v1.0.19

What's Changed

• docs(copaw): add news for copaw by @qbc2016 in #1379
• feat(formatter): support local multimedia paths starting with file:// by @qbc2016 in #1385
• feat(memory): add tablestore memory support by @zhanghaochenFCB in #1308
• fix(examples): rename ReflectFailure.decompose_subtask.rephrased_plan to failed_subtask in deep research example by @alex-xinlu in #1151
• docs(news): update the news for 2.0 by @DavdGao in #1442
• chore(assets): update the png by @DavdGao in #1468
• fix(agent): add missing await on memory.add in DeepResearchAgent._summarizing by @Ricardo-M-L in #1477
• fix: handle missing 'type' field in tool parameter properties for OpenAITokenCounter by @octo-patch in #1403
• fix(agent): handle thinking blocks in DeepResearchAgent to support thinking and non-thinking models by @Luohh5 in #1492
• fix(memory): serialize concurrent writes in AsyncSQLAlchemyMemory by @umerkhan95 in #1390
• fix(agent): prevent duplicate hook execution when subclass overrides _reasoning or _acting by @qbc2016 in #1481
• feat(model): add fallback for structured output for openai chat model by @qbc2016 in #1430
• fix(sqlalchemy_memory): flush the session to ensure message records are written to the database by @qbc2016 in #1396
• feat(formatter): translate local file path to base64 in image blocks in Anthropic formatter by @qbc2016 in #1361
• fix: use underscore naming for Tavily tool functions in DeepResearch agent by @octo-patch in #1400
• feat(model): refine counting input tokens for anthropic chat model by @qbc2016 in #1319
• fix(DashScope formatter): convert local files to base64 data in dashscope formatter by @qbc2016 in #1253
• fix(agent): guard DeepResearchAgent tool metadata access by @YingchaoX in #1489
• fix(unittest): hotfix for unittest by @qbc2016 in #1507
• chore(version): bumping verstion to 1.0.19 by @qbc2016 in #1506

New Contributors

• @zhanghaochenFCB made their first contribution in #1308
• @alex-xinlu made their first contribution in #1151
• @Ricardo-M-L made their first contribution in #1477
• @octo-patch made their first contribution in #1403
• @umerkhan95 made their first contribution in #1390

Full Changelog: v1.0.18...v1.0.19

v1.0.18

What's Changed

• fix(huggingface): add huggingface endpoint fix by @garyzhang99 in #1340
• docs(readme): update the README.md and README_zh.md with copaw by @DavdGao in #1353
• feat(test): fix version of pymilvus by @qbc2016 in #1355
• feat(formatter): enhance _to_openai_image_url for local files without extension by @kingofpowers in #1341
• feat(tuner): enhance tuner with prompt tuning and model selection by @Kanaricc in #1190
• fix(tuner): set monitor_type on monitor config instead of overwriting monitor object by @PatrickG1014 in #1365
• feat(toolkit): support background execution for tools by @DavdGao in #1342
• feat(agent): filter thinking content before broadcast by @qbc2016 in #1332
• feat(formatter): supprot audio path start with file:// in OpenAI formatter by @qbc2016 in #1349
• docs: update github trending image by @qbc2016 in #1368
• fix(model): avoid streaming tool input regression by @YingchaoX in #1356
• feat(model): pass through the model's response id by @qbc2016 in #1333
• chore(version): update version to 1.0.18 for release by @qbc2016 in #1370

New Contributors

• @kingofpowers made their first contribution in #1341
• @Kanaricc made their first contribution in #1190

Full Changelog: v1.0.17...v1/0.18

v1.0.17

What's Changed

• fix(tool): expand user home in text file tools for paths with tilde by @YingchaoX in #1262
• fix(docs): correct typo in quickstart_agent.py by @04cb in #1273
• fix(openai-model): support newer vllm reasoning field parsing by @WeiSibo in #1271
• fix(model): update DashScopeChatModel to use AioMultiModalConversatio… by @YingchaoX in #1290
• fix(utils): resolve double dot in file extension when saving base64 data by @YingchaoX in #1289
• feat(dashscope): move generate_kwargs after defaults to enable parameter override by @qbc2016 in #1304
• fix(formatter): correct local path identification logic by @DavdGao in #1284
• chore(github-actions): upgrade GitHub actions for node 24 compatibility by @salmanmkc in #1283
• fix(hooks): prevent Agent crash when Studio disconnects by @YingchaoX in #1298
• fix(docs): fix the typo in docstrings and remove unnecessary close statement by @dipeshbabu in #1247
• feat(session): make jsonsession file read and write async by @qbc2016 in #1313
• fix(plan): trigger hooks when recovering historical plans by @QianCyrus in #1279
• fix(hook): make set_console_output_enabled only affect console printing by @zhijianma in #1186
• fix(deep_research_agent): fix the bug in multi-turn deep research by @Luohh5 in #1239
• fix(gemini): handle None usage in streaming response parsing by @shlokmestry in #1251
• fix(examples): await register_mcp_client in deep_research_agent by @YingchaoX in #1299
• chore(version): update version to 1.0.17 for release by @DavdGao in #1325

New Contributors

• @YingchaoX made their first contribution in #1262
• @04cb made their first contribution in #1273
• @WeiSibo made their first contribution in #1271
• @salmanmkc made their first contribution in #1283
• @dipeshbabu made their first contribution in #1247
• @QianCyrus made their first contribution in #1279
• @shlokmestry made their first contribution in #1251

Full Changelog: v1.0.16...v1.0.17

v1.0.16

Highlight

• fix bugs in the previous version (1.0.15)

What's Changed

• fix(dependency): lazy import the websockets library by @DavdGao in #1214
• fix(stream_printing_messages): add sleep in print to avoid blocking consumption by @qbc2016 in #1218
• feat(model): add multimodality parameter in DashScope chat model by @qbc2016 in #1215
• fix(openai realtime): Add tool format for openai realtime model by @qbc2016 in #1216
• feat(realtime agent): Add video recording in realtime agent example and typo fix in realtime event by @qbc2016 in #1225
• feat(github): add checking for creating pull request titles by @DavdGao in #1233
• fix(memory): fix the memory compression bug in ReActAgent and the serialization error in InMemoryMemory class by @DavdGao in #1231
• perf(msg): set empty dictionary as defautl value for msg.metadata and improve the structured model in the werewolf game example by @qbc2016 in #1234
• fix(rag): fix the KeyError: 'v' in WrodReader when reading Word documents contain… by @qbc2016 in #1228
• feat(middleware): support toolkit middleware to control the tool execution by @DavdGao in #1232
• fix(plan): improve plan module test coverage and fix hint bug by @WangCheng0116 in #1220
• ci(realtime): add unittests for OpenAIRealtimeModel and GeminiRealtimeModel by @qbc2016 in #1235
• feat(tts): support dashscope cosyvoice tts model by @qbc2016 in #1040
• perf(browser-use): update the example of the browser-use agent with the lastest ReActAgent by @cuiyuebing in #1230
• chore(version): bump version from 1.0.16dev to 1.0.16 by @DavdGao in #1241

New Contributors

• @WangCheng0116 made their first contribution in #1220

Full Changelog: v1.0.15...v1.0.16

v1.0.16dev

What's Changed

• fix(dependency): lazy import the websockets library by @DavdGao in #1214
• fix(stream_printing_messages): add sleep in print to avoid blocking consumption by @qbc2016 in #1218
• feat(model): add multimodality parameter in DashScope chat model by @qbc2016 in #1215
• fix(openai realtime): Add tool format for openai realtime model by @qbc2016 in #1216

Full Changelog: v1.0.15...v1.0.16dev

v1.0.15

What's Changed

• feat(tuner): Add Logger and Tinker Support by @pan-x-c in #1178
• feat(rag/store): add OceanBaseStore as a vdb choice by @PsiACE in #1078
• feat(voice agent): implement realtime voice agent by @qbc2016 in #1056
• docs(evaluation): add openjudge evaluation integration by @ployts in #1168
• docs(api): abandon the API documentation temporarily by @DavdGao in #1196
• docs(tutorial): remove the huggingface related code in tutorial to avoid rate limit by @DavdGao in #1198
• fix(tutorial): fix the bug in the tutorial by @DavdGao in #1199
• fix(mcp): fix the timeout argument in MCPToolFunction class by @DavdGao in #1192
• Adapt Mem0LongtermMemory to mem0 v1 by @Osier-Yi in #1191
• fix(gemini): fix GeminiChatModel compatibility with Gemini-3-pro by @DavdGao in #1206
• chore(version): update version to 1.0.15 for new release by @DavdGao in #1209
• fix(redis_memory): support decode_response to be False in the given connection_pool argument by @ceshihao in #1187
• perf(redis_memory): avoid scan operations in RedisMemory to improve efficiency by @DavdGao in #1211

New Contributors

• @PsiACE made their first contribution in #1078
• @ployts made their first contribution in #1168

Full Changelog: v1.0.14...v1.0.15

v1.0.14

Highlight

• Allow to disable the tool use input parsing by stream_tool_parsing=False in the streaming mode #1097
• Fix the bugs in redis memory and mem0 based long-term memroy

What's Changed

• fix(memory): fix the bug in redis memory that use bytes data as the message key by @DavdGao in #1146
• fix the bug when use ollama model in mem0 by @Osier-Yi in #1148
• fix ollama bug in mem0 (event loop close issue) by ensuring it always runs in the same event loop by @Osier-Yi in #1157
• fix(OpenAIFormatter & AnthropicTokenCounter): fix related bugs by @qbc2016 in #1154
• feat(session): add redis based session in agentscope by @rayrayraykk in #1140
• feat(a2ui): add a2ui example in agentscope by @Osier-Yi in #1101
• fix(a2ui): fix package path issue in pyproject.toml & improve performance by @Osier-Yi in #1167
• fix(agent): remove duplicated message saved to long-term memory by @Osier-Yi in #1171
• feat(rag): add powerpoint reader for slide files by @qbc2016 in #873
• feat(mcp): support execution timeout for MCP tools by @DavdGao in #1176
• feat(model): support passing usage (e.g., cached_tokens) by @MengsD in #1166
• chore(version): update the version to 1.0.14 for pypi release by @DavdGao in #1179
• feat(model): add stream_tool_parsing for chat model by @qbc2016 in #1097

Full Changelog: v1.0.13...v1.0.14

v1.0.13

Highlight

RAG

• Support MongoDB vector database
• Support Excel reader

Example

• Integration with Qwen-Deep-Research model

What's Changed

• Add example integration for Qwen-Deep-Research model by @denverdino in #869
• feat(tool): add func_name parameter to support custom tool renaming by @qbc2016 in #1115
• feat(rag): add MongoDB vector store in the RAG module. by @qbc2016 in #860
• ci(gemini): add code review guide for the gemini code assist by @DavdGao in #1135
• fix(doc): fix typos by @qbc2016 in #1137
• feat(rag): add excel reader to support excel files in the rag module by @qbc2016 in #872
• docs: update the documentations in the AgentScope repo by @DavdGao in #1128
• fix(formattter): assigns content as an empty list [] for messages without valid content blocks by @qbc2016 in #1141
• fix(model): fix openai stream parse when delta is None by @qbc2016 in #1142
• chore(version): update the version to 1.0.13 for a quick release by @DavdGao in #1143
• feat(dashscope): support to load headers from the environment by @DavdGao in #1096

New Contributors

• @denverdino made their first contribution in #869

Full Changelog: v1.0.12...v1.0.13

v1.0.12

Highlight Changes

• ReActAgent supports automatic memory compression (#1081 )
• The memory module supports (#1081 )
  • various relational databases
  • redis
• Compatible with the Azure OpenAI API (#932 )

What's Changed

• fix(a2a): fix the bug of a2a server in the example by @zhijianma in #1080
• fix(ollama model): bugfix for stream output by @qbc2016 in #1082
• feat(rag): add AlibabaCloud MySQL vector store implementation by @wangype in #857
• feat(model): add azure openai support by @kristol07 in #932
• docs(task_prompt):DeedSeek to DeepSeek by @godeamon in #1085
• feat(werewolf): Add commented tts codes for werewolf game by @qbc2016 in #1090
• fix(doc): fix hyperlinks in readme by @qbc2016 in #1098
• fix(evaluator_storage): correct docstring on directory organization by @kristol07 in #925
• update the browser-use agent example by @cuiyuebing in #705
• feat(memory): support database memory and memory compression by @DavdGao in #1081
• fix(memory): fix the memory compression functionality by @DavdGao in #1107
• feat(tuner): Enhance Agent Tune Interface by @pan-x-c in #1079
• fix(mem0): fix the bug in mem0 that cannot find the _mem0_utils.py file by @DavdGao in #1114
• fix(ReActAgent): ensure stream flag resets during query rewriting by @DavdGao in #1124
• fix(session): fix the bug when the saving state contains illegal Unic… by @DavdGao in #1123
• docs(README): add news about the biweekly meeting by @DavdGao in #1127
• fix(tuner): Fix links and typos in tuner doc by @pan-x-c in #1131
• fix(tuner): Update Links by @pan-x-c in #1132

New Contributors

• @wangype made their first contribution in #857
• @kristol07 made their first contribution in #932
• @godeamon made their first contribution in #1085

Full Changelog: v1.0.11...v1.0.12

v1.0.11

What's Changed

• add record_to_memory before generate return reply_message by @Osier-Yi in #1039
• fix(werewolf game): Broadcast game result when game ends at night phase by @qbc2016 in #1065
• fix(openai formatter): Correctly extract image extension from URLs with query parameters by @qbc2016 in #1066
• feat(agent): Add A2A protocol support for inter-agent communication by @Sunrisea in #1027
• raise exception on MCP disconnection by @MengsD in #1024
• fix(gemini model): flatten json schema in tools for gemini chat model by @qbc2016 in #1050
• bugfix: parse anthropic response content block type logic error. by @FFengIll in #1070
• chore(version): update version to 1.0.11 by @DavdGao in #1074

New Contributors

• @Sunrisea made their first contribution in #1027
• @MengsD made their first contribution in #1024
• @FFengIll made their first contribution in #1070

Full Changelog: v1.0.10...v1.0.11