v0.4.2

• Change async input strategy in order to remove unintentional and accidentally added GPL dependency (#5060)

Full Changelog: v0.4.1...v0.4.2

v0.4.1

What's Important

• Fixed console user input bug that affects m1 and other apps that use console user input. #4995
• Improved component config by allowing subclassing the BaseComponent class. #5017 To read more about how to create your own component config to support serializable components: https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/framework/component-config.html
• Fixed stop_reason related bug by making the stop reason setting more robust #5027
• Disable Console output statistics by default.
• Minor doc fixes.

All Changes since v0.4.0

• Update magentic-one-cli version to 0.2.0 by @jackgerrits in #4973
• Update switcher versions and make 0.4.0 stable by @jackgerrits in #4940
• Fix version switcher rendering by @jackgerrits in #4974
• Don't show banner on stable by @jackgerrits in #4976
• Remove accidentally added character by @jackgerrits in #4980
• Update README.md to fix spelling error by @guinaut in #4982
• Minor API doc update for openai assistant agent by @ekzhu in #4986
• Add guidance for docstrings when adding an API by @jackgerrits in #4981
• Fix typo in Multi-Agent Design Patterns -> Intro docs by @timrogers in #4991
• Add missing py.typed in autogen_ext, fix type issue in core by @jackgerrits in #4993
• Minor Updates to AGS Docs by @victordibia in #5010
• Fix: Properly await agent.run() in README Hello World example by @Programmer-RD-AI in #5013
• Add python version requirement to frontpage and readme by @ekzhu in #5014
• Disable output usage stat summary in Console as the stats is often inaccurate. by @ekzhu in #5021
• Add AGS to README.md by @ekzhu in #5019
• fix: fix user input in m1 by @jackgerrits in #4995
• Typo in teams.ipynb by @SudhakarPunniyakotti in #5028
• fix: Normalize openai client stop reason to make more robust by @jackgerrits in #5027
• Add tiktoken as a dependency in pyproject.toml by @JohanForngren in #5008
• fix: Fix provider string for AzureTokenProvider by @jackgerrits in #4992
• Split apart component infra to allow for abstract class integration by @jackgerrits in #5017
• Update version to 0.4.1 by @jackgerrits in #5029
• Fixup autogen-ext version by @jackgerrits in #5030

New Contributors

• @guinaut made their first contribution in #4982
• @timrogers made their first contribution in #4991
• @Programmer-RD-AI made their first contribution in #5013
• @SudhakarPunniyakotti made their first contribution in #5028
• @JohanForngren made their first contribution in #5008

Full Changelog: v0.4.0...v0.4.1

v0.4.0

What's Important

🎉 🎈 Our first stable release of v0.4! 🎈 🎉

To upgrade from v0.2, read the migration guide. For a basic setup:

pip install -U "autogen-agentchat" "autogen-ext[openai]"

You can refer to our updated README for more information about the new API.

Major Changes from v0.4.0.dev13

• [New] Added m1 cli package by @afourney in #4949
• [New] Activate deactivate agents by @peterychang in #4800
• [New] Add coverage task & integrate with poe check by @srjoglekar246 in #4847
• [New] Move core samples to /python/samples by @ekzhu in #4911
• [New] feat: Add o1-2024-12-17 model by @bassmang in #4965
• [Breaking] fix!: Move azure auth provider to separate module by @jackgerrits in #4912
• [Breaking] feat!: Add message context to signature of intervention handler, add more to docs by @jackgerrits in #4882
• [Breaking] Remove deprecated items for release by @jackgerrits in #4927

Change Log from v0.4.0.dev13: v0.4.0.dev13...v0.4.0

New Contributors to v0.4.0

❤️ Big thanks to all the contributors since the first preview version was open sourced. ❤️

• @lspinheiro made their first contribution in #3652
• @husseinmozannar made their first contribution in #3714
• @NiklasGustafsson made their first contribution in #3727
• @maxgolov made their first contribution in #3758
• @vikas434 made their first contribution in #3770
• @tarockey made their first contribution in #3813
• @zboyles made their first contribution in #3855
• @markdouthwaite made their first contribution in #3871
• @gziz made their first contribution in #3876
• @SeryioGonzalez made their first contribution in #3901
• @rohanthacker made their first contribution in #3929
• @Ucoming made their first contribution in #3979
• @auphof made their first contribution in #3972
• @ReubenBond made their first contribution in #4034
• @maheshpec made their first contribution in #4070
• @mbaneshi made their first contribution in #4168
• @hasamm90 made their first contribution in #4170
• @tsinggggg made their first contribution in #4130
• @genlin made their first contribution in #4205
• @kkasemos made their first contribution in #4218
• @JMLX42 made their first contribution in #4201
• @ksachdeva made their first contribution in #4265
• @MervinPraison made their first contribution in #4280
• @thainduy made their first contribution in #4123
• @goyalpramod made their first contribution in #4149
• @kartikx made their first contribution in #4336
• @wi-ski made their first contribution in #4102
• @timparka made their first contribution in #4432
• @vballoli made their first contribution in #4548
• @eranco74 made their first contribution in #4639
• @hsm207 made their first contribution in #4655
• @iamarunbrahma made their first contribution in #4500
• @inbal2l made their first contribution in #4717
• @r-bit-rry made their first contribution in #4759
• @jspv made their first contribution in #4755
• @akurniawan made their first contribution in #4681
• @lanbaoshen made their first contribution in #4767
• @srjoglekar246 made their first contribution in #4801
• @richard-gyiko made their first contribution in #4826
• @kimmywork made their first contribution in #4732
• @Leon0402 made their first contribution in #4848
• @w121211 made their first contribution in #4874
• @PratyushNag made their first contribution in #4903

Changes from v0.2.36

• Use trusted publisher for pypi release by @jackgerrits in #3596
• Fix typos in Cerebras doc by @henrytwo in #3590
• Add blog post announcing the new architecture preview by @jackgerrits in #3599
• Fix dotnet test and reformat dotnet code by @LittleLittleCloud in #3603
• Update PR link in blog post by @jackgerrits in #3602
• Create CI to tag issues with needs triage by @jackgerrits in #3605
• Update Magentic-One Results by @afourney in #3611
• Update issue templates by @jackgerrits in #3610
• add logging to agentchat by @victordibia in #3606
• Add staging to workflow target; fix circular imports in autogen_agentchat by @ekzhu in #3651
• Add redirects from current website to /0.2/ by @jackgerrits in #3659
• Remove accidentally added files from 0.2 by @jackgerrits in #3661
• Try fix docs CI by @jackgerrits in #3660
• fix: remove subscription on client disconnect in worker runtime by @MohMaz in #3653
• Move tools to agent in agentchat; refactored logging to support tool events by @ekzhu in #3665
• [.Net] Remove merging primitive from .editorconfig and gitignore by @LittleLittleCloud in #3676
• Add poethepoet to dev deps by @jackgerrits in #3675
• Rysweet hello fix by @rysweet in #3683
• add a way to provide extra grpc options by @MohMaz in #3667
• Selector group chat that uses LLM to select the next speaker by @ekzhu in #3680
• Add Documentation for AgentChat by @victordibia in #3635
• Set logging of internal messages to debug by @ekzhu in #3694
• Lspinheiro/chore/migrate azure executor autogen ext by @lspinheiro in #3652
• remove broken sample and update readme quickstart for the good sample by @rysweet in #3687
• Website design tweaks by @jackgerrits in #3699
• Termination condition for agentchat teams by @ekzhu in #3696
• Rysweet dotnet folder moves by @rysweet in #3693
• add documentation for dotnet AutoGen 0.4 HellowWorld sample by @rysweet in #3698
• Add clarity to new site by @jackgerrits in #3704
• Documentation tweaks by @jackgerrits in #3705
• Add more FAQs to readme by @jackgerrits in #3707
• Include license file in package by @jackgerrits in #3703
• Update references by @jackgerrits in #3708
• Refactor logging in agentchat by @ekzhu in #3709
• New AutoGen Architecture Preview by @jackgerrits in #3600
• Fix output directory for website by @jackgerrits in #3712
• Update logo link by @jackgerrits in #3713
• Fix redirects taking into account base path by @jackgerrits in #3716
• Fix packages link by @jackgerrits in #3718
• Move from tomllib to tomli by @husseinmozannar in #3714
• Add workflow for package releases by @jackgerrits i...

v0.4.0.dev13

What's new

• An initial version of the migration guide is ready. Find it here! (#4765)
• Model family is now available in the model client (#4856)

Breaking changes

• Previously deprecated module paths have been removed (#4853)
• SingleThreadedAgentRuntime.process_next is now blocking and has moved to be an internal API (#4855)

Fixes

• Fix SingleThreadedAgentRuntime busy loop by @jackgerrits in #4855
• Fix BaseOpenAIChatCompletionClient token usage by @gziz in #4770

Doc changes

• Migration guide for 0.4 by @ekzhu in #4765
• Clarify tool use in agent tutorial by @ekzhu in #4860
• AgentChat tutorial update to include model context usage and langchain tool by @ekzhu in #4843
• Add missing model context attribute by @Leon0402 in #4848

Other

• Replace Tuple[type[ChatMessage], ...] with Sequence[type[ChatMessage]] by @ekzhu in #4857
• Make register_factory a user facing API by @jackgerrits in #4854
• Move intervention objects to root module by @jackgerrits in #4859

New Contributors

• @Leon0402 made their first contribution in #4848

Full Changelog: v0.4.0.dev12...v0.4.0.dev13

v0.4.0.dev12

Important Changes

• run and run_stream now support a list of messages as task input.
• Introduces AgentEvent union type in AgentChat, for all messages that are not meant to be consumed by other agents. Replace AgentMessage with AgentEvent | ChatMessage union type in your code, e.g., in your custom selector function for SelectorGroupChat and processing code for TaskResult.messages.
• Introduce ToolCallSummaryMessage to ChatMessage for tool call results from agents. Read AssistantAgent Doc
• Introduce ModelContext parameter for AssistantAgent, allow usage of BufferedChatCompletionContext to limit context window size sent to model.
• Introduce ComponentConfig and add configuration loader for ChatCompletionClient. See Component Config
• Moved autogen_core.tools.PythonCodeExecutorTool to autogen_ext.tools.code_execution.PythonCodeExecutionTool.
• Documentation updates.

Upcoming Changes

• Deprecating @message_handler. Use @event or @rpc to annotate handlers instead. @message_handler will be kept with a deprecation warning until further notice. #4828
• Token counting mechanism bug fixes #4719

New Contributors

• @hsm207 made their first contribution in #4655
• @iamarunbrahma made their first contribution in #4500
• @inbal2l made their first contribution in #4717
• @r-bit-rry made their first contribution in #4759
• @jspv made their first contribution in #4755
• @akurniawan made their first contribution in #4681
• @lanbaoshen made their first contribution in #4767
• @srjoglekar246 made their first contribution in #4801
• @richard-gyiko made their first contribution in #4826
• @kimmywork made their first contribution in #4732

Full Changelog: v0.4.0.dev11...v0.4.0.dev12

v0.2.40

What's Changed

• Add warning message when NoEligibleSpeaker by @thinkall in #4535
• [Bug]: Bedrock client uses incorrect environment variables for authentication by @vaisakh-prod in #4657
• fix "keep_first_message" to make sure messages are in correct order, by @milkmeat in #4653
• fix: No context vars for async agents replies by @violonistahiles in #4640
• update version by @ekzhu in #4713

New Contributors

• @vaisakh-prod made their first contribution in #4657
• @milkmeat made their first contribution in #4653
• @violonistahiles made their first contribution in #4640

Full Changelog: v0.2.39...v0.2.40

v0.4.0.dev11

Important Changes:

1. autogen_agentchat.agents.AssistantAgent behavior has been updated in dev10. It will not perform multiple rounds of tool calls -- only 1 round of tool call, followed by an optional reflection step to provide a natural language response. Please see the API doc for AssistantAgent.
2. Module renamings:

• autogen_core.base --> autogen_core
• autogen_core.application.SingleThreadedAgentRuntime --> autogen_core.SingleThreadedAgentRuntime.
• autogen_core.application.logging --> autogen_core.logging.
• autogen_core.components.* --> autogen_core.*, for models, model_context, tools, tool_agent and code_executor.
• autogen_core.components.code_executor.LocalCommandLineCodeExecutor --> autogen_ext.code_executors.local.LocalCommandLineCodeExecutor
• autogen_agentchat.task.Console --> autogen_agentchat.ui.Console.
• autogen_agentchat.task.<termination conditions> --> autogen_agentchat.conditions.<termination_conditions>.
• autogen_ext.models gets divided into autogen_ext.models.openai, autogen_ext.models.replay.
• autogen_ext.agents gets divided into separate submodules for each extension agent class.
• autogen_ext.code_executors gets divided into separate submodules for each executor class.

New Contributors

• @eranco74 made their first contribution in #4639

Full Changelog: v0.4.0.dev9...v0.4.0.dev11

v0.2.39

What's Changed

• fix: GroupChatManager async run throws an exception if no eligible speaker by @leryor in #4283
• Bugfix: Web surfer creating incomplete copy of messages by @Hedrekao in #4050

New Contributors

• @leryor made their first contribution in #4283
• @Hedrekao made their first contribution in #4050

Full Changelog: v0.2.38...v0.2.39

v0.2.38

What's Changed

• docs: fix bullet formatting for kubernetes pod executor by @lukehsiao in #3911
• Fix 0.2 Quickstart example llm_config issue by @victordibia in #4060
• Bugfix: Optional rate limiting by @kampernet in #4066

New Contributors

• @lukehsiao made their first contribution in #3911
• @kampernet made their first contribution in #4066

Full Changelog: v0.2.37...v0.2.38

v0.2.37

What's Changed

• Use trusted publisher for pypi release by @jackgerrits in #3596
• Fix typos in Cerebras doc by @henrytwo in #3590
• Add blog post announcing the new architecture preview by @jackgerrits in #3599
• Update PR link in blog post by @jackgerrits in #3602
• Create CI to tag issues with needs triage by @jackgerrits in #3605
• Update issue templates by @jackgerrits in #3610
• Fix small typo in the docs by @jknaudt21 in #3650
• Update 0.2 CI to target branch, remove merge queue by @jackgerrits in #3656
• Update BaseUrl of docusaurus site by @jackgerrits in #3658
• Add announcement bar for 0.4 by @jackgerrits in #3717
• Update links on 0.2 website by @jackgerrits in #3734
• Function Calling Support for Gemini - Part 2 by @luxzoli in #3726
• Fix #2643 - groupchat model registration by @Matteo-Frattaroli in #2696
• Added a demonstartion notebook featuring the usage of Langchain with AutoGen by @Kirushikesh in #3461
• Autobuild Function calling by @krishnashed in #3238
• Update Docs to Point to 0.4 by @victordibia in #3764
• Notebook on web crawling by @WilliamEspegren in #2720
• Fix link to v0.4 documentation by @ekzhu in #3772
• Remove path filter for website testing in 0.2 by @jackgerrits in #3782
• Fix broken image URL in README by @gagb in #3776
• Clarify stable package name and version on home page by @jackgerrits in #3775
• Fix CTA button alignment in docs home page by @victordibia in #3788
• K8s code executor by @questcollector in #3419
• Add Couchbase Vector DB Example Notebook and Minor Bug Fix by @lokesh-couchbase in #3804
• Add Zep ecosystem doc and notebook by @danielchalef in #3681
• [bug] Changes Text Cache Default to None by @WaelKarkoub in #3872
• [bug] Validates If The Role Tool is Handled Correctly after Transforms by @WaelKarkoub in #3875
• [CAP] Abstraction of actor_connector to go along with runtime factory and runtime abstraction by @rajan-chari in #3296

New Contributors

• @jknaudt21 made their first contribution in #3650
• @Matteo-Frattaroli made their first contribution in #2696
• @WilliamEspegren made their first contribution in #2720
• @questcollector made their first contribution in #3419
• @danielchalef made their first contribution in #3681

Full Changelog: v0.2.36...v0.2.37