v2.6.0

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.

v2.5.17

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

v2.5.16

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

v2.5.15

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

v2.5.14

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

v2.5.13

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

v2.5.12

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

v2.5.10

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

v2.5.9

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

v2.5.8

Changelog

New Features

• Human-Readable IDs: Agents and teams now use human-readable identifiers (e.g., brave-falcon-7x3k) instead of UUIDs, making debugging and monitoring more intuitive.
• AgentOS: serve() now supports AGENT_OS_HOST and AGENT_OS_PORT environment variables as fallbacks, simplifying container deployments.
• GitlabTools: Added GitlabTools with read-focused GitLab integrations, async support, and cleaner tool configuration.
• GmailTools: Extended GmailTools with new tools and service account auth.

Bug Fixes

• Media in Run Output: Generated media (images, audio) is now always included in run output, regardless of the store_media setting and is rather scrubbed before storing in DB
• OpenAIResponses: Fixed handling of mixed external_execution and regular tools when using OpenAI Responses API.
• MySQL: Added json_serializer to MySQL engine creation for proper JSON handling.
• PostgreSQL: Removed session_type filter from get_session to prevent session data loss when session types change.
• Workflow: Fixed a bug where Loop iterations always received the original input instead of the previous iteration's output. Added a flag forward_iteration_output to opt-in to this behaviour.

What's Changed

• feat: Docker-style human-readable IDs for agents and teams by @ysolanky in #6869
• feat: add AGENT_OS_HOST/AGENT_OS_PORT env var fallbacks to serve() by @Mustafa-Esoofally in #6857
• fix: remove session_type filter from PostgreSQL get_session to prevent session data loss by @kausmeows in #6873
• fix: add json_serializer to MySQL engine creation by @willemcdejongh in #6848
• [fix] handle mixed external_execution and regular tools for OpenAI by @hztBUAA in #6630
• fix: include generated media in run output regardless of store_media setting by @Br1an67 in #6793
• cookbook: add x402scan MCP tools example by @SamOpenClaw in #6555
• feat: add GitlabTools with tests and cookbook example by @SalimELMARDI in #6721
• feat: extend GmailTools with new tools, service account auth, and agentic cookbooks by @Mustafa-Esoofally in #6765
• fix: loop iterations to forward output from previous iteration by @kausmeows in #6868
• fix: resolve duplicate operationId warnings in disabled feature router by @kausmeows in #6887
• chore: Release v2.5.8 by @kausmeows in #6886

New Contributors

• @SamOpenClaw made their first contribution in #6555
• @SalimELMARDI made their first contribution in #6721

Full Changelog: v2.5.7...v2.5.8