AgentScope 发布: v2.0.3

来源摘要

## Major New Features **RAG Module** - Introduced a native RAG (Retrieval-Augmented Generation) module with full support for distributed, multi-tenant, and multi-session RAG services, significantly enhancing knowledge retrieval capabilities. **Long-Term Memory Middleware** - Added a mem0-backed long-term memory middleware, enabling agents to retain persistent memory across sessions. **Budget Control Middleware** - Introduced BudgetControlMiddleware for enforcing token budget limits, helping teams manage and control API costs effectively. **Tool-Level Onion Middleware** - ToolBase now supports onion-style middleware at the tool level, allowing flexible pre/post-processing logic to be injected around tool execution. ## What's Changed * fix(dashscope): correct qwen max 3.7 model id by @Rise1024 in https://github.com/agentscope-ai/agentscope/pull/1876 * feat(middleware): add mem0-backed long-term memory middleware by @Osier-Yi in https://github.com/agentscope-ai/agentscope/pull/1775 * fix(model): handle Gemini function calls without an id by @he-yufeng in https://github.com/agentscope-ai/agentscope/pull/1883 * feat(middleware): add BudgetControlMiddleware for token budget enforcement by @MannXo in https://github.com/agentscope-ai/agentscope/pull/1738 * feat(tts): add cosyvoice realtime tts model by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1855 * feat(model): add gpt-4o, gpt-4o-mini, and gpt-4.1-nano cards for openai-response by @nuthalapativarun in https://github.com/agentscope-ai/agentscope/pull/1750 * fix(schema): remove max_length constraints from SummarySchema fields and increase tool result limit by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1891 * fix(gemini): add _sanitize_schema_for_gemini to strip Gemini-incompatible JSON Schem