Python: Azure AI client based on new azure-ai-projects package (#1910)

* Added changes (#1909) * Python: [Feature Branch] Renamed Azure AI agent and small fixes (#1919) * Renaming * Small fixes * Update python/packages/core/agent_framework/openai/_shared.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Small fix * Python: [Feature Branch] Added use_latest_version parameter to AzureAIClient (#1959) * Added use_latest_version parameter to AzureAIClient * Added unit tests * Update python/samples/getting_started/agents/azure_ai/azure_ai_use_latest_version.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/packages/azure-ai/agent_framework_azure_ai/_client.py Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> * Python: [Feature Branch] Structured Outputs and more examples for AzureAIClient (#1987) * Small updates * Added support for structured outputs * Added code interpreter example * More examples and fixes * Added more examples and README * Small fix * Addressed PR feedback * Removed optional ID from FunctionResultContent (#2011) * Added hosted MCP support (#2018) * Python: [Feature Branch] Fixed "store" parameter handling (#2069) * Fixed store parameter handling * Small fix * Python: [Feature Branch] Added more examples and fixes for Azure AI agent (#2077) * Updated azure-ai-projects package version * Added an example of hosted MCP with approval required * Updated code interpreter example * Added file search example * Update python/samples/getting_started/agents/azure_ai/azure_ai_with_file_search.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update python/samples/getting_started/agents/azure_ai/azure_ai_with_file_search.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Small fix --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Added handling for conversation_id (#2098) * Merge from main * Revert "Merge from main" This reverts commit b8206a85d7. * Python: [Feature Branch] Merge from main to Azure AI branch (#2111) * Do not build DevUI assets during .NET project build (#2010) * .NET: Add unit tests for declarative executor SetMultipleVariables (#2016) * Add unit tests for create conversation executor * Update indentation and comment typo. * Added unit tests for declarative executor SetMultipleVariablesExecutor * Updated comments and syntactic sugar * Python: DevUI: Use metadata.entity_id instead of model field (#1984) * DevUI: Use metadata.entity_id for agent/workflow name instead of model field * OpenAI Responses: add explicit request validation * Review feedback * .NET: DevUI - Do not automatically add/map OpenAI services/endpoints (#2014) * Don't add OpenAIResponses as part of Dev UI You should be able to add and remove Dev UI without impacting your other production endpoints. * Remove `AddDevUI()` and do not map OpenAI endpoints from `MapDevUI()` * Fix comment wording * Revise documentation --------- Co-authored-by: Daniel Roth <daroth@microsoft.com> * Python: DevUI: Add OpenAI Responses API proxy support + HIL for Workflows (#1737) * DevUI: Add OpenAI Responses API proxy support with enhanced UI features This commit adds support for proxying requests to OpenAI's Responses API, allowing DevUI to route conversations to OpenAI models when configured to enable testing. Backend changes: - Add OpenAI proxy executor with conversation routing logic - Enhance event mapper to support OpenAI Responses API format - Extend server endpoints to handle OpenAI proxy mode - Update models with OpenAI-specific response types - Remove emojis from logging and CLI output for cleaner text Frontend changes: - Add settings modal with OpenAI proxy configuration UI - Enhance agent and workflow views with improved state management - Add new UI components (separator, switch) for settings - Update debug panel with better event filtering - Improve message renderers for OpenAI content types - Update types and API client for OpenAI integration * update ui, settings modal and workflow input form, add register cleanup hooks. * add workflow HIL support, user mode, other fixes * feat(devui): add human-in-the-loop (HIL) support with dynamic response schemas Implement HIL workflow support allowing workflows to pause for user input with dynamically generated JSON schemas based on response handler type hints. Key Features: - Automatic response schema extraction from @response_handler decorators - Dynamic form generation in UI based on Pydantic/dataclass response types - Checkpoint-based conversation storage for HIL requests/responses - Resume workflow execution after user provides HIL response Backend Changes: - Add extract_response_type_from_executor() to introspect response handlers - Enrich RequestInfoEvent with response_schema via _enrich_request_info_event_with_response_schema() - Map RequestInfoEvent to response.input.requested OpenAI event format - Store HIL responses in conversation history and restore checkpoints Frontend Changes: - Add HILInputModal component with SchemaFormRenderer for dynamic forms - Support Pydantic BaseModel and dataclass response types - Render enum fields as dropdowns, strings as text/textarea, numbers, booleans, arrays, objects - Display original request context alongside response form Testing: - Add tests for checkpoint storage (test_checkpoints.py) - Add schema generation tests for all input types (test_schema_generation.py) - Validate end-to-end HIL flow with spam workflow sample This enables workflows to seamlessly pause execution and request structured user input with type-safe, validated forms generated automatically from response type annotations. * improve HIL support, improve workflow execution view * ui updates * ui updates * improve HIL for workflows, add auth and view modes * update workflow * security improvements , ui fixes * fix mypy error * update loading spinner in ui --------- Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: Remove launchSettings.json from .gitignore in dotnet/samples (#2006) * Remove launchSettings.json from .gitignore in dotnet/samples * Update dotnet/samples/GettingStarted/DevUI/DevUI_Step01_BasicUsage/Properties/launchSettings.json Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update dotnet/samples/AGUIClientServer/AGUIServer/Properties/launchSettings.json Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * DevUI: Serialize workflow input as string to maintain conformance with OpenAI Responses format (#2021) Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> * Add Microsoft Agent Framework logo to assets (#2007) * Updated package versions (#2027) * DevUI: Prevent line breaks within words in the agent view (#2024) Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> * .NET [AG-UI]: Adds support for shared state. (#1996) * Product changes * Tests * Dojo project * Cleanups * Python: Fix underlying tool choice bug and all for return to previous Handoff subagent (#2037) * Fix tool_choice override bug and add enable_return_to_previous support * Add unit test for handoff checkpointing * Handle tools when we have them * added missing chatAgent params (#2044) * .NET: fix ChatCompletions Tools serialization (#2043) * fix serialization in chat completions on tools * nit * .NET: assign AgentCard's URL to mapped-endpoint if not defined explicitly (#2047) * fix serialization in chat completions on tools * nit * write e2e test for agent card resolve + adjust behavior * nit * Version 1.0.0-preview.251110.1 (#2048) * .NET: Remove moved OpenAPI sample and point to SK one. (#1997) * Remove moved OpenAPI sample and point to SK one. * Update dotnet/samples/GettingStarted/Agents/README.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.2 to 4.0.4.6 (#2031) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.6 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .NET: Separate all memory and rag samples into their own folders (#2000) * Separate all memory and rag samples into their own folders * Fix broken link. * Python: .Net: Dotnet devui compatibility fixes (#2026) * DevUI: Add OpenAI Responses API proxy support with enhanced UI features This commit adds support for proxying requests to OpenAI's Responses API, allowing DevUI to route conversations to OpenAI models when configured to enable testing. Backend changes: - Add OpenAI proxy executor with conversation routing logic - Enhance event mapper to support OpenAI Responses API format - Extend server endpoints to handle OpenAI proxy mode - Update models with OpenAI-specific response types - Remove emojis from logging and CLI output for cleaner text Frontend changes: - Add settings modal with OpenAI proxy configuration UI - Enhance agent and workflow views with improved state management - Add new UI components (separator, switch) for settings - Update debug panel with better event filtering - Improve message renderers for OpenAI content types - Update types and API client for OpenAI integration * update ui, settings modal and workflow input form, add register cleanup hooks. * add workflow HIL support, user mode, other fixes * feat(devui): add human-in-the-loop (HIL) support with dynamic response schemas Implement HIL workflow support allowing workflows to pause for user input with dynamically generated JSON schemas based on response handler type hints. Key Features: - Automatic response schema extraction from @response_handler decorators - Dynamic form generation in UI based on Pydantic/dataclass response types - Checkpoint-based conversation storage for HIL requests/responses - Resume workflow execution after user provides HIL response Backend Changes: - Add extract_response_type_from_executor() to introspect response handlers - Enrich RequestInfoEvent with response_schema via _enrich_request_info_event_with_response_schema() - Map RequestInfoEvent to response.input.requested OpenAI event format - Store HIL responses in conversation history and restore checkpoints Frontend Changes: - Add HILInputModal component with SchemaFormRenderer for dynamic forms - Support Pydantic BaseModel and dataclass response types - Render enum fields as dropdowns, strings as text/textarea, numbers, booleans, arrays, objects - Display original request context alongside response form Testing: - Add tests for checkpoint storage (test_checkpoints.py) - Add schema generation tests for all input types (test_schema_generation.py) - Validate end-to-end HIL flow with spam workflow sample This enables workflows to seamlessly pause execution and request structured user input with type-safe, validated forms generated automatically from response type annotations. * improve HIL support, improve workflow execution view * ui updates * ui updates * improve HIL for workflows, add auth and view modes * update workflow * security improvements , ui fixes * fix mypy error * update loading spinner in ui * DevUI: Serialize workflow input as string to maintain conformance with OpenAI Responses format * Phase 1: Add /meta endpoint and fix workflow event naming for .NET DevUI compatibility * additional fixes for .NET DevUI workflow visualization item ID tracking **Problem:** .NET DevUI was generating different item IDs for ExecutorInvokedEvent and ExecutorCompletedEvent, causing only the first executor to highlight in the workflow graph. Long executor names and error messages also broke UI layout. **Changes:** - Add ExecutorActionItemResource to match Python DevUI implementation - Track item IDs per executor using dictionary in AgentRunResponseUpdateExtensions - Reuse same item ID across invoked/completed/failed events for proper pairing - Add truncateText() utility to workflow-utils.ts - Truncate executor names to 35 chars in execution timeline - Truncate error messages to 150 chars in workflow graph nodes ** Details:** - ExecutorActionItemResource registered with JSON source generation context - Dictionary cleaned up after executor completion/failure to prevent memory leaks - Frontend item tracking by unique item.id supports multiple executor runs - All changes follow existing codebase patterns and conventions Tested with review-workflow showing correct executor highlighting and state transitions for sequential and concurrent executors. * format fixes, remove cors tests * remove unecessary attributes --------- Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Reuben Bond <reuben.bond@gmail.com> * DevUI: support having both an agent and a workflow with the same id in discovery (#2023) * Python: Fix Model ID attribute not showing up in `invoke_agent` span (#2061) * Best effort to surface the model id to invoke agent span * Fix tests * Fix tests * Version 1.0.0-preview.251107.2 (#2065) * Version 1.0.0-preview.251110.2 (#2067) * Update README.md to change Grafana links to Azure portal links for dashboard access (#1983) * .NET - Enable build & test on branch `feature-foundry-agents` (#2068) * Tests good, mkay * Update .github/workflows/dotnet-build-and-test.yml Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Enable feature build pipelines --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> * Python: Add concrete AGUIChatClient (#2072) * Add concrete AGUIChatClient * Update logging docstrings and conventions * PR feedback * Updates to support client-side tool calls * .NET: Move catalog samples to the HostedAgents folder (#2090) * move catalog samples to the HostedAgents folder * move the catalog samples' projects to the HostedAgents folder * Bump OpenTelemetry.Instrumentation.Runtime from 1.12.0 to 1.13.0 (#1856) --- updated-dependencies: - dependency-name: OpenTelemetry.Instrumentation.Runtime dependency-version: 1.13.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * .NET: Bump Microsoft.SemanticKernel.Agents.Abstractions from 1.66.0 to 1.67.0 (#1962) * Bump Microsoft.SemanticKernel.Agents.Abstractions from 1.66.0 to 1.67.0 --- updated-dependencies: - dependency-name: Microsoft.SemanticKernel.Agents.Abstractions dependency-version: 1.67.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * .NET: Bump all Microsoft.SemanticKernel packages from 1.66.* to 1.67.* (#1969) * Initial plan * Update all Microsoft.SemanticKernel packages to 1.67.* Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Remove unrelated changes to package-lock.json and yarn.lock Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com> * .NET: fix: WorkflowAsAgent Sample (#1787) * fix: WorkflowAsAgent Sample * Also makes ChatForwardingExecutor public * feat: Expand ChatForwardingExecutor handled types Make ChatForwardingExecutor match the input types of ChatProtocolExecutor. * fix: Update for the new AgentRunResponseUpdate merge logic AIAgent always sends out List<ChatMessage> now. * Updated (#2076) * Bump vite in /python/samples/demos/chatkit-integration/frontend (#1918) Bumps [vite](https://github.com/vitejs/vite/tree/HEAD/packages/vite) from 7.1.9 to 7.1.12. - [Release notes](https://github.com/vitejs/vite/releases) - [Changelog](https://github.com/vitejs/vite/blob/v7.1.12/packages/vite/CHANGELOG.md) - [Commits](https://github.com/vitejs/vite/commits/v7.1.12/packages/vite) --- updated-dependencies: - dependency-name: vite dependency-version: 7.1.12 dependency-type: direct:development ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump Roslynator.Analyzers from 4.14.0 to 4.14.1 (#1857) --- updated-dependencies: - dependency-name: Roslynator.Analyzers dependency-version: 4.14.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump MishaKav/pytest-coverage-comment from 1.1.57 to 1.1.59 (#2034) Bumps [MishaKav/pytest-coverage-comment](https://github.com/mishakav/pytest-coverage-comment) from 1.1.57 to 1.1.59. - [Release notes](https://github.com/mishakav/pytest-coverage-comment/releases) - [Changelog](https://github.com/MishaKav/pytest-coverage-comment/blob/main/CHANGELOG.md) - [Commits](https://github.com/mishakav/pytest-coverage-comment/compare/v1.1.57...v1.1.59) --- updated-dependencies: - dependency-name: MishaKav/pytest-coverage-comment dependency-version: 1.1.59 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Handle agent user input request in AgentExecutor (#2022) * Handle agent user input request in AgentExecutor * fix test * Address comments * Fix tests * Fix tests * Address comments * Address comments * Python: OpenAI Responses Image Generation Stream Support, Sample and Unit Tests (#1853) * support for image gen streaming * small fixes * fixes * added comment * Python: Fix MCP Tool Parameter Descriptions Not Propagated to LLMs (#1978) * mcp tool description fix * small fix * .NET: Allow extending agent run options via additional properties (#1872) * Allow extending agent run options via additional properties This mirrors the M.E.AI model in ChatOptions.AdditionalProperties which is very useful when building functionality pipelines. Fixes https://github.com/microsoft/agent-framework/issues/1815 * Expand XML documentation Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Add AdditionalProperties tests to AgentRunOptions Co-authored-by: kzu <169707+kzu@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: kzu <169707+kzu@users.noreply.github.com> * Python: Use the last entry in the task history to avoid empty responses (#2101) * Use the last entry in the task history to avoid empty responses * History only contains Messages * Updated package versions (#2104) --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Reuben Bond <203839+ReubenBond@users.noreply.github.com> Co-authored-by: Peter Ibekwe <109177538+peibekwe@users.noreply.github.com> Co-authored-by: Jeff Handley <jeffhandley@users.noreply.github.com> Co-authored-by: Daniel Roth <daroth@microsoft.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Shawn Henry <sphenry@gmail.com> Co-authored-by: Javier Calvarro Nelson <jacalvar@microsoft.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Reuben Bond <reuben.bond@gmail.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: wuweng <wuweng@microsoft.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Daniel Cazzulino <daniel@cazzulino.com> Co-authored-by: kzu <169707+kzu@users.noreply.github.com> * Updated azure-ai-projects package version and small fixes (#2139) * Python: [Feature Branch] Resolve CI issues (#2143) * Small documentation and code fixes * Small fix in documentation * Addressed PR feedback * Added AI Search example --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Reuben Bond <203839+ReubenBond@users.noreply.github.com> Co-authored-by: Peter Ibekwe <109177538+peibekwe@users.noreply.github.com> Co-authored-by: Jeff Handley <jeffhandley@users.noreply.github.com> Co-authored-by: Daniel Roth <daroth@microsoft.com> Co-authored-by: Victor Dibia <chuvidi2003@gmail.com> Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com> Co-authored-by: Shawn Henry <sphenry@gmail.com> Co-authored-by: Javier Calvarro Nelson <jacalvar@microsoft.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Korolev Dmitry <deagle.gross@gmail.com> Co-authored-by: westey <164392973+westey-m@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Reuben Bond <reuben.bond@gmail.com> Co-authored-by: Tao Chen <taochen@microsoft.com> Co-authored-by: wuweng <wuweng@microsoft.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: SergeyMenshykh <68852919+SergeyMenshykh@users.noreply.github.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: Jacob Alber <jaalber@microsoft.com> Co-authored-by: Giles Odigwe <79032838+giles17@users.noreply.github.com> Co-authored-by: Daniel Cazzulino <daniel@cazzulino.com> Co-authored-by: kzu <169707+kzu@users.noreply.github.com>
2026-06-16 21:04:09 +08:00 · 2025-11-12 15:20:53 -08:00
parent 4bffe1ebc8
commit edb367a2b9
42 changed files with 2538 additions and 488 deletions
@@ -564,10 +564,6 @@ class BaseChatClient(SerializationMixin, ABC):

        # Validate that store is True when conversation_id is set
        if chat_options.conversation_id is not None and chat_options.store is not True:
-            logger.warning(
-                "When conversation_id is set, store must be True for service-managed threads. "
-                "Automatically setting store=True."
-            )
            chat_options.store = True

        if chat_options.instructions:
@@ -663,10 +659,6 @@ class BaseChatClient(SerializationMixin, ABC):

        # Validate that store is True when conversation_id is set
        if chat_options.conversation_id is not None and chat_options.store is not True:
-            logger.warning(
-                "When conversation_id is set, store must be True for service-managed threads. "
-                "Automatically setting store=True."
-            )
            chat_options.store = True

        if chat_options.instructions:
@@ -1636,7 +1636,7 @@ def _handle_function_calls_response(
                    # this runs in every but the first run
                    # we need to keep track of all function call messages
                    fcc_messages.extend(response.messages)
-                    if getattr(kwargs.get("chat_options"), "store", False):
+                    if response.conversation_id is not None:
                        prepped_messages.clear()
                        prepped_messages.append(result_message)
                    else:
@@ -1839,7 +1839,7 @@ def _handle_function_calls_streaming_response(
                    # this runs in every but the first run
                    # we need to keep track of all function call messages
                    fcc_messages.extend(response.messages)
-                    if getattr(kwargs.get("chat_options"), "store", False):
+                    if response.conversation_id is not None:
                        prepped_messages.clear()
                        prepped_messages.append(result_message)
                    else:
@@ -6,6 +6,7 @@ from typing import Any

 _IMPORTS: dict[str, tuple[str, str]] = {
    "AzureAIAgentClient": ("agent_framework_azure_ai", "azure-ai"),
+    "AzureAIClient": ("agent_framework_azure_ai", "azure-ai"),
    "AzureOpenAIAssistantsClient": ("agent_framework.azure._assistants_client", "core"),
    "AzureOpenAIChatClient": ("agent_framework.azure._chat_client", "core"),
    "AzureAISettings": ("agent_framework_azure_ai", "azure-ai"),
@@ -1,6 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.

-from agent_framework_azure_ai import AzureAIAgentClient, AzureAISettings
+from agent_framework_azure_ai import AzureAIAgentClient, AzureAIClient, AzureAISettings

 from agent_framework.azure._assistants_client import AzureOpenAIAssistantsClient
 from agent_framework.azure._chat_client import AzureOpenAIChatClient
@@ -10,6 +10,7 @@ from agent_framework.azure._shared import AzureOpenAISettings

 __all__ = [
    "AzureAIAgentClient",
+    "AzureAIClient",
    "AzureAISettings",
    "AzureOpenAIAssistantsClient",
    "AzureOpenAIChatClient",
@@ -161,7 +161,8 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):
    async def close(self) -> None:
        """Clean up any assistants we created."""
        if self._should_delete_assistant and self.assistant_id is not None:
-            await self.client.beta.assistants.delete(self.assistant_id)
+            client = await self.ensure_client()
+            await client.beta.assistants.delete(self.assistant_id)
            object.__setattr__(self, "assistant_id", None)
            object.__setattr__(self, "_should_delete_assistant", False)

@@ -215,7 +216,11 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):
        """
        # If no assistant is provided, create a temporary assistant
        if self.assistant_id is None:
-            created_assistant = await self.client.beta.assistants.create(name=self.assistant_name, model=self.model_id)
+            if not self.model_id:
+                raise ServiceInitializationError("Parameter 'model_id' is required for assistant creation.")
+
+            client = await self.ensure_client()
+            created_assistant = await client.beta.assistants.create(name=self.assistant_name, model=self.model_id)
            self.assistant_id = created_assistant.id
            self._should_delete_assistant = True

@@ -233,6 +238,7 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):
        Returns:
            tuple: (stream, final_thread_id)
        """
+        client = await self.ensure_client()
        # Get any active run for this thread
        thread_run = await self._get_active_thread_run(thread_id)

@@ -240,7 +246,7 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):

        if thread_run is not None and tool_run_id is not None and tool_run_id == thread_run.id and tool_outputs:
            # There's an active run and we have tool results to submit, so submit the results.
-            stream = self.client.beta.threads.runs.submit_tool_outputs_stream(  # type: ignore[reportDeprecated]
+            stream = client.beta.threads.runs.submit_tool_outputs_stream(  # type: ignore[reportDeprecated]
                run_id=tool_run_id, thread_id=thread_run.thread_id, tool_outputs=tool_outputs
            )
            final_thread_id = thread_run.thread_id
@@ -249,7 +255,7 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):
            final_thread_id = await self._prepare_thread(thread_id, thread_run, run_options)

            # Now create a new run and stream the results.
-            stream = self.client.beta.threads.runs.stream(  # type: ignore[reportDeprecated]
+            stream = client.beta.threads.runs.stream(  # type: ignore[reportDeprecated]
                assistant_id=assistant_id, thread_id=final_thread_id, **run_options
            )

@@ -257,19 +263,21 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):

    async def _get_active_thread_run(self, thread_id: str | None) -> Run | None:
        """Get any active run for the given thread."""
+        client = await self.ensure_client()
        if thread_id is None:
            return None

-        async for run in self.client.beta.threads.runs.list(thread_id=thread_id, limit=1, order="desc"):  # type: ignore[reportDeprecated]
+        async for run in client.beta.threads.runs.list(thread_id=thread_id, limit=1, order="desc"):  # type: ignore[reportDeprecated]
            if run.status not in ["completed", "cancelled", "failed", "expired"]:
                return run
        return None

    async def _prepare_thread(self, thread_id: str | None, thread_run: Run | None, run_options: dict[str, Any]) -> str:
        """Prepare the thread for a new run, creating or cleaning up as needed."""
+        client = await self.ensure_client()
        if thread_id is None:
            # No thread ID was provided, so create a new thread.
-            thread = await self.client.beta.threads.create(  # type: ignore[reportDeprecated]
+            thread = await client.beta.threads.create(  # type: ignore[reportDeprecated]
                messages=run_options["additional_messages"],
                tool_resources=run_options.get("tool_resources"),
                metadata=run_options.get("metadata"),
@@ -280,7 +288,7 @@ class OpenAIAssistantsClient(OpenAIConfigMixin, BaseChatClient):

        if thread_run is not None:
            # There was an active run; we need to cancel it before starting a new run.
-            await self.client.beta.threads.runs.cancel(run_id=thread_run.id, thread_id=thread_id)  # type: ignore[reportDeprecated]
+            await client.beta.threads.runs.cancel(run_id=thread_run.id, thread_id=thread_id)  # type: ignore[reportDeprecated]

        return thread_id

@@ -69,10 +69,11 @@ class OpenAIBaseChatClient(OpenAIBase, BaseChatClient):
        chat_options: ChatOptions,
        **kwargs: Any,
    ) -> ChatResponse:
+        client = await self.ensure_client()
        options_dict = self._prepare_options(messages, chat_options)
        try:
            return self._create_chat_response(
-                await self.client.chat.completions.create(stream=False, **options_dict), chat_options
+                await client.chat.completions.create(stream=False, **options_dict), chat_options
            )
        except BadRequestError as ex:
            if ex.code == "content_filter":
@@ -97,10 +98,11 @@ class OpenAIBaseChatClient(OpenAIBase, BaseChatClient):
        chat_options: ChatOptions,
        **kwargs: Any,
    ) -> AsyncIterable[ChatResponseUpdate]:
+        client = await self.ensure_client()
        options_dict = self._prepare_options(messages, chat_options)
        options_dict["stream_options"] = {"include_usage": True}
        try:
-            async for chunk in await self.client.chat.completions.create(stream=True, **options_dict):
+            async for chunk in await client.chat.completions.create(stream=True, **options_dict):
                if len(chunk.choices) == 0 and chunk.usage is None:
                    continue
                yield self._create_chat_response_update(chunk)
@@ -89,23 +89,24 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
        chat_options: ChatOptions,
        **kwargs: Any,
    ) -> ChatResponse:
-        options_dict = self._prepare_options(messages, chat_options)
+        client = await self.ensure_client()
+        run_options = await self.prepare_options(messages, chat_options)
        try:
-            if not chat_options.response_format:
-                response = await self.client.responses.create(
+            response_format = run_options.pop("response_format", None)
+            if not response_format:
+                response = await client.responses.create(
                    stream=False,
-                    **options_dict,
+                    **run_options,
                )
-                chat_options.conversation_id = response.id if chat_options.store is True else None
+                chat_options.conversation_id = self.get_conversation_id(response, chat_options.store)
                return self._create_response_content(response, chat_options=chat_options)
            # create call does not support response_format, so we need to handle it via parse call
-            resp_format = chat_options.response_format
-            parsed_response: ParsedResponse[BaseModel] = await self.client.responses.parse(
-                text_format=resp_format,
+            parsed_response: ParsedResponse[BaseModel] = await client.responses.parse(
+                text_format=response_format,
                stream=False,
-                **options_dict,
+                **run_options,
            )
-            chat_options.conversation_id = parsed_response.id if chat_options.store is True else None
+            chat_options.conversation_id = self.get_conversation_id(parsed_response, chat_options.store)
            return self._create_response_content(parsed_response, chat_options=chat_options)
        except BadRequestError as ex:
            if ex.code == "content_filter":
@@ -130,13 +131,15 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
        chat_options: ChatOptions,
        **kwargs: Any,
    ) -> AsyncIterable[ChatResponseUpdate]:
-        options_dict = self._prepare_options(messages, chat_options)
+        client = await self.ensure_client()
+        run_options = await self.prepare_options(messages, chat_options)
        function_call_ids: dict[int, tuple[str, str]] = {}  # output_index: (call_id, name)
        try:
-            if not chat_options.response_format:
-                response = await self.client.responses.create(
+            response_format = run_options.pop("response_format", None)
+            if not response_format:
+                response = await client.responses.create(
                    stream=True,
-                    **options_dict,
+                    **run_options,
                )
                async for chunk in response:
                    update = self._create_streaming_response_content(
@@ -145,9 +148,9 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                    yield update
                return
            # create call does not support response_format, so we need to handle it via stream call
-            async with self.client.responses.stream(
-                text_format=chat_options.response_format,
-                **options_dict,
+            async with client.responses.stream(
+                text_format=response_format,
+                **run_options,
            ) as response:
                async for chunk in response:
                    update = self._create_streaming_response_content(
@@ -170,6 +173,12 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                inner_exception=ex,
            ) from ex

+    def get_conversation_id(
+        self, response: OpenAIResponse | ParsedResponse[BaseModel], store: bool | None
+    ) -> str | None:
+        """Get the conversation ID from the response if store is True."""
+        return response.id if store else None
+
    # region Prep methods

    def _tools_to_response_tools(
@@ -180,31 +189,7 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
            if isinstance(tool, ToolProtocol):
                match tool:
                    case HostedMCPTool():
-                        mcp: Mcp = {
-                            "type": "mcp",
-                            "server_label": tool.name.replace(" ", "_"),
-                            "server_url": str(tool.url),
-                            "server_description": tool.description,
-                            "headers": tool.headers,
-                        }
-                        if tool.allowed_tools:
-                            mcp["allowed_tools"] = list(tool.allowed_tools)
-                        if tool.approval_mode:
-                            match tool.approval_mode:
-                                case str():
-                                    mcp["require_approval"] = (
-                                        "always" if tool.approval_mode == "always_require" else "never"
-                                    )
-                                case _:
-                                    if always_require_approvals := tool.approval_mode.get("always_require_approval"):
-                                        mcp["require_approval"] = {
-                                            "always": {"tool_names": list(always_require_approvals)}
-                                        }
-                                    if never_require_approvals := tool.approval_mode.get("never_require_approval"):
-                                        mcp["require_approval"] = {
-                                            "never": {"tool_names": list(never_require_approvals)}
-                                        }
-                        response_tools.append(mcp)
+                        response_tools.append(self.get_mcp_tool(tool))
                    case HostedCodeInterpreterTool():
                        tool_args: CodeInterpreterContainerCodeInterpreterToolAuto = {"type": "auto"}
                        if tool.inputs:
@@ -306,12 +291,36 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                    response_tools.append(tool_dict)
        return response_tools

-    def _prepare_options(self, messages: MutableSequence[ChatMessage], chat_options: ChatOptions) -> dict[str, Any]:
+    def get_mcp_tool(self, tool: HostedMCPTool) -> Any:
+        """Get MCP tool from HostedMCPTool."""
+        mcp: Mcp = {
+            "type": "mcp",
+            "server_label": tool.name.replace(" ", "_"),
+            "server_url": str(tool.url),
+            "server_description": tool.description,
+            "headers": tool.headers,
+        }
+        if tool.allowed_tools:
+            mcp["allowed_tools"] = list(tool.allowed_tools)
+        if tool.approval_mode:
+            match tool.approval_mode:
+                case str():
+                    mcp["require_approval"] = "always" if tool.approval_mode == "always_require" else "never"
+                case _:
+                    if always_require_approvals := tool.approval_mode.get("always_require_approval"):
+                        mcp["require_approval"] = {"always": {"tool_names": list(always_require_approvals)}}
+                    if never_require_approvals := tool.approval_mode.get("never_require_approval"):
+                        mcp["require_approval"] = {"never": {"tool_names": list(never_require_approvals)}}
+
+        return mcp
+
+    async def prepare_options(
+        self, messages: MutableSequence[ChatMessage], chat_options: ChatOptions
+    ) -> dict[str, Any]:
        """Take ChatOptions and create the specific options for Responses API."""
-        options_dict: dict[str, Any] = chat_options.to_dict(
+        run_options: dict[str, Any] = chat_options.to_dict(
            exclude={
                "type",
-                "response_format",  # handled in inner get methods
                "presence_penalty",  # not supported
                "frequency_penalty",  # not supported
                "logit_bias",  # not supported
@@ -320,6 +329,10 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                "instructions",  # already added as system message
            }
        )
+
+        if chat_options.response_format:
+            run_options["response_format"] = chat_options.response_format
+
        translations = {
            "model_id": "model",
            "allow_multiple_tool_calls": "parallel_tool_calls",
@@ -327,35 +340,37 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
            "max_tokens": "max_output_tokens",
        }
        for old_key, new_key in translations.items():
-            if old_key in options_dict and old_key != new_key:
-                options_dict[new_key] = options_dict.pop(old_key)
+            if old_key in run_options and old_key != new_key:
+                run_options[new_key] = run_options.pop(old_key)

        # tools
        if chat_options.tools is None:
-            options_dict.pop("parallel_tool_calls", None)
+            run_options.pop("parallel_tool_calls", None)
        else:
-            options_dict["tools"] = self._tools_to_response_tools(chat_options.tools)
+            run_options["tools"] = self._tools_to_response_tools(chat_options.tools)

        # model id
-        if not options_dict.get("model"):
-            options_dict["model"] = self.model_id
+        if not run_options.get("model"):
+            if not self.model_id:
+                raise ValueError("model_id must be a non-empty string")
+            run_options["model"] = self.model_id

        # messages
        request_input = self._prepare_chat_messages_for_request(messages)
        if not request_input:
            raise ServiceInvalidRequestError("Messages are required for chat completions")
-        options_dict["input"] = request_input
+        run_options["input"] = request_input

        # additional provider specific settings
-        if additional_properties := options_dict.pop("additional_properties", None):
+        if additional_properties := run_options.pop("additional_properties", None):
            for key, value in additional_properties.items():
                if value is not None:
-                    options_dict[key] = value
-        if "store" not in options_dict:
-            options_dict["store"] = False
-        if (tool_choice := options_dict.get("tool_choice")) and len(tool_choice.keys()) == 1:
-            options_dict["tool_choice"] = tool_choice["mode"]
-        return options_dict
+                    run_options[key] = value
+        if "store" not in run_options:
+            run_options["store"] = False
+        if (tool_choice := run_options.get("tool_choice")) and len(tool_choice.keys()) == 1:
+            run_options["tool_choice"] = tool_choice["mode"]
+        return run_options

    def _prepare_chat_messages_for_request(self, chat_messages: Sequence[ChatMessage]) -> list[dict[str, Any]]:
        """Prepare the chat messages for a request.
@@ -504,7 +519,6 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                # call_id for the result needs to be the same as the call_id for the function call
                args: dict[str, Any] = {
                    "call_id": content.call_id,
-                    "id": call_id_to_id.get(content.call_id),
                    "type": "function_call_output",
                }
                if content.result:
@@ -734,7 +748,7 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
            "raw_representation": response,
        }
        if chat_options.store:
-            args["conversation_id"] = response.id
+            args["conversation_id"] = self.get_conversation_id(response, chat_options.store)
        if response.usage and (usage_details := self._usage_details_from_openai(response.usage)):
            args["usage_details"] = usage_details
        if structured_response:
@@ -834,7 +848,7 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                contents.append(TextReasoningContent(text=event.text, raw_representation=event))
                metadata.update(self._get_metadata_from_response(event))
            case "response.completed":
-                conversation_id = event.response.id if chat_options.store is True else None
+                conversation_id = self.get_conversation_id(event.response, chat_options.store)
                model = event.response.model
                if event.response.usage:
                    usage = self._usage_details_from_openai(event.response.usage)
@@ -127,18 +127,18 @@ class OpenAIBase(SerializationMixin):

    INJECTABLE: ClassVar[set[str]] = {"client"}

-    def __init__(self, *, client: AsyncOpenAI, model_id: str, **kwargs: Any) -> None:
+    def __init__(self, *, model_id: str | None = None, client: AsyncOpenAI | None = None, **kwargs: Any) -> None:
        """Initialize OpenAIBase.

        Keyword Args:
            client: The AsyncOpenAI client instance.
-            model_id: The AI model ID to use (non-empty, whitespace stripped).
+            model_id: The AI model ID to use.
            **kwargs: Additional keyword arguments.
        """
-        if not model_id or not model_id.strip():
-            raise ValueError("model_id must be a non-empty string")
        self.client = client
-        self.model_id = model_id.strip()
+        self.model_id = None
+        if model_id:
+            self.model_id = model_id.strip()

        # Call super().__init__() to continue MRO chain (e.g., BaseChatClient)
        # Extract known kwargs that belong to other base classes
@@ -162,6 +162,21 @@ class OpenAIBase(SerializationMixin):
        for key, value in kwargs.items():
            setattr(self, key, value)

+    async def initialize_client(self) -> None:
+        """Initialize OpenAI client asynchronously.
+
+        Override in subclasses to initialize the OpenAI client asynchronously.
+        """
+        pass
+
+    async def ensure_client(self) -> AsyncOpenAI:
+        """Ensure OpenAI client is initialized."""
+        await self.initialize_client()
+        if self.client is None:
+            raise ServiceInitializationError("OpenAI client is not initialized")
+
+        return self.client
+
    def _get_api_key(
        self, api_key: str | SecretStr | Callable[[], str | Awaitable[str]] | None
    ) -> str | Callable[[], str | Awaitable[str]] | None:
@@ -1407,27 +1407,27 @@ def test_create_response_content_image_generation_fallback():
    assert f"data:image/png;base64,{unrecognized_base64}" == content.uri


-def test_prepare_options_store_parameter_handling() -> None:
+async def test_prepare_options_store_parameter_handling() -> None:
    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
    messages = [ChatMessage(role="user", text="Test message")]

    test_conversation_id = "test-conversation-123"
    chat_options = ChatOptions(store=True, conversation_id=test_conversation_id)
-    options = client._prepare_options(messages, chat_options)  # type: ignore
+    options = await client.prepare_options(messages, chat_options)
    assert options["store"] is True
    assert options["previous_response_id"] == test_conversation_id

    chat_options = ChatOptions(store=False, conversation_id="")
-    options = client._prepare_options(messages, chat_options)  # type: ignore
+    options = await client.prepare_options(messages, chat_options)
    assert options["store"] is False

    chat_options = ChatOptions(store=None, conversation_id=None)
-    options = client._prepare_options(messages, chat_options)  # type: ignore
+    options = await client.prepare_options(messages, chat_options)
    assert options["store"] is False
    assert "previous_response_id" not in options

    chat_options = ChatOptions()
-    options = client._prepare_options(messages, chat_options)  # type: ignore
+    options = await client.prepare_options(messages, chat_options)
    assert options["store"] is False
    assert "previous_response_id" not in options