追踪 AI Agent、MCP、模型连接工具、智能体框架和自动化工作流。
## 🚀 What's New in v1.14.1? v1.14.1 is a patch release focused on security hardening, workflow and knowledge-base stability, deployment cleanup, and continued UI platform migration after v1.14.0. ### 🔐 Security - **Self-hosted `SECRET_KEY` hardening** — Dock
## What's Changed * fix(soul): clear partial UI output when LLM step is retried by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2177 * fix(tests): unbreak main CI after #2177 by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2213 * fix(shel
Explore how AlphaEvolve's Gemini-powered algorithms are driving impact across business, infrastructure, and science.
## What's Changed * fix(clipboard): enable clipboard paste on headless Linux over SSH by @ZichenWen1 in https://github.com/MoonshotAI/kimi-cli/pull/2115 * fix(plugin): support installing from .zip URL by @tempurai in https://github.com/MoonshotAI/kimi-cli/pull
## 🚀 What's New in v1.14.0? ### Collaboration Collaboration allows workspace members to edit the same workflow together, with synced graph updates, online presence, and shared visibility into who is working where. On self-hosted deployments, collaboration is
Details: Cherry pick a bug fixing from master branch commit ID: 2f0404d Tickets: CVS-184283 AI Assistance: AI assistance used: yes If yes, summarize how AI was used and what human validation was performed (build/tests/manual checks). Use the github agent to ch
With the following crawler configuration: ```python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader( url=url, max_depth=2, extractor=lambda x: Soup(x, "html.parser").text ) docs = loader.load() ``` An attacker in c
## Context A serialization injection vulnerability exists in LangChain JS's `toJSON()` method (and subsequently when string-ifying objects using `JSON.stringify()`. The method did not escape objects with `'lc'` keys when serializing free-form data in kwargs. T
## What's Changed * Fix docs dotnet core typo by @lach-g in https://github.com/microsoft/autogen/pull/6950 * Fix loading streaming Bedrock response with tool usage with empty argument by @pawel-dabro in https://github.com/microsoft/autogen/pull/6979 * Support
来源标注日期：2025-09-22（未提供具体时刻）。 Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1-Terminus. deepseek-chat corresponds to DeepSeek-V3.1-Terminus's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode. This update ma
来源标注日期：2025-08-21（未提供具体时刻）。 Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1. deepseek-chat corresponds to DeepSeek-V3.1's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode. Key updates in DeepSeek-V3.1: Hy
## What's Changed * Update docs for 0.7.3 by @ekzhu in https://github.com/microsoft/autogen/pull/6948 * Update readme with agent-as-tool by @ekzhu in https://github.com/microsoft/autogen/pull/6949 * Fix Redis Deserialization Error by @BenConstable9 in https://
## What's Changed * Update website for 0.7.2 by @ekzhu in https://github.com/microsoft/autogen/pull/6902 * Typo in docs for 'NoOpTracerProvider' by @nicsuzor in https://github.com/microsoft/autogen/pull/6915 * Fix MCP example in readme by @ekzhu in https://git
## What's Changed * Update website 0.7.1 by @ekzhu in https://github.com/microsoft/autogen/pull/6869 * Update OpenAIAssistantAgent doc by @ekzhu in https://github.com/microsoft/autogen/pull/6870 * Update 0.7.1 website ref by @ekzhu in https://github.com/micros
## What's New ### `OpenAIAgent` supports all built-in tools * Feat/OpenAI agent builtin tools 6657 by @tejas-dharani in https://github.com/microsoft/autogen/pull/6671 ### Support nested `Team` as a participant in a `Team` * Supporting Teams as Participants in
# What's New More helps from @copilot-swe-agent for this release. ### Improvements to `GraphFlow` Now it behaves the same way as `RoundRobinGroupChat`, `SelectorGroupChat` and others after termination condition hits -- it retains its execution state and can be
## What's New ### Streaming Tools This release introduces streaming tools and updates `AgentTool` and `TeamTool` to support `run_json_stream`. The new interface exposes the inner events of tools when calling `run_stream` of agents and teams. `AssistantAgent` i
## Bug Fixes * Fix bug in GraphFlow cycle check by @ekzhu in https://github.com/microsoft/autogen/pull/6629 * Fix graph validation logic and add tests by @ekzhu in https://github.com/microsoft/autogen/pull/6630 ## Others * Add list of function calls and result
## What's New ### Change to `BaseGroupChatManager.select_speaker` and support for concurrent agents in `GraphFlow` We made a type hint change to the `select_speaker` method of `BaseGroupChatManager` to allow for a list of agent names as a return value. This ma
## What's New ### `AzureAISearchTool` Improvements The Azure AI Search Tool API now features unified methods: - `create_full_text_search()` (supporting `"simple"`, `"full"`, and `"semantic"` query types) - `create_vector_search()` and - `create_hybrid_search()
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all
Denial of service in `SitemapLoader` Document Loader in the `langchain-community` package, affecting versions below 0.2.5. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a
A path traversal vulnerability exists in the `getFullPath` method of langchain-ai/langchainjs version 0.2.5. This vulnerability allows attackers to save files anywhere in the filesystem, overwrite existing text files, read `.txt` files, and delete files. The v
langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory ('Path Traversal') in its LocalFileStore functionality. An attacker can leverage this vulnerability to read or write files anywhere on the
LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub rep
In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.
