AgentScope 发布: v2.0.4

来源摘要

## Highlight **Agent** - Support agent interruption with context handling #1995 **Longterm Memory Integration** - Integrate ReMe based longterm memory #1972 - Integrate agentic longterm memory #1927 **TTS** - Support OpenAI TTS API #1878 - Support DashScope CosyVoice TTS API #1866 **RAG** - Support Milvus Lite VDB #1969 **Agent Service** - Support `AgentInvite` to import existing agent as team member, i.e. supporting p2p communication between agents - Add session status endpoint #1984 - Support agent interruption in agent service backend & frontend #1995 ## What's Changed * fix: prevent duplicate credential registration in CredentialFactory by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1964 * fix(tool): reject negative grep pagination values by @VectorPeak in https://github.com/agentscope-ai/agentscope/pull/1954 * feat(middleware): add file-based long-term memory middleware by @y1y5 in https://github.com/agentscope-ai/agentscope/pull/1927 * refactor(workspace): re-organize the code implementation logic of the workspace by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1971 * fix(agent): preserve middleware kwargs across next handlers by @h2h2h in https://github.com/agentscope-ai/agentscope/pull/1966 * fix(agent): guard against empty or interrupted streaming responses by @xueshanfeihu007 in https://github.com/agentscope-ai/agentscope/pull/1861 * fix(model): use flat estimate for multimodal data blocks by @dongfeng3692 in https://github.com/agentscope-ai/agentscope/pull/1899 * feat: add DashScope CosyVoice TTS model by @YingchaoX in https://github.com/agentscope-ai/agentscope/pull/1866 * feat(rag): add Milvus Lite vector store by @Trefoi1 in https://github.com/agentscope-ai/agentscope/pull/1969 * fix(agent): emit ThinkingBlockEnd before Tex