NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI
PyPI
Microsoft Agent Framework for building AI Agents with Python. This package contains core and a curated set of optional integrations.
Latest stable
1.25.0
Last release 15 days ago
07 Nov 2026
Ships on a steady schedule
a new release about every 2 weeks
Nearly every release is documented
notes for 31 of 32 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
66 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
Nothing published for this version
Redis context index migration: The beta RedisContextProvider now preserves exact scope identity and rejects the legacy raw-scope index schema. Delete
Warning
Redis context index migration: The beta RedisContextProvider now preserves exact scope identity and rejects the legacy raw-scope index schema. Delete the old context index and its context hashes, let the provider create a new index, and re-ingest the context data. overwrite_index=True does not migrate incompatible indexes.
Important
Python support: Python 3.11 or later is now the supported baseline, subject to package-specific upper limits. Python 3.10 installation remains permitted by Requires-Python in this release, but compatibility is not guaranteed. The next release will also remove Python 3.10 installation eligibility from Requires-Python . Upgrade to Python 3.11 or later as soon as possible.
agent-framework-core : Add an explicit default approval mode for local MCP tools and prompts outside the per-tool approval lists, and warn when never_require_approval leaves the default implicit while preserving the existing fallback ( #9828 )
agent-framework-core : Add the shared microsoft.agent-framework telemetry resource attribute across logs, traces, and metrics while preserving explicit resource overrides ( #9589 )
agent-framework-core : Add experimental agent-triggered in-run compaction and skill unloading with AgentTriggeredCompactionStrategy and UnloadSkillsCompactionStrategy ( #9384 )
agent-framework-core : Support async conditions in switch-case workflow edge groups ( #9669 )
agent-framework-core : Load Agent Hooks middleware from a host declaration and support tool-name prefixes on FileAccessProvider ( #9405 , #9654 )
agent-framework-core , agent-framework-anthropic , agent-framework-bedrock , agent-framework-foundry , agent-framework-foundry-local , agent-framework-gemini , agent-framework-mistral , agent-framework-ollama , agent-framework-openai : Add optional async chat-client contexts and ownership-aware connection cleanup without closing caller-supplied resources ( #9748 )
agent-framework-foundry : Add a timeout parameter to FoundryChatClient ( #9699 )
agent-framework-nvidia , agent-framework-openai : Add an alpha NVIDIA NIM embedding client and the OpenAI-compatible embedding request-options extension point it requires ( #8920 )
agent-framework-oracle : Require python-oracledb 3.0 or later so the supported dependency floor passes strict pool API type checking.
tests : Declare package-local test dependencies for isolated dependency-bound checks, match NVIDIA test transports to the OpenAI SDK's HTTPX version, preserve meaningful assertions across supported Pydantic and Foundry SDK versions, and exclude virtual environments from feature-registry source discovery.
agent-framework-claude : Require Claude Agent SDK 0.2.140 or later for custom-tool servers compatible with MCP 2.
agent-framework-azure-documentdb , agent-framework-mongodb : Require PyMongo 4.15 or later for complete asynchronous bulk-write type annotations at the supported dependency floor.
agent-framework-redis : [BREAKING] Preserve case-sensitive, punctuation-safe context scope identity with dedicated scope tokens, enforce configured scope on writes and searches, and reject incompatible legacy indexes ( #9461 )
agent-framework , agent-framework-a2a , agent-framework-ag-ui , agent-framework-anthropic , agent-framework-azure-ai-search , agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos , agent-framework-azure-documentdb , agent-framework-bedrock , agent-framework-chatkit , agent-framework-claude , agent-framework-copilotstudio , agent-framework-core , agent-framework-declarative , agent-framework-devui , agent-framework-duckdb , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-foundry-local , agent-framework-gemini , agent-framework-hosting , agent-framework-hosting-a2a , agent-framework-hosting-mcp , agent-framework-hosting-responses , agent-framework-hosting-telegram , agent-framework-hyperlight , agent-framework-mem0 , agent-framework-mistral , agent-framework-mongodb , agent-framework-monty , agent-framework-nvidia , agent-framework-ollama , agent-framework-openai , agent-framework-oracle , agent-framework-orchestrations , agent-framework-postgres , agent-framework-purview , agent-framework-qdrant , agent-framework-redis , agent-framework-sql-server , agent-framework-tools , agent-framework-typesafe : Stop advertising Python 3.10 support while retaining installation compatibility metadata, and document Python 3.11 as the supported baseline ( #9824 )
agent-framework-monty : Bound captured file counts and per-file and total byte sizes, and report omitted output explicitly ( #9802 )
agent-framework-tools : Apply shell output limits to standard error as well as standard output ( #9795 )
agent-framework-devui : Improve generated file display and URL handling ( #9792 )
agent-framework-devui : Update Zustand to 5.0.16 and ESLint to 10.13.0, pin TypeScript to the compatible 5.9.3 version, and rebuild the bundled UI ( #9833 , #9835 )
agent-framework-nvidia : Allow Flit Core 4.x as a build backend ( #9839 )
tests , samples : Update Pyrefly to 1.4.0 with explicit provider option types, upgrade Griffe to 2.4.1 so attribute-value changes no longer produce API compatibility false positives, and refresh the standalone Lab lockfile to LiteLLM 1.106.2 ( #9838 , #9840 , #9842 , #9834 , #9837 )
agent-framework-azure-contentunderstanding : Align the Azure Content Understanding SDK dependency floor ( #9695 )
agent-framework , agent-framework-core : Advance the exact Core pin and standard-install dependency cohort to the versions in this release.
agent-framework-anthropic , agent-framework-azure-cosmos , agent-framework-bedrock , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-foundry-local , agent-framework-gemini , agent-framework-mistral , agent-framework-ollama , agent-framework-openai : Require Core 1.24 for inherited chat-client lifecycle methods, citation helpers, or checkpoint encoding; retain other Core floors under the strict API-usage policy.
agent-framework-foundry , agent-framework-foundry-local , agent-framework-nvidia : Require OpenAI 1.18 for owned-client cleanup or the new embedding request-options hook.
agent-framework-hosting-a2a , agent-framework-hosting-mcp , agent-framework-hosting-responses , agent-framework-hosting-telegram : Keep the exact shared hosting dependency pin aligned with its co-released version.
docs , samples : Refresh chat-client selectors and lifecycle guidance, compaction, harness file-memory configuration, skills environment setup, Foundry Toolbox tool search, Foundry memory settings, Redis context usage, ChatKit startup and weather widgets, migration examples, and sample run commands; add OpenViking, Membase, BotsRated, and ACGS community entries ( #9673 , #9748 , #9384 , #9670 , #9700 , #9113 , #9741 , #9446 , #9579 , #9599 , #9580 , #9641 , #9683 , #9660 , #9618 )
docs , tests : Refresh development setup, coding standards, sample guidance, and tooling helpers; validate dependency bounds for version bumps and new packages; prepare reviewed release manifests for the protected Azure DevOps publisher ( #9733 , #9637 , #9706 , #9668 , [ #9801 ]( https://github.com/microsoft/agent ...
Read more
Assets 89 Loading
There was an error while loading. Please reload this page .
All reactions
Your coding agent can read these notes before it upgrades. Set up the MCP server →
agent-framework-a2a : Add allowlisted forwarding of function-invocation and client arguments from A2A request metadata
agent-framework-a2a : Add allowlisted forwarding of function-invocation and client arguments from A2A request metadata ( #9193 )
agent-framework-core , agent-framework-orchestrations : Add an opt-in synthetic trailing user turn for providers that return empty text after assistant-ending prompts ( #8779 )
agent-framework , agent-framework-ag-ui , agent-framework-core , agent-framework-declarative , agent-framework-foundry-hosting , agent-framework-hosting-mcp , agent-framework-lab : [BREAKING] Add the MCP 2.x compatibility foundation and migrate MCP transports, errors, schemas, and lifecycle handling ( #9236 )
agent-framework-ag-ui , agent-framework-core : [BREAKING] Require an explicit AG-UI authorization scope or single-user declaration for endpoint registration ( #9413 )
agent-framework-tools : [BREAKING] Rename Docker shell extra_run_args to unsafe_extra_run_args and make its trust requirements explicit ( #9453 )
agent-framework-tools : Raise the psutil floor to the first release with Windows ABI3 wheels for the supported Python range.
agent-framework , agent-framework-core : Advance the exact Core pin and standard-install dependency cohort to the package versions released in this cut.
agent-framework-declarative , agent-framework-devui , agent-framework-foundry-hosting , agent-framework-orchestrations : Raise the Core floor to 1.23 for packages that consume the new MCP lifecycle or executor behavior.
agent-framework-core , agent-framework-devui : Define caller-owned and framework-owned MCP client lifecycles, remove DevUI's stale-connection workaround, and update lifecycle guidance and workflow samples ( #9237 , #9532 )
agent-framework , agent-framework-ag-ui , agent-framework-core , agent-framework-duckdb , agent-framework-hyperlight : Add Python 3.15 support for DuckDB, Hyperlight, and the AG-UI A2UI extra by requiring DuckDB 2.0 on Python 3.15, Hyperlight 0.8, and A2UI toolkit 0.0.5, and adapt Hyperlight output-limit handling to the 0.8 size and quota behavior ( ag-ui-protocol/ag-ui#3057 , duckdb/duckdb-python#659 , hyperlight-dev/hyperlight-sandbox#239 )
agent-framework-devui , agent-framework-lab , tests , samples : Refresh Hugging Face Hub, frontend, Agent Framework, Pydantic, OpenTelemetry, orjson, development-tooling, and security-constrained dependencies ( #9416 , #9420 , #9421 , #9422 , #9423 , #9590 )
docs , samples : Refresh Content base64, Message URI, ChatResponse aggregation, and tool-normalization examples; ATR validation; Cosmos memory scoping; community MCP and Tracekit catalog entries; Foundry Toolbox setup; Foundry evals; Copilot Studio migrations; A2A hosting; ChatKit streaming; Purview middleware; and DevUI local-auth guidance ( #9332 , #9333 , #9433 , #9443 , #9447 , #9467 , #9497 , #9518 , #9521 , #9523 , #9550 , #9551 , #9553 , #9575 , #9576 , #9577 )
tests : Expand DevUI coverage for reasoning chunks without text ( #9543 )
agent-framework-core : Rebuild nested content, accept Literal workflow-edge sources, close abandoned inner streams, pass stream errors into nested streams during closure, make Memory and Todo writes atomic, bind background completion waits to execution identity, support keyword-only functional-workflow contexts, isolate MCP task contexts, normalize tool-name whitespace, recommend include_detailed_errors=True in function-execution warnings only when detailed errors are disabled, improve settled approval matching, recover owned MCP connections safely, and omit span-only tool attributes from invocation metrics ( #9304 , #9355 , #9331 , #9397 , #9412 , #9442 , #9451 , #9472 , #9476 , #9557 , #9535 , #9583 , #9592 )
agent-framework-ag-ui : Preserve every queued approval result and repeated single-chunk text deltas ( #8851 , #9339 )
agent-framework-anthropic : Keep bash tool-result files nested inside their shell tool result ( #9343 )
agent-framework-azure-cosmos-memory : Reject non-positive result limits and confidence values outside the supported range ( #9318 )
agent-framework-bedrock : Merge per-call client arguments into Converse requests, resolve embedding regions consistently, and report the requested model on non-streaming responses ( #9345 , #9349 , #9399 )
agent-framework-declarative : Match custom functions as whole calls and honor the configured variable in SetValue actions ( #9176 , #9428 )
agent-framework-devui : Emit an empty reasoning delta when a reasoning chunk has no text ( #9546 )
agent-framework-foundry-hosting , agent-framework-hosting-responses : Sanitize unexpected streaming response failures before exposing them through Responses-shaped adapters ( #9460 )
agent-framework-gemini : Send extracted structured-output schemas through the Gemini JSON Schema request field and set the assistant role on streamed updates ( #9491 , #9590 )
agent-framework-lab : Prefer the over-budget warning when a Tau2 sliding window exceeds its token limit ( #9341 )
agent-framework-ollama : Decode and validate inline image data before passing it to the Ollama SDK ( #9459 )
agent-framework-redis : Close the RedisVL search-index connection when the context provider owns it ( #9510 )
agent-framework-tools : Prevent stateless shell tools from inheriting host standard input ( #9469 )
Assets 91 Loading
There was an error while loading. Please reload this page .
All reactions
Python 3.15 support: The core framework and root agent-framework package now support Python 3.15, but not every package, optional extra, or feature su
Important
Python 3.15 support: The core framework and root agent-framework package now support Python 3.15, but not every package, optional extra, or feature supports it yet because of upstream dependency constraints. Before upgrading, check the README for each package and extra you use. The Python README summarizes the currently known limitations.
Warning
Persisted-state compatibility: This applies to persisted artifacts that contain serialized Agent Framework Content or streamed response-update records. That includes chat and message histories; session stores and protocol snapshots when they embed those records; and workflow checkpoints only when their checkpoint state contains them. Plain session metadata and checkpoints without serialized messages, content, or response updates are unaffected.
The 1.22 runtime can read records written by earlier releases, but pre-1.22 runtimes cannot read new records containing hosted or merge_mode . Do not run old and new workers against the same affected store during a rolling deployment, and do not downgrade after 1.22 has written these records unless the new state is isolated or migrated.
agent-framework-azure-cosmos-memory : Add a dedicated Cosmos memory provider User-Agent token ( #9223 )
agent-framework-foundry : Surface OAuth consent requests in non-streaming responses ( #8976 )
agent-framework-ollama , agent-framework-openai : Add configurable service URLs to chat clients ( #9222 , #9225 )
agent-framework-oracle : Forward Oracle connection-pool configuration settings ( #9233 )
agent-framework , agent-framework-a2a , agent-framework-ag-ui , agent-framework-anthropic , agent-framework-azure-ai-search , agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos , agent-framework-azure-cosmos-memory , agent-framework-azure-documentdb , agent-framework-bedrock , agent-framework-chatkit , agent-framework-claude , agent-framework-copilotstudio , agent-framework-core , agent-framework-declarative , agent-framework-devui , agent-framework-duckdb , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-foundry-local , agent-framework-gemini , agent-framework-github-copilot , agent-framework-hosting , agent-framework-hosting-a2a , agent-framework-hosting-mcp , agent-framework-hosting-responses , agent-framework-hosting-telegram , agent-framework-hyperlight , agent-framework-mem0 , agent-framework-mistral , agent-framework-mongodb , agent-framework-monty , agent-framework-ollama , agent-framework-openai , agent-framework-oracle , agent-framework-orchestrations , agent-framework-postgres , agent-framework-purview , agent-framework-qdrant , agent-framework-redis , agent-framework-sql-server , agent-framework-tools , agent-framework-typesafe : Add Python 3.15 compatibility metadata where supported, document package-specific limitations, and refresh shared dependencies and automation ( #9363 )
agent-framework-a2a , agent-framework-ag-ui , agent-framework-anthropic , agent-framework-bedrock , agent-framework-claude , agent-framework-copilotstudio , agent-framework-core , agent-framework-devui , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-gemini , agent-framework-github-copilot , agent-framework-hosting-a2a , agent-framework-hosting-responses , agent-framework-mistral , agent-framework-ollama , agent-framework-openai : [BREAKING] Consolidate content identity, hosted execution, protocol metadata, replay, and stream-merge semantics across providers and adapters ( #8886 )
agent-framework-ag-ui : [BREAKING] Enforce fail-closed request trust boundaries and bind workflow continuations and interrupts to the resolved thread ID ( #9316 , #9365 )
agent-framework-ag-ui : [BREAKING] Prevent client Shared State and stored Thread Snapshots from replacing tool-approval state, including when AG-UI wraps an agent that does not expose its middleware ( #9368 )
agent-framework-declarative : [BREAKING] Bound HTTP response bodies and compressed decoding stages with a configurable limit ( #9358 )
agent-framework-devui : Refresh frontend runtime and development dependencies ( #9230 , #9306 , #9310 )
agent-framework-purview : Include citations and error details in Purview policy checks ( #9375 )
docs , samples : Refresh response-stream, hosted-agent, security, media-detection, hosting, approval-reuse, community-project, package-promotion, and development-tooling guidance ( #8985 , #9107 , #9201 , #9229 , #9232 , #9311 , #9188 , #9360 , #9356 , #9390 )
tests : Consolidate dependency updates, separate optional provider development dependencies, and expand tool-role coverage ( #9292 , #9255 , #9323 )
agent-framework-a2a , agent-framework-core , agent-framework-openai : Preserve continuation tokens across conversions; allow empty A2A attachments and forward selected run metadata ( #9002 , #9056 , #9192 )
agent-framework-core : Accept bare container edge targets, fold streamed text efficiently, preserve memory summaries and Mermaid node identities, correlate mixed-pause host responses, validate complex tool arguments, serialize plain enums, refresh MCP prompt catalogs, retain dictionary tool schemas, restore subworkflow sibling requests, merge single mapping tools, redact sensitive telemetry, omit tool arguments from metrics, and preserve concurrent workflow steps across pauses ( #8731 , #8953 , #9079 , #9082 , #9203 , #8824 , #9195 , #9121 , #9299 , #9289 , #8732 , #9288 , #9361 , #9291 )
agent-framework-core : Treat a single string passed to Message as one text content item instead of one item per character ( #9327 )
agent-framework-core , agent-framework-declarative , agent-framework-foundry-hosting : Discard pending workflow state after failed or interrupted execution ( #8819 )
agent-framework-core , agent-framework-openai : Concatenate overlapping code-interpreter stream deltas without duplicating content ( #9142 )
agent-framework-core , agent-framework-orchestrations : Start a new streamed message when the response author changes ( #9353 )
agent-framework-core : Allow switch-case branches to share a target executor ( #9300 )
agent-framework-declarative : Parse scientific notation, evaluate quoted concatenations, preserve reusable model options, substitute templates at the correct positions, honor BreakLoop in Foreach , and avoid generated executor ID collisions ( #9077 , #9073 , #9068 , #9096 , [ #9091 ]( https://github.com/microsoft/agent-framework/ ...
Read more
Assets 89 Loading
There was an error while loading. Please reload this page .
All reactions
agent-framework , agent-framework-core , agent-framework-purview : Add tool-result standing guidance, expose rewritten variable-expansion arguments, a
agent-framework , agent-framework-core , agent-framework-purview : Add tool-result standing guidance, expose rewritten variable-expansion arguments, and support full-buffer Purview policy evaluation for streamed responses ( #8784 , #8506 , #8702 )
agent-framework-openai : Add the maximum reasoning-effort option ( #8857 )
agent-framework-oracle : Add the alpha Oracle native vector-store connector ( #8676 )
samples : Demonstrate group-chat response filtering and expand the get-started sample progression ( #9005 , #9133 )
agent-framework-core , agent-framework-foundry , agent-framework-github-copilot : Isolate provider-owned service session state when agents are invoked as tools ( #8853 )
agent-framework-anthropic : Update the Anthropic SDK to 1.11 and adapt Anthropic and Bedrock client behavior ( #9119 )
agent-framework-github-copilot : Update the GitHub Copilot SDK to 1.0.16 ( #9135 )
agent-framework-devui : Update source-map-js , Radix UI Scroll Area, tailwind-merge , Tailwind CSS and its Vite plugin, and patch brace-expansion 1.x ( #9104 , #9154 , #9155 , #9156 , #8888 )
agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos-memory , samples : Normalize Foundry project endpoint configuration and examples ( #9070 )
agent-framework-foundry : Clarify Foundry agent-tool ownership and lifecycle behavior ( #8852 )
agent-framework-foundry-hosting : Warn against hosting a WorkflowAgent through the agent= shortcut ( #9146 )
agent-framework-hyperlight , agent-framework-monty : Warn when CodeAct tools cannot support FIDES security enforcement ( #9175 )
agent-framework-hosting : Persist the session in the hosting quickstart ( #9030 )
docs : Add the AI-assisted contribution policy and issue-first contribution workflow ( #9134 )
samples : Update multidict and source-map-js lockfiles and make file-access samples type-check on Windows ( #9105 , #9145 , #9161 )
tests : Update Python GitHub Actions dependencies ( #9038 , #9039 , #9158 )
tests : Isolate the mixed-middleware warning assertion ( #9001 )
tests , samples : Refresh Python development dependencies and type-checker compatibility ( #9190 )
agent-framework-core : Run local sibling tools in declaration-only mixed batches, serialize shared file edits, correct data URI validation and media detection, warn when streamed result gates lack buffering, and handle flat function mappings in progressive tool-name checks ( #9050 , #9032 , #8918 , #9029 , #9117 )
agent-framework-ag-ui , agent-framework-core : Close delegated provider streams when public streams are released while preserving primary failures during cleanup ( #9100 )
agent-framework-declarative : Preserve falsy values returned by Power Fx Search() ( #8974 )
agent-framework-devui : Page checkpoint item listings and scope function approvals to their conversations ( #9126 , #9180 )
agent-framework-gemini , agent-framework-ollama : Close SDK streams when consumers stop early ( #9144 )
agent-framework-hosting : Avoid retaining per-session locks after runs complete ( #9172 )
agent-framework-hosting-responses : Parse input messages that omit the optional type field ( #9124 )
agent-framework-openai : Preserve streamed log probabilities across empty chunks ( #8997 )
agent-framework-orchestrations : Reject unknown group-chat participants and sanitize generated handoff tool names ( #9026 , #9035 )
agent-framework-foundry-hosting : Preserve Foundry Toolbox container-file citations and refresh stale Toolbox call IDs ( #9055 , #9059 )
agent-framework-typesafe : Honor proxy environment variables in connector-owned clients ( #8984 )
agent-framework-bedrock : Preserve extended-thinking reasoning content across tool calls ( #8936 )
agent-framework-tools : Preserve table-formatted output in persistent PowerShell sessions ( #9043 )
Full Changelog : python-1.20.0...python-1.21.0
Assets 89 Loading
There was an error while loading. Please reload this page .
All reactions
agent-framework-foundry-hosting : Host native workflows over Foundry Responses and Foundry Invocations ( #8947 , #8966 )
agent-framework-foundry-hosting : Host native workflows over Foundry Responses and Foundry Invocations ( #8947 , #8966 )
agent-framework-duckdb , agent-framework-sql-server , agent-framework-typesafe : Add DuckDB and SQL Server native vector-store connectors and the TypeSafe AI connector ( #8675 , #8686 , #8592 )
agent-framework , agent-framework-core : Add response-stream gates and buffering, session-scoped file-access isolation, an AgentExecutor checkpoint-state TypedDict , and opt-in FunctionInvocationContext injection for skill scripts ( #8829 , #8542 , #8284 , #8749 )
agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-openai : Add native computer-use support to Responses clients and Foundry project embeddings ( #8751 , #8454 )
agent-framework-azure-ai-search : Support knowledge_source_params in AzureAISearchContextProvider ( #8673 )
agent-framework-mongodb , samples : Add a MongoDB agent RAG sample ( #8725 )
agent-framework-foundry-hosting : [BREAKING] Redesign Foundry hosting around request-scoped agent factories, persistent sandbox-isolated sessions, parsed and durable Invocations runs, and configurable Responses history, background execution, and options ( #8372 , #8593 , #8741 , #8794 , #8894 )
agent-framework-core : Harden approval and MCP runtime context handling, treat matched function results as terminal, require session-backed local approvals, and fail closed when approval bindings or agent-tool approvals cannot be resolved ( #8579 , #8589 , #8750 , #8780 , #8527 )
agent-framework-declarative : [BREAKING - experimental] Align workflow state attribute lookup, bound PowerFx state construction, normalize workflow HTTP request URLs, and preserve expression results in SendActivity output ( #8893 , #8511 , #8588 , #8509 )
agent-framework-gemini , agent-framework-core : [BREAKING] Add Gemini Embedding 2 and vector task options, use the GOOGLE_* settings namespace, and support operation-specific embedding options in shared vector APIs ( #8798 )
agent-framework-ag-ui , agent-framework-core : Treat matched tool results as terminal; make disconnected AG-UI runs durable, emit RUN_STARTED before execution when IDs are supplied, and isolate custom approval-state namespaces ( #8579 , #8672 , #8807 , #8714 )
agent-framework , agent-framework-core : Bound the all integration set to the current release cohort to avoid pip resolver backtracking, and support msgspec 0.22 for Python 3.15 installations
agent-framework-a2a , agent-framework-anthropic , agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos-memory , agent-framework-bedrock , agent-framework-claude , agent-framework-copilotstudio , agent-framework-declarative , agent-framework-devui , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-github-copilot , agent-framework-hosting , agent-framework-hosting-responses , agent-framework-hosting-telegram , agent-framework-mem0 , agent-framework-purview , agent-framework-redis : Add missing py.typed markers and enforce their presence in package checks ( #8823 )
agent-framework-bedrock : Forward Converse guardrail and additional-model-request options, send user images, and stream through ConverseStream ( #8680 , #8683 , #8685 )
agent-framework-chatkit : Support structured input and generated-image conversion ( #8843 , #8844 )
agent-framework-orchestrations : Create Magentic managers per workflow, optionally disable return-to-previous handoff routing, gate sequential output on approval, and validate generated handoffs before routing ( #8581 , #8639 , #8595 , #8587 )
agent-framework-redis : Allow RedisHistoryProvider to borrow a Redis client, clarify context-retrieval scope, and declare the current Python <3.15 limit imposed by redisvl ( #8883 , #8584 )
agent-framework-postgres , agent-framework-hyperlight : Restore supported Python 3.15 dependency resolution ( #8505 )
agent-framework-foundry : Require Azure Monitor OpenTelemetry 1.8.10 for trace propagation and support Azure AI Projects through 2.7 ( #8512 , #8751 )
agent-framework-hyperlight , agent-framework-monty : Clarify CodeAct guest-package installation and host-network access ( #8781 )
tests : Refresh root and Lab development dependencies, type checkers, transitive security dependencies, and lockfiles; require Python 3.15 checks and add bounded Windows 3.14 meta-package install coverage ( #8505 , #8612 , #8650 , #8727 , #8942 , #8945 )
docs , samples : Cross-reference security patterns, clarify file-search retrieval scope, improve local-shell filtering guidance, and correct README instructions ( #8726 , #8591 , #8766 , #8822 )
agent-framework-openai : Isolate OpenAI metadata defaults from Azure-routed clients ( #8969 )
agent-framework-core : Apply MCP security labels before dynamically discovered and progressively disclosed tools become callable ( #8972 )
agent-framework-core : Reduce response-stream hot-path overhead and avoid loading tool-approval middleware for agent runs without middleware ( #8971 )
agent-framework-core : Preserve functional-workflow replay identity, scope invocation arguments and activity IDs to workflow runs, deduplicate fan-out targets, propagate nested cancellation arguments, and support orchestration checkpoint deserialization ( #8887 , #8596 , #8549 , #8739 , #8602 , #8723 )
agent-framework-core : Preserve repeated history turns, compaction through middleware rewrites, checkpoint dictionary subclasses, response metadata, annotations, native vector keys, integer precision, and boolean set values ( #8800 , #8671 , #8519 , #8464 , #8701 , [ #8535 ]( https://github.c ...
Read more
Assets 87 Loading
There was an error while loading. Please reload this page .
All reactions
agent-framework-core : [BREAKING] Limit MCP skill archives to ZIP files and deprecate the MCP sampling callback ( #8290 , #8401 )
agent-framework , agent-framework-core : Add generic vector-store provider protocols, instrumentation message-event controls, and per-tool AgentModeProvider exposure controls ( #8421 , #8451 , #8450 )
agent-framework-mongodb : Add the alpha MongoDB vector-store connector ( #8184 )
agent-framework-azure-documentdb : Add the alpha Azure DocumentDB vector-store connector ( #8185 )
agent-framework-azure-cosmos , agent-framework-core : Add an Azure Cosmos DB NoSQL implementation of the shared vector-store APIs ( #8186 )
agent-framework-orchestrations : Add stable names for built-in orchestration workflows and register their checkpoint types for restoration ( #8384 , #8258 )
agent-framework-devui : Display Aspire traces in the developer UI ( #7874 )
agent-framework-core : Add an option to invoke function calls sequentially ( #8453 )
agent-framework-core , agent-framework-hyperlight , agent-framework-monty : Expose CodeAct tool parameter schemas and configurable compact or JSON descriptions ( #8459 )
agent-framework-a2a , agent-framework-ag-ui , agent-framework-core , agent-framework-declarative : [BREAKING] Make HTTP cookie persistence explicit for framework-owned and caller-owned clients ( #8371 )
agent-framework-core : [BREAKING] Limit MCP skill archives to ZIP files and deprecate the MCP sampling callback ( #8290 , #8401 )
agent-framework-declarative : [BREAKING] Scope provider-backed MCP sessions per invocation ( #8425 )
agent-framework-redis : [BREAKING - beta] Scope history storage keys by provider and session identity ( #8236 )
agent-framework-core : Refine skill frontmatter parsing, propagate runtime arguments to skill callbacks, and clarify MCP annotation override behavior ( #8430 , #8387 , #8399 )
agent-framework-core , agent-framework-hosting-a2a : Tighten security-label enforcement and restrict owned-input argument labels ( #8238 , #8394 )
agent-framework-purview : Handle additional content types during Purview policy processing ( #8370 )
agent-framework-mistral , agent-framework-hosting-responses : Reject unsupported per-call Mistral transport options ( #8392 )
agent-framework-monty : Update the Monty bridge for the current pydantic-monty pool API and reuse registered tools in callbacks ( #8152 , #8395 )
agent-framework-openai : Separate hosted and local shell calls ( #8294 )
agent-framework-ag-ui , agent-framework-anthropic , agent-framework-bedrock , agent-framework-core , agent-framework-foundry-hosting , agent-framework-hosting-a2a , agent-framework-hosting-mcp , agent-framework-hosting-responses , agent-framework-openai : Keep tool diagnostics internal by default ( #8235 )
agent-framework-azure-cosmos : Clarify Cosmos history-provider storage scope ( #8391 )
tests : Add public API compatibility checks and update root and Lab development dependencies and lockfiles ( #8271 , #8469 , #8266 , #8470 , #8249 , #8471 , #8472 , #8473 )
docs : Document keyed web search through the Serply MCP server and correct Python documentation wording ( #8319 , #8323 )
agent-framework-core : Preserve function-call and approval context across mixed batches, resumed runs, nested workflows, and streaming merges ( #8428 , #8433 , #8345 , #8337 )
agent-framework-core : Preserve compaction summaries and configuration while excluding encrypted reasoning payloads from token counts ( #8354 , #8329 , #8117 , #7944 )
agent-framework-core : Make file checkpoint saves, deletion, encoding, and round trips concurrency-safe and lossless ( #7757 , #8261 , #8272 , #8262 , #8181 )
agent-framework-core : Preserve workflow streaming, response metadata, state, return types, and invocation keyword arguments across completion and resume paths ( #8231 , #8389 , #8300 , #8309 , #8311 , #7999 , #8287 , #8331 )
agent-framework-core : Authenticate and scope MCP requests and sessions to the correct invocation identity, origin, and ownership ( #8303 , #8285 , #8246 , #8225 )
agent-framework-core : Verify MCP skill archive digests, avoid duplicate structured content, and reject ambiguous MCP configuration matches ( #8404 , #8274 , #8386 )
agent-framework-core : Propagate result-parser and asynchronous tool invocation failures correctly and count async invocation exceptions ( #8420 , #8278 )
agent-framework-core : Avoid OpenTelemetry context detach errors and record failed client-operation durations ( #8398 , #8347 )
agent-framework-core : Preserve instruction ordering, support Literal annotations, allow middleware argument repair, and deduplicate MessagePack history writes ( #8353 , #8351 , #8288 , #8224 )
agent-framework-core : Bound stateless approval pause batches to the current user turn ( #8449 )
agent-framework-ag-ui , agent-framework-core , agent-framework-foundry : Preserve checkpoint, approval, replay, reasoning, and session metadata across AG-UI interrupts and resumes ( #8163 , #8373 , #8058 , #8149 , #8279 , #8199 )
agent-framework-anthropic , agent-framework-core : Isolate Anthropic request parsing state and handle provider-invalidated responses ( #8237 , [...
Read more
Assets 81 Loading
There was an error while loading. Please reload this page .
👍 1 mdimai666 reacted with thumbs up emoji ❤️ 1 gabe-santana reacted with heart emoji All reactions
👍 1 reaction
❤️ 1 reaction
2 people reacted
samples : Add Magentic custom-manager prompts and MLflow observability examples ( #7876 , #8085 )
samples : Add Magentic custom-manager prompts and MLflow observability examples ( #7876 , #8085 )
agent-framework-core : Add shared vector-store abstractions, portable filters, and an in-memory vector store ( #8014 , #8115 )
agent-framework-core : Add a maximum-duration bound and stop-reason signal to the tool invocation loop ( #7772 )
agent-framework-core : Support mixed workflow invocation keyword arguments ( #7963 )
agent-framework-ag-ui : Add emit_messages_snapshot configuration for suppressing the terminal message snapshot ( #7808 )
agent-framework-ag-ui , agent-framework-core : Add supported MCP Host-history conversion for persisted AG-UI conversations ( #8130 )
agent-framework-azure-ai-search , agent-framework-core : Add an Azure AI Search implementation of the shared vector-store APIs ( #8153 )
agent-framework-redis , agent-framework-core : Add Redis HASH and JSON vector stores ( #8156 )
agent-framework-qdrant : Add the alpha Qdrant vector-store connector ( #8154 )
agent-framework-postgres : Add the alpha PostgreSQL/pgvector connector ( #8155 )
agent-framework , agent-framework-core , agent-framework-foundry , agent-framework-lab : [BREAKING] Isolate Lab dependency resolution, remove Lab from core[all] , and support Azure AI Projects through 2.6 with OpenAI 3.x ( #8188 )
agent-framework-core : [BREAKING - experimental] Add ranged file reads and move the line-numbering contract onto AgentFileStore ( #7669 )
agent-framework-core : [BREAKING - experimental] Centralize file, memory, session, and skill path normalization ( #8123 )
agent-framework-anthropic , agent-framework-azure-ai-search , agent-framework-azure-cosmos , agent-framework-bedrock , agent-framework-copilotstudio , agent-framework-core , agent-framework-foundry , agent-framework-gemini , agent-framework-mem0 , agent-framework-openai : [BREAKING] Make SecretString a masked value wrapper rather than a str subclass and align provider credential handling ( #8127 )
agent-framework-github-copilot : [BREAKING] Make workspace file hooks opt-in and document enable_file_hooks migration ( #7517 )
agent-framework-foundry-hosting : [BREAKING - beta] Restrict checkpoint deserialization by default and allow applications to register additional checkpoint types ( #8045 )
agent-framework-core , agent-framework-foundry : Move Foundry evaluation serialization into the Foundry integration ( #8031 )
agent-framework-github-copilot : Update the GitHub Copilot SDK dependency to 1.0.11 and align file-operation behavior ( #8002 )
agent-framework-ag-ui , agent-framework-devui : Expand compatibility through FastAPI 0.141 ( #8052 )
agent-framework-core , agent-framework-hyperlight : Update Hyperlight Sandbox to 0.6 and enable supported Python 3.14 installations ( #8174 )
agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-openai : Lazily load Foundry and OpenAI integrations to avoid unnecessary import-time dependencies ( #8219 )
agent-framework-devui : Update frontend transitive dependencies ( #8019 , #8009 , #8175 )
agent-framework : Replace stale Python documentation placeholders with live documentation links ( #7777 )
docs : Repair external links, document anonymous Parallel Search MCP usage, and correct Python documentation wording ( #8090 , #8084 , #7942 )
tests : Update uv, Ruff, Zuban, ty, pytest, and Python type-checking dependencies; isolate Lab test dependencies; and make the optional Lightning test robust to nested import failures ( #8038 , #8036 , #8037 , #8062 , #8110 , #8064 , #8071 , #8209 , #8207 , #8208 )
agent-framework-purview : Request inline policy evaluation while the protection-scope cache is cold ( #7976 )
agent-framework-anthropic , agent-framework-gemini : Wrap provider SDK failures consistently in ChatClientException ( #7855 )
agent-framework-a2a : Avoid AttributeError and preserve caller ownership when an A2AAgent uses a supplied HTTP client ( #8095 , #7951 )
agent-framework-chatkit : Preserve ChatKit input tags when converting user messages ( #8097 )
agent-framework-claude , agent-framework-github-copilot : Reject MCP servers passed through provider-agent tool collections ( #7835 )
agent-framework-claude : Preserve message roles in Claude prompt history ( #8122 )
agent-framework-declarative : Preserve URL query parameters and correctly route DevUI message input in declarative workflows ( #7765 , #7839 )
agent-framework-core : Preserve runtime raw representations and recursively serialize nested container values ( #8023 , #7790 )
agent-framework-core : Scope MCP headers to transport requests, clean up failed HTTP connections, and retain bounded MCP Host payload metadata ( #8039 , #8126 , #8128 )
agent-framework-core : Finalize abandoned functional-workflow streams, restore fan-in edge buffers, and validate checkpoint state when saving ( #7798 , #7948 , #8215 )
agent-framework-core : Include tool trajectory details in summarizer input ( #8087 )
agent-framework-core : Preserve the Param unset sentinel with current typing-extensions releases ( #8145 )
agent-framework-core : Preserve empty signed Anthropic thinking blocks during streaming replay ( #8171 )
agent-framework-core : Revalidate discovered skill paths immediately before use ( #8151 )
agent-framework-core : Isolate FIDES state per session, enforce labels on expanded variables, preserve confidentiality through security tools, and keep MCP labels subordinate to local policy ( #8138 , #8139 , #8141 , #8187 )
agent-framework-ag-ui : Stamp checkpoint ownership, surface workflow intermediate events as reasoning, and preserve function-call/result ordering ( #8011 , #8003 , #8005 )
agent-framework-ag-ui : Scope internal session identifiers and reject empty scope-resolver results ([ #8158 ]( https://github.com/microso ...
Read more
Assets 77 Loading
There was an error while loading. Please reload this page .
🎉 3 LL-LIN, droideronline, and mdimai666 reacted with hooray emoji All reactions
3 people reacted
samples : Add an end-to-end Foundry-hosted Telegram agent sample
samples : Add an end-to-end Foundry-hosted Telegram agent sample ( #7883 )
agent-framework-foundry-hosting : Add explicit Agent Server or agent-owned model history selection while preventing duplicated conversation replay ( #7997 )
agent-framework-core , agent-framework-foundry : [BREAKING] Restore sequence-only agent middleware inputs and remove the experimental agent-hooks core extra ( #7918 )
agent-framework-core , agent-framework-foundry , agent-framework-openai : Document the same-event-loop concurrency contract for shared chat clients ( #7680 )
agent-framework-devui , agent-framework-hosting-responses , agent-framework-openai : Support OpenAI SDK 3.x while retaining the existing supported floors ( #7967 )
agent-framework-mistral : Migrate chat and embedding clients to the official Mistral SDK ( #7960 )
agent-framework-core , agent-framework-devui , agent-framework-foundry-hosting , agent-framework-hosting-responses , agent-framework-openai : Preserve provider refusals as marked text across history, replay, hosting, and UI conversion ( #7992 )
agent-framework-ag-ui , agent-framework-core , agent-framework-devui , agent-framework-openai : Bind approvals to stable function-call occurrences while preserving legacy approval compatibility ( #7988 )
agent-framework-foundry-hosting : Persist valid OAuth consent responses and restore consent state during recovery ( #8006 )
agent-framework-core : Surface the underlying MCP initialization error when cancellation masks a connection failure ( #7704 )
agent-framework-ag-ui , agent-framework-core : Preserve client tools and request correlation when resuming workflow-as-agent approvals ( #7776 )
agent-framework-core : Project each model call's effective tool set to agent-hooks pre_model_call events ( #7747 )
agent-framework-ag-ui : Preserve every parallel function result during AG-UI message conversion ( #7980 )
agent-framework-devui , agent-framework-openai : Preserve Responses message boundaries, multimodal content, measured usage, and streamed response IDs in DevUI ( #7968 )
agent-framework-hosting-responses : Align continuation, input, output, and media parsing with the OpenAI Responses schemas ( #7966 )
agent-framework-foundry : Declare the HTTPX runtime dependency required by Azure AI Projects 2.3
agent-framework-openai : Preserve falsey provider values, valid request content, usage details, and embedding order ( #7964 )
agent-framework-foundry-hosting : Preserve JSON-safe arguments, falsey results, MCP output consistency, and shell limits in response conversion ( #7965 )
agent-framework-ag-ui , agent-framework-foundry , agent-framework-openai : Preserve Responses replay metadata across stateless and provider-managed AG-UI continuations ( #7906 )
agent-framework-core : Preserve compaction mutations across tool-loop calls and align thresholds and observability ( #7912 )
agent-framework-gemini : Send Pydantic response formats to Gemini as response schemas ( #7879 )
agent-framework-redis : Keep history-provider typing compatible across the supported Redis range ( #7604 )
Full Changelog : python-1.16.0...python-1.17.0
Assets 73 Loading
There was an error while loading. Please reload this page .
👍 2 mdimai666 and mjpsws reacted with thumbs up emoji All reactions
2 people reacted
Previous 1 2 3 4 5 6 7 8 Next
Previous Next
You can’t perform that action at this time.
agent-framework-core : Add configurable timeouts for waiting on the first background-agent task completion
agent-framework-core : Add configurable timeouts for waiting on the first background-agent task completion ( #7908 )
agent-framework-core : Allow programmatic OpenTelemetry service metadata, resource attributes, and OTLP exporter configuration ( #7703 )
agent-framework-foundry-hosting : Update Agent Server dependencies and expose parent FoundryToolbox constructor options ( #7921 )
samples : Apply ChatKit attachment lifecycle checks consistently in the end-to-end sample ( #7846 )
agent-framework-ag-ui , agent-framework-foundry-hosting : Preserve backend-owned service-session snapshots and validate incremental provider continuation input ( #7770 )
agent-framework-anthropic , agent-framework-mistral : Preserve unmapped provider finish reasons ( #7850 )
agent-framework-azure-ai-search : Preserve the kinds of heterogeneous knowledge sources ( #7875 )
agent-framework-core : Prevent workflow checkpoints from being mutated outside storage implementations ( #7847 )
agent-framework-core : Discard unsafe Content fields during deep copy ( #7903 )
agent-framework-core : Avoid mutating caller input in SerializationMixin.from_dict() ( #7901 )
agent-framework-core : Keep the private agent-loop iteration marker out of provider SDK requests ( #7860 )
agent-framework-gemini : Preserve unmapped finish reasons and attach usage details to the correct response ( #7837 )
agent-framework-openai : Preserve streaming when GenAI instrumentation replaces the raw SDK response ( #7705 )
Assets 73 Loading
There was an error while loading. Please reload this page .
👍 1 mdimai666 reacted with thumbs up emoji All reactions
1 person reacted
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-ag-ui , agent-framework-openai : Add optional A2UI support for agent-generated interfaces and preserve streaming tool-call indices for
agent-framework-ag-ui , agent-framework-openai : Add optional A2UI support for agent-generated interfaces and preserve streaming tool-call indices for A2UI consumers ( #7423 )
agent-framework-core : Add MiddlewareFailure as a first-class fatal signal for function middleware ( #7562 )
agent-framework-core , agent-framework-azure-cosmos : Add a process-wide workflow checkpoint type registry, register Cosmos checkpoint state types, and declare the compatibility dependency required by the supported Cosmos SDK floor ( #7636 )
agent-framework-core , agent-framework-foundry-hosting : Add steering, retry, and recovery support for resilient Foundry Hosted Agents, with long-running workflow samples ( #7670 )
samples : Add the production-ready installment of the build-your-own-claw harness sample ( #7698 )
agent-framework-ag-ui , agent-framework-core : [BREAKING] Consolidate OpenTelemetry GenAI semantic-convention support around stable and experimental modes with explicit message-event controls ( #7673 )
agent-framework-ag-ui : Align run continuity and avoid emitting unchanged predictive state snapshots ( #7662 , #7766 )
agent-framework-core : Defer turn-scoped after_run context providers to the agent-loop boundary ( #7289 )
agent-framework-ag-ui , agent-framework-core , agent-framework-declarative : Persist approval state and distinguish absent values from falsey approval data ( #7631 )
agent-framework-devui : Forward function_invocation_kwargs through DevUI agent runs ( #7779 )
agent-framework-core , samples : Clarify skill script arguments and MCP tool argument-filtering behavior ( #7695 , #7801 )
tests : Update uv, Ruff, mypy, ty, Flit, and the root build-system dependency range ( #7644 , #7645 , #7780 , #7781 , #7782 , #7783 , #7784 )
docs : Clarify PR review resolution and pin the Agent Lightning installation documentation link ( #7746 , #7693 )
agent-framework-a2a , agent-framework-core , agent-framework-orchestrations : Preserve and normalize A2A inputs when used through orchestrations ( #7761 )
agent-framework-ag-ui : Preserve tool-message IDs, URL-source attachments, and JSON workflow resume payloads ( #7510 , #7655 , #7684 )
agent-framework-anthropic , agent-framework-core : Preserve structured instructions when merging chat options ( #7730 )
agent-framework-core : Preserve all fan-in trace contexts and restrict workflow type deserialization ( #7557 , #7500 )
agent-framework-core : Avoid remote MCP tool-name shadowing while retaining the documented argument allowlist ( #7799 )
agent-framework-core : Always emit an arguments field for zero-argument tool calls in Foundry evaluations ( #7734 )
agent-framework-core , agent-framework-github-copilot : Forward telemetry configuration to the GitHub Copilot client ( #7625 )
agent-framework-core , agent-framework-redis : Prevent superlinear history growth by deduplicating saved messages ( #7242 )
agent-framework-devui : Deduplicate streamed tool calls ( #7652 )
agent-framework-foundry-hosting : Surface A2A preview consent URLs and prevent duplicate streamed function calls ( #7606 , #7486 )
agent-framework-orchestrations : Preserve agent additional_properties in handoff clones ( #7755 )
Assets 73 Loading
There was an error while loading. Please reload this page .
👍 1 mdimai666 reacted with thumbs up emoji All reactions
1 person reacted
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-core , agent-framework-mistral : Add a Mistral chat client with native chat, streaming, tools, structured output, and embeddings suppo
agent-framework-core , agent-framework-mistral : Add a Mistral chat client with native chat, streaming, tools, structured output, and embeddings support ( #7392 )
agent-framework-core : Add experimental AGENT-HOOKS-0.1 enforcement middleware behind the opt-in agent-hooks extra ( #7515 )
agent-framework-openai : Add request preparation and response parsing hooks to OpenAIChatCompletionClient ( #7028 )
agent-framework-ag-ui : Add workflow checkpoint creation and resume support to AgentFrameworkWorkflow ( #6646 )
agent-framework-core : Add BackgroundAgentsProvider.release_session() for safely cancelling work and releasing per-session runtime state ( #7450 )
agent-framework-foundry-hosting : Add provider-based Foundry state stores for agent sessions, checkpoints, and function approvals ( #7533 )
agent-framework-foundry : Export the Foundry hosted-agent session-state key used for service session continuity ( #7608 )
agent-framework-orchestrations : Expose the Magentic orchestrator manager name as MagenticOrchestrator.MANAGER_NAME ( #7350 )
agent-framework-gemini : Surface Gemini thought summaries as reasoning content ( #7488 )
samples : Add a locally hosted Responses sample for the agent harness ( #7010 )
agent-framework , agent-framework-core , agent-framework-azurefunctions , agent-framework-durabletask : Move the Durable Task and Azure Functions integrations to the Durable Agent Framework extension repository ; core continues to re-export their public symbols and install their independently published packages through the all extra ( #7465 )
agent-framework-core : [BREAKING — experimental] Require functional workflow definitions to be built into stateful workflow instances before running or adapting them as agents ( #7521 )
agent-framework-foundry-hosting : [BREAKING — beta] Migrate Foundry Hosted Agents to the Agent Server Responses 2.x storage model ( #7533 )
agent-framework-foundry-hosting , agent-framework-azure-contentunderstanding : Update Azure Agent Server dependencies to the 2.1 beta line and adapt request and storage handling ( #7621 )
agent-framework-foundry : Make encrypted reasoning opt-in for Foundry chat requests ( #7536 )
agent-framework-mem0 : Separate Mem0 storage and search scopes ( #7531 )
agent-framework-ag-ui : Consolidate thread-snapshot ownership and remove unused internal orchestration helpers ( #7426 , #7479 )
agent-framework-devui : Update frontend transitive dependencies ( #7493 , #7554 )
agent-framework-mistral , agent-framework-ollama : Expand the supported uv_build version range ( #7445 )
tests : Update Python development tools and improve sample validation with deterministic replay ( #7350 , #7445 , #7541 , #7545 )
samples : Update frontend dependencies and add a Foundry Hosted Agents custom-storage sample ( #7529 , #7621 )
agent-framework-core : Ignore excluded tool results during compaction ( #7391 )
agent-framework-core : Bound tool-result compaction summaries before provider calls ( #7396 )
agent-framework-core : Report evaluator results with zero checks correctly ( #7399 )
agent-framework-core : Reject Windows junctions while discovering and accessing skills ( #7507 )
agent-framework-core : Warn when advertised MCP archives are rejected ( #7622 )
agent-framework-core : Prevent streaming transcript duplication with message injection and per-service-call persistence ( #7605 )
agent-framework-ag-ui , agent-framework-core : Preserve conversation correlation across AG-UI runs ( #7430 )
agent-framework-ag-ui : Preserve approval resume semantics at the protocol boundary ( #7480 )
agent-framework-ag-ui : Make approval lifecycle, interruption recovery, and replay behavior occurrence-safe ( #7594 )
agent-framework-azure-ai-search : Forward query-source identity to Azure AI Search ( #7278 )
agent-framework-azure-cosmos-memory : Call the renamed Cosmos toolkit registration API ( #7635 )
agent-framework-claude : Avoid reusing one Claude SDK client across distinct fresh sessions ( #7404 )
agent-framework-copilotstudio : Handle large activities without line-length failures, update the Copilot Studio client dependency, and declare its required HTTP and authentication runtime dependencies ( #7417 )
agent-framework-declarative : Preserve falsey EditTableV2 items and robustly extract JSON from declarative workflow responses ( #7380 , #7550 )
agent-framework-foundry : Preserve Foundry hosted-agent session IDs independently from conversation continuation IDs ( #7608 )
agent-framework-gemini : Restore thought_signature values during approval replay ( #7546 )
agent-framework-github-copilot : Scope under-specified approve-for-session decisions to the current tool and align package metadata with the SDK's Python 3.11 minimum ( #7607 )
agent-framework-mistral : Preserve prompt-cache usage details ( #7597 )
agent-framework-openai : Prevent orphaned local approval responses and safely ignore non-string Chat Completions content ( #7462 , #7028 )
agent-framework-redis : Honor a max_messages retention limit of zero ( #7470 )
Full Changelog : python-1.13.0...python-1.14.0
Assets 2 Loading
There was an error while loading. Please reload this page .
👀 2 jijaraba and mdimai666 reacted with eyes emoji All reactions
2 people reacted
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-core , agent-framework-foundry-hosting : Add bounded, in-memory archive skill discovery for MCP sources and expose archive controls th
agent-framework-core , agent-framework-foundry-hosting : Add bounded, in-memory archive skill discovery for MCP sources and expose archive controls through FoundryToolbox ( #7121 )
agent-framework-core , agent-framework-foundry-hosting , agent-framework-hosting , agent-framework-hosting-responses , agent-framework-hosting-telegram : Add reusable session stores and persist complete Foundry Responses sessions ( #7306 )
agent-framework-a2a , agent-framework-ag-ui , agent-framework-anthropic , agent-framework-azure-ai-search , agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos , agent-framework-azure-cosmos-memory , agent-framework-azurefunctions , agent-framework-bedrock , agent-framework-chatkit , agent-framework-claude , agent-framework-copilotstudio , agent-framework-core , agent-framework-declarative , agent-framework-devui , agent-framework-durabletask , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-foundry-local , agent-framework-gemini , agent-framework-github-copilot , agent-framework-hosting , agent-framework-hosting-a2a , agent-framework-hosting-mcp , agent-framework-hosting-responses , agent-framework-hosting-telegram , agent-framework-hyperlight , agent-framework-lab , agent-framework-mem0 , agent-framework-mistral , agent-framework-monty , agent-framework-ollama , agent-framework-openai , agent-framework-orchestrations , agent-framework-purview , agent-framework-redis , agent-framework-tools : Add process-wide feature-usage telemetry with first-party User-Agent reporting ( #7420 )
agent-framework-core , agent-framework-openai : Add OpenAI cache-write token usage details to observability data ( #7369 )
agent-framework-openai : Support ephemeral per-request instructions in the Responses API ( #7292 )
agent-framework-foundry-hosting : Support asynchronous credentials in FoundryToolbox ( #7208 )
samples : Demonstrate archive-backed MCP skills with progressive disclosure in the Foundry Toolbox sample ( #7121 )
samples : Add FileMemoryProvider, TodoProvider, AgentModeProvider, and GitHub Copilot BYOK samples ( #7309 , #7336 , #7428 )
agent-framework-ag-ui , agent-framework-core : [BREAKING] Make workflow checkpoints fully replayable from initial input and human-in-the-loop responses ( #7374 )
agent-framework-devui : Update frontend transitive dependencies ( #7232 )
samples : Remove numeric prefixes from Foundry Hosted Agent sample names and update frontend dependencies ( #7314 , #7315 , #7405 )
tests : Add isolated lower- and upper-bound release validation and improve Python package-management tooling ( #7274 , #7342 )
agent-framework-core : Restrict unpickler module-prefix allowances to type objects ( #5923 )
agent-framework-core : Apply MCP header_provider headers to initialization and ambient requests ( #7305 )
agent-framework-core : Enforce the documented target-type check in SerializationMixin.from_dict ( #7256 )
agent-framework-ag-ui : Preserve model emission order in MESSAGES_SNAPSHOT events ( #7239 )
agent-framework-foundry : Prevent agent-reference requests from inheriting OPENAI_CHAT_MODEL ( #7283 )
agent-framework-core : Bound summarization input before provider calls ( #7375 )
agent-framework-openai : Sanitize Chat Completions message author names ( #7127 )
agent-framework-anthropic : Prevent streaming token usage from being counted twice ( #7162 )
agent-framework-core : Preserve declaration-only streaming metadata ( #7409 )
agent-framework-openai : Preserve approval decisions across Responses API continuations ( #7407 )
agent-framework-core : Omit tool content returned after function invocation limits are reached ( #7408 )
agent-framework-core : Keep function-call and result occurrences atomic during compaction ( #7406 )
agent-framework-ag-ui : Correlate confirm_changes snapshots by call ID ( #7411 )
agent-framework-ag-ui : Defer provider-injected approvals to in-run execution ( #7410 )
agent-framework-foundry-hosting : Store hosted checkpoints under the durable home directory ( #7220 )
agent-framework-ag-ui , agent-framework-core : Improve function approval resume and replay behavior ( #7345 )
agent-framework-openai : Pass raw JSON Schema response formats through Chat Completions without wrapping ( #7199 )
agent-framework-core : Extract keywords from non-English text for topic selection ( #7130 )
agent-framework-gemini : Preserve harness tool declarations ( #7322 )
agent-framework-core : Handle callable-class middleware safely during type detection ( #7333 )
agent-framework-core : Reject Windows junctions in FileSystemAgentFileStore ( #7291 )
agent-framework-azurefunctions , agent-framework-core , agent-framework-durabletask : Preserve sub-workflow state during checkpoint restoration ( #7097 )
agent-framework-core : Prevent duplicate function calls after approval round trips ( #7271 )
agent-framework-foundry-hosting : Preserve authentication credentials across FoundryToolbox reconnections ( #7202 )
agent-framework-ag-ui : Scope workflow caches correctly ( #7277 )
samples : Fix stale agent.json references in the A2A sample ( #7281 )
tests : Fix GitHub Actions token propagation for Python integration and sample-validation workflows ( #7427 )
Assets 2 Loading
There was an error while loading. Please reload this page .
👍 2 mdimai666 and jiachangkun02 reacted with thumbs up emoji All reactions
2 people reacted
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-openai : Add explicit prompt cache breakpoints for GPT-5.6 models and a usage sample
agent-framework-ag-ui : Promote the package from release candidate to stable
agent-framework-core : Add security guidance for custom MCP Streamable HTTP clients ( #7245 )
agent-framework-gemini : Preserve Gemini 3 thought signatures across function-call replays ( #7095 )
agent-framework-core , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-openai : Fix stateless replay of reasoning-paired tool calls ( #7233 )
Full Changelog : python-1.12.0...python-1.12.1
Assets 2 Loading
There was an error while loading. Please reload this page .
All reactions
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-azure-cosmos-memory : Add an alpha Azure Cosmos DB semantic-memory context provider with fact extraction, user profiles, samples, and
agent-framework-azure-cosmos-memory : Add an alpha Azure Cosmos DB semantic-memory context provider with fact extraction, user profiles, samples, and integration coverage ( #6719 )
agent-framework-azurefunctions , agent-framework-core , agent-framework-durabletask : Add HITL response-URL addressing for requests raised from inside workflows ( #7001 )
agent-framework-core : Add cross-session origin attribution to context-injected messages ( #7041 )
agent-framework-core , agent-framework-tools : Warn when auto-approved tools have name collisions ( #7090 )
agent-framework-core : Add a session_provider option to MCPSkillsSource and MCPSkill (mutually exclusive with client ) that resolves the MCP session on every fetch, keeping cached skills reconnect-safe when the underlying session is replaced ( #7135 )
agent-framework-hosting-a2a : Add app-owned A2A hosting helpers ( #7050 )
agent-framework-hosting-mcp : Add app-owned MCP hosting helpers for exposing agents and workflows as native MCP tools ( #7209 )
agent-framework-hosting-responses : [BREAKING] Add Responses conversation ID creation and parsing helpers, and distinguish conversation IDs from previous response IDs ( #7234 )
agent-framework-hosting-telegram : Add Telegram hosting helpers and samples ( #7047 )
samples : Add a Microsoft OpenTelemetry Distro observability sample ( #5632 )
agent-framework-ag-ui : [BREAKING] Emit TOOL_CALL events for workflow participant tool calls ( #7039 )
agent-framework-a2a : Reduce A2AExecutor log noise for content types without protocol mappings ( #7034 )
agent-framework-ag-ui , agent-framework-core : Optimize shared serialization paths ( #7165 )
agent-framework-ag-ui , agent-framework-bedrock , agent-framework-claude , agent-framework-core , agent-framework-github-copilot , agent-framework-ollama , agent-framework-openai : Normalize chat finish reasons across providers ( #7105 )
agent-framework-anthropic , agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos , agent-framework-core , agent-framework-declarative , agent-framework-devui , agent-framework-foundry , agent-framework : Update Microsoft Foundry branding in shipped APIs and package documentation ( #6999 )
agent-framework-azure-contentunderstanding , agent-framework-azure-cosmos-memory , agent-framework-chatkit , agent-framework-core , agent-framework-durabletask , agent-framework-foundry , agent-framework-foundry-hosting , agent-framework-gemini , agent-framework-hyperlight , agent-framework-lab , agent-framework-monty , agent-framework-openai , agent-framework-tools , agent-framework : Consolidate dependency updates and compatibility adjustments ( #7204 )
agent-framework-azurefunctions , agent-framework-devui , agent-framework-foundry , agent-framework-hosting-responses , agent-framework-lab , agent-framework-mistral , agent-framework : Clean up dependency groups and compatibility handling ( #7046 )
agent-framework-azurefunctions , agent-framework-durabletask : Normalize initial durable workflow inputs across hosting paths ( #7205 )
agent-framework-core : [BREAKING — experimental] Correct harness before-strategy compaction when state persists per service call ( #7055 )
agent-framework-core : [BREAKING] Graduate create_harness_agent from experimental to stable ( #7120 )
agent-framework-core : Graduate the mode and todo providers from experimental to stable ( #7053 )
agent-framework-core : Graduate ToolApprovalMiddleware from experimental to stable ( #7106 )
agent-framework-core : Graduate FileMemoryProvider from experimental to stable ( #7113 )
agent-framework-core : Make FileAccessProvider opt-in for harness agents ( #7094 )
agent-framework-core : Serialize tool definitions best-effort for observability ( #7029 )
agent-framework-declarative : Promote declarative workflows from release candidate to stable ( #7065 )
agent-framework-devui : Refine request logging ( #7083 )
agent-framework-foundry-hosting : Promote the package to beta and add it to the main installation surface; make the Foundry Toolbox MCP skills sample self-contained ( #7099 )
agent-framework-azure-contentunderstanding , agent-framework-gemini , agent-framework-mistral , agent-framework-monty , agent-framework-tools : Promote the packages to beta, add them to the main installation surface, expose lazy-loading namespaces, and move package-local samples into the root sample tree
agent-framework-github-copilot : Forward GitHubCopilotOptions verbatim when creating sessions ( #7155 )
docs : Add self-hosting sample snippets ( #7104 )
docs : Add environment-file templates for Durable Task hosting samples ( #5948 )
samples : Keep ChatKit attachments close to the sample application that owns them ( #7038 )
agent-framework-ag-ui : Bind streamed tool arguments to their call ids ( #6342 )
agent-framework-ag-ui : Accept state data URIs whose media type includes parameters ( #6905 )
agent-framework-ag-ui : Coalesce reasoning deltas without content ids into a single reasoning block ( #6804 )
agent-framework-ag-ui : Bridge request state and session continuity ( #7084 )
agent-framework-ag-ui : Replay workflow handoff results correctly ( #7102 )
agent-framework-ag-ui : Clarify require_confirmation documentation for confirm_changes HITL gating ( #6884 )
agent-framework-anthropic : Prevent per-run additional_beta_flags from leaking into request keyword arguments ( #7060 )
agent-framework-core : Clear service_session_id in the agent wrapper when session propagation is enabled ( #5875 )
agent-framework-core : Preserve tool span context for parallel calls ( #6512 )
agent-framework-core : Parse structured values assembled from split text chunks ( #6990 )
agent-framework-core : Raise ValueError for malformed data URIs ( #6916 )
agent-framework-core : Preserve function-call names when merging streaming deltas ( #6809 )
agent-framework-core , agent-framework-durabletask : Handle checkpoint encodings consistently ( #6579 )
agent-framework-core : Preserve explicit null arguments during automatic function calling ( #7108 )
agent-framework-core : Count non-ASCII text correctly during compaction ( #7124 )
agent-framework-core : Forward header_provider headers to streamable HTTP MCP transports ( #7218 )
agent-framework-core : Prevent compaction from emitting empty projections ( #7219 )
agent-framework-core : Return MCP tool-use sampling results to the requesting server ( #7189 )
agent-framework-foundry-hosting : Make FoundryToolbox.as_skills_provider() cache toolbox skill discovery by default so skill://index.json is read once instead of on every agent run, give disable_caching an observable effect, and add a cache_refresh_interval o...
Read more
Assets 2 Loading
There was an error while loading. Please reload this page .
All reactions
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
agent-framework-core : Add message injection middleware so tools or host code can enqueue messages into an active run and drain them into the next mod
agent-framework-core : Add message injection middleware so tools or host code can enqueue messages into an active run and drain them into the next model call within the same AgentSession ( #6998 )
agent-framework-core : Integrate message injection into create_harness_agent and the harness console sample so a running harness agent can be nudged mid-turn ( #7027 )
agent-framework-core : Add progressive MCP disclosure so agents can discover, load, and unload MCP tool schemas on demand while keeping the allowed_tools boundary intact ( #6850 )
agent-framework-core : Add refresh_interval (TTL) to CachingSkillsSource so cached skill lists expire and re-fetch on a configured interval ( #6977 )
agent-framework-core , agent-framework-foundry-hosting : Add SkillsSourceContext (invoking agent plus optional session) threaded through the skills source pipeline, enabling context-aware filtering and per-key cache isolation ( #6895 )
agent-framework-core : Allow disabling approval for SkillsProvider tools ( #6867 )
agent-framework-core : Allow opting out of FileAccessProvider tool approval ( #6879 )
agent-framework-core : Allow custom argument parsing for inline skill scripts so non-conforming tool-call argument shapes (for example, vLLM) can be handled ( #6817 )
agent-framework-hosting , agent-framework-hosting-responses : Add a hosting protocol helper surface ( AgentState , WorkflowState , SessionStore , AgentRunArgs , WorkflowRunArgs ) and Responses helpers ( create_response_id , responses_session_id , responses_to_run , responses_from_run , responses_from_streaming_run ) ( #6891 )
agent-framework-ag-ui : Add FastAPI SSE keepalive support for long, output-silent streams ( #6980 )
agent-framework-github-copilot : Forward skill_directories and disabled_skills to the Copilot session ( #6937 )
agent-framework-openai : Allow tool_choice: required when allowed_tools is set ( #7024 )
agent-framework-anthropic , agent-framework-core , agent-framework-foundry-hosting , agent-framework-gemini , agent-framework-openai : Mark hosted/provider-executed tool calls as informational-only via Content.informational_only so they remain visible in transcripts without local re-invocation ( #6997 )
samples : Add a deterministic action-boundary validation middleware sample ( #6528 )
samples : Add Agent Harness blog post accompanying samples, part 3 ( #6741 )
samples : Add a declarative Foundry Hosted Agent workflow sample ( #6897 )
agent-framework-core : [BREAKING — experimental] Extract caching from SkillsProvider into a CachingSkillsSource decorator ( #6847 )
agent-framework-core : [BREAKING — experimental] Treat nested SKILL.md content as part of the parent skill instead of discovering it as a separate skill root ( #6849 )
agent-framework-core : [BREAKING — experimental] FileAccess / FileMemory replace_lines now performs literal replacement (including line deletion) instead of always re-adding a line terminator ( #6859 )
agent-framework-core : Remove the experimental marker from the Skills API now that its surface is stable ( #6974 )
agent-framework-core : Lazy-load root agent_framework exports to reduce import cost for narrow-surface scenarios ( #6962 )
agent-framework-a2a , agent-framework-claude , agent-framework-copilotstudio , agent-framework-core , agent-framework-durabletask , agent-framework-github-copilot , agent-framework-purview : Implement ADR-0029 service_session_id lifecycle mapping, separating durable continuation state, per-run identity forwarding, and telemetry conversation-id extraction ( #6724 )
agent-framework-azurefunctions , agent-framework-core , agent-framework-durabletask : [BREAKING] Support multi-workflow hosting and sub-workflows on the Durable Task host, including per-workflow durable naming and nested human-in-the-loop request routing ( #6696 )
agent-framework-ag-ui : [BREAKING] Canonicalize AG-UI interrupt and resume handling around RUN_FINISHED.outcome.interrupts and canonical ResumeEntry payloads ( #6925 )
agent-framework-mem0 : Support the mem0ai 2.x OSS search call shape ( #7004 )
agent-framework-mistral : Widen the uv_build backend requirement to allow newer uv releases ( #7033 )
agent-framework-lab : Raise the agentlightning dependency ceiling for the lightning extra ( #6984 )
agent-framework-claude , agent-framework-durabletask , agent-framework-gemini , agent-framework-monty , agent-framework-openai : Raise dependency floors to the first versions that provide the SDK APIs and typing consumed by these packages
docs : Clarify AgentSession.service_session_id scoping to document backing API key/project boundaries and hosted multi-tenant guidance ( #6993 )
docs : Add security guidance for external skill sources and script execution to harness feature docstrings ( #6936 )
samples : Bump vite and @vitejs/plugin-react-swc in the ChatKit integration sample frontend ( #6613 )
samples : Add a multi-tenant hosting security consideration note to the A2A sample ( #6983 )
samples : Update Foundry Hosted Agent samples for the v2 protocol changes ( #6841 )
samples : Use a writable runtime directory for the Foundry Skills sample ( #6606 )
tests : Add Agent typing smoke tests across chat clients ( #6950 )
tests : Skip NumPy stubs during mypy typing to unblock scheduled dependency-maintenance typing runs ( #6969 )
tests : Consolidate Dependabot dependency updates for dev tooling ( uv , ruff , pytest , mypy , pyright , mcp , opentelemetry-sdk , poethepoet ) across the workspace and package dev-dependency groups ( #6984 , #7033 )
tests : Bump the transitive js-yaml dependency in the DevUI frontend lockfile ( #6813 )
agent-framework-core : Parse the structured response value from the final message instead of concatenated text, avoiding spurious ValidationError / JSONDecodeError ( #6383 )
agent-framework-core : Fix read_skill_resource instruction dropping the .md extension ( #7031 )
agent-framework-core : Bind policy-enforcement approvals to a single tool invocation (call id, function, arguments, security label, and session) and consume them on first use ( #6966 )
agent-framework-core : Process messages to an executor serially within a superstep to prevent concurrent handler invocations for the same target executor ( #6776 )
agent-framework-core : Auto-inject local conversation history on stateless clients even when non-history context providers (for example, SkillsProvider and FileAccessProvider ) are registered ( #6810 )
agent-framework-core : Improve the error message when a TypeVar is used in handler/executor registration ( #4553 )
agent-framework-anthropic , agent-framework-core : Fix Anthropic requests that mix tool calls and tool results in one assistant message, and return a deterministic result when the function-loop limit is reached with a blank final response ( #6794 )
agent-framework-anthropic , agent-framework-core , agent-framework-foundry-hosting , agent-framework-openai : Fix Foundry reasoning/MCP compaction so reasoning output keeps its provider id and ...
Read more
Assets 2 Loading
There was an error while loading. Please reload this page .
👍 2 Yuya218 and ghominejad reacted with thumbs up emoji All reactions
2 people reacted
Previous 1 2 3 4 5 6 7 Next
Previous Next
You can’t perform that action at this time.
AgentSession (#6998)create_harness_agent and the harness console sample so a running harness agent can be nudged mid-turn (#7027)allowed_tools boundary intact (#6850)refresh_interval (TTL) to CachingSkillsSource so cached skill lists expire and re-fetch on a configured interval (#6977)SkillsSourceContext (invoking agent plus optional session) threaded through the skills source pipeline, enabling context-aware filtering and per-key cache isolation (#6895)SkillsProvider tools (#6867)FileAccessProvider tool approval (#6879)AgentState, WorkflowState, SessionStore, AgentRunArgs, WorkflowRunArgs) and Responses helpers (create_response_id, responses_session_id, responses_to_run, responses_from_run, responses_from_streaming_run) (#6891)skill_directories and disabled_skills to the Copilot session (#6937)tool_choice: required when allowed_tools is set (#7024)Content.informational_only so they remain visible in transcripts without local re-invocation (#6997)SkillsProvider into a CachingSkillsSource decorator (#6847)SKILL.md content as part of the parent skill instead of discovering it as a separate skill root (#6849)FileAccess/FileMemory replace_lines now performs literal replacement (including line deletion) instead of always re-adding a line terminator (#6859)agent_framework exports to reduce import cost for narrow-surface scenarios (#6962)service_session_id lifecycle mapping, separating durable continuation state, per-run identity forwarding, and telemetry conversation-id extraction (#6724)RUN_FINISHED.outcome.interrupts and canonical ResumeEntry payloads (#6925)uv_build backend requirement to allow newer uv releases (#7033)agentlightning dependency ceiling for the lightning extra (#6984)AgentSession.service_session_id scoping to document backing API key/project boundaries and hosted multi-tenant guidance (#6993)vite and @vitejs/plugin-react-swc in the ChatKit integration sample frontend (#6613)uv, ruff, pytest, mypy, pyright, mcp, opentelemetry-sdk, poethepoet) across the workspace and package dev-dependency groups (#6984, #7033)js-yaml dependency in the DevUI frontend lockfile (#6813)ValidationError/JSONDecodeError (#6383)read_skill_resource instruction dropping the .md extension (#7031)SkillsProvider and FileAccessProvider) are registered (#6810)TypeVar is used in handler/executor registration (#4553)output_config.format shape to avoid malformed/concatenated JSON when tools are also present (#5884)include_reference_source_data in agentic search requests so source_data is populated on returned references (#5100)allow_preview=True) to avoid invalid_payload errors (#6644)GeminiChatClient dropping image/file content on multimodal messages (#6751);base64 marker (#6818)list[Message] input handling for declarative ToolAgent entries (#6534)web_search_options sent to the Azure OpenAI Chat Completions API (#6225)ChatAgent references in _clients.py docstrings and make tool-support examples copy/paste-safe (#6924)options kwarg in the workflow shared-session sample (#6294)agent-framework-core: Explicitly emit available_resources and available_scripts in skill content
available_resources and available_scripts in skill content (#6694)create_harness_agent skills_paths accepts str | Path | Sequence[str | Path] | None (#6717)FoundryAgent conversation session helper (#6623)on_pre_tool_use hook (#6750)FileSkillsSource for depth-based discovery and predicate filters (#6488)HarnessAgent (#6607)FileMemoryProvider and integrate into harness agent (#6547)SkillsProvider tools require approval by default (#6754)response_format to JSON schema in OllamaChatClient (#6782)FunctionShellTool throw and empty streaming shell command (#6763)agent-framework-core: Add AgentLoopMiddleware for re-running agents in a loop
AgentLoopMiddleware for re-running agents in a loop (#6174)sampling_approval_callback, sampling_max_tokens, and sampling_max_requests parameters (#6413)azure-ai-contentunderstanding to_llm_input in the CU context provider (#5796)1.0.0)function_invocation_configuration kwarg from as_agent (#6520)allowed_tools empty-list handling (#6296)CallToolResult.structuredContent to prevent tool results returning None (#6421)ImportError during hosted-environment detection so optional Foundry hosting probing cannot crash user-agent setupaiohttp dependency specification (#6567)ollama_chat_client.py to pass tools via the options dict (#6480)agent-framework-core: Add MCP client OTel spans per GenAI semantic conventions
claude-agent-sdk to 0.2.87 (#6248)getattr for non-OpenAI provider response compatibility (#6270)outputSchema, not just JSON mode (#5893)app_id payload (#6242)agent-framework-core: Add MCP-based skills discovery (McpSkillsSource)
McpSkillsSource) (#6169)FunctionInvocationContext (#6233)AgentFileStore and FileAccessProvider for file access operations (#6099)timeout parameter to FoundryAgent to fix ConnectTimeout on multi-turn conversations (#6263)supported_protocol_bindings as configurable parameter (#6098)message_id on AgentResponseUpdate for message-bearing paths (#6163)mcp_call output (#6070)github-copilot-sdk to v1.0.0 (stable) (#6292)1.0.0rc1)1.0.0rc1) (#6256)FoundryAgent stripping model from PromptAgent requests (#5526)/v1/{signal} auto-append (#5913)tests: Replace deprecated asyncio.iscoroutinefunction usage in DevUI cleanup-hook tests
HarnessAgent and background-agents harness provider (#6041, #6069)A2AAgentSession with referenced task IDs and input-required support (#5980)openai-chatkit dependency floor to >=1.6.4 to match the current typed API usage.asyncio.iscoroutinefunction usage in DevUI cleanup-hook tests (#4563)@experimental warnings at user code (#5996)MessageRole values (#6049)get_url metadata (#6037).headers (#6028, #6029)agent-framework-core: Shell tool with support for local and Docker execution
FoundryChatClient (#5958)return_immediately for background ops (#5963)agent-framework-core, agent-framework-foundry, agent-framework-openai: Record actual served model from Azure OpenAI
durabletask and durabletask-azuremanaged floors to >=1.4.0 and exclude upstream durabletask 1.4.1, 1.4.2, and 1.4.3 from the supported version range.ContextProvider.before_run in session creation (#5780)InMemoryCacheProvider.remove (#5795)agent-framework-core: Forward MCP tool call metadata
list[str] arguments for file-based skill scripts (#5850)SkillFrontmatter (#5775)agent-framework-core: Add ClassSkill for class-based skill definitions with declarative metadata and automatic method discovery
ClassSkill for class-based skill definitions with declarative metadata and automatic method discovery (#5678)AgentModeProvider mode changes (#5650)allowed_tools tool choice (#5322)agent_reference (#5619)base_url parameter to AnthropicClient and RawAnthropicClient (#5685)InvokeMcpTool in declarative workflow (#5630)HttpRequestAction in declarative workflow (#5599)approval_mode in Claude and GitHub Copilot agents (#5562)github-copilot-sdk to v1.0.0b2 with instruction_directories, copilot_home, and runtime options forwarding on session resume (#5665)MCPStreamableHTTPTool leaking asyncio.CancelledError when MCP server is unreachable (#5687)continuation_token from shared options in tool loop (#5462)toolChoice when no tools are configured (#5172)WasmSandbox cross-thread Drop and harden hosted-agent sample (#5603)created_at to executor events (#5615)function_call_output (#5581)agent-framework-azure-contentunderstanding: New alpha package — Azure AI Content Understanding context provider that auto-analyzes file attachments (d
AnalysisSection, and auto-registered list_documents / get_analyzed_document tools (#4829)Workflow.as_agent() end-to-end via the foundry hosting layer (#5531)AgentResponse so Workflow.as_agent() returns the final answer only; aligns sequential-approval (with_request_info) and concurrent participant output designation flows on the same output contract (#5301)Workflow.run() shared state across calls so multi-turn WorkflowAgent invocations retain context, accept list[Message] input in the declarative start executor, and coerce Enum values when serializing PowerFx symbols (#5531)mcp[ws] / uvicorn[standard] extras through override-dependencies in /python (#5555)file_search citations breaking the assistant-message history roundtrip — skip hosted_file content in the assistant role so the Responses API no longer rejects input_file (#5557)agent-framework-foundry-hosting: Add file data type support to hosted-agent Responses, refresh foundry-hosted-agents samples, and add response test co
foundry-hosted-agents samples, and add response test coverage (#5485)requirements.txt and .env.example to the a2a/ hosting sample for pip-based setup (#5510)rich requirement from <15.0.0,>=13.7.1 to >=13.7.1,<16.0.0 in /python (#5227)prek from 0.3.8 to 0.3.9 in /python (#5228)python-multipart from 0.0.22 to 0.0.26 in /python (#5286)pyasn1 from 0.6.2 to 0.6.3 in /python (#4748)pytest from 9.0.2 to 9.0.3 in /python/packages/ag-ui (#5461)pytest from 9.0.2 to 9.0.3 in /python/packages/devui (#5492)pytest from 9.0.2 to 9.0.3 in /python/packages/lab (#5470)uv from 0.11.3 to 0.11.6 in /python/packages/lab (#5469)vite from 7.1.12 to 7.3.2 in /python/packages/devui/frontend (#5127)vite from 7.1.12 to 7.3.2 in /python/samples/05-end-to-end/chatkit-integration/frontend (#5126)postcss from 8.5.6 to 8.5.10 in /python/packages/devui/frontend (#5484)postcss from 8.5.6 to 8.5.10 in /python/samples/05-end-to-end/chatkit-integration/frontend (#5491)postcss from 8.5.6 to 8.5.12 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#5527)picomatch from 4.0.3 to 4.0.4 in /python/packages/devui/frontend (#4921)picomatch from 4.0.3 to 4.0.4 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#4936)inner_exception from being lost in AgentFrameworkException (#5167)agent-framework-core: Add functional workflow API
GitHubCopilotAgent (#5142)oauth_consent_request events from Responses API in Foundry clients (#5070)FoundryAgent for hosted agent sessions (#5447)[TOOLBOXES] warning for every FoundryChatClient call (#5440)agent-framework-core: Add expected_output ground-truth support to evaluate_workflow for similarity evaluators
expected_output ground-truth support to evaluate_workflow for similarity evaluators (#5234)thread_id and forwarded_props through AG-UI to A2A context_id (#5383)set_stop_loss) to concurrent_builder_tool_approval sample (#4875)SKIP_PARSING sentinel for FunctionTool.invoke to bypass Content-wrapping and return raw function results (#5424)SKIP_PARSING, switch execute_code input schema to a plain JSON-schema dict, and tighten public API surface (#5424)created_at from the final response.completed event (#5382)OpenAIEmbeddingClient to use AsyncOpenAI for /openai/v1 endpoints (#5137)file_id from input_image payload to prevent schema 400 errors (#5125)thread_id as session_id when constructing AgentSession (#5384)WasmSandbox interactions via per-entry ThreadPoolExecutor to eliminate the PyO3 unsendable panic when touched from asyncio worker threads (#5424)agent-framework-gemini: Add GeminiChatClient
GeminiChatClient (#4847)context_providers and description to workflow.as_agent() (#4651)AgentExecutorResponse.with_text() to preserve conversation history through custom executors (#5255)Message, Artifact, Task, and event types (#5256)finish_reason support to AgentResponse and AgentResponseUpdate (#5211)forwardedProps to agents and tools via session metadata (#5264)CosmosCheckpointStorage now uses restricted pickle deserialization by default, matching FileCheckpointStorage behavior. If your checkpoints contain application-defined types, pass them via allowed_checkpoint_types=["my_app.models:MyState"]. (#5200)allowed_checkpoint_types support to CosmosCheckpointStorage for parity with FileCheckpointStorage (#5202)InMemory history provider injection to first invocation (#5236)SessionConfig in GitHubCopilotAgent (#5195)execute_code output (#5333)pygments from 2.19.2 to 2.20.0 in /python (#4978)python-feature-lifecycle skill YAML frontmatter (#5226)HandoffBuilder dropping function-level middleware when cloning agents (#5220)get_final_response in _finalize_stream when the stream has errored (#5232)store=False (#5250)url_citation annotations in FoundryChatClient streaming responses (#5071)CopilotStudioAgent to reuse conversation ID from an existing session (#5299)samples: Add sample documentation for two separate Neo4j context providers for retrieval and memory
README.md (#5067)CHANGELOG with v1.0.0 release (#5069)vite from 7.3.1 to 7.3.2 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#5132)cryptography from 46.0.6 to 46.0.7 (#5176)mcp from 1.26.0 to 1.27.0 (#5117)mcp[ws] from 1.26.0 to 1.27.0 (#5119)TypeVar annotations (#4944)response_format crash on background polling with empty text (#5146)FoundryAgent request when agent_reference is present (#5101)response.reasoning_text.done and response.reasoning_summary_text.done events (#5162)agent-framework-github-copilot: Forward input attachments (images, documents, and other inline binary content) to GitHub Copilot as inline blobs
agent-framework-core: [BREAKING] Remove deprecated kwargs compatibility paths
structuredContent in MCP tool results and fix sampling options type (#4763)MESSAGES_SNAPSHOT events (#4844)AgentExecutor (#4668)flatted from 3.3.3 to 3.4.2 in frontend (#4805)ag_ui_workflow_handoff demo from demos/ to 05-end-to-end/ (#4900)mcp_server_tool_result on output_item.done instead of output_item.added (#4821)A2AAgent to surface message content from in-progress TaskStatusUpdateEvents (#4798)PydanticSchemaGenerationError when using from __future__ import annotations with @tool (#4822)samples: Add foundry hosted agents samples for python
Content items with rich content support (#4331)A2AAgent name and description from AgentCard (#4661)null (#4683)context_id (#4686)danielpalme/ReportGenerator-GitHub-Action from 5.5.1 to 5.5.3 (#4542)MishaKav/pytest-coverage-comment from 1.2.0 to 1.6.0 (#4543)pyjwt from 2.11.0 to 2.12.0 (#4699)invoke_agent span (#4739)detail field in OpenAI Chat API image_url payload (#4756)deepcopy for state snapshots so nested mutations are detected in durable workflow activities (#4518)BedrockChatClient sending invalid toolChoice "none" to the Bedrock API (#4535)Case and Default (#3985)_deduplicate_messages catch-all branch dropping valid repeated messages (#4716)RUN_FINISHED.interrupt to accumulate all interrupts when multiple tools need approval (#4717)Content class in durable tasks (#4738)ENABLE_SENSITIVE_DATA being ignored when set after module import (#4743)A2AAgent to invoke context providers before and after run (#4757)properties key (#4771)agent-framework-core: Add propagate_session to as_tool() for session sharing in agent-as-tool scenarios
propagate_session to as_tool() for session sharing in agent-as-tool scenarios (#4439)ToolInvocation and ToolResult types (#4551)azure-ai-projects 2.0+ (#4536)isError flag through the function middleware pipeline (#4511)as_agent() not defaulting name/description from client properties (#4484)conversation_id from chat completions API options (#4517)chat_options is a dict (#4340)ResponseStream on iteration completion (#4478)executor_completed event handling for non-copyable raw_representation in mixed workflows (#4493)store=False not overriding client default (#4569)RedisContextProvider compatibility with redisvl 0.14.0 by using AggregateHybridQuery (#3954)chat_response_cancellation sample to use Message objects (#4532)agent-framework-core: Add Shell tool
file_ids and data_sources support to get_code_interpreter_tool() (#4201)TextDeltaBlock in Assistants API streaming (#4316, #4320)ClaudeAgent (#4278, #4326)auto_retry.py sample for rate limit handling (#4223)HandoffBuilder to require Agent instead of SupportsAgentRun (#4301, #4302)AzureOpenAIResponsesClient (#4285)meta attribute (#4287)response_format resolution in streaming finalizer (#4291)AgentExecutor to prevent duplicate-argument TypeError (#4298)run(responses=...) (#4296)WorkflowAgent not persisting response messages to session history (#4319)OpenAIResponsesClient._prepare_tools_for_openai (#4312)from __future__ import annotations (#4317)model_id kwarg in AzureOpenAIResponsesClient (#4310)thread.message.completed event in Assistants API streaming (#4333)CurrentUICulture to en-US (#4408)StandardMagenticManager to propagate session to manager agent (#4409)IndexError when reasoning models produce reasoning-only messages in Magentic-One workflow (#4413)oauth_consent_request events in Azure AI client (#4197)role="assistant" on message_start streaming update (#4329)AgentResponse.value instead of model_validate_json in HITL sample (#4405)agent-framework-core: Support Agent Skills
max_function_calls to FunctionInvocationConfiguration (#4175)CreateConversationExecutor, fix input routing, remove unused handler layer (#4159)InvokeFunctionTool action for declarative workflows (#3716)max_iterations is reached (#4234)tool_call arguments in MESSAGES_SNAPSHOT when streaming (#4200)structured_output propagation in ClaudeAgent (#4137)Release candidate for agent-framework-core and agent-framework-azure-ai packages.
Release candidate for agent-framework-core and agent-framework-azure-ai packages.
source_id and standardize source IDs (#3995)FunctionTool[Any] compatibility shim for schema passthrough (#3907)invoke_agent span (#4012)agent-framework-core: Allow AzureOpenAIResponsesClient creation with Foundry project endpoint
AzureOpenAIResponsesClient creation with Foundry project endpoint (#3814)Hosted*Tool classes with tool methods (#3634)TypedDict + load_settings() (#3843)FunctionTool.invoke() (#3854)AzureOpenAIResponsesClient, reorganize orchestration examples, and fix workflow/orchestration bugs (#3873)AgentExecutor streams (#3882)Workflow.as_agent() streaming regression (#3875)response_format kwarg error (#3841)agent-framework-core: Add long-running agents and background responses support with ContinuationToken TypedDict, background option in OpenAIResponsesO
ContinuationToken TypedDict, background option in OpenAIResponsesOptions, and continuation token propagation through response types (#3808)@handler, @executor and request_info (#3472)@tool decorator (#3734)ChatAgent → Agent, RawChatAgent → RawAgent, ChatMessage → Message, ChatClientProtocol → SupportsChatGetResponse (#3747)get_response and run API (#3379)send_responses into run method (#3720)AgentRunContext to AgentContext (#3714)AgentProtocol to SupportsAgentRun (#3717)call_next (#3735)TName → NameT) (#3770)SharedState to State with sync methods and superstep caching (#3667)context_provider during agent cloning (#3721)response_format from MCP tool call kwargs (#3494)model_deployment_name validation for application endpoints (#3621)run_stream() method (#3653)$defs in JSON schema for nested Pydantic models (#3655)agent-framework-claude: Add BaseAgent implementation for Claude Agent SDK
agent-framework-core: [BREAKING] Renamed @ai_function decorator to @tool and AIFunction to FunctionTool
agent-framework-github-copilot: Add BaseAgent implementation for GitHub Copilot SDK
agent-framework-azure-ai: Add support for rai_config in agent creation
rai_config in agent creation (#3265)AzureAIClient (#3403)response_format support for structured outputs (#3301)response_format validation errors visible to users (#3274)kwargs for conversation_id in OpenAI Responses client (#3312)conversation_id when passing kwargs to agent as tool (#3266)use_agent_middleware calling private _normalize_messages (#3264)system_instructions to ChatClient LLM span tracing (#3164)HostedImageGenerationTool mapping to ImageGenTool for Azure AI (#3263)AzureAIProjectAgentProvider (#3315)int (#3201)agent-framework-azure-ai: Create/Get Agent API for Azure V1
create_agent to as_agent (#3249)WorkflowOutputEvent.source_executor_id to executor_id for API consistency (#3166)FunctionResultContent ordering in WorkflowAgent.merge_updates (#3168)DurableAIAgent and fix integration tests (#3241)agent-framework-azure-ai: Create/Get Agent API for Azure V2 (#3059) by @moonbox3
agent-framework-devui: Improve DevUI and add Context Inspector view as a new tab under traces (#2742) by @victordibia
repo: Add issue template and additional labeling (#3006) by @eavanvalkenburg
agent-framework-bedrock: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.)
response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975)agent-framework-core: Azure AI Agent with Bing Grounding Citations sample
_mcp.py (#2901)agent-framework-ollama: Ollama connector for Agent Framework
ai_function kwargs (#2769)WorkflowAgent (#2774)HandoffBuilder auto-generated tools (#2714)WorkflowAgent to include thread conversation history (#2774)WorkflowAgent to emit yield_output as agent response (#2866)agent-framework-core: Extend HITL support for all orchestration patterns
agent-framework-core: Support an autonomous handoff flow
async_credential to credential (#2648)agent-framework-core: Add support for Pydantic BaseModel as function call result
BaseModel as function call result (#2606)Message; allow agent as group chat manager (#2291)AgentRunResponse including serialized structured output (#2285)executor_id and edge_group_id as span names for clearer traces (#2538)AgentRunResponse.created_at returning local datetime labeled as UTC (#2590)ExecutorFailedEvent before WorkflowFailedEvent when executor throws (#2537)repr string for tool call content (#2566)agent-framework-core: Introducing support for declarative YAML spec
as_tool() kwargs and add runtime context + middleware sample (#2311)evaluations (#2355)@ai_function now correctly handles self parameter (#2266)FunctionExecutor (#2308)samples: Bing Custom Search sample using HostedWebSearchTool
HostedWebSearchTool (#2226)AzureAIClient (#2198)uv build for packaging (#2161)agent-framework-azurefunctions: Merge Azure Functions feature branch
agent-framework-azure-ai: Azure AI client based on new azure-ai-projects package
azure-ai-projects package (#1910)agent-framework-core: Add OpenAI Responses Image Generation Stream Support with partial images and unit tests
invoke_agent span (#2061)agent-framework-devui: Add OpenAI Responses API proxy support + HIL (Human-in-the-Loop) for Workflows
One column per month.