microsoft--agent-framework/python/CHANGELOG.md

Changelog

All notable changes to the Agent Framework Python packages will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

Unreleased

1.11.0 - 2026-07-09

Added

• 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)

Changed

• 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)

Fixed

• 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 reasoning plus MCP call pairs stay atomic (#6907)
• agent-framework-anthropic: Normalize a single Anthropic tool value the same as a one-item sequence during request preparation (#6903)
• agent-framework-anthropic: Migrate structured outputs to the stable output_config.format shape to avoid malformed/concatenated JSON when tools are also present (#5884)
• agent-framework-azure-ai-search: Pass include_reference_source_data in agentic search requests so source_data is populated on returned references (#5100)
• agent-framework-bedrock: Fix non-ASCII escaping in JSON content blocks returned by the Converse API (#6628)
• agent-framework-foundry: Strip tools from the Foundry agent request on the preview path (allow_preview=True) to avoid invalid_payload errors (#6644)
• agent-framework-gemini: Fix GeminiChatClient dropping image/file content on multimodal messages (#6751)
• agent-framework-claude, agent-framework-core, agent-framework-github-copilot, agent-framework-ollama: Fix response metadata construction so usage, finish reason, raw response, continuation token, and structured value are propagated consistently across providers (#6955)
• agent-framework-a2a: Accept A2A data URIs whose media type includes parameters before the ;base64 marker (#6818)
• agent-framework-ag-ui: Prefer explicit AG-UI resume payloads over message-derived responses (#6360)
• agent-framework-ag-ui: Clear queued approvals on cancel so cancelled flows do not leave stale prompts for later turns (#6947)
• agent-framework-ag-ui: Preserve the streamed text message id in mixed snapshots with pending tool calls and streamed trailing text (#6269)
• agent-framework-devui: Fix list[Message] input handling for declarative ToolAgent entries (#6534)
• agent-framework-devui: Fix DevUI deployment Dockerfile auth args (#6150)
• agent-framework-hyperlight: Harden workspace staging against symlinks and reparse points that could escape the sandbox workspace/mount root (#6856)
• agent-framework-openai: Fix web_search_options sent to the Azure OpenAI Chat Completions API (#6225)
• docs: Fix stale ChatAgent references in _clients.py docstrings and make tool-support examples copy/paste-safe (#6924)
• samples: Fix an invalid options kwarg in the workflow shared-session sample (#6294)
• docs: Add prerequisite command documentation for Python hosting samples (#5935)

Removed

• agent-framework-hosting-telegram: [BREAKING] Remove the unreleased hosting-telegram package and the earlier host/channel surface from the workspace, superseded by the new hosting protocol helper surface (#6891)

1.10.0 - 2026-06-30

Added

• agent-framework-core: Explicitly emit available_resources and available_scripts in skill content (#6694)
• agent-framework-core: Autolabelling MCP servers based on hints and GitHub MCP server interface labels (#6171)
• agent-framework-core: create_harness_agent skills_paths accepts str | Path | Sequence[str | Path] | None (#6717)
• agent-framework-core: Background agent loop resolves provider automatically and adds feedback message builder (#6735)
• agent-framework-core: Stop swallowing skill script and resource errors so the model can self-correct (#6755)
• agent-framework-foundry: Add FoundryAgent conversation session helper (#6623)
• agent-framework-foundry: Add support for Foundry Adaptive evals (#6267)
• agent-framework-bedrock, agent-framework-gemini: Surface cache and reasoning token counts (#6640)
• agent-framework-durabletask: Host MAF workflows on a standalone Durable Task worker (#6418)
• agent-framework-azure-ai-search: Support stable and preview Azure AI Search (Foundry IQ) API versions (#6603)
• agent-framework-github-copilot: Align function approval to use SDK on_pre_tool_use hook (#6750)

Changed

• agent-framework-core: [BREAKING — experimental] Refactor FileSkillsSource for depth-based discovery and predicate filters (#6488)
• agent-framework-core: [BREAKING — experimental] Require approval for file-access tools with read-only auto-approval (#6599)
• agent-framework-core: [BREAKING — experimental] Integrate looping into HarnessAgent (#6607)
• agent-framework-core: [BREAKING — experimental] Port FileMemoryProvider and integrate into harness agent (#6547)
• agent-framework-core: [BREAKING — experimental] Make all SkillsProvider tools require approval by default (#6754)
• agent-framework-core: [BREAKING — experimental] Improve FileAccess/FileMemory harness providers (surgical edits, read-only tier, consistent naming) (#6801)
• agent-framework-core: Align serialized tool format to OTel GenAI tool definition format (#6556)
• agent-framework-foundry-hosting: [BREAKING] Foundry Hosted Agent V2 protocol upgrade (#6811)
• agent-framework-foundry-hosting: Add MCP as a hard dependency (#6634)
• agent-framework-purview: Prefer token principal for user identity (#6693)
• agent-framework-ollama: Convert Pydantic model class response_format to JSON schema in OllamaChatClient (#6782)

Fixed

• agent-framework-core: Fix background agent telemetry context error (#6764)
• agent-framework-core: Fix MCP metadata and tool name handling (#6656)
• agent-framework-core: Ensure spans created inside sync preparations in streaming call are correctly nested (#6552)
• agent-framework-openai: Preserve OTel parent context for deferred streams (#6709)
• agent-framework-openai: Fix FunctionShellTool throw and empty streaming shell command (#6763)
• agent-framework-ag-ui: Fix tool history replay sanitization (#6581)
• agent-framework-anthropic: Re-role trailing assistant message to user for Anthropic compatibility (#6207)
• agent-framework-hyperlight: Fix CodeAct span parenting (#6712)
• agent-framework-hyperlight: Harden output capture against symlinks (#6601)

1.9.0 - 2026-06-18

Added

• agent-framework-core: Add AgentLoopMiddleware for re-running agents in a loop (#6174)
• agent-framework-core: Integrate tool approval into the harness agent (#6522)
• agent-framework-core: Add tool approval middleware (#6414)
• agent-framework-core: Integrate the shell tool into the harness agent (#6451)
• agent-framework-core: Capture context provider instructions in agent telemetry (#6515)
• agent-framework-core, agent-framework-ag-ui: Add opt-in AG-UI thread snapshot persistence and hydration (#6471)
• agent-framework-foundry-hosting: Emit failed events for hosted agent responses (#6502)

Changed

• agent-framework-core: [BREAKING] Add sampling guardrails to MCP tools — deny server-initiated sampling by default and add sampling_approval_callback, sampling_max_tokens, and sampling_max_requests parameters (#6413)
• agent-framework-core: [BREAKING] Align FileAccess tools with .NET, adding directory discovery and recursive search (#6476)
• agent-framework-declarative: [BREAKING] Additional fixes for declarative workflow execution (#6489)
• agent-framework-azure-contentunderstanding: Adopt azure-ai-contentunderstanding to_llm_input in the CU context provider (#5796)
• agent-framework-orchestrations: Promote to stable (1.0.0)

Fixed

• agent-framework-core: Stop forwarding the unsupported function_invocation_configuration kwarg from as_agent (#6520)
• agent-framework-core: Fix MCP allowed_tools empty-list handling (#6296)
• agent-framework-core: Disable harness compaction when max tokens are not provided (#6410)
• agent-framework-core: Parse MCP CallToolResult.structuredContent to prevent tool results returning None (#6421)
• agent-framework-core: Catch bare ImportError during hosted-environment detection so optional Foundry hosting probing cannot crash user-agent setup
• agent-framework-anthropic, agent-framework-core, agent-framework-openai: Fix OTel usage detail attributes (#6493)
• agent-framework-foundry, agent-framework-openai: Fix Azure AI Search citation URLs (#6453)
• agent-framework-foundry: Fix aiohttp dependency specification (#6567)
• agent-framework-declarative: Fix declarative workflow execution (#6468)
• samples: Fix harness console rendering a single streamed tool call multiple times (#6549)
• samples: Fix ollama_chat_client.py to pass tools via the options dict (#6480)

1.8.1 - 2026-06-09

Added

• agent-framework-core: Add MCP client OTel spans per GenAI semantic conventions (#6349)
• agent-framework-core: Add MCP long-running task support (#6319)

Changed

• agent-framework-claude: Bump claude-agent-sdk to 0.2.87 (#6248)
• agent-framework-core: Document checkpoint storage security model and deserialization trust boundaries (#6295)
• agent-framework-azurefunctions: Document checkpoint storage security model and deserialization trust boundaries (#6295)

Fixed

• agent-framework-core: Filter MCP tool kwargs to declared params via allowlist (#6399)
• agent-framework-core: Fix per-service-call history persistence with server-storing clients (#6310)
• agent-framework-openai: Use getattr for non-OpenAI provider response compatibility (#6270)
• agent-framework-foundry-hosting: Refactor workflow-as-agent pending request handling (#6259)
• agent-framework-gemini: Make Gemini honor declarative outputSchema, not just JSON mode (#5893)
• agent-framework-mem0: Isolate entity retrieval and correct app_id payload (#6242)
• agent-framework-ag-ui: Match AG-UI approval responses to requested arguments (#6376)

1.8.0 - 2026-06-04

Added

• agent-framework-core: Add MCP-based skills discovery (McpSkillsSource) (#6169)
• agent-framework-core: Progressive tool exposure via FunctionInvocationContext (#6233)
• agent-framework-core: Add background agent support to harness agent (#6155)
• agent-framework-core: Add AgentFileStore and FileAccessProvider for file access operations (#6099)
• agent-framework-core: Coalesce code interpreter history chunks (#5801)
• agent-framework-core: Run sync tools off the event loop (#5773)
• agent-framework-bedrock: Implement native structured output support via Converse API (#6052)
• agent-framework-foundry: Add Foundry Adaptive Evals integration for rubric-generation (#6101)
• agent-framework-foundry: Add timeout parameter to FoundryAgent to fix ConnectTimeout on multi-turn conversations (#6263)
• agent-framework-mistral: Add Mistral AI embedding client package (#5480)
• agent-framework-a2a: Expose supported_protocol_bindings as configurable parameter (#6098)
• agent-framework-a2a: Set message_id on AgentResponseUpdate for message-bearing paths (#6163)
• agent-framework-foundry-hosting: Persist hosted MCP call/results as canonical mcp_call output (#6070)

Changed

• agent-framework-github-copilot: [BREAKING] Upgrade github-copilot-sdk to v1.0.0 (stable) (#6292)
• agent-framework-core: [BREAKING — experimental] Refactor Skill API to async resource and script lookup (#6135)
• agent-framework-github-copilot: Promote to release candidate (1.0.0rc1)
• agent-framework-declarative: Promote to release candidate (1.0.0rc1) (#6256)

Fixed

• agent-framework-core: Fix compaction message-id collisions and tool-loop summary persistence (#6299)
• agent-framework-core: Fix observability unsafe serialization of function-call arguments containing dataclass/framework objects (#6026)
• agent-framework-core: Consolidate MCP reliability fixes (#6145)
• agent-framework-core: Backfill chat span request model if unknown and response model is available (#6160)
• agent-framework-anthropic: Skip orphan anthropic thinking signatures (#5784)
• agent-framework-foundry: Fix FoundryAgent stripping model from PromptAgent requests (#5526)
• agent-framework-foundry-hosting: Fix toolbox consent flow in hosted agent (#6249)
• agent-framework-foundry-hosting: Drop hosted MCP calls when reasoning is stripped (#6210)
• agent-framework-openai: Fix OTLP HTTP base-endpoint losing /v1/{signal} auto-append (#5913)
• agent-framework-openai: Drop hosted MCP calls when reasoning is stripped (#6210)
• agent-framework-orchestrations: Fix spurious Magentic custom manager warning (#6261)
• agent-framework-azurefunctions: Fix integration test worker crashes on Py3.13 (#4260)

1.7.0 - 2026-05-28

Added

• agent-framework-core: Add HarnessAgent and background-agents harness provider (#6041, #6069)
• agent-framework-core, agent-framework-a2a: Add A2AAgentSession with referenced task IDs and input-required support (#5980)
• agent-framework-foundry: Add experimental prompt-agent conversion and deployment APIs (#5959)
• agent-framework-declarative: Add Foundry Toolbox MCP invocation support and sample (#5933)
• samples: Add hosting samples overview README (#5407)

Changed

• agent-framework-core: Align TodoProvider tool names with the C# implementation (#6107)
• agent-framework-core: Align ModeProvider tool names and instructions (#6071)
• agent-framework-chatkit: Raise the openai-chatkit dependency floor to >=1.6.4 to match the current typed API usage.
• agent-framework-declarative: [BREAKING] Remove Python-only declarative actions and rename alias kinds to C# canonical names (#6126)
• tests: Replace deprecated asyncio.iscoroutinefunction usage in DevUI cleanup-hook tests (#4563)

Fixed

• agent-framework-core: Point @experimental warnings at user code (#5996)
• agent-framework-declarative: Fix Foreach body exit wiring (#6050)
• agent-framework-devui: Fix streaming memory growth regression (#6038)
• agent-framework-foundry: Pass default headers to Foundry agents (#6040)
• agent-framework-foundry-hosting: Fix hosted handoff argument serialization (#5861)
• agent-framework-foundry-hosting: Allow hosted checkpoints to restore MessageRole values (#6049)
• agent-framework-openai: Preserve citation get_url metadata (#6037)
• agent-framework-openai: Guard Chat Completions streaming against null deltas (#5734)
• agent-framework-openai: Read response headers defensively for stream wrappers without .headers (#6028, #6029)
• samples: Fix sequential workflow sample output handling (#5976)

1.6.0 - 2026-05-21

Added

• agent-framework-core: Shell tool with support for local and Docker execution (#5664)
• agent-framework-monty: New Monty-backed CodeAct provider package (#5915)
• agent-framework-foundry: Add experimental hosted tool factories on FoundryChatClient (#5958)
• agent-framework-foundry: Include tool definitions for Foundry agent evals (#5974)
• agent-framework-a2a: Use non-streaming transport and return_immediately for background ops (#5963)

Changed

• agent-framework-core, agent-framework-foundry: [BREAKING] Enable instrumentation by default (#5865)
• agent-framework-foundry: Show more authentication methods in Foundry Toolbox MCP (#5719)

Fixed

• agent-framework-core: Skip MCP prompt loading when unsupported (#5370)

1.5.0 - 2026-05-19

Added

• agent-framework-core, agent-framework-foundry, agent-framework-openai: Record actual served model from Azure OpenAI (#5910)
• samples: New Foundry Hosted Agents samples for RAG, Skills, and Memory (#5822)

Changed

• agent-framework-core, agent-framework-azurefunctions, agent-framework-devui, agent-framework-foundry, agent-framework-orchestrations: Improve handling of intermediate outputs for workflows and orchestrations (#5623)
• agent-framework-durabletask: Pin 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.
• agent-framework-orchestrations: Bumped package to release candidate stage.

Fixed

• agent-framework-core: Parse YAML block scalars in SKILL.md frontmatter (#5863)
• agent-framework-github-copilot: Include tools added by ContextProvider.before_run in session creation (#5780)
• agent-framework-hyperlight: Skip symlinks when staging sandbox input (#5919)
• agent-framework-purview: Remove duplicate pop in InMemoryCacheProvider.remove (#5795)

1.4.0 - 2026-05-14

Added

• agent-framework-core: Forward MCP tool call metadata (#5815)
• agent-framework-core: Support list[str] arguments for file-based skill scripts (#5850)
• agent-framework-core: Strip server-issued response item IDs under storage (#5690)
• agent-framework-ag-ui: Add tool result display channel (#5762)
• agent-framework-ag-ui: Promote to release candidate stage (#5844)
• agent-framework-devui: Improvements for DevUI (#5840)

Changed

• agent-framework-core: [BREAKING — experimental skills API] Align file skill folder discovery with agentskills.io spec (#5807)
• agent-framework-core: [BREAKING — experimental skills API] Extract skill spec metadata into SkillFrontmatter (#5775)
• agent-framework-devui: [BREAKING] Tighten default access controls and CORS posture (#5740)
• agent-framework-a2a: [BREAKING] Migrate to a2a-sdk v1.0 (#5752)

Fixed

• agent-framework-a2a: Fix A2A v1.0 non-streaming response and sample runtime issues (#5849)
• agent-framework-foundry-hosting: Reject path-traversal context IDs in checkpoint storage (#5851)
• agent-framework-core: Prevent MCP message_handler deadlock on notification reload (#4866)

1.3.0 - 2026-05-07

Added

• agent-framework-core: Add ClassSkill for class-based skill definitions with declarative metadata and automatic method discovery (#5678)
• agent-framework-core: Add experimental session-mode harness context provider (#5611)
• agent-framework-core: Add experimental todo-list harness context provider (#5612)
• agent-framework-core: Add experimental memory harness context provider (#5613)
• agent-framework-core: Notify agent of external AgentModeProvider mode changes (#5650)
• agent-framework-core: Information-flow control prompt injection defense (#5331)
• agent-framework-openai: Support OpenAI and Gemini allowed_tools tool choice (#5322)
• agent-framework-openai: Support GPT-5 verbosity option and restore Foundry agent_reference (#5619)
• agent-framework-anthropic: Add base_url parameter to AnthropicClient and RawAnthropicClient (#5685)
• agent-framework-foundry-hosting: Add support for function approval flow in Foundry hosted agent (#5666)
• agent-framework-declarative: Add Python parity for InvokeMcpTool in declarative workflow (#5630)
• agent-framework-declarative: Add Python parity for HttpRequestAction in declarative workflow (#5599)
• agent-framework-claude, agent-framework-github-copilot: Enforce approval_mode in Claude and GitHub Copilot agents (#5562)
• agent-framework-github-copilot: Upgrade github-copilot-sdk to v1.0.0b2 with instruction_directories, copilot_home, and runtime options forwarding on session resume (#5665)
• samples: Add hosted agent sample with observability (#5608)
• samples: Add sample for hosted agent with files (#5596)

Changed

• agent-framework-core: [BREAKING — experimental skills API] Restructure agent skills to use multi-source architecture (#5584)
• agent-framework-foundry: Remove bespoke Foundry toolbox helpers; standardize on MCP for toolbox consumption (#5671)

Fixed

• agent-framework-core: Fix MCPStreamableHTTPTool leaking asyncio.CancelledError when MCP server is unreachable (#5687)
• agent-framework-openai: Drop completed continuation_token from shared options in tool loop (#5462)
• agent-framework-bedrock: Don't send toolChoice when no tools are configured (#5172)
• agent-framework-hyperlight: Fix WasmSandbox cross-thread Drop and harden hosted-agent sample (#5603)
• agent-framework-devui: Fix incorrect workflow timings by adding created_at to executor events (#5615)
• agent-framework-foundry-hosting: Fix hosted MCP replay producing orphan function_call_output (#5581)

1.2.2 - 2026-04-29

Added

• agent-framework-azure-contentunderstanding: New alpha package — Azure AI Content Understanding context provider that auto-analyzes file attachments (documents, images, audio, video) and injects structured results into the LLM context, with multi-document session state, configurable timeout, output filtering via AnalysisSection, and auto-registered list_documents / get_analyzed_document tools (#4829)
• agent-framework-foundry-hosting: Add hosted Durable Workflow support — propagate full conversation history to workflow agents and wire Workflow.as_agent() end-to-end via the foundry hosting layer (#5531)

Changed

• agent-framework-orchestrations: [BREAKING] Standardize orchestration terminal outputs as 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)
• agent-framework-core, agent-framework-declarative: Preserve 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)
• dependencies: Update workspace package dependencies and preserve mcp[ws] / uvicorn[standard] extras through override-dependencies in /python (#5555)

Fixed

• agent-framework-core: Fix observability spans not being correctly nested when using streaming (#5552)
• agent-framework-openai: Fix 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)

1.2.1 - 2026-04-28

Added

• agent-framework-foundry-hosting: Add file data type support to hosted-agent Responses, refresh foundry-hosted-agents samples, and add response test coverage (#5485)
• samples: Add requirements.txt and .env.example to the a2a/ hosting sample for pip-based setup (#5510)

Changed

• dependencies: Update rich requirement from <15.0.0,>=13.7.1 to >=13.7.1,<16.0.0 in /python (#5227)
• dependencies: Bump prek from 0.3.8 to 0.3.9 in /python (#5228)
• dependencies: Bump python-multipart from 0.0.22 to 0.0.26 in /python (#5286)
• dependencies: Bump pyasn1 from 0.6.2 to 0.6.3 in /python (#4748)
• dependencies: Bump pytest from 9.0.2 to 9.0.3 in /python/packages/ag-ui (#5461)
• dependencies: Bump pytest from 9.0.2 to 9.0.3 in /python/packages/devui (#5492)
• dependencies: Bump pytest from 9.0.2 to 9.0.3 in /python/packages/lab (#5470)
• dependencies: Bump uv from 0.11.3 to 0.11.6 in /python/packages/lab (#5469)
• dependencies: Bump vite from 7.1.12 to 7.3.2 in /python/packages/devui/frontend (#5127)
• dependencies: Bump vite from 7.1.12 to 7.3.2 in /python/samples/05-end-to-end/chatkit-integration/frontend (#5126)
• dependencies: Bump postcss from 8.5.6 to 8.5.10 in /python/packages/devui/frontend (#5484)
• dependencies: Bump postcss from 8.5.6 to 8.5.10 in /python/samples/05-end-to-end/chatkit-integration/frontend (#5491)
• dependencies: Bump postcss from 8.5.6 to 8.5.12 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#5527)
• dependencies: Bump picomatch from 4.0.3 to 4.0.4 in /python/packages/devui/frontend (#4921)
• dependencies: Bump picomatch from 4.0.3 to 4.0.4 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#4936)

Fixed

• agent-framework-core: Prevent inner_exception from being lost in AgentFrameworkException (#5167)

1.2.0 - 2026-04-24

Added

• agent-framework-core: Add functional workflow API (#4238)
• agent-framework-core, agent-framework-github-copilot: Add OpenTelemetry integration for GitHubCopilotAgent (#5142)
• agent-framework-a2a: Add Agent Framework to A2A bridge support (#2403)
• agent-framework-foundry: Surface oauth_consent_request events from Responses API in Foundry clients (#5070)

Changed

• agent-framework-core, agent-framework-foundry: Update FoundryAgent for hosted agent sessions (#5447)
• agent-framework-foundry-hosting: Upgrade hosting server dependency and add more type support (#5459)

Fixed

• agent-framework-ag-ui: Fix reasoning role and multimodal media parsing to follow specification (#5389)
• agent-framework-foundry: Stop emitting [TOOLBOXES] warning for every FoundryChatClient call (#5440)
• agent-framework-anthropic, agent-framework-azure-ai-search, agent-framework-azure-cosmos: Fix user agent prefix (#5455)

1.1.1 - 2026-04-23

Added

• agent-framework-core: Add expected_output ground-truth support to evaluate_workflow for similarity evaluators (#5234)
• agent-framework-ag-ui, agent-framework-a2a: Propagate thread_id and forwarded_props through AG-UI to A2A context_id (#5383)
• samples: Add second approval-required tool (set_stop_loss) to concurrent_builder_tool_approval sample (#4875)
• agent-framework-core: Add SKIP_PARSING sentinel for FunctionTool.invoke to bypass Content-wrapping and return raw function results (#5424)

Changed

• agent-framework-foundry-hosting: Correct Development Status classifier from Beta (4) to Alpha (3) to match the package's lifecycle stage (#5387)
• tests: Add Python flaky test report workflow (#5342)
• agent-framework-hyperlight: Simplify host callback to pass raw Python results via SKIP_PARSING, switch execute_code input schema to a plain JSON-schema dict, and tighten public API surface (#5424)

Fixed

• agent-framework-openai: Fix OpenAI Responses streaming to propagate created_at from the final response.completed event (#5382)
• agent-framework-openai: Fix OpenAIEmbeddingClient to use AsyncOpenAI for /openai/v1 endpoints (#5137)
• agent-framework-openai: Exclude null file_id from input_image payload to prevent schema 400 errors (#5125)
• agent-framework-foundry: Reconcile Toolbox hosted-tool payloads with the Responses API (#5414)
• agent-framework-ag-ui: Pass client thread_id as session_id when constructing AgentSession (#5384)
• agent-framework-hyperlight: Thread-confine WasmSandbox interactions via per-entry ThreadPoolExecutor to eliminate the PyO3 unsendable panic when touched from asyncio worker threads (#5424)

1.1.0 - 2026-04-21

Added

• agent-framework-gemini: Add GeminiChatClient (#4847)
• agent-framework-core: Add context_providers and description to workflow.as_agent() (#4651)
• agent-framework-core: Add experimental file history provider (#5248)
• agent-framework-core: Add OpenAI types to the default checkpoint encoding allow list (#5297)
• agent-framework-core: Add AgentExecutorResponse.with_text() to preserve conversation history through custom executors (#5255)
• agent-framework-a2a: Propagate A2A metadata from Message, Artifact, Task, and event types (#5256)
• agent-framework-core: Add finish_reason support to AgentResponse and AgentResponseUpdate (#5211)
• agent-framework-hyperlight: Add Hyperlight CodeAct package and docs (#5185)
• agent-framework-openai: Add search tool content support for OpenAI responses (#5302)
• agent-framework-foundry: Add support for Foundry Toolboxes (#5346)
• agent-framework-ag-ui: Expose forwardedProps to agents and tools via session metadata (#5264)
• agent-framework-foundry: Add hosted agent V2 support (#5379)

Changed

• agent-framework-azure-cosmos: [BREAKING] 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)
• agent-framework-core: Improve skill name validation (#4530)
• agent-framework-azure-cosmos: Add allowed_checkpoint_types support to CosmosCheckpointStorage for parity with FileCheckpointStorage (#5202)
• agent-framework-core: Move InMemory history provider injection to first invocation (#5236)
• agent-framework-github-copilot: Forward provider config to SessionConfig in GitHubCopilotAgent (#5195)
• agent-framework-hyperlight-codeact: Flatten execute_code output (#5333)
• dependencies: Bump pygments from 2.19.2 to 2.20.0 in /python (#4978)
• tests: Bump misc integration retry delay to 30s (#5293)
• tests: Improve misc integration test robustness (#5295)
• tests: Skip hosted tools test on transient upstream MCP errors (#5296)

Fixed

• agent-framework-core: Fix python-feature-lifecycle skill YAML frontmatter (#5226)
• agent-framework-core: Fix HandoffBuilder dropping function-level middleware when cloning agents (#5220)
• agent-framework-ag-ui: Fix deterministic state updates from tool results (#5201)
• agent-framework-devui: Fix streaming memory growth and add cross-platform regression coverage (#5221)
• agent-framework-core: Skip get_final_response in _finalize_stream when the stream has errored (#5232)
• agent-framework-openai: Fix reasoning replay when store=False (#5250)
• agent-framework-foundry: Handle url_citation annotations in FoundryChatClient streaming responses (#5071)
• agent-framework-gemini: Fix Gemini client support for Gemini API and Vertex AI (#5258)
• agent-framework-copilotstudio: Fix CopilotStudioAgent to reuse conversation ID from an existing session (#5299)

[devui-1.0.0b260414] - 2026-04-14

Fixed

• agent-framework-devui: Fix streaming memory growth in DevUI frontend (#5221)

1.0.1 - 2026-04-09

Added

• samples: Add sample documentation for two separate Neo4j context providers for retrieval and memory (#4010)
• agent-framework-azure-cosmos: Add Cosmos DB NoSQL checkpoint storage for Python workflows (#4916)

Changed

• docs: Remove pre-release flag from agent-framework installation instructions (#5082)
• samples: Revise agent examples in README.md (#5067)
• repo: Update CHANGELOG with v1.0.0 release (#5069)
• agent-framework-orchestrations: [BREAKING] Fix handoff workflow context management and improve AG-UI demo (#5136)
• agent-framework-core: Restrict persisted checkpoint deserialization by default (#4941)
• samples: Bump vite from 7.3.1 to 7.3.2 in /python/samples/05-end-to-end/ag_ui_workflow_handoff/frontend (#5132)
• python: Bump cryptography from 46.0.6 to 46.0.7 (#5176)
• python: Bump mcp from 1.26.0 to 1.27.0 (#5117)
• python: Bump mcp[ws] from 1.26.0 to 1.27.0 (#5119)

Fixed

• agent-framework-core: Raise clear handler registration error for unresolved TypeVar annotations (#4944)
• agent-framework-openai: Fix response_format crash on background polling with empty text (#5146)
• agent-framework-foundry: Strip tools from FoundryAgent request when agent_reference is present (#5101)
• agent-framework-core: Fix test compatibility for entity key validation (#5179)
• agent-framework-openai: Stop emitting duplicate reasoning content from response.reasoning_text.done and response.reasoning_summary_text.done events (#5162)

1.0.0 - 2026-04-02

Added

• repo: Add PACKAGE_STATUS.md to track lifecycle status of all Python packages (#5062)

Changed

• agent-framework, agent-framework-core, agent-framework-openai, agent-framework-foundry: [BREAKING] Promote from 1.0.0rc6 to 1.0.0 (Production/Stable) (#5062)
• agent-framework-core, agent-framework-openai, agent-framework-foundry: [BREAKING] Dependency floors now require released >=1.0.0,<2 packages, breaking compatibility with older RC installs (#5062)
• agent-framework-a2a, agent-framework-ag-ui, agent-framework-anthropic, agent-framework-azure-ai-search, agent-framework-azure-cosmos, agent-framework-azurefunctions, agent-framework-bedrock, agent-framework-chatkit, agent-framework-claude, agent-framework-copilotstudio, agent-framework-declarative, agent-framework-devui, agent-framework-durabletask, agent-framework-foundry-local, agent-framework-github-copilot, agent-framework-lab, agent-framework-mem0, agent-framework-ollama, agent-framework-orchestrations, agent-framework-purview, agent-framework-redis: Bump beta versions from 1.0.0b260330 to 1.0.0b260402 (#5062)
• docs: Update install instructions to drop --pre flag for released packages (#5062)

Removed

• agent-framework-core: [BREAKING] Remove deprecated BaseContextProvider and BaseHistoryProvider aliases (#5062)
• agent-framework-core: [BREAKING] Remove deprecated text parameter from Message constructor (#5062)

Fixed

• agent-framework-core, agent-framework-openai, agent-framework-foundry, agent-framework-azurefunctions, agent-framework-devui, agent-framework-orchestrations, agent-framework-azure-ai-search: Migrate message construction from Message(text=...) to Message(contents=[...]) throughout codebase (#5062)
• agent-framework-devui: Accept legacy payload formats (text, message, content, input, data) and convert to framework-native Message(contents=...) (#5062)
• samples: Fix Foundry samples to use env vars consistently and update install guidance (#5062)

1.0.0rc6 - 2026-03-30

Added

• agent-framework-openai: New package extracted from core for OpenAI and Azure OpenAI provider support (#4818)
• agent-framework-foundry: New package for Azure AI Foundry integration (#4818)
• agent-framework-core: Support structuredContent in MCP tool results and fix sampling options type (#4763)
• agent-framework-core: Include reasoning messages in MESSAGES_SNAPSHOT events (#4844)
• agent-framework-core: [BREAKING] Add context mode to AgentExecutor (#4668)

Changed

• agent-framework-core: [BREAKING] Remove deprecated kwargs compatibility paths (#4858)
• agent-framework-core: [BREAKING] Reduce core dependencies and simplify optional integrations (#4904)
• agent-framework-openai: [BREAKING] Provider-leading client design & OpenAI package extraction (#4818)
• agent-framework-openai: [BREAKING] Fix OpenAI Azure routing and provider samples (#4925)
• agent-framework-azure-ai: Deprecate Azure AI v1 (Persistent Agents API) helper methods (#4804)
• agent-framework-core: Avoid duplicate agent response telemetry (#4685)
• agent-framework-devui: Bump flatted from 3.3.3 to 3.4.2 in frontend (#4805)
• samples: Move ag_ui_workflow_handoff demo from demos/ to 05-end-to-end/ (#4900)

Fixed

• agent-framework-core: Fix streaming path to emit mcp_server_tool_result on output_item.done instead of output_item.added (#4821)
• agent-framework-a2a: Fix A2AAgent to surface message content from in-progress TaskStatusUpdateEvents (#4798)
• agent-framework-core: Fix PydanticSchemaGenerationError when using from __future__ import annotations with @tool (#4822)
• samples: Fix broken samples for GitHub Copilot, declarative, and Responses API (#4915)
• repo: Fix: update PyRIT repository link from Azure/PyRIT to microsoft/PyRIT (#4960)

1.0.0rc5 - 2026-03-19

Added

• samples: Add foundry hosted agents samples for python (#4648)
• repo: Add automated stale issue and PR follow-up ping workflow (#4776)
• agent-framework-ag-ui: Emit AG-UI events for MCP tool calls, results, and text reasoning (#4760)
• agent-framework-ag-ui: Emit TOOL_CALL_RESULT events when resuming after tool approval (#4758)

Changed

• agent-framework-devui: Bump minimatch from 3.1.2 to 3.1.5 in frontend (#4337)
• agent-framework-devui: Bump rollup from 4.47.1 to 4.59.0 in frontend (#4338)
• agent-framework-core: Unify tool results as Content items with rich content support (#4331)
• agent-framework-a2a: Default A2AAgent name and description from AgentCard (#4661)
• agent-framework-core: [BREAKING] Clean up kwargs across agents, chat clients, tools, and sessions (#4581)
• agent-framework-devui: Bump tar from 7.5.9 to 7.5.11 (#4688)
• repo: Improve Python dependency range automation (#4343)
• agent-framework-core: Normalize empty MCP tool output to null (#4683)
• agent-framework-core: Remove bad dependency (#4696)
• agent-framework-core: Keep MCP cleanup on the owner task (#4687)
• agent-framework-a2a: Preserve A2A message context_id (#4686)
• repo: Bump danielpalme/ReportGenerator-GitHub-Action from 5.5.1 to 5.5.3 (#4542)
• repo: Bump MishaKav/pytest-coverage-comment from 1.2.0 to 1.6.0 (#4543)
• agent-framework-core: Bump pyjwt from 2.11.0 to 2.12.0 (#4699)
• agent-framework-azure-ai: Reduce Azure chat client import overhead (#4744)
• repo: Simplify Python Poe tasks and unify package selectors (#4722)
• agent-framework-core: Aggregate token usage across tool-call loop iterations in invoke_agent span (#4739)
• agent-framework-core: Support detail field in OpenAI Chat API image_url payload (#4756)
• agent-framework-anthropic: [BREAKING] Refactor middleware layering and split Anthropic raw client (#4746)
• agent-framework-github-copilot: Emit tool call events in GitHubCopilotAgent streaming (4711)

Fixed

• agent-framework-core: Validate approval responses against the server-side pending request registry (#4548)
• agent-framework-devui: Validate function approval responses in the DevUI executor (#4598)
• agent-framework-azurefunctions: Use deepcopy for state snapshots so nested mutations are detected in durable workflow activities (#4518)
• agent-framework-bedrock: Fix BedrockChatClient sending invalid toolChoice "none" to the Bedrock API (#4535)
• agent-framework-core: Fix type hint for Case and Default (#3985)
• agent-framework-core: Fix duplicate tool names between supplied tools and MCP servers (#4649)
• agent-framework-core: Fix _deduplicate_messages catch-all branch dropping valid repeated messages (#4716)
• samples: Fix Azure Redis sample missing session for history persistence (#4692)
• agent-framework-core: Fix thread serialization for multi-turn tool calls (#4684)
• agent-framework-core: Fix RUN_FINISHED.interrupt to accumulate all interrupts when multiple tools need approval (#4717)
• agent-framework-azurefunctions: Fix missing methods on the Content class in durable tasks (#4738)
• agent-framework-core: Fix ENABLE_SENSITIVE_DATA being ignored when set after module import (#4743)
• agent-framework-a2a: Fix A2AAgent to invoke context providers before and after run (#4757)
• agent-framework-core: Fix MCP tool schema normalization for zero-argument tools missing the properties key (#4771)

1.0.0rc4 - 2026-03-11

Added

• agent-framework-core: Add propagate_session to as_tool() for session sharing in agent-as-tool scenarios (#4439)
• agent-framework-core: Forward runtime kwargs to skill resource functions (#4417)
• samples: Add A2A server sample (#4528)

Changed

• agent-framework-github-copilot: [BREAKING] Update integration to use ToolInvocation and ToolResult types (#4551)
• agent-framework-azure-ai: [BREAKING] Upgrade to azure-ai-projects 2.0+ (#4536)

Fixed

• agent-framework-core: Propagate MCP isError flag through the function middleware pipeline (#4511)
• agent-framework-core: Fix as_agent() not defaulting name/description from client properties (#4484)
• agent-framework-core: Exclude conversation_id from chat completions API options (#4517)
• agent-framework-core: Fix conversation ID propagation when chat_options is a dict (#4340)
• agent-framework-core: Auto-finalize ResponseStream on iteration completion (#4478)
• agent-framework-core: Prevent pickle deserialization of untrusted HITL HTTP input (#4566)
• agent-framework-core: Fix executor_completed event handling for non-copyable raw_representation in mixed workflows (#4493)
• agent-framework-core: Fix store=False not overriding client default (#4569)
• agent-framework-redis: Fix RedisContextProvider compatibility with redisvl 0.14.0 by using AggregateHybridQuery (#3954)
• samples: Fix chat_response_cancellation sample to use Message objects (#4532)
• agent-framework-purview: Fix broken link in Purview README (Microsoft 365 Dev Program URL) (#4610)

1.0.0rc3 - 2026-03-04

Added

• agent-framework-core: Add Shell tool (#4339)
• agent-framework-core: Add file_ids and data_sources support to get_code_interpreter_tool() (#4201)
• agent-framework-core: Map file citation annotations from TextDeltaBlock in Assistants API streaming (#4316, #4320)
• agent-framework-claude: Add OpenTelemetry instrumentation to ClaudeAgent (#4278, #4326)
• agent-framework-azure-cosmos: Add Azure Cosmos history provider package (#4271)
• samples: Add auto_retry.py sample for rate limit handling (#4223)
• tests: Add regression tests for Entry JoinExecutor workflow input initialization (#4335)

Changed

• samples: Restructure and improve Python samples (#4092)
• agent-framework-orchestrations: [BREAKING] Tighten HandoffBuilder to require Agent instead of SupportsAgentRun (#4301, #4302)
• samples: Update workflow orchestration samples to use AzureOpenAIResponsesClient (#4285)

Fixed

• agent-framework-bedrock: Fix embedding test stub missing meta attribute (#4287)
• agent-framework-ag-ui: Fix approval payloads being re-processed on subsequent conversation turns (#4232)
• agent-framework-core: Fix response_format resolution in streaming finalizer (#4291)
• agent-framework-core: Strip reserved kwargs in AgentExecutor to prevent duplicate-argument TypeError (#4298)
• agent-framework-core: Preserve workflow run kwargs when continuing with run(responses=...) (#4296)
• agent-framework-core: Fix WorkflowAgent not persisting response messages to session history (#4319)
• agent-framework-core: Fix single-tool input handling in OpenAIResponsesClient._prepare_tools_for_openai (#4312)
• agent-framework-core: Fix agent option merge to support dict-defined tools (#4314)
• agent-framework-core: Fix executor handler type resolution when using from __future__ import annotations (#4317)
• agent-framework-core: Fix walrus operator precedence for model_id kwarg in AzureOpenAIResponsesClient (#4310)
• agent-framework-core: Handle thread.message.completed event in Assistants API streaming (#4333)
• agent-framework-core: Fix MCP tools duplicated on second turn when runtime tools are present (#4432)
• agent-framework-core: Fix PowerFx eval crash on non-English system locales by setting CurrentUICulture to en-US (#4408)
• agent-framework-orchestrations: Fix StandardMagenticManager to propagate session to manager agent (#4409)
• agent-framework-orchestrations: Fix IndexError when reasoning models produce reasoning-only messages in Magentic-One workflow (#4413)
• agent-framework-azure-ai: Fix parsing oauth_consent_request events in Azure AI client (#4197)
• agent-framework-anthropic: Set role="assistant" on message_start streaming update (#4329)
• samples: Fix samples discovered by auto validation pipeline (#4355)
• samples: Use AgentResponse.value instead of model_validate_json in HITL sample (#4405)
• agent-framework-devui: Fix .NET conversation memory handling in DevUI integration (#3484, #4294)

1.0.0rc2 - 2026-02-25

Added

• agent-framework-core: Support Agent Skills (#4210)
• agent-framework-core: Add embedding abstractions and OpenAI implementation (Phase 1) (#4153)
• agent-framework-core: Add Foundry Memory Context Provider (#3943)
• agent-framework-core: Add max_function_calls to FunctionInvocationConfiguration (#4175)
• agent-framework-core: Add CreateConversationExecutor, fix input routing, remove unused handler layer (#4159)
• agent-framework-azure-ai-search: Azure AI Search provider improvements - EmbeddingGenerator, async context manager, KB message handling (#4212)
• agent-framework-azure-ai-search: Enhance Azure AI Search Citations with Document URLs in Foundry V2 (#4028)
• agent-framework-ag-ui: Add Workflow Support, Harden Streaming Semantics, and add Dynamic Handoff Demo (#3911)

Changed

• agent-framework-declarative: [BREAKING] Add InvokeFunctionTool action for declarative workflows (#3716)

Fixed

• agent-framework-core: Fix thread corruption when max_iterations is reached (#4234)
• agent-framework-core: Fix workflow runner concurrent processing (#4143)
• agent-framework-core: Fix doubled tool_call arguments in MESSAGES_SNAPSHOT when streaming (#4200)
• agent-framework-core: Fix OpenAI chat client compatibility with third-party endpoints and OTel 0.4.14 (#4161)
• agent-framework-claude: Fix structured_output propagation in ClaudeAgent (#4137)

1.0.0rc1 - 2026-02-19

Release candidate for agent-framework-core and agent-framework-azure-ai packages.

Added

• agent-framework-core: Add default in-memory history provider for workflow agents (#3918)
• agent-framework-core: Durable support for workflows (#3630)

Changed

• agent-framework-core: [BREAKING] Scope provider state by source_id and standardize source IDs (#3995)
• agent-framework-core: [BREAKING] Fix chat/agent message typing alignment (#3920)
• agent-framework-core: [BREAKING] Remove FunctionTool[Any] compatibility shim for schema passthrough (#3907)
• agent-framework-core: Inject OpenTelemetry trace context into MCP requests (#3780)
• agent-framework-core: Replace wildcard imports with explicit imports (#3908)

Fixed

• agent-framework-core: Fix hosted MCP tool approval flow for all session/streaming combinations (#4054)
• agent-framework-core: Prevent repeating instructions in continued Responses API conversations (#3909)
• agent-framework-core: Add missing system instruction attribute to invoke_agent span (#4012)
• agent-framework-core: Fix tool normalization and provider sample consolidation (#3953)
• agent-framework-azure-ai: Warn on unsupported AzureAIClient runtime tool/structured_output overrides (#3919)
• agent-framework-azure-ai-search: Improve Azure AI Search package test coverage (#4019)
• agent-framework-anthropic: Fix Anthropic option conflicts and manager parse retries (#4000)
• agent-framework-anthropic: Track and enforce 85%+ unit test coverage for anthropic package (#3926)
• agent-framework-azurefunctions: Achieve 85%+ unit test coverage for azurefunctions package (#3866)
• samples: Fix workflow, declarative, Redis, Anthropic, GitHub Copilot, Azure AI, MCP, eval, and migration samples (#4055, #4051, #4049, #4046, #4033, #4030, #4027, #4032, #4025, #4021, #4022, #4001)

1.0.0b260212 - 2026-02-12

Added

• agent-framework-core: Allow AzureOpenAIResponsesClient creation with Foundry project endpoint (#3814)

Changed

• agent-framework-core: [BREAKING] Wire context provider pipeline, remove old types, update all consumers (#3850)
• agent-framework-core: [BREAKING] Checkpoint refactor: encode/decode, checkpoint format, etc (#3744)
• agent-framework-core: [BREAKING] Replace Hosted*Tool classes with tool methods (#3634)
• agent-framework-core: Replace Pydantic Settings with TypedDict + load_settings() (#3843)
• agent-framework-core: Centralize tool result parsing in FunctionTool.invoke() (#3854)
• samples: Restructure Python samples into progressive 01-05 layout (#3862)
• samples: Adopt AzureOpenAIResponsesClient, reorganize orchestration examples, and fix workflow/orchestration bugs (#3873)

Fixed

• agent-framework-core: Fix non-ascii chars in span attributes (#3894)
• agent-framework-core: Fix streamed workflow agent continuation context by finalizing AgentExecutor streams (#3882)
• agent-framework-ag-ui: Fix Workflow.as_agent() streaming regression (#3875)
• agent-framework-declarative: Fix declarative package powerfx import crash and response_format kwarg error (#3841)

1.0.0b260210 - 2026-02-10

Added

• agent-framework-core: Add long-running agents and background responses support with ContinuationToken TypedDict, background option in OpenAIResponsesOptions, and continuation token propagation through response types (#3808)
• agent-framework-core: Add streaming support for code interpreter deltas (#3775)
• agent-framework-core: Add explicit input, output, and workflow_output parameters to @handler, @executor and request_info (#3472)
• agent-framework-core: Add explicit schema handling to @tool decorator (#3734)
• agent-framework-core: New session and context provider types (#3763)
• agent-framework-purview: Add tests to Purview package (#3513)

Changed

• agent-framework-core: [BREAKING] Renamed core types for simpler API: ChatAgent → Agent, RawChatAgent → RawAgent, ChatMessage → Message, ChatClientProtocol → SupportsChatGetResponse (#3747)
• agent-framework-core: [BREAKING] Moved to a single get_response and run API (#3379)
• agent-framework-core: [BREAKING] Merge send_responses into run method (#3720)
• agent-framework-core: [BREAKING] Renamed AgentRunContext to AgentContext (#3714)
• agent-framework-core: [BREAKING] Renamed AgentProtocol to SupportsAgentRun (#3717)
• agent-framework-core: [BREAKING] Renamed next middleware parameter to call_next (#3735)
• agent-framework-core: [BREAKING] Standardize TypeVar naming convention (TName → NameT) (#3770)
• agent-framework-core: [BREAKING] Refactor workflow events to unified discriminated union pattern (#3690)
• agent-framework-core: [BREAKING] Refactor SharedState to State with sync methods and superstep caching (#3667)
• agent-framework-core: [BREAKING] Move single-config fluent methods to constructor parameters (#3693)
• agent-framework-core: [BREAKING] Types API Review improvements (#3647)
• agent-framework-core: [BREAKING] Fix workflow as agent streaming output (#3649)
• agent-framework-orchestrations: [BREAKING] Move orchestrations to dedicated package (#3685)
• agent-framework-core: [BREAKING] Remove workflow register factory methods; update tests and samples (#3781)
• agent-framework-core: Include sub-workflow structure in graph signature for checkpoint validation (#3783)
• agent-framework-core: Adjust workflows TypeVars from prefix to suffix naming convention (#3661)
• agent-framework-purview: Update CorrelationId (#3745)
• agent-framework-anthropic: Added internal kwargs filtering for Anthropic client (#3544)
• agent-framework-github-copilot: Updated instructions/system_message logic in GitHub Copilot agent (#3625)
• agent-framework-mem0: Disable mem0 telemetry by default (#3506)

Fixed

• agent-framework-core: Fix workflow not pausing when agent calls declaration-only tool (#3757)
• agent-framework-core: Fix GroupChat orchestrator message cleanup issue (#3712)
• agent-framework-core: Fix HandoffBuilder silently dropping context_provider during agent cloning (#3721)
• agent-framework-core: Fix subworkflow duplicate request info events (#3689)
• agent-framework-core: Fix workflow cancellation not propagating to active executors (#3663)
• agent-framework-core: Filter response_format from MCP tool call kwargs (#3494)
• agent-framework-core: Fix broken Content API imports in Python samples (#3639)
• agent-framework-core: Potential fix for clear-text logging of sensitive information (#3573)
• agent-framework-core: Skip model_deployment_name validation for application endpoints (#3621)
• agent-framework-azure-ai: Fix AzureAIClient dropping agent instructions (Responses API) (#3636)
• agent-framework-azure-ai: Fix AzureAIAgentClient dropping agent instructions in sequential workflows (#3563)
• agent-framework-ag-ui: Fix AG-UI message handling and MCP tool double-call bug (#3635)
• agent-framework-claude: Handle API errors in run_stream() method (#3653)
• agent-framework-claude: Preserve $defs in JSON schema for nested Pydantic models (#3655)

1.0.0b260130 - 2026-01-30

Added

• agent-framework-claude: Add BaseAgent implementation for Claude Agent SDK (#3509)
• agent-framework-core: Add core types and agents unit tests (#3470)
• agent-framework-core: Add core utilities unit tests (#3487)
• agent-framework-core: Add observability unit tests to improve coverage (#3469)
• agent-framework-azure-ai: Improved AzureAI package test coverage (#3452)

Changed

• agent-framework-core: Added generic types to ChatOptions and ChatResponse/AgentResponse for Response Format (#3305)
• agent-framework-durabletask: Update durabletask package (#3492)

1.0.0b260128 - 2026-01-28

Changed

• agent-framework-core: [BREAKING] Renamed @ai_function decorator to @tool and AIFunction to FunctionTool (#3413)
• agent-framework-core: [BREAKING] Add factory pattern to GroupChatBuilder and MagenticBuilder (#3224)
• agent-framework-github-copilot: [BREAKING] Renamed Github to GitHub (#3486)

1.0.0b260127 - 2026-01-27

Added

• agent-framework-github-copilot: Add BaseAgent implementation for GitHub Copilot SDK (#3404)

1.0.0b260123 - 2026-01-23

Added

• agent-framework-azure-ai: Add support for rai_config in agent creation (#3265)
• agent-framework-azure-ai: Support reasoning config for AzureAIClient (#3403)
• agent-framework-anthropic: Add response_format support for structured outputs (#3301)

Changed

• agent-framework-core: [BREAKING] Simplify content types to a single class with classmethod constructors (#3252)
• agent-framework-core: [BREAKING] Make response_format validation errors visible to users (#3274)
• agent-framework-ag-ui: [BREAKING] Simplify run logic; fix MCP and Anthropic client issues (#3322)
• agent-framework-core: Prefer runtime kwargs for conversation_id in OpenAI Responses client (#3312)

Fixed

• agent-framework-core: Verify types during checkpoint deserialization to prevent marker spoofing (#3243)
• agent-framework-core: Filter internal args when passing kwargs to MCP tools (#3292)
• agent-framework-core: Handle anyio cancel scope errors during MCP connection cleanup (#3277)
• agent-framework-core: Filter conversation_id when passing kwargs to agent as tool (#3266)
• agent-framework-core: Fix use_agent_middleware calling private _normalize_messages (#3264)
• agent-framework-core: Add system_instructions to ChatClient LLM span tracing (#3164)
• agent-framework-core: Fix Azure chat client asynchronous filtering (#3260)
• agent-framework-core: Fix HostedImageGenerationTool mapping to ImageGenTool for Azure AI (#3263)
• agent-framework-azure-ai: Fix local MCP tools with AzureAIProjectAgentProvider (#3315)
• agent-framework-azurefunctions: Fix MCP tool invocation to use the correct agent (#3339)
• agent-framework-declarative: Fix MCP tool connection not passed from YAML to Azure AI agent creation API (#3248)
• agent-framework-ag-ui: Properly handle JSON serialization with handoff workflows as agent (#3275)
• agent-framework-devui: Ensure proper form rendering for int (#3201)

1.0.0b260116 - 2026-01-16

Added

• agent-framework-azure-ai: Create/Get Agent API for Azure V1 (#3192)
• agent-framework-core: Create/Get Agent API for OpenAI Assistants (#3208)
• agent-framework-ag-ui: Support service-managed thread on AG-UI (#3136)
• agent-framework-ag-ui: Add MCP tool support for AG-UI approval flows (#3212)
• samples: Add AzureAI sample for downloading code interpreter generated files (#3189)

Changed

• agent-framework-core: [BREAKING] Rename create_agent to as_agent (#3249)
• agent-framework-core: [BREAKING] Rename WorkflowOutputEvent.source_executor_id to executor_id for API consistency (#3166)

Fixed

• agent-framework-core: Properly configure structured outputs based on new options dict (#3213)
• agent-framework-core: Correct FunctionResultContent ordering in WorkflowAgent.merge_updates (#3168)
• agent-framework-azurefunctions: Update DurableAIAgent and fix integration tests (#3241)
• agent-framework-azure-ai: Create/Get Agent API fixes and example improvements (#3246)

1.0.0b260114 - 2026-01-14

Added

• agent-framework-azure-ai: Create/Get Agent API for Azure V2 (#3059) by @moonbox3
• agent-framework-declarative: Add declarative workflow runtime (#2815) by @moonbox3
• agent-framework-ag-ui: Add dependencies param to ag-ui FastAPI endpoint (#3191) by @moonbox3
• agent-framework-ag-ui: Add Pydantic request model and OpenAPI tags support to AG-UI FastAPI endpoint (#2522) by @claude89757
• agent-framework-core: Add tool call/result content types and update connectors and samples (#2971) by @moonbox3
• agent-framework-core: Add more specific exceptions to Workflow (#3188) by @TaoChenOSU

Changed

• agent-framework-core: [BREAKING] Refactor orchestrations (#3023) by @TaoChenOSU
• agent-framework-core: [BREAKING] Introducing Options as TypedDict and Generic (#3140) by @eavanvalkenburg
• agent-framework-core: [BREAKING] Removed display_name, renamed context_providers, middleware and AggregateContextProvider (#3139) by @eavanvalkenburg
• agent-framework-core: MCP Improvements: improved connection loss behavior, pagination for loading and a param to control representation (#3154) by @eavanvalkenburg
• agent-framework-azure-ai: Azure AI direct A2A endpoint support (#3127) by @moonbox3

Fixed

• agent-framework-anthropic: Fix duplicate ToolCallStartEvent in streaming tool calls (#3051) by @moonbox3
• agent-framework-anthropic: Fix Anthropic streaming response bugs (#3141) by @eavanvalkenburg
• agent-framework-ag-ui: Execute tools with approval_mode, fix shared state, code cleanup (#3079) by @moonbox3
• agent-framework-azure-ai: Fix AzureAIClient tool call bug for AG-UI use (#3148) by @moonbox3
• agent-framework-core: Fix MCPStreamableHTTPTool to use new streamable_http_client API (#3088) by @Copilot
• agent-framework-core: Multiple bug fixes (#3150) by @eavanvalkenburg

1.0.0b260107 - 2026-01-07

Added

• agent-framework-devui: Improve DevUI and add Context Inspector view as a new tab under traces (#2742) by @victordibia
• samples: Add streaming sample for Azure Functions (#3057) by @gavin-aguiar

Changed

• repo: Update templates (#3106) by @eavanvalkenburg

Fixed

• agent-framework-ag-ui: Fix MCP tool result serialization for list[TextContent] (#2523) by @claude89757
• agent-framework-azure-ai: Fix response_format handling for structured outputs (#3114) by @moonbox3

1.0.0b260106 - 2026-01-06

Added

• repo: Add issue template and additional labeling (#3006) by @eavanvalkenburg

Changed

• None

Fixed

• agent-framework-core: Fix max tokens translation and add extra integer test (#3037) by @eavanvalkenburg
• agent-framework-azure-ai: Fix failure when conversation history contains assistant messages (#3076) by @moonbox3
• agent-framework-core: Use HTTP exporter for http/protobuf protocol (#3070) by @takanori-terai
• agent-framework-core: Fix ExecutorInvokedEvent and ExecutorCompletedEvent observability data (#3090) by @moonbox3
• agent-framework-core: Honor tool_choice parameter passed to agent.run() and chat client methods (#3095) by @moonbox3
• samples: AzureAI SharePoint sample fix (#3108) by @giles17

1.0.0b251223 - 2025-12-23

Added

• agent-framework-bedrock: Introducing support for Bedrock-hosted models (Anthropic, Cohere, etc.) (#2610)
• agent-framework-core: Added response.created and response.in_progress event process to OpenAIBaseResponseClient (#2975)
• agent-framework-foundry-local: Introducing Foundry Local Chat Clients (#2915)
• samples: Added GitHub MCP sample with PAT (#2967)

Changed

• agent-framework-core: Preserve reasoning blocks with OpenRouter (#2950)

1.0.0b251218 - 2025-12-18

Added

• agent-framework-core: Azure AI Agent with Bing Grounding Citations sample (#2892)
• agent-framework-core: Workflow option to visualize internal executors (#2917)
• agent-framework-core: Workflow cancellation sample (#2732)
• agent-framework-core: Azure Managed Redis support with credential provider (#2887)
• agent-framework-core: Additional arguments for Azure AI agent configuration (#2922)

Changed

• agent-framework-ollama: Updated Ollama package version (#2920)
• agent-framework-ollama: Move Ollama samples to samples getting started directory (#2921)
• agent-framework-core: Cleanup and refactoring of chat clients (#2937)
• agent-framework-core: Align Run ID and Thread ID casing with AG-UI TypeScript SDK (#2948)

Fixed

• agent-framework-core: Fix Pydantic error when using Literal types for tool parameters (#2893)
• agent-framework-core: Correct MCP image type conversion in _mcp.py (#2901)
• agent-framework-core: Fix BadRequestError when using Pydantic models in response formatting (#1843)
• agent-framework-core: Propagate workflow kwargs to sub-workflows via WorkflowExecutor (#2923)
• agent-framework-core: Fix WorkflowAgent event handling and kwargs forwarding (#2946)

1.0.0b251216 - 2025-12-16

Added

• agent-framework-ollama: Ollama connector for Agent Framework (#1104)
• agent-framework-core: Added custom args and thread object to ai_function kwargs (#2769)
• agent-framework-core: Enable checkpointing for WorkflowAgent (#2774)

Changed

• agent-framework-core: [BREAKING] Observability updates (#2782)
• agent-framework-core: Use agent description in HandoffBuilder auto-generated tools (#2714)
• agent-framework-core: Remove warnings from workflow builder when not using factories (#2808)

Fixed

• agent-framework-core: Fix WorkflowAgent to include thread conversation history (#2774)
• agent-framework-core: Fix context duplication in handoff workflows when restoring from checkpoint (#2867)
• agent-framework-core: Fix middleware terminate flag to exit function calling loop immediately (#2868)
• agent-framework-core: Fix WorkflowAgent to emit yield_output as agent response (#2866)
• agent-framework-core: Filter framework kwargs from MCP tool invocations (#2870)

1.0.0b251211 - 2025-12-11

Added

• agent-framework-core: Extend HITL support for all orchestration patterns (#2620)
• agent-framework-core: Add factory pattern to concurrent orchestration builder (#2738)
• agent-framework-core: Add factory pattern to sequential orchestration builder (#2710)
• agent-framework-azure-ai: Capture file IDs from code interpreter in streaming responses (#2741)

Changed

• agent-framework-azurefunctions: Change DurableAIAgent log level from warning to debug when invoked without thread (#2736)

Fixed

• agent-framework-core: Added more complete parsing for mcp tool arguments (#2756)
• agent-framework-core: Fix GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outputs (#2750)
• samples: Standardize OpenAI API key environment variable naming (#2629)

1.0.0b251209 - 2025-12-09

Added

• agent-framework-core: Support an autonomous handoff flow (#2497)
• agent-framework-core: WorkflowBuilder registry (#2486)
• agent-framework-a2a: Add configurable timeout support to A2AAgent (#2432)
• samples: Added Azure OpenAI Responses File Search sample + Integration test update (#2645)
• samples: Update fan in fan out sample to show concurrency (#2705)

Changed

• agent-framework-azure-ai: [BREAKING] Renamed async_credential to credential (#2648)
• samples: Improve sample logging (#2692)
• samples: azureai image gen sample update (#2709)

Fixed

• agent-framework-core: Fix DurableState schema serializations (#2670)
• agent-framework-core: Fix context provider lifecycle agentic mode (#2650)
• agent-framework-devui: Fix WorkflowFailedEvent error extraction (#2706)
• agent-framework-devui: Fix DevUI fails when uploading Pdf file (#2675)
• agent-framework-devui: Fix message serialization issue (#2674)
• observability: Display system prompt in langfuse (#2653)

1.0.0b251204 - 2025-12-04

Added

• agent-framework-core: Add support for Pydantic BaseModel as function call result (#2606)
• agent-framework-core: Executor events now include I/O data (#2591)
• samples: Inline YAML declarative sample (#2582)
• samples: Handoff-as-agent with HITL sample (#2534)

Changed

• agent-framework-core: [BREAKING] Support Magentic agent tool call approvals and plan stalling HITL behavior (#2569)
• agent-framework-core: [BREAKING] Standardize orchestration outputs as list of Message; allow agent as group chat manager (#2291)
• agent-framework-core: [BREAKING] Respond with AgentRunResponse including serialized structured output (#2285)
• observability: Use executor_id and edge_group_id as span names for clearer traces (#2538)
• agent-framework-devui: Add multimodal input support for workflows and refactor chat input (#2593)
• docs: Update Python orchestration documentation (#2087)

Fixed

• observability: Resolve mypy error in observability module (#2641)
• agent-framework-core: Fix AgentRunResponse.created_at returning local datetime labeled as UTC (#2590)
• agent-framework-core: Emit ExecutorFailedEvent before WorkflowFailedEvent when executor throws (#2537)
• agent-framework-core: Fix MagenticAgentExecutor producing repr string for tool call content (#2566)
• agent-framework-core: Fixed empty text content Pydantic validation failure (#2539)
• agent-framework-azure-ai: Added support for application endpoints in Azure AI client (#2460)
• agent-framework-azurefunctions: Add MCP tool support (#2385)
• agent-framework-core: Preserve MCP array items schema in Pydantic field generation (#2382)
• agent-framework-devui: Make tool call view optional and fix links (#2243)
• agent-framework-core: Always include output in function call result messages (#2414)
• agent-framework-redis: Fix TypeError (#2411)

1.0.0b251120 - 2025-11-20

Added

• agent-framework-core: Introducing support for declarative YAML spec (#2002)
• agent-framework-core: Use AI Foundry evaluators for self-reflection (#2250)
• agent-framework-core: Propagate as_tool() kwargs and add runtime context + middleware sample (#2311)
• agent-framework-anthropic: Anthropic Foundry integration (#2302)
• samples: M365 Agent SDK Hosting sample (#2292)
• samples: Foundry Sample for A2A + SharePoint Samples (#2313)

Changed

• agent-framework-azurefunctions: [BREAKING] Schema changes for Azure Functions package (#2151)
• agent-framework-core: Move evaluation folders under evaluations (#2355)
• agent-framework-core: Move red teaming files to their own folder (#2333)
• agent-framework-core: "fix all" task now single source of truth (#2303)
• agent-framework-core: Improve and clean up exception handling (#2337, #2319)
• agent-framework-core: Clean up imports (#2318)

Fixed

• agent-framework-azure-ai: Fix for Azure AI client (#2358)
• agent-framework-core: Fix tool execution bleed-over in aiohttp/Bot Framework scenarios (#2314)
• agent-framework-core: @ai_function now correctly handles self parameter (#2266)
• agent-framework-core: Resolve string annotations in FunctionExecutor (#2308)
• agent-framework-core: Langfuse observability captures Agent system instructions (#2316)
• agent-framework-core: Incomplete URL substring sanitization fix (#2274)
• observability: Handle datetime serialization in tool results (#2248)

1.0.0b251117 - 2025-11-17

Fixed

• agent-framework-ag-ui: Fix ag-ui state handling issues (#2289)

1.0.0b251114 - 2025-11-14

Added

• samples: Bing Custom Search sample using HostedWebSearchTool (#2226)
• samples: Fabric and Browser Automation samples (#2207)
• samples: Hosted agent samples (#2205)
• samples: Azure OpenAI Responses API Hosted MCP sample (#2108)
• samples: Bing Grounding and Custom Search samples (#2200)

Changed

• agent-framework-azure-ai: Enhance Azure AI Search citations with complete URL information (#2066)
• agent-framework-azurefunctions: Update samples to latest stable Azure Functions Worker packages (#2189)
• agent-framework-azure-ai: Agent name now required for AzureAIClient (#2198)
• build: Use uv build for packaging (#2161)
• tooling: Pre-commit improvements (#2222)
• dependencies: Updated package versions (#2208)

Fixed

• agent-framework-core: Prevent duplicate MCP tools and prompts (#1876) (#1890)
• agent-framework-devui: Fix HIL regression (#2167)
• agent-framework-chatkit: ChatKit sample fixes (#2174)

1.0.0b251112.post1 - 2025-11-12

Added

• agent-framework-azurefunctions: Merge Azure Functions feature branch (#1916)

Fixed

• agent-framework-ag-ui: fix tool call id mismatch in ag-ui (#2166)

1.0.0b251112 - 2025-11-12

Added

• agent-framework-azure-ai: Azure AI client based on new azure-ai-projects package (#1910)
• agent-framework-anthropic: Add convenience method on data content (#2083)

Changed

• agent-framework-core: Update OpenAI samples to use agents (#2012)

Fixed

• agent-framework-anthropic: Fixed image handling in Anthropic client (#2083)

1.0.0b251111 - 2025-11-11

Added

• agent-framework-core: Add OpenAI Responses Image Generation Stream Support with partial images and unit tests (#1853)
• agent-framework-ag-ui: Add concrete AGUIChatClient implementation (#2072)

Fixed

• agent-framework-a2a: Use the last entry in the task history to avoid empty responses (#2101)
• agent-framework-core: Fix MCP Tool Parameter Descriptions not propagated to LLMs (#1978)
• agent-framework-core: Handle agent user input request in AgentExecutor (#2022)
• agent-framework-core: Fix Model ID attribute not showing up in invoke_agent span (#2061)
• agent-framework-core: Fix underlying tool choice bug and enable return to previous Handoff subagent (#2037)

1.0.0b251108 - 2025-11-08

Added

• agent-framework-devui: Add OpenAI Responses API proxy support + HIL (Human-in-the-Loop) for Workflows (#1737)
• agent-framework-purview: Add Caching and background processing in Python Purview Middleware (#1844)

Changed

• agent-framework-devui: Use metadata.entity_id instead of model field (#1984)
• agent-framework-devui: Serialize workflow input as string to maintain conformance with OpenAI Responses format (#2021)

1.0.0b251106.post1 - 2025-11-06

Fixed

• agent-framework-ag-ui: Fix ag-ui examples packaging for PyPI publish (#1953)

1.0.0b251106 - 2025-11-06

Changed

• agent-framework-ag-ui: export sample ag-ui agents (#1927)

1.0.0b251105 - 2025-11-05

Added

• agent-framework-ag-ui: Initial release of AG-UI protocol integration for Agent Framework (#1826)
• agent-framework-chatkit: ChatKit integration with a sample application (#1273)
• Added parameter to disable agent cleanup in AzureAIAgentClient (#1882)
• Add support for Python 3.14 (#1904)

Changed

• [BREAKING] Replaced AIProjectClient with AgentsClient in Foundry (#1936)
• Updates to Tools (#1835)

Fixed

• Fix missing packaging dependency (#1929)

1.0.0b251104 - 2025-11-04

Added

• Introducing the Anthropic Client (#1819)

Changed

• [BREAKING] Consolidate workflow run APIs (#1723)
• [BREAKING] Remove request_type param from ctx.request_info() (#1824)
• [BREAKING] Cleanup of dependencies (#1803)
• [BREAKING] Replace RequestInfoExecutor with request_info API and @response_handler (#1466)
• Azure AI Search Support Update + Refactored Samples & Unit Tests (#1683)
• Lab: Updates to GAIA module (#1763)

Fixed

• Azure AI top_p and temperature parameters fix (#1839)
• Ensure agent thread is part of checkpoint (#1756)
• Fix middleware and cleanup confusing function (#1865)
• Fix type compatibility check (#1753)
• Fix mcp tool cloning for handoff pattern (#1883)

1.0.0b251028 - 2025-10-28

Added

• Added thread to AgentRunContext (#1732)
• AutoGen migration samples (#1738)
• Add Handoff orchestration pattern support (#1469)
• Added Samples for HostedCodeInterpreterTool with files (#1583)

Changed

• [BREAKING] Introduce group chat and refactor orchestrations. Fix as_agent(). Standardize orchestration start msg types. (#1538)
• [BREAKING] Update Agent Framework Lab Lightning to use Agent-lightning v0.2.0 API (#1644)
• [BREAKING] Refactor Checkpointing for runner and runner context (#1645)
• Update lab packages and installation instructions (#1687)
• Remove deprecated add_agent() calls from workflow samples (#1508)

Fixed

• Reject @executor on staticmethod/classmethod with clear error message (#1719)
• DevUI Fix Serialization, Timestamp and Other Issues (#1584)
• MCP Error Handling Fix + Added Unit Tests (#1621)
• InMemoryCheckpointManager is not JSON serializable (#1639)
• Fix gen_ai.operation.name to be invoke_agent (#1729)

1.0.0b251016 - 2025-10-16

Added

• Add Purview Middleware (#1142)
• Added URL Citation Support to Azure AI Agent (#1397)
• Added MCP headers for AzureAI (#1506)
• Add Function Approval UI to DevUI (#1401)
• Added function approval example with streaming (#1365)
• Added A2A AuthInterceptor Support (#1317)
• Added example with MCP and authentication (#1389)
• Added sample with Foundry Redteams (#1306)
• Added AzureAI Agent AI Search Sample (#1281)
• Added AzureAI Bing Connection Name Support (#1364)

Changed

• Enhanced documentation for dependency injection and serialization features (#1324)
• Update README to list all available examples (#1394)
• Reorganize workflows modules (#1282)
• Improved thread serialization and deserialization with better tests (#1316)
• Included existing agent definition in requests to Azure AI (#1285)
• DevUI - Internal Refactor, Conversations API support, and performance improvements (#1235)
• Refactor RequestInfoExecutor (#1403)

Fixed

• Fix AI Search Tool Sample and improve AI Search Exceptions (#1206)
• Fix Failure with Function Approval Messages in Chat Clients (#1322)
• Fix deadlock in Magentic workflow (#1325)
• Fix tool call content not showing up in workflow events (#1290)
• Fixed instructions duplication in model clients (#1332)
• Agent Name Sanitization (#1523)

1.0.0b251007 - 2025-10-07

Added

• Added method to expose agent as MCP server (#1248)
• Add PDF file support to OpenAI content parser with filename mapping (#1121)
• Sample on integration of Azure OpenAI Responses Client with a local MCP server (#1215)
• Added approval_mode and allowed_tools to local MCP (#1203)
• Introducing AI Function approval (#1131)
• Add name and description to workflows (#1183)
• Add Ollama example using OpenAIChatClient (#1100)
• Add DevUI improvements with color scheme, linking, agent details, and token usage data (#1091)
• Add semantic-kernel to agent-framework migration code samples (#1045)

Changed

• [BREAKING] Parameter naming and other fixes (#1255)
• [BREAKING] Introduce add_agent functionality and added output_response to AgentExecutor; agent streaming behavior to follow workflow invocation (#1184)
• OpenAI Clients accepting api_key callback (#1139)
• Updated docstrings (#1225)
• Standardize docstrings: Use Keyword Args for Settings classes and add environment variable examples (#1202)
• Update References to Agent2Agent protocol to use correct terminology (#1162)
• Update getting started samples to reflect AF and update unit test (#1093)
• Update Lab Installation instructions to install from source (#1051)
• Update python DEV_SETUP to add brew-based uv installation (#1173)
• Update docstrings of all files and add example code in public interfaces (#1107)
• Clarifications on installing packages in README (#1036)
• DevUI Fixes (#1035)
• Packaging fixes: removed lab from dependencies, setup build/publish tasks, set homepage url (#1056)
• Agents + Chat Client Samples Docstring Updates (#1028)
• Python: Foundry Agent Completeness (#954)

Fixed

• Ollama + azureai openapi samples fix (#1244)
• Fix multimodal input sample: Document required environment variables and configuration options (#1088)
• Fix Azure AI Getting Started samples: Improve documentation and code readability (#1089)
• Fix a2a import (#1058)
• Fix DevUI serialization and agent structured outputs (#1055)
• Default DevUI workflows to string input when start node is auto-wrapped agent (#1143)
• Add missing pre flags on pip packages (#1130)

1.0.0b251001 - 2025-10-01

Added

• First release of Agent Framework for Python
• agent-framework-core: Main abstractions, types and implementations for OpenAI and Azure OpenAI
• agent-framework-azure-ai: Integration with Azure AI Foundry Agents
• agent-framework-copilotstudio: Integration with Microsoft Copilot Studio agents
• agent-framework-a2a: Create A2A agents
• agent-framework-devui: Browser-based UI to chat with agents and workflows, with tracing visualization
• agent-framework-mem0 and agent-framework-redis: Integrations for Mem0 Context Provider and Redis Context Provider/Chat Memory Store
• agent-framework: Meta-package for installing all packages

For more information, see the announcement blog post.