Compare commits

..

4 Commits

Author SHA1 Message Date
Robert Brennan 8e7cac1437 empty commit 2024-11-11 17:33:49 -05:00
Robert Brennan c5d4a7fa3e use gh lib 2024-11-11 17:31:54 -05:00
Robert Brennan 2144296735 add github lib 2024-11-11 17:31:33 -05:00
Robert Brennan 8414a72693 fix infinite loop 2024-11-09 18:00:04 -05:00
11 changed files with 511 additions and 1549 deletions
+2 -2
View File
@@ -4,11 +4,11 @@ OpenHands can connect to any LLM supported by LiteLLM. However, it requires a po
## Model Recommendations
Based on our evaluations of language models for coding tasks (using the SWE-bench dataset), we can provide some recommendations for model selection. Some analyses can be found in [this blog article comparing LLMs](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) and [this blog article with some more recent results](https://www.all-hands.dev/blog/openhands-codeact-21-an-open-state-of-the-art-software-development-agent).
Based on a recent evaluation of language models for coding tasks (using the SWE-bench dataset), we can provide some recommendations for model selection. The full analysis can be found in [this blog article](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed).
When choosing a model, consider both the quality of outputs and the associated costs. Here's a summary of the findings:
- Claude 3.5 Sonnet is the best by a fair amount, achieving a 53% resolve rate on SWE-Bench Verified with the default agent in OpenHands.
- Claude 3.5 Sonnet is the best by a fair amount, achieving a 27% resolve rate with the default agent in OpenHands.
- GPT-4o lags behind, and o1-mini actually performed somewhat worse than GPT-4o. We went in and analyzed the results a little, and briefly it seemed like o1 was sometimes "overthinking" things, performing extra environment configuration tasks when it could just go ahead and finish the task.
- Finally, the strongest open models were Llama 3.1 405 B and deepseek-v2.5, and they performed reasonably, even besting some of the closed models.
@@ -59,9 +59,9 @@ describe("extractModelAndProvider", () => {
separator: "/",
});
expect(extractModelAndProvider("claude-3-5-sonnet-20240620")).toEqual({
expect(extractModelAndProvider("claude-3-5-sonnet-20241022")).toEqual({
provider: "anthropic",
model: "claude-3-5-sonnet-20240620",
model: "claude-3-5-sonnet-20241022",
separator: "/",
});
@@ -15,7 +15,7 @@ test("organizeModelsAndProviders", () => {
"gpt-4o",
"together-ai-21.1b-41b",
"gpt-4o-mini",
"anthropic/claude-3-5-sonnet-20241022",
"claude-3-5-sonnet-20241022",
"claude-3-haiku-20240307",
"claude-2",
"claude-2.1",
+34 -276
View File
@@ -535,8 +535,7 @@
"pt": "Socket não inicializado",
"ko-KR": "소켓이 초기화되지 않았습니다",
"ar": "لم يتم تهيئة Socket",
"tr": "Soket başlatılmadı",
"no": "Socket ikke initialisert"
"tr": "Soket başlatılmadı"
},
"EXPLORER$UPLOAD_ERROR_MESSAGE": {
"en": "Error uploading file",
@@ -549,8 +548,7 @@
"pt": "Erro ao fazer upload do arquivo",
"ko-KR": "파일 업로드 중 오류 발생",
"ar": "خطأ في تحميل الملف",
"tr": "Dosya yüklenirken hata oluştu",
"no": "Feil ved opplasting av fil"
"tr": "Dosya yüklenirken hata oluştu"
},
"EXPLORER$LABEL_DROP_FILES": {
"en": "Drop files here",
@@ -559,7 +557,6 @@
"zh-TW": "將檔案拖曳至此",
"es": "Suelta los archivos aquí",
"fr": "Déposez les fichiers ici",
"no": "Slipp filer her",
"it": "Trascina i file qui",
"pt": "Solte os arquivos aqui",
"ko-KR": "파일을 여기에 놓으세요",
@@ -577,8 +574,7 @@
"pt": "Espaço de trabalho",
"ko-KR": "작업 공간",
"ar": "مساحة العمل",
"tr": "Çalışma alanı",
"no": "Arbeidsområde"
"tr": "Çalışma alanı"
},
"EXPLORER$EMPTY_WORKSPACE_MESSAGE": {
"en": "No files in workspace",
@@ -591,8 +587,7 @@
"pt": "Nenhum arquivo no espaço de trabalho",
"ko-KR": "작업 공간에 파일이 없습니다",
"ar": "لا توجد ملفات في مساحة العمل",
"tr": "Çalışma alanında dosya yok",
"no": "Ingen filer i arbeidsområdet"
"tr": "Çalışma alanında dosya yok"
},
"EXPLORER$LOADING_WORKSPACE_MESSAGE": {
"en": "Loading workspace...",
@@ -605,8 +600,7 @@
"pt": "Carregando espaço de trabalho...",
"ko-KR": "작업 공간 로딩 중...",
"ar": "جارٍ تحميل مساحة العمل...",
"tr": "Çalışma alanı yükleniyor...",
"no": "Laster arbeidsområde..."
"tr": "Çalışma alanı yükleniyor..."
},
"EXPLORER$REFRESH_ERROR_MESSAGE": {
"en": "Error refreshing workspace",
@@ -619,8 +613,7 @@
"pt": "Erro ao atualizar o espaço de trabalho",
"ko-KR": "작업 공간 새로 고침 오류",
"ar": "خطأ في تحديث مساحة العمل",
"tr": "Çalışma alanı yenilenirken hata oluştu",
"no": "Feil ved oppdatering av arbeidsområde"
"tr": "Çalışma alanı yenilenirken hata oluştu"
},
"EXPLORER$UPLOAD_SUCCESS_MESSAGE": {
"en": "Successfully uploaded {{count}} file(s)",
@@ -633,8 +626,7 @@
"pt": "{{count}} arquivo(s) carregado(s) com sucesso",
"ko-KR": "{{count}}개의 파일을 성공적으로 업로드했습니다",
"ar": "تم تحميل {{count}} ملف (ملفات) بنجاح",
"tr": "{{count}} dosya başarıyla yüklendi",
"no": "Lastet opp {{count}} fil(er) vellykket"
"tr": "{{count}} dosya başarıyla yüklendi"
},
"EXPLORER$NO_FILES_UPLOADED_MESSAGE": {
"en": "No files were uploaded",
@@ -647,8 +639,7 @@
"pt": "Nenhum arquivo foi carregado",
"ko-KR": "업로드된 파일이 없습니다",
"ar": "لم يتم تحميل أي ملفات",
"tr": "Hiçbir dosya yüklenmedi",
"no": "Ingen filer ble lastet opp"
"tr": "Hiçbir dosya yüklenmedi"
},
"EXPLORER$UPLOAD_PARTIAL_SUCCESS_MESSAGE": {
"en": "{{count}} file(s) were skipped during upload",
@@ -661,8 +652,7 @@
"pt": "{{count}} arquivo(s) foram ignorados durante o upload",
"ko-KR": "업로드 중 {{count}}개의 파일이 건너뛰어졌습니다",
"ar": "تم تخطي {{count}} ملف (ملفات) أثناء التحميل",
"tr": "Yükleme sırasında {{count}} dosya atlandı",
"no": "{{count}} fil(er) ble hoppet over under opplasting"
"tr": "Yükleme sırasında {{count}} dosya atlandı"
},
"EXPLORER$UPLOAD_UNEXPECTED_RESPONSE_MESSAGE": {
"en": "Unexpected response structure from server",
@@ -675,8 +665,7 @@
"pt": "Estrutura de resposta inesperada do servidor",
"ko-KR": "서버로부터 예상치 못한 응답 구조",
"ar": "بنية استجابة غير متوقعة من الخادم",
"tr": "Sunucudan beklenmeyen yanıt yapısı",
"no": "Uventet responsstruktur fra serveren"
"tr": "Sunucudan beklenmeyen yanıt yapısı"
},
"LOAD_SESSION$MODAL_TITLE": {
"en": "Return to existing session?",
@@ -810,325 +799,95 @@
},
"FEEDBACK$EMAIL_PLACEHOLDER": {
"en": "Enter your email address",
"es": "Ingresa tu correo electrónico",
"zh-CN": "输入您的电子邮件地址",
"zh-TW": "輸入您的電子郵件地址",
"ko-KR": "이메일 주소를 입력하세요",
"no": "Skriv inn din e-postadresse",
"ar": "أدخل عنوان بريدك الإلكتروني",
"de": "Geben Sie Ihre E-Mail-Adresse ein",
"fr": "Entrez votre adresse e-mail",
"it": "Inserisci il tuo indirizzo email",
"pt": "Digite seu endereço de e-mail",
"tr": "E-posta adresinizi girin"
"es": "Ingresa tu correo electrónico"
},
"FEEDBACK$PASSWORD_COPIED_MESSAGE": {
"en": "Password copied to clipboard.",
"es": "Contraseña copiada al portapapeles.",
"zh-CN": "密码已复制到剪贴板。",
"zh-TW": "密碼已複製到剪貼板。",
"ko-KR": "비밀번호가 클립보드에 복사되었습니다.",
"no": "Passord kopiert til utklippstavlen.",
"ar": "تم نسخ كلمة المرور إلى الحافظة.",
"de": "Passwort in die Zwischenablage kopiert.",
"fr": "Mot de passe copié dans le presse-papiers.",
"it": "Password copiata negli appunti.",
"pt": "Senha copiada para a área de transferência.",
"tr": "Parola panoya kopyalandı."
"es": "Contraseña copiada al portapapeles."
},
"FEEDBACK$GO_TO_FEEDBACK": {
"en": "Go to shared feedback",
"es": "Ir a feedback compartido",
"zh-CN": "转到共享反馈",
"zh-TW": "前往共享反饋",
"ko-KR": "공유된 피드백으로 이동",
"no": "Gå til delt tilbakemelding",
"ar": "الذهاب إلى التعليقات المشتركة",
"de": "Zum geteilten Feedback gehen",
"fr": "Aller aux commentaires partagés",
"it": "Vai al feedback condiviso",
"pt": "Ir para feedback compartilhado",
"tr": "Paylaşılan geri bildirimlere git"
"es": "Ir a feedback compartido"
},
"FEEDBACK$PASSWORD": {
"en": "Password:",
"es": "Contraseña:",
"zh-CN": "密码:",
"zh-TW": "密碼:",
"ko-KR": "비밀번호:",
"no": "Passord:",
"ar": "كلمة المرور:",
"de": "Passwort:",
"fr": "Mot de passe :",
"it": "Password:",
"pt": "Senha:",
"tr": "Parola:"
"es": "Contraseña:"
},
"FEEDBACK$INVALID_EMAIL_FORMAT": {
"en": "Invalid email format",
"es": "Formato de correo inválido",
"zh-CN": "无效的电子邮件格式",
"zh-TW": "無效的電子郵件格式",
"ko-KR": "잘못된 이메일 형식",
"no": "Ugyldig e-postformat",
"ar": "تنسيق البريد الإلكتروني غير صالح",
"de": "Ungültiges E-Mail-Format",
"fr": "Format d'e-mail invalide",
"it": "Formato email non valido",
"pt": "Formato de e-mail inválido",
"tr": "Geçersiz e-posta biçimi"
"es": "Formato de correo inválido"
},
"FEEDBACK$FAILED_TO_SHARE": {
"en": "Failed to share, please contact the developers:",
"es": "Error al compartir, por favor contacta con los desarrolladores:",
"zh-CN": "分享失败,请联系开发人员:",
"zh-TW": "分享失敗,請聯繫開發人員:",
"ko-KR": "공유 실패, 개발자에게 문의하세요:",
"no": "Deling mislyktes, vennligst kontakt utviklerne:",
"ar": "فشل المشاركة، يرجى الاتصال بالمطورين:",
"de": "Teilen fehlgeschlagen, bitte kontaktieren Sie die Entwickler:",
"fr": "Échec du partage, veuillez contacter les développeurs :",
"it": "Condivisione fallita, contattare gli sviluppatori:",
"pt": "Falha ao compartilhar, entre em contato com os desenvolvedores:",
"tr": "Paylaşım başarısız, lütfen geliştiricilerle iletişime geçin:"
"es": "Error al compartir, por favor contacta con los desarrolladores:"
},
"FEEDBACK$COPY_LABEL": {
"en": "Copy",
"es": "Copiar",
"zh-CN": "复制",
"zh-TW": "複製",
"ko-KR": "복사",
"no": "Kopier",
"ar": "نسخ",
"de": "Kopieren",
"fr": "Copier",
"it": "Copia",
"pt": "Copiar",
"tr": "Kopyala"
"es": "Copiar"
},
"FEEDBACK$SHARING_SETTINGS_LABEL": {
"en": "Sharing settings",
"es": "Configuración de compartir",
"zh-CN": "共享设置",
"zh-TW": "共享設定",
"ko-KR": "공유 설정",
"no": "Delingsinnstillinger",
"ar": "إعدادات المشاركة",
"de": "Freigabeeinstellungen",
"fr": "Paramètres de partage",
"it": "Impostazioni di condivisione",
"pt": "Configurações de compartilhamento",
"tr": "Paylaşım ayarları"
"es": "Configuración de compartir"
},
"SECURITY$UNKNOWN_ANALYZER_LABEL":{
"en": "Unknown security analyzer chosen",
"es": "Analizador de seguridad desconocido",
"zh-CN": "选择了未知的安全分析器",
"zh-TW": "選擇了未知的安全分析器",
"ko-KR": "알 수 없는 보안 분석기가 선택되었습니다",
"no": "Ukjent sikkerhetsanalysator valgt",
"ar": "تم اختيار محلل أمان غير معروف",
"de": "Unbekannter Sicherheitsanalysator ausgewählt",
"fr": "Analyseur de sécurité inconnu choisi",
"it": "Analizzatore di sicurezza sconosciuto selezionato",
"pt": "Analisador de segurança desconhecido escolhido",
"tr": "Bilinmeyen güvenlik analizörü seçildi"
"es": "Analizador de seguridad desconocido"
},
"INVARIANT$UPDATE_POLICY_LABEL": {
"en": "Update Policy",
"es": "Actualizar política",
"zh-CN": "更新策略",
"zh-TW": "更新策略",
"ko-KR": "정책 업데이트",
"no": "Oppdater policy",
"ar": "تحديث السياسة",
"de": "Richtlinie aktualisieren",
"fr": "Mettre à jour la politique",
"it": "Aggiorna policy",
"pt": "Atualizar política",
"tr": "İlkeyi güncelle"
"es": "Actualizar política"
},
"INVARIANT$UPDATE_SETTINGS_LABEL": {
"en": "Update Settings",
"es": "Actualizar configuración",
"zh-CN": "更新设置",
"zh-TW": "更新設定",
"ko-KR": "설정 업데이트",
"no": "Oppdater innstillinger",
"ar": "تحديث الإعدادات",
"de": "Einstellungen aktualisieren",
"fr": "Mettre à jour les paramètres",
"it": "Aggiorna impostazioni",
"pt": "Atualizar configurações",
"tr": "Ayarları güncelle"
"es": "Actualizar configuración"
},
"INVARIANT$SETTINGS_LABEL": {
"en": "Settings",
"es": "Configuración",
"zh-CN": "设置",
"zh-TW": "設定",
"ko-KR": "설정",
"no": "Innstillinger",
"ar": "الإعدادات",
"de": "Einstellungen",
"fr": "Paramètres",
"it": "Impostazioni",
"pt": "Configurações",
"tr": "Ayarlar"
"es": "Configuración"
},
"INVARIANT$ASK_CONFIRMATION_RISK_SEVERITY_LABEL": {
"en": "Ask for user confirmation on risk severity:",
"es": "Preguntar por confirmación del usuario sobre severidad del riesgo:",
"zh-CN": "询问用户确认风险等级:",
"zh-TW": "詢問用戶確認風險等級:",
"ko-KR": "위험 심각도에 대한 사용자 확인 요청:",
"no": "Be om brukerbekreftelse på risikoalvorlighet:",
"ar": "اطلب تأكيد المستخدم على مستوى الخطورة:",
"de": "Nach Benutzerbestätigung für Risikoschweregrad fragen:",
"fr": "Demander la confirmation de l'utilisateur sur la gravité du risque :",
"it": "Chiedi conferma all'utente sulla gravità del rischio:",
"pt": "Solicitar confirmação do usuário sobre a gravidade do risco:",
"tr": "Risk şiddeti için kullanıcı onayı iste:"
"es": "Preguntar por confirmación del usuario sobre severidad del riesgo:"
},
"INVARIANT$DONT_ASK_FOR_CONFIRMATION_LABEL": {
"en": "Don't ask for confirmation",
"es": "No solicitar confirmación",
"zh-CN": "不要请求确认",
"zh-TW": "不要請求確認",
"ko-KR": "확인 요청하지 않음",
"no": "Ikke spør om bekreftelse",
"ar": "لا تطلب التأكيد",
"de": "Nicht nach Bestätigung fragen",
"fr": "Ne pas demander de confirmation",
"it": "Non chiedere conferma",
"pt": "Não solicitar confirmação",
"tr": "Onay isteme"
"es": "No solicitar confirmación"
},
"INVARIANT$INVARIANT_ANALYZER_LABEL": {
"en": "Invariant Analyzer",
"es": "Analizador de invariantes",
"zh-CN": "不变量分析器",
"zh-TW": "不變量分析器",
"ko-KR": "불변성 분석기",
"no": "Invariant-analysator",
"ar": "محلل الثوابت",
"de": "Invarianten-Analysator",
"fr": "Analyseur d'invariants",
"it": "Analizzatore di invarianti",
"pt": "Analisador de invariantes",
"tr": "Değişmez Analizörü"
"es": "Analizador de invariantes"
},
"INVARIANT$INVARIANT_ANALYZER_MESSAGE": {
"en": "Invariant Analyzer continuously monitors your OpenHands agent for security issues.",
"es": "Analizador de invariantes continuamente monitorea tu agente de OpenHands por problemas de seguridad.",
"zh-CN": "不变量分析器持续监控您的 OpenHands 代理的安全问题。",
"zh-TW": "不變量分析器持續監控您的 OpenHands 代理的安全問題。",
"ko-KR": "불변성 분석기는 OpenHands 에이전트의 보안 문제를 지속적으로 모니터링합니다.",
"no": "Invariant-analysatoren overvåker kontinuerlig OpenHands-agenten din for sikkerhetsproblemer.",
"ar": "يراقب محلل الثوابت وكيل OpenHands الخاص بك باستمرار للتحقق من المشاكل الأمنية.",
"de": "Der Invarianten-Analysator überwacht kontinuierlich Ihren OpenHands-Agenten auf Sicherheitsprobleme.",
"fr": "L'analyseur d'invariants surveille en permanence votre agent OpenHands pour détecter les problèmes de sécurité.",
"it": "L'analizzatore di invarianti monitora continuamente il tuo agente OpenHands per problemi di sicurezza.",
"pt": "O analisador de invariantes monitora continuamente seu agente OpenHands em busca de problemas de segurança.",
"tr": "Değişmez Analizörü, OpenHands ajanınızı güvenlik sorunları için sürekli olarak izler."
"es": "Analizador de invariantes continuamente monitorea tu agente de OpenHands por problemas de seguridad."
},
"INVARIANT$CLICK_TO_LEARN_MORE_LABEL": {
"en": "Click to learn more",
"es": "Clic para aprender más",
"zh-CN": "点击了解更多",
"zh-TW": "點擊了解更多",
"ko-KR": "자세히 알아보기",
"no": "Klikk for å lære mer",
"ar": "انقر لمعرفة المزيد",
"de": "Klicken Sie, um mehr zu erfahren",
"fr": "Cliquez pour en savoir plus",
"it": "Clicca per saperne di più",
"pt": "Clique para saber mais",
"tr": "Daha fazla bilgi için tıklayın"
"es": "Clic para aprender más"
},
"INVARIANT$POLICY_LABEL": {
"en": "Policy",
"es": "Política",
"zh-CN": "策略",
"zh-TW": "策略",
"ko-KR": "정책",
"no": "Policy",
"ar": "السياسة",
"de": "Richtlinie",
"fr": "Politique",
"it": "Policy",
"pt": "Política",
"tr": "İlke"
"es": "Política"
},
"INVARIANT$LOG_LABEL": {
"en": "Logs",
"es": "Logs",
"zh-CN": "日志",
"zh-TW": "日誌",
"ko-KR": "로그",
"no": "Logger",
"ar": "السجلات",
"de": "Protokolle",
"fr": "Journaux",
"it": "Log",
"pt": "Logs",
"tr": "Günlükler"
"es": "Logs"
},
"INVARIANT$EXPORT_TRACE_LABEL": {
"en": "Export Trace",
"es": "Exportar traza",
"zh-CN": "导出跟踪",
"zh-TW": "匯出追蹤",
"ko-KR": "추적 내보내기",
"no": "Eksporter sporing",
"ar": "تصدير التتبع",
"de": "Ablaufverfolgung exportieren",
"fr": "Exporter la trace",
"it": "Esporta traccia",
"pt": "Exportar rastreamento",
"tr": "İzlemeyi dışa aktar"
"es": "Exportar traza"
},
"INVARIANT$TRACE_EXPORTED_MESSAGE": {
"en": "Trace exported",
"es": "Traza exportada",
"zh-CN": "跟踪已导出",
"zh-TW": "追蹤已匯出",
"ko-KR": "추적 내보내기 완료",
"no": "Sporing eksportert",
"ar": "تم تصدير التتبع",
"de": "Ablaufverfolgung exportiert",
"fr": "Trace exportée",
"it": "Traccia esportata",
"pt": "Rastreamento exportado",
"tr": "İzleme dışa aktarıldı"
"es": "Traza exportada"
},
"INVARIANT$POLICY_UPDATED_MESSAGE": {
"en": "Policy updated",
"es": "Política actualizada",
"zh-CN": "策略已更新",
"zh-TW": "策略已更新",
"ko-KR": "정책이 업데이트되었습니다",
"no": "Policy oppdatert",
"ar": "تم تحديث السياسة",
"de": "Richtlinie aktualisiert",
"fr": "Politique mise à jour",
"it": "Policy aggiornata",
"pt": "Política atualizada",
"tr": "İlke güncellendi"
"es": "Política actualizada"
},
"INVARIANT$SETTINGS_UPDATED_MESSAGE": {
"en": "Settings updated",
"es": "Configuración actualizada",
"zh-CN": "设置已更新",
"zh-TW": "設定已更新",
"ko-KR": "설정이 업데이트되었습니다",
"no": "Innstillinger oppdatert",
"ar": "تم تحديث الإعدادات",
"de": "Einstellungen aktualisiert",
"fr": "Paramètres mis à jour",
"it": "Impostazioni aggiornate",
"pt": "Configurações atualizadas",
"tr": "Ayarlar güncellendi"
"es": "Configuración actualizada"
},
"CHAT_INTERFACE$INITIALIZING_AGENT_LOADING_MESSAGE": {
"en": "Starting up!",
@@ -1517,8 +1276,7 @@
"pt": "Conversa de chat",
"es": "Conversación de chat",
"ar": "محادثة تلقيم",
"fr": "Conversation de chat",
"tr": "Sohbet Konuşması"
"fr": "Conversation de chat"
},
"CHAT_INTERFACE$UNKNOWN_SENDER": {
"en": "Unknown",
@@ -26,7 +26,6 @@ import { extractModelAndProvider } from "./extractModelAndProvider";
*/
export const organizeModelsAndProviders = (models: string[]) => {
const object: Record<string, { separator: string; models: string[] }> = {};
models.forEach((model) => {
const {
separator,
@@ -46,6 +45,5 @@ export const organizeModelsAndProviders = (models: string[]) => {
}
object[key].models.push(modelId);
});
return object;
};
-744
View File
@@ -1,744 +0,0 @@
#!/bin/sh
set -e
# Docker Engine for Linux installation script.
#
# This script is intended as a convenient way to configure docker's package
# repositories and to install Docker Engine, This script is not recommended
# for production environments. Before running this script, make yourself familiar
# with potential risks and limitations, and refer to the installation manual
# at https://docs.docker.com/engine/install/ for alternative installation methods.
#
# The script:
#
# - Requires `root` or `sudo` privileges to run.
# - Attempts to detect your Linux distribution and version and configure your
# package management system for you.
# - Doesn't allow you to customize most installation parameters.
# - Installs dependencies and recommendations without asking for confirmation.
# - Installs the latest stable release (by default) of Docker CLI, Docker Engine,
# Docker Buildx, Docker Compose, containerd, and runc. When using this script
# to provision a machine, this may result in unexpected major version upgrades
# of these packages. Always test upgrades in a test environment before
# deploying to your production systems.
# - Isn't designed to upgrade an existing Docker installation. When using the
# script to update an existing installation, dependencies may not be updated
# to the expected version, resulting in outdated versions.
#
# Source code is available at https://github.com/docker/docker-install/
#
# Usage
# ==============================================================================
#
# To install the latest stable versions of Docker CLI, Docker Engine, and their
# dependencies:
#
# 1. download the script
#
# $ curl -fsSL https://get.docker.com -o install-docker.sh
#
# 2. verify the script's content
#
# $ cat install-docker.sh
#
# 3. run the script with --dry-run to verify the steps it executes
#
# $ sh install-docker.sh --dry-run
#
# 4. run the script either as root, or using sudo to perform the installation.
#
# $ sudo sh install-docker.sh
#
# Command-line options
# ==============================================================================
#
# --version <VERSION>
# Use the --version option to install a specific version, for example:
#
# $ sudo sh install-docker.sh --version 23.0
#
# --channel <stable|test>
#
# Use the --channel option to install from an alternative installation channel.
# The following example installs the latest versions from the "test" channel,
# which includes pre-releases (alpha, beta, rc):
#
# $ sudo sh install-docker.sh --channel test
#
# Alternatively, use the script at https://test.docker.com, which uses the test
# channel as default.
#
# --mirror <Aliyun|AzureChinaCloud>
#
# Use the --mirror option to install from a mirror supported by this script.
# Available mirrors are "Aliyun" (https://mirrors.aliyun.com/docker-ce), and
# "AzureChinaCloud" (https://mirror.azure.cn/docker-ce), for example:
#
# $ sudo sh install-docker.sh --mirror AzureChinaCloud
#
# ==============================================================================
# Git commit from https://github.com/docker/docker-install when
# the script was uploaded (Should only be modified by upload job):
SCRIPT_COMMIT_SHA="711a0d41213afabc30b963f82c56e1442a3efe1c"
# strip "v" prefix if present
VERSION="${VERSION#v}"
# The channel to install from:
# * stable
# * test
DEFAULT_CHANNEL_VALUE="stable"
if [ -z "$CHANNEL" ]; then
CHANNEL=$DEFAULT_CHANNEL_VALUE
fi
DEFAULT_DOWNLOAD_URL="https://download.docker.com"
if [ -z "$DOWNLOAD_URL" ]; then
DOWNLOAD_URL=$DEFAULT_DOWNLOAD_URL
fi
DEFAULT_REPO_FILE="docker-ce.repo"
if [ -z "$REPO_FILE" ]; then
REPO_FILE="$DEFAULT_REPO_FILE"
fi
mirror=''
DRY_RUN=${DRY_RUN:-}
while [ $# -gt 0 ]; do
case "$1" in
--channel)
CHANNEL="$2"
shift
;;
--dry-run)
DRY_RUN=1
;;
--mirror)
mirror="$2"
shift
;;
--version)
VERSION="${2#v}"
shift
;;
--*)
echo "Illegal option $1"
;;
esac
shift $(( $# > 0 ? 1 : 0 ))
done
case "$mirror" in
Aliyun)
DOWNLOAD_URL="https://mirrors.aliyun.com/docker-ce"
;;
AzureChinaCloud)
DOWNLOAD_URL="https://mirror.azure.cn/docker-ce"
;;
"")
;;
*)
>&2 echo "unknown mirror '$mirror': use either 'Aliyun', or 'AzureChinaCloud'."
exit 1
;;
esac
case "$CHANNEL" in
stable|test)
;;
*)
>&2 echo "unknown CHANNEL '$CHANNEL': use either stable or test."
exit 1
;;
esac
command_exists() {
command -v "$@" > /dev/null 2>&1
}
# version_gte checks if the version specified in $VERSION is at least the given
# SemVer (Maj.Minor[.Patch]), or CalVer (YY.MM) version.It returns 0 (success)
# if $VERSION is either unset (=latest) or newer or equal than the specified
# version, or returns 1 (fail) otherwise.
#
# examples:
#
# VERSION=23.0
# version_gte 23.0 // 0 (success)
# version_gte 20.10 // 0 (success)
# version_gte 19.03 // 0 (success)
# version_gte 26.1 // 1 (fail)
version_gte() {
if [ -z "$VERSION" ]; then
return 0
fi
version_compare "$VERSION" "$1"
}
# version_compare compares two version strings (either SemVer (Major.Minor.Path),
# or CalVer (YY.MM) version strings. It returns 0 (success) if version A is newer
# or equal than version B, or 1 (fail) otherwise. Patch releases and pre-release
# (-alpha/-beta) are not taken into account
#
# examples:
#
# version_compare 23.0.0 20.10 // 0 (success)
# version_compare 23.0 20.10 // 0 (success)
# version_compare 20.10 19.03 // 0 (success)
# version_compare 20.10 20.10 // 0 (success)
# version_compare 19.03 20.10 // 1 (fail)
version_compare() (
set +x
yy_a="$(echo "$1" | cut -d'.' -f1)"
yy_b="$(echo "$2" | cut -d'.' -f1)"
if [ "$yy_a" -lt "$yy_b" ]; then
return 1
fi
if [ "$yy_a" -gt "$yy_b" ]; then
return 0
fi
mm_a="$(echo "$1" | cut -d'.' -f2)"
mm_b="$(echo "$2" | cut -d'.' -f2)"
# trim leading zeros to accommodate CalVer
mm_a="${mm_a#0}"
mm_b="${mm_b#0}"
if [ "${mm_a:-0}" -lt "${mm_b:-0}" ]; then
return 1
fi
return 0
)
is_dry_run() {
if [ -z "$DRY_RUN" ]; then
return 1
else
return 0
fi
}
is_wsl() {
case "$(uname -r)" in
*microsoft* ) true ;; # WSL 2
*Microsoft* ) true ;; # WSL 1
* ) false;;
esac
}
is_darwin() {
case "$(uname -s)" in
*darwin* ) true ;;
*Darwin* ) true ;;
* ) false;;
esac
}
deprecation_notice() {
distro=$1
distro_version=$2
echo
printf "\033[91;1mDEPRECATION WARNING\033[0m\n"
printf " This Linux distribution (\033[1m%s %s\033[0m) reached end-of-life and is no longer supported by this script.\n" "$distro" "$distro_version"
echo " No updates or security fixes will be released for this distribution, and users are recommended"
echo " to upgrade to a currently maintained version of $distro."
echo
printf "Press \033[1mCtrl+C\033[0m now to abort this script, or wait for the installation to continue."
echo
sleep 10
}
get_distribution() {
lsb_dist=""
# Every system that we officially support has /etc/os-release
if [ -r /etc/os-release ]; then
lsb_dist="$(. /etc/os-release && echo "$ID")"
fi
# Returning an empty string here should be alright since the
# case statements don't act unless you provide an actual value
echo "$lsb_dist"
}
echo_docker_as_nonroot() {
if is_dry_run; then
return
fi
if command_exists docker && [ -e /var/run/docker.sock ]; then
(
set -x
$sh_c 'docker version'
) || true
fi
# intentionally mixed spaces and tabs here -- tabs are stripped by "<<-EOF", spaces are kept in the output
echo
echo "================================================================================"
echo
if version_gte "20.10"; then
echo "To run Docker as a non-privileged user, consider setting up the"
echo "Docker daemon in rootless mode for your user:"
echo
echo " dockerd-rootless-setuptool.sh install"
echo
echo "Visit https://docs.docker.com/go/rootless/ to learn about rootless mode."
echo
fi
echo
echo "To run the Docker daemon as a fully privileged service, but granting non-root"
echo "users access, refer to https://docs.docker.com/go/daemon-access/"
echo
echo "WARNING: Access to the remote API on a privileged Docker daemon is equivalent"
echo " to root access on the host. Refer to the 'Docker daemon attack surface'"
echo " documentation for details: https://docs.docker.com/go/attack-surface/"
echo
echo "================================================================================"
echo
}
# Check if this is a forked Linux distro
check_forked() {
# Check for lsb_release command existence, it usually exists in forked distros
if command_exists lsb_release; then
# Check if the `-u` option is supported
set +e
lsb_release -a -u > /dev/null 2>&1
lsb_release_exit_code=$?
set -e
# Check if the command has exited successfully, it means we're in a forked distro
if [ "$lsb_release_exit_code" = "0" ]; then
# Print info about current distro
cat <<-EOF
You're using '$lsb_dist' version '$dist_version'.
EOF
# Get the upstream release info
lsb_dist=$(lsb_release -a -u 2>&1 | tr '[:upper:]' '[:lower:]' | grep -E 'id' | cut -d ':' -f 2 | tr -d '[:space:]')
dist_version=$(lsb_release -a -u 2>&1 | tr '[:upper:]' '[:lower:]' | grep -E 'codename' | cut -d ':' -f 2 | tr -d '[:space:]')
# Print info about upstream distro
cat <<-EOF
Upstream release is '$lsb_dist' version '$dist_version'.
EOF
else
if [ -r /etc/debian_version ] && [ "$lsb_dist" != "ubuntu" ] && [ "$lsb_dist" != "raspbian" ]; then
if [ "$lsb_dist" = "osmc" ]; then
# OSMC runs Raspbian
lsb_dist=raspbian
else
# We're Debian and don't even know it!
lsb_dist=debian
fi
dist_version="$(sed 's/\/.*//' /etc/debian_version | sed 's/\..*//')"
case "$dist_version" in
12)
dist_version="bookworm"
;;
11)
dist_version="bullseye"
;;
10)
dist_version="buster"
;;
9)
dist_version="stretch"
;;
8)
dist_version="jessie"
;;
esac
fi
fi
fi
}
do_install() {
echo "# Executing docker install script, commit: $SCRIPT_COMMIT_SHA"
if command_exists docker; then
cat >&2 <<-'EOF'
Warning: the "docker" command appears to already exist on this system.
If you already have Docker installed, this script can cause trouble, which is
why we're displaying this warning and provide the opportunity to cancel the
installation.
If you installed the current Docker package using this script and are using it
again to update Docker, you can safely ignore this message.
You may press Ctrl+C now to abort this script.
EOF
( set -x; sleep 20 )
fi
user="$(id -un 2>/dev/null || true)"
sh_c='sh -c'
if [ "$user" != 'root' ]; then
if command_exists sudo; then
sh_c='sudo -E sh -c'
elif command_exists su; then
sh_c='su -c'
else
cat >&2 <<-'EOF'
Error: this installer needs the ability to run commands as root.
We are unable to find either "sudo" or "su" available to make this happen.
EOF
exit 1
fi
fi
if is_dry_run; then
sh_c="echo"
fi
# perform some very rudimentary platform detection
lsb_dist=$( get_distribution )
lsb_dist="$(echo "$lsb_dist" | tr '[:upper:]' '[:lower:]')"
if is_wsl; then
echo
echo "WSL DETECTED: We recommend using Docker Desktop for Windows."
echo "Please get Docker Desktop from https://www.docker.com/products/docker-desktop/"
echo
cat >&2 <<-'EOF'
You may press Ctrl+C now to abort this script.
EOF
( set -x; sleep 20 )
fi
case "$lsb_dist" in
ubuntu)
if command_exists lsb_release; then
dist_version="$(lsb_release --codename | cut -f2)"
fi
if [ -z "$dist_version" ] && [ -r /etc/lsb-release ]; then
dist_version="$(. /etc/lsb-release && echo "$DISTRIB_CODENAME")"
fi
;;
debian|raspbian)
dist_version="$(sed 's/\/.*//' /etc/debian_version | sed 's/\..*//')"
case "$dist_version" in
12)
dist_version="bookworm"
;;
11)
dist_version="bullseye"
;;
10)
dist_version="buster"
;;
9)
dist_version="stretch"
;;
8)
dist_version="jessie"
;;
esac
;;
centos|rhel)
if [ -z "$dist_version" ] && [ -r /etc/os-release ]; then
dist_version="$(. /etc/os-release && echo "$VERSION_ID")"
fi
;;
*)
if command_exists lsb_release; then
dist_version="$(lsb_release --release | cut -f2)"
fi
if [ -z "$dist_version" ] && [ -r /etc/os-release ]; then
dist_version="$(. /etc/os-release && echo "$VERSION_ID")"
fi
;;
esac
# Check if this is a forked Linux distro
check_forked
# Print deprecation warnings for distro versions that recently reached EOL,
# but may still be commonly used (especially LTS versions).
case "$lsb_dist.$dist_version" in
centos.8|centos.7|rhel.7)
deprecation_notice "$lsb_dist" "$dist_version"
;;
debian.buster|debian.stretch|debian.jessie)
deprecation_notice "$lsb_dist" "$dist_version"
;;
raspbian.buster|raspbian.stretch|raspbian.jessie)
deprecation_notice "$lsb_dist" "$dist_version"
;;
ubuntu.bionic|ubuntu.xenial|ubuntu.trusty)
deprecation_notice "$lsb_dist" "$dist_version"
;;
ubuntu.mantic|ubuntu.lunar|ubuntu.kinetic|ubuntu.impish|ubuntu.hirsute|ubuntu.groovy|ubuntu.eoan|ubuntu.disco|ubuntu.cosmic)
deprecation_notice "$lsb_dist" "$dist_version"
;;
fedora.*)
if [ "$dist_version" -lt 39 ]; then
deprecation_notice "$lsb_dist" "$dist_version"
fi
;;
esac
# Run setup for each distro accordingly
case "$lsb_dist" in
ubuntu|debian|raspbian)
pre_reqs="ca-certificates curl"
apt_repo="deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] $DOWNLOAD_URL/linux/$lsb_dist $dist_version $CHANNEL"
(
if ! is_dry_run; then
set -x
fi
$sh_c 'apt-get -qq update >/dev/null'
$sh_c "DEBIAN_FRONTEND=noninteractive apt-get -y -qq install $pre_reqs >/dev/null"
$sh_c 'install -m 0755 -d /etc/apt/keyrings'
$sh_c "curl -fsSL \"$DOWNLOAD_URL/linux/$lsb_dist/gpg\" -o /etc/apt/keyrings/docker.asc"
$sh_c "chmod a+r /etc/apt/keyrings/docker.asc"
$sh_c "echo \"$apt_repo\" > /etc/apt/sources.list.d/docker.list"
$sh_c 'apt-get -qq update >/dev/null'
)
pkg_version=""
if [ -n "$VERSION" ]; then
if is_dry_run; then
echo "# WARNING: VERSION pinning is not supported in DRY_RUN"
else
# Will work for incomplete versions IE (17.12), but may not actually grab the "latest" if in the test channel
pkg_pattern="$(echo "$VERSION" | sed 's/-ce-/~ce~.*/g' | sed 's/-/.*/g')"
search_command="apt-cache madison docker-ce | grep '$pkg_pattern' | head -1 | awk '{\$1=\$1};1' | cut -d' ' -f 3"
pkg_version="$($sh_c "$search_command")"
echo "INFO: Searching repository for VERSION '$VERSION'"
echo "INFO: $search_command"
if [ -z "$pkg_version" ]; then
echo
echo "ERROR: '$VERSION' not found amongst apt-cache madison results"
echo
exit 1
fi
if version_gte "18.09"; then
search_command="apt-cache madison docker-ce-cli | grep '$pkg_pattern' | head -1 | awk '{\$1=\$1};1' | cut -d' ' -f 3"
echo "INFO: $search_command"
cli_pkg_version="=$($sh_c "$search_command")"
fi
pkg_version="=$pkg_version"
fi
fi
(
pkgs="docker-ce${pkg_version%=}"
if version_gte "18.09"; then
# older versions didn't ship the cli and containerd as separate packages
pkgs="$pkgs docker-ce-cli${cli_pkg_version%=} containerd.io"
fi
if version_gte "20.10"; then
pkgs="$pkgs docker-compose-plugin docker-ce-rootless-extras$pkg_version"
fi
if version_gte "23.0"; then
pkgs="$pkgs docker-buildx-plugin"
fi
if ! is_dry_run; then
set -x
fi
$sh_c "DEBIAN_FRONTEND=noninteractive apt-get -y -qq install $pkgs >/dev/null"
)
echo_docker_as_nonroot
exit 0
;;
centos|fedora|rhel)
repo_file_url="$DOWNLOAD_URL/linux/$lsb_dist/$REPO_FILE"
(
if ! is_dry_run; then
set -x
fi
if command_exists dnf5; then
$sh_c "dnf -y -q --setopt=install_weak_deps=False install dnf-plugins-core"
$sh_c "dnf5 config-manager addrepo --save-filename=docker-ce.repo --from-repofile='$repo_file_url'"
if [ "$CHANNEL" != "stable" ]; then
$sh_c "dnf5 config-manager setopt \"docker-ce-*.enabled=0\""
$sh_c "dnf5 config-manager setopt \"docker-ce-$CHANNEL.enabled=1\""
fi
$sh_c "dnf makecache"
elif command_exists dnf; then
$sh_c "dnf -y -q --setopt=install_weak_deps=False install dnf-plugins-core"
$sh_c "dnf config-manager --add-repo $repo_file_url"
if [ "$CHANNEL" != "stable" ]; then
$sh_c "dnf config-manager --set-disabled \"docker-ce-*\""
$sh_c "dnf config-manager --set-enabled \"docker-ce-$CHANNEL\""
fi
$sh_c "dnf makecache"
else
$sh_c "yum -y -q install yum-utils"
$sh_c "yum-config-manager --add-repo $repo_file_url"
if [ "$CHANNEL" != "stable" ]; then
$sh_c "yum-config-manager --disable \"docker-ce-*\""
$sh_c "yum-config-manager --enable \"docker-ce-$CHANNEL\""
fi
$sh_c "yum makecache"
fi
)
pkg_version=""
if command_exists dnf; then
pkg_manager="dnf"
pkg_manager_flags="-y -q --best"
else
pkg_manager="yum"
pkg_manager_flags="-y -q"
fi
if [ -n "$VERSION" ]; then
if is_dry_run; then
echo "# WARNING: VERSION pinning is not supported in DRY_RUN"
else
if [ "$lsb_dist" = "fedora" ]; then
pkg_suffix="fc$dist_version"
else
pkg_suffix="el"
fi
pkg_pattern="$(echo "$VERSION" | sed 's/-ce-/\\\\.ce.*/g' | sed 's/-/.*/g').*$pkg_suffix"
search_command="$pkg_manager list --showduplicates docker-ce | grep '$pkg_pattern' | tail -1 | awk '{print \$2}'"
pkg_version="$($sh_c "$search_command")"
echo "INFO: Searching repository for VERSION '$VERSION'"
echo "INFO: $search_command"
if [ -z "$pkg_version" ]; then
echo
echo "ERROR: '$VERSION' not found amongst $pkg_manager list results"
echo
exit 1
fi
if version_gte "18.09"; then
# older versions don't support a cli package
search_command="$pkg_manager list --showduplicates docker-ce-cli | grep '$pkg_pattern' | tail -1 | awk '{print \$2}'"
cli_pkg_version="$($sh_c "$search_command" | cut -d':' -f 2)"
fi
# Cut out the epoch and prefix with a '-'
pkg_version="-$(echo "$pkg_version" | cut -d':' -f 2)"
fi
fi
(
pkgs="docker-ce$pkg_version"
if version_gte "18.09"; then
# older versions didn't ship the cli and containerd as separate packages
if [ -n "$cli_pkg_version" ]; then
pkgs="$pkgs docker-ce-cli-$cli_pkg_version containerd.io"
else
pkgs="$pkgs docker-ce-cli containerd.io"
fi
fi
if version_gte "20.10"; then
pkgs="$pkgs docker-compose-plugin docker-ce-rootless-extras$pkg_version"
fi
if version_gte "23.0"; then
pkgs="$pkgs docker-buildx-plugin"
fi
if ! is_dry_run; then
set -x
fi
$sh_c "$pkg_manager $pkg_manager_flags install $pkgs"
)
echo_docker_as_nonroot
exit 0
;;
sles)
if [ "$(uname -m)" != "s390x" ]; then
echo "Packages for SLES are currently only available for s390x"
exit 1
fi
repo_file_url="$DOWNLOAD_URL/linux/$lsb_dist/$REPO_FILE"
pre_reqs="ca-certificates curl libseccomp2 awk"
(
if ! is_dry_run; then
set -x
fi
$sh_c "zypper install -y $pre_reqs"
$sh_c "zypper addrepo $repo_file_url"
if ! is_dry_run; then
cat >&2 <<-'EOF'
WARNING!!
openSUSE repository (https://download.opensuse.org/repositories/security:/SELinux) will be enabled now.
Do you wish to continue?
You may press Ctrl+C now to abort this script.
EOF
( set -x; sleep 30 )
fi
opensuse_repo="https://download.opensuse.org/repositories/security:/SELinux/openSUSE_Factory/security:SELinux.repo"
$sh_c "zypper addrepo $opensuse_repo"
$sh_c "zypper --gpg-auto-import-keys refresh"
$sh_c "zypper lr -d"
)
pkg_version=""
if [ -n "$VERSION" ]; then
if is_dry_run; then
echo "# WARNING: VERSION pinning is not supported in DRY_RUN"
else
pkg_pattern="$(echo "$VERSION" | sed 's/-ce-/\\\\.ce.*/g' | sed 's/-/.*/g')"
search_command="zypper search -s --match-exact 'docker-ce' | grep '$pkg_pattern' | tail -1 | awk '{print \$6}'"
pkg_version="$($sh_c "$search_command")"
echo "INFO: Searching repository for VERSION '$VERSION'"
echo "INFO: $search_command"
if [ -z "$pkg_version" ]; then
echo
echo "ERROR: '$VERSION' not found amongst zypper list results"
echo
exit 1
fi
search_command="zypper search -s --match-exact 'docker-ce-cli' | grep '$pkg_pattern' | tail -1 | awk '{print \$6}'"
# It's okay for cli_pkg_version to be blank, since older versions don't support a cli package
cli_pkg_version="$($sh_c "$search_command")"
pkg_version="-$pkg_version"
fi
fi
(
pkgs="docker-ce$pkg_version"
if version_gte "18.09"; then
if [ -n "$cli_pkg_version" ]; then
# older versions didn't ship the cli and containerd as separate packages
pkgs="$pkgs docker-ce-cli-$cli_pkg_version containerd.io"
else
pkgs="$pkgs docker-ce-cli containerd.io"
fi
fi
if version_gte "20.10"; then
pkgs="$pkgs docker-compose-plugin docker-ce-rootless-extras$pkg_version"
fi
if version_gte "23.0"; then
pkgs="$pkgs docker-buildx-plugin"
fi
if ! is_dry_run; then
set -x
fi
$sh_c "zypper -q install -y $pkgs"
)
echo_docker_as_nonroot
exit 0
;;
*)
if [ -z "$lsb_dist" ]; then
if is_darwin; then
echo
echo "ERROR: Unsupported operating system 'macOS'"
echo "Please get Docker Desktop from https://www.docker.com/products/docker-desktop"
echo
exit 1
fi
fi
echo
echo "ERROR: Unsupported distribution '$lsb_dist'"
echo
exit 1
;;
esac
exit 1
}
# wrapped up in a function so that we have some protection against only getting
# half the file during "curl | sh"
do_install
+11 -20
View File
@@ -1,10 +1,12 @@
import os
import httpx
from github import Github
from github.GithubException import GithubException
from tenacity import retry, stop_after_attempt, wait_exponential
from openhands.core.logger import openhands_logger as logger
from openhands.server.sheets_client import GoogleSheetsClient
from openhands.utils.async_utils import call_sync_from_async
GITHUB_CLIENT_ID = os.getenv('GITHUB_CLIENT_ID', '').strip()
GITHUB_CLIENT_SECRET = os.getenv('GITHUB_CLIENT_SECRET', '').strip()
@@ -113,24 +115,13 @@ async def get_github_user(token: str) -> str:
github handle of the user
"""
logger.info('Fetching GitHub user info from token')
headers = {
'Accept': 'application/vnd.github+json',
'Authorization': f'Bearer {token}',
}
async with httpx.AsyncClient(
timeout=httpx.Timeout(connect=5.0, read=5.0, write=5.0, pool=5.0)
) as client:
try:
response = await client.get('https://api.github.com/user', headers=headers)
except httpx.RequestError as e:
logger.error(f'Error making request to GitHub API: {str(e)}')
logger.error(e)
raise
logger.info('Received response from GitHub API')
logger.debug(f'Response status code: {response.status_code}')
response.raise_for_status()
user_data = response.json()
login = user_data.get('login')
try:
g = Github(token)
user = await call_sync_from_async(g.get_user)
login = user.login
logger.info(f'Successfully retrieved GitHub user: {login}')
return login
except GithubException as e:
logger.error(f'Error making request to GitHub API: {str(e)}')
logger.error(e)
raise
Generated
+338 -314
View File
File diff suppressed because it is too large Load Diff
+9 -6
View File
@@ -28,7 +28,7 @@ uvicorn = "*"
types-toml = "*"
numpy = "*"
json-repair = "*"
browsergym = "0.13.0" # integrate browsergym as the browsing interface
browsergym = "0.10.2" # integrate browsergym as the browsing interface
html2text = "*"
e2b = "^0.17.1"
pexpect = "*"
@@ -37,7 +37,7 @@ python-multipart = "*"
boto3 = "*"
minio = "^7.2.8"
gevent = "^24.2.1"
pyarrow = "18.0.0" # transitive dependency, pinned here to avoid conflicts
pyarrow = "17.0.0" # transitive dependency, pinned here to avoid conflicts
tenacity = "^8.5.0"
zope-interface = "7.1.1"
pathspec = "^0.12.1"
@@ -60,20 +60,21 @@ whatthepatch = "^1.0.6"
protobuf = "^4.21.6,<5.0.0" # chromadb currently fails on 5.0+
opentelemetry-api = "1.25.0"
opentelemetry-exporter-otlp-proto-grpc = "1.25.0"
modal = ">=0.64.145,<0.66.0"
runloop-api-client = "0.10.0"
modal = "^0.64.145"
runloop-api-client = "0.7.0"
pygithub = "^2.5.0"
[tool.poetry.group.llama-index.dependencies]
llama-index = "*"
llama-index-vector-stores-chroma = "*"
chromadb = "*"
llama-index-embeddings-huggingface = "*"
torch = "2.5.1"
torch = "2.5.0"
llama-index-embeddings-azure-openai = "*"
llama-index-embeddings-ollama = "*"
[tool.poetry.group.dev.dependencies]
ruff = "0.7.3"
ruff = "0.7.1"
mypy = "1.13.0"
pre-commit = "4.0.1"
build = "*"
@@ -93,6 +94,7 @@ reportlab = "*"
[tool.coverage.run]
concurrency = ["gevent"]
[tool.poetry.group.runtime.dependencies]
jupyterlab = "*"
notebook = "*"
@@ -123,6 +125,7 @@ ignore = ["D1"]
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.poetry.group.evaluation.dependencies]
streamlit = "*"
whatthepatch = "*"
+64 -40
View File
@@ -544,59 +544,83 @@ def _format_size_to_gb(bytes_size):
def test_list_dangling_images():
mock_client = MagicMock()
mock_client.images.list.return_value = []
with patch('docker.from_env', return_value=mock_client):
client = docker.from_env()
dangling_images = client.images.list(filters={'dangling': True})
assert len(dangling_images) == 0
client = docker.from_env()
dangling_images = client.images.list(filters={'dangling': True})
if dangling_images and len(dangling_images) > 0:
for image in dangling_images:
if 'Size' in image.attrs and isinstance(image.attrs['Size'], int):
size_gb = _format_size_to_gb(image.attrs['Size'])
logger.info(f'Dangling image: {image.tags}, Size: {size_gb} GB')
else:
logger.info(f'Dangling image: {image.tags}, Size: n/a')
else:
logger.info('No dangling images found')
def test_build_image_from_repo(tmp_path):
mock_client = MagicMock()
mock_client.images.build.return_value = (MagicMock(), [])
with patch('docker.from_env', return_value=mock_client):
docker_runtime_builder = DockerRuntimeBuilder(mock_client)
context_path = str(tmp_path)
tags = ['alpine:latest']
def test_build_image_from_repo(docker_runtime_builder, tmp_path):
context_path = str(tmp_path)
tags = ['alpine:latest']
# Create a minimal Dockerfile in the context path
with open(os.path.join(context_path, 'Dockerfile'), 'w') as f:
f.write(f"""FROM {DEFAULT_BASE_IMAGE}
# Create a minimal Dockerfile in the context path
with open(os.path.join(context_path, 'Dockerfile'), 'w') as f:
f.write(f"""FROM {DEFAULT_BASE_IMAGE}
CMD ["sh", "-c", "echo 'Hello, World!'"]
""")
# Build the image
built_image_name = docker_runtime_builder.build(context_path, tags=tags)
assert built_image_name == tags[0]
mock_client.images.build.assert_called_once_with(
path=context_path,
tag=tags[0],
rm=True,
forcerm=True,
platform=None,
decode=True,
built_image_name = None
container = None
client = docker.from_env()
try:
built_image_name = docker_runtime_builder.build(
context_path,
tags,
use_local_cache=False,
)
assert built_image_name == f'{tags[0]}'
image = client.images.get(tags[0])
assert image is not None
except docker.errors.ImageNotFound:
pytest.fail('test_build_image_from_repo: test image not found!')
finally:
# Clean up the container
if container:
try:
container.remove(force=True)
logger.info(f'Removed test container: `{container.id}`')
except Exception as e:
logger.warning(
f'Failed to remove test container `{container.id}`: {str(e)}'
)
# Clean up the image
if built_image_name:
try:
client.images.remove(built_image_name, force=True)
logger.info(f'Removed test image: `{built_image_name}`')
except Exception as e:
logger.warning(
f'Failed to remove test image `{built_image_name}`: {str(e)}'
)
else:
logger.warning('No image was built, so no image cleanup was necessary.')
def test_image_exists_local():
def test_image_exists_local(docker_runtime_builder):
mock_client = MagicMock()
mock_client.images.get.return_value = MagicMock()
with patch('docker.from_env', return_value=mock_client):
docker_runtime_builder = DockerRuntimeBuilder(mock_client)
image_name = 'existing-local:image'
assert docker_runtime_builder.image_exists(image_name)
mock_client.images.get.assert_called_once_with(image_name)
mock_client.version().get.return_value = '18.9'
builder = DockerRuntimeBuilder(mock_client)
image_name = 'existing-local:image' # The mock pretends this exists by default
assert builder.image_exists(image_name)
def test_image_exists_not_found():
mock_client = MagicMock()
mock_client.images.get.side_effect = docker.errors.ImageNotFound('not found')
with patch('docker.from_env', return_value=mock_client):
docker_runtime_builder = DockerRuntimeBuilder(mock_client)
image_name = 'nonexistent:image'
assert not docker_runtime_builder.image_exists(image_name)
mock_client.images.get.assert_called_once_with(image_name)
mock_client.version().get.return_value = '18.9'
mock_client.images.get.side_effect = docker.errors.ImageNotFound(
"He doesn't like you!"
)
mock_client.api.pull.side_effect = docker.errors.ImageNotFound(
"I don't like you either!"
)
+50 -142
View File
@@ -49,56 +49,24 @@ def add_events(event_stream: EventStream, data: list[tuple[Event, EventSource]])
def test_msg(temp_dir: str):
mock_container = MagicMock()
mock_container.status = 'running'
mock_container.attrs = {
'NetworkSettings': {'Ports': {'8000/tcp': [{'HostPort': 34567}]}}
}
mock_docker = MagicMock()
mock_docker.from_env().containers.list.return_value = [mock_container]
mock_requests = MagicMock()
mock_requests.get().json.return_value = {'id': 'mock-session-id'}
mock_requests.post().json.side_effect = [
{'monitor_id': 'mock-monitor-id'},
[],
[],
[],
[],
[],
[],
[],
[
'PolicyViolation(Disallow ABC [risk=medium], ranges=[<2 ranges>])'
],
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
raise "Disallow ABC [risk=medium]" if:
(msg: Message)
"ABC" in msg.content
"""
InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(MessageAction('AB!'), EventSource.AGENT),
(MessageAction('Hello world!'), EventSource.USER),
(MessageAction('ABC!'), EventSource.AGENT),
]
with (
patch(f'{InvariantAnalyzer.__module__}.docker', mock_docker),
patch(f'{InvariantClient.__module__}.requests', mock_requests),
):
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
raise "Disallow ABC [risk=medium]" if:
(msg: Message)
"ABC" in msg.content
"""
analyzer = InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(MessageAction('AB!'), EventSource.AGENT),
(MessageAction('Hello world!'), EventSource.USER),
(MessageAction('ABC!'), EventSource.AGENT),
]
for event, source in data:
event.security_risk = ActionSecurityRisk.LOW
event_stream.add_event(event, source)
if event.content == 'ABC!':
event.security_risk = ActionSecurityRisk.MEDIUM
for i in range(3):
assert data[i][0].security_risk == ActionSecurityRisk.LOW
assert data[3][0].security_risk == ActionSecurityRisk.MEDIUM
add_events(event_stream, data)
for i in range(3):
assert data[i][0].security_risk == ActionSecurityRisk.LOW
assert data[3][0].security_risk == ActionSecurityRisk.MEDIUM
@pytest.mark.parametrize(
@@ -106,51 +74,22 @@ def test_msg(temp_dir: str):
[('rm -rf root_dir', ActionSecurityRisk.MEDIUM), ['ls', ActionSecurityRisk.LOW]],
)
def test_cmd(cmd, expected_risk, temp_dir: str):
mock_container = MagicMock()
mock_container.status = 'running'
mock_container.attrs = {
'NetworkSettings': {'Ports': {'8000/tcp': [{'HostPort': 34567}]}}
}
mock_docker = MagicMock()
mock_docker.from_env().containers.list.return_value = [mock_container]
mock_requests = MagicMock()
mock_requests.get().json.return_value = {'id': 'mock-session-id'}
mock_requests.post().json.side_effect = [
{'monitor_id': 'mock-monitor-id'},
[],
[],
[],
[
'PolicyViolation(Disallow rm -rf [risk=medium], ranges=[<2 ranges>])'
if expected_risk == ActionSecurityRisk.MEDIUM else []
],
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
raise "Disallow rm -rf [risk=medium]" if:
(call: ToolCall)
call is tool:run
match("rm -rf", call.function.arguments.command)
"""
InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(CmdRunAction(cmd), EventSource.USER),
]
with (
patch(f'{InvariantAnalyzer.__module__}.docker', mock_docker),
patch(f'{InvariantClient.__module__}.requests', mock_requests),
):
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
raise "Disallow rm -rf [risk=medium]" if:
(call: ToolCall)
call is tool:run
match("rm -rf", call.function.arguments.command)
"""
analyzer = InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(CmdRunAction(cmd), EventSource.USER),
]
for event, source in data:
event.security_risk = ActionSecurityRisk.LOW
event_stream.add_event(event, source)
if isinstance(event, CmdRunAction) and 'rm -rf' in event.command:
event.security_risk = ActionSecurityRisk.MEDIUM
assert data[0][0].security_risk == ActionSecurityRisk.LOW
assert data[1][0].security_risk == expected_risk
add_events(event_stream, data)
assert data[0][0].security_risk == ActionSecurityRisk.LOW
assert data[1][0].security_risk == expected_risk
@pytest.mark.parametrize(
@@ -161,57 +100,26 @@ def test_cmd(cmd, expected_risk, temp_dir: str):
],
)
def test_leak_secrets(code, expected_risk, temp_dir: str):
mock_container = MagicMock()
mock_container.status = 'running'
mock_container.attrs = {
'NetworkSettings': {'Ports': {'8000/tcp': [{'HostPort': 34567}]}}
}
mock_docker = MagicMock()
mock_docker.from_env().containers.list.return_value = [mock_container]
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
from invariant.detectors import secrets
mock_requests = MagicMock()
mock_requests.get().json.return_value = {'id': 'mock-session-id'}
mock_requests.post().json.side_effect = [
{'monitor_id': 'mock-monitor-id'},
[],
[],
[],
[],
[],
[
'PolicyViolation(Disallow writing secrets [risk=medium], ranges=[<2 ranges>])'
if expected_risk == ActionSecurityRisk.MEDIUM else []
],
raise "Disallow writing secrets [risk=medium]" if:
(call: ToolCall)
call is tool:run_ipython
any(secrets(call.function.arguments.code))
"""
InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(IPythonRunCellAction(code), EventSource.AGENT),
(IPythonRunCellAction('hello'), EventSource.AGENT),
]
with (
patch(f'{InvariantAnalyzer.__module__}.docker', mock_docker),
patch(f'{InvariantClient.__module__}.requests', mock_requests),
):
file_store = get_file_store('local', temp_dir)
event_stream = EventStream('main', file_store)
policy = """
from invariant.detectors import secrets
raise "Disallow writing secrets [risk=medium]" if:
(call: ToolCall)
call is tool:run_ipython
any(secrets(call.function.arguments.code))
"""
analyzer = InvariantAnalyzer(event_stream, policy)
data = [
(MessageAction('Hello world!'), EventSource.USER),
(IPythonRunCellAction(code), EventSource.AGENT),
(IPythonRunCellAction('hello'), EventSource.AGENT),
]
for event, source in data:
event.security_risk = ActionSecurityRisk.LOW
event_stream.add_event(event, source)
if isinstance(event, IPythonRunCellAction) and 'AKIAIOSFODNN7EXAMPLE' in event.code:
event.security_risk = ActionSecurityRisk.MEDIUM
assert data[0][0].security_risk == ActionSecurityRisk.LOW
assert data[1][0].security_risk == expected_risk
assert data[2][0].security_risk == ActionSecurityRisk.LOW
add_events(event_stream, data)
assert data[0][0].security_risk == ActionSecurityRisk.LOW
assert data[1][0].security_risk == expected_risk
assert data[2][0].security_risk == ActionSecurityRisk.LOW
def test_unsafe_python_code(temp_dir: str):