | requêtes par mois | +| ------------ | --------------------- | -------------------- | ----------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Les estimations sont basées sur les modèles de requêtes moyens observés : - GLM-5/5.1 — 700 tokens en entrée, 52,000 en cache, 150 tokens en sortie par requête - Kimi K2.5 — 870 tokens en entrée, 55,000 en cache, 200 tokens en sortie par requête - MiniMax M2.7/M2.5 — 300 tokens en entrée, 55,000 en cache, 125 tokens en sortie par requête +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 tokens en entrée, 41,000 en cache, 250 tokens en sortie par requête - MiMo-V2-Omni — 1000 tokens en entrée, 60,000 en cache, 140 tokens en sortie par requête @@ -120,6 +130,8 @@ Vous pouvez également accéder aux modèles Go via les points de terminaison d' | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | L'[ID de modèle](/docs/config/#models) dans votre configuration OpenCode utilise le format `opencode-go/<model-id>`. Par exemple, pour Kimi K2.5, vous utiliseriez `opencode-go/kimi-k2.5` dans votre configuration. diff --git a/packages/web/src/content/docs/fr/modes.mdx b/packages/web/src/content/docs/fr/modes.mdx index 8c3ad62e4..6985dbd57 100644 --- a/packages/web/src/content/docs/fr/modes.mdx +++ b/packages/web/src/content/docs/fr/modes.mdx @@ -231,7 +231,6 @@ Voici tous les outils pouvant être contrôlés via le mode config. | `read` | Lire le contenu du fichier | | `grep` | Rechercher le contenu du fichier | | `glob` | Rechercher des fichiers par modèle | -| `list` | Liste du contenu du répertoire | | `patch` | Appliquer des correctifs aux fichiers | | `todowrite` | Gérer les listes de tâches | | `webfetch` | Récupérer du contenu Web | diff --git a/packages/web/src/content/docs/fr/permissions.mdx b/packages/web/src/content/docs/fr/permissions.mdx index 176fa34ad..b1c1d6800 100644 --- a/packages/web/src/content/docs/fr/permissions.mdx +++ b/packages/web/src/content/docs/fr/permissions.mdx @@ -88,7 +88,7 @@ Vous pouvez utiliser `~` ou `$HOME` au début d'un modèle pour référencer vot ### Répertoires externes -Utilisez `external_directory` pour autoriser les appels d'outils qui touchent des chemins en dehors du répertoire de travail où OpenCode a été démarré. Cela s'applique à tout outil qui prend un chemin en entrée (par exemple `read`, `edit`, `list`, `glob`, `grep` et de nombreuses commandes `bash`). +Utilisez `external_directory` pour autoriser les appels d'outils qui touchent des chemins en dehors du répertoire de travail où OpenCode a été démarré. Cela s'applique à tout outil qui prend un chemin en entrée (par exemple `read`, `edit`, `glob`, `grep` et de nombreuses commandes `bash`). L'expansion du répertoire personnel (comme `~/...`) n'affecte que la façon dont un modèle est écrit. Cela n'intègre pas un chemin externe à l'espace de travail actuel, donc les chemins en dehors du répertoire de travail doivent toujours être autorisés via `external_directory`. @@ -133,7 +133,6 @@ Les autorisations OpenCode sont classées par nom d'outil, plus quelques garde-f - `edit` — toutes les modifications de fichiers (couvre `edit`, `write`, `patch`, `multiedit`) - `glob` — globalisation de fichiers (correspond au modèle global) - `grep` — recherche de contenu (correspond au modèle regex) -- `list` — listant les fichiers dans un répertoire (correspond au chemin du répertoire) - `bash` - exécution de commandes shell (correspond aux commandes analysées comme `git status --porcelain`) - `task` — lancement de sous-agents (correspond au type de sous-agent) - `skill` — chargement d'une compétence (correspond au nom de la compétence) diff --git a/packages/web/src/content/docs/fr/tools.mdx b/packages/web/src/content/docs/fr/tools.mdx index 62579c2bf..4f3f18046 100644 --- a/packages/web/src/content/docs/fr/tools.mdx +++ b/packages/web/src/content/docs/fr/tools.mdx @@ -151,23 +151,6 @@ Recherchez des fichiers à l'aide de modèles globaux tels que `**/*.js` ou `src --- -### liste - -Répertoriez les fichiers et les répertoires dans un chemin donné. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Cet outil répertorie le contenu du répertoire. Il accepte les modèles globaux pour filtrer les résultats. - ---- - ### lsp (expérimental) Interagissez avec vos serveurs LSP configurés pour obtenir des fonctionnalités d'intelligence du code telles que des définitions, des références, des informations de survol et une hiérarchie d'appels. @@ -341,7 +324,7 @@ Les serveurs MCP (Model Context Protocol) vous permettent d'intégrer des outils ## Internes -En interne, des outils comme `grep`, `glob` et `list` utilisent [ripgrep](https://github.com/BurntSushi/ripgrep) sous le capot. Par défaut, ripgrep respecte les modèles `.gitignore`, ce qui signifie que les fichiers et répertoires répertoriés dans votre `.gitignore` seront exclus des recherches et des listes. +En interne, des outils comme `grep` et `glob` utilisent [ripgrep](https://github.com/BurntSushi/ripgrep) sous le capot. Par défaut, ripgrep respecte les modèles `.gitignore`, ce qui signifie que les fichiers et répertoires répertoriés dans votre `.gitignore` seront exclus des recherches et des listes. --- diff --git a/packages/web/src/content/docs/fr/zen.mdx b/packages/web/src/content/docs/fr/zen.mdx index f65fcac08..a71328a72 100644 --- a/packages/web/src/content/docs/fr/zen.mdx +++ b/packages/web/src/content/docs/fr/zen.mdx @@ -80,6 +80,8 @@ Vous pouvez également accéder à nos modèles via les points de terminaison AP | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ Vous pouvez également accéder à nos modèles via les points de terminaison AP | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 5.3 Codex, vous utiliseriez `opencode/gpt-5.3-codex` dans votre configuration. @@ -114,7 +115,8 @@ Nous prenons en charge un modèle de paiement à l'utilisation. Vous trouverez c | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ Les modèles gratuits : - 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. - MiMo V2 Pro Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle. - MiMo V2 Omni Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle. -- Qwen3.6 Plus 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. @@ -208,8 +209,7 @@ Tous nos modèles sont hébergés aux US. Nos fournisseurs suivent une politique - MiniMax M2.5 Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle. - MiMo V2 Pro Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle. - MiMo V2 Omni Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle. -- Qwen3.6 Plus Free : Pendant sa période gratuite, les données collectées peuvent être utilisées pour améliorer le modèle. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/go.mdx b/packages/web/src/content/docs/go.mdx index df65aa76a..b8d608a4a 100644 --- a/packages/web/src/content/docs/go.mdx +++ b/packages/web/src/content/docs/go.mdx @@ -70,6 +70,8 @@ The current list of models includes: - **MiMo-V2-Omni** - **MiniMax M2.5** - **MiniMax M2.7** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** The list of models may change as we test and add new ones. @@ -83,15 +85,21 @@ OpenCode Go includes the following limits: - **Weekly limit** — $30 of usage - **Monthly limit** — $60 of usage -Limits are defined in dollar value. This means your actual request count depends on the model you use. Cheaper models like MiniMax M2.5 allow for more requests, while higher-cost models like GLM-5.1 allow for fewer. +Limits are defined in dollar value. This means your actual request count depends on the model you use. Cheaper models like Qwen3.5 Plus allow for more requests, while higher-cost models like GLM-5.1 allow for fewer. The table below provides an estimated request count based on typical Go usage patterns: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| requests per 5 hour | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| requests per week | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| requests per month | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | requests per 5 hour | requests per week | requests per month | +| ------------ | ------------------- | ----------------- | ------------------ | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Estimates are based on observed average request patterns: @@ -100,6 +108,8 @@ Estimates are based on observed average request patterns: - MiniMax M2.7/M2.5 — 300 input, 55,000 cached, 125 output tokens per request - MiMo-V2-Pro — 350 input, 41,000 cached, 250 output tokens per request - MiMo-V2-Omni — 1000 input, 60,000 cached, 140 output tokens per request +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request You can track your current usage in the **<a href={console}>console</a>**. @@ -132,6 +142,8 @@ You can also access Go models through the following API endpoints. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | The [model id](/docs/config/#models) in your OpenCode config uses the format `opencode-go/<model-id>`. For example, for Kimi K2.5, you would diff --git a/packages/web/src/content/docs/it/go.mdx b/packages/web/src/content/docs/it/go.mdx index e4b95d228..f90dce509 100644 --- a/packages/web/src/content/docs/it/go.mdx +++ b/packages/web/src/content/docs/it/go.mdx @@ -67,6 +67,8 @@ L'elenco attuale dei modelli include: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** L'elenco dei modelli potrebbe cambiare man mano che ne testiamo e aggiungiamo di nuovi. @@ -85,17 +87,25 @@ I limiti sono definiti in valore in dollari. Questo significa che il conteggio e La tabella seguente fornisce una stima del conteggio delle richieste in base a pattern di utilizzo tipici di Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| --------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| richieste ogni 5 ore | 880 | 1.150 | 1.850 | 1.290 | 2.150 | 14.000 | 20.000 | -| richieste a settimana | 2.150 | 2.880 | 4.630 | 3.225 | 5.450 | 35.000 | 50.000 | -| richieste al mese | 4.300 | 5.750 | 9.250 | 6.450 | 10.900 | 70.000 | 100.000 | +| Model | richieste ogni 5 ore | richieste a settimana | richieste al mese | +| ------------ | -------------------- | --------------------- | ----------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Le stime si basano sui pattern medi di richieste osservati: - GLM-5/5.1 — 700 di input, 52.000 in cache, 150 token di output per richiesta - Kimi K2.5 — 870 di input, 55.000 in cache, 200 token di output per richiesta - MiniMax M2.7/M2.5 — 300 di input, 55.000 in cache, 125 token di output per richiesta +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 di input, 41.000 in cache, 250 token di output per richiesta - MiMo-V2-Omni — 1000 di input, 60.000 in cache, 140 token di output per richiesta @@ -130,6 +140,8 @@ Puoi anche accedere ai modelli Go tramite i seguenti endpoint API. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | Il [model id](/docs/config/#models) nella tua OpenCode config utilizza il formato `opencode-go/<model-id>`. Ad esempio, per Kimi K2.5, useresti diff --git a/packages/web/src/content/docs/it/modes.mdx b/packages/web/src/content/docs/it/modes.mdx index 8f5c22d6e..052808f7a 100644 --- a/packages/web/src/content/docs/it/modes.mdx +++ b/packages/web/src/content/docs/it/modes.mdx @@ -224,18 +224,17 @@ Se non specifichi gli strumenti, tutti gli strumenti sono abilitati per impostaz Ecco tutti gli strumenti che possono essere controllati tramite la configurazione della modalita. -| Strumento | Descrizione | -| ----------- | --------------------------------- | -| `bash` | Esegue comandi shell | -| `edit` | Modifica file esistenti | -| `write` | Crea nuovi file | -| `read` | Legge contenuti dei file | -| `grep` | Cerca nei contenuti dei file | -| `glob` | Trova file per pattern | -| `list` | Elenca contenuti di una directory | -| `patch` | Applica patch ai file | -| `todowrite` | Gestisce liste todo | -| `webfetch` | Recupera contenuti web | +| Strumento | Descrizione | +| ----------- | ---------------------------- | +| `bash` | Esegue comandi shell | +| `edit` | Modifica file esistenti | +| `write` | Crea nuovi file | +| `read` | Legge contenuti dei file | +| `grep` | Cerca nei contenuti dei file | +| `glob` | Trova file per pattern | +| `patch` | Applica patch ai file | +| `todowrite` | Gestisce liste todo | +| `webfetch` | Recupera contenuti web | --- diff --git a/packages/web/src/content/docs/it/permissions.mdx b/packages/web/src/content/docs/it/permissions.mdx index 3f255c89d..49f0e8e4d 100644 --- a/packages/web/src/content/docs/it/permissions.mdx +++ b/packages/web/src/content/docs/it/permissions.mdx @@ -88,7 +88,7 @@ Puoi usare `~` o `$HOME` all'inizio di un pattern per riferirti alla tua home di ### Directory esterne -Usa `external_directory` per consentire chiamate a strumenti che toccano percorsi al di fuori della directory di lavoro da cui e' stato avviato OpenCode. Si applica a qualsiasi strumento che accetta un path come input (ad esempio `read`, `edit`, `list`, `glob`, `grep` e molti comandi `bash`). +Usa `external_directory` per consentire chiamate a strumenti che toccano percorsi al di fuori della directory di lavoro da cui e' stato avviato OpenCode. Si applica a qualsiasi strumento che accetta un path come input (ad esempio `read`, `edit`, `glob`, `grep` e molti comandi `bash`). L'espansione della home (come `~/...`) influisce solo su come viene scritto un pattern. Non rende un percorso esterno parte della workspace corrente, quindi i path fuori dalla directory di lavoro devono comunque essere consentiti tramite `external_directory`. @@ -133,7 +133,6 @@ I permessi di OpenCode sono indicizzati per nome dello strumento, piu' un paio d - `edit` — tutte le modifiche ai file (include `edit`, `write`, `patch`, `multiedit`) - `glob` — ricerca file tramite glob (corrisponde al pattern glob) - `grep` — ricerca nel contenuto (corrisponde al pattern regex) -- `list` — elenco file in una directory (corrisponde al path della directory) - `bash` — esecuzione comandi di shell (corrisponde a comandi parsati come `git status --porcelain`) - `task` — avvio subagenti (corrisponde al tipo di subagente) - `skill` — caricamento di una skill (corrisponde al nome della skill) diff --git a/packages/web/src/content/docs/it/tools.mdx b/packages/web/src/content/docs/it/tools.mdx index 50609fd61..c1e69f8be 100644 --- a/packages/web/src/content/docs/it/tools.mdx +++ b/packages/web/src/content/docs/it/tools.mdx @@ -151,23 +151,6 @@ Cerca file usando pattern glob come `**/*.js` o `src/**/*.ts`. Restituisce i per --- -### list - -Elenca file e directory in un percorso specifico. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Questo strumento elenca il contenuto di una directory. Accetta pattern glob per filtrare i risultati. - ---- - ### lsp (experimental) Interagisci con i server LSP configurati per ottenere funzionalita' di code intelligence come definizioni, riferimenti, hover info e call hierarchy. @@ -341,7 +324,7 @@ I server MCP (Model Context Protocol) permettono di integrare strumenti e serviz ## Interni -Internamente, strumenti come `grep`, `glob` e `list` usano [ripgrep](https://github.com/BurntSushi/ripgrep) sotto al cofano. Di default, ripgrep rispetta i pattern di `.gitignore`, quindi i file e le directory elencati in `.gitignore` vengono esclusi da ricerche ed elenchi. +Internamente, strumenti come `grep` e `glob` usano [ripgrep](https://github.com/BurntSushi/ripgrep) sotto al cofano. Di default, ripgrep rispetta i pattern di `.gitignore`, quindi i file e le directory elencati in `.gitignore` vengono esclusi da ricerche ed elenchi. --- diff --git a/packages/web/src/content/docs/it/zen.mdx b/packages/web/src/content/docs/it/zen.mdx index c099c903c..cdc2c9a45 100644 --- a/packages/web/src/content/docs/it/zen.mdx +++ b/packages/web/src/content/docs/it/zen.mdx @@ -89,6 +89,8 @@ Puoi anche accedere ai nostri modelli tramite i seguenti endpoint API. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ Puoi anche accedere ai nostri modelli tramite i seguenti endpoint API. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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 @@ -125,7 +126,8 @@ Supportiamo un modello pay-as-you-go. Qui sotto trovi i prezzi **per 1M token**. | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ I modelli gratuiti: - MiniMax M2.5 Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello. - MiMo V2 Pro Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello. - MiMo V2 Omni Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello. -- Qwen3.6 Plus 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. @@ -222,8 +223,7 @@ Tutti i nostri modelli sono ospitati negli US. I nostri provider seguono una pol - MiniMax M2.5 Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello. - MiMo V2 Pro Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello. - MiMo V2 Omni Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello. -- Qwen3.6 Plus Free: durante il periodo gratuito, i dati raccolti possono essere usati per migliorare il modello. -- Nemotron 3 Super 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). diff --git a/packages/web/src/content/docs/ja/go.mdx b/packages/web/src/content/docs/ja/go.mdx index 35e2775b4..01f1d6390 100644 --- a/packages/web/src/content/docs/ja/go.mdx +++ b/packages/web/src/content/docs/ja/go.mdx @@ -59,6 +59,8 @@ OpenCode Goをサブスクライブできるのは、1つのワークスペー� - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** 新しいモデルをテストして追加するにつれて、モデルのリストは変更される場合があります。 @@ -77,17 +79,25 @@ OpenCode Goには以下の制限が含まれています： 以下の表は、一般的なGoの利用パターンに基づいた推定リクエスト数を示しています： -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| 5時間あたりのリクエスト数 | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| 週間リクエスト数 | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| 月間リクエスト数 | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | 5時間あたりのリクエスト数 | 週間リクエスト数 | 月間リクエスト数 | +| ------------ | ------------------------- | ---------------- | ---------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | 推定値は、観測された平均的なリクエストパターンに基づいています： - GLM-5/5.1 — リクエストあたり 入力 700トークン、キャッシュ 52,000トークン、出力 150トークン - Kimi K2.5 — リクエストあたり 入力 870トークン、キャッシュ 55,000トークン、出力 200トークン - MiniMax M2.7/M2.5 — リクエストあたり 入力 300トークン、キャッシュ 55,000トークン、出力 125トークン +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — リクエストあたり 入力 350トークン、キャッシュ 41,000トークン、出力 250トークン - MiMo-V2-Omni — リクエストあたり 入力 1000トークン、キャッシュ 60,000トークン、出力 140トークン @@ -120,6 +130,8 @@ Zen残高にクレジットがある場合は、コンソールで**Use balance* | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | OpenCode設定の[model id](/docs/config/#models)は、`opencode-go/<model-id>`という形式を使用します。たとえば、Kimi K2.5の場合は、設定で`opencode-go/kimi-k2.5`を使用します。 diff --git a/packages/web/src/content/docs/ja/modes.mdx b/packages/web/src/content/docs/ja/modes.mdx index c9f2a4d5e..8ebe7f5e6 100644 --- a/packages/web/src/content/docs/ja/modes.mdx +++ b/packages/web/src/content/docs/ja/modes.mdx @@ -223,18 +223,17 @@ Markdown ファイル名はモード名になります (例: `review.md` は `re ここでは、モード設定を通じて制御できるすべてのツールを示します。 -| ツール | 説明 | -| ----------- | ------------------------------ | -| `bash` | シェルコマンドを実行する | -| `edit` | 既存のファイルを変更する | -| `write` | 新しいファイルを作成する | -| `read` | ファイルの内容を読み取る | -| `grep` | ファイルの内容を検索 | -| `glob` | パターンでファイルを検索 | -| `list` | ディレクトリの内容をリストする | -| `patch` | ファイルにパッチを適用する | -| `todowrite` | ToDo リストを管理する | -| `webfetch` | Web コンテンツを取得する | +| ツール | 説明 | +| ----------- | -------------------------- | +| `bash` | シェルコマンドを実行する | +| `edit` | 既存のファイルを変更する | +| `write` | 新しいファイルを作成する | +| `read` | ファイルの内容を読み取る | +| `grep` | ファイルの内容を検索 | +| `glob` | パターンでファイルを検索 | +| `patch` | ファイルにパッチを適用する | +| `todowrite` | ToDo リストを管理する | +| `webfetch` | Web コンテンツを取得する | --- diff --git a/packages/web/src/content/docs/ja/permissions.mdx b/packages/web/src/content/docs/ja/permissions.mdx index 5f5df6675..f2b097825 100644 --- a/packages/web/src/content/docs/ja/permissions.mdx +++ b/packages/web/src/content/docs/ja/permissions.mdx @@ -88,7 +88,7 @@ OpenCode は `permission` 設定を使用して、特定のアクションを自 ### 外部ディレクトリ -`external_directory` を使用して、OpenCode が開始された作業ディレクトリの外部のパスに触れるツール呼び出しを許可します。これは、パスを入力として受け取るすべてのツール (`read`、`edit`、`list`、`glob`、`grep`、および多くの `bash` コマンドなど) に適用されます。 +`external_directory` を使用して、OpenCode が開始された作業ディレクトリの外部のパスに触れるツール呼び出しを許可します。これは、パスを入力として受け取るすべてのツール (`read`、`edit`、`glob`、`grep`、および多くの `bash` コマンドなど) に適用されます。 ホーム展開 (`~/...` など) は、パターンの記述方法にのみ影響します。外部パスは現在のワークスペースの一部にはならないため、作業ディレクトリの外部のパスも `external_directory` 経由で許可する必要があります。 @@ -133,7 +133,6 @@ OpenCode の権限は、ツール名に加えて、いくつかの安全対策� - `edit` — すべてのファイル変更 (`edit`、`write`、`patch`、`multiedit` をカバー) - `glob` — ファイルのグロビング (グロブパターンと一致) - `grep` — コンテンツ検索 (正規表現パターンと一致) -- `list` — ディレクトリ内のファイルのリスト (ディレクトリパスと一致) - `bash` — シェルコマンドの実行 (`git status --porcelain` などの解析されたコマンドと一致します) - `task` — サブエージェントの起動 (サブエージェントのタイプと一致) - `skill` — スキルをロードしています（スキル名と一致します） diff --git a/packages/web/src/content/docs/ja/tools.mdx b/packages/web/src/content/docs/ja/tools.mdx index 0e0f8fe95..394506393 100644 --- a/packages/web/src/content/docs/ja/tools.mdx +++ b/packages/web/src/content/docs/ja/tools.mdx @@ -151,23 +151,6 @@ OpenCode で利用可能なすべての組み込みツールを次に示しま� --- -### list - -指定されたパス内のファイルとディレクトリを一覧表示します。 - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -このツールはディレクトリの内容を一覧表示します。結果をフィルタリングするための glob パターンを受け入れます。 - ---- - ### lsp (実験的) 構成された LSP サーバーと対話して、定義、参照、ホバー情報、呼び出し階層などのコードインテリジェンス機能を取得します。 @@ -341,7 +324,7 @@ MCP (Model Context Protocol) サーバーを使用すると、外部ツールと ## 内部動作 -内部的には、`grep`、`glob`、`list` などのツールは内部で [ripgrep](https://github.com/BurntSushi/ripgrep) を使用します。デフォルトでは、ripgrep は `.gitignore` パターンを尊重します。つまり、`.gitignore` にリストされているファイルとディレクトリは検索とリストから除外されます。 +内部的には、`grep`、`glob` などのツールは内部で [ripgrep](https://github.com/BurntSushi/ripgrep) を使用します。デフォルトでは、ripgrep は `.gitignore` パターンを尊重します。つまり、`.gitignore` にリストされているファイルとディレクトリは検索とリストから除外されます。 --- diff --git a/packages/web/src/content/docs/ja/zen.mdx b/packages/web/src/content/docs/ja/zen.mdx index 93ec6fbec..b8da1308c 100644 --- a/packages/web/src/content/docs/ja/zen.mdx +++ b/packages/web/src/content/docs/ja/zen.mdx @@ -80,6 +80,8 @@ OpenCode Zen は、OpenCode のほかのプロバイダーと同じように動� | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ OpenCode Zen は、OpenCode のほかのプロバイダーと同じように動� | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | OpenCode 設定で使う [model id](/docs/config/#models) は `opencode/<model-id>` 形式です。たとえば、GPT 5.3 Codex では設定に `opencode/gpt-5.3-codex` を使用します。 @@ -114,7 +115,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。 - MiMo V2 Pro Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。 - MiMo V2 Omni Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。 -- Qwen3.6 Plus Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。 - Nemotron 3 Super Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。 - Big Pickle はステルスモデルで、期間限定で OpenCode で無料提供されています。チームはこの期間中にフィードバックを集め、モデルを改善しています。 @@ -208,8 +209,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: 無料提供期間中、収集されたデータがモデル改善に使われる場合があります。 - MiMo V2 Pro Free: 無料提供期間中、収集されたデータがモデル改善に使われる場合があります。 - MiMo V2 Omni Free: 無料提供期間中、収集されたデータがモデル改善に使われる場合があります。 -- Qwen3.6 Plus Free: 無料提供期間中、収集されたデータがモデル改善に使われる場合があります。 -- Nemotron 3 Super Free: 無料提供期間中、収集されたデータがモデル改善に使われる場合があります。 +- Nemotron 3 Super Free（NVIDIA の無料エンドポイント）: [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) に基づいて提供されます。試用専用であり、本番環境や機密性の高いデータには使用しないでください。プロンプトと出力は、NVIDIA が自社のモデルとサービスを改善するために記録します。個人情報や機密データは送信しないでください。 - OpenAI APIs: リクエストは [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) に従って 30 日間保持されます。 - Anthropic APIs: リクエストは [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) に従って 30 日間保持されます。 diff --git a/packages/web/src/content/docs/ko/go.mdx b/packages/web/src/content/docs/ko/go.mdx index 25d4c2760..9af7541e1 100644 --- a/packages/web/src/content/docs/ko/go.mdx +++ b/packages/web/src/content/docs/ko/go.mdx @@ -59,6 +59,8 @@ workspace당 한 명의 멤버만 OpenCode Go를 구독할 수 있습니다. - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** 새로운 모델을 테스트하고 추가함에 따라 이 목록은 변경될 수 있습니다. @@ -77,17 +79,25 @@ OpenCode Go에는 다음과 같은 한도가 포함됩니다. 아래 표는 일반적인 Go 사용 패턴을 기준으로 한 예상 요청 횟수를 보여줍니다. -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ----------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| 5시간당 요청 횟수 | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| 주간 요청 횟수 | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| 월간 요청 횟수 | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | 5시간당 요청 횟수 | 주간 요청 횟수 | 월간 요청 횟수 | +| ------------ | ----------------- | -------------- | -------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | 예상치는 관찰된 평균 요청 패턴을 기준으로 합니다. - GLM-5/5.1 — 요청당 입력 700, 캐시 52,000, 출력 토큰 150 - Kimi K2.5 — 요청당 입력 870, 캐시 55,000, 출력 토큰 200 - MiniMax M2.7/M2.5 — 요청당 입력 300, 캐시 55,000, 출력 토큰 125 +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 요청당 입력 350, 캐시 41,000, 출력 토큰 250 - MiMo-V2-Omni — 요청당 입력 1000, 캐시 60,000, 출력 토큰 140 @@ -120,6 +130,8 @@ Zen 잔액에 크레딧도 있다면, console에서 **Use balance** 옵션을 � | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | OpenCode config의 [model id](/docs/config/#models)는 `opencode-go/<model-id>` 형식을 사용합니다. 예를 들어 Kimi K2.5의 경우 config에서 `opencode-go/kimi-k2.5`를 사용하면 됩니다. diff --git a/packages/web/src/content/docs/ko/modes.mdx b/packages/web/src/content/docs/ko/modes.mdx index 35bc4d226..32746d1d0 100644 --- a/packages/web/src/content/docs/ko/modes.mdx +++ b/packages/web/src/content/docs/ko/modes.mdx @@ -232,7 +232,6 @@ Markdown 파일 이름은 모드 이름 (예 : `review.md`는 `review` 모드를 | `read` | 읽는 파일 내용 | | `grep` | 파일 검색 | | `glob` | 패턴으로 찾기 | -| `list` | 디렉토리 내용 보기 | | `patch` | 파일에 패치 적용 | | `todowrite` | 할 일(Todo) 목록 관리 | | `webfetch` | 웹사이트 가져오기 | diff --git a/packages/web/src/content/docs/ko/permissions.mdx b/packages/web/src/content/docs/ko/permissions.mdx index ec129f45c..0742089d6 100644 --- a/packages/web/src/content/docs/ko/permissions.mdx +++ b/packages/web/src/content/docs/ko/permissions.mdx @@ -88,7 +88,7 @@ Permission 본 사용 간단한 wildcard 일치: ## 외부 디렉터리 -`external_directory`를 사용하여 도구가 opencode가 시작된 작업 디렉토리 밖에 터치 경로가 호출되도록합니다. 이것은 입력 (예 : `read`, `edit`, `list`, `glob`, `glob`, `grep` 및 많은 `bash` 명령)로 경로를 수행하는 모든 도구에 적용됩니다. +`external_directory`를 사용하여 도구가 opencode가 시작된 작업 디렉토리 밖에 터치 경로가 호출되도록합니다. 이것은 입력 (예 : `read`, `edit`, `glob`, `grep` 및 많은 `bash` 명령)로 경로를 수행하는 모든 도구에 적용됩니다. 홈 확장 (`~/...`와 같은) 패턴이 작성된 방법에 영향을 미칩니다. 그것은 현재의 작업 공간의 외부 경로 부분을 만들지 않습니다, 그래서 작업 디렉토리 외부 경로는 여전히 `external_directory`를 통해 허용해야합니다. @@ -133,7 +133,6 @@ opencode 권한은 도구 이름에 의해 키 입력되며, 두 개의 안전 � - `edit` - 모든 파일 수정 (covers `edit`, `write`, `patch`, `multiedit`) - `glob` - 파일 globbing (glob 패턴 매칭) - `grep` - 콘텐츠 검색 ( regex 패턴 매칭) -- `list` - 디렉토리의 목록 파일 (폴더 경로 매칭) - `bash` - shell 명령 실행 (`git status --porcelain`와 같은 팟 명령) - `task` - 에이전트 실행 (작업 에이전트 유형) - `skill` - 기술을 로딩 (기술 이름을 매칭) diff --git a/packages/web/src/content/docs/ko/tools.mdx b/packages/web/src/content/docs/ko/tools.mdx index 33976b66f..49bea93cb 100644 --- a/packages/web/src/content/docs/ko/tools.mdx +++ b/packages/web/src/content/docs/ko/tools.mdx @@ -151,23 +151,6 @@ Codebase에서 빠른 콘텐츠 검색. 전체 regex 문법 및 파일 패턴 � --- -### list - -주어진 경로의 파일 및 디렉토리 목록. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -이 도구는 디렉토리 내용을 나열합니다. 그것은 glob 패턴을 필터 결과에 받아들입니다. - ---- - ### lsp (실험적) 정의, 참고, hover info 및 호출 hierarchy와 같은 코드 인텔리전스 기능을 얻기 위해 구성 된 LSP 서버와 인터랙트. @@ -341,7 +324,7 @@ MCP 서버 구성에 대한 [Learn more](/docs/mcp-servers). ## 내부 -내부, 도구 `grep`, `glob`, 그리고 `list` 사용 [ripgrep](https://github.com/BurntSushi/ripgrep) 후드 아래에. 기본적으로 ripgrep은 `.gitignore` 패턴을 존중하며 `.gitignore`에 나열된 파일 및 디렉토리를 검색 및 목록에서 제외됩니다. +내부, 도구 `grep` 그리고 `glob` 사용 [ripgrep](https://github.com/BurntSushi/ripgrep) 후드 아래에. 기본적으로 ripgrep은 `.gitignore` 패턴을 존중하며 `.gitignore`에 나열된 파일 및 디렉토리를 검색 및 목록에서 제외됩니다. --- diff --git a/packages/web/src/content/docs/ko/zen.mdx b/packages/web/src/content/docs/ko/zen.mdx index 08f57eaf9..af74b71af 100644 --- a/packages/web/src/content/docs/ko/zen.mdx +++ b/packages/web/src/content/docs/ko/zen.mdx @@ -80,6 +80,8 @@ OpenCode Zen은 OpenCode의 다른 provider와 똑같이 작동합니다. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ OpenCode Zen은 OpenCode의 다른 provider와 똑같이 작동합니다. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | OpenCode config에서 사용하는 [모델 ID](/docs/config/#models)는 `opencode/<model-id>` 형식입니다. 예를 들어 GPT 5.3 Codex를 사용하려면 config에서 `opencode/gpt-5.3-codex`를 사용하면 됩니다. @@ -114,7 +115,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. - MiMo V2 Pro Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. - MiMo V2 Omni Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. -- Qwen3.6 Plus Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. - Nemotron 3 Super Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. - Big Pickle은 한정된 기간 동안 OpenCode에서 무료로 제공되는 stealth model입니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다. @@ -208,8 +209,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: 무료 제공 기간에는 수집된 데이터가 모델 개선에 사용될 수 있습니다. - MiMo V2 Pro Free: 무료 제공 기간에는 수집된 데이터가 모델 개선에 사용될 수 있습니다. - MiMo V2 Omni Free: 무료 제공 기간에는 수집된 데이터가 모델 개선에 사용될 수 있습니다. -- Qwen3.6 Plus Free: 무료 제공 기간에는 수집된 데이터가 모델 개선에 사용될 수 있습니다. -- Nemotron 3 Super Free: 무료 제공 기간에는 수집된 데이터가 모델 개선에 사용될 수 있습니다. +- Nemotron 3 Super Free(NVIDIA 무료 엔드포인트): [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf)에 따라 제공됩니다. 평가판 전용이며 프로덕션 환경이나 민감한 데이터에는 사용할 수 없습니다. NVIDIA는 자사 모델과 서비스를 개선하기 위해 프롬프트와 출력을 기록합니다. 개인 정보나 기밀 데이터는 제출하지 마세요. - OpenAI APIs: 요청은 [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data)에 따라 30일 동안 보관됩니다. - Anthropic APIs: 요청은 [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage)에 따라 30일 동안 보관됩니다. diff --git a/packages/web/src/content/docs/modes.mdx b/packages/web/src/content/docs/modes.mdx index 5f23df254..b8ea69739 100644 --- a/packages/web/src/content/docs/modes.mdx +++ b/packages/web/src/content/docs/modes.mdx @@ -225,18 +225,17 @@ If no tools are specified, all tools are enabled by default. Here are all the tools can be controlled through the mode config. -| Tool | Description | -| ----------- | ----------------------- | -| `bash` | Execute shell commands | -| `edit` | Modify existing files | -| `write` | Create new files | -| `read` | Read file contents | -| `grep` | Search file contents | -| `glob` | Find files by pattern | -| `list` | List directory contents | -| `patch` | Apply patches to files | -| `todowrite` | Manage todo lists | -| `webfetch` | Fetch web content | +| Tool | Description | +| ----------- | ---------------------- | +| `bash` | Execute shell commands | +| `edit` | Modify existing files | +| `write` | Create new files | +| `read` | Read file contents | +| `grep` | Search file contents | +| `glob` | Find files by pattern | +| `patch` | Apply patches to files | +| `todowrite` | Manage todo lists | +| `webfetch` | Fetch web content | --- diff --git a/packages/web/src/content/docs/nb/go.mdx b/packages/web/src/content/docs/nb/go.mdx index cdf0c1b46..1638e5e48 100644 --- a/packages/web/src/content/docs/nb/go.mdx +++ b/packages/web/src/content/docs/nb/go.mdx @@ -69,6 +69,8 @@ Den nåværende listen over modeller inkluderer: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Listen over modeller kan endres etter hvert som vi tester og legger til nye. @@ -87,17 +89,25 @@ Grensene er definert i dollarverdi. Dette betyr at ditt faktiske antall forespø Tabellen nedenfor gir et estimert antall forespørsler basert på typiske bruksmønstre for Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------------ | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| forespørsler per 5 timer | 880 | 1 150 | 1 850 | 1 290 | 2 150 | 14 000 | 20 000 | -| forespørsler per uke | 2 150 | 2 880 | 4 630 | 3 225 | 5 450 | 35 000 | 50 000 | -| forespørsler per måned | 4 300 | 5 750 | 9 250 | 6 450 | 10 900 | 70 000 | 100 000 | +| Model | forespørsler per 5 timer | forespørsler per uke | forespørsler per måned | +| ------------ | ------------------------ | -------------------- | ---------------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Estimatene er basert på observerte gjennomsnittlige forespørselsmønstre: - GLM-5/5.1 — 700 input, 52 000 bufret, 150 output-tokens per forespørsel - Kimi K2.5 — 870 input, 55 000 bufret, 200 output-tokens per forespørsel - MiniMax M2.7/M2.5 — 300 input, 55 000 bufret, 125 output-tokens per forespørsel +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 input, 41 000 bufret, 250 output-tokens per forespørsel - MiMo-V2-Omni — 1000 input, 60 000 bufret, 140 output-tokens per forespørsel @@ -132,6 +142,8 @@ Du kan også få tilgang til Go-modeller gjennom følgende API-endepunkter. | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | [Modell-ID-en](/docs/config/#models) i din OpenCode-konfigurasjon bruker formatet `opencode-go/<model-id>`. For eksempel, for Kimi K2.5, vil du diff --git a/packages/web/src/content/docs/nb/modes.mdx b/packages/web/src/content/docs/nb/modes.mdx index bf73ff040..e99c511be 100644 --- a/packages/web/src/content/docs/nb/modes.mdx +++ b/packages/web/src/content/docs/nb/modes.mdx @@ -232,7 +232,6 @@ Her er alle verktøyene som kan kontrolleres gjennom moduskonfigurasjonen. | `read` | Les filinnhold | | `grep` | Søk i filinnhold | | `glob` | Finn filer etter mønster | -| `list` | List opp kataloginnhold | | `patch` | Bruk patcher på filer | | `todowrite` | Administrer gjøremålslister | | `webfetch` | Hent webinnhold | diff --git a/packages/web/src/content/docs/nb/permissions.mdx b/packages/web/src/content/docs/nb/permissions.mdx index 6437555a2..5c63b251e 100644 --- a/packages/web/src/content/docs/nb/permissions.mdx +++ b/packages/web/src/content/docs/nb/permissions.mdx @@ -88,7 +88,7 @@ Du kan bruke `~` eller `$HOME` i starten av et mønster for å referere til hjem ### Eksterne kataloger -Bruk `external_directory` for å tillate verktøyanrop som berører stier utenfor arbeidskatalogen der OpenCode ble startet. Dette gjelder alle verktøy som tar en bane som input (for eksempel `read`, `edit`, `list`, `glob`, `grep` og mange `bash`-kommandoer). +Bruk `external_directory` for å tillate verktøyanrop som berører stier utenfor arbeidskatalogen der OpenCode ble startet. Dette gjelder alle verktøy som tar en bane som input (for eksempel `read`, `edit`, `glob`, `grep` og mange `bash`-kommandoer). Hjemmeutvidelse (som `~/...`) påvirker bare hvordan et mønster skrives. Den gjør ikke en ekstern bane til en del av det gjeldende arbeidsområdet, så stier utenfor arbeidskatalogen må fortsatt tillates via `external_directory`. @@ -133,7 +133,6 @@ OpenCode-tillatelser tastes inn etter verktøynavn, pluss et par sikkerhetsvakte - `edit` — alle filendringer (dekker `edit`, `write`, `patch`, `multiedit`) - `glob` — fil-globing (tilsvarer glob-mønsteret) - `grep` — innholdssøk (samsvarer med regex-mønsteret) -- `list` — viser filer i en katalog (tilsvarer katalogbanen) - `bash` — kjører skallkommandoer (matcher analyserte kommandoer som `git status --porcelain`) - `task` — start av subagenter (tilsvarer subagenttypen) - `skill` — laster en ferdighet (tilsvarer navnet på ferdigheten) diff --git a/packages/web/src/content/docs/nb/tools.mdx b/packages/web/src/content/docs/nb/tools.mdx index be80a0e2b..8c871f11c 100644 --- a/packages/web/src/content/docs/nb/tools.mdx +++ b/packages/web/src/content/docs/nb/tools.mdx @@ -151,23 +151,6 @@ Søk etter filer ved å bruke glob-mønstre som `**/*.js` eller `src/**/*.ts`. R --- -### list - -List filer og kataloger i en gitt bane. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Dette verktøyet viser kataloginnhold. Den aksepterer glob-mønstre for å filtrere resultater. - ---- - ### lsp (eksperimentell) Samhandle med dine konfigurerte LSP-servere for å få kodeintelligens-funksjoner som definisjoner, referanser, hover-informasjon og kallhierarki. @@ -341,7 +324,7 @@ MCP (Model Context Protocol) servere lar deg integrere eksterne verktøy og tjen ## Internaler -Internt bruker verktøy som `grep`, `glob` og `list` [ripgrep](https://github.com/BurntSushi/ripgrep) i bakgrunnen. Som standard respekterer ripgrep `.gitignore`-mønstre, noe som betyr at filer og kataloger som er oppført i `.gitignore` vil bli ekskludert fra søk og oppføringer. +Internt bruker verktøy som `grep` og `glob` [ripgrep](https://github.com/BurntSushi/ripgrep) i bakgrunnen. Som standard respekterer ripgrep `.gitignore`-mønstre, noe som betyr at filer og kataloger som er oppført i `.gitignore` vil bli ekskludert fra søk og oppføringer. --- diff --git a/packages/web/src/content/docs/nb/zen.mdx b/packages/web/src/content/docs/nb/zen.mdx index 02ae767b6..a216be106 100644 --- a/packages/web/src/content/docs/nb/zen.mdx +++ b/packages/web/src/content/docs/nb/zen.mdx @@ -89,6 +89,8 @@ Du kan også få tilgang til modellene våre gjennom følgende API-endepunkter. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ Du kan også få tilgang til modellene våre gjennom følgende API-endepunkter. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | [modell-id](/docs/config/#models) i OpenCode-konfigurasjonen din @@ -125,7 +126,8 @@ Vi støtter en pay-as-you-go-modell. Nedenfor er prisene **per 1M tokens**. | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ Gratis-modellene: - MiniMax M2.5 Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. - MiMo V2 Pro Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. - MiMo V2 Omni Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. -- Qwen3.6 Plus Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. - Nemotron 3 Super Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. - Big Pickle er en stealth-modell som er gratis på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen. @@ -222,8 +223,7 @@ Alle modellene våre hostes i US. Leverandørene våre følger en policy for zer - MiniMax M2.5 Free: I gratisperioden kan innsamlede data brukes til å forbedre modellen. - MiMo V2 Pro Free: I gratisperioden kan innsamlede data brukes til å forbedre modellen. - MiMo V2 Omni Free: I gratisperioden kan innsamlede data brukes til å forbedre modellen. -- Qwen3.6 Plus Free: I gratisperioden kan innsamlede data brukes til å forbedre modellen. -- Nemotron 3 Super Free: I gratisperioden kan innsamlede data brukes til å forbedre modellen. +- Nemotron 3 Super Free (gratis NVIDIA-endepunkter): 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 for prøvebruk, ikke for produksjon eller sensitive data. Prompter og svar logges av NVIDIA for å forbedre modellene og tjenestene deres. Ikke send inn personopplysninger eller konfidensielle data. - OpenAI APIs: Forespørsler lagres i 30 dager i samsvar med [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data). - Anthropic APIs: Forespørsler lagres i 30 dager i samsvar med [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage). diff --git a/packages/web/src/content/docs/permissions.mdx b/packages/web/src/content/docs/permissions.mdx index a470fddd7..6383b2a3f 100644 --- a/packages/web/src/content/docs/permissions.mdx +++ b/packages/web/src/content/docs/permissions.mdx @@ -88,7 +88,7 @@ You can use `~` or `$HOME` at the start of a pattern to reference your home dire ### External Directories -Use `external_directory` to allow tool calls that touch paths outside the working directory where OpenCode was started. This applies to any tool that takes a path as input (for example `read`, `edit`, `list`, `glob`, `grep`, and many `bash` commands). +Use `external_directory` to allow tool calls that touch paths outside the working directory where OpenCode was started. This applies to any tool that takes a path as input (for example `read`, `edit`, `glob`, `grep`, and many `bash` commands). Home expansion (like `~/...`) only affects how a pattern is written. It does not make an external path part of the current workspace, so paths outside the working directory must still be allowed via `external_directory`. @@ -133,7 +133,6 @@ OpenCode permissions are keyed by tool name, plus a couple of safety guards: - `edit` — all file modifications (covers `edit`, `write`, `patch`, `multiedit`) - `glob` — file globbing (matches the glob pattern) - `grep` — content search (matches the regex pattern) -- `list` — listing files in a directory (matches the directory path) - `bash` — running shell commands (matches parsed commands like `git status --porcelain`) - `task` — launching subagents (matches the subagent type) - `skill` — loading a skill (matches the skill name) diff --git a/packages/web/src/content/docs/pl/go.mdx b/packages/web/src/content/docs/pl/go.mdx index a11a38d3e..c5f17672a 100644 --- a/packages/web/src/content/docs/pl/go.mdx +++ b/packages/web/src/content/docs/pl/go.mdx @@ -63,6 +63,8 @@ Obecna lista modeli obejmuje: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Lista modeli może ulec zmianie w miarę testowania i dodawania nowych. @@ -81,17 +83,25 @@ Limity są zdefiniowane w wartości w dolarach. Oznacza to, że rzeczywista licz Poniższa tabela przedstawia szacunkową liczbę żądań na podstawie typowych wzorców korzystania z Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| żądania na 5 godzin | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| żądania na tydzień | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| żądania na miesiąc | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | żądania na 5 godzin | żądania na tydzień | żądania na miesiąc | +| ------------ | ------------------- | ------------------ | ------------------ | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Szacunki opierają się na zaobserwowanych średnich wzorcach żądań: - GLM-5/5.1 — 700 tokenów wejściowych, 52 000 w pamięci podręcznej, 150 tokenów wyjściowych na żądanie - Kimi K2.5 — 870 tokenów wejściowych, 55 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie - MiniMax M2.7/M2.5 — 300 tokenów wejściowych, 55 000 w pamięci podręcznej, 125 tokenów wyjściowych na żądanie +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 tokenów wejściowych, 41 000 w pamięci podręcznej, 250 tokenów wyjściowych na żądanie - MiMo-V2-Omni — 1000 tokenów wejściowych, 60 000 w pamięci podręcznej, 140 tokenów wyjściowych na żądanie @@ -124,6 +134,8 @@ Możesz również uzyskać dostęp do modeli Go za pośrednictwem następującyc | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | [ID modelu](/docs/config/#models) w Twojej konfiguracji OpenCode używa formatu `opencode-go/<model-id>`. Na przykład dla Kimi K2.5 należy użyć diff --git a/packages/web/src/content/docs/pl/modes.mdx b/packages/web/src/content/docs/pl/modes.mdx index b28b16086..8d7c2568d 100644 --- a/packages/web/src/content/docs/pl/modes.mdx +++ b/packages/web/src/content/docs/pl/modes.mdx @@ -233,7 +233,6 @@ Oto wszystkie narzędzia, które można sterować za pomocą konfiguracji trybó | `read` | Przeczytaj zawartość pliku | | `grep` | Wyszukaj zawartość pliku | | `glob` | Znajdź pliki według wzorca | -| `list` | Lista zawartości katalogu | | `patch` | Zastosuj poprawki do plików | | `todowrite` | Zarządzaj listami rzeczy do wykonania | | `webfetch` | Pobierz zawartość internetową | diff --git a/packages/web/src/content/docs/pl/permissions.mdx b/packages/web/src/content/docs/pl/permissions.mdx index 6a7840ac7..a5c05b6dc 100644 --- a/packages/web/src/content/docs/pl/permissions.mdx +++ b/packages/web/src/content/docs/pl/permissions.mdx @@ -88,7 +88,7 @@ Możesz używać `~` lub `$HOME` na początku wzorca, aby zastosować się do sw ### Katalogi zewnętrzne -Użycie `external_directory`, aby zezwolić na wywołanie narzędzia, które obsługuje obsługę poza katalogiem roboczym, z uruchomieniem opencode. Dotyczy każdego narzędzia, które jako dane wejściowe zostało przyjęte (na przykład `read`, `edit`, `list`, `glob`, `grep` i wiele założycieli `bash`). +Użycie `external_directory`, aby zezwolić na wywołanie narzędzia, które obsługuje obsługę poza katalogiem roboczym, z uruchomieniem opencode. Dotyczy każdego narzędzia, które jako dane wejściowe zostało przyjęte (na przykład `read`, `edit`, `glob`, `grep` i wiele założycieli `bash`). Rozszerzenie domu (jak `~/...`) wpływa tylko na sposób za zwyczajowy wzorca. Nie powoduje to, że strategie zewnętrzne stają się stosowane przez `external_directory`. @@ -133,7 +133,6 @@ Uprawnienia opencode są określane na podstawie nazwy narzędzia i kilku zabezp - `edit` — wszystkie modyfikacje plików (obejmuje `edit`, `write`, `patch`, `multiedit`) - `glob` — maglowanie plików (pasuje do wzorców globowania) - `grep` — wyszukiwanie treści (pasuje do wzorca regularnego) -- `list` — wyświetlanie listy plików w katalogu (pasuje do katalogu) - `bash` — uruchamianie poleceń shell (pasuje do poleceń przeanalizowanych, takich jak `git status --porcelain`) - `task` — uruchamianie podagentów (odpowiada typowi podagenta) - `skill` — ładowanie umiejętności (pasuje do nazwy umiejętności) diff --git a/packages/web/src/content/docs/pl/tools.mdx b/packages/web/src/content/docs/pl/tools.mdx index 649c744e0..180e043cd 100644 --- a/packages/web/src/content/docs/pl/tools.mdx +++ b/packages/web/src/content/docs/pl/tools.mdx @@ -151,23 +151,6 @@ Szukaj plików przy użyciu wzorców glob, takich jak `**/*.js` lub `src/**/*.ts --- -### list - -Wyświetla listę plików i katalogów w podanej ścieżce. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -To narzędzie wyświetla zawartość katalogu. Akceptuje wzorce glob do filtrowania wyników. - ---- - ### LSP (eksperymentalne) Interakcja ze skonfigurowanymi serwerami LSP w celu uzyskania funkcji analizy kodu, takich jak definicje, referencje, podpowiedzi (hover) i hierarchia wywołań. @@ -341,7 +324,7 @@ Serwery MCP (Model Context Protocol) umożliwiają integrację zewnętrznych nar ## Szczegóły techniczne -Wewnętrznie narzędzia takie jak `grep`, `glob` i `list` używają [ripgrep](https://github.com/BurntSushi/ripgrep). Domyślnie ripgrep respektuje wzorce `.gitignore`, co oznacza, że pliki i katalogi wymienione w Twoim `.gitignore` zostaną wykluczone z wyszukiwań i list. +Wewnętrznie narzędzia takie jak `grep` i `glob` używają [ripgrep](https://github.com/BurntSushi/ripgrep). Domyślnie ripgrep respektuje wzorce `.gitignore`, co oznacza, że pliki i katalogi wymienione w Twoim `.gitignore` zostaną wykluczone z wyszukiwań i list. --- diff --git a/packages/web/src/content/docs/pl/zen.mdx b/packages/web/src/content/docs/pl/zen.mdx index 98c8b85ef..ffbdb66fa 100644 --- a/packages/web/src/content/docs/pl/zen.mdx +++ b/packages/web/src/content/docs/pl/zen.mdx @@ -89,6 +89,8 @@ Możesz też uzyskać dostęp do naszych modeli przez poniższe endpointy API. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ Możesz też uzyskać dostęp do naszych modeli przez poniższe endpointy API. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | [ID modelu](/docs/config/#models) w Twojej konfiguracji OpenCode używa formatu @@ -125,7 +126,8 @@ Obsługujemy model pay-as-you-go. Poniżej znajdują się ceny **za 1M tokenów* | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -174,7 +176,6 @@ Darmowe modele: - MiniMax M2.5 Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. - MiMo V2 Pro Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. - MiMo V2 Omni Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. -- Qwen3.6 Plus Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. - Nemotron 3 Super Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. - Big Pickle to stealth model, który jest darmowy w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu. @@ -223,8 +224,7 @@ Wszystkie nasze modele są hostowane w US. Nasi dostawcy stosują politykę zero - MiniMax M2.5 Free: W czasie darmowego okresu zebrane dane mogą być wykorzystywane do ulepszania modelu. - MiMo V2 Pro Free: W czasie darmowego okresu zebrane dane mogą być wykorzystywane do ulepszania modelu. - MiMo V2 Omni Free: W czasie darmowego okresu zebrane dane mogą być wykorzystywane do ulepszania modelu. -- Qwen3.6 Plus Free: W czasie darmowego okresu zebrane dane mogą być wykorzystywane do ulepszania modelu. -- Nemotron 3 Super Free: W czasie darmowego okresu zebrane dane mogą być wykorzystywane do ulepszania modelu. +- Nemotron 3 Super Free (darmowe endpointy NVIDIA): Udostępniany zgodnie z [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Tylko do użytku próbnego, nie do produkcji ani danych wrażliwych. NVIDIA rejestruje prompty i odpowiedzi, aby ulepszać swoje modele i usługi. Nie przesyłaj danych osobowych ani poufnych. - OpenAI APIs: Żądania są przechowywane przez 30 dni zgodnie z [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data). - Anthropic APIs: Żądania są przechowywane przez 30 dni zgodnie z [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage). diff --git a/packages/web/src/content/docs/pt-br/go.mdx b/packages/web/src/content/docs/pt-br/go.mdx index ef1827b63..48afe36d9 100644 --- a/packages/web/src/content/docs/pt-br/go.mdx +++ b/packages/web/src/content/docs/pt-br/go.mdx @@ -69,6 +69,8 @@ A lista atual de modelos inclui: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** A lista de modelos pode mudar conforme testamos e adicionamos novos. @@ -87,17 +89,25 @@ Os limites são definidos em valor em dólares. Isso significa que a sua contage A tabela abaixo fornece uma contagem estimada de requisições com base nos padrões típicos de uso do Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ----------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| requisições por 5 horas | 880 | 1.150 | 1.850 | 1.290 | 2.150 | 14.000 | 20.000 | -| requisições por semana | 2.150 | 2.880 | 4.630 | 3.225 | 5.450 | 35.000 | 50.000 | -| requisições por mês | 4.300 | 5.750 | 9.250 | 6.450 | 10.900 | 70.000 | 100.000 | +| Model | requisições por 5 horas | requisições por semana | requisições por mês | +| ------------ | ----------------------- | ---------------------- | ------------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | As estimativas baseiam-se nos padrões médios de requisições observados: - GLM-5/5.1 — 700 tokens de entrada, 52.000 em cache, 150 tokens de saída por requisição - Kimi K2.5 — 870 tokens de entrada, 55.000 em cache, 200 tokens de saída por requisição - MiniMax M2.7/M2.5 — 300 tokens de entrada, 55.000 em cache, 125 tokens de saída por requisição +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 tokens de entrada, 41.000 em cache, 250 tokens de saída por requisição - MiMo-V2-Omni — 1000 tokens de entrada, 60.000 em cache, 140 tokens de saída por requisição @@ -132,6 +142,8 @@ Você também pode acessar os modelos do Go através dos seguintes endpoints de | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | O [ID do modelo](/docs/config/#models) na sua configuração do OpenCode usa o formato `opencode-go/<model-id>`. Por exemplo, para o Kimi K2.5, você usaria diff --git a/packages/web/src/content/docs/pt-br/modes.mdx b/packages/web/src/content/docs/pt-br/modes.mdx index b549d69de..b53fb4fcb 100644 --- a/packages/web/src/content/docs/pt-br/modes.mdx +++ b/packages/web/src/content/docs/pt-br/modes.mdx @@ -230,7 +230,6 @@ Aqui estão todas as ferramentas que podem ser controladas através da configura | `read` | Ler conteúdos de arquivos | | `grep` | Pesquisar conteúdos de arquivos | | `glob` | Encontrar arquivos por padrão | -| `list` | Listar conteúdos de diretório | | `patch` | Aplicar patches a arquivos | | `todowrite` | Gerenciar listas de tarefas | | `webfetch` | Buscar conteúdo da web | diff --git a/packages/web/src/content/docs/pt-br/permissions.mdx b/packages/web/src/content/docs/pt-br/permissions.mdx index c3850c00c..4facc9f72 100644 --- a/packages/web/src/content/docs/pt-br/permissions.mdx +++ b/packages/web/src/content/docs/pt-br/permissions.mdx @@ -88,7 +88,7 @@ Você pode usar `~` ou `$HOME` no início de um padrão para referenciar seu dir ### Diretórios Externos -Use `external_directory` para permitir chamadas de ferramentas que tocam em caminhos fora do diretório de trabalho onde o opencode foi iniciado. Isso se aplica a qualquer ferramenta que aceite um caminho como entrada (por exemplo, `read`, `edit`, `list`, `glob`, `grep` e muitos comandos `bash`). +Use `external_directory` para permitir chamadas de ferramentas que tocam em caminhos fora do diretório de trabalho onde o opencode foi iniciado. Isso se aplica a qualquer ferramenta que aceite um caminho como entrada (por exemplo, `read`, `edit`, `glob`, `grep` e muitos comandos `bash`). A expansão do home (como `~/...`) afeta apenas como um padrão é escrito. Não torna um caminho externo parte do espaço de trabalho atual, então caminhos fora do diretório de trabalho ainda devem ser permitidos via `external_directory`. @@ -133,7 +133,6 @@ As permissões do opencode são indexadas pelo nome da ferramenta, além de algu - `edit` — todas as modificações de arquivo (cobre `edit`, `write`, `patch`, `multiedit`) - `glob` — globbing de arquivos (corresponde ao padrão glob) - `grep` — busca de conteúdo (corresponde ao padrão regex) -- `list` — listagem de arquivos em um diretório (corresponde ao caminho do diretório) - `bash` — execução de comandos de shell (corresponde a comandos analisados como `git status --porcelain`) - `task` — lançamento de subagentes (corresponde ao tipo de subagente) - `skill` — carregamento de uma habilidade (corresponde ao nome da habilidade) diff --git a/packages/web/src/content/docs/pt-br/tools.mdx b/packages/web/src/content/docs/pt-br/tools.mdx index d762fdf14..4c7b37197 100644 --- a/packages/web/src/content/docs/pt-br/tools.mdx +++ b/packages/web/src/content/docs/pt-br/tools.mdx @@ -151,23 +151,6 @@ Pesquise arquivos usando padrões glob como `**/*.js` ou `src/**/*.ts`. Retorna --- -### list - -Liste arquivos e diretórios em um determinado caminho. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Esta ferramenta lista o conteúdo do diretório. Aceita padrões glob para filtrar resultados. - ---- - ### lsp (experimental) Interaja com seus servidores LSP configurados para obter recursos de inteligência de código, como definições, referências, informações de hover e hierarquia de chamadas. @@ -341,7 +324,7 @@ Servidores MCP (Model Context Protocol) permitem que você integre ferramentas e ## Internos -Internamente, ferramentas como `grep`, `glob` e `list` usam [ripgrep](https://github.com/BurntSushi/ripgrep) por trás dos panos. Por padrão, o ripgrep respeita padrões `.gitignore`, o que significa que arquivos e diretórios listados em seu `.gitignore` serão excluídos de buscas e listagens. +Internamente, ferramentas como `grep` e `glob` usam [ripgrep](https://github.com/BurntSushi/ripgrep) por trás dos panos. Por padrão, o ripgrep respeita padrões `.gitignore`, o que significa que arquivos e diretórios listados em seu `.gitignore` serão excluídos de buscas e listagens. --- diff --git a/packages/web/src/content/docs/pt-br/zen.mdx b/packages/web/src/content/docs/pt-br/zen.mdx index fd6848df7..d911e441f 100644 --- a/packages/web/src/content/docs/pt-br/zen.mdx +++ b/packages/web/src/content/docs/pt-br/zen.mdx @@ -80,6 +80,8 @@ Você também pode acessar nossos modelos pelos seguintes endpoints de API. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ Você também pode acessar nossos modelos pelos seguintes endpoints de API. | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | O [model id](/docs/config/#models) na sua configuração do OpenCode usa o formato `opencode/<model-id>`. Por exemplo, para GPT 5.3 Codex, você usaria `opencode/gpt-5.3-codex` na sua configuração. @@ -114,7 +115,8 @@ Oferecemos um modelo pay-as-you-go. Abaixo estão os preços **por 1M tokens**. | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ Os modelos gratuitos: - MiniMax M2.5 Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. - MiMo V2 Pro Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. - MiMo V2 Omni Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. -- Qwen3.6 Plus Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. - Nemotron 3 Super Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. - Big Pickle é um modelo stealth que está gratuito no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo. @@ -208,8 +209,7 @@ Todos os nossos modelos são hospedados nos US. Nossos provedores seguem uma pol - MiniMax M2.5 Free: Durante seu período gratuito, os dados coletados podem ser usados para melhorar o modelo. - MiMo V2 Pro Free: Durante seu período gratuito, os dados coletados podem ser usados para melhorar o modelo. - MiMo V2 Omni Free: Durante seu período gratuito, os dados coletados podem ser usados para melhorar o modelo. -- Qwen3.6 Plus Free: Durante seu período gratuito, os dados coletados podem ser usados para melhorar o modelo. -- Nemotron 3 Super Free: Durante seu período gratuito, os dados coletados podem ser usados para melhorar o modelo. +- Nemotron 3 Super Free (endpoints gratuitos da NVIDIA): Fornecido sob os [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Apenas para uso de avaliação, não para produção nem dados sensíveis. A NVIDIA registra prompts e saídas para melhorar seus modelos e serviços. Não envie dados pessoais ou confidenciais. - OpenAI APIs: As solicitações são retidas por 30 dias de acordo com [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data). - Anthropic APIs: As solicitações são retidas por 30 dias de acordo com [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage). diff --git a/packages/web/src/content/docs/ru/go.mdx b/packages/web/src/content/docs/ru/go.mdx index ed74aed73..dacaf6527 100644 --- a/packages/web/src/content/docs/ru/go.mdx +++ b/packages/web/src/content/docs/ru/go.mdx @@ -69,6 +69,8 @@ OpenCode Go работает так же, как и любой другой пр - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Список моделей может меняться по мере того, как мы тестируем и добавляем новые. @@ -87,17 +89,25 @@ OpenCode Go включает следующие лимиты: В таблице ниже приведено примерное количество запросов на основе типичных сценариев использования Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| запросов за 5 часов | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| запросов в неделю | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| запросов в месяц | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | запросов за 5 часов | запросов в неделю | запросов в месяц | +| ------------ | ------------------- | ----------------- | ---------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Оценки основаны на наблюдаемых средних показателях запросов: - GLM-5/5.1 — 700 входных, 52,000 кешированных, 150 выходных токенов на запрос - Kimi K2.5 — 870 входных, 55,000 кешированных, 200 выходных токенов на запрос - MiniMax M2.7/M2.5 — 300 входных, 55,000 кешированных, 125 выходных токенов на запрос +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 входных, 41,000 кешированных, 250 выходных токенов на запрос - MiMo-V2-Omni — 1000 входных, 60,000 кешированных, 140 выходных токенов на запрос @@ -132,6 +142,8 @@ OpenCode Go включает следующие лимиты: | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | [ID модели](/docs/config/#models) в вашем конфиге OpenCode использует формат `opencode-go/<model-id>`. Например, для Kimi K2.5 вам нужно diff --git a/packages/web/src/content/docs/ru/modes.mdx b/packages/web/src/content/docs/ru/modes.mdx index f1ebca386..e63c91ace 100644 --- a/packages/web/src/content/docs/ru/modes.mdx +++ b/packages/web/src/content/docs/ru/modes.mdx @@ -225,18 +225,17 @@ Provide constructive feedback without making direct changes. Вот всеми инструментами можно управлять через конфигурацию режима. -| Инструмент | Описание | -| ----------- | ----------------------- | -| `bash` | Execute shell commands | -| `edit` | Modify existing files | -| `write` | Create new files | -| `read` | Read file contents | -| `grep` | Search file contents | -| `glob` | Find files by pattern | -| `list` | List directory contents | -| `patch` | Apply patches to files | -| `todowrite` | Manage todo lists | -| `webfetch` | Fetch web content | +| Инструмент | Описание | +| ----------- | ---------------------- | +| `bash` | Execute shell commands | +| `edit` | Modify existing files | +| `write` | Create new files | +| `read` | Read file contents | +| `grep` | Search file contents | +| `glob` | Find files by pattern | +| `patch` | Apply patches to files | +| `todowrite` | Manage todo lists | +| `webfetch` | Fetch web content | --- diff --git a/packages/web/src/content/docs/ru/permissions.mdx b/packages/web/src/content/docs/ru/permissions.mdx index 70f3a804a..961a06824 100644 --- a/packages/web/src/content/docs/ru/permissions.mdx +++ b/packages/web/src/content/docs/ru/permissions.mdx @@ -88,7 +88,7 @@ opencode использует конфигурацию `permission`, чтобы ### Внешние каталоги -Используйте `external_directory`, чтобы разрешить вызовы инструментов, затрагивающие пути за пределами рабочего каталога, в котором был запущен opencode. Это применимо к любому инструменту, который принимает путь в качестве входных данных (например, `read`, `edit`, `list`, `glob`, `grep` и многие команды `bash`). +Используйте `external_directory`, чтобы разрешить вызовы инструментов, затрагивающие пути за пределами рабочего каталога, в котором был запущен opencode. Это применимо к любому инструменту, который принимает путь в качестве входных данных (например, `read`, `edit`, `glob`, `grep` и многие команды `bash`). Расширение дома (например, `~/...`) влияет только на запись шаблона. Он не делает внешний путь частью текущего рабочего пространства, поэтому пути за пределами рабочего каталога все равно должны быть разрешены через `external_directory`. @@ -133,7 +133,6 @@ opencode использует конфигурацию `permission`, чтобы - `edit` — все модификации файлов (охватывает `edit`, `write`, `patch`, `multiedit`) - `glob` — подстановка файла (соответствует шаблону подстановки) - `grep` — поиск по контенту (соответствует шаблону регулярного выражения) -- `list` — список файлов в каталоге (соответствует пути к каталогу) - `bash` — запуск shell-команд (соответствует проанализированным командам, например `git status --porcelain`) - `task` — запуск субагентов (соответствует типу субагента) - `skill` — загрузка навыка (соответствует названию навыка) diff --git a/packages/web/src/content/docs/ru/tools.mdx b/packages/web/src/content/docs/ru/tools.mdx index def6663fc..35958e036 100644 --- a/packages/web/src/content/docs/ru/tools.mdx +++ b/packages/web/src/content/docs/ru/tools.mdx @@ -151,23 +151,6 @@ description: Управляйте инструментами, которые м� --- -### list - -Список файлов и каталогов по заданному пути. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Этот инструмент отображает содержимое каталога. Он принимает шаблоны glob для фильтрации результатов. - ---- - ### lsp (экспериментальный) Взаимодействуйте с настроенными серверами LSP, чтобы получить функции анализа кода, такие как определения, ссылки, информация о наведении и иерархия вызовов. @@ -341,7 +324,7 @@ OPENCODE_ENABLE_EXA=1 opencode ## Внутреннее устройство -Внутренне такие инструменты, как `grep`, `glob` и `list`, используют [ripgrep](https://github.com/BurntSushi/ripgrep). По умолчанию ripgrep учитывает шаблоны `.gitignore`, что означает, что файлы и каталоги, перечисленные в вашем `.gitignore`, будут исключены из поиска и списков. +Внутренне такие инструменты, как `grep` и `glob`, используют [ripgrep](https://github.com/BurntSushi/ripgrep). По умолчанию ripgrep учитывает шаблоны `.gitignore`, что означает, что файлы и каталоги, перечисленные в вашем `.gitignore`, будут исключены из поиска и списков. --- diff --git a/packages/web/src/content/docs/ru/zen.mdx b/packages/web/src/content/docs/ru/zen.mdx index 7a087d85a..8a92bf502 100644 --- a/packages/web/src/content/docs/ru/zen.mdx +++ b/packages/web/src/content/docs/ru/zen.mdx @@ -89,6 +89,8 @@ OpenCode Zen работает как любой другой провайдер | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -97,7 +99,6 @@ OpenCode Zen работает как любой другой провайдер | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | [идентификатор модели](/docs/config/#models) в вашей конфигурации OpenCode @@ -125,7 +126,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -173,7 +175,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. - MiMo V2 Pro Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. - MiMo V2 Omni Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. -- Qwen3.6 Plus Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. - Nemotron 3 Super Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. - Big Pickle — это скрытая модель, которая доступна бесплатно в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель. @@ -222,8 +223,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: во время бесплатного периода собранные данные могут использоваться для улучшения модели. - MiMo V2 Pro Free: во время бесплатного периода собранные данные могут использоваться для улучшения модели. - MiMo V2 Omni Free: во время бесплатного периода собранные данные могут использоваться для улучшения модели. -- Qwen3.6 Plus Free: во время бесплатного периода собранные данные могут использоваться для улучшения модели. -- Nemotron 3 Super Free: во время бесплатного периода собранные данные могут использоваться для улучшения модели. +- Nemotron 3 Super Free (бесплатные эндпоинты NVIDIA): предоставляется в соответствии с [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Только для пробного использования, не для продакшена и не для чувствительных данных. NVIDIA логирует запросы и ответы, чтобы улучшать свои модели и сервисы. Не отправляйте персональные или конфиденциальные данные. - OpenAI APIs: запросы хранятся 30 дней в соответствии с [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data). - Anthropic APIs: запросы хранятся 30 дней в соответствии с [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage). diff --git a/packages/web/src/content/docs/th/go.mdx b/packages/web/src/content/docs/th/go.mdx index b0cf2a8bf..aa26f7dcf 100644 --- a/packages/web/src/content/docs/th/go.mdx +++ b/packages/web/src/content/docs/th/go.mdx @@ -59,6 +59,8 @@ OpenCode Go ทำงานเหมือนกับผู้ให้บร� - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** รายชื่อโมเดลอาจมีการเปลี่ยนแปลงเมื่อเราทำการทดสอบและเพิ่มโมเดลใหม่ๆ @@ -77,17 +79,25 @@ OpenCode Go มีขีดจำกัดดังต่อไปนี้: ตารางด้านล่างแสดงจำนวน request โดยประมาณตามรูปแบบการใช้งานปกติของ Go: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ---------------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| requests ต่อ 5 ชั่วโมง | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| requests ต่อสัปดาห์ | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| requests ต่อเดือน | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | requests ต่อ 5 ชั่วโมง | requests ต่อสัปดาห์ | requests ต่อเดือน | +| ------------ | ---------------------- | ------------------- | ----------------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | การประมาณการอ้างอิงจากรูปแบบการใช้งาน request โดยเฉลี่ยที่สังเกตพบ: - GLM-5/5.1 — 700 input, 52,000 cached, 150 output tokens ต่อ request - Kimi K2.5 — 870 input, 55,000 cached, 200 output tokens ต่อ request - MiniMax M2.7/M2.5 — 300 input, 55,000 cached, 125 output tokens ต่อ request +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 350 input, 41,000 cached, 250 output tokens ต่อ request - MiMo-V2-Omni — 1000 input, 60,000 cached, 140 output tokens ต่อ request @@ -120,6 +130,8 @@ OpenCode Go มีขีดจำกัดดังต่อไปนี้: | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | [model id](/docs/config/#models) ใน OpenCode config ของคุณจะใช้รูปแบบ `opencode-go/<model-id>` ตัวอย่างเช่น สำหรับ Kimi K2.5 คุณจะใช้ `opencode-go/kimi-k2.5` ใน config ของคุณ diff --git a/packages/web/src/content/docs/th/modes.mdx b/packages/web/src/content/docs/th/modes.mdx index 2cbb05a26..6cca30998 100644 --- a/packages/web/src/content/docs/th/modes.mdx +++ b/packages/web/src/content/docs/th/modes.mdx @@ -225,18 +225,17 @@ Provide constructive feedback without making direct changes. นี่คือเครื่องมือทั้งหมดที่สามารถควบคุมได้ผ่านการกำหนดค่าโหมด -| เครื่องมือ | คำอธิบาย | -| ----------- | --------------------------- | -| `bash` | ดำเนินการคำสั่ง shell | -| `edit` | แก้ไขไฟล์ที่มีอยู่ | -| `write` | สร้างไฟล์ใหม่ | -| `read` | อ่านเนื้อหาไฟล์ | -| `grep` | ค้นหาเนื้อหาไฟล์ | -| `glob` | ค้นหาไฟล์ตามรูปแบบ | -| `list` | แสดงรายการเนื้อหาไดเร็กทอรี | -| `patch` | ใช้แพทช์กับไฟล์ | -| `todowrite` | จัดการรายการสิ่งที่ต้องทำ | -| `webfetch` | ดึงเนื้อหาเว็บ | +| เครื่องมือ | คำอธิบาย | +| ----------- | ------------------------- | +| `bash` | ดำเนินการคำสั่ง shell | +| `edit` | แก้ไขไฟล์ที่มีอยู่ | +| `write` | สร้างไฟล์ใหม่ | +| `read` | อ่านเนื้อหาไฟล์ | +| `grep` | ค้นหาเนื้อหาไฟล์ | +| `glob` | ค้นหาไฟล์ตามรูปแบบ | +| `patch` | ใช้แพทช์กับไฟล์ | +| `todowrite` | จัดการรายการสิ่งที่ต้องทำ | +| `webfetch` | ดึงเนื้อหาเว็บ | --- diff --git a/packages/web/src/content/docs/th/permissions.mdx b/packages/web/src/content/docs/th/permissions.mdx index adf381dee..5fed61615 100644 --- a/packages/web/src/content/docs/th/permissions.mdx +++ b/packages/web/src/content/docs/th/permissions.mdx @@ -88,7 +88,7 @@ OpenCode ใช้การกำหนดค่า `permission` เพื่อ ### ไดเรกทอรีภายนอก -ใช้ `external_directory` เพื่ออนุญาตการเรียกใช้เครื่องมือที่สัมผัสเส้นทางนอกไดเร็กทอรีการทำงานที่ OpenCode เริ่มทำงาน สิ่งนี้ใช้ได้กับเครื่องมือใดๆ ที่ใช้เส้นทางเป็นอินพุต (เช่น `read`, `edit`, `list`, `glob`, `grep` และคำสั่ง `bash` จำนวนมาก) +ใช้ `external_directory` เพื่ออนุญาตการเรียกใช้เครื่องมือที่สัมผัสเส้นทางนอกไดเร็กทอรีการทำงานที่ OpenCode เริ่มทำงาน สิ่งนี้ใช้ได้กับเครื่องมือใดๆ ที่ใช้เส้นทางเป็นอินพุต (เช่น `read`, `edit`, `glob`, `grep` และคำสั่ง `bash` จำนวนมาก) การขยายบ้าน (เช่น `~/...`) ส่งผลต่อวิธีการเขียนรูปแบบเท่านั้น ไม่ได้ทำให้เส้นทางภายนอกเป็นส่วนหนึ่งของพื้นที่ทำงานปัจจุบัน ดังนั้นเส้นทางภายนอกไดเรกทอรีการทำงานยังต้องได้รับอนุญาตผ่าน `external_directory` @@ -133,7 +133,6 @@ OpenCode ใช้การกำหนดค่า `permission` เพื่อ - `edit` — การแก้ไขไฟล์ทั้งหมด (ครอบคลุมถึง `edit`, `write`, `patch`, `multiedit`) - `glob` — ไฟล์ globbing (ตรงกับรูปแบบ glob) - `grep` — การค้นหาเนื้อหา (ตรงกับรูปแบบ regex) -- `list` — แสดงรายการไฟล์ในไดเร็กทอรี (ตรงกับเส้นทางไดเร็กทอรี) - `bash` — การรันคำสั่ง shell (ตรงกับคำสั่งที่แยกวิเคราะห์เช่น `git status --porcelain`) - `task` — การเปิดตัวตัวแทนย่อย (ตรงกับประเภทตัวแทนย่อย) - `skill` — กำลังโหลดทักษะ (ตรงกับชื่อทักษะ) diff --git a/packages/web/src/content/docs/th/tools.mdx b/packages/web/src/content/docs/th/tools.mdx index 17dbd9fdb..0ead63846 100644 --- a/packages/web/src/content/docs/th/tools.mdx +++ b/packages/web/src/content/docs/th/tools.mdx @@ -151,23 +151,6 @@ description: จัดการเครื่องมือที่ LLM ส� --- -### list - -แสดงรายการไฟล์และไดเร็กทอรีในพาธที่กำหนด - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -เครื่องมือนี้แสดงรายการเนื้อหาไดเร็กทอรี ยอมรับรูปแบบ glob เพื่อกรองผลลัพธ์ - ---- - ### lsp (ขั้นทดลอง) โต้ตอบกับเซิร์ฟเวอร์ LSP ที่กำหนดค่าของคุณเพื่อรับฟีเจอร์อัจฉริยะด้านโค้ด เช่น คำจำกัดความ การอ้างอิง ข้อมูลโฮเวอร์ และลำดับชั้นการโทร @@ -341,7 +324,7 @@ OPENCODE_ENABLE_EXA=1 opencode ## ภายใน -ภายใน เครื่องมือต่างๆ เช่น `grep`, `glob` และ `list` ใช้ [ripgrep](https://github.com/BurntSushi/ripgrep) ภายใต้ประทุน ตามค่าเริ่มต้น ripgrep เคารพรูปแบบ `.gitignore` ซึ่งหมายความว่าไฟล์และไดเร็กทอรีที่อยู่ใน `.gitignore` ของคุณจะถูกแยกออกจากการค้นหาและรายการ +ภายใน เครื่องมือต่างๆ เช่น `grep` และ `glob` ใช้ [ripgrep](https://github.com/BurntSushi/ripgrep) ภายใต้ประทุน ตามค่าเริ่มต้น ripgrep เคารพรูปแบบ `.gitignore` ซึ่งหมายความว่าไฟล์และไดเร็กทอรีที่อยู่ใน `.gitignore` ของคุณจะถูกแยกออกจากการค้นหาและรายการ --- diff --git a/packages/web/src/content/docs/th/zen.mdx b/packages/web/src/content/docs/th/zen.mdx index cf272576c..2c82c1e07 100644 --- a/packages/web/src/content/docs/th/zen.mdx +++ b/packages/web/src/content/docs/th/zen.mdx @@ -82,6 +82,8 @@ OpenCode Zen ทำงานเหมือน provider อื่น ๆ ใน | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -90,7 +92,6 @@ OpenCode Zen ทำงานเหมือน provider อื่น ๆ ใน | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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) ใน OpenCode config ของคุณใช้รูปแบบ `opencode/<model-id>` ตัวอย่างเช่น สำหรับ GPT 5.3 Codex คุณจะใช้ `opencode/gpt-5.3-codex` ใน config ของคุณ @@ -116,7 +117,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -164,7 +166,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล - MiMo V2 Pro Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล - MiMo V2 Omni Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล -- Qwen3.6 Plus Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล - Nemotron 3 Super Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล - Big Pickle เป็น stealth model ที่ใช้งานฟรีบน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล @@ -210,8 +211,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: ระหว่างช่วงที่เปิดให้ใช้ฟรี ข้อมูลที่เก็บรวบรวมอาจถูกนำไปใช้เพื่อปรับปรุงโมเดล - MiMo V2 Pro Free: ระหว่างช่วงที่เปิดให้ใช้ฟรี ข้อมูลที่เก็บรวบรวมอาจถูกนำไปใช้เพื่อปรับปรุงโมเดล - MiMo V2 Omni Free: ระหว่างช่วงที่เปิดให้ใช้ฟรี ข้อมูลที่เก็บรวบรวมอาจถูกนำไปใช้เพื่อปรับปรุงโมเดล -- Qwen3.6 Plus Free: ระหว่างช่วงที่เปิดให้ใช้ฟรี ข้อมูลที่เก็บรวบรวมอาจถูกนำไปใช้เพื่อปรับปรุงโมเดล -- Nemotron 3 Super Free: ระหว่างช่วงที่เปิดให้ใช้ฟรี ข้อมูลที่เก็บรวบรวมอาจถูกนำไปใช้เพื่อปรับปรุงโมเดล +- Nemotron 3 Super Free (endpoint ฟรีของ NVIDIA): ให้บริการภายใต้ [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) ใช้สำหรับการทดลองเท่านั้น ไม่เหมาะสำหรับ production หรือข้อมูลที่อ่อนไหว NVIDIA จะบันทึก prompt และ output เพื่อนำไปปรับปรุงโมเดลและบริการของตน โปรดอย่าส่งข้อมูลส่วนบุคคลหรือข้อมูลลับ. - OpenAI APIs: คำขอจะถูกเก็บไว้เป็นเวลา 30 วันตาม [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data). - Anthropic APIs: คำขอจะถูกเก็บไว้เป็นเวลา 30 วันตาม [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage). diff --git a/packages/web/src/content/docs/tools.mdx b/packages/web/src/content/docs/tools.mdx index abd486aeb..f05e980b8 100644 --- a/packages/web/src/content/docs/tools.mdx +++ b/packages/web/src/content/docs/tools.mdx @@ -151,23 +151,6 @@ Search for files using glob patterns like `**/*.js` or `src/**/*.ts`. Returns ma --- -### list - -List files and directories in a given path. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -This tool lists directory contents. It accepts glob patterns to filter results. - ---- - ### lsp (experimental) Interact with your configured LSP servers to get code intelligence features like definitions, references, hover info, and call hierarchy. @@ -345,7 +328,7 @@ MCP (Model Context Protocol) servers allow you to integrate external tools and s ## Internals -Internally, tools like `grep`, `glob`, and `list` use [ripgrep](https://github.com/BurntSushi/ripgrep) under the hood. By default, ripgrep respects `.gitignore` patterns, which means files and directories listed in your `.gitignore` will be excluded from searches and listings. +Internally, tools like `grep` and `glob` use [ripgrep](https://github.com/BurntSushi/ripgrep) under the hood. By default, ripgrep respects `.gitignore` patterns, which means files and directories listed in your `.gitignore` will be excluded from searches and listings. --- diff --git a/packages/web/src/content/docs/tr/go.mdx b/packages/web/src/content/docs/tr/go.mdx index b7b24b8de..b085f6d06 100644 --- a/packages/web/src/content/docs/tr/go.mdx +++ b/packages/web/src/content/docs/tr/go.mdx @@ -59,6 +59,8 @@ Mevcut model listesi şunları içerir: - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** Test edip yenilerini ekledikçe model listesi değişebilir. @@ -77,17 +79,25 @@ Limitler dolar değeri üzerinden belirlenmiştir. Bu, gerçek istek sayınızı Aşağıdaki tablo, tipik Go kullanım modellerine dayalı tahmini bir istek sayısı sunmaktadır: -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| ------------------ | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| 5 saatte bir istek | 880 | 1.150 | 1.850 | 1.290 | 2.150 | 14.000 | 20.000 | -| haftalık istek | 2.150 | 2.880 | 4.630 | 3.225 | 5.450 | 35.000 | 50.000 | -| aylık istek | 4.300 | 5.750 | 9.250 | 6.450 | 10.900 | 70.000 | 100.000 | +| Model | 5 saatte bir istek | haftalık istek | aylık istek | +| ------------ | ------------------ | -------------- | ----------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | Tahminler, gözlemlenen ortalama istek modellerine dayanmaktadır: - GLM-5/5.1 — İstek başına 700 girdi, 52.000 önbelleğe alınmış, 150 çıktı token'ı - Kimi K2.5 — İstek başına 870 girdi, 55.000 önbelleğe alınmış, 200 çıktı token'ı - MiniMax M2.7/M2.5 — İstek başına 300 girdi, 55.000 önbelleğe alınmış, 125 çıktı token'ı +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — İstek başına 350 girdi, 41.000 önbelleğe alınmış, 250 çıktı token'ı - MiMo-V2-Omni — İstek başına 1000 girdi, 60.000 önbelleğe alınmış, 140 çıktı token'ı @@ -120,6 +130,8 @@ Go modellerine aşağıdaki API uç noktaları aracılığıyla da erişebilirsi | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | OpenCode yapılandırmanızdaki [model id](/docs/config/#models) formatı `opencode-go/<model-id>` şeklindedir. Örneğin, Kimi K2.5 için yapılandırmanızda `opencode-go/kimi-k2.5` kullanmalısınız. diff --git a/packages/web/src/content/docs/tr/modes.mdx b/packages/web/src/content/docs/tr/modes.mdx index 09538e788..8f722ec22 100644 --- a/packages/web/src/content/docs/tr/modes.mdx +++ b/packages/web/src/content/docs/tr/modes.mdx @@ -233,7 +233,6 @@ Hiçbir araç belirtilmezse tüm araçlar varsayılan olarak etkindir. | `read` | Dosya içeriğini oku | | `grep` | Dosya içeriğini ara | | `glob` | Dosyaları desene göre bul | -| `list` | Dizinin içeriğini listele | | `patch` | Dosyalara yama uygula | | `todowrite` | Yapılacaklar listelerini yönet | | `webfetch` | Web içeriğini getir | diff --git a/packages/web/src/content/docs/tr/permissions.mdx b/packages/web/src/content/docs/tr/permissions.mdx index f608ce7e0..976ee0a7f 100644 --- a/packages/web/src/content/docs/tr/permissions.mdx +++ b/packages/web/src/content/docs/tr/permissions.mdx @@ -88,7 +88,7 @@ Ana dizininize referans vermek için bir modelin başlangıcında `~` veya `$HOM ### Harici Dizinler -opencode'un başlatıldığı çalışma dizini dışındaki yollara dokunan araç çağrılarına izin vermek için `external_directory` kullanın. Bu, girdi olarak bir yolu alan tüm araçlar için geçerlidir (örneğin `read`, `edit`, `list`, `glob`, `grep` ve birçok `bash` komutu). +opencode'un başlatıldığı çalışma dizini dışındaki yollara dokunan araç çağrılarına izin vermek için `external_directory` kullanın. Bu, girdi olarak bir yolu alan tüm araçlar için geçerlidir (örneğin `read`, `edit`, `glob`, `grep` ve birçok `bash` komutu). Ana sayfa genişletmesi (`~/...` gibi) yalnızca bir kalıbın nasıl yazıldığını etkiler. Geçerli çalışma alanının harici bir yolunu oluşturmaz, dolayısıyla çalışma dizini dışındaki yollara yine de `external_directory` aracılığıyla izin verilmesi gerekir. @@ -133,7 +133,6 @@ opencode izinleri araç adına ve birkaç güvenlik önlemine göre anahtarlanı - `edit` — tüm dosya değişiklikleri (`edit`, `write`, `patch`, `multiedit`'yi kapsar) - `glob` — dosya genellemesi (glob düzeniyle eşleşir) - `grep` — içerik arama (regex modeliyle eşleşir) -- `list` — bir dizideki dosyaları listeleme (dizin yoluyla eşleşir) - `bash` — kabuk komutlarını çalıştırma (`git status --porcelain` gibi ayrıştırılmış komutlarla eşleşir) - `task` — alt agent'ların başlatılması (alt agent türüyle eşleşir) - `skill` — bir skill yükleniyor (skill adıyla eşleşir) diff --git a/packages/web/src/content/docs/tr/tools.mdx b/packages/web/src/content/docs/tr/tools.mdx index e65ffec3a..2beb19009 100644 --- a/packages/web/src/content/docs/tr/tools.mdx +++ b/packages/web/src/content/docs/tr/tools.mdx @@ -151,23 +151,6 @@ Desen eşleştirme ile dosya bulur. --- -### list - -Verilen yoldaki dosya ve dizinleri listeler. - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -Bu araç dizin içeriğini listeler. Sonuçları filtrelemek için glob desenlerini kabul eder. - ---- - ### lsp (deneysel) Tanım, referans, hover bilgisi ve çağrılar hiyerarşisi gibi kod zekası özellikleri için yapılandırdığınız LSP sunucularıyla etkileşir. @@ -341,7 +324,7 @@ MCP sunucularını yapılandırma için [daha fazla bilgi alın](/docs/mcp-serve ## Dahili detaylar -Dahilde `grep`, `glob` ve `list` gibi araçlar [ripgrep](https://github.com/BurntSushi/ripgrep) kullanır. Varsayılan olarak ripgrep `.gitignore` desenlerine uyar; yani `.gitignore` içindeki dosya ve dizinler arama ve listeleme sonucuna dahil edilmez. +Dahilde `grep` ve `glob` gibi araçlar [ripgrep](https://github.com/BurntSushi/ripgrep) kullanır. Varsayılan olarak ripgrep `.gitignore` desenlerine uyar; yani `.gitignore` içindeki dosya ve dizinler arama ve listeleme sonucuna dahil edilmez. --- diff --git a/packages/web/src/content/docs/tr/zen.mdx b/packages/web/src/content/docs/tr/zen.mdx index 89276dd4c..30aa2bb9d 100644 --- a/packages/web/src/content/docs/tr/zen.mdx +++ b/packages/web/src/content/docs/tr/zen.mdx @@ -80,6 +80,8 @@ Modellerimize aşağıdaki API uç noktaları aracılığıyla da erişebilirsin | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ Modellerimize aşağıdaki API uç noktaları aracılığıyla da erişebilirsin | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | OpenCode yapılandırmanızdaki [model id](/docs/config/#models) `opencode/<model-id>` biçimini kullanır. Örneğin, GPT 5.3 Codex için yapılandırmanızda `opencode/gpt-5.3-codex` kullanırsınız. @@ -114,7 +115,8 @@ Kullandıkça öde modelini destekliyoruz. Aşağıda **1M token başına** fiya | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ Kredi kartı ücretleri maliyet üzerinden yansıtılır (%4.4 + işlem başına - MiniMax M2.5 Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. - MiMo V2 Pro Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. - MiMo V2 Omni Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. -- Qwen3.6 Plus Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. - Nemotron 3 Super Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. - Big Pickle, sınırlı bir süre için OpenCode'da ücretsiz olan gizli bir modeldir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor. @@ -208,8 +209,7 @@ Tüm modellerimiz US'de barındırılıyor. Sağlayıcılarımız zero-retention - MiniMax M2.5 Free: Ücretsiz döneminde toplanan veriler modeli iyileştirmek için kullanılabilir. - MiMo V2 Pro Free: Ücretsiz döneminde toplanan veriler modeli iyileştirmek için kullanılabilir. - MiMo V2 Omni Free: Ücretsiz döneminde toplanan veriler modeli iyileştirmek için kullanılabilir. -- Qwen3.6 Plus Free: Ücretsiz döneminde toplanan veriler modeli iyileştirmek için kullanılabilir. -- Nemotron 3 Super Free: Ücretsiz döneminde toplanan veriler modeli iyileştirmek için kullanılabilir. +- Nemotron 3 Super Free (ücretsiz NVIDIA uç noktaları): [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) kapsamında sunulur. Yalnızca deneme amaçlıdır; üretim veya hassas veriler için uygun değildir. NVIDIA, modellerini ve hizmetlerini geliştirmek için promptları ve çıktıları kaydeder. Kişisel veya gizli veri göndermeyin. - OpenAI APIs: İstekler [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) uyarınca 30 gün boyunca saklanır. - Anthropic APIs: İstekler [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) uyarınca 30 gün boyunca saklanır. diff --git a/packages/web/src/content/docs/zen.mdx b/packages/web/src/content/docs/zen.mdx index f16ec6f71..cf634a9c9 100644 --- a/packages/web/src/content/docs/zen.mdx +++ b/packages/web/src/content/docs/zen.mdx @@ -89,13 +89,14 @@ You can also access our models through the following API endpoints. | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5 | glm-5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | Kimi K2.5 | kimi-k2.5 | `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` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | The [model id](/docs/config/#models) in your OpenCode config @@ -121,14 +122,14 @@ We support a pay-as-you-go model. Below are the prices **per 1M tokens**. | Model | Input | Output | Cached Read | Cached Write | | --------------------------------- | ------ | ------- | ----------- | ------------ | | Big Pickle | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | | GLM 5.1 | $1.40 | $4.40 | $0.26 | - | | GLM 5 | $1.00 | $3.20 | $0.20 | - | | Kimi K2.5 | $0.60 | $3.00 | $0.10 | - | -| Qwen3 Coder 480B | $0.45 | $1.50 | - | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Claude Opus 4.6 | $5.00 | $25.00 | $0.50 | $6.25 | | Claude Opus 4.5 | $5.00 | $25.00 | $0.50 | $6.25 | | Claude Opus 4.1 | $15.00 | $75.00 | $1.50 | $18.75 | @@ -167,7 +168,6 @@ Credit card fees are passed along at cost (4.4% + $0.30 per transaction); we don The free models: - MiniMax M2.5 Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model. -- Qwen3.6 Plus Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model. - Nemotron 3 Super Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model. - Big Pickle is a stealth model that's free on OpenCode for a limited time. The team is using this time to collect feedback and improve the model. @@ -214,8 +214,7 @@ All our models are hosted in the US. Our providers follow a zero-retention polic - Big Pickle: During its free period, collected data may be used to improve the model. - MiniMax M2.5 Free: During its free period, collected data may be used to improve the model. -- Qwen3.6 Plus Free: During its free period, collected data may be used to improve the model. -- Nemotron 3 Super Free: During its free period, collected data may be used to improve the model. +- Nemotron 3 Super Free (NVIDIA free endpoints): Provided under the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Trial use only — not for production or sensitive data. Prompts and outputs are logged by NVIDIA to improve its models and services. Do not submit personal or confidential data. - 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). diff --git a/packages/web/src/content/docs/zh-cn/go.mdx b/packages/web/src/content/docs/zh-cn/go.mdx index 7b1a3b77f..df74f35ec 100644 --- a/packages/web/src/content/docs/zh-cn/go.mdx +++ b/packages/web/src/content/docs/zh-cn/go.mdx @@ -59,6 +59,8 @@ OpenCode Go 的工作方式与 OpenCode 中的其他提供商一样。 - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** 随着我们进行测试和添加新模型，该列表可能会发生变化。 @@ -77,11 +79,17 @@ OpenCode Go 包含以下限制： 下表提供了基于典型 Go 使用模式的预估请求数： -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| --------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| 每 5 小时请求数 | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| 每周请求数 | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| 每月请求数 | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | 每 5 小时请求数 | 每周请求数 | 每月请求数 | +| ------------ | --------------- | ---------- | ---------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | 预估值基于观察到的平均请求模式： @@ -90,6 +98,8 @@ OpenCode Go 包含以下限制： - MiMo-V2-Pro — 每次请求 350 个输入 token，41,000 个缓存 token，250 个输出 token - MiMo-V2-Omni — 每次请求 1000 个输入 token，60,000 个缓存 token，140 个输出 token - MiniMax M2.7/M2.5 — 每次请求 300 个输入 token，55,000 个缓存 token，125 个输出 token +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request 你可以在 **<a href={console}>控制台</a>** 中跟踪你当前的使用情况。 @@ -120,6 +130,8 @@ OpenCode Go 包含以下限制： | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | 你 OpenCode 配置中的 [模型 ID](/docs/config/#models) 使用 `opencode-go/<model-id>` 格式。例如，对于 Kimi K2.5，你将在配置中使用 `opencode-go/kimi-k2.5`。 diff --git a/packages/web/src/content/docs/zh-cn/modes.mdx b/packages/web/src/content/docs/zh-cn/modes.mdx index 4570c801c..256cffe81 100644 --- a/packages/web/src/content/docs/zh-cn/modes.mdx +++ b/packages/web/src/content/docs/zh-cn/modes.mdx @@ -230,7 +230,6 @@ Markdown 文件名即为模式名称（例如，`review.md` 创建一个名为 ` | `read` | 读取文件内容 | | `grep` | 搜索文件内容 | | `glob` | 按模式查找文件 | -| `list` | 列出目录内容 | | `patch` | 对文件应用补丁 | | `todowrite` | 管理待办事项列表 | | `webfetch` | 获取网页内容 | diff --git a/packages/web/src/content/docs/zh-cn/permissions.mdx b/packages/web/src/content/docs/zh-cn/permissions.mdx index 24104e2a2..f928554f2 100644 --- a/packages/web/src/content/docs/zh-cn/permissions.mdx +++ b/packages/web/src/content/docs/zh-cn/permissions.mdx @@ -88,7 +88,7 @@ OpenCode 使用 `permission` 配置来决定某个操作是否应自动运行、 ### 外部目录 -使用 `external_directory` 允许工具调用访问 OpenCode 启动时工作目录之外的路径。这适用于任何接受路径作为输入的工具（例如 `read`、`edit`、`list`、`glob`、`grep` 以及许多 `bash` 命令）。 +使用 `external_directory` 允许工具调用访问 OpenCode 启动时工作目录之外的路径。这适用于任何接受路径作为输入的工具（例如 `read`、`edit`、`glob`、`grep` 以及许多 `bash` 命令）。 主目录展开（如 `~/...`）仅影响模式的书写方式。它不会将外部路径纳入当前工作空间，因此工作目录之外的路径仍然必须通过 `external_directory` 来允许。 @@ -133,7 +133,6 @@ OpenCode 的权限以工具名称为键，外加几个安全防护项： - `edit` — 所有文件修改（涵盖 `edit`、`write`、`patch`、`multiedit`） - `glob` — 文件通配（匹配通配模式） - `grep` — 内容搜索（匹配正则表达式模式） -- `list` — 列出目录中的文件（匹配目录路径） - `bash` — 运行 shell 命令（匹配解析后的命令，如 `git status --porcelain`） - `task` — 启动子代理（匹配子代理类型） - `skill` — 加载技能（匹配技能名称） diff --git a/packages/web/src/content/docs/zh-cn/tools.mdx b/packages/web/src/content/docs/zh-cn/tools.mdx index 4f68a9cf3..4c6037059 100644 --- a/packages/web/src/content/docs/zh-cn/tools.mdx +++ b/packages/web/src/content/docs/zh-cn/tools.mdx @@ -151,23 +151,6 @@ description: 管理 LLM 可以使用的工具。 --- -### list - -列出指定路径下的文件和目录。 - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -该工具用于列出目录内容。它接受 glob 模式来过滤结果。 - ---- - ### lsp（实验性） 与已配置的 LSP 服务器交互，获取代码智能功能，如定义跳转、引用查找、悬停信息和调用层次结构。 @@ -341,7 +324,7 @@ MCP（Model Context Protocol）服务器允许您集成外部工具和服务，� ## 内部机制 -在内部，`grep`、`glob` 和 `list` 等工具底层使用 [ripgrep](https://github.com/BurntSushi/ripgrep)。默认情况下，ripgrep 遵循 `.gitignore` 中的模式，这意味着 `.gitignore` 中列出的文件和目录将被排除在搜索和列表结果之外。 +在内部，`grep` 和 `glob` 等工具底层使用 [ripgrep](https://github.com/BurntSushi/ripgrep)。默认情况下，ripgrep 遵循 `.gitignore` 中的模式，这意味着 `.gitignore` 中列出的文件和目录将被排除在搜索和列表结果之外。 --- diff --git a/packages/web/src/content/docs/zh-cn/zen.mdx b/packages/web/src/content/docs/zh-cn/zen.mdx index 5df360954..cd281a4b0 100644 --- a/packages/web/src/content/docs/zh-cn/zen.mdx +++ b/packages/web/src/content/docs/zh-cn/zen.mdx @@ -80,6 +80,8 @@ OpenCode Zen 的工作方式与 OpenCode 中的任何其他提供商相同。 | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -88,7 +90,6 @@ OpenCode Zen 的工作方式与 OpenCode 中的任何其他提供商相同。 | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | 在你的 OpenCode 配置中，[模型 ID](/docs/config/#models) 使用 `opencode/<model-id>` 格式。例如，对于 GPT 5.3 Codex，你需要在配置中使用 `opencode/gpt-5.3-codex`。 @@ -114,7 +115,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -162,7 +164,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 - MiMo V2 Pro Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 - MiMo V2 Omni Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 -- Qwen3.6 Plus Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 - Nemotron 3 Super Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 - Big Pickle 是一个隐身模型，目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。 @@ -208,8 +209,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free：在免费期间，收集的数据可能会被用于改进模型。 - MiMo V2 Pro Free：在免费期间，收集的数据可能会被用于改进模型。 - MiMo V2 Omni Free：在免费期间，收集的数据可能会被用于改进模型。 -- Qwen3.6 Plus Free：在免费期间，收集的数据可能会被用于改进模型。 -- Nemotron 3 Super Free：在免费期间，收集的数据可能会被用于改进模型。 +- Nemotron 3 Super Free（NVIDIA 免费端点）：根据 [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) 提供。仅供试用，不适用于生产环境或敏感数据。NVIDIA 会记录提示词和输出内容，以改进其模型和服务。请勿提交个人或机密数据。 - OpenAI APIs：请求会根据 [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) 保留 30 天。 - Anthropic APIs：请求会根据 [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) 保留 30 天。 diff --git a/packages/web/src/content/docs/zh-tw/go.mdx b/packages/web/src/content/docs/zh-tw/go.mdx index b6b76afff..9c12710a0 100644 --- a/packages/web/src/content/docs/zh-tw/go.mdx +++ b/packages/web/src/content/docs/zh-tw/go.mdx @@ -59,6 +59,8 @@ OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。 - **MiMo-V2-Pro** - **MiMo-V2-Omni** - **MiniMax M2.5** +- **Qwen3.5 Plus** +- **Qwen3.6 Plus** - **MiniMax M2.7** 隨著我們測試並加入新模型，模型清單可能會有所變動。 @@ -77,17 +79,25 @@ OpenCode Go 包含以下限制： 下表提供了基於典型 Go 使用模式的預估請求次數： -| | GLM-5.1 | GLM-5 | Kimi K2.5 | MiMo-V2-Pro | MiMo-V2-Omni | MiniMax M2.7 | MiniMax M2.5 | -| --------------- | ------- | ----- | --------- | ----------- | ------------ | ------------ | ------------ | -| 每 5 小時請求數 | 880 | 1,150 | 1,850 | 1,290 | 2,150 | 14,000 | 20,000 | -| 每週請求數 | 2,150 | 2,880 | 4,630 | 3,225 | 5,450 | 35,000 | 50,000 | -| 每月請求數 | 4,300 | 5,750 | 9,250 | 6,450 | 10,900 | 70,000 | 100,000 | +| Model | 每 5 小時請求數 | 每週請求數 | 每月請求數 | +| ------------ | --------------- | ---------- | ---------- | +| GLM-5.1 | 880 | 2,150 | 4,300 | +| GLM-5 | 1,150 | 2,880 | 5,750 | +| Kimi K2.5 | 1,850 | 4,630 | 9,250 | +| MiMo-V2-Pro | 1,290 | 3,225 | 6,450 | +| MiMo-V2-Omni | 2,150 | 5,450 | 10,900 | +| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | +| MiniMax M2.7 | 3,400 | 8,500 | 17,000 | +| MiniMax M2.5 | 6,300 | 15,900 | 31,800 | +| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | 預估值是基於觀察到的平均請求模式： - GLM-5/5.1 — 每次請求 700 個輸入 token、52,000 個快取 token、150 個輸出 token - Kimi K2.5 — 每次請求 870 個輸入 token、55,000 個快取 token、200 個輸出 token - MiniMax M2.7/M2.5 — 每次請求 300 個輸入 token、55,000 個快取 token、125 個輸出 token +- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request +- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request - MiMo-V2-Pro — 每次請求 350 個輸入 token、41,000 個快取 token、250 個輸出 token - MiMo-V2-Omni — 每次請求 1000 個輸入 token、60,000 個快取 token、140 個輸出 token @@ -120,6 +130,8 @@ OpenCode Go 包含以下限制： | MiMo-V2-Omni | mimo-v2-omni | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/alibaba` | 您的 OpenCode 設定中的 [model id](/docs/config/#models) 使用 `opencode-go/<model-id>` 格式。例如，Kimi K2.5 在設定中應使用 `opencode-go/kimi-k2.5`。 diff --git a/packages/web/src/content/docs/zh-tw/modes.mdx b/packages/web/src/content/docs/zh-tw/modes.mdx index c97aeb61b..625b4d021 100644 --- a/packages/web/src/content/docs/zh-tw/modes.mdx +++ b/packages/web/src/content/docs/zh-tw/modes.mdx @@ -230,7 +230,6 @@ Markdown 檔案名稱即為模式名稱（例如，`review.md` 建立一個名� | `read` | 讀取檔案內容 | | `grep` | 搜尋檔案內容 | | `glob` | 按模式尋找檔案 | -| `list` | 列出目錄內容 | | `patch` | 對檔案套用補丁 | | `todowrite` | 管理待辦事項清單 | | `webfetch` | 擷取網頁內容 | diff --git a/packages/web/src/content/docs/zh-tw/permissions.mdx b/packages/web/src/content/docs/zh-tw/permissions.mdx index 05b522e9c..bacd87c1e 100644 --- a/packages/web/src/content/docs/zh-tw/permissions.mdx +++ b/packages/web/src/content/docs/zh-tw/permissions.mdx @@ -88,7 +88,7 @@ OpenCode 使用 `permission` 設定來決定某個操作是否應自動執行、 ### 外部目錄 -使用 `external_directory` 允許工具呼叫存取 OpenCode 啟動時工作目錄之外的路徑。這適用於任何接受路徑作為輸入的工具（例如 `read`、`edit`、`list`、`glob`、`grep` 以及許多 `bash` 指令）。 +使用 `external_directory` 允許工具呼叫存取 OpenCode 啟動時工作目錄之外的路徑。這適用於任何接受路徑作為輸入的工具（例如 `read`、`edit`、`glob`、`grep` 以及許多 `bash` 指令）。 主目錄展開（如 `~/...`）僅影響模式的書寫方式。它不會將外部路徑納入當前工作空間，因此工作目錄之外的路徑仍然必須透過 `external_directory` 來允許。 @@ -133,7 +133,6 @@ OpenCode 的權限以工具名稱為鍵，外加幾個安全防護項： - `edit` — 所有檔案修改（涵蓋 `edit`、`write`、`patch`、`multiedit`） - `glob` — 檔案萬用字元比對（比對萬用字元模式） - `grep` — 內容搜尋（比對正規表示式模式） -- `list` — 列出目錄中的檔案（比對目錄路徑） - `bash` — 執行 shell 指令（比對解析後的指令，如 `git status --porcelain`） - `task` — 啟動子代理（比對子代理類型） - `skill` — 載入技能（比對技能名稱） diff --git a/packages/web/src/content/docs/zh-tw/tools.mdx b/packages/web/src/content/docs/zh-tw/tools.mdx index 80e27ea0c..6ce68d9fb 100644 --- a/packages/web/src/content/docs/zh-tw/tools.mdx +++ b/packages/web/src/content/docs/zh-tw/tools.mdx @@ -151,23 +151,6 @@ description: 管理 LLM 可以使用的工具。 --- -### list - -列出指定路徑下的檔案和目錄。 - -```json title="opencode.json" {4} -{ - "$schema": "https://opencode.ai/config.json", - "permission": { - "list": "allow" - } -} -``` - -該工具用於列出目錄內容。它接受 glob 模式來過濾結果。 - ---- - ### lsp（實驗性） 與已設定的 LSP 伺服器互動，取得程式碼智慧功能，如定義跳轉、參考查找、懸停資訊和呼叫階層結構。 @@ -341,7 +324,7 @@ MCP（Model Context Protocol）伺服器允許您整合外部工具和服務，� ## 內部機制 -在內部，`grep`、`glob` 和 `list` 等工具底層使用 [ripgrep](https://github.com/BurntSushi/ripgrep)。預設情況下，ripgrep 遵循 `.gitignore` 中的模式，這意味著 `.gitignore` 中列出的檔案和目錄將被排除在搜尋和列表結果之外。 +在內部，`grep` 和 `glob` 等工具底層使用 [ripgrep](https://github.com/BurntSushi/ripgrep)。預設情況下，ripgrep 遵循 `.gitignore` 中的模式，這意味著 `.gitignore` 中列出的檔案和目錄將被排除在搜尋和列表結果之外。 --- diff --git a/packages/web/src/content/docs/zh-tw/zen.mdx b/packages/web/src/content/docs/zh-tw/zen.mdx index 1b2beb2c1..bdc3c07db 100644 --- a/packages/web/src/content/docs/zh-tw/zen.mdx +++ b/packages/web/src/content/docs/zh-tw/zen.mdx @@ -84,6 +84,8 @@ OpenCode Zen 的運作方式和 OpenCode 中的其他供應商一樣。 | Claude Haiku 3.5 | claude-3-5-haiku | `https://opencode.ai/zen/v1/messages` | `@ai-sdk/anthropic` | | Gemini 3.1 Pro | gemini-3.1-pro | `https://opencode.ai/zen/v1/models/gemini-3.1-pro` | `@ai-sdk/google` | | Gemini 3 Flash | gemini-3-flash | `https://opencode.ai/zen/v1/models/gemini-3-flash` | `@ai-sdk/google` | +| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | +| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/alibaba` | | MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiniMax M2.5 Free | minimax-m2.5-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | GLM 5.1 | glm-5.1 | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | @@ -92,7 +94,6 @@ OpenCode Zen 的運作方式和 OpenCode 中的其他供應商一樣。 | Big Pickle | big-pickle | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Pro Free | mimo-v2-pro-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | | MiMo V2 Omni Free | mimo-v2-omni-free | `https://opencode.ai/zen/v1/chat/completions` | `@ai-sdk/openai-compatible` | -| Qwen3.6 Plus Free | qwen3.6-plus-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` | OpenCode 設定中的 [模型 ID](/docs/config/#models) 會使用 `opencode/<model-id>` @@ -119,7 +120,8 @@ https://opencode.ai/zen/v1/models | Big Pickle | Free | Free | Free | - | | MiMo V2 Pro Free | Free | Free | Free | - | | MiMo V2 Omni Free | Free | Free | Free | - | -| Qwen3.6 Plus Free | Free | Free | Free | - | +| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 | +| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 | | Nemotron 3 Super Free | Free | Free | Free | - | | MiniMax M2.5 Free | Free | Free | Free | - | | MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | @@ -168,7 +170,6 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。 - MiMo V2 Pro Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。 - MiMo V2 Omni Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。 -- Qwen3.6 Plus Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。 - Nemotron 3 Super Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。 - Big Pickle 是一個隱身模型，在 OpenCode 上限時免費提供。團隊正在利用這段時間收集回饋並改進模型。 @@ -215,8 +216,7 @@ https://opencode.ai/zen/v1/models - MiniMax M2.5 Free: 在免費期間，收集到的資料可能會用於改進模型。 - MiMo V2 Pro Free: 在免費期間，收集到的資料可能會用於改進模型。 - MiMo V2 Omni Free: 在免費期間，收集到的資料可能會用於改進模型。 -- Qwen3.6 Plus Free: 在免費期間，收集到的資料可能會用於改進模型。 -- Nemotron 3 Super Free: 在免費期間，收集到的資料可能會用於改進模型。 +- Nemotron 3 Super Free（NVIDIA 免費端點）：依據 [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) 提供。僅供試用，不適用於正式環境或敏感資料。NVIDIA 會記錄提示詞與輸出內容，以改進其模型與服務。請勿提交個人或機密資料。 - OpenAI APIs: 請求會依據 [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) 保留 30 天。 - Anthropic APIs: 請求會依據 [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) 保留 30 天。 |