The Azure SDK team is pleased to announce our June 2026 client library releases.

141 packages released this month.

Stable Packages (21)

  • AI Evaluation

  • AI Projects

  • App Configuration Provider

  • Azure AI Transcription

  • Cosmos DB

  • Key Vault - Administration

  • Machine Learning

  • Microsoft Planetary Computer Pro

  • Resource Management - Computelimit

  • Resource Management - Container Service

  • Resource Management - Health Bot

  • Resource Management - Image Builder

  • Resource Management - Standby Pool

  • Resource Management - Storage

  • Resource Management - Storage Mover

  • Storage - Blobs

  • Storage - Files Data Lake

  • Storage - Files Share

  • Storage - Queues

  • Text Translation

  • Voice Live

Patch Updates (33)

  • AI Evaluation

  • Azure Monitor OpenTelemetry

  • Cosmos DB

  • Key Vault - Keys

  • Resource Management - Advisor

  • Resource Management - Alerts Management

  • Resource Management - Arc Data

  • Resource Management - Automation

  • Resource Management - Azure Stack

  • Resource Management - BareMetal Infrastructure

  • Resource Management - Change Analysis

  • Resource Management - Commerce

  • Resource Management - Custom Providers

  • Resource Management - Data Share

  • Resource Management - DevTest Labs

  • Resource Management - HANA on Azure

  • Resource Management - HDInsight

  • Resource Management - IoT Central

  • Resource Management - Machine Learning Services

  • Resource Management - Managed Services

  • Resource Management - Management Partner

  • Resource Management - Marketplace Ordering

  • Resource Management - Operations Management

  • Resource Management - Peering

  • Resource Management - Policy Insights

  • Resource Management - Portal

  • Resource Management - Power BI Dedicated

  • Resource Management - Purview

  • Resource Management - Recovery Services

  • Resource Management - Relay

  • Resource Management - Serial Console

  • Resource Management - Storage Sync

  • Resource Management - Trusted Signing

Beta Packages (69)

  • AI Agent Server - Core

  • Azure AI Search

  • Azure Content Understanding in Foundry Tools

  • Key Vault - Administration

  • Key Vault - Certificates

  • Key Vault - Keys

  • OpenTelemetry Exporter

  • Resource Management - AKS Developer Hub

  • Resource Management - Alerts Management

  • Resource Management - Application Insights

  • Resource Management - Arc Data

  • Resource Management - Billing

  • Resource Management - Chaos

  • Resource Management - Cloudhealth

  • Resource Management - Cognitive Services

  • Resource Management - Consumption

  • Resource Management - Container Apps

  • Resource Management - Container Instances

  • Resource Management - Container Service

  • Resource Management - Container Service Fleet

  • Resource Management - Content Delivery Network

  • Resource Management - Cost Management

  • Resource Management - Data Box Edge

  • Resource Management - Data Factory

  • Resource Management - Data Migration

  • Resource Management - Databricks

  • Resource Management - Deployment Manager

  • Resource Management - Discovery

  • Resource Management - Education

  • Resource Management - Event Grid

  • Resource Management - Extended Location

  • Resource Management - Fileshares

  • Resource Management - HANA on Azure

  • Resource Management - HDInsight

  • Resource Management - Healthcare APIs

  • Resource Management - Hybrid Compute

  • Resource Management - Hybrid Kubernetes

  • Resource Management - IoT Hub

  • Resource Management - Kusto

  • Resource Management - Log Analytics

  • Resource Management - Maintenance

  • Resource Management - Managed Service Identity

  • Resource Management - Mongo Cluster

  • Resource Management - Monitor

  • Resource Management - Monitorworkspaces

  • Resource Management - Network

  • Resource Management - Policy Insights

  • Resource Management - PostgreSQL Flexible Servers

  • Resource Management - Red Hat OpenShift

  • Resource Management - Redis

  • Resource Management - Redis Enterprise

  • Resource Management - Reservations

  • Resource Management - Resource Graph

  • Resource Management - Resource Health

  • Resource Management - Resource-Databoundaries

  • Resource Management - Resource-Deployments

  • Resource Management - Resource-Policy

  • Resource Management - Resource-Subscriptions

  • Resource Management - Resources

  • Resource Management - SQL

  • Resource Management - Security

  • Resource Management - Security Insights

  • Resource Management - Serial Console

  • Resource Management - Service Fabric

  • Resource Management - Storage Cache

  • Resource Management - Subscriptions

  • Resource Management - Traffic Manager

  • Voice Live

  • unknown

Release highlights

AI Agent Server - Core 2.0.0b4 Changelog

Features Added

  • Added _platform_headers module with cross-cutting protocol header name constants (x-request-id, x-platform-server, x-agent-session-id, x-platform-error-source, x-platform-error-detail, and others). Protocol packages now import shared header name strings from core instead of maintaining their own copies.
  • Added TraceContextMiddleware — a lightweight pure-ASGI middleware that propagates W3C trace context (traceparent, tracestate) and baggage from incoming HTTP requests. Any spans created by downstream frameworks (e.g. MAF / agent-framework) are automatically children of the caller’s trace without additional framework spans.
  • Added enable_sensitive_data parameter to configure_observability() to control whether prompts, tool arguments, and results are recorded in telemetry. Respects OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT environment variable.
  • Added A365 tracing export support — when FOUNDRY_HOSTING_ENVIRONMENT and FOUNDRY_AGENT365_TRACING_ENABLED are set, telemetry is exported via the A365 observability pipeline.
  • Added resolve_agent_id(), resolve_agent_blueprint_id(), and resolve_agent_tenant_id() config helpers for new Foundry environment variables (FOUNDRY_AGENT_INSTANCE_CLIENT_ID, FOUNDRY_AGENT_BLUEPRINT_CLIENT_ID, FOUNDRY_AGENT_TENANT_ID).
  • Added gen_ai.agent.blueprint.id and microsoft.tenant.id span attributes to the FoundryEnrichmentSpanProcessor.
  • AgentConfig.ws_ping_interval — new field resolved from the WS_KEEPALIVE_INTERVAL environment variable (auto-injected by AgentService into hosted-agent containers). 0 disables; negative/non-finite values raise ValueError at startup. AgentServerHost._build_hypercorn_config wires this into Hypercorn’s websocket_ping_interval so any protocol package serving WebSocket routes inherits keep-alive without per-package wiring.

Breaking Changes

  • Removed request_span() method from AgentServerHost. Trace context propagation is now handled automatically by TraceContextMiddleware.

AI Agent Server - Core 2.0.0b5 Changelog

Bugs Fixed

  • Fixed the blueprint telemetry attribute key name from gen_ai.agent.blueprint.id to microsoft.a365.agent.blueprint.id to align with A365 schema and cross-SDK behavior.

AI Agent Server - Core 2.0.0b6 Changelog

Bugs Fixed

  • Populated agent metadata when operation IDs are zeroed so agent metadata remains available for telemetry and downstream processing.
  • Suppressed noisy observability/exporter INFO logs by default in tracing setup while preserving DEBUG visibility when explicitly enabled.

AI Evaluation 1.16.8 Changelog

AI Evaluation 1.16.9 Changelog

Bugs Fixed

  • Fixed format_llm_response raising UnboundLocalError when inputs was not provided by ensuring sample_input is always initialized.

AI Evaluation 1.17.0 Changelog

Breaking Changes

  • Updated EVALUATOR_NAME_METRICS_MAPPINGS so document_retrieval and rouge_score report single primary metrics (document_retrieval, rouge), with previous sub-metrics now represented in each evaluator’s *_properties payload.

Bugs Fixed

  • Fixed format_llm_response raising UnboundLocalError when inputs was not provided by ensuring sample_input is always initialized.

AI Projects 2.2.0 Changelog

Breaking Changes

Breaking changes in beta methods:

  • Required keyword isolation_key removed from .beta.agents.create_session() and .beta.agents.delete_session() methods.
  • Argument body in methods .beta.evaluation_taxonomies.create() and .beta.evaluation_taxonomies.update() renamed to taxonomy.
  • Argument body in method .beta.skills.create_from_files() renamed to content.
  • Method .beta.agents.get_session_files renamed to .beta.agents.list_session_files.
  • Method .beta.skills.create signature changed — now takes name and keyword inline_content: SkillInlineContent; returns SkillVersion.
  • Method .beta.skills.create_from_package renamed to .beta.skills.create_from_files.
  • Method .beta.skills.create_from_files signature changed — now takes name and content: CreateSkillVersionFromFilesBody; returns SkillVersion.
  • Method .beta.skills.update signature changed — now only accepts keyword default_version; returns SkillDetails.

Breaking changes in beta classes:

  • Required property isolation_key_source removed from class EntraAuthorizationScheme.
  • Renamed class AgentEndpoint to AgentEndpointConfig.
  • Renamed class DeleteSkillResponse to DeleteSkillResult.
  • Renamed class SessionDirectoryListResponse to SessionDirectoryListResult.
  • Renamed class SessionFileWriteResponse to SessionFileWriteResult.
  • Renamed class SkillObject to SkillDetails. Property skill_id renamed to id. Properties has_blob and metadata were removed.
  • Renamed class Target to EvaluationTarget.
  • Renamed class TargetConfig to RedTeamTargetConfig.

Bugs Fixed

  • Fixed telemetry instrumentor to correctly call is_recording() as a method on spans, ensuring non-recording spans are properly skipped (e.g., when sampling is configured) (GitHub issue 46544).

Features Added

  • Support integration of external Agents (in preview). See new ExternalAgentDefinition class.
  • New Agent tool in preview FabricIQPreviewTool.
  • New Agent tool in preview ToolboxSearchPreviewTool.
  • New methods on .beta.agents for
  • Code-based hosted agents: create_version_from_code, download_code.
  • Optimization jobs: create_optimization_job, get_optimization_job, list_optimization_jobs, cancel_optimization_job, list_optimization_candidates.
  • Optimization candidate management: list_optimization_candidates, get_optimization_candidate, get_optimization_candidate_config, get_optimization_candidate_results, get_candidate_file, promote_candidate.
  • stop_session to stop a running agent session.
  • New .beta.datasets sub-client with data generation job operations: create_generation_job, get_generation_job, list_generation_jobs, cancel_generation_job, delete_generation_job.
  • New .beta.models sub-client to handle AI model weights: create, list_versions, list, get, delete, update, pending_create_version, pending_upload, get_credentials.
  • New .beta.routines sub-client with routine operations: create_or_update, get, enable, disable, list, delete, list_runs, dispatch.
  • New methods on .beta.evaluators for evaluator generation jobs: create_generation_job, get_generation_job, list_generation_jobs, cancel_generation_job, delete_generation_job.
  • New methods on .beta.memory_stores to handle individual memory items: create_memory, update_memory, list_memories, get_memory, delete_memory.
  • New methods on .beta.skills for versioned skill management: create, list_versions, get_version, download_version, delete_version.
  • New optional string properties description and name added to Agent tools classes which did not have them before.
  • New optional tool_configs added to Agent tool classes.
  • New read-only property content_hash on CodeConfiguration, returning the SHA-256 hex digest of the uploaded code zip.
  • New optional force parameter on agents.delete and agents.delete_version methods.
  • New optional blueprint_reference parameters on agents.create_version method.

App Configuration Provider 2.5.0 Changelog

Features Added

  • Added refresh_enabled parameter to the load method. Defaults to True if refresh_on is set. When set to True without refresh_on keys, all selected key-values are monitored for changes. When set to False, calling refresh will be a no-op.
  • Added the ability to monitor all selected key-values for refresh with the refresh_enabled kwarg. When this kwarg is set to True, and refresh_on is not specified, changes to any selected key-values will trigger configuration reload.

Azure AI Search 12.1.0b1 Changelog

Breaking Changes

These changes do not impact the API of stable versions such as 12.0.0. Only code written against a beta version such as 11.7.0b2 may be affected.

  • Below methods do not exist on models in this release. Use as_dict() to serialize and the model constructor to deserialize (for example, index.as_dict() instead of index.serialize(), and SearchIndex(data) instead of SearchIndex.deserialize(data)).
  • deserialize()

  • serialize()

  • Below models are renamed
  • azure.search.documents.indexes.models.ChatCompletionResponseFormatJsonSchemaProperties -> azure.search.documents.indexes.models.ChatCompletionSchemaProperties
  • azure.search.documents.indexes.models.CommonModelParameters -> azure.search.documents.indexes.models.ChatCompletionCommonModelParameters
  • azure.search.documents.indexes.models.EntityRecognitionSkill -> azure.search.documents.indexes.models.EntityRecognitionSkillV3 (V3 does not include include_typeless_entities or skill_version)
  • azure.search.documents.indexes.models.SentimentSkill -> azure.search.documents.indexes.models.SentimentSkillV3 (V3 does not include skill_version)

  • azure.search.documents.knowledgebases.models.SharePointSensitivityLabelInfo -> azure.search.documents.knowledgebases.models.PurviewSensitivityLabelInfo

  • Below properties are renamed
  • azure.search.documents.indexes.models.ChatCompletionResponseFormat.chat_completion_schema_properties -> azure.search.documents.indexes.models.ChatCompletionResponseFormat.json_schema_properties
  • azure.search.documents.indexes.models.CommonModelParameters.model -> azure.search.documents.indexes.models.ChatCompletionCommonModelParameters.model_name
  • azure.search.documents.indexes.models.KeywordTokenizer.max_token_length -> azure.search.documents.indexes.models.KeywordTokenizer.buffer_size
  • azure.search.documents.indexes.models.SearchIndexerDataSourceConnection.connection_string -> azure.search.documents.indexes.models.SearchIndexerDataSourceConnection.credentials
  • azure.search.documents.indexes.models.SplitSkill.parameters -> azure.search.documents.indexes.models.SplitSkill.azure_open_ai_tokenizer_parameters
  • azure.search.documents.knowledgebases.models.SharePointSensitivityLabelInfo.tooltip -> azure.search.documents.knowledgebases.models.PurviewSensitivityLabelInfo.tool_tip
  • azure.search.documents.models.VectorQuery.k -> azure.search.documents.models.VectorQuery.k_nearest_neighbors
  • azure.search.documents.models.VectorizableImageBinaryQuery.k -> azure.search.documents.models.VectorizableImageBinaryQuery.k_nearest_neighbors
  • azure.search.documents.models.VectorizableImageUrlQuery.k -> azure.search.documents.models.VectorizableImageUrlQuery.k_nearest_neighbors
  • azure.search.documents.models.VectorizableTextQuery.k -> azure.search.documents.models.VectorizableTextQuery.k_nearest_neighbors

  • azure.search.documents.models.VectorizedQuery.k -> azure.search.documents.models.VectorizedQuery.k_nearest_neighbors

  • Below enum members are renamed
  • azure.search.documents.indexes.models.AIFoundryModelCatalogName.FACEBOOK_DINO_V2_IMAGE_EMBEDDINGS_VI_T_BASE -> azure.search.documents.indexes.models.AIFoundryModelCatalogName.FACEBOOK_DINO_V2_IMAGE_EMBEDDINGS_VIT_BASE
  • azure.search.documents.indexes.models.AIFoundryModelCatalogName.FACEBOOK_DINO_V2_IMAGE_EMBEDDINGS_VI_T_GIANT -> azure.search.documents.indexes.models.AIFoundryModelCatalogName.FACEBOOK_DINO_V2_IMAGE_EMBEDDINGS_VIT_GIANT
  • azure.search.documents.indexes.models.AIFoundryModelCatalogName.OPEN_AI_CLIP_IMAGE_TEXT_EMBEDDINGS_VI_T_LARGE_PATCH14_336 -> azure.search.documents.indexes.models.AIFoundryModelCatalogName.OPEN_AI_CLIP_IMAGE_TEXT_EMBEDDINGS_VIT_LARGE_PATCH14_336
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT5_MINI -> azure.search.documents.indexes.models.AzureOpenAIModelName.GPT_5_MINI
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT5_NANO -> azure.search.documents.indexes.models.AzureOpenAIModelName.GPT_5_NANO
  • azure.search.documents.indexes.models.KnowledgeSourceKind.INDEXED_ONE_LAKE -> azure.search.documents.indexes.models.KnowledgeSourceKind.INDEXED_ONELAKE
  • azure.search.documents.indexes.models.RankingOrder.RE_RANKER_SCORE -> azure.search.documents.indexes.models.RankingOrder.RERANKER_SCORE
  • azure.search.documents.indexes.models.SearchIndexerDataSourceType.MY_SQL -> azure.search.documents.indexes.models.SearchIndexerDataSourceType.MYSQL
  • azure.search.documents.indexes.models.SearchIndexerDataSourceType.ONE_LAKE -> azure.search.documents.indexes.models.SearchIndexerDataSourceType.ONELAKE

  • azure.search.documents.indexes.models.SearchIndexerDataSourceType.SHARE_POINT -> azure.search.documents.indexes.models.SearchIndexerDataSourceType.SHAREPOINT

  • Below models do not exist in this release
  • azure.search.documents.indexes.models.AIServices (moved to azure.search.documents.knowledgebases.models.AIServices)
  • azure.search.documents.indexes.models.CompletedSynchronizationState (moved to azure.search.documents.knowledgebases.models.CompletedSynchronizationState)
  • azure.search.documents.indexes.models.EntityRecognitionSkillVersion
  • azure.search.documents.indexes.models.KnowledgeRetrievalLowReasoningEffort
  • azure.search.documents.indexes.models.KnowledgeRetrievalMediumReasoningEffort
  • azure.search.documents.indexes.models.KnowledgeRetrievalMinimalReasoningEffort
  • azure.search.documents.indexes.models.KnowledgeRetrievalOutputMode
  • azure.search.documents.indexes.models.KnowledgeRetrievalReasoningEffort
  • azure.search.documents.indexes.models.KnowledgeRetrievalReasoningEffortKind
  • azure.search.documents.indexes.models.KnowledgeSourceAzureOpenAIVectorizer (moved to azure.search.documents.knowledgebases.models.KnowledgeSourceAzureOpenAIVectorizer)
  • azure.search.documents.indexes.models.KnowledgeSourceIngestionParameters (moved to azure.search.documents.knowledgebases.models.KnowledgeSourceIngestionParameters)
  • azure.search.documents.indexes.models.KnowledgeSourceStatistics (moved to azure.search.documents.knowledgebases.models.KnowledgeSourceStatistics)
  • azure.search.documents.indexes.models.KnowledgeSourceStatus (moved to azure.search.documents.knowledgebases.models.KnowledgeSourceStatus)
  • azure.search.documents.indexes.models.KnowledgeSourceVectorizer (moved to azure.search.documents.knowledgebases.models.KnowledgeSourceVectorizer)
  • azure.search.documents.indexes.models.PathHierarchyTokenizer (use PathHierarchyTokenizerV2 instead, which is still available)
  • azure.search.documents.indexes.models.SentimentSkillVersion
  • azure.search.documents.indexes.models.SuggestOptions
  • azure.search.documents.indexes.models.SynchronizationState (moved to azure.search.documents.knowledgebases.models.SynchronizationState)
  • azure.search.documents.knowledgebases.models.ErrorAdditionalInfo (moved to azure.search.documents.models.ErrorAdditionalInfo)
  • azure.search.documents.knowledgebases.models.ErrorDetail (moved to azure.search.documents.models.ErrorDetail)
  • azure.search.documents.knowledgebases.models.ErrorResponse (moved to azure.search.documents.models.ErrorResponse)
  • azure.search.documents.knowledgebases.models.KnowledgeBaseMessageImageContentImage
  • azure.search.documents.knowledgebases.models.KnowledgeBaseRetrievalActivityRecord
  • azure.search.documents.knowledgebases.models.KnowledgeSourceKind (still available as azure.search.documents.indexes.models.KnowledgeSourceKind)
  • azure.search.documents.knowledgebases.models.RequestOptions

  • azure.search.documents.knowledgebases.models.SearchIndexFieldReference (still available as azure.search.documents.indexes.models.SearchIndexFieldReference)

  • Below properties do not exist in this release
  • azure.search.documents.indexes.models.ChatCompletionSkill.auth_resource_id
  • azure.search.documents.indexes.models.ChatCompletionSkill.batch_size
  • azure.search.documents.indexes.models.ChatCompletionSkill.degree_of_parallelism
  • azure.search.documents.indexes.models.ChatCompletionSkill.http_headers
  • azure.search.documents.indexes.models.ChatCompletionSkill.http_method
  • azure.search.documents.indexes.models.ChatCompletionSkill.timeout
  • azure.search.documents.indexes.models.SearchField.sensitivity_label (replaced by sensitivity_label_id and sensitivity_label_name)
  • azure.search.documents.indexes.models.SearchResourceEncryptionKey.application_id (replaced by access_credentials)
  • azure.search.documents.indexes.models.SearchResourceEncryptionKey.application_secret (replaced by access_credentials)

Features Added

  • Below models, operations, and enum members are added for File knowledge source support
  • azure.search.documents.indexes.SearchIndexClient.delete_knowledge_source_file
  • azure.search.documents.indexes.SearchIndexClient.list_knowledge_source_files
  • azure.search.documents.indexes.SearchIndexClient.upload_knowledge_source_file
  • azure.search.documents.indexes.models.FileKnowledgeSource
  • azure.search.documents.indexes.models.FileKnowledgeSourceParameters
  • azure.search.documents.indexes.models.KnowledgeSourceFile
  • azure.search.documents.indexes.models.KnowledgeSourceKind.FILE
  • azure.search.documents.knowledgebases.models.FileKnowledgeSourceParams
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFileActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFileActivityRecord

  • azure.search.documents.knowledgebases.models.KnowledgeBaseFileReference

  • Below models and enum members are added for indexed SQL knowledge source support
  • azure.search.documents.indexes.models.ContentColumnMapping
  • azure.search.documents.indexes.models.EmbeddingColumnMapping
  • azure.search.documents.indexes.models.IndexedSqlKnowledgeSource
  • azure.search.documents.indexes.models.IndexedSqlKnowledgeSourceParameters
  • azure.search.documents.indexes.models.KnowledgeSourceKind.INDEXED_SQL
  • azure.search.documents.knowledgebases.models.IndexedSqlKnowledgeSourceParams
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedSqlActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedSqlActivityRecord

  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedSqlReference

  • Below models and enum members are added for MCP server knowledge source support
  • azure.search.documents.indexes.models.KnowledgeSourceKind.MCP_SERVER
  • azure.search.documents.indexes.models.McpServerAuthentication
  • azure.search.documents.indexes.models.McpServerAuthenticationKind
  • azure.search.documents.indexes.models.McpServerAutoOutputParsing
  • azure.search.documents.indexes.models.McpServerFoundryConnectionAuthentication
  • azure.search.documents.indexes.models.McpServerFoundryConnectionParameters
  • azure.search.documents.indexes.models.McpServerHeaders
  • azure.search.documents.indexes.models.McpServerJsonOutputParsing
  • azure.search.documents.indexes.models.McpServerKnowledgeSource
  • azure.search.documents.indexes.models.McpServerKnowledgeSourceParameters
  • azure.search.documents.indexes.models.McpServerNoneOutputParsing
  • azure.search.documents.indexes.models.McpServerOutputParsing
  • azure.search.documents.indexes.models.McpServerOutputParsingJsonParameters
  • azure.search.documents.indexes.models.McpServerOutputParsingKind
  • azure.search.documents.indexes.models.McpServerOutputParsingSplitParameters
  • azure.search.documents.indexes.models.McpServerSplitOutputParsing
  • azure.search.documents.indexes.models.McpServerStoredHeadersAuthentication
  • azure.search.documents.indexes.models.McpServerStoredHeadersParameters
  • azure.search.documents.indexes.models.McpServerTool
  • azure.search.documents.indexes.models.McpServerToolInclusionMode
  • azure.search.documents.knowledgebases.models.KnowledgeBaseMcpServerActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseMcpServerActivityRecord
  • azure.search.documents.knowledgebases.models.KnowledgeBaseMcpServerReference

  • azure.search.documents.knowledgebases.models.McpServerKnowledgeSourceParams

  • Below models and enum members are added for Fabric Data Agent knowledge source support
  • azure.search.documents.indexes.models.FabricDataAgentKnowledgeSource
  • azure.search.documents.indexes.models.FabricDataAgentKnowledgeSourceParameters
  • azure.search.documents.indexes.models.KnowledgeSourceKind.FABRIC_DATA_AGENT
  • azure.search.documents.knowledgebases.models.FabricDataAgentKnowledgeSourceParams
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricDataAgentActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricDataAgentActivityRecord

  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricDataAgentReference

  • Below models and enum members are added for Fabric Ontology knowledge source support
  • azure.search.documents.indexes.models.FabricOntologyKnowledgeSource
  • azure.search.documents.indexes.models.FabricOntologyKnowledgeSourceParameters
  • azure.search.documents.indexes.models.KnowledgeSourceKind.FABRIC_ONTOLOGY
  • azure.search.documents.knowledgebases.models.FabricOntologyKnowledgeSourceParams
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricOntologyActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricOntologyActivityRecord

  • azure.search.documents.knowledgebases.models.KnowledgeBaseFabricOntologyReference

  • Below models and enum members are added for WorkIQ knowledge source support
  • azure.search.documents.indexes.models.KnowledgeSourceKind.WORK_IQ
  • azure.search.documents.indexes.models.WorkIQKnowledgeSource
  • azure.search.documents.knowledgebases.models.KnowledgeBaseWorkIQActivityArguments
  • azure.search.documents.knowledgebases.models.KnowledgeBaseWorkIQActivityRecord
  • azure.search.documents.knowledgebases.models.KnowledgeBaseWorkIQReference
  • azure.search.documents.knowledgebases.models.WorkIQAttribution

  • azure.search.documents.knowledgebases.models.WorkIQKnowledgeSourceParams

  • Below models and properties are added for image serving in knowledge sources
  • azure.search.documents.indexes.models.KnowledgeSourceReference.enable_image_serving
  • azure.search.documents.knowledgebases.models.ImageServingStatistics
  • azure.search.documents.knowledgebases.models.KnowledgeBaseAzureBlobActivityRecord.image_serving
  • azure.search.documents.knowledgebases.models.KnowledgeBaseImageContent
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedOneLakeActivityRecord.image_serving
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedSharePointActivityRecord.image_serving
  • azure.search.documents.knowledgebases.models.KnowledgeBaseRemoteSharePointActivityRecord.image_serving
  • azure.search.documents.knowledgebases.models.KnowledgeBaseSearchIndexActivityRecord.image_serving
  • azure.search.documents.knowledgebases.models.KnowledgeBaseWebActivityRecord.image_serving

  • azure.search.documents.knowledgebases.models.KnowledgeSourceParams.enable_image_serving

  • Below properties and enum members are added for Purview sensitivity label support
  • azure.search.documents.indexes.models.KnowledgeSourceIngestionPermissionOption.SENSITIVITY_LABELS
  • azure.search.documents.knowledgebases.models.KnowledgeBaseAzureBlobReference.search_sensitivity_label_info
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedOneLakeReference.search_sensitivity_label_info
  • azure.search.documents.knowledgebases.models.KnowledgeBaseIndexedSharePointReference.search_sensitivity_label_info
  • azure.search.documents.knowledgebases.models.KnowledgeBaseRetrievalResponse.response_sensitivity_label_info

  • azure.search.documents.knowledgebases.models.KnowledgeBaseSearchIndexReference.search_sensitivity_label_info

  • Below models and properties are added for content freshness
  • azure.search.documents.indexes.models.KnowledgeSourceReference.enable_freshness
  • azure.search.documents.indexes.models.WebKnowledgeSourceParameters.count
  • azure.search.documents.indexes.models.WebKnowledgeSourceParameters.freshness
  • azure.search.documents.indexes.models.WebKnowledgeSourceParameters.language
  • azure.search.documents.indexes.models.WebKnowledgeSourceParameters.market

  • azure.search.documents.knowledgebases.models.FreshnessPolicy

  • Below properties are added for knowledge source resilience and output limits
  • azure.search.documents.knowledgebases.models.KnowledgeBaseRetrievalRequest.max_output_documents
  • azure.search.documents.knowledgebases.models.KnowledgeBaseRetrievalRequest.max_output_size_in_tokens
  • azure.search.documents.knowledgebases.models.KnowledgeSourceParams.fail_on_error

  • azure.search.documents.knowledgebases.models.KnowledgeSourceParams.max_output_documents

  • Below properties are added for knowledge base activity records
  • azure.search.documents.knowledgebases.models.KnowledgeBaseActivityRecord.warning
  • azure.search.documents.knowledgebases.models.KnowledgeBaseModelAnswerSynthesisActivityRecord.model_name

  • azure.search.documents.knowledgebases.models.KnowledgeBaseModelQueryPlanningActivityRecord.model_name

  • Below models are added for knowledge base activity dispatch
  • azure.search.documents.knowledgebases.models.KnowledgeBaseActivityRecordType

  • azure.search.documents.knowledgebases.models.KnowledgeBaseReferenceType

  • Below models and properties are added for knowledge base service capabilities
  • azure.search.documents.indexes.models.KnowledgeBase.cors_options
  • azure.search.documents.indexes.models.SearchIndexKnowledgeSourceParameters.base_filter
  • azure.search.documents.indexes.models.SearchServiceCounters.knowledge_base_counter
  • azure.search.documents.indexes.models.SearchServiceCounters.knowledge_source_counter

  • azure.search.documents.knowledgebases.models.AssetStore

  • Below models, enum members, and properties are added for content understanding skill chunking
  • azure.search.documents.indexes.models.ContentUnderstandingSkillChunkingMethod
  • azure.search.documents.indexes.models.ContentUnderstandingSkillChunkingProperties.method

  • azure.search.documents.indexes.models.ContentUnderstandingSkillChunkingUnit.TOKENS

  • Below properties are added for federated identity on indexer data sources

  • azure.search.documents.indexes.models.SearchIndexerDataUserAssignedIdentity.federated_identity_client_id

  • Below models are added for indexer execution diagnostics

  • azure.search.documents.indexes.models.IndexerExecutionStatusDetail

  • Below enum members are added for the GPT-5 Azure OpenAI model family
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT51
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT52
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT54
  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT_5_4_MINI

  • azure.search.documents.indexes.models.AzureOpenAIModelName.GPT_5_4_NANO

  • Below models and properties are added for SharePoint connector configuration
  • azure.search.documents.indexes.models.SearchIndex.share_point_connector_app_registration

  • azure.search.documents.indexes.models.SharePointConnectorAppRegistration

  • Below models are added for Microsoft Entra application credentials

  • azure.search.documents.indexes.models.AzureActiveDirectoryApplicationCredentials

  • Below models are added for multi-resource creation responses

  • azure.search.documents.indexes.models.CreatedResources

  • Below properties are added for search field permissioning and source attribution
  • azure.search.documents.indexes.models.SearchField.retrievable
  • azure.search.documents.indexes.models.SearchField.sensitivity_label_id
  • azure.search.documents.indexes.models.SearchField.sensitivity_label_name
  • azure.search.documents.indexes.models.SearchField.sharepoint_site_url

  • azure.search.documents.indexes.models.SearchField.source_document_id

  • Below properties are added for indexer data source connection sub-typing

  • azure.search.documents.indexes.models.SearchIndexerDataSourceConnection.sub_type

  • Below properties are added for resource encryption key access credentials
  • azure.search.documents.indexes.models.SearchResourceEncryptionKey.access_credentials

  • azure.search.documents.indexes.models.SearchResourceEncryptionKey.is_service_level_key

  • Below properties are added for custom analyzer configuration
  • azure.search.documents.indexes.models.CustomAnalyzer.char_filters
  • azure.search.documents.indexes.models.CustomAnalyzer.token_filters

  • azure.search.documents.indexes.models.CustomAnalyzer.tokenizer_name

  • Below models are added as new V2 tokenizers and token filters
  • azure.search.documents.indexes.models.EdgeNGramTokenFilterV2
  • azure.search.documents.indexes.models.KeywordTokenizerV2
  • azure.search.documents.indexes.models.LuceneStandardTokenizerV2
  • azure.search.documents.indexes.models.NGramTokenFilterV2

  • azure.search.documents.indexes.models.PathHierarchyTokenizerV2

  • Below models are added for indexer knowledge store parameters and web API skill headers
  • azure.search.documents.indexes.models.SearchIndexerKnowledgeStoreParameters

  • azure.search.documents.indexes.models.WebApiHttpHeaders

  • Below models are added for knowledge source vectorization and synchronization
  • azure.search.documents.knowledgebases.models.AIServices
  • azure.search.documents.knowledgebases.models.CompletedSynchronizationState
  • azure.search.documents.knowledgebases.models.KnowledgeSourceAzureOpenAIVectorizer
  • azure.search.documents.knowledgebases.models.KnowledgeSourceIngestionParameters
  • azure.search.documents.knowledgebases.models.KnowledgeSourceStatistics
  • azure.search.documents.knowledgebases.models.KnowledgeSourceStatus
  • azure.search.documents.knowledgebases.models.KnowledgeSourceSynchronizationError
  • azure.search.documents.knowledgebases.models.KnowledgeSourceVectorizer

  • azure.search.documents.knowledgebases.models.SynchronizationState

  • Below models are added for richer model activity records on knowledge bases

  • azure.search.documents.knowledgebases.models.KnowledgeBaseModelWebSummarizationActivityRecord

  • Below models are added for document plane debug, autocomplete, suggest, and search result types
  • azure.search.documents.models.AutocompleteItem
  • azure.search.documents.models.DocumentDebugInfo
  • azure.search.documents.models.ErrorAdditionalInfo
  • azure.search.documents.models.ErrorDetail
  • azure.search.documents.models.ErrorResponse
  • azure.search.documents.models.FacetResult
  • azure.search.documents.models.IndexActionType
  • azure.search.documents.models.IndexDocumentsBatch
  • azure.search.documents.models.LookupDocument
  • azure.search.documents.models.QueryResultDocumentRerankerInput
  • azure.search.documents.models.QueryResultDocumentSemanticField
  • azure.search.documents.models.QueryResultDocumentSubscores
  • azure.search.documents.models.QueryRewritesDebugInfo
  • azure.search.documents.models.QueryRewritesValuesDebugInfo
  • azure.search.documents.models.SearchResult
  • azure.search.documents.models.SemanticDebugInfo
  • azure.search.documents.models.SemanticFieldState
  • azure.search.documents.models.SingleVectorFieldResult
  • azure.search.documents.models.SuggestResult
  • azure.search.documents.models.TextResult
  • azure.search.documents.models.VectorQueryKind

  • azure.search.documents.models.VectorsDebugInfo

  • Below operations are added for arbitrary REST requests
  • azure.search.documents.indexes.SearchIndexerClient.send_request

  • azure.search.documents.knowledgebases.KnowledgeBaseRetrievalClient.send_request

  • Below models are added or changed for typed search field data

  • azure.search.documents.indexes.models.SearchFieldDataType (now an enum class; was a sub-module of string constants)

  • Below properties are added or changed for synonym maps
  • azure.search.documents.indexes.models.SynonymMap.format (now a writable property; was a fixed solr constant)

Azure AI Transcription 1.0.0 Changelog

Features Added

  • First stable release of the Azure AI Transcription client library for Python.

Azure Content Understanding in Foundry Tools 1.2.0b2 Changelog

Bugs Fixed

  • Filtered service-emitted LLMStats: telemetry entries from the rendered rai_warnings front matter.

Azure Monitor OpenTelemetry 1.8.8 Changelog

Features Added

  • Move AZURE_MONITOR_DISTRO_VERSION env var assignment before exporter imports (#46869)
  • Set AZURE_MONITOR_DISTRO_VERSION environment variable to pass distro version to the exporter (#46666)
  • Register GenAI main-agent attribution processors to automatically propagate microsoft.gen_ai.main_agent.* attributes in multi-agent GenAI systems per spec (#46703)

Breaking Changes

Cosmos DB 4.14.7 Changelog

Bugs Fixed

  • Fixed SELECT VALUE aggregation classification across partitions: booleans are no longer treated as numeric aggregates, non-aggregate numeric projections are no longer merged, and MIN/MAX detection is now correct. See PR 46692
  • Fixed a bug in query_items(feed_range=...) where pagination could return incorrect results after a partition split caused the supplied feed range to overlap multiple physical partitions. See PR 46692
  • Fixed bug where unavailable regional endpoints were dropped from the routing list instead of being kept as fallback options. See PR 45200

Cosmos DB 4.16.1 Changelog

Bugs Fixed

  • Fixed a bug in the sync and async /pkranges change-feed refresh where some containers could fail to build a complete routing map. See PR 47245.

Cosmos DB 4.16.0 Changelog

Breaking Changes

  • CosmosItemPaged.get_response_headers() and CosmosAsyncItemPaged.get_response_headers() now return a single CaseInsensitiveDict (the latest page) instead of List[CaseInsensitiveDict] (introduced in 4.16.0b1); get_last_response_headers() has been removed. This avoids unbounded memory growth on large queries. Migration: code that previously accessed headers[i]['x-ms-request-charge'] should switch to headers['x-ms-request-charge'] for the latest page, or pass response_hook= to the query method to receive per-page headers as they arrive. See PR 47172.

Bugs Fixed

  • Fixed bug where the Content-Length HTTP request header was computed from the character count of the request body instead of its UTF-8 byte count. See PR 47008
  • Added an opt-in fallback for invalid UTF-8 in response bodies. Default behavior is unchanged (strict decode). Setting AZURE_COSMOS_CHARSET_DECODER_ERROR_ACTION_ON_MALFORMED_INPUT to REPLACE or IGNORE enables a permissive decode so reads, queries, and change-feed iteration can make progress past corrupt payloads. See PR 47008
  • Fixed bug where CosmosClient construction with AAD credentials would crash at startup if the semantic reranking inference endpoint environment variable was not set, even when semantic reranking was not being used. The inference service is now lazily initialized on first use. See PR 46243
  • Fixed bug where region names in preferred_locations and excluded_locations (client-level and per-request) were not matched tolerantly for differences in case, whitespace, hyphens, and underscores. See PR 46937
  • Fixed a bug in query_items(feed_range=...) where pagination could return incorrect results after a partition split caused the supplied feed range to overlap multiple physical partitions. See PR 47105
  • Fixed bug where SELECT VALUE AVG(...) queries spanning multiple physical partitions returned mathematically incorrect merged values from client-side aggregation. These queries now raise ValueError. See PR 47105
  • Fixed bug where a ValueError("Ranges overlap") or an AssertionError("code bug: returned overlapping ranges ... is empty") from the partition key range cache could escape to the caller when the /pkranges response contained a transiently inconsistent snapshot (overlap or gap). See PR 47091

Features Added

  • Added preview support for the optional embeddingSource field on entries in vector_embedding_policy.vectorEmbeddings, which allows the service to generate vector embeddings from the specified item paths. Requires the embedding-generation service to be enabled on the account. See 46870
  • Added aio extras to the package, allowing users to install async dependencies with pip install azure-cosmos[aio]. See PR 47143

Key Vault - Administration 4.7.0 Changelog

Breaking Changes

  • Changed the continuation token format. Continuation tokens generated by previous versions of azure-keyvault-administration are not compatible with this version. Similarly, continuation tokens generated by previous versions of this library are not compatible with versions of azure-core>=1.38.0.

Features Added

  • Added support for service API version 2025-07-01 #46716

Key Vault - Administration 4.8.0b1 Changelog

Features Added

  • Added support for service API version 2026-01-01-preview #46895
  • Added KeyVaultEkmClient for managing Managed HSM External Key Manager (EKM) connections. This new client exposes get_ekm_connection, create_ekm_connection, update_ekm_connection, delete_ekm_connection, get_ekm_certificate, and check_ekm_connection.
  • Added KeyVaultEkmConnection, KeyVaultEkmProxyClientCertificateInfo, and KeyVaultEkmProxyInfo models supporting the EKM client.

Key Vault - Certificates 4.12.0b1 Changelog

Features Added

  • Added an experimental PlatformManaged property on CertificatePolicy for Azure Key Vault internal usage. Any calls using this property will fail and it is not recommended to be used at this point.
  • The default service version is now 2026-03-01-preview

Key Vault - Keys 4.11.1 Changelog

Features Added

  • Added support for service API version 2025-07-01 #46716

Key Vault - Keys 4.12.0b2 Changelog

Features Added

  • Added the ExternalKey model and the new KeyClient.create_external_key method for registering a Key Vault key whose material is held in an external HSM #47200.
  • Added the KeyProperties.external_key read-only property.

Key Vault - Keys 4.12.0b1 Changelog

Features Added

  • Added support for service API version 2026-01-01-preview #47116.
  • Added KeyProperties.key_size read-only property.

Machine Learning 1.33.0 Changelog

Bugs Fixed

  • Removing deployment templates experimental warning while initializing.
  • Resolving next-pylint 4.0.5 issues for azure-ai-ml sdk and updating.
  • Update Major Version Checker due to setup removal.
  • Path traversal protection in unzip to temp file.

Machine Learning 1.34.0 Changelog

Bugs Fixed

  • Fixed cross-tenant registry endpoint resolution for deployment template operations by using the registry discovery API instead of ARM calls.
  • Fixed deployment template update failing with immutable field errors by ensuring allowedInstanceType and allowedEnvironmentVariableOverrides are properly round-tripped during serialization.

Microsoft Planetary Computer Pro 1.0.0 Changelog

Features Added

  • Added models AssetStatisticsResponse, BandStatisticsMap, ClassMapLegendResponse, QueryableDefinitionsResponse, TilerAssetGeoJson, TilerInfoMapResponse.
  • get_collection_queryables, list_queryables now return QueryableDefinitionsResponse.
  • get_class_map_legend now returns ClassMapLegendResponse.

Breaking Changes

  • Renamed StacOperations.list_collections to StacOperations.get_collections.

OpenTelemetry Exporter 1.0.0b52 Changelog

Features Added

  • Add ownership checks for storage directories (#46725)
  • Add logger name to custom dimensions for Message, Exception and Event telemetry (#46096)
  • Add support for populating SDK version from distro and Microsoft OpenTelemetry distro environment variables (#46613)
  • Add GenAI main-agent attribution processors to propagate microsoft.gen_ai.main_agent.* attributes across spans and log records in multi-agent systems per spec (#46700)

Breaking Changes

Bugs Fixed

  • Fix success field on HTTP request telemetry resolving to an integer instead of a boolean when no status code is present (#46311)

OpenTelemetry Exporter 1.0.0b53 Changelog

Bugs Fixed

  • Validate QuickPulse redirect targets against trusted Azure domains (#46966)
  • Fix retry amplification storm in Azure Monitor OpenTelemetry exporter (#47002)

Features Added

  • Read for global feature sdkstats bitmap and add a 15 second delay timer (#47031)
  • Use APPLICATIONINSIGHTS_PYTHON_ATTACHTYPE environment variable in _is_attach_enabled to reliably detect successful auto-instrumentation attach, with fallback to legacy path-based detection (#46955)
  • Safeguard URL redirection issues (#47265)
  • Add client-side token-bucket rate limiter for telemetry export (#46999)

Resource Management - AKS Developer Hub 1.0.0b2 Changelog

Resource Management - Advisor 9.0.1 Changelog

Resource Management - Alerts Management 1.0.1 Changelog

Resource Management - Alerts Management 2.0.0b3 Changelog

Resource Management - Application Insights 5.0.0b2 Changelog

Resource Management - Arc Data 2.0.0b2 Changelog

Resource Management - Arc Data 1.0.1 Changelog

Resource Management - Automation 1.0.1 Changelog

Resource Management - Azure Stack 1.0.1 Changelog

Resource Management - BareMetal Infrastructure 1.0.1 Changelog

Resource Management - Billing 8.0.0b1 Changelog

Resource Management - Change Analysis 1.0.1 Changelog

Resource Management - Change Analysis 1.0.2 Changelog

Resource Management - Chaos 3.0.0b1 Changelog

Resource Management - Cloudhealth 1.0.0b2 Changelog

Resource Management - Cognitive Services 15.0.0b2 Changelog

Resource Management - Commerce 6.0.1 Changelog

Resource Management - Computelimit 1.1.0 Changelog

Resource Management - Consumption 11.0.0b2 Changelog

Resource Management - Container Apps 5.0.0b1 Changelog

Resource Management - Container Instances 10.2.0b2 Changelog

Resource Management - Container Service 41.2.0 Changelog

Resource Management - Container Service 41.3.0b1 Changelog

Resource Management - Container Service 41.3.0 Changelog

Resource Management - Container Service 41.4.0b1 Changelog

Resource Management - Container Service Fleet 4.0.0b4 Changelog

Resource Management - Content Delivery Network 14.0.0b1 Changelog

Resource Management - Cost Management 5.0.0b1 Changelog

Resource Management - Custom Providers 1.0.1 Changelog

Resource Management - Data Box Edge 3.0.0b2 Changelog

Resource Management - Data Factory 10.0.0b1 Changelog

Resource Management - Data Migration 11.0.0b1 Changelog

Resource Management - Data Share 1.0.1 Changelog

Resource Management - Databricks 3.0.0b1 Changelog

Resource Management - Deployment Manager 2.0.0b2 Changelog

Resource Management - DevTest Labs 9.0.1 Changelog

Resource Management - Discovery 1.0.0b1 Changelog

Resource Management - Education 1.0.0b3 Changelog

Resource Management - Event Grid 10.5.0b2 Changelog

Resource Management - Extended Location 3.0.0b1 Changelog

Resource Management - Fileshares 1.0.0b1 Changelog

Resource Management - HANA on Azure 1.0.1 Changelog

Resource Management - HANA on Azure 1.1.0b2 Changelog

Resource Management - HDInsight 9.0.1 Changelog

Resource Management - HDInsight 9.1.0b3 Changelog

Resource Management - Health Bot 1.0.0 Changelog

Resource Management - Healthcare APIs 3.0.0b1 Changelog

Resource Management - Hybrid Compute 9.1.0b3 Changelog

Resource Management - Hybrid Kubernetes 2.0.0b1 Changelog

Resource Management - Image Builder 2.0.0 Changelog

Resource Management - IoT Central 9.0.1 Changelog

Resource Management - IoT Hub 5.0.0b3 Changelog

Resource Management - Kusto 4.0.0b1 Changelog

Resource Management - Log Analytics 14.0.0b1 Changelog

Resource Management - Machine Learning Services 1.0.1 Changelog

Resource Management - Maintenance 2.2.0b3 Changelog

Resource Management - Managed Service Identity 8.0.0b2 Changelog

Resource Management - Managed Services 6.0.1 Changelog

Resource Management - Management Partner 1.0.1 Changelog

Resource Management - Marketplace Ordering 1.1.1 Changelog

Resource Management - Mongo Cluster 1.2.0b1 Changelog

Resource Management - Monitor 8.0.0b3 Changelog

Resource Management - Monitorworkspaces 1.0.0b1 Changelog

Resource Management - Network 31.0.0b1 Changelog

Resource Management - Operations Management 1.0.1 Changelog

Resource Management - Peering 1.0.1 Changelog

Resource Management - Policy Insights 1.0.1 Changelog

Resource Management - Policy Insights 1.1.0b6 Changelog

Resource Management - Portal 1.0.1 Changelog

Resource Management - PostgreSQL Flexible Servers 3.0.0b2 Changelog

Resource Management - Power BI Dedicated 1.0.1 Changelog

Resource Management - Purview 1.0.1 Changelog

Resource Management - Recovery Services 4.0.1 Changelog

Resource Management - Red Hat OpenShift 4.0.0b1 Changelog

Resource Management - Redis 15.0.0b1 Changelog

Resource Management - Redis Enterprise 4.0.0b2 Changelog

Resource Management - Relay 1.1.1 Changelog

Resource Management - Reservations 3.0.0b1 Changelog

Resource Management - Resource Graph 8.1.0b4 Changelog

Resource Management - Resource Health 1.0.0b7 Changelog

Resource Management - Resource-Databoundaries 1.0.0b2 Changelog

Resource Management - Resource-Deployments 1.0.0b2 Changelog

Resource Management - Resource-Policy 1.0.0b3 Changelog

Resource Management - Resource-Subscriptions 1.0.0b2 Changelog

Resource Management - Resources 26.0.0b1 Changelog

Resource Management - SQL 4.0.0b25 Changelog

Resource Management - Security 8.0.0b2 Changelog

Resource Management - Security Insights 2.0.0b3 Changelog

Resource Management - Serial Console 1.0.1 Changelog

Resource Management - Serial Console 1.1.0b2 Changelog

Resource Management - Service Fabric 2.2.0b2 Changelog

Resource Management - Standby Pool 2.1.0 Changelog

Resource Management - Storage 25.0.0 Changelog

Resource Management - Storage Cache 4.0.0b1 Changelog

Resource Management - Storage Mover 3.1.0 Changelog

Resource Management - Storage Sync 1.0.1 Changelog

Resource Management - Subscriptions 3.2.0b2 Changelog

Resource Management - Traffic Manager 2.0.0b1 Changelog

Resource Management - Trusted Signing 1.0.1 Changelog

Storage - Blobs 12.29.0 Changelog

Bugs Fixed

  • Fixed an issue where BlobClient’s download_blob did not retry upon ServiceReponseError and ServiceResponseTimeoutError exceptions
  • Fixed various issues with configuring logging via logging_enable and logging_body keywords on a per-request basis and with retries. Prior to this fix logging may have not behaved as expected, especially on retries.
  • Fix a potential memory leak caused by improper exception handling that could occur under rare circumstances.

Features Added

  • Stable release of features from 12.29.0b1

Storage - Blobs 12.30.0 Changelog

Features Added

  • Stable release of features from 12.30.0b1

Storage - Files Data Lake 12.24.0 Changelog

Bugs Fixed

  • Fixed various issues with configuring logging via logging_enable and logging_body keywords on a per-request basis and with retries. Prior to this fix logging may have not behaved as expected, especially on retries.
  • Fix a potential memory leak caused by improper exception handling that could occur under rare circumstances.

Features Added

  • Stable release of features from 12.24.0b1

Storage - Files Data Lake 12.25.0 Changelog

Features Added

  • Stable release of features from 12.25.0b1

Storage - Files Share 12.25.0 Changelog

Bugs Fixed

  • Fixed various issues with configuring logging via logging_enable and logging_body keywords on a per-request basis and with retries. Prior to this fix logging may have not behaved as expected, especially on retries.
  • Fix a potential memory leak caused by improper exception handling that could occur under rare circumstances.

Features Added

  • Stable release of features from 12.25.0b1

Storage - Files Share 12.26.0 Changelog

Features Added

  • Stable release of features from 12.26.0b1

Storage - Queues 12.16.0 Changelog

Bugs Fixed

  • Fixed various issues with configuring logging via logging_enable and logging_body keywords on a per-request basis and with retries. Prior to this fix logging may have not behaved as expected, especially on retries.
  • Fix a potential memory leak caused by improper exception handling that could occur under rare circumstances.

Features Added

  • Stable release of features from 12.16.0b1

Storage - Queues 12.17.0 Changelog

Features Added

  • Stable release of features from 12.17.0b1

Text Translation 2.0.0 Changelog

Breaking Changes

  • Removed grade parameter from translation options.

Features Added

  • GA release of Azure AI Translator Text Translation SDK version 2.0.0.
  • Updated to stable API version 2026-06-06.
  • Added TranslationTone and TranslationGender enums for type-safe tone and gender options.

Voice Live 1.2.0 Changelog

Features Added

  • Web Search & File Search: Added support for built-in web search and file search tools:
  • New item types: ResponseWebSearchCallItem, ResponseFileSearchCallItem
  • New server events for web/file search lifecycle (searching, in_progress, completed)
  • New models: ActionFind, ActionOpenPage, ActionSearch, ActionSearchSource, FileSearchResult
  • New enum values: ItemType.WEB_SEARCH_CALL, ItemType.FILE_SEARCH_CALL
  • New SessionIncludeOption enum for controlling what data is included in session responses
  • MCP (Model Context Protocol) Support: Added comprehensive support for Model Context Protocol integration:
  • MCPServer tool type for defining MCP server configurations with authorization, headers, and approval requirements
  • MCPTool model for representing MCP tool definitions with input schemas and annotations
  • MCPApprovalType enum for controlling approval workflows (never, always, or tool-specific)
  • New item types for MCP approval and call workflows
  • New server events for MCP tool listing, call lifecycle, and approval flows
  • Avatar Enhancements:
  • Added AzureAvatarVoiceSyncVoice for avatar voice sync configuration
  • Added ServerEventSessionAvatarSwitchToIdle and ServerEventSessionAvatarSwitchToSpeaking events
  • Added ServerEventResponseVideoDelta for avatar video frame streaming
  • Added ClientEventOutputAudioBufferClear and ServerEventOutputAudioBufferCleared for output buffer management
  • Added AvatarConfigTypes enum with support for video-avatar and photo-avatar types
  • Added AvatarOutputProtocol enum for avatar streaming protocols (webrtc, websocket)
  • Added Scene model for controlling avatar zoom, position, rotation, and movement amplitude
  • Added output_audit_audio field to AvatarConfig
  • OpenTelemetry Tracing Support: Added VoiceLiveInstrumentor for opt-in OpenTelemetry-based tracing of VoiceLive WebSocket connections, following Azure SDK and GenAI semantic conventions.
  • Enable via AZURE_EXPERIMENTAL_ENABLE_GENAI_TRACING=true environment variable
  • Content recording controlled by OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT
  • Comprehensive session-level telemetry: session ID, audio format, first-token latency, turn count, interruption count, audio bytes sent/received, message size
  • Response & function call ID tracking for end-to-end tracing
  • Agent v2 telemetry with agent identity and configuration tracking
  • MCP telemetry with tool call and approval flow tracking
  • Agent Session Configuration: Added flattened connect() keyword arguments for configuring Azure AI Foundry agents at connection time with agent_name, project_name, agent_version, conversation_id, and more
  • Transcription Improvements:
  • Added TranscriptionPhrase and TranscriptionWord models for detailed transcription data
  • Added ServerEventResponseAudioTranscriptAnnotationAdded event
  • Added gpt-4o-transcribe-diarize and mai-transcribe-1 transcription model support
  • Interim Response Configuration: Added StaticInterimResponseConfig and LlmInterimResponseConfig for generating interim responses during latency or tool calls
  • Image Content Support: Added RequestImageContentPart for image inputs in conversations
  • Reasoning Effort Control: Added reasoning_effort field with ReasoningEffort enum
  • Response Metadata: Added metadata field to Response and ResponseCreateParams
  • Server Warning Events: Added ServerEventWarning for handling non-fatal warnings
  • Personal Voice Models: Added DragonHDOmniLatestNeural and MAI-Voice-1 model options
  • Enhanced OpenAI Voices: Added marin and cedar voices to OpenAIVoiceName enum
  • Enhanced Azure Personal Voice: Added custom_lexicon_url, prefer_locales, locale, style, pitch, rate, and volume properties
  • Pre-generated Assistant Messages: Added pre_generated_assistant_message in ResponseCreateParams
  • Explicit Null Values: Enhanced RequestSession to properly serialize explicitly set None values

Breaking Changes

  • Removed Foundry Agent Tool classes (FoundryAgentTool, ResponseFoundryAgentCallItem, etc.) — use flattened Azure AI Foundry keyword arguments with connect() instead
  • Audio Format Values: Changed OutputAudioFormat enum values to use underscore format (pcm16_8000hz, pcm16_16000hz) instead of the previous hyphenated values. This is a breaking change for code that compares, persists, or serializes the raw enum values. Legacy hyphenated values continue to deserialize for backward compatibility.
  • Renamed AvatarConfig.type field to avatar_type to avoid conflict with Python’s built-in type

Voice Live 1.3.0b1 Changelog

Breaking Changes

  • Image Input Field Rename: Renamed RequestImageContentPart.url to image_url. Update image input construction to use image_url= instead of url=.
  • Default API Version Update: Changed the SDK default API version from 2026-04-10 to 2026-06-01-preview. Pass api_version="2026-04-10" explicitly to keep the previous default behavior.

Features Added

  • Azure Realtime Native Voice Support: Added AzureRealtimeNativeVoice and AzureRealtimeNativeVoiceName, and expanded voice fields to accept Azure realtime native voices.
  • WebRTC Call Negotiation Support: Added ClientEventRtcCallSdpCreate, ServerEventRtcCallSdpCreated, ServerEventRtcCallError, and RtcCallErrorDetails for SDP-based WebRTC call setup.
  • Input Text Streaming Support: Added ClientEventInputTextDelta and ClientEventInputTextDone for incrementally streaming text input into existing conversation items.
  • Hosted Agent Invocation Input: Added invoke_input to ResponseCreateParams and ServerEventResponseInvocationDelta for hosted agent invocation passthrough data.
  • Audio Playback Lifecycle Events: Added ServerEventOutputAudioBufferStarted and ServerEventOutputAudioBufferStopped to track model audio playback start and stop.
  • Echo Cancellation Configuration: Added EchoCancellationReferenceSource and new reference_source / channels options on AudioEchoCancellation to support both the default server loopback reference path and client-provided stereo echo reference input.
  • Smart End-of-Turn Detection: Added SmartEndOfTurnDetection as an audio-based end-of-turn detection option.
  • Parallel Tool Call Control: Added parallel_tool_calls to session models so callers can control whether tool calls may run in parallel.

unknown 1.0.0b6 Changelog

Bugs Fixed

  • Removed ContentDecodePolicy from the FoundryStorageProvider HTTP pipeline. The policy eagerly decoded every response body as JSON and crashed with UnicodeDecodeError when the storage backend (or an intermediary gateway/load-balancer) returned a non-UTF-8 body — for example a gzip-compressed payload, an HTML error page, or a transport-corrupted response. The crash propagated up before our error-classification code could see the response, masking the underlying status with a generic decode error. Our serializers and error-extraction helpers already call http_resp.text() lazily with defensive error handling, so the eager decode policy was never needed.

Features Added

  • Error source classification headers: All HTTP error responses now include x-platform-error-source with a value of user, platform, or upstream to indicate which component caused the error. Client validation errors (400/404) are classified as user, Foundry storage infrastructure errors (transport failures, 5xx) as platform, and developer handler exceptions as upstream. Platform errors additionally include x-platform-error-detail with truncated exception details (max 2048 characters) for diagnostics. Matches the container image specification §8 error source classification.

Breaking Changes

  • Removed the automatic invoke_agent server span that was created on each response creation request. Trace context propagation is now handled by the core TraceContextMiddleware, and user-created spans inside handlers are correctly parented without framework-generated spans.
  • Removed _safe_set_attrs, _wrap_streaming_response, and _classify_error_code internal helpers (no longer needed without framework-level span management).
  • Removed OTel error tagging attributes (azure.ai.agentserver.responses.error.code, azure.ai.agentserver.responses.error.message) that were set on the framework span.

unknown 1.0.0b7 Changelog

Features Added

  • Added MCP output item builder enhancements for hosted MCP relay scenarios: ResponseEventStream.add_output_item_mcp_call() now supports caller-supplied item IDs, and MCP call emit_done() supports optional output and error payloads for canonical mcp_call persistence and replay.

unknown 1.0.0b1 Changelog

Features Added

  • Added WorkspaceClient for managing Discovery workspace resources, with operation groups for:
  • investigations — create, list, get, and delete investigations, and start/stop/get/update the per-investigation Discovery Engine.
  • conversations — create, list, get, update, and delete conversations that interact with the Discovery Engine.
  • tasks — create, list (with $filter support), get, update, comment on, start, and delete tasks; record execution history.
  • tools — run tools on supercomputer node pools, monitor run status with log retrieval, cancel runs, and query compute usage.
  • Added BookshelfClient for managing knowledge bases, with operation groups for:
  • knowledge_bases — list available knowledge bases.
  • knowledge_base_versions — create or update, get, list, delete, and retrieve the latest version of a knowledge base; start, cancel, and monitor indexing.
  • Added shared model types under azure.ai.discovery.models covering investigations, conversations, tasks, tools, knowledge bases, and the Discovery Engine.

unknown 1.0.0b1 Changelog

Features Added

  • Initial beta release.
  • load_config(*, config_dir) — single-call config loader with 4-priority resolution and graceful fallback.
  • load_skills_from_dir(path) — load skills from a directory on demand (not loaded inline by load_config).
  • OptimizationConfig with instructions, model, temperature, skills, skills_dir, tool_definitions, source, and candidate_id.
  • OptimizationConfig.apply_tool_descriptions(tools) — patch __doc__, .description, and input_model parameter descriptions on @tool-decorated functions from optimized tool definitions.
  • OptimizationConfig.compose_instructions() — append skill catalog to instructions.
  • CandidateConfig — typed representation of the resolver API payload.
  • Skill — learned skill model (name, description, body).
  • 4-priority resolution order:
    1. Inline JSON via OPTIMIZATION_CONFIG env var.
    2. Resolver API via OPTIMIZATION_CANDIDATE_ID + OPTIMIZATION_RESOLVE_ENDPOINT (endpoint is the full job-scoped URL).
    3. Local directory layout (OPTIMIZATION_LOCAL_DIR or config_dir param, defaults to .agent_configs/).
    4. No config found → returns None.
  • Local directory layout: metadata.yaml + instructions.md + tools.json + skills/ per candidate, with baseline/ fallback.
  • Tool definitions use the OpenAI function-calling list format exclusively.
  • Skill loading from SKILL.md files with YAML frontmatter.
  • Resolver API persists fetched configs and skill files to local directory for offline use.
  • Path traversal (zip-slip) protection on skill file downloads from the API.

unknown 1.0.0b2 Changelog

Latest Releases

View all the latest versions of Python packages here.

Installation Instructions

To install the latest beta version of the packages, copy and paste the following commands into a terminal:

$> pip install azure-ai-agentserver-core==2.0.0b4
$> pip install azure-ai-agentserver-core==2.0.0b5
$> pip install azure-ai-agentserver-core==2.0.0b6
$> pip install azure-ai-agentserver-optimization==1.0.0b1
$> pip install azure-ai-agentserver-responses==1.0.0b6
$> pip install azure-ai-agentserver-responses==1.0.0b7
$> pip install azure-ai-contentunderstanding==1.2.0b2
$> pip install azure-ai-discovery==1.0.0b1
$> pip install azure-ai-evaluation==1.16.8
$> pip install azure-ai-evaluation==1.16.9
$> pip install azure-ai-evaluation==1.17.0
$> pip install azure-ai-ml==1.33.0
$> pip install azure-ai-ml==1.34.0
$> pip install azure-ai-projects==2.2.0
$> pip install azure-ai-transcription==1.0.0
$> pip install azure-ai-translation-text==2.0.0
$> pip install azure-ai-voicelive==1.2.0
$> pip install azure-ai-voicelive==1.3.0b1
$> pip install azure-appconfiguration-provider==2.5.0
$> pip install azure-cosmos==4.14.7
$> pip install azure-cosmos==4.16.1
$> pip install azure-cosmos==4.16.0
$> pip install azure-keyvault-administration==4.7.0
$> pip install azure-keyvault-administration==4.8.0b1
$> pip install azure-keyvault-certificates==4.12.0b1
$> pip install azure-keyvault-keys==4.11.1
$> pip install azure-keyvault-keys==4.12.0b2
$> pip install azure-keyvault-keys==4.12.0b1
$> pip install azure-mgmt-advisor==9.0.1
$> pip install azure-mgmt-alertsmanagement==1.0.1
$> pip install azure-mgmt-alertsmanagement==2.0.0b3
$> pip install azure-mgmt-appcontainers==5.0.0b1
$> pip install azure-mgmt-applicationinsights==5.0.0b2
$> pip install azure-mgmt-automation==1.0.1
$> pip install azure-mgmt-azurearcdata==2.0.0b2
$> pip install azure-mgmt-azurearcdata==1.0.1
$> pip install azure-mgmt-azurestack==1.0.1
$> pip install azure-mgmt-baremetalinfrastructure==1.0.1
$> pip install azure-mgmt-billing==8.0.0b1
$> pip install azure-mgmt-cdn==14.0.0b1
$> pip install azure-mgmt-changeanalysis==1.0.1
$> pip install azure-mgmt-changeanalysis==1.0.2
$> pip install azure-mgmt-chaos==3.0.0b1
$> pip install azure-mgmt-cloudhealth==1.0.0b2
$> pip install azure-mgmt-cognitiveservices==15.0.0b2
$> pip install azure-mgmt-commerce==6.0.1
$> pip install azure-mgmt-computelimit==1.1.0
$> pip install azure-mgmt-consumption==11.0.0b2
$> pip install azure-mgmt-containerinstance==10.2.0b2
$> pip install azure-mgmt-containerservice==41.2.0
$> pip install azure-mgmt-containerservice==41.3.0b1
$> pip install azure-mgmt-containerservice==41.3.0
$> pip install azure-mgmt-containerservice==41.4.0b1
$> pip install azure-mgmt-containerservicefleet==4.0.0b4
$> pip install azure-mgmt-costmanagement==5.0.0b1
$> pip install azure-mgmt-customproviders==1.0.1
$> pip install azure-mgmt-databoxedge==3.0.0b2
$> pip install azure-mgmt-databricks==3.0.0b1
$> pip install azure-mgmt-datafactory==10.0.0b1
$> pip install azure-mgmt-datamigration==11.0.0b1
$> pip install azure-mgmt-datashare==1.0.1
$> pip install azure-mgmt-deploymentmanager==2.0.0b2
$> pip install azure-mgmt-devhub==1.0.0b2
$> pip install azure-mgmt-devtestlabs==9.0.1
$> pip install azure-mgmt-discovery==1.0.0b1
$> pip install azure-mgmt-education==1.0.0b3
$> pip install azure-mgmt-eventgrid==10.5.0b2
$> pip install azure-mgmt-extendedlocation==3.0.0b1
$> pip install azure-mgmt-fileshares==1.0.0b1
$> pip install azure-mgmt-hanaonazure==1.0.1
$> pip install azure-mgmt-hanaonazure==1.1.0b2
$> pip install azure-mgmt-hdinsight==9.0.1
$> pip install azure-mgmt-hdinsight==9.1.0b3
$> pip install azure-mgmt-healthbot==1.0.0
$> pip install azure-mgmt-healthcareapis==3.0.0b1
$> pip install azure-mgmt-hybridcompute==9.1.0b3
$> pip install azure-mgmt-hybridkubernetes==2.0.0b1
$> pip install azure-mgmt-imagebuilder==2.0.0
$> pip install azure-mgmt-iotcentral==9.0.1
$> pip install azure-mgmt-iothub==5.0.0b3
$> pip install azure-mgmt-kusto==4.0.0b1
$> pip install azure-mgmt-loganalytics==14.0.0b1
$> pip install azure-mgmt-machinelearningservices==1.0.1
$> pip install azure-mgmt-maintenance==2.2.0b3
$> pip install azure-mgmt-managedservices==6.0.1
$> pip install azure-mgmt-managementpartner==1.0.1
$> pip install azure-mgmt-marketplaceordering==1.1.1
$> pip install azure-mgmt-mongocluster==1.2.0b1
$> pip install azure-mgmt-monitor==8.0.0b3
$> pip install azure-mgmt-monitorslis==1.0.0b2
$> pip install azure-mgmt-monitorworkspaces==1.0.0b1
$> pip install azure-mgmt-msi==8.0.0b2
$> pip install azure-mgmt-network==31.0.0b1
$> pip install azure-mgmt-operationsmanagement==1.0.1
$> pip install azure-mgmt-peering==1.0.1
$> pip install azure-mgmt-policyinsights==1.0.1
$> pip install azure-mgmt-policyinsights==1.1.0b6
$> pip install azure-mgmt-portal==1.0.1
$> pip install azure-mgmt-postgresqlflexibleservers==3.0.0b2
$> pip install azure-mgmt-powerbidedicated==1.0.1
$> pip install azure-mgmt-purview==1.0.1
$> pip install azure-mgmt-recoveryservices==4.0.1
$> pip install azure-mgmt-redhatopenshift==4.0.0b1
$> pip install azure-mgmt-redis==15.0.0b1
$> pip install azure-mgmt-redisenterprise==4.0.0b2
$> pip install azure-mgmt-relay==1.1.1
$> pip install azure-mgmt-reservations==3.0.0b1
$> pip install azure-mgmt-resource==26.0.0b1
$> pip install azure-mgmt-resource-databoundaries==1.0.0b2
$> pip install azure-mgmt-resource-deployments==1.0.0b2
$> pip install azure-mgmt-resource-policy==1.0.0b3
$> pip install azure-mgmt-resource-subscriptions==1.0.0b2
$> pip install azure-mgmt-resourcegraph==8.1.0b4
$> pip install azure-mgmt-resourcehealth==1.0.0b7
$> pip install azure-mgmt-security==8.0.0b2
$> pip install azure-mgmt-securityinsight==2.0.0b3
$> pip install azure-mgmt-serialconsole==1.0.1
$> pip install azure-mgmt-serialconsole==1.1.0b2
$> pip install azure-mgmt-servicefabric==2.2.0b2
$> pip install azure-mgmt-sql==4.0.0b25
$> pip install azure-mgmt-standbypool==2.1.0
$> pip install azure-mgmt-storage==25.0.0
$> pip install azure-mgmt-storagecache==4.0.0b1
$> pip install azure-mgmt-storagemover==3.1.0
$> pip install azure-mgmt-storagesync==1.0.1
$> pip install azure-mgmt-subscription==3.2.0b2
$> pip install azure-mgmt-trafficmanager==2.0.0b1
$> pip install azure-mgmt-trustedsigning==1.0.1
$> pip install azure-monitor-opentelemetry==1.8.8
$> pip install azure-monitor-opentelemetry-exporter==1.0.0b52
$> pip install azure-monitor-opentelemetry-exporter==1.0.0b53
$> pip install azure-planetarycomputer==1.0.0
$> pip install azure-search-documents==12.1.0b1
$> pip install azure-storage-blob==12.29.0
$> pip install azure-storage-blob==12.30.0
$> pip install azure-storage-file-datalake==12.24.0
$> pip install azure-storage-file-datalake==12.25.0
$> pip install azure-storage-file-share==12.25.0
$> pip install azure-storage-file-share==12.26.0
$> pip install azure-storage-queue==12.16.0
$> pip install azure-storage-queue==12.17.0

Feedback

If you have a bug or feature request for one of the libraries, please post an issue to GitHub.