docs: update changelog and version for v1.14.4
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Vulnerability Scan / pip-audit (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Nightly Canary Release / Check for new commits (push) Has been cancelled
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled

This commit is contained in:
Greyson LaLonde
2026-05-01 03:11:30 +08:00
committed by GitHub
parent 2c0323c3fe
commit 898f860916
5 changed files with 2053 additions and 4 deletions

View File

@@ -4,6 +4,47 @@ description: "تحديثات المنتج والتحسينات وإصلاحات
icon: "clock"
mode: "wide"
---
<Update label="1 مايو 2026">
## v1.14.4
[عرض الإصدار على GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
## ما الذي تغير
### الميزات
- إضافة دعم لمفتاح الاستمرارية المخصص في @persist
- إضافة دعم واجهة برمجة التطبيقات للردود لمزود Azure OpenAI
- تمرير credential_scopes إلى عميل Azure AI Inference
- إضافة دليل إعداد هوية عبء العمل لـ Vertex AI
- إضافة Tavily Research والحصول على Research
- إضافة أدوات MCP من You.com للبحث، البحث، واستخراج المحتوى
### إصلاحات الأخطاء
- إصلاح مشكلة السقوط عند عدم تطابق تعبير JSON regex مع JSON صالح
- إصلاح للحفاظ على tool_calls عندما تحتوي الاستجابة أيضًا على نص
- إصلاح لتمرير base_url و api_key إلى instructor.from_provider
- إصلاح لتحذير وإرجاع فارغ عندما لا يُرجع خادم MCP الأصلي أي أدوات
- إصلاح لاستخدام متغير الرسائل الموثقة في معالجات غير البث
- إصلاح لحماية مساعدي وصف دردشة الطاقم ضد فشل LLM
- إصلاح لإعادة تعيين الرسائل والتكرارات بين الاستدعاءات
- إصلاح لتمرير ملف trained-agents من خلال replay و test
- إصلاح لاحترام ملف trained-agents المخصص في الاستدلال
- إصلاح لربط الوكلاء المخصصين بالمهام فقط بالطاقم لملفات الإدخال متعددة الأنماط
- إصلاح لتسلسل callable الحواجز كـ null لتسجيل JSON
- إصلاح إعادة تسمية force_final_answer لتجنب توجيه ذاتي
- إصلاح زيادة litellm لإصلاح SSTI؛ تجاهل CVE غير القابل للإصلاح في pip
### الوثائق
- تحديث سجل التغييرات والإصدار لـ v1.14.4a1
- إضافة صفحة أدوات E2B Sandbox
- إضافة وثائق أدوات صندوق Daytona
## المساهمون
@EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
</Update>
<Update label="29 أبريل 2026">
## v1.14.4a1

File diff suppressed because it is too large Load Diff

View File

@@ -4,6 +4,47 @@ description: "Product updates, improvements, and bug fixes for CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="May 01, 2026">
## v1.14.4
[View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
## What's Changed
### Features
- Add support for custom persistence key in @persist
- Add Responses API support for Azure OpenAI provider
- Forward credential_scopes to Azure AI Inference client
- Add Vertex AI workload identity setup guide
- Add Tavily Research and get Research
- Add You.com MCP tools for search, research, and content extraction
### Bug Fixes
- Fix fall through when JSON regex match isn't valid JSON
- Fix to preserve tool_calls when response also contains text
- Fix to forward base_url and api_key to instructor.from_provider
- Fix to warn and return empty when native MCP server returns no tools
- Fix to use validated messages variable in non-streaming handlers
- Fix to guard crew chat description helpers against LLM failures
- Fix to reset messages and iterations between invocations
- Fix to forward trained-agents file through replay and test
- Fix to honor custom trained-agents file at inference
- Fix to bind task-only agents to crew for multimodal input_files
- Fix to serialize guardrail callables as null for JSON checkpointing
- Fix renaming of force_final_answer to avoid self-referential router
- Fix bump of litellm for SSTI fix; ignore unfixable pip CVE
### Documentation
- Update changelog and version for v1.14.4a1
- Add E2B Sandbox Tools page
- Add Daytona sandbox tools documentation
## Contributors
@EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
</Update>
<Update label="Apr 29, 2026">
## v1.14.4a1

View File

@@ -4,6 +4,47 @@ description: "CrewAI의 제품 업데이트, 개선 사항 및 버그 수정"
icon: "clock"
mode: "wide"
---
<Update label="2026년 5월 1일">
## v1.14.4
[GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
## 변경 사항
### 기능
- @persist에서 사용자 정의 지속성 키 지원 추가
- Azure OpenAI 공급자를 위한 응답 API 지원 추가
- Azure AI 추론 클라이언트에 credential_scopes 전달
- Vertex AI 작업 부하 신원 설정 가이드 추가
- Tavily Research 및 Research 가져오기 추가
- 검색, 연구 및 콘텐츠 추출을 위한 You.com MCP 도구 추가
### 버그 수정
- JSON 정규 표현식이 유효한 JSON이 아닐 때의 fall through 수정
- 응답에 텍스트가 포함될 때 tool_calls를 보존하도록 수정
- instructor.from_provider에 base_url 및 api_key를 전달하도록 수정
- 기본 MCP 서버가 도구를 반환하지 않을 때 경고하고 빈 값을 반환하도록 수정
- 비스트리밍 핸들러에서 검증된 메시지 변수를 사용하도록 수정
- LLM 실패에 대한 크루 채팅 설명 도우미를 보호하도록 수정
- 호출 간 메시지 및 반복을 재설정하도록 수정
- replay 및 test를 통해 훈련된 에이전트 파일을 전달하도록 수정
- 추론 시 사용자 정의 훈련된 에이전트 파일을 존중하도록 수정
- 다중 모드 input_files에 대해 작업 전용 에이전트를 크루에 바인딩하도록 수정
- JSON 체크포인팅을 위해 가드레일 호출 가능 항목을 null로 직렬화하도록 수정
- 자기 참조 라우터를 피하기 위해 force_final_answer의 이름 변경 수정
- SSTI 수정을 위한 litellm 버전 증가; 수정할 수 없는 pip CVE 무시
### 문서
- v1.14.4a1에 대한 변경 로그 및 버전 업데이트
- E2B 샌드박스 도구 페이지 추가
- Daytona 샌드박스 도구 문서 추가
## 기여자
@EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
</Update>
<Update label="2026년 4월 29일">
## v1.14.4a1

View File

@@ -4,6 +4,47 @@ description: "Atualizações de produto, melhorias e correções do CrewAI"
icon: "clock"
mode: "wide"
---
<Update label="01 mai 2026">
## v1.14.4
[Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/1.14.4)
## O que mudou
### Recursos
- Adicionar suporte para chave de persistência personalizada em @persist
- Adicionar suporte à API de Respostas para o provedor Azure OpenAI
- Encaminhar credential_scopes para o cliente de Inferência da Azure AI
- Adicionar guia de configuração de identidade de carga de trabalho do Vertex AI
- Adicionar Tavily Research e obter Pesquisa
- Adicionar ferramentas MCP do You.com para pesquisa, pesquisa e extração de conteúdo
### Correções de Bugs
- Corrigir falha quando a correspondência de regex JSON não é um JSON válido
- Corrigir para preservar tool_calls quando a resposta também contém texto
- Corrigir para encaminhar base_url e api_key para instructor.from_provider
- Corrigir para avisar e retornar vazio quando o servidor MCP nativo não retorna ferramentas
- Corrigir para usar a variável de mensagens validadas em manipuladores não-streaming
- Corrigir para proteger os ajudantes de descrição do chat da equipe contra falhas do LLM
- Corrigir para redefinir mensagens e iterações entre invocações
- Corrigir para encaminhar o arquivo de agentes treinados através de replay e teste
- Corrigir para honrar o arquivo de agentes treinados personalizados na inferência
- Corrigir para vincular agentes apenas de tarefa à equipe para arquivos de entrada multimodal
- Corrigir para serializar chamadas de guardrail como nulas para checkpointing JSON
- Corrigir renomeação de force_final_answer para evitar roteador autorreferencial
- Corrigir aumento de litellm para correção de SSTI; ignorar CVE pip não corrigível
### Documentação
- Atualizar changelog e versão para v1.14.4a1
- Adicionar página de Ferramentas do Sandbox E2B
- Adicionar documentação de ferramentas do sandbox Daytona
## Contributors
@EdwardIrby, @dependabot[bot], @factory-droid-oss, @factory-droid[bot], @greysonlalonde, @kunalk16, @lorenzejay, @lucasgomide, @manisrinivasan2k1, @mattatcha, @vinibrsl
</Update>
<Update label="29 abr 2026">
## v1.14.4a1