Agno Release Notes

Changelog

New Features:

Gemini Multimodal File Search: Added multimodal support in the Gemini File Search API (for google-genai≥1.75.0). See cookbook.

Context Providers: Added GmailContextProvider and CalendarContextProvider following the same pattern as existing providers (GDrive, Slack, Database). Also updates GDriveContextProvider to support OAuth in addition to service account auth.

Scheduler: Added scheduler support for Mongo and AsyncMongo Db to run agents, teams, and workflows on a cron in AgentOS.

Workflow Condition Step: Added on_error handling to the Condition workflow step, allowing users to control how errors are handled when sub-steps within a condition fail.

Improvements:

LLMsTxt Tools: Added an allowed_hosts param so agents only fetch from hosts you trust.

SlackContextProvider: Add enable_media_tools flag (default: False) to control file download/upload.

download_file added to read tools

upload_file added to write tools

Bug Fixes:

MCP IDOR: Fixed to bind the user_id on AgentOS MCP tool handlers to the authenticated JWT subject to prevent cross-tenant reads and writes.

Toolkit Instructions: Fixed @tool(instructions=...) to take effect when used inside a Toolkit.

Metrics: Fixed to accumulate parser, output, and member metrics in team run_response.

Workflow: Fixed to persist mid-step workflow run cancellation.

SQLTools: Updated to include column default in describe_table.

Slack Interface: Fixed to replace Slack bot @mention with display name instead of stripping.

GoogleDriveTools: Fixed binary file errors + Office extraction + Shared Drive params in GoogleDriveTools.

ChromaDb: Fixed to offload async batch upsert/insert to worker thread.

Memory: Fixed include identity fields in update_memory and delete_memory tools.

What's Changed

fix: accumulate parser, output, and member metrics in team run_response by @ysolanky in #7704

fix: workflow cancellation persistance by @kausmeows in #7732

fix: include column default in describe_table by @Mustafa-Esoofally in #7703

feat: add search_messages and media tools to SlackContextProvider by @Mustafa-Esoofally in #7702

cookbook: frameworks quickstart for Agno + Claude Code + LangGraph + DSPy by @ashpreetbedi in #7743

fix: replace Slack bot @mention with display name instead of stripping by @Mustafa-Esoofally in #7750

fix: add allowed_hosts allowlist to LLMsTxtTools by @harshsinha03 in #7759

feat: add on_error handling to Condition step by @rotem-bar-cyera in #7214

feat: add Gmail and Calendar context providers by @Mustafa-Esoofally in #7747

fix: binary file errors + Office extraction + Shared Drive params in GoogleDriveTools by @Mustafa-Esoofally in #7764

fix: surface per-tool instructions when registered via Toolkit by @harshsinha03 in #7798

fix: chromadb offload async batch upsert/insert to worker thread by @basnijholt in #7711

fix: include identity fields in update_memory and delete_memory tools by @Mustafa-Esoofally in #6550

[feat] Added scheduler support for mongo by @abhi10691 in #6938

fix: bind MCP tool user_id to JWT subject by @sannya-singal in #7811

feat: gemini file api multimodal by @kausmeows in #7788

chore: Release v2.6.5 by @kausmeows in #7809

New Contributors

@rotem-bar-cyera made their first contribution in #7214

Full Changelog: v2.6.4...v2.6.5

Original source

Changelog

New Features

WorkspaceContextProvider (#7709): Project-aware context provider for repository roots, backed by the read-only Workspace toolkit instead of generic FileTools. Centralizes local filesystem exclude patterns so both FileTools and Workspace skip .context, .venvs, and other agent/dependency/build noise by default. FilesystemContextProvider now accepts exclude_patterns for explicit opt-out/customization.

Improvements

SlackContextProvider (#7710): Simplified provider and inlined SlackTools construction. Removed for_bot_read(), for_assistant_search(), and for_write() factory methods in favor of explicit flags. Added opt-in enable_workspace_search parameter. Tools are now self-documenting via SlackTools, removing runtime agent switching.

Bug Fixes

Slack:

• Gracefully fall back to public channels when the groups:read scope is missing.
• Restore Slack read instruction override and tighten briefing guidance.
• Expose Slack update in agent mode; agent mode returns query-only.

What's Changed

• feat: add workspace context provider by @ashpreetbedi in #7709
• refactor: simplify SlackContextProvider, remove factory methods by @Mustafa-Esoofally in #7710
• refactor: clean up SlackContextProvider and optimize channel resolution by @Mustafa-Esoofally in #7708
• refactor: clean up Slack context provider and add engineering briefing cookbook by @ashpreetbedi in #7706
• Release: v2.6.3 by @ashpreetbedi in #7713
• Full Changelog: v2.6.2...v2.6.3

Original source

Changelog

New Features:

Workspace Tools: Added a polished local-machine toolkit that gives agents read/list/search/write/edit/move/delete/shell access to a root directory tree, with destructive operations gated by Agno's built-in human-in-the-loop confirmation by default.

Improvements:

Models: Updated default id for multiple model providers to newer, actively supported models to prevent upcoming deprecations, improve performance consistency, and significantly reduce operational costs.

Bug Fixes:

Workflow HITL: Fixed to preserve HITL review config in deep_copy for Step, Router, and Loop.

What's Changed

fix: preserve HITL review config in deep_copy for Step, Router, and Loop by @kausmeows in #7694

[feat] migrate to latest provider models and remove deprecated ones by @chiruu12 in #7681

feat: add Workspace toolkit with HITL confirmation gates by @ashpreetbedi in #7683

chore: Release v2.6.2 by @kausmeows in #7701

Full Changelog: v2.6.1...v2.6.2

Original source

Changelog

New Features:

Claude Prompt Caching (Multi-Block): Three Anthropic prompt caching enhancements, scoped to the Claude model (#7662):

New system_prompt_blocks: List[SystemPromptBlock] on Claude — each block has text, cache, and optional ttl ("5m" or "1h") that overrides the model-level extended_cache_time flag per block.

New cache_tools: bool on Claude (Anthropic, AWS Bedrock, VertexAI). Adds cache_control to the last tool so the tool prefix is cached.

Deterministic tool ordering in Model._format_tools (sort by name), so request prefixes stay stable across runs and prompt caches actually hit. Applies across Anthropic, OpenAI, Gemini, and Bedrock.

Parallel MCP Backend: Added ParallelMCPBackend as a new web backend for WebContextProvider (#7667). Talks to Parallel's public MCP server at search.parallel.ai/mcp, exposing web_search + web_fetch (compressed markdown output). Keyless by default; Bearer-auth via PARALLEL_API_KEY for higher rate limits; optional OAuth endpoint via use_oauth=True. Defaults to a 30s timeout (up from MCPTools' 10s) because web_fetch frequently runs longer on large pages.

Improvements:

OpenAI Model String: Mapped "openai:" model string prefix to OpenAIResponses (previously OpenAIChat). Added "openai-chat:" as a fallback for users who still need OpenAIChat. Agent(model="openai:gpt-5.4") now resolves to OpenAIResponses(id="gpt-5.4").

Bug Fixes:

A2A: Pinned a2a-sdk>=0.3.0,<1.0 in the release workflow. a2a-sdk v1.0 has breaking changes that need to be adopted in a follow-up.

Cookbook:

Fixed outdated Redis cookbook docs - removed dependency install and setup commands that are no longer needed (#7615).

Fixed output_schema example to demonstrate output_schema with a Pydantic model (it was incorrectly using output_model with web search).

Fixed typo in cookbook/05_agent_os/README.md that referenced a non-existent agno_agent.py (corrected to agno_assist.py) (#7663).

What's Changed

chore: map "openai:" model string to OpenAIResponses by @kausmeows in #7655

fix typo in 05_agent_os readme by @asifshaikh in #7663

[cookbook] fix outdated docs for Redis by @edlng in #7615

feat: add ParallelMCPBackend for web search via Parallel MCP by @Mustafa-Esoofally in #7667

feat: multi-block prompt caching for Claude by @ysolanky in #7662

chore: Release v2.6.1 by @kausmeows in #7666

New Contributors

@asifshaikh made their first contribution in #7663

@edlng made their first contribution in #7615

Full Changelog: v2.6.0...v2.6.1

Original source

Changelog

New Features:

Team HITL: Added API layer for Team human in the loop and support in AgentOS chat page.

Team Approvals: Added support for Approvals in Team, along with in AgentOS chat page.

Workflow Executor HITL: Added support for executor level human in the loop in case when a pause tool flow is setup on an agent/team in a particular step of a workflow.

Multi-framework support in AgentOS (Beta): Added basic support for ClaudeAgentSDK, Langgraph and DSPy using a single AgentProtocol as the backbone which works with AgentOS runtime.

Reconnection and Resume Runs: Agent/Team running in background using SSE can now be reconnected and resumed in AgentOS in case of a interruption (refresh) so you start from where you left.

Factories: Agent/Team/Workflow can now be created dynamically at run-time using AgentFactory, TeamFactory and WorkflowFactory allowing for more multi-tenant usecases.

Context Provider: Added agno.context — a first-party API for plugging an external source (filesystem, web, SQL database, Slack, Google Drive, MCP server) into anagent as a natural-language tool.

Bug Fixes:

Callable Factory:

Fixed to preserve factory tools and members when Agent/Team is copied.

Fixed to skip iteration of callable-factory tools in Agent.deep_copy.

Telegram Interface:

Fixed to respect retry_after on Telegram 429 rate limit errors

Added quoted_responses option to Telegram interface

Agent OS Router:

Fixed GET /workflows/{id} which omitted nested workflow steps and Condition.else_steps (along with the agents inside them) from the response

Workflow:

Fixed to preserve parent_step_id through nested workflow enrichment layers in case of workflow as a workflow step.

MCP:

Fixed to handle None headers when merging init headers in MCP tools.

Claude:

Fixed to make anthropic imports lazy in agno.utils.models.claude.

Remote Content Source:

Fixed where two uploads of the same filename from different remote sources (GitHub repos, S3 buckets, GCS buckets, etc.) produced identical content_hash values.

FileTools:

Fixed to add exclude_patterns to FileTools.

Agent HITL:

Fixed pause-continue flow not handling subsequent tool calls.

Breaking Changes:

Session Type Filter: The /sessions endpoint now returns all session types (agent, team, and workflow) by default, giving you a complete view of your sessions in a single call. To filter for a specific type, pass?type=agent ?type=team, or ?type=workflow in your request.

Original source

Changelog

Improvements

Option to disable Claude file citations (#7511)

Allow GitHubConfig repo to be specified per request (#7496)

Bug Fixes

Preserve custom db table names when loading components (#7508)

Apply header_provider headers during MCP initialization (#7507)

Preserve inner workflow event identity and add nested_depth to agent/team events (#7491)

Build knowledge dbs live in config API (#7498)

Stop injecting shared HTTP/2 client into all model providers (#7492)

Catch CancelledError explicitly in all router streaming generators (#7379)

Try raw JSON parse before cleaning to preserve code blocks in strings (#7402)

Exclude framework-injected params from user_input_schema (#7485)

Include extra_messages in memory pipeline gate check (#7470)

What's Changed

[fix] Include extra_messages in memory pipeline gate check by @ArielTM in #7470

chore: add weekly scheduled run to main validation workflow by @sannya-singal in #7453

fix: exclude framework-injected params from user_input_schema by @kausmeows in #7485

fix: try raw JSON parse before cleaning to preserve code blocks in strings by @ysolanky in #7402

fix: catch CancelledError explicitly in all router streaming generators by @ysolanky in #7379

fix: stop injecting shared HTTP/2 client into all model providers by @ysolanky in #7492

fix: build knowledge dbs live in config API by @sannya-singal in #7498

fix: preserve inner workflow event identity and add nested_depth to agent/team events by @Ayush0054 in #7491

fix: apply header_provider headers during MCP initialization by @ysolanky in #7507

fix: preserve custom db table names when loading components by @ysolanky in #7508

feat: allow GitHubConfig repo to be specified per request by @ysolanky in #7496

[feat] Option to disable Claude file citations by @joeportela in #7511

chore: release 2.5.17 by @ysolanky in #7494

New Contributors

@ArielTM made their first contribution in #7470

Full Changelog: v2.5.16...v2.5.17

Original source

Changelog

New Features:

LLMsTxtTools and LLMsTxtReader: Adds support for the llms.txt standard - a standardized way for websites to provide LLM-friendly documentation indexes (e.g. https://docs.agno.com/llms.txt).

SalesforceTools: Added Salesforce CRM Tools.

Model: Added new Azure AI Foundry Claude model provider.

OpenAIResponses: Added background mode support for OpenAI Responses API.

Bug Fixes:

Knowledge: Fixed to read knowledge_table from contents_db instead of agent.db.

AGUI:

Fixed to emit reasoning events in AGUI interface.

Fixed AGUI input_content to store current user input instead of message history.

Workflow: Fixed to handle file path images in workflow step conversion.

OpenAIResponses: Fixed to handles response.reasoning_summary_text.delta events to stream reasoning content as it arrives.

Team: Fixed TeamSession.from_dict() to not mutate input mapping.

What's Changed

fix: read knowledge_table from contents_db instead of agent.db by @sannya-singal in #7437

chore: update cookbook to use 5.4 and openai responses model by @kausmeows in #7442

fix: emit reasoning events in AGUI interface by @Mustafa-Esoofally in #7429

[feat] Add Salesforce CRM tools by @raghavenderreddygrudhanti in #7079

[feat] Add Azure AI Foundry Claude model provider by @alejandro-workpath in #6816

[fix] Fix AGUI input_content to store current user input instead of message history by @RowanLane in #5469

fix: handle filepath images in workflow step conversion by @ItsRoy69 in #7457

feat: add background mode support for OpenAI Responses API by @ysolanky in #7444

fix: TeamSession.from_dict() no longer mutates input mapping by @YizukiAme in #7462

fix: stream reasoning summary deltas in OpenAI Responses API by @ysolanky in #7445

fix: sort order enum default in remotedb routes by @Shiv1909 in #7452

feat: add LLMsTxtReader and LLMsTxtTools for llms.txt support by @ashpreetbedi in #7458

chore: Release v2.5.16 by @kausmeows in #7463

New Contributors

@raghavenderreddygrudhanti made their first contribution in #7079

@alejandro-workpath made their first contribution in #6816

@RowanLane made their first contribution in #5469

@YizukiAme made their first contribution in #7462

Full Changelog: v2.5.15...v2.5.16

Original source

Changelog

New Features

Skills: Added skills support to Team. See docs.

Workflow: Added workflow as a workflow step (nested workflow) support. See docs.

Improvements

Workflow HITL:

Workflow steps now support post-execution human-in-the-loop review - pause after a step runs to review, approve, reject with feedback and retry, or edit the output before it continues (requires_output_review on Step, Router, and Loop). See docs.

Parameters consolidated into HumanReview config class - pass human_review=HumanReview(...) on Step, Loop, and Router instead of flat params. Fully backward compatible. See docs

Traceback Logging: Added AGNO_LOG_TRACEBACKS env var (opt-in) to control traceback visibility in log_error and log_warning — off by default (clean logs), full tracebacks when set to true.

SessionSummaryManager: Adds last_n_runs and conversation_limit parameters to
SessionSummaryManager so users can control how much conversation history is included when generating session summaries.

Bug Fixes

OpenAI: Stop injecting shared HTTP/2 client into OpenAI and Azure OpenAI models. Fixes transient 400 errors under concurrent usage by letting the OpenAI SDK manage its own HTTP client.

Metrics: Fixed audio_total_tokens not being computed for OpenAI, Perplexity, and LiteLLM.

Workflow:

Fixed else_steps not being copied for Condition step type.

Fixed StepInput to_dict to properly serialize File objects.

SurrealDb: Updated correct SurrealDB flexible field syntax.

AgentOS: Added missing MIME types for .msg, .xlsx and .xls in AgentOS file upload.

A2A: Fixed to serialize Pydantic output_schema content before str concatenation.

Team: Fixed TeamSession.get_messages(..) returning duplicate messages.

SlackTools: Fixed to add thread-aware messaging instructions to SlackTools.

GitHubTool: Fixed IndexError in get_pull_requests when fewer PRs than requested limit

WikipediaTools: Fixed to handle Wikipedia DisambiguationError and add configurable auto_suggest.

What's Changed

fix: else_steps are not copied for Condition step type by @korntewin in #7198

[cookbook] fix Slack cookbook configs: history context and MemoryManager model by @Himanshu040604 in #7288

[fix] correct SurrealDB flexible field syntax by @pandego in #7303

fix: add missing MIME types for .msg, .xlsx and .xls in AgentOS file upload by @wildchron in #7329

[fix] a2a stream: serialize Pydantic output_schema content before str concatenation by @NIK-TIGER-BILL in #6936

feat: add skills support to Team by @uzaxirr in #7017

[fix] Workflow StepInput to_dict was not serializing File objects by @luisnmartins in #7364

fix: TeamSession.get_messages return duplicated messages by @kausmeows in #7372

fix: add thread-aware messaging instructions to SlackTools by @Mustafa-Esoofally in #7308

Fix IndexError in get_pull_requests when fewer PRs than requested limit by @kaiisfree in #7353

chore: improve exception logging across the SDK by @kausmeows in #7358

fix: remove extra session_type query filter in AsyncMongoDb.get_session by @lethuan127 in #7392

[fix] Add error handling to get_top_hackernews_stories by @lawrence3699 in #7343

fix: stop injecting shared HTTP/2 client into OpenAI-based models by @fehmisener in #7328

[fix] compute audio_total_tokens and correct cookbook metrics examples by @Shiv1909 in #7417

[fix] handle Wikipedia DisambiguationError and add configurable auto_suggest by @Himanshu040604 in #7222

feat: add last_n_runs and conversation_limit to SessionSummaryManager by @ysolanky in #7401

fix: correct stale docstring param name in AgentSession.get_messages by @harshsinha03 in #7423

feat: add post-execution output review and 6 other HITL features for workflows by @ysolanky in #7409

feat: workflow within a workflow by @kausmeows in #6116

refactor: consolidate HITL params into HITL config class by @ysolanky in #7428

refactor: add HumanReview support to Condition, Steps, and Parallel by @ysolanky in #7433

chore: Release v2.5.15 by @kausmeows in #7420

New Contributors

@korntewin made their first contribution in #7198

@wildchron made their first contribution in #7329

@luisnmartins made their first contribution in #7364

@kaiisfree made their first contribution in #7353

@lethuan127 made their first contribution in #7392

@lawrence3699 made their first contribution in #7343

@Shiv1909 made their first contribution in #7417

Full Changelog: v2.5.14...v2.5.15

Original source

Changelog

New Features:

• Fallback Models: Added support for Fallback Models on Agents and Teams. See docs

agent = Agent(
model=OpenAIChat(id="gpt-4o", base_url="http://localhost:1/v1", retries=0),
fallback_models=[Claude(id="claude-sonnet-4-20250514")],
)

• Azure Blob Storage: Added SAS token authentication support for AzureBlobConfig.
• SlackTools: Added workspace search tool to SlackTools.

Bug Fixes:

• LearningMachine: Fixed to filter non-conversational messages from learning extraction.
• OpenAIResponses: Fixed to use correct MIME type for image bytes in OpenAI Responses API.
• Claude: Add automatic trailing user message injection for Claude 4.6+ models that don't support assistant message prefill, with centralized detection across all providers (Anthropic, Bedrock, Vertex AI, LiteLLM).

What's Changed

• feat: add SAS token authentication support for AzureBlobConfig by @ashpreetbedi in #7247
• feat: add fallback model support to Agent and Team by @ysolanky in #7080
• fix: revert IntermediateRunContentEvent changes done in teams by @kausmeows in #7295
• fix: patch review bugs across fallback cookbooks, JWT middleware, and OpenAI error handling by @harshsinha03 in #7299
• feat: add workspace search tool to SlackTools by @Mustafa-Esoofally in #7277
• fix: filter non-conversational messages from learning extraction by @Mustafa-Esoofally in #7280
• fix: use correct MIME type for image bytes in OpenAI Responses API by @Mustafa-Esoofally in #7285
• fix: suppress duplicate member content in Slack team streaming by @Mustafa-Esoofally in #7300
• fix: add text/markdown mime type and fix Anthropic nested schema validation by @ysolanky in #7287
• fix: add inject_trailing_user_message and `trailing_user_message_content for models that reject assistant prefill by @harshsinha03 in #7304
• chore: release 2.5.14 by @ysolanky in #7282

Full Changelog: v2.5.13...v2.5.14

Original source

Changelog

Improvements:

ReliabilityEval: Add subset matching, argument validation, and missing tool call tracking with multi-round tool call collection fixes.

AgentOS: Enhance /sessions list API to return additional fields (user_id, agent_id, team_id, workflow_id, session_summary, metrics, total_tokens, metadata).

AgentOS: Add /info API endpoint to return agent, team, and workflow count as lightweight, unauthenticated instance metadata.

ChromaDB: Implement dynamic batch splitting for large upsert/query operations.

Reader: Propagate chunk_size to default chunking strategies in reader classes.

Slack Interface: Add show_member_tool_calls param and automatic card overflow rotation — rotates to a new message when text exceeds a threshold

Bug Fixes:

VertexAI/Bedrock Claude: Support messages parameter in _prepare_request_kwargs for Claude sub classes

Workflows: Fix continue_run to correctly pause at Condition, Loop, and Router HITL steps — previously only Step instances were checked.

AgentOS: Exclude interface routes (Slack, Telegram, WhatsApp, A2A) from JWT middleware so webhook deliveries are not rejected with 401.

Tracing: Fix trace session stats grouping to use session_id only, preventing duplicate rows when a session has runs from different users.

SurrealDB: Fix trace session stats to use array::first() instead of math::max() for string fields.

ReliabilityEval: Fix multi-round tool call extraction so all rounds are collected; fix mutation bug modifying original RunOutput.messages; fix arun() using wrong ID for file save.

What's Changed

• fix: propagate chunk_size to default chunking strategies in reader classes by @sannya-singal in #7212
• cookbook: offline mode support for Qdrant hybrid search by @sannya-singal in #7181
• fix: implement dynamic batch splitting for ChromaDB operations by @sannya-singal in #7148
• fix: continue_run now pauses at Condition, Loop, and Router HITL steps by @ysolanky in #7227
• fix: exclude interface routes from JWT middleware by @ashpreetbedi in #7252
• cookbook: add HITL config save/load workflow examples by @ysolanky in #7225
• feat: add /info api to return agent, team, workflow count by @kausmeows in #7190
• fix: improve /info endpoint auth bypass and response model by @ysolanky in #7256
• fix: group trace session stats by session_id only by @kausmeows in #7243
• fix: use array::first() for SurrealDB trace session stats by @ysolanky in #7257
• fix: enhance /sessions list API to return additional session fields responses by @uzaxirr in #6270
• feat: add show_member_tool_calls param and card overflow rotation for Slack streaming by @Mustafa-Esoofally in #7244
• feat: add subset matching and argument validation to ReliabilityEval by @harshsinha03 in #7230
• fix: add missing messages parameter to VertexAI and Bedrock _prepare_request_kwargs by @harshsinha03 in #7245
• feat: enable channel summarization in Slack interface by @Mustafa-Esoofally in #7255
• chore: release 2.5.13 by @ysolanky in #7258

Full Changelog: v2.5.12...v2.5.13

Original source

What's Changed

• fix: preserve server tool blocks in Claude conversation history by @Mustafa-Esoofally in #6879
• [feat] Docling tool integration with tests and cookbook example by @juliomsilva in #6277
• feat: add SchedulerTools toolkit for agent-driven schedule management by @ysolanky in #7221
• fix: Coda integration fixes (CodingTools, Slack, team streaming, learning) by @ashpreetbedi in #7208
• fix: handle msg_too_long in Slack streaming path by @Mustafa-Esoofally in #7219
• chore: release 2.5.12 by @ysolanky in #7229

New Contributors

• @juliomsilva made their first contribution in #6277

Full Changelog: v2.5.11...v2.5.12

Original source

Changelog

New Features

Google Sides Toolkit: Added new slides toolkits for creating / editing and working with Google slides

Google Auth Toolkit: Added GoogleAuth toolkit and shared auth decorator for Google toolkits.

Models: Added cross-model tool call compatibility to facilitate interchanging model pattern.

Chunking: Added custom prompt support to AgenticChunking

Perplexity: Added a PerplexitySearch toolkit.

Improvements

Migration: Added migration for approvals table run_status column valid for ≥v2.5.6

LanceDb: Updated to deduplicate search results in search() in order to avoid hybrid search returning the same document from both vector and FTS branches.

Seltz Toolkit: Updates for Seltz SDK integration from 0.1.x to 0.2.0.

Bug Fixes

Team: Fixed async toolkit tools not appearing in team system message tool names.

LanceDB: Fixed duplicate results when using hybrid search.

Claude:

Added support for Anthropic's top-level output_config request parameter for Claude wrappers, so users can pass values like output_config={"effort": "high"} together with adaptive thinking.

Preserve $defs in Claude tool schema formatting

Extract file_ids and container info in streaming path for Claude skills

Tool Calling: Fixed parsing of tool calls to use assign instead of append function name in streaming parse_tool_calls.

LiteLLM: Updated to prevent empty strings from overwriting tool names in LiteLLM streaming

AWS Bedrock: Fixed to ****fail fast for unsupported AWS_BEDROCK_API_KEY auth in Claude.

Azure OpenAI: Fixed to override deepcopy to preserve client references.

Openrouter: Fixed to skip empty reasoning block for non-reasoning models.

Caching Responses: Updated to handle non-serializable types in cache key generation.

What's Changed

• fix: include async toolkit functions in team system message tool names by @kausmeows in #7042
• feat: cross-model tool call compatibility for interchange model pattern by @ysolanky in #6971
• feat: add Claude output_config passthrough by @SalimELMARDI in #7067
• chore: update exa tools description by @theishangoswami in #7099
• fix: assign instead of append function name in streaming parse_tool_calls by @metaphorics in #6989
• feat: add custom prompt support to AgenticChunking by @sannya-singal in #7085
• fix: prevent empty strings from overwriting tool names in LiteLLM streaming by @kausmeows in #7132
• fix: preserve $defs in Claude tool schema formatting by @Mustafa-Esoofally in #6085
• [fix] fail fast for unsupported AWS_BEDROCK_API_KEY auth in Claude by @pandego in #6855
• [fix] Extract file_ids and container info in streaming path for Claude skills by @adiberk in #7109
• fix: Azure OpenAI async client auth by @lmgarret in #6955
• fix(openrouter): skip empty reasoning block for non-reasoning models by @pratikm778 in #6946
• feat(tools): add PerplexitySearch toolkit by @kesku in #6951
• feat: Add GoogleSlidesTools toolkit (Closes #6829) by @anshul-jain-devx108 in #6830
• fix: gh ci workflow by @kausmeows in #7152
• fix: handle non-serializable types in cache key generation by @ysolanky in #7155
• fix: remove litellm from ci due to incident by @kausmeows in #7154
• feat: rewrite GoogleDriveTools with smart export and async support by @Mustafa-Esoofally in #6995
• feat: add GoogleAuth toolkit and shared auth decorator for Google toolkits by @Mustafa-Esoofally in #7098
• chore: add migration for approvals table run_status column by @kausmeows in #7158
• fix: lancedb deduplicate search results by @harsh21234i in #7061
• feat: update seltz integration to SDK 0.2.0 by @WilliamEspegren in #6891
• fix: resolve grpcio version conflict breaking CI tests by @ysolanky in #7184
• chore: release 2.5.11 by @ysolanky in #7071

New Contributors

@theishangoswami made their first contribution in #7099

@metaphorics made their first contribution in #6989

@pandego made their first contribution in #6855

@lmgarret made their first contribution in #6955

@pratikm778 made their first contribution in #6946

@kesku made their first contribution in #6951

@anshul-jain-devx108 made their first contribution in #6830

@harsh21234i made their first contribution in #7061

Full Changelog: v2.5.10...v2.5.11

Original source

Changelog

New Features:

Parallel Search Tool: Add Parallel AI Search support for Vertex AI with native ToolParallelAiSearch integration

Observability: Extended support with MLflow to have full traces observability of your agents. See docs.

Docling Reader: Integrated Docling library as a new reader, enabling document processing across a multiple range of file formats.

WhatsApp Interface V2:

Added media support (images, video, audio, documents), interactive messages (reply buttons, list menus, locations, reactions), and Team/Workflow support.

Users can send /new to start fresh conversations.

Added enable_encryption parameter for encrypting phone numbers

Telegram Interface:

Added new Telegram interfaces for AgentOS with support for agents, teams, and workflows.

Multi-modal support and use /new to start fresh conversations.

Telegram Tools: Added new tools so agents can send photos, documents, videos, audio, animations, stickers among other things

Improvements:

Workflow:

Added version query param to GET /workflows/{id}to fetch specific workflow versions.

Added run level params like- metadata, dependencies, add_dependencies_to_context, add_session_state_to_context similar to agent/team.

Mistral: Added mistralai v2 support while maintaining backward compatibility with v1.

Gemini: Added timeout parameter to Gemini model class.

Bug Fixes:

MCPTools: Fixed race condition where parallel MCP tool calls with header_provider would each create duplicate sessions, causing the agent to get stuck.

Claude: Fixed structured output detection for supported models

Streaming Tool Calls: Fixed duplicate tool execution in streaming mode caused by shared dict references in parse_tool_calls

MongoDb: Fixed the incorrect import of the pymongo async modules.

What's Changed

fix: prevent deadlock in parallel MCP tool calls with header_provider (fixes #6094) by @giulio-leone in #6821

fix: remove unnecessary fast-path stale session cleanup in MCPTools by @ysolanky in #6949

feat: add Parallel web search grounding for Vertex AI Gemini by @ysolanky in #6060

fix: correct async MongoDB import by @v-vinson in #6399

fix: mongo validation by @kausmeows in #6957

feat: add version query param to GET /workflows/{id} endpoint by @harshsinha03 in #6956

fix: async PostgresDb returns None for missing tables instead of logging ERROR by @kausmeows in #6965

[fix] replace fragile blocklist with prefix-based structured output detection by @hztBUAA in #6643

cookbook: add MLflow observability integration via OpenInference by @ysolanky in #6930

chore: add PR triage automation and improve contribution guidelines by @ysolanky in #6959

fix: support mistral v2 imports by @harshsinha03 in #6969

feat: add run-level params to Workflow.run() and arun() by @uzaxirr in #6927

fix: separate chat and responses metrics by @ysolanky in #6973

feat: add Telegram interface and extended TelegramTools by @Mustafa-Esoofally in #6377

chore: consolidate pr-triage workflow into single comment by @ysolanky in #7013

feat: add timeout parameter to Gemini model class by @fehmisener in #7021

fix: use list comprehension in parse_tool_calls to prevent shared dict references by @ArivunidhiA in #6579

feat: add Docling reader integration for advanced document processing by @sannya-singal in #6981

fix: register Telegram interfaces in system test gateway by @Mustafa-Esoofally in #7026

feat: WhatsApp interface V2 — media I/O, interactive tools, Team/Workflow support by @Mustafa-Esoofally in #6466

fix: use valid Telegram bot token format in system tests by @Mustafa-Esoofally in #7027

chore: Release v2.5.10 by @kausmeows in #7011

New Contributors

@v-vinson made their first contribution in #6399

@sannya-singal made their first contribution in #6981

Full Changelog: v2.5.9...v2.5.10

Original source

Changelog

New Features:

• Followups: Added built-in followup suggestions for Agent and Team. See cookbook.
• Datetime Format: Added datetime_format parameter to Agent and Team, allowing custom strftime formatting for datetime context (e.g., ISO-8601, date-only, localized).
• Tool Hook Message History: Tool pre/post hooks and agent-level tool_hooks can now access the current run's message history via run_context.messages
• GoogleCalendarTools: Extended GoogleCalendarTools with new tools, service account auth, and cookbooks.

Bug Fixes:

• HITL: Fixed human in the loop to support add_history_to_context during multi-round conversations while running
• Tools: Removed (None) prefix from tool parameter descriptions
• Siliconflow Model Provider: Updated to use correct default base_url from .com to .cn
• Learning PROPOSE Mode: Auto-enable chat history for LearningMode.PROPOSE for multi-turn confirmation.
• AgentOS API Docs: Added descriptions to all Form/File parameters across agent, team, and workflow API endpoints for OpenAPI/Swagger visibility

What's Changed

• fix: resolved continue_run, missing history messages issue by @abhi10691 in #6888
• fix: remove (None) prefix from tool parameter descriptions by @fehmisener in #6906
• feat: add datetime_format to Agent and Team for custom datetime context by @hztBUAA in #6649
• feat: expose run message history to tool hooks with mutation safety by @hztBUAA in #6652
• feat: built-in followup suggestions for Agent and Team by @ysolanky in #6672
• [fix] siliconflow: correct default base_url from .com to .cn by @NIK-TIGER-BILL in #6933
• feat: extend GoogleCalendarTools with new tools, service account auth, and cookbooks by @Mustafa-Esoofally in #6926
• fix: auto-enable chat history for LearningMode.PROPOSE by @Mustafa-Esoofally in #6928
• chore: add form parameter descriptions to AgentOS API endpoints by @uzaxirr in #6941
• chore: Release v2.5.9 by @kausmeows in #6940

New Contributors

• @abhi10691 made their first contribution in #6888
• @NIK-TIGER-BILL made their first contribution in #6933

Full Changelog: v2.5.8...v2.5.9

Original source