Compare commits

..
9 Commits
Author SHA1 Message Date
Wolfsblvt ad29cbda62 docs: route new provider contributions before implementation (#6099)
* docs: route new provider contributions before implementation

* docs: point provider PR authors to integration guide
2026-10-03 00:05:27 +02:00
EmandWolfsblvt bc81b9f7e3 Change API button warning from credit to charge (#6049)
* Change API button warning from credit to charge

Updated the warning message for the test API button to indicate a charge instead of a credit. (you are using tokens to send the message, the provider is not giving you tokens because you sent a test)

* fix: clarify test message usage charges

---------

Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
2026-09-23 23:19:13 +02:00
EmandWolfsblvt 8901f28b01 Fix typos in property descriptions in char-data.js (#6054)
* Fix typos in property descriptions in char-data.js

Wether → Whether x6

* docs: correct character description property text

---------

Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
2026-09-23 23:16:59 +02:00
Em 9758a6cd5e Fix typo in readme regarding open source status (#6047)
Corrected 'open sourced' to 'open source' for consistency.
2026-09-23 23:08:52 +02:00
Em ca7330f1af Fix typo in comment for tool calls (#6052)
assistent → assistant
2026-09-23 23:08:18 +02:00
Em a1c7f19bac Fix typo in comment (#6053)
posible  →  possible
2026-09-23 23:07:45 +02:00
Wolfsblvt e9860754ad feat: add GPT-6 Sol and Luna, Opus 5.5, and Gemini 3.8 Flash (#6070) 2026-09-23 21:59:01 +02:00
Wolfsblvt 7c39941963 Merge pull request #6038 from SillyTavern/release
Sync npm publishing workflow to staging.
2026-09-14 21:16:18 +02:00
Wolfsblvt 06bde939fb Fix npm release publishing workflow (#6037)
Allow npm releases to be retried from an existing release tag through the trusted publishing workflow, and scope the `allow-directory` workaround to the publish command.
2026-09-14 21:01:34 +02:00
33 changed files with 119 additions and 58 deletions
+6
View File
@@ -1,5 +1,11 @@
<!-- Put X in the box below to confirm -->
<!--
Adding a new named external provider or service?
Read https://docs.sillytavern.app/for-contributors/provider-integrations/
before implementing or submitting it, and link the prior issue when the guide requires one.
-->
## Checklist:
- [ ] I have read the [Contribution guidelines](https://github.com/SillyTavern/SillyTavern/blob/release/CONTRIBUTING.md).
+1 -1
View File
@@ -29,7 +29,7 @@ Beginning in February 2023 as a fork of TavernAI 1.2.8, SillyTavern now has over
1. We aim to empower users with as much utility and control over their LLM prompts as possible. The steep learning curve is part of the fun!
2. We do not provide any online or hosted services, nor programmatically track any user data.
3. SillyTavern is a passion project brought to you by a dedicated community of LLM enthusiasts, and will always be free and open sourced.
3. SillyTavern is a passion project brought to you by a dedicated community of LLM enthusiasts, and will always be free and open source.
## Do I need a powerful PC to run SillyTavern?
+19 -2
View File
@@ -1,4 +1,4 @@
# This workflow will run tests using node and then publish a package to GitHub Packages when a release is created
# Publish to npm for a new release or explicitly retry an existing release tag.
# For more information see: https://docs.github.com/en/actions/publishing-packages/publishing-nodejs-packages
name: Node.js Package
@@ -6,6 +6,16 @@ name: Node.js Package
on:
release:
types: [created]
workflow_dispatch:
inputs:
tag:
description: Existing release tag to publish
required: true
type: string
env:
PUBLISH_TAG: ${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.event.release.tag_name }}
PUBLISH_REF: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/{0}', inputs.tag) || github.ref }}
permissions:
id-token: write # Required for OIDC
@@ -16,9 +26,13 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@f43a0e5ff2bd294095638e18286ca9a3d1956744 # v3
with:
ref: ${{ env.PUBLISH_REF }}
- uses: actions/setup-node@3235b876344d2a9aa001b8d1453c930bba69e610 # v3
with:
node-version: 24
- name: Verify release tag matches package version
run: test "$(node -p "require('./package.json').version")" = "$PUBLISH_TAG"
- run: npm ci --omit=dev --ignore-scripts
publish-npm:
@@ -26,9 +40,12 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@f43a0e5ff2bd294095638e18286ca9a3d1956744 # v3
with:
ref: ${{ env.PUBLISH_REF }}
- uses: actions/setup-node@3235b876344d2a9aa001b8d1453c930bba69e610 # v3
with:
node-version: 24
registry-url: https://registry.npmjs.org/
- run: npm ci --omit=dev --ignore-scripts
- run: npm publish
# https://github.com/npm/cli/issues/9755
- run: npm publish --allow-directory=all
+13 -2
View File
@@ -62,6 +62,16 @@ Write at least somewhat meaningful PR descriptions and commit messages. There's
- What did you do to achieve this?
- How would a reviewer test the change?
### Discuss new provider integrations before implementing them
Do not use a completed pull request as the first product discussion for a new named external provider or service.
- Model routers, resellers, rerouters, gateways, and aggregators should use **Custom (OpenAI-compatible)** and publish provider-owned setup instructions. Provider-specific convenience may be implemented as a third-party UI extension or server plugin.
- New first-party model, TTS, speech, web search, image, vectorization, embedding, reranking, and similar integrations are exceptional and should begin with a public issue and maintainer discussion before implementation.
- Existing-provider maintenance and provider-neutral improvements to generic compatibility remain welcome.
Read [Integrating an External Provider](https://docs.sillytavern.app/for-contributors/provider-integrations/) before starting implementation.
### We (likely) don't speak your language
English is the primary language of communication in this project. Please use only English when writing commit messages, PR descriptions, comments and other text. This does not apply to contributions to localization files.
@@ -81,5 +91,6 @@ We do not prohibit nor encourage the use of AI tools for coding assistance to he
## Further reading
1. [How to write UI extensions](https://docs.sillytavern.app/for-contributors/writing-extensions/)
2. [How to write server plugins](https://docs.sillytavern.app/for-contributors/server-plugins)
1. [How to integrate an external provider](https://docs.sillytavern.app/for-contributors/provider-integrations/)
2. [How to write UI extensions](https://docs.sillytavern.app/for-contributors/writing-extensions/)
3. [How to write server plugins](https://docs.sillytavern.app/for-contributors/server-plugins)
+14 -5
View File
@@ -3068,6 +3068,8 @@
<select id="model_openai_select">
<optgroup label="GPT-6">
<option value="gpt-6-astra">gpt-6-astra</option>
<option value="gpt-6-sol">gpt-6-sol</option>
<option value="gpt-6-luna">gpt-6-luna</option>
</optgroup>
<optgroup label="GPT-5.6">
<option value="gpt-5.6">gpt-5.6</option>
@@ -3098,12 +3100,12 @@
<optgroup label="GPT-5.1">
<option value="gpt-5.1">gpt-5.1</option>
<option value="gpt-5.1-2025-11-13">gpt-5.1-2025-11-13</option>
<option value="gpt-5.1-chat-latest">gpt-5.1-chat-latest</option>
<option value="gpt-5.1-chat-latest">gpt-5.1-chat-latest (deprecated)</option>
</optgroup>
<optgroup label="GPT-5">
<option value="gpt-5">gpt-5</option>
<option value="gpt-5-2025-08-07">gpt-5-2025-08-07 (deprecated)</option>
<option value="gpt-5-chat-latest">gpt-5-chat-latest</option>
<option value="gpt-5-chat-latest">gpt-5-chat-latest (deprecated)</option>
<option value="gpt-5-mini">gpt-5-mini</option>
<option value="gpt-5-mini-2025-08-07">gpt-5-mini-2025-08-07 (deprecated)</option>
<option value="gpt-5-nano">gpt-5-nano</option>
@@ -3154,8 +3156,8 @@
<option value="gpt-3.5-turbo-instruct">gpt-3.5-turbo-instruct (deprecated)</option>
</optgroup>
<optgroup label="Other">
<option value="babbage-002">babbage-002</option>
<option value="davinci-002">davinci-002</option>
<option value="babbage-002">babbage-002 (deprecated)</option>
<option value="davinci-002">davinci-002 (deprecated)</option>
</optgroup>
<optgroup id="openai_external_category" label="External">
</optgroup>
@@ -3188,6 +3190,7 @@
<optgroup label="Versions">
<option value="claude-fable-5-1">claude-fable-5-1</option>
<option value="claude-fable-5">claude-fable-5</option>
<option value="claude-opus-5-5">claude-opus-5-5</option>
<option value="claude-opus-5">claude-opus-5</option>
<option value="claude-sonnet-5">claude-sonnet-5</option>
<option value="claude-opus-4-8">claude-opus-4-8</option>
@@ -3311,6 +3314,9 @@
<div>
<h4 data-i18n="Google Model">Google Model</h4>
<select id="model_google_select">
<optgroup label="Gemini 3.8">
<option value="gemini-3.8-flash">gemini-3.8-flash</option>
</optgroup>
<optgroup label="Gemini 3.7">
<option value="gemini-3.7-flash">gemini-3.7-flash</option>
</optgroup>
@@ -3481,6 +3487,9 @@
<h4 data-i18n="Google Model">Google Model</h4>
<select id="model_vertexai_select">
<!-- data-mode="full" is for models that require a service account -->
<optgroup label="Gemini 3.8">
<option value="gemini-3.8-flash">gemini-3.8-flash</option>
</optgroup>
<optgroup label="Gemini 3.7">
<option value="gemini-3.7-flash">gemini-3.7-flash</option>
</optgroup>
@@ -4070,7 +4079,7 @@
<div class="api_loading menu_button menu_button_icon" data-i18n="Cancel">Cancel</div>
<div data-source="custom" id="customize_additional_parameters" class="menu_button menu_button_icon" data-i18n="Additional Parameters">Additional Parameters</div>
<div data-source="openrouter" class="menu_button menu_button_icon openrouter_authorize" title="Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai" data-i18n="Authorize;[title]Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai">Authorize</div>
<div id="test_api_button" class="menu_button menu_button_icon" title="Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!" data-i18n="Test Message;[title]Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!">Test Message</div>
<div id="test_api_button" class="menu_button menu_button_icon" title="Verifies your API connection by sending a short test message. This may incur usage charges." data-i18n="Test Message;[title]Verifies your API connection by sending a short test message. This may incur usage charges.">Test Message</div>
</div>
<div class="online_status">
<div class="online_status_indicator"></div>
+1 -1
View File
@@ -396,7 +396,7 @@
"Available Models": "النماذج المتاحة",
"Prompt Post-Processing": "موجه بعد المعالجة",
"Applies additional processing to the prompt before sending it to the API.": "يطبق معالجة إضافية على الموجه قبل إرساله إلى واجهة برمجة التطبيقات.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "تتحقق من اتصالك بواجهة برمجة التطبيقات من خلال إرسال رسالة اختبار قصيرة. كن على علم بأنك ستحصل على الفضل في ذلك!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "يتحقق من اتصال API الخاص بك عن طريق إرسال رسالة اختبار قصيرة. قد يؤدي ذلك إلى فرض رسوم استخدام.",
"Test Message": "رسالة اختبار",
"Auto-connect to Last Server": "الاتصال التلقائي بآخر خادم",
"Missing key": "❌المفتاح مفقود",
+1 -1
View File
@@ -396,7 +396,7 @@
"Available Models": "Verfügbare Modelle",
"Prompt Post-Processing": "Zeitnahe Nachbearbeitung",
"Applies additional processing to the prompt before sending it to the API.": "Wendet zusätzliche Verarbeitungsvorgänge auf die Eingabeaufforderung an, bevor sie an die API gesendet wird.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Überprüft deine API-Verbindung durch Senden einer kurzen Testnachricht. Sei dir bewusst, dass du dafür gutgeschrieben wirst!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Überprüft deine API-Verbindung durch Senden einer kurzen Testnachricht. Dabei können Nutzungsgebühren anfallen.",
"Test Message": "Testnachricht",
"Auto-connect to Last Server": "Automatisch mit dem letzten Server verbinden",
"Missing key": "❌ Fehlender Schlüssel",
+1 -1
View File
@@ -396,7 +396,7 @@
"Available Models": "Modelos disponibles",
"Prompt Post-Processing": "Postprocesamiento rápido",
"Applies additional processing to the prompt before sending it to the API.": "Aplica procesamiento adicional al mensaje antes de enviarlo a la API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Verifica su conexión de API enviando un breve mensaje de prueba. ¡Tenga en cuenta que se le cobrará por ello!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Verifica su conexión API enviando un breve mensaje de prueba. Esto puede generar cargos de uso.",
"Test Message": "Mensaje de prueba",
"Auto-connect to Last Server": "Conexión automática al último servidor",
"Missing key": "❌ Llave faltante",
+1 -1
View File
@@ -376,7 +376,7 @@
"Available Models": "Modèles disponibles",
"Prompt Post-Processing": "Post-traitement de prompt",
"Applies additional processing to the prompt before sending it to the API.": "Applique un traitement supplémentaire au prompt avant de l'envoyer à l'API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Vérifie votre connexion API en envoyant un court message de test. Soyez conscient que vous serez crédité pour cela !",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Vérifie votre connexion API en envoyant un court message de test. Cela peut entraîner des frais d'utilisation.",
"Test Message": "Message de test",
"Auto-connect to Last Server": "Connexion automatique au dernier serveur",
"Missing key": "❌ Clé manquante",
+1 -1
View File
@@ -394,7 +394,7 @@
"Available Models": "Módel í boði",
"Prompt Post-Processing": "Skjót eftirvinnsla",
"Applies additional processing to the prompt before sending it to the API.": "Beitir viðbótarvinnslu á boðunina áður en hún er send í API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Sannreynir API tengingu þína með því að senda stutt skilaboð til að prófa. Vertu meðvituð(ur/ur) um að þú færð fyrir það!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Staðfestir API tenginguna þína með því að senda stutt prufuskilaboð. Þetta gæti haft afnotagjöld í för með sér.",
"Test Message": "Prufu skilaboð",
"Auto-connect to Last Server": "Tengjast sjálfkrafa við síðustu framendurnar",
"Missing key": "❌ Vantar lykil",
+1 -1
View File
@@ -396,7 +396,7 @@
"Available Models": "Modelli disponibili",
"Prompt Post-Processing": "Post-elaborazione rapida",
"Applies additional processing to the prompt before sending it to the API.": "Applica un'ulteriore elaborazione al prompt prima di inviarlo all'API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Verifica la tua connessione API inviando un breve messaggio di prova. Tieni presente che verrai accreditato per questo!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Verifica la tua connessione API inviando un breve messaggio di prova. Ciò potrebbe comportare costi di utilizzo.",
"Test Message": "Messaggio di prova",
"Auto-connect to Last Server": "Connetti automaticamente all'ultimo server",
"Missing key": "❌ Chiave mancante",
+1 -1
View File
@@ -396,7 +396,7 @@
"Available Models": "利用可能なモデル",
"Prompt Post-Processing": "迅速な後処理",
"Applies additional processing to the prompt before sending it to the API.": "プロンプトを API に送信する前に追加の処理を適用します。",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "短いテストメッセージを送信してAPI接続を検証します。それに対してクレジットが与えられることに注意してください!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "短いテストメッセージを送信してAPI接続を検証します。これにより利用料金が発生する場合があります。",
"Test Message": "テストメッセージ",
"Auto-connect to Last Server": "前回のサーバーに自動接続",
"Missing key": "❌ キーがありません",
+1 -1
View File
@@ -404,7 +404,7 @@
"Prompt Post-Processing": "신속한 후처리",
"api_no_connection": "연결이 되지 않았습니다...",
"Applies additional processing to the prompt before sending it to the API.": "API로 보내기 전에 프롬프트에 추가 처리를 적용합니다.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "짧은 테스트 메시지를 보내어 API 연결을 확인합니다. 이에 대해 유료 크레딧이 지불될 수 있음을 인식하세요!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "짧은 테스트 메시지를 보내 API 연결을 확인합니다. 이로 인해 사용 요금이 부과될 수 있습니다.",
"Test Message": "테스트 메시지",
"Auto-connect to Last Server": "마지막 서버에 자동으로 연결",
"Missing key": "❌ 현재 저장된 키가 존재하지 않습니다.",
+1 -1
View File
@@ -392,7 +392,7 @@
"Available Models": "Beschikbare modellen",
"Prompt Post-Processing": "Snelle naverwerking",
"Applies additional processing to the prompt before sending it to the API.": "Past extra verwerking toe op de prompt voordat deze naar de API wordt verzonden.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Verifieert uw API-verbinding door een kort testbericht te verzenden. Wees ervan bewust dat u hiervoor wordt gecrediteerd!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Verifieert uw API-verbinding door een kort testbericht te verzenden. Hiervoor kunnen gebruikskosten in rekening worden gebracht.",
"Test Message": "Testbericht",
"Auto-connect to Last Server": "Automatisch verbinden met de laatste server",
"Missing key": "❌ Ontbrekende sleutel",
+1 -1
View File
@@ -394,7 +394,7 @@
"Available Models": "Modelos Disponíveis",
"Prompt Post-Processing": "Pós-processamento imediato",
"Applies additional processing to the prompt before sending it to the API.": "Aplica processamento adicional ao prompt antes de enviá-lo para a API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Verifica sua conexão com a API enviando uma mensagem de teste curta. Esteja ciente de que você será creditado por isso!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Verifica a ligação à API ao enviar uma mensagem de teste curta. Isto pode implicar custos de utilização.",
"Test Message": "Mensagem de Teste",
"Auto-connect to Last Server": "Conectar-se automaticamente ao último servidor",
"Missing key": "❌ Chave faltando",
+1 -1
View File
@@ -514,7 +514,7 @@
"Clear your API key": "Стереть ключ от API",
"Refresh models": "Обновить модели",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai": "Получите свой OpenRouter API токен используя OAuth. У вас будет открыта вкладка openrouter.ai",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Проверка работоспособности вашего соединения с API путём отправки короткого тестового сообщения. Внимание: оно будет отправлено от вашего имени.",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Проверяет соединение с API, отправляя короткое тестовое сообщение. Это может повлечь плату за использование.",
"Edit": "Редактировать",
"Locked = World Editor will stay open": "Закреплено = Редактор мира останется открытым",
"Entries can activate other entries by mentioning their keywords": "Записи могут активировать другие записи, если в них содержатся ключевые слова",
+1 -1
View File
@@ -401,7 +401,7 @@
"Available Models": "โมเดลที่สามารถใช้ได้",
"Prompt Post-Processing": "การประมวลผลพรอมต์หลังการส่ง",
"Applies additional processing to the prompt before sending it to the API.": "ใช้การประมวลผลเพิ่มเติมกับพรอมต์ก่อนส่งไปยัง API",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "ตรวจสอบการเชื่อมต่อ API โดยส่งข้อความทดสอบสั้นๆ โปรดทราบว่าคุณจะถูกเรียกเก็บเงินสำหรับการทดสอบนี้!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "ตรวจสอบการเชื่อมต่อ API โดยส่งข้อความทดสอบสั้นๆ ซึ่งอาจมีค่าใช้จ่ายในการใช้งาน",
"Test Message": "ทดสอบการส่งข้อความ",
"Auto-connect to Last Server": "เชื่อมต่อเซิฟเวอร์อัตโนมัติ",
"Missing key": "โปรดใส่ API Key",
+1 -1
View File
@@ -394,7 +394,7 @@
"Available Models": "Доступні моделі",
"Prompt Post-Processing": "Швидка постобробка",
"Applies additional processing to the prompt before sending it to the API.": "Застосовує додаткову обробку запиту перед надсиланням його в API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Підтверджує ваше підключення до API, надсилаючи коротке тестове повідомлення. Пам'ятайте, що ви будете платити за це!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Перевіряє підключення до API, надсилаючи коротке тестове повідомлення. За це може стягуватися плата за використання.",
"Test Message": "Тестове повідомлення",
"Auto-connect to Last Server": "Автоматичне підключення до останнього сервера",
"Missing key": "❌ Відсутній ключ",
+1 -1
View File
@@ -394,7 +394,7 @@
"Available Models": "Các Model hiện có",
"Prompt Post-Processing": "Xử lý hậu kỳ Prompt",
"Applies additional processing to the prompt before sending it to the API.": "Áp dụng xử lý bổ sung cho Prompt trước khi gửi nó tới API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "Xác minh kết nối API của bạn bằng cách gửi một tin nhắn kiểm tra ngắn. Hãy nhớ rằng bạn sẽ được ghi nhận về điều đó!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "Xác minh kết nối API của bạn bằng cách gửi tin nhắn kiểm tra ngắn. Việc này có thể phát sinh phí sử dụng.",
"Test Message": "Test tin nhắn",
"Auto-connect to Last Server": "Tự động kết nối với link trước đó",
"Missing key": "❌ Thiếu Key",
+1 -1
View File
@@ -556,7 +556,7 @@
"prompt_post_processing_single": "单一用户消息(无工具)",
"Additional Parameters": "附加参数",
"Test Message": "发送测试消息",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "通过发送简短的测试消息验证您的API连接。请注意,您将因此消耗额度!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "通过发送简短的测试消息验证您的 API 连接。这可能会产生使用费用。",
"Auto-connect to Last Server": "自动连接到上次的服务器",
"Missing key": "❌ 缺少密钥",
"Key saved": "密钥已保存",
+1 -1
View File
@@ -393,7 +393,7 @@
"Available Models": "可用模型",
"Prompt Post-Processing": "提示詞後處理",
"Applies additional processing to the prompt before sending it to the API.": "這個選項會在將提示詞送往 API 之前,對它進行額外的處理。",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!": "透過傳送簡短的測試訊息來驗證您的 API 連線。請注意,您將因此獲得榮譽!",
"Verifies your API connection by sending a short test message. This may incur usage charges.": "透過傳送簡短的測試訊息來驗證您的 API 連線。這可能會產生使用費用。",
"Test Message": "測試訊息",
"Auto-connect to Last Server": "自動連線至上次使用的伺服器",
"Missing key": "❌ 鑰匙遺失",
+1 -1
View File
@@ -9774,7 +9774,7 @@ export async function createOrEditCharacter(e) {
return;
}
try {
//if the character name text area isn't empty (only posible when creating a new character)
//if the character name text area isn't empty (only possible when creating a new character)
let url = '/api/characters/create';
if (crop_data != undefined) {
+6 -6
View File
@@ -33,12 +33,12 @@
* @property {number} role - The specific function or purpose of the extension.
* @property {boolean} vectorized - Indicates if the extension is optimized for vectorized processing.
* @property {number} display_index - The order in which the extension should be displayed for user interfaces.
* @property {boolean} match_persona_description - Wether to match against the persona description.
* @property {boolean} match_character_description - Wether to match against the persona description.
* @property {boolean} match_character_personality - Wether to match against the character personality.
* @property {boolean} match_character_depth_prompt - Wether to match against the character depth prompt.
* @property {boolean} match_scenario - Wether to match against the character scenario.
* @property {boolean} match_creator_notes - Wether to match against the character creator notes.
* @property {boolean} match_persona_description - Whether to match against the persona description.
* @property {boolean} match_character_description - Whether to match against the character description.
* @property {boolean} match_character_personality - Whether to match against the character personality.
* @property {boolean} match_character_depth_prompt - Whether to match against the character depth prompt.
* @property {boolean} match_scenario - Whether to match against the character scenario.
* @property {boolean} match_creator_notes - Whether to match against the character creator notes.
*/
/**
+1 -1
View File
@@ -55,7 +55,7 @@ function migrateSettings() {
}
if (!extension_settings.caption.multimodal_model) {
extension_settings.caption.multimodal_model = 'gpt-5.6-luna';
extension_settings.caption.multimodal_model = 'gpt-6-luna';
}
if (!extension_settings.caption.prompt) {
@@ -55,6 +55,8 @@
<option data-type="cohere" value="c4ai-aya-vision-32b">c4ai-aya-vision-32b</option>
<option data-type="cohere" value="command-a-vision-07-2025">command-a-vision-07-2025</option>
<option data-type="openai" value="gpt-6-astra">gpt-6-astra</option>
<option data-type="openai" value="gpt-6-sol">gpt-6-sol</option>
<option data-type="openai" value="gpt-6-luna">gpt-6-luna</option>
<option data-type="openai" value="gpt-5.6">gpt-5.6</option>
<option data-type="openai" value="gpt-5.6-sol">gpt-5.6-sol</option>
<option data-type="openai" value="gpt-5.6-terra">gpt-5.6-terra</option>
@@ -99,6 +101,7 @@
<option data-type="openai" value="o4-mini-2025-04-16">o4-mini-2025-04-16</option>
<option data-type="anthropic" value="claude-fable-5-1">claude-fable-5-1</option>
<option data-type="anthropic" value="claude-fable-5">claude-fable-5</option>
<option data-type="anthropic" value="claude-opus-5-5">claude-opus-5-5</option>
<option data-type="anthropic" value="claude-opus-5">claude-opus-5</option>
<option data-type="anthropic" value="claude-sonnet-5">claude-sonnet-5</option>
<option data-type="anthropic" value="claude-opus-4-8">claude-opus-4-8</option>
@@ -115,6 +118,7 @@
<option data-type="anthropic" value="claude-opus-4-20250514">claude-opus-4-20250514</option>
<option data-type="anthropic" value="claude-sonnet-4-0">claude-sonnet-4-0</option>
<option data-type="anthropic" value="claude-sonnet-4-20250514">claude-sonnet-4-20250514</option>
<option data-type="google" value="gemini-3.8-flash">gemini-3.8-flash</option>
<option data-type="google" value="gemini-3.7-flash">gemini-3.7-flash</option>
<option data-type="google" value="gemini-3.6-flash">gemini-3.6-flash</option>
<option data-type="google" value="gemini-3.5-flash">gemini-3.5-flash</option>
@@ -138,6 +142,7 @@
<option data-type="google" value="gemma-3-27b-it">gemma-3-27b-it</option>
<option data-type="google" value="gemma-3-12b-it">gemma-3-12b-it</option>
<option data-type="google" value="gemma-3-4b-it">gemma-3-4b-it</option>
<option data-type="vertexai" value="gemini-3.8-flash">gemini-3.8-flash</option>
<option data-type="vertexai" value="gemini-3.7-flash">gemini-3.7-flash</option>
<option data-type="vertexai" value="gemini-3.6-flash">gemini-3.6-flash</option>
<option data-type="vertexai" value="gemini-3.5-flash">gemini-3.5-flash</option>
+15 -11
View File
@@ -437,10 +437,10 @@ const default_settings = {
personality_format: default_personality_format,
sort_models: 'alphabetically',
group_models: false,
openai_model: 'gpt-5.6-terra',
openai_model: 'gpt-6-sol',
claude_model: 'claude-sonnet-5',
google_model: 'gemini-3.7-flash',
vertexai_model: 'gemini-3.7-flash',
google_model: 'gemini-3.8-flash',
vertexai_model: 'gemini-3.8-flash',
ai21_model: 'jamba-large',
mistralai_model: 'mistral-large-latest',
cohere_model: 'command-r-plus',
@@ -2621,7 +2621,7 @@ function getReasoningEffort(settings = null, model = null) {
}
if ([chat_completion_sources.OPENAI, chat_completion_sources.AZURE_OPENAI].includes(settings.chat_completion_source)) {
if (/^gpt-5\.(4|5|6)/.test(model)) {
if (/^(?:gpt-5\.(?:4|5|6)|gpt-6-(?:sol|luna))/.test(model)) {
return 'none';
}
if (/^gpt-5/.test(model)) {
@@ -2632,7 +2632,7 @@ function getReasoningEffort(settings = null, model = null) {
return reasoning_effort_types.low;
case reasoning_effort_types.max:
if ([chat_completion_sources.OPENAI, chat_completion_sources.AZURE_OPENAI].includes(settings.chat_completion_source)
&& /^gpt-6-astra/.test(model)) {
&& /^gpt-6-/.test(model)) {
return reasoning_effort_types.max;
}
if ([chat_completion_sources.OPENAI, chat_completion_sources.AZURE_OPENAI].includes(settings.chat_completion_source)
@@ -3094,13 +3094,15 @@ export async function createGenerationParameters(settings, model, type, messages
}
}
if (gptSources.includes(settings.chat_completion_source) && /gpt-6-astra/.test(model)) {
if (gptSources.includes(settings.chat_completion_source) && /gpt-6-/.test(model)) {
generate_data.max_completion_tokens = generate_data.max_tokens;
delete generate_data.max_tokens;
delete generate_data.temperature;
delete generate_data.top_p;
delete generate_data.logprobs;
delete generate_data.top_logprobs;
if (model.includes('gpt-6-astra') || generate_data.reasoning_effort !== 'none') {
delete generate_data.temperature;
delete generate_data.top_p;
delete generate_data.logprobs;
delete generate_data.top_logprobs;
}
}
// Claude Fable / Claude 5 models removed sampling parameters and reject them with HTTP 400,
@@ -5092,7 +5094,7 @@ function getMaxContextOpenAI(value) {
/** @type {[RegExp, number][]} */
const contextMap = [
[/^gpt-6-astra/, max_1050k],
[/^gpt-6-/, max_1050k],
[/^gpt-5\.6/, max_1050k],
[/^gpt-5\.[45]/, max_1mil],
[/^gpt-5/, max_400k],
@@ -6242,6 +6244,8 @@ export function isImageInliningSupported() {
'gpt-4.5-preview',
'gpt-4o',
'gpt-6-astra',
'gpt-6-sol',
'gpt-6-luna',
'gpt-5',
'o1',
'o3',
+1 -1
View File
@@ -639,7 +639,7 @@ export function getTokenizerModel() {
}
if (oai_settings.chat_completion_source == chat_completion_sources.ELECTRONHUB && oai_settings.electronhub_model) {
if (oai_settings.electronhub_model.includes('gpt-4o') || oai_settings.electronhub_model.includes('gpt-5') || oai_settings.electronhub_model.includes('gpt-6-astra')) {
if (oai_settings.electronhub_model.includes('gpt-4o') || oai_settings.electronhub_model.includes('gpt-5') || oai_settings.electronhub_model.includes('gpt-6-')) {
return gpt4oTokenizer;
} else if (oai_settings.electronhub_model.includes('gpt-4.1') || oai_settings.electronhub_model.includes('gpt-4.5')) {
return gpt4oTokenizer;
+2 -2
View File
@@ -619,9 +619,9 @@ export class ToolManager {
return false;
}
// GPT-6 Astra supports tool calling only through the Responses API.
// GPT-6 Astra requires Responses for tools. Sol and Luna allow Chat Completions tools only without reasoning.
if ([chat_completion_sources.OPENAI, chat_completion_sources.AZURE_OPENAI].includes(settings.chat_completion_source)
&& /^gpt-6-astra/.test(model)) {
&& (/^gpt-6-astra/.test(model) || (/^gpt-6-(sol|luna)/.test(model) && settings.reasoning_effort !== 'min'))) {
return false;
}
+3 -1
View File
@@ -456,7 +456,7 @@ export const AZURE_OPENAI_KEYS = [
'reasoning_effort',
];
export const OPENAI_VERBOSITY_MODELS = /^(?:gpt-5|gpt-6-astra)/;
export const OPENAI_VERBOSITY_MODELS = /^(?:gpt-5|gpt-6-)/;
export const OPENAI_REASONING_EFFORT_MODELS = [
'o1',
@@ -492,6 +492,8 @@ export const OPENAI_REASONING_EFFORT_MODELS = [
'gpt-5.6-terra',
'gpt-5.6-luna',
'gpt-6-astra',
'gpt-6-sol',
'gpt-6-luna',
];
export const OPENAI_REASONING_EFFORT_MAP = {
+4 -4
View File
@@ -250,7 +250,7 @@ async function sendClaudeRequest(request, response) {
const convertedPrompt = convertClaudeMessages(request.body.messages, request.body.assistant_prefill, useSystemPrompt, useTools, getPromptNames(request));
// Unanchored to also match prefixed ids passed through proxies, e.g. 'anthropic/claude-fable-5'
const isFableModel = /claude-fable/.test(request.body.model);
const isFable51Model = /claude-fable-5-1/.test(request.body.model);
const useNativeJsonOutput = /claude-(fable-5-1|opus-5-5)/.test(request.body.model);
const isClaude5Model = /claude-(opus-5|sonnet-5)/.test(request.body.model);
const useThinking = /^claude-(3-7|opus-4|sonnet-4|haiku-4-5|opus-4-5|opus-4-6|sonnet-4-6|opus-4-7)/.test(request.body.model) || isFableModel || isClaude5Model;
const useWebSearch = (/^claude-(3-5|3-7|opus-4|sonnet-4|haiku-4-5|opus-4-5|opus-4-6|sonnet-4-6|opus-4-7)/.test(request.body.model) || isFableModel || isClaude5Model) && Boolean(request.body.enable_web_search);
@@ -299,9 +299,9 @@ async function sendClaudeRequest(request, response) {
}
}
// Fable 5.1 rejects forced tools, but supports native JSON outputs.
// Fable 5.1 and Opus 5.5 reject forced tools, but support native JSON outputs.
if (request.body.json_schema) {
if (isFable51Model) {
if (useNativeJsonOutput) {
requestBody.output_config = {
format: {
type: 'json_schema',
@@ -526,7 +526,7 @@ async function sendMakerSuiteRequest(request, response) {
const isThinkingConfigModel = m => (/^gemini-2.5-(flash|pro)/.test(m) && !/-image(-preview)?$/.test(m)) || (/^gemini-3[.\d]*-(flash|pro)/.test(m));
const isImageSizeModel = m => /^gemini-3/.test(m);
// https://ai.google.dev/gemini-api/docs/latest-model#api-changes-and-parameter-updates
const noSamplingModel = /gemini-3\.[67]-flash|gemini-3\.5-flash-lite/.test(model);
const noSamplingModel = /gemini-3\.[678]-flash|gemini-3\.5-flash-lite/.test(model);
const noSearchModels = [
'gemini-2.0-flash-lite',
+1 -1
View File
@@ -442,7 +442,7 @@ export function getTokenizerModel(requestModel) {
return 'o1';
}
if (requestModel.includes('gpt-5') || requestModel.includes('gpt-6-astra') || requestModel.includes('o3') || requestModel.includes('o4-mini')) {
if (requestModel.includes('gpt-5') || requestModel.includes('gpt-6-') || requestModel.includes('o3') || requestModel.includes('o4-mini')) {
return 'o1';
}
+3 -3
View File
@@ -390,7 +390,7 @@ export function convertCohereMessages(messages, names) {
}
messages.forEach((msg, index) => {
// Tool calls require an assistent primer
// Tool calls require an assistant primer
if (Array.isArray(msg.tool_calls)) {
if (index > 0 && messages[index - 1].role === 'assistant') {
msg.content = messages[index - 1].content;
@@ -454,7 +454,7 @@ export function convertGooglePrompt(messages, model, useSysPrompt, names) {
const toolNameMap = {};
// https://ai.google.dev/gemini-api/docs/latest-model#prefilled-model-turn-validation
const noPrefillModel = /gemini-3\.[67]-flash|gemini-3\.5-flash-lite/.test(model);
const noPrefillModel = /gemini-3\.[678]-flash|gemini-3\.5-flash-lite/.test(model);
const contents = [];
messages.forEach((message, index) => {
@@ -1264,7 +1264,7 @@ export function calculateGoogleBudgetTokens(maxTokens, reasoningEffort, model) {
function getGemini3FlashBudget() {
// https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash
const noMinimalThinking = /gemini-3\.7-flash/.test(model);
const noMinimalThinking = /gemini-3\.[78]-flash/.test(model);
switch (reasoningEffort) {
case REASONING_EFFORT.auto:
return null;
+8 -1
View File
@@ -173,6 +173,13 @@ describe('calculateGoogleBudgetTokens', () => {
expect(mod.calculateGoogleBudgetTokens(8192, 'max', 'gemini-3.7-flash')).toBe('high');
});
test('Gemini 3.8 Flash uses Gemini 3 thinking levels without minimal', () => {
expect(mod.calculateGoogleBudgetTokens(8192, 'auto', 'gemini-3.8-flash')).toBeNull();
expect(mod.calculateGoogleBudgetTokens(8192, 'min', 'gemini-3.8-flash')).toBe('low');
expect(mod.calculateGoogleBudgetTokens(8192, 'low', 'gemini-3.8-flash')).toBe('low');
expect(mod.calculateGoogleBudgetTokens(8192, 'max', 'gemini-3.8-flash')).toBe('high');
});
test('Gemini 3.6 Flash uses Gemini 3 thinking levels', () => {
expect(mod.calculateGoogleBudgetTokens(8192, 'auto', 'gemini-3.6-flash')).toBeNull();
expect(mod.calculateGoogleBudgetTokens(8192, 'min', 'gemini-3.6-flash')).toBe('minimal');
@@ -1062,7 +1069,7 @@ describe('convertGooglePrompt', () => {
expect(result.contents.filter(c => c.role === 'user')).toHaveLength(1);
});
for (const model of ['gemini-3.7-flash', 'gemini-3.6-flash', 'gemini-3.5-flash-lite']) {
for (const model of ['gemini-3.8-flash', 'gemini-3.7-flash', 'gemini-3.6-flash', 'gemini-3.5-flash-lite']) {
test(`merges a trailing prefill into the user turn on ${model}`, () => {
const messages = [
{ role: 'user', content: 'Hi' },