v3.0.11
microsoft/TinyTroupev3.0.11Sep 23, 2026by kausmeows
Upgrading?
AI Summary
Update introducing knowledge retrieval pipelines, new rerankers, and enhanced MCP tool schemas.
Key Highlights
- Introduced Knowledge Retrieval Pipeline with MMR and Recency Rerankers.
- Added Y-API as an OpenAI-compatible model provider.
- Enhanced MCP tool schemas with descriptions and improved pagination.
- Added typed page tool results and cancellation stage tracking.
Breaking Changes
- Vector DB Reranker is deprecated in favor of the reranker on Knowledge.
New Features
- Knowledge search pipeline with reranking capabilities.
- MMR (Maximal Marginal Relevance) Reranker.
- Recency Reranker for prioritizing newer revisions.
- Page Source Relocation API.
- Typed Page Command Results.
- Cancellation stage tracking for runs.
Full Release Notes
# Changelog ## New Features: - **Knowledge Retrieval Pipeline**: `Knowledge.search()` now runs a knowledge level retrieval pipeline that can widen the candidate pool before a reranker reorders it, so rerankers no longer need to be implemented per vector db. - **MMR Reranker**: Added `MMRReranker` (Maximal Marginal Relevance) as a retrieval strategy that balances relevance against diversity so near-duplicate chunks do not crowd out the result set. - **Page Source Relocation**: Added `Knowledge.inspect_page_source` / `ainspect_page_source` and guarded `migrate_page_source` / `amigrate_page_source` to move an indexed documentation source to a new hostname. Migration is a dry run by default. - **Recency Reranker**: Added `RecencyReranker`, which blends the search score with an exponential decay on a timestamp so newer revisions outrank superseded ones. Built on the knowledge level pipeline, focused on pgvector. - **Typed Page Tool Results**: Added `PageCommandResult` and `PageFileSystem.run_command_result` / `arun_command_result` with explicit error, completeness and truncation metadata. `Knowledge.get_tools(page_results=True)` returns ranked `SearchResult` objects, including as MCP structured output. - **Y-API**: Added `YAPI` as an OpenAI-compatible model provider. - **Cancellation Stage**: Added a machine-readable `cancellation_stage` (`PENDING`, `EXECUTING`, `INTERRUPTED`, or unknown) to `RunOutput`, `TeamRunOutput`, `WorkflowRunOutput` and the run API schemas, so clients no longer match on the cancellation message text. - **OpenAIResponses**: Added `use_previous_response_id` so `store=True` no longer forces automatic `previous_response_id` chaining. ## Improvements: - **MCP Tool Schemas**: Every argument on the AgentOS MCP tools now carries a description in its `inputSchema`, and `get_sessions` bounds `limit` and `page` to a minimum of 1. - **Reasoning Detection**: DeepSeek thinking-mode model IDs are recognised as reasoning models when served through any `OpenAILike` provider such as `DashScope`. - **Tools**: Removed phantom `Args` entries from tool docstrings and corrected streaming docstring parameter names in two model classes. ## Bug Fixes: - **Tool Hooks**: Sync hooks that return `function_call(**arguments)` now work in the async execution path. Previously the chain treated the unawaited coroutine as the tool result and the tool body never ran. - **MCP Server Card**: Bare `mcp=True` now installs the same routing layer as `MCPConfig`, so the Host check and mount prefix apply on both spellings. Dropped the unimplemented `ETag` / `If-None-Match` CORS headers. - **MCP Tools**: Tool discovery over a raw `ClientSession` now collects every `tools/list` page instead of only the first. - **AG-UI**: Support `ag-ui-protocol` 1.0, including list-valued tool result content on resume. - **Workflows over WebSocket**: Version-pinned submissions are no longer queued without their pin, session ownership is checked on the write path, and a missing session id mints a new session like HTTP. - **JSONReader**: Preserve scalar JSON roots. - **CSVReader**: Read text streams, not only byte streams. - **CSVReader & FieldLabeledCSVReader**: Validate `page_size` before reading, so zero or negative values raise `ValueError` instead of silently returning no documents. - **Structured Output Parsing**: Ignore unmatched closing braces in prose when extracting JSON objects from model output. - **GoogleDriveTools**: Read text inside grouped shapes and honour line breaks when extracting `.pptx` text. - **UTF-8 Files**: `read_yaml_file` / `write_yaml_file`, `AntigravityTools` and `AirflowTools` now read and write files as UTF-8 regardless of locale. - **DuckDbTools**: Escape CSV delimiters. - **TavilyTools**: Forward extract options. - **Cookbooks & Docs**: Replaced dead links in knowledge sources and fixed a duplicated word in the V3 migration guide. Added Inspeximus memory and Confident AI observability examples. ## Deprecations: - **Vector DB Reranker**: The `reranker` parameter on vector databases is deprecated in favour of the reranker on `Knowledge`, which applies to every vector db and supports async. ## What's Changed * chore: remove phantom Args entries in the tool docstrings by @simpleqt in https://github.com/agno-agi/agno/pull/10229 * cookbook: add Confident AI observability example by @kausmeows in https://github.com/agno-agi/agno/pull/10257 * fix: correct streaming docstring parameter names in two model classes by @simpleqt in https://github.com/agno-agi/agno/pull/10228 * feat: add knowledge level retrieval pipeline and MMR reranker by @sannya-singal in https://github.com/agno-agi/agno/pull/10115 * fix: bring WebSocket workflow submissions in line with the HTTP admission rules by @ysolanky in https://github.com/agno-agi/agno/pull/10179 * [fix] Paginate MCP tool discovery for ClientSession by @sicauzxl in https://github.com/agno-agi/agno/pull/10012 * fix: support ag-ui-protocol 1.0 in the AG-UI interface by @Himanshu040604 in https://github.com/agno-agi/agno/pull/10283 * [feat] Add Y-API as an OpenAI-compatible model provider by @jiweiyeah in https://github.com/agno-agi/agno/pull/10326 * [fix] Correct duplicated word in V3 migration guide by @yetuge in https://github.com/agno-agi/agno/pull/10315 * [fix] replace dead links in cookbook knowledge sources and docs references by @Theater-ahyeon in https://github.com/agno-agi/agno/pull/10160 * [cookbook] Add inspeximus memory integration example by @DanceNitra in https://github.com/agno-agi/agno/pull/10146 * fix: recognize DeepSeek thinking-mode IDs in OpenAILike reasoning detection by @yetuge in https://github.com/agno-agi/agno/pull/10342 * [fix] Validate page_size in FieldLabeledCSVReader by @tdog54646 in https://github.com/agno-agi/agno/pull/10358 * fix: decouple OpenAI response storage from automatic chaining by @ashpreetbedi in https://github.com/agno-agi/agno/pull/10075 * feat: deprecate the vector db level reranker by @sannya-singal in https://github.com/agno-agi/agno/pull/10385 * feat: add guarded documentation source relocation API by @ashpreetbedi in https://github.com/agno-agi/agno/pull/10096 * feat: expose typed page command and search tool results by @ashpreetbedi in https://github.com/agno-agi/agno/pull/10097 * [fix] read text streams in CSVReader instead of only byte streams by @harbinresearcher in https://github.com/agno-agi/agno/pull/10355 * [fix] Escape CSV delimiters in DuckDbTools by @imexlovery in https://github.com/agno-agi/agno/pull/10415 * [fix] Forward Tavily extract options by @daleselaji-dev in https://github.com/agno-agi/agno/pull/10403 * [fix] Preserve scalar JSON roots in JSONReader by @daleselaji-dev in https://github.com/agno-agi/agno/pull/10402 * fix: route bare mcp=True like MCPConfig for the MCP server card by @ysolanky in https://github.com/agno-agi/agno/pull/10418 * fix: describe and bound the MCP tool arguments by @ysolanky in https://github.com/agno-agi/agno/pull/10419 * [fix] Validate CSVReader page sizes before reading by @emme1t in https://github.com/agno-agi/agno/pull/10437 * feat: add cancellation_stage to cancelled runs by @ysolanky in https://github.com/agno-agi/agno/pull/10411 * fix: read and write YAML, Antigravity and Airflow files as UTF-8 by @MohammadHijjawi97 in https://github.com/agno-agi/agno/pull/10242 * fix: read grouped shapes and line breaks in Drive pptx text by @devYRPauli in https://github.com/agno-agi/agno/pull/10473 * [fix] Ignore unmatched closing braces when extracting JSON objects by @makiaveli1 in https://github.com/agno-agi/agno/pull/10421 * feat: add recency reranker by @sannya-singal in https://github.com/agno-agi/agno/pull/10396 * fix: await sync hook continuations in async chains by @kausmeows in https://github.com/agno-agi/agno/pull/10481 * fix: drop IMDB CSV from knowledge URL tests to stop CI timeouts by @sannya-singal in https://github.com/agno-agi/agno/pull/10498 * chore: Release v3.0.11 by @kausmeows in https://github.com/agno-agi/agno/pull/10444 ## New Contributors * @sicauzxl made their first contribution in https://github.com/agno-agi/agno/pull/10012 * @jiweiyeah made their first contribution in https://github.com/agno-agi/agno/pull/10326 * @yetuge made their first contribution in https://github.com/agno-agi/agno/pull/10315 * @Theater-ahyeon made their first contribution in https://github.com/agno-agi/agno/pull/10160 * @DanceNitra made their first contribution in https://github.com/agno-agi/agno/pull/10146 * @tdog54646 made their first contribution in https://github.com/agno-agi/agno/pull/10358 * @harbinresearcher made their first contribution in https://github.com/agno-agi/agno/pull/10355 * @imexlovery made their first contribution in https://github.com/agno-agi/agno/pull/10415 * @emme1t made their first contribution in https://github.com/agno-agi/agno/pull/10437 * @MohammadHijjawi97 made their first contribution in https://github.com/agno-agi/agno/pull/10242 * @makiaveli1 made their first contribution in https://github.com/agno-agi/agno/pull/10421 **Full Changelog**: https://github.com/agno-agi/agno/compare/v3.0.10...v3.0.11
Related Repositories
rasbt/LLMs-from-scratch★ 107,077
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lyogavin/airllm★ 40,206
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,960
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,539
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,907
Neural Networks: Zero to Hero