agentscope

AgentScope 2.0 is released!

Please refer to the new docs for more information.

What's Changed

• chore(project): temporarily deprecate evaluate/module/rag/tts/realtime modules pending refactor by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1438
• refactor(msg): simplify core building blocks and Msg class structure by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1440
• feat(msg): formalize Msg type rules and constraints and add message related tests by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1454
• feat(permission): build the basic permission classes by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1486
• refactor(tool): refactor the tool module, including providing new base class and toolkit logic by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1493
• ci(mcp): refactor the previous MCP unittests for the new version by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1505
• feat(tool): implement builtin tools with ToolBase inheritance and add comprehensive tests by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1502
• refactor(skill): refactor the skill in the toolkit by adding a new skill loader class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1513
• feat(agent): implement permission checking logic within the agent class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1518
• feat(context): support context compression in Agent class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1544
• feat(task): add task related tools in agentscope 2.0 by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1549
• refactor(mcp): rename the mcp when registered into the toolkit by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1552
• refactor(mcp): unify the MCP implementation into a MCPClient class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1572
• feat(middleware): support 2.0 middlewares in the agent class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1565
• feat(context): support tool result compact within the Agent class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1585
• feat(workspace): built the workspace module in agentscope 2.0 by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1586
• refactor(model): refactor the chat model implementation by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1564
• factor(tool): refactor the tool_choice argument to support advanced prompt cache in OpenAI response API by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1524
• feat(scripts): add scripts for model call by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1604
• feat(model): add cache_creation_input_tokens and cache_input_tokens in ChatUsage by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1602
• fix(dashscope): fix KeyError in dashscope response by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1615
• refactor(model): refactor dashscope model to openai compatible by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1617
• refactor: rename kimi to moonshot by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1609
• refactor(tracing): refactor tracing module, except model and formatter by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1579
• fix(formatter): refine formatters and unittest by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1621
• feat(service): implement the FastAPI based agent service by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1568
• feat(trace): add trace as a middleware by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1633
• feat(model): uniform thinking tag by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1622
• fix(model): refine _format_tools for openai response model by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1635
• fix(scripts): assign a list of textblock to the content instead of a string by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1629
• fix(mcp): preserve $defs in MCPTool input schema and strip titles recursively by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1595
• feat(model): handle audio output for openai by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1623
• feat(msg): add usage in msg by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1639
• feat(tool): integrate the tool and workspace modules with the Agent class by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1642
• feat(model): fix dashscope structured output and add examples by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1651
• fix(formatter): download remote image URLs to base64 for Moonshot by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1653
• fix(tool): close .env bypass gap and refine dangerous-path API for Write/Edit/Bash by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/1656
• refactor(workspace): support e2b and docker workspace, as well as their managers by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1650
• docs(readme): udpate the docs for 2.0 release by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1657
• chore(version): update the version to 2.0.0 and release to PyPI by @DavdGao in https://github.com/agentscope-ai/agentscope/pull/1658

Full Changelog: https://github.com/agentscope-ai/agentscope/compare/v1.0.21...v2.0.0