Changelog

New Features:

• WorkflowTools: Added WorkflowTools as a tool for agents and teams that allows the agent/team to run a workflow. Also has reasoning support for think/analyze.
• MemoryTools: Added MemoryTools as a tool for agents and teams to add, update, delete memories. Also has reasoning support for think/analyze.
• Gemini TTS: Added support for Gemini Text to Speech.
• Added support for encoding to be passed on reader class.

Improvements:

• AgentOS kwargs on runs: Added support for additional arguments on running an agent/team/workflow via AgentOS API.

Bug Fixes:

• Cerebras: Fixed issues with parallel_tool_calls in Cerebras model.
• OpenAIResponses: Fixed a bug with store=False in OpenAIResponses class.
• AgentOS Slack Interface: the events endpoint was wrongly exposed on slack/slack/events, it is now exposed on slack/events
• AgentOS WhatsApp Interface: fixed a bug where some messages wouldn’t be sent.
• Team MemoryManager: Added memory_manager parameter to Teams.
• FixedSizeChunking: Default chunk_size increased to 5000.
• Parser Model output in print_response_stream: In streaming case the structured output from parser model was not being displayed json formatted in cli.

What's Changed

• [fix] Add 'docker' to allowed commands in MCP command preparation by @ishrath99 in #4482
• chore: opt out of telemetry on pipelines by @SamJupe in #4503
• fix: whatsapp router on agentos by @VirusDumb in #4504
• feat: WorkflowTool and MemoryTool by @dirkbrnd in #4506
• fix: Cerebras parallel_tool_calls by @dirkbrnd in #4513
• fix: slack router prefix by @manuhortet in #4517
• fix: Update fixedChunking size by @willemcdejongh in #4518
• feat: handle kwargs in OS endpoints by @manuhortet in #4509
• fix: dont raise if no session when getting chat history by @manuhortet in #4516
• feat: Support custom encoding on reader class by @willemcdejongh in #4521
• feat: Only warn if LiteLLM client is not provided by @whitfin in #4470
• feat: update structured input output example with parser model by @kausmeows in #4515
• fix: team memory manager by @anuragts in #4523
• feat: Gemini TTS by @Mustafa-Esoofally in #4307
• feat: update SSE format by @manuhortet in #4524
• fix: print response stream changes for parser model by @kausmeows in #4530
• Update structured IO cookbook by @ashpreetbedi in #4532
• feat: Handle Zdr model for OpenAI reasoning models by @Mustafa-Esoofally in #4520
• chore: Release 2.0.3 by @ysolanky in #4529

New Contributors

• @ishrath99 made their first contribution in #4482
• @SamJupe made their first contribution in #4503
• @whitfin made their first contribution in #4470

Full Changelog: v2.0.2...v2.0.3