Merge branch 'main' into taochen/python-update-sample-validation-scripts

force node22
force node24
2026-06-16 21:04:09 +08:00 · 2026-03-24 18:16:22 -07:00 · 2026-03-24 17:10:25 -07:00 · 2026-03-24 17:06:41 -07:00 · 2026-03-24 16:58:18 -07:00 · 2026-03-24 16:51:44 -07:00
528 changed files with 12224 additions and 12718 deletions
@@ -1,166 +0,0 @@
-name: Setup Local MCP Server
-description: Start and validate a local streamable HTTP MCP server for integration tests
-
-inputs:
-  fallback_url:
-    description: Existing LOCAL_MCP_URL value to keep as a fallback if local startup fails
-    required: false
-    default: ''
-  host:
-    description: Host interface to bind the local MCP server
-    required: false
-    default: '127.0.0.1'
-  port:
-    description: Port to bind the local MCP server
-    required: false
-    default: '8011'
-  mount_path:
-    description: Mount path for the local streamable HTTP MCP endpoint
-    required: false
-    default: '/mcp'
-
-outputs:
-  effective_url:
-    description: Local MCP URL when startup succeeds, otherwise the provided fallback URL
-    value: ${{ steps.start.outputs.effective_url }}
-  local_url:
-    description: URL of the local MCP server
-    value: ${{ steps.start.outputs.local_url }}
-  started:
-    description: Whether the local MCP server started and passed validation
-    value: ${{ steps.start.outputs.started }}
-  pid:
-    description: PID of the local MCP server process when startup succeeded
-    value: ${{ steps.start.outputs.pid }}
-
-runs:
-  using: composite
-  steps:
-    - name: Start and validate local MCP server
-      id: start
-      shell: bash
-      run: |
-        set -euo pipefail
-
-        host="${{ inputs.host }}"
-        port="${{ inputs.port }}"
-        mount_path="${{ inputs.mount_path }}"
-        fallback_url="${{ inputs.fallback_url }}"
-
-        if [[ ! "$mount_path" =~ ^/ ]]; then
-          mount_path="/$mount_path"
-        fi
-
-        local_url="http://${host}:${port}${mount_path}"
-        health_url="http://${host}:${port}/healthz"
-        log_file="$RUNNER_TEMP/local-mcp-server.log"
-        pid_file="$RUNNER_TEMP/local-mcp-server.pid"
-        rm -f "$log_file" "$pid_file"
-
-        server_pid="$(
-          python3 - "$GITHUB_WORKSPACE/python" "$log_file" "$host" "$port" "$mount_path" <<'PY'
-        from __future__ import annotations
-
-        import subprocess
-        import sys
-
-        workspace, log_file, host, port, mount_path = sys.argv[1:]
-
-        with open(log_file, "w", encoding="utf-8") as log:
-            process = subprocess.Popen(
-                [
-                    "uv",
-                    "run",
-                    "python",
-                    "scripts/local_mcp_streamable_http_server.py",
-                    "--host",
-                    host,
-                    "--port",
-                    port,
-                    "--mount-path",
-                    mount_path,
-                ],
-                cwd=workspace,
-                stdout=log,
-                stderr=subprocess.STDOUT,
-                start_new_session=True,
-            )
-
-        print(process.pid)
-        PY
-        )"
-        echo "$server_pid" > "$pid_file"
-
-        started=false
-        for _ in $(seq 1 30); do
-          if curl --silent --fail "$health_url" >/dev/null; then
-            started=true
-            break
-          fi
-          if ! kill -0 "$server_pid" 2>/dev/null; then
-            break
-          fi
-          sleep 1
-        done
-
-        if [[ "$started" == "true" ]]; then
-          if ! (
-            cd "$GITHUB_WORKSPACE/python"
-            LOCAL_MCP_URL="$local_url" uv run python - <<'PY'
-        from __future__ import annotations
-
-        import asyncio
-        import os
-
-        from agent_framework import Content, MCPStreamableHTTPTool
-
-
-        def result_to_text(result: str | list[Content]) -> str:
-            if isinstance(result, str):
-                return result
-            return "\n".join(content.text for content in result if content.type == "text" and content.text)
-
-
-        async def main() -> None:
-            tool = MCPStreamableHTTPTool(
-                name="local_ci_mcp",
-                url=os.environ["LOCAL_MCP_URL"],
-                approval_mode="never_require",
-            )
-
-            async with tool:
-                assert tool.functions, "Local MCP server did not expose any tools."
-                result = result_to_text(await tool.functions[0].invoke(query="What is Agent Framework?"))
-                assert result, "Local MCP server returned an empty response."
-
-
-        asyncio.run(main())
-        PY
-          ); then
-            started=false
-          fi
-        fi
-
-        effective_url="$local_url"
-        pid="$server_pid"
-
-        if [[ "$started" != "true" ]]; then
-          effective_url="$fallback_url"
-          pid=""
-          if kill -0 "$server_pid" 2>/dev/null; then
-            kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" || true
-            sleep 1
-            kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" || true
-          fi
-          echo "Local MCP server was unavailable; continuing with fallback LOCAL_MCP_URL."
-          if [[ -f "$log_file" ]]; then
-            tail -n 100 "$log_file" || true
-          fi
-        else
-          echo "Using local MCP server at $local_url"
-        fi
-
-        echo "started=$started" >> "$GITHUB_OUTPUT"
-        echo "local_url=$local_url" >> "$GITHUB_OUTPUT"
-        echo "effective_url=$effective_url" >> "$GITHUB_OUTPUT"
-        echo "pid=$pid" >> "$GITHUB_OUTPUT"
@@ -41,7 +41,8 @@ ENFORCED_TARGETS: set[str] = {
    "packages.purview.agent_framework_purview",
    "packages.anthropic.agent_framework_anthropic",
    "packages.azure-ai-search.agent_framework_azure_ai_search",
-    "packages.openai.agent_framework_openai",
+    "packages.core.agent_framework.azure",
+    "packages.core.agent_framework.openai",
    # Individual files (if you want to enforce specific files instead of whole packages)
    "packages/core/agent_framework/observability.py",
    # Add more targets here as coverage improves
@@ -63,8 +63,6 @@ jobs:
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
    defaults:
      run:
@@ -83,8 +81,8 @@ jobs:
      - name: Test with pytest (OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
-          packages/openai/tests
-          -m "integration and not azure"
+          packages/core/tests/openai
+          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
@@ -96,9 +94,8 @@ jobs:
    environment: integration
    timeout-minutes: 60
    env:
-      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
-      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
    defaults:
@@ -124,9 +121,7 @@ jobs:
      - name: Test with pytest (Azure OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
-          packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
-          packages/openai/tests/openai/test_openai_chat_client_azure.py
-          packages/azure-ai/tests/azure_openai
+          packages/core/tests/azure
          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
@@ -156,13 +151,6 @@ jobs:
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
-      - name: Start local MCP server
-        id: local-mcp
-        uses: ./.github/actions/setup-local-mcp-server
-        with:
-          fallback_url: ${{ env.LOCAL_MCP_URL }}
-      - name: Prefer local MCP URL when available
-        run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
      - name: Test with pytest (Anthropic, Ollama, MCP integration)
        run: >
          uv run pytest --import-mode=importlib
@@ -173,26 +161,6 @@ jobs:
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
-      - name: Stop local MCP server
-        if: always()
-        shell: bash
-        run: |
-          set -euo pipefail
-          server_pid="${{ steps.local-mcp.outputs.pid }}"
-          if [[ -z "$server_pid" ]]; then
-            exit 0
-          fi
-          if ! kill -0 "$server_pid" 2>/dev/null; then
-            exit 0
-          fi
-          kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
-          for _ in $(seq 1 10); do
-            if ! kill -0 "$server_pid" 2>/dev/null; then
-              exit 0
-            fi
-            sleep 1
-          done
-          kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true

  # Azure Functions + Durable Task integration tests
  python-tests-functions:
@@ -204,13 +172,10 @@ jobs:
      UV_PYTHON: "3.11"
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
-      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
+      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
-      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
-      FOUNDRY_MODEL: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
-      FOUNDRY_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
      FUNCTIONS_WORKER_RUNTIME: "python"
      DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
      AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -244,8 +209,7 @@ jobs:
          packages/durabletask/tests/integration_tests
          -m integration
          -n logical --dist worksteal
-          -x
-          --timeout=360 --session-timeout=900 --timeout_method thread
+          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5

  # Azure AI integration tests
@@ -257,8 +221,6 @@ jobs:
    env:
      AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
      AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
-      FOUNDRY_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
-      FOUNDRY_MODEL: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
      LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
    defaults:
      run:
@@ -282,9 +244,7 @@ jobs:
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
      - name: Test with pytest
        timeout-minutes: 15
-        run: |
-          uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
-          uv run --directory packages/foundry poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
+        run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5

  # Azure Cosmos integration tests
  python-tests-cosmos:
@@ -47,9 +47,6 @@ jobs:
          filters: |
            python:
              - 'python/**'
-              - '.github/actions/setup-local-mcp-server/**'
-              - '.github/workflows/python-merge-tests.yml'
-              - '.github/workflows/python-integration-tests.yml'
            core:
              - 'python/packages/core/agent_framework/_*.py'
              - 'python/packages/core/agent_framework/_workflows/**'
@@ -57,30 +54,20 @@ jobs:
              - 'python/packages/core/agent_framework/observability.py'
            openai:
              - 'python/packages/core/agent_framework/openai/**'
-              - 'python/packages/openai/**'
-              - 'python/samples/**/providers/openai/**'
+              - 'python/packages/core/tests/openai/**'
            azure:
-              - 'python/packages/openai/**'
              - 'python/packages/core/agent_framework/azure/**'
-              - 'python/packages/azure-ai/agent_framework_azure_ai/_deprecated_azure_openai.py'
-              - 'python/packages/azure-ai/tests/azure_openai/**'
-              - 'python/samples/**/providers/azure/openai_chat_completion_client_azure*.py'
+              - 'python/packages/core/tests/azure/**'
            misc:
              - 'python/packages/anthropic/**'
              - 'python/packages/ollama/**'
              - 'python/packages/core/agent_framework/_mcp.py'
              - 'python/packages/core/tests/core/test_mcp.py'
-              - 'python/scripts/local_mcp_streamable_http_server.py'
-              - '.github/actions/setup-local-mcp-server/**'
-              - '.github/workflows/python-merge-tests.yml'
-              - '.github/workflows/python-integration-tests.yml'
            functions:
              - 'python/packages/azurefunctions/**'
              - 'python/packages/durabletask/**'
            azure-ai:
              - 'python/packages/azure-ai/**'
-              - 'python/packages/foundry/**'
-              - 'python/samples/**/providers/foundry/**'
            cosmos:
              - 'python/packages/azure-cosmos/**'
      # run only if 'python' files were changed
@@ -144,8 +131,6 @@ jobs:
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_EMBEDDINGS_MODEL_ID: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
    defaults:
      run:
@@ -161,8 +146,8 @@ jobs:
      - name: Test with pytest (OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
-          packages/openai/tests
-          -m "integration and not azure"
+          packages/core/tests/openai
+          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
@@ -195,9 +180,8 @@ jobs:
    runs-on: ubuntu-latest
    environment: integration
    env:
-      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
-      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
    defaults:
@@ -221,9 +205,7 @@ jobs:
      - name: Test with pytest (Azure OpenAI integration)
        run: >
          uv run pytest --import-mode=importlib
-          packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
-          packages/openai/tests/openai/test_openai_chat_client_azure.py
-          packages/azure-ai/tests/azure_openai
+          packages/core/tests/azure
          -m integration
          -n logical --dist worksteal
          --timeout=120 --session-timeout=900 --timeout_method thread
@@ -271,13 +253,6 @@ jobs:
        with:
          python-version: ${{ env.UV_PYTHON }}
          os: ${{ runner.os }}
-      - name: Start local MCP server
-        id: local-mcp
-        uses: ./.github/actions/setup-local-mcp-server
-        with:
-          fallback_url: ${{ env.LOCAL_MCP_URL }}
-      - name: Prefer local MCP URL when available
-        run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
      - name: Test with pytest (Anthropic, Ollama, MCP integration)
        run: >
          uv run pytest --import-mode=importlib
@@ -289,26 +264,6 @@ jobs:
          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
-      - name: Stop local MCP server
-        if: always()
-        shell: bash
-        run: |
-          set -euo pipefail
-          server_pid="${{ steps.local-mcp.outputs.pid }}"
-          if [[ -z "$server_pid" ]]; then
-            exit 0
-          fi
-          if ! kill -0 "$server_pid" 2>/dev/null; then
-            exit 0
-          fi
-          kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
-          for _ in $(seq 1 10); do
-            if ! kill -0 "$server_pid" 2>/dev/null; then
-              exit 0
-            fi
-            sleep 1
-          done
-          kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
      - name: Surface failing tests
        if: always()
        uses: pmeier/pytest-results-action@v0.7.2
@@ -335,13 +290,10 @@ jobs:
      UV_PYTHON: "3.11"
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
-      OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
+      AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
      AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
-      AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
-      FOUNDRY_MODEL: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
-      FOUNDRY_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
      FUNCTIONS_WORKER_RUNTIME: "python"
      DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
      AzureWebJobsStorage: "UseDevelopmentStorage=true"
@@ -373,8 +325,7 @@ jobs:
          packages/durabletask/tests/integration_tests
          -m integration
          -n logical --dist worksteal
-          -x
-          --timeout=360 --session-timeout=900 --timeout_method thread
+          --timeout=120 --session-timeout=900 --timeout_method thread
          --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Surface failing tests
@@ -401,8 +352,6 @@ jobs:
    env:
      AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
      AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
-      FOUNDRY_PROJECT_ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
-      FOUNDRY_MODEL: ${{ vars.AZUREAI__DEPLOYMENTNAME }}
      LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
    defaults:
      run:
@@ -424,9 +373,7 @@ jobs:
          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
      - name: Test with pytest
        timeout-minutes: 15
-        run: |
-          uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
-          uv run --directory packages/foundry poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
+        run: uv run --directory packages/azure-ai poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
        working-directory: ./python
      - name: Test Azure AI samples
        timeout-minutes: 10
@@ -78,7 +78,6 @@ jobs:
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
      # GitHub MCP
      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      # Observability
      ENABLE_INSTRUMENTATION: "true"
    defaults:
@@ -347,7 +346,7 @@ jobs:

  validate-02-agents-amazon:
    name: Validate 02-agents/providers/amazon
-    if: false # Temporarily disabled - requires AWS credentials
+    if: false  # Temporarily disabled - requires AWS credentials
    runs-on: ubuntu-latest
    environment: integration
    env:
@@ -379,7 +378,7 @@ jobs:

  validate-02-agents-ollama:
    name: Validate 02-agents/providers/ollama
-    if: false # Temporarily disabled - requires local Ollama server
+    if: false  # Temporarily disabled - requires local Ollama server
    runs-on: ubuntu-latest
    environment: integration
    env:
@@ -411,7 +410,7 @@ jobs:

  validate-02-agents-foundry-local:
    name: Validate 02-agents/providers/foundry_local
-    if: false # Temporarily disabled - requires local Foundry setup
+    if: false  # Temporarily disabled - requires local Foundry setup
    runs-on: ubuntu-latest
    environment: integration
    defaults:
@@ -441,7 +440,7 @@ jobs:

  validate-02-agents-copilotstudio:
    name: Validate 02-agents/providers/copilotstudio
-    if: false # Temporarily disabled - requires Copilot Studio setup
+    if: false  # Temporarily disabled - requires Copilot Studio setup
    runs-on: ubuntu-latest
    environment: integration
    env:
@@ -557,7 +556,7 @@ jobs:

  validate-04-hosting:
    name: Validate 04-hosting
-    if: false # Temporarily disabled because of sample complexity
+    if: false  # Temporarily disabled because of sample complexity
    runs-on: ubuntu-latest
    environment: integration
    env:
@@ -596,7 +595,7 @@ jobs:

  validate-05-end-to-end:
    name: Validate 05-end-to-end
-    if: false # Temporarily disabled because of sample complexity
+    if: false  # Temporarily disabled because of sample complexity
    runs-on: ubuntu-latest
    environment: integration
    env:
@@ -653,7 +652,6 @@ jobs:
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
    defaults:
      run:
        working-directory: python
@@ -705,7 +703,6 @@ jobs:
      OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
      OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
      OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
-      OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
      # Copilot Studio
      COPILOTSTUDIOAGENT__ENVIRONMENTID: ${{ secrets.COPILOTSTUDIOAGENT__ENVIRONMENTID }}
      COPILOTSTUDIOAGENT__SCHEMANAME: ${{ secrets.COPILOTSTUDIOAGENT__SCHEMANAME }}
@@ -1,72 +0,0 @@
---
-status: accepted
-contact: eavanvalkenburg
-date: 2026-03-20
-deciders: eavanvalkenburg, sphenry, chetantoshnival
-consulted: taochenosu, moonbox3, dmytrostruk, giles17, alliscode
---
-
-# Provider-Leading Client Design & OpenAI Package Extraction
-
-## Context and Problem Statement
-
-The `agent-framework-core` package currently bundles OpenAI and Azure OpenAI client implementations along with their dependencies (`openai`, `azure-identity`, `azure-ai-projects`, `packaging`). This makes core heavier than necessary for users who don't use OpenAI, and it conflates the core abstractions with a specific provider implementation. Additionally, the current class naming (`OpenAIResponsesClient`, `OpenAIChatClient`) is based on the underlying OpenAI API names rather than what users actually want to do, making discoverability harder for newcomers.
-
-## Decision Drivers
-
- **Lightweight core**: Core should only contain abstractions, middleware infrastructure, and telemetry — no provider-specific code or dependencies.
- **Discoverability-first**: Import namespaces should guide users to the right client. `from agent_framework.openai import ...` should surface all OpenAI-related clients; `from agent_framework.azure import ...` should surface Foundry, Azure AI, and other Azure-specific classes.
- **Provider-leading naming**: The primary client name should reflect the provider, not the underlying API. The Responses API is now the recommended default for OpenAI, so its client should be called `OpenAIChatClient` (not `OpenAIResponsesClient`).
- **Clean separation of concerns**: Azure-specific deprecated wrappers belong in the azure-ai package, not in the OpenAI package.
-
-## Considered Options
-
- **Keep OpenAI in core**: Simpler but keeps core heavy; doesn't help discoverability.
- **Extract OpenAI with Azure wrappers in the OpenAI package**: Keeps Azure OpenAI wrappers alongside OpenAI code, but pollutes the OpenAI package with Azure concerns.
- **Extract OpenAI, place Azure wrappers in azure-ai**: Clean separation; the OpenAI package has zero Azure dependencies; deprecated Azure wrappers live in a single file in azure-ai for easy future deletion.
-
-## Decision Outcome
-
-Chosen option: "Extract OpenAI, place Azure wrappers in azure-ai", because it achieves the lightest core, cleanest OpenAI package, and the most maintainable deprecation path.
-
-Key changes:
-
-1. **New `agent-framework-openai` package** with dependencies on `agent-framework-core`, `openai`, and `packaging` only.
-2. **Class renames**: `OpenAIResponsesClient` → `OpenAIChatClient` (Responses API), `OpenAIChatClient` → `OpenAIChatCompletionClient` (Chat Completions API). Old names remain as deprecated aliases.
-3. **Deprecated classes**: `OpenAIAssistantsClient`, all `AzureOpenAI*Client` classes, `AzureAIClient`, `AzureAIAgentClient`, and `AzureAIProjectAgentProvider` are marked deprecated.
-4. **New `FoundryChatClient`** in azure-ai for Azure AI Foundry Responses API access, built on `RawFoundryChatClient(RawOpenAIChatClient)`.
-5. **All deprecated `AzureOpenAI*` classes** consolidated into a single file (`_deprecated_azure_openai.py`) in the azure-ai package for clean future deletion.
-6. **Core's `agent_framework.openai` and `agent_framework.azure` namespaces** become lazy-loading gateways, preserving backward-compatible import paths while removing hard dependencies.
-7. **Unified `model` parameter** replaces `model_id` (OpenAI), `deployment_name` (Azure OpenAI), and `model_deployment_name` (Azure AI) across all client constructors. The term `model` is intentionally generic: it naturally maps to an OpenAI model name *and* to an Azure OpenAI deployment name, making it straightforward to use `OpenAIChatClient` with either OpenAI or Azure OpenAI backends (via `AsyncAzureOpenAI`). Environment variables are similarly unified (e.g., `OPENAI_MODEL` instead of separate `OPENAI_RESPONSES_MODEL_ID` / `OPENAI_CHAT_MODEL_ID`).
-8. **`FoundryAgent`** replaces the pattern of `Agent(client=AzureAIClient(...))` for connecting to pre-configured agents in Azure AI Foundry (PromptAgents and HostedAgents). The underlying `RawFoundryAgentChatClient` is an implementation detail — most users interact only with `FoundryAgent`. `AzureAIAgentClient` is separately deprecated as it refers to the V1 Agents Service API. See below for design rationale.
-
-### Foundry Agent Design: `FoundryAgentClient` vs `FoundryAgent`
-
-The existing `AzureAIClient` combines two concerns: CRUD lifecycle management (creating/deleting agents on the service) and runtime communication (sending messages via the Responses API). The new design removes CRUD entirely — users connect to agents that already exist in Foundry.
-
-**Two approaches were considered:**
-
-**Option A — `FoundryAgentClient` only (public ChatClient):**
-Users compose `Agent(client=FoundryAgentClient(...), tools=[...])`. This follows the universal `Agent(client=X)` pattern used by every other provider. However, a "client" that wraps a named remote agent (with `agent_name` as a constructor param) is semantically odd — clients typically wrap a model endpoint, not a specific agent.
-
-**Option B — `FoundryAgent` (Agent subclass) + private `_FoundryAgentChatClient` and public `RawFoundryAgentChatClient`:**
-Users write `FoundryAgent(agent_name="my-agent", ...)` for the common case. Internally, `FoundryAgent` creates a `_FoundryAgentChatClient` and passes it to the standard `Agent` base class. For advanced customization, users pass `client_type=RawFoundryAgentChatClient` (or a custom subclass) to control the client middleware layers. The `Agent(client=RawFoundryAgentChatClient(...))` composition pattern still works for users who prefer it.
-
-**Chosen option: Option B**, because:
- The common case (`FoundryAgent(...)`) is a single object with no boilerplate.
- `client_type=` gives full control over client middleware without parameter duplication — the agent forwards connection params to the client internally.
- `RawFoundryAgent(RawAgent)` and `FoundryAgent(Agent)` mirror the established `RawAgent`/`Agent` pattern.
- Runtime validation (only `FunctionTool` allowed) lives in `RawFoundryAgentChatClient._prepare_options`, ensuring it applies regardless of how the client is used — through `FoundryAgent`, `Agent(client=...)`, or any custom composition.
-
-**Public classes:**
- `RawFoundryAgentChatClient(RawOpenAIChatClient)` — Responses API client that injects agent reference and validates tools. Extension point for custom client middleware.
- `RawFoundryAgent(RawAgent)` — Agent without agent-level middleware/telemetry.
- `FoundryAgent(AgentTelemetryLayer, AgentMiddlewareLayer, RawFoundryAgent)` — Recommended production agent.
-
-**Internal (private):**
- `_FoundryAgentChatClient` — Full client with function invocation, chat middleware, and telemetry layers. Created automatically by `FoundryAgent`; users customize via `client_type=RawFoundryAgentChatClient` or a custom subclass.
-
-**Deprecated:**
- `AzureAIClient` — replaced by `FoundryAgent` (which uses `FoundryAgentClient` internally).
- `AzureAIAgentClient` — refers to V1 Agents Service API, no direct replacement.
- `AzureAIProjectAgentProvider` — replaced by `FoundryAgent`.
@@ -57,7 +57,6 @@
    <Project Path="samples/02-agents/Agents/Agent_Step16_Declarative/Agent_Step16_Declarative.csproj" />
    <Project Path="samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj" />
    <Project Path="samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj" />
-    <Project Path="samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Agent_Step19_InFunctionLoopCheckpointing.csproj" />
  </Folder>
  <Folder Name="/Samples/02-agents/DeclarativeAgents/">
    <Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
@@ -77,8 +76,6 @@
    <Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/01_SequentialWorkflow/01_SequentialWorkflow.csproj" />
    <Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/02_ConcurrentWorkflow/02_ConcurrentWorkflow.csproj" />
    <Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/03_WorkflowHITL/03_WorkflowHITL.csproj" />
-    <Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/04_WorkflowMcpTool/04_WorkflowMcpTool.csproj" />
-    <Project Path="samples/04-hosting/DurableWorkflows/AzureFunctions/05_WorkflowAndAgents/05_WorkflowAndAgents.csproj" />
  </Folder>
  <Folder Name="/Samples/GettingStarted/">
    <File Path="samples/GettingStarted/README.md" />
@@ -18,7 +18,6 @@ using OpenTelemetry.Trace;

 #region Setup Telemetry

-// Source name for this sample's custom ActivitySource and Meter; other instrumentation uses their own sources/categories.
 const string SourceName = "OpenTelemetryAspire.ConsoleApp";
 const string ServiceName = "AgentOpenTelemetry";

@@ -41,6 +40,7 @@ var resource = ResourceBuilder.CreateDefault()
 var tracerProviderBuilder = Sdk.CreateTracerProviderBuilder()
    .SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
    .AddSource(SourceName) // Our custom activity source
+    .AddSource("*Microsoft.Agents.AI") // Agent Framework telemetry
    .AddHttpClientInstrumentation() // Capture HTTP calls to OpenAI
    .AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint));

@@ -54,7 +54,8 @@ using var tracerProvider = tracerProviderBuilder.Build();
 // Setup metrics with resource and instrument name filtering
 using var meterProvider = Sdk.CreateMeterProviderBuilder()
    .SetResourceBuilder(ResourceBuilder.CreateDefault().AddService(ServiceName, serviceVersion: "1.0.0"))
-    .AddMeter(SourceName) // Our custom meter source
+    .AddMeter(SourceName) // Our custom meter
+    .AddMeter("*Microsoft.Agents.AI") // Agent Framework metrics
    .AddHttpClientInstrumentation() // HTTP client metrics
    .AddRuntimeInstrumentation() // .NET runtime metrics
    .AddOtlpExporter(options => options.Endpoint = new Uri(otlpEndpoint))
@@ -127,7 +128,7 @@ var agent = new ChatClientAgent(instrumentedChatClient,
    instructions: "You are a helpful assistant that provides concise and informative responses.",
    tools: [AIFunctionFactory.Create(GetWeatherAsync)])
    .AsBuilder()
-    .UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
+    .UseOpenTelemetry(SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
    .Build();

 var session = await agent.CreateSessionAsync();
@@ -1,20 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <OutputType>Exe</OutputType>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-
-    <Nullable>enable</Nullable>
-    <ImplicitUsings>enable</ImplicitUsings>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Azure.AI.OpenAI" />
-    <PackageReference Include="Azure.Identity" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
-  </ItemGroup>
-
-</Project>
@@ -1,226 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-// This sample demonstrates how the ChatClientAgent persists chat history after each individual
-// call to the AI service.
-// When an agent uses tools, FunctionInvokingChatClient may loop multiple times
-// (service call → tool execution → service call), and intermediate messages (tool calls and
-// results) are persisted after each service call. This allows you to inspect or recover them
-// even if the process is interrupted mid-loop, but may also result in chat history that is not
-// yet finalized (e.g., tool calls without results) being persisted, which may be undesirable in some cases.
-//
-// To opt into end-of-run persistence instead (atomic run semantics), set
-// PersistChatHistoryAtEndOfRun = true on ChatClientAgentOptions.
-//
-// The sample runs two multi-turn conversations: one using non-streaming (RunAsync) and one
-// using streaming (RunStreamingAsync), to demonstrate correct behavior in both modes.
-
-using System.ComponentModel;
-using Azure.AI.OpenAI;
-using Azure.Identity;
-using Microsoft.Agents.AI;
-using Microsoft.Extensions.AI;
-using OpenAI.Responses;
-
-var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
-var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
-var store = Environment.GetEnvironmentVariable("AZURE_OPENAI_RESPONSES_STORE") ?? "false";
-
-// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
-// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
-// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
-AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
-
-// Define multiple tools so the model makes several tool calls in a single run.
-[Description("Get the current weather for a city.")]
-static string GetWeather([Description("The city name.")] string city) =>
-    city.ToUpperInvariant() switch
-    {
-        "SEATTLE" => "Seattle: 55°F, cloudy with light rain.",
-        "NEW YORK" => "New York: 72°F, sunny and warm.",
-        "LONDON" => "London: 48°F, overcast with fog.",
-        "DUBLIN" => "Dublin: 43°F, overcast with fog.",
-        _ => $"{city}: weather data not available."
-    };
-
-[Description("Get the current time in a city.")]
-static string GetTime([Description("The city name.")] string city) =>
-    city.ToUpperInvariant() switch
-    {
-        "SEATTLE" => "Seattle: 9:00 AM PST",
-        "NEW YORK" => "New York: 12:00 PM EST",
-        "LONDON" => "London: 5:00 PM GMT",
-        "DUBLIN" => "Dublin: 5:00 PM GMT",
-        _ => $"{city}: time data not available."
-    };
-
-// Create the agent — per-service-call persistence is the default behavior.
-// The in-memory ChatHistoryProvider is used by default when the service does not require service stored chat
-// history, so for those cases, we can inspect the chat history via session.TryGetInMemoryChatHistory().
-IChatClient chatClient = string.Equals(store, "TRUE", StringComparison.OrdinalIgnoreCase) ?
-    openAIClient.GetResponsesClient().AsIChatClient(deploymentName) :
-    openAIClient.GetResponsesClient().AsIChatClientWithStoredOutputDisabled(deploymentName);
-AIAgent agent = chatClient.AsAIAgent(
-    new ChatClientAgentOptions
-    {
-        Name = "WeatherAssistant",
-        ChatOptions = new()
-        {
-            Instructions = "You are a helpful assistant. When asked about multiple cities, call the appropriate tool for each city.",
-            Tools = [AIFunctionFactory.Create(GetWeather), AIFunctionFactory.Create(GetTime)]
-        },
-    });
-
-await RunNonStreamingAsync();
-await RunStreamingAsync();
-
-async Task RunNonStreamingAsync()
-{
-    int lastChatHistorySize = 0;
-    string lastConversationId = string.Empty;
-
-    Console.ForegroundColor = ConsoleColor.Yellow;
-    Console.WriteLine("\n=== Non-Streaming Mode ===");
-    Console.ResetColor();
-
-    AgentSession session = await agent.CreateSessionAsync();
-
-    // First turn — ask about multiple cities so the model calls tools.
-    const string Prompt = "What's the weather and time in Seattle, New York, and London?";
-    PrintUserMessage(Prompt);
-
-    var response = await agent.RunAsync(Prompt, session);
-    PrintAgentResponse(response.Text);
-    PrintChatHistory(session, "After run", ref lastChatHistorySize, ref lastConversationId);
-
-    // Second turn — follow-up to verify chat history is correct.
-    const string FollowUp1 = "And Dublin?";
-    PrintUserMessage(FollowUp1);
-
-    response = await agent.RunAsync(FollowUp1, session);
-    PrintAgentResponse(response.Text);
-    PrintChatHistory(session, "After second run", ref lastChatHistorySize, ref lastConversationId);
-
-    // Third turn — follow-up to verify chat history is correct.
-    const string FollowUp2 = "Which city is the warmest?";
-    PrintUserMessage(FollowUp2);
-
-    response = await agent.RunAsync(FollowUp2, session);
-    PrintAgentResponse(response.Text);
-    PrintChatHistory(session, "After third run", ref lastChatHistorySize, ref lastConversationId);
-}
-
-async Task RunStreamingAsync()
-{
-    int lastChatHistorySize = 0;
-    string lastConversationId = string.Empty;
-
-    Console.ForegroundColor = ConsoleColor.Yellow;
-    Console.WriteLine("\n=== Streaming Mode ===");
-    Console.ResetColor();
-
-    AgentSession session = await agent.CreateSessionAsync();
-
-    // First turn — ask about multiple cities so the model calls tools.
-    const string Prompt = "What's the weather and time in Seattle, New York, and London?";
-    PrintUserMessage(Prompt);
-
-    Console.ForegroundColor = ConsoleColor.Cyan;
-    Console.Write("\n[Agent] ");
-    Console.ResetColor();
-
-    await foreach (var update in agent.RunStreamingAsync(Prompt, session))
-    {
-        Console.Write(update);
-
-        // During streaming we should be able to see updates to the chat history
-        // before the full run completes, as each service call is made and persisted.
-        PrintChatHistory(session, "During run", ref lastChatHistorySize, ref lastConversationId);
-    }
-
-    Console.WriteLine();
-    PrintChatHistory(session, "After run", ref lastChatHistorySize, ref lastConversationId);
-
-    // Second turn — follow-up to verify chat history is correct.
-    const string FollowUp1 = "And Dublin?";
-    PrintUserMessage(FollowUp1);
-
-    Console.ForegroundColor = ConsoleColor.Cyan;
-    Console.Write("\n[Agent] ");
-    Console.ResetColor();
-
-    await foreach (var update in agent.RunStreamingAsync(FollowUp1, session))
-    {
-        Console.Write(update);
-
-        // During streaming we should be able to see updates to the chat history
-        // before the full run completes, as each service call is made and persisted.
-        PrintChatHistory(session, "During second run", ref lastChatHistorySize, ref lastConversationId);
-    }
-
-    Console.WriteLine();
-    PrintChatHistory(session, "After second run", ref lastChatHistorySize, ref lastConversationId);
-
-    // Third turn — follow-up to verify chat history is correct.
-    const string FollowUp2 = "Which city is the warmest?";
-    PrintUserMessage(FollowUp2);
-
-    Console.ForegroundColor = ConsoleColor.Cyan;
-    Console.Write("\n[Agent] ");
-    Console.ResetColor();
-
-    await foreach (var update in agent.RunStreamingAsync(FollowUp2, session))
-    {
-        Console.Write(update);
-
-        // During streaming we should be able to see updates to the chat history
-        // before the full run completes, as each service call is made and persisted.
-        PrintChatHistory(session, "During third run", ref lastChatHistorySize, ref lastConversationId);
-    }
-
-    Console.WriteLine();
-    PrintChatHistory(session, "After third run", ref lastChatHistorySize, ref lastConversationId);
-}
-
-void PrintUserMessage(string message)
-{
-    Console.ForegroundColor = ConsoleColor.Cyan;
-    Console.Write("\n[User] ");
-    Console.ResetColor();
-    Console.WriteLine(message);
-}
-
-void PrintAgentResponse(string? text)
-{
-    Console.ForegroundColor = ConsoleColor.Cyan;
-    Console.Write("\n[Agent] ");
-    Console.ResetColor();
-    Console.WriteLine(text);
-}
-
-// Helper to print the current chat history from the session.
-void PrintChatHistory(AgentSession session, string label, ref int lastChatHistorySize, ref string lastConversationId)
-{
-    if (session.TryGetInMemoryChatHistory(out var history) && history.Count != lastChatHistorySize)
-    {
-        Console.ForegroundColor = ConsoleColor.DarkGray;
-        Console.WriteLine($"\n  [{label} — Chat history: {history.Count} message(s)]");
-        foreach (var msg in history)
-        {
-            var preview = msg.Text?.Length > 80 ? msg.Text[..80] + "…" : msg.Text;
-            var contentTypes = string.Join(", ", msg.Contents.Select(c => c.GetType().Name));
-            Console.WriteLine($"    {msg.Role,-12} | {(string.IsNullOrWhiteSpace(preview) ? $"[{contentTypes}]" : preview)}");
-        }
-
-        Console.ResetColor();
-
-        lastChatHistorySize = history.Count;
-    }
-
-    if (session is ChatClientAgentSession ccaSession && ccaSession.ConversationId is not null && ccaSession.ConversationId != lastConversationId)
-    {
-        Console.ForegroundColor = ConsoleColor.DarkGray;
-        Console.WriteLine($"  [{label} — Conversation ID: {ccaSession.ConversationId}]");
-        Console.ResetColor();
-        lastConversationId = ccaSession.ConversationId;
-    }
-}
@@ -1,63 +0,0 @@
-# In-Function-Loop Checkpointing
-
-This sample demonstrates how `ChatClientAgent` persists chat history after each individual call to the AI service by default. This per-service-call persistence ensures intermediate progress is saved during the function invocation loop.
-
-## What This Sample Shows
-
-When an agent uses tools, the `FunctionInvokingChatClient` loops multiple times (service call → tool execution → service call → …). By default, chat history is persisted after each service call via the `ChatHistoryPersistingChatClient` decorator:
-
- A `ChatHistoryPersistingChatClient` decorator is automatically inserted into the chat client pipeline
- After each service call, the decorator notifies the `ChatHistoryProvider` (and any `AIContextProvider` instances) with the new messages
- Only **new** messages are sent to providers on each notification — messages that were already persisted in an earlier call within the same run are deduplicated automatically
-
-To opt into end-of-run persistence instead (atomic run semantics), set `PersistChatHistoryAtEndOfRun = true` on `ChatClientAgentOptions`. In that mode, the decorator marks messages with metadata rather than persisting them immediately, and `ChatClientAgent` persists only the marked messages at the end of the run.
-
-Per-service-call persistence is useful for:
- **Crash recovery** — if the process is interrupted mid-loop, the intermediate tool calls and results are already persisted
- **Observability** — you can inspect the chat history while the agent is still running (e.g., during streaming)
- **Long-running tool loops** — agents with many sequential tool calls benefit from incremental persistence
-
-## How It Works
-
-The sample asks the agent about the weather and time in three cities. The model calls the `GetWeather` and `GetTime` tools for each city, resulting in multiple service calls within a single `RunStreamingAsync` invocation. After the run completes, the sample prints the full chat history to show all the intermediate messages that were persisted along the way.
-
-### Pipeline Architecture
-
-```
-ChatClientAgent
-  └─ FunctionInvokingChatClient    (handles tool call loop)
-       └─ ChatHistoryPersistingChatClient  (persists after each service call)
-            └─ Leaf IChatClient            (Azure OpenAI)
-```
-
-## Prerequisites
-
- .NET 10 SDK or later
- Azure OpenAI service endpoint and model deployment
- Azure CLI installed and authenticated
-
-**Note**: This sample uses `DefaultAzureCredential`. Sign in with `az login` before running. For production, prefer a specific credential such as `ManagedIdentityCredential`. For more information, see the [Azure CLI authentication documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
-
-## Environment Variables
-
-```powershell
-$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"  # Required
-$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o-mini"                       # Optional, defaults to gpt-4o-mini
-```
-
-## Running the Sample
-
-```powershell
-cd dotnet/samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing
-dotnet run
-```
-
-## Expected Behavior
-
-The sample runs two conversation turns:
-
-1. **First turn** — asks about weather and time in three cities. The model calls `GetWeather` and `GetTime` tools (potentially in parallel or sequentially), then provides a summary. The chat history dump after the run shows all the intermediate tool call and result messages.
-
-2. **Second turn** — asks a follow-up question ("Which city is the warmest?") that uses the persisted conversation context. The chat history dump shows the full accumulated conversation.
-
-The chat history printout uses `session.TryGetInMemoryChatHistory()` to inspect the in-memory storage.
@@ -45,7 +45,6 @@ Before you begin, ensure you have the following prerequisites:
 |[Declarative agent](./Agent_Step16_Declarative/)|This sample demonstrates how to declaratively define an agent.|
 |[Providing additional AI Context to an agent using multiple AIContextProviders](./Agent_Step17_AdditionalAIContext/)|This sample demonstrates how to inject additional AI context into a ChatClientAgent using multiple custom AIContextProvider components that are attached to the agent.|
 |[Using compaction pipeline with an agent](./Agent_Step18_CompactionPipeline/)|This sample demonstrates how to use a compaction pipeline to efficiently limit the size of the conversation history for an agent.|
-|[In-function-loop checkpointing](./Agent_Step19_InFunctionLoopCheckpointing/)|This sample demonstrates how to persist chat history after each service call during a tool-calling loop, enabling crash recovery and mid-run observability.|

 ## Running the samples from the console

@@ -1,35 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-  <PropertyGroup>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-    <AzureFunctionsVersion>v4</AzureFunctionsVersion>
-    <OutputType>Exe</OutputType>
-    <ImplicitUsings>enable</ImplicitUsings>
-    <Nullable>enable</Nullable>
-    <!-- The Functions build tools don't like namespaces that start with a number -->
-    <AssemblyName>WorkflowMcpTool</AssemblyName>
-    <RootNamespace>WorkflowMcpTool</RootNamespace>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <FrameworkReference Include="Microsoft.AspNetCore.App" />
-  </ItemGroup>
-
-  <!-- Azure Functions packages -->
-  <ItemGroup>
-    <PackageReference Include="Microsoft.Azure.Functions.Worker" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask.AzureManaged" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Sdk" />
-  </ItemGroup>
-
-  <!-- Local projects that should be switched to package references when using the sample outside of this MAF repo -->
-  <!--
-  <ItemGroup>
-    <PackageReference Include="Microsoft.Agents.AI.Hosting.AzureFunctions" />
-  </ItemGroup>
-  -->
-  <ItemGroup>
-    <ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Hosting.AzureFunctions\Microsoft.Agents.AI.Hosting.AzureFunctions.csproj" />
-  </ItemGroup>
-</Project>
@@ -1,59 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using Microsoft.Agents.AI.Workflows;
-
-namespace WorkflowMcpTool;
-
-internal sealed class TranslateText() : Executor<string, TranslationResult>("TranslateText")
-{
-    public override ValueTask<TranslationResult> HandleAsync(
-        string message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine($"[Activity] TranslateText: '{message}'");
-        return ValueTask.FromResult(new TranslationResult(message, message.ToUpperInvariant()));
-    }
-}
-
-internal sealed class FormatOutput() : Executor<TranslationResult, string>("FormatOutput")
-{
-    public override ValueTask<string> HandleAsync(
-        TranslationResult message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine("[Activity] FormatOutput: Formatting result");
-        return ValueTask.FromResult($"Original: {message.Original} => Translated: {message.Translated}");
-    }
-}
-
-internal sealed class LookupOrder() : Executor<string, OrderInfo>("LookupOrder")
-{
-    public override ValueTask<OrderInfo> HandleAsync(
-        string message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine($"[Activity] LookupOrder: '{message}'");
-        return ValueTask.FromResult(new OrderInfo(message, "Alice Johnson", "Wireless Headphones", Quantity: 2, UnitPrice: 49.99m));
-    }
-}
-
-internal sealed class EnrichOrder() : Executor<OrderInfo, OrderSummary>("EnrichOrder")
-{
-    public override ValueTask<OrderSummary> HandleAsync(
-        OrderInfo message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine($"[Activity] EnrichOrder: '{message.OrderId}'");
-        return ValueTask.FromResult(new OrderSummary(message, TotalPrice: message.Quantity * message.UnitPrice, Status: "Confirmed"));
-    }
-}
-
-internal sealed record TranslationResult(string Original, string Translated);
-
-internal sealed record OrderInfo(string OrderId, string CustomerName, string Product, int Quantity, decimal UnitPrice);
-
-internal sealed record OrderSummary(OrderInfo Order, decimal TotalPrice, string Status);
@@ -1,44 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-// This sample demonstrates how to expose a durable workflow as an MCP (Model Context Protocol) tool.
-// When using AddWorkflow with exposeMcpToolTrigger: true, the Functions host will automatically
-// generate a remote MCP endpoint for the app at /runtime/webhooks/mcp with a workflow-specific
-// tool name. MCP-compatible clients can then invoke the workflow as a tool.
-
-using Microsoft.Agents.AI.Hosting.AzureFunctions;
-using Microsoft.Agents.AI.Workflows;
-using Microsoft.Azure.Functions.Worker.Builder;
-using Microsoft.Extensions.Hosting;
-using WorkflowMcpTool;
-
-// Define executors
-TranslateText translateText = new();
-FormatOutput formatOutput = new();
-LookupOrder lookupOrder = new();
-EnrichOrder enrichOrder = new();
-
-// Build a simple workflow: TranslateText -> FormatOutput
-Workflow translateWorkflow = new WorkflowBuilder(translateText)
-    .WithName("Translate")
-    .WithDescription("Translate text to uppercase and format the result")
-    .AddEdge(translateText, formatOutput)
-    .Build();
-
-// Build a workflow that returns a POCO: LookupOrder -> EnrichOrder
-Workflow orderLookupWorkflow = new WorkflowBuilder(lookupOrder)
-    .WithName("OrderLookup")
-    .WithDescription("Look up an order by ID and return enriched order details")
-    .AddEdge(lookupOrder, enrichOrder)
-    .Build();
-
-using IHost app = FunctionsApplication
-    .CreateBuilder(args)
-    .ConfigureFunctionsWebApplication()
-    .ConfigureDurableWorkflows(workflows =>
-    {
-        // Expose both workflows as MCP tool triggers.
-        workflows.AddWorkflow(translateWorkflow, exposeStatusEndpoint: false, exposeMcpToolTrigger: true);
-        workflows.AddWorkflow(orderLookupWorkflow, exposeStatusEndpoint: false, exposeMcpToolTrigger: true);
-    })
-    .Build();
-app.Run();
@@ -1,81 +0,0 @@
-# Workflow as MCP Tool Sample
-
-This sample demonstrates how to expose durable workflows as [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) tools, enabling MCP-compatible clients to invoke workflows directly.
-
-## Key Concepts Demonstrated
-
- **Workflow as MCP Tool**: Expose workflows as callable MCP tools using `exposeMcpToolTrigger: true`
- **MCP Server Hosting**: The Azure Functions host automatically generates a remote MCP endpoint at `/runtime/webhooks/mcp`
- **String and POCO Results**: Shows workflows returning both plain strings and structured JSON objects
-
-## Sample Architecture
-
-The sample creates two workflows exposed as MCP tools:
-
-### Translate Workflow (returns a string)
-
-| Executor | Input | Output | Description |
-|----------|-------|--------|-------------|
-| **TranslateText** | `string` | `TranslationResult` | Converts input text to uppercase |
-| **FormatOutput** | `TranslationResult` | `string` | Formats the result into a readable string |
-
-### OrderLookup Workflow (returns a POCO)
-
-| Executor | Input | Output | Description |
-|----------|-------|--------|-------------|
-| **LookupOrder** | `string` | `OrderInfo` | Looks up an order by ID |
-| **EnrichOrder** | `OrderInfo` | `OrderSummary` | Adds computed fields (total price, status) |
-
-## Environment Setup
-
-See the [README.md](../../README.md) file in the parent directory for complete setup instructions, including:
-
- Prerequisites installation
- Durable Task Scheduler setup
- Storage emulator configuration
-
-For this sample, you'll also need [Node.js](https://nodejs.org/en/download) to use the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector).
-
-## Running the Sample
-
-1. **Start the Function App**:
-
-   ```bash
-   cd dotnet/samples/04-hosting/DurableWorkflows/AzureFunctions/04_WorkflowMcpTool
-   func start
-   ```
-
-2. **Note the MCP Server Endpoint**: When the app starts, you'll see the MCP server endpoint in the terminal output:
-
-   ```text
-   MCP server endpoint:  http://localhost:7071/runtime/webhooks/mcp
-   ```
-
-## Invoking Workflows via MCP Inspector
-
-1. Install and run the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector):
-
-   ```bash
-   npx @modelcontextprotocol/inspector
-   ```
-
-2. Connect to the MCP server endpoint:
-   - For **Transport Type**, select **"Streamable HTTP"**
-   - For **URL**, enter `http://localhost:7071/runtime/webhooks/mcp`
-   - Click the **Connect** button
-
-3. Click the **List Tools** button. You should see two tools: `Translate` and `OrderLookup`.
-
-4. Test the **Translate** tool (returns a plain string):
-   - Select the `Translate` tool
-   - Set `hello world` as the `input` parameter
-   - Click **Run Tool**
-   - Expected result: `Original: hello world => Translated: HELLO WORLD`
-
-5. Test the **OrderLookup** tool (returns a JSON object):
-   - Select the `OrderLookup` tool
-   - Set `ORD-2025-42` as the `input` parameter
-   - Click **Run Tool**
-   - Expected result: A JSON object containing order details such as `OrderId`, `CustomerName`, `Product`, `TotalPrice`, and `Status`
-
-You'll see the workflow executor activities logged in the terminal where you ran `func start`.
@@ -1,20 +0,0 @@
-{
-  "version": "2.0",
-  "logging": {
-    "logLevel": {
-      "Microsoft.Agents.AI.DurableTask": "Information",
-      "Microsoft.Agents.AI.Hosting.AzureFunctions": "Information",
-      "DurableTask": "Information",
-      "Microsoft.DurableTask": "Information"
-    }
-  },
-  "extensions": {
-    "durableTask": {
-      "hubName": "default",
-      "storageProvider": {
-        "type": "AzureManaged",
-        "connectionStringName": "DURABLE_TASK_SCHEDULER_CONNECTION_STRING"
-      }
-    }
-  }
-}
@@ -1,8 +0,0 @@
-{
-  "IsEncrypted": false,
-  "Values": {
-    "FUNCTIONS_WORKER_RUNTIME": "dotnet-isolated",
-    "AzureWebJobsStorage": "UseDevelopmentStorage=true",
-    "DURABLE_TASK_SCHEDULER_CONNECTION_STRING": "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
-  }
-}
@@ -1,42 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-  <PropertyGroup>
-    <TargetFrameworks>net10.0</TargetFrameworks>
-    <AzureFunctionsVersion>v4</AzureFunctionsVersion>
-    <OutputType>Exe</OutputType>
-    <ImplicitUsings>enable</ImplicitUsings>
-    <Nullable>enable</Nullable>
-    <!-- The Functions build tools don't like namespaces that start with a number -->
-    <AssemblyName>WorkflowAndAgents</AssemblyName>
-    <RootNamespace>WorkflowAndAgents</RootNamespace>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <FrameworkReference Include="Microsoft.AspNetCore.App" />
-  </ItemGroup>
-
-  <!-- Azure Functions packages -->
-  <ItemGroup>
-    <PackageReference Include="Microsoft.Azure.Functions.Worker" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.DurableTask.AzureManaged" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" />
-    <PackageReference Include="Microsoft.Azure.Functions.Worker.Sdk" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <PackageReference Include="Azure.AI.OpenAI" />
-    <PackageReference Include="Azure.Identity" />
-  </ItemGroup>
-
-  <!-- Local projects that should be switched to package references when using the sample outside of this MAF repo -->
-  <!--
-  <ItemGroup>
-    <PackageReference Include="Microsoft.Agents.AI.Hosting.AzureFunctions" />
-    <PackageReference Include="Microsoft.Agents.AI.OpenAI" />
-  </ItemGroup>
-  -->
-  <ItemGroup>
-    <ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.Hosting.AzureFunctions\Microsoft.Agents.AI.Hosting.AzureFunctions.csproj" />
-    <ProjectReference Include="..\..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
-  </ItemGroup>
-</Project>
@@ -1,31 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using Microsoft.Agents.AI.Workflows;
-
-namespace WorkflowAndAgents;
-
-internal sealed class TranslateText() : Executor<string, TranslationResult>("TranslateText")
-{
-    public override ValueTask<TranslationResult> HandleAsync(
-        string message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine($"[Activity] TranslateText: '{message}'");
-        return ValueTask.FromResult(new TranslationResult(message, message.ToUpperInvariant()));
-    }
-}
-
-internal sealed class FormatOutput() : Executor<TranslationResult, string>("FormatOutput")
-{
-    public override ValueTask<string> HandleAsync(
-        TranslationResult message,
-        IWorkflowContext context,
-        CancellationToken cancellationToken = default)
-    {
-        Console.WriteLine("[Activity] FormatOutput: Formatting result");
-        return ValueTask.FromResult($"Original: {message.Original} => Translated: {message.Translated}");
-    }
-}
-
-internal sealed record TranslationResult(string Original, string Translated);
@@ -1,64 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-// This sample demonstrates using ConfigureDurableOptions to register BOTH agents AND workflows
-// in a single Azure Functions app. It uses a workflow to translate text and a standalone AI agent
-// accessible via HTTP and MCP tool triggers.
-
-#pragma warning disable IDE0002 // Simplify Member Access
-
-using Azure;
-using Azure.AI.OpenAI;
-using Azure.Identity;
-using Microsoft.Agents.AI;
-using Microsoft.Agents.AI.Hosting.AzureFunctions;
-using Microsoft.Agents.AI.Workflows;
-using Microsoft.Azure.Functions.Worker.Builder;
-using Microsoft.Extensions.Hosting;
-using OpenAI.Chat;
-using WorkflowAndAgents;
-
-// Get the Azure OpenAI endpoint and deployment name from environment variables.
-string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
-    ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
-string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME")
-    ?? throw new InvalidOperationException("AZURE_OPENAI_DEPLOYMENT_NAME is not set.");
-
-// Use Azure Key Credential if provided, otherwise use Azure CLI Credential.
-string? azureOpenAiKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
-AzureOpenAIClient client = !string.IsNullOrEmpty(azureOpenAiKey)
-    ? new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(azureOpenAiKey))
-    : new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential());
-
-ChatClient chatClient = client.GetChatClient(deploymentName);
-
-// Define a standalone AI agent
-AIAgent assistant = chatClient.AsAIAgent(
-    "You are a helpful assistant. Answer questions clearly and concisely.",
-    "Assistant",
-    description: "A general-purpose helpful assistant.");
-
-// Define workflow executors
-TranslateText translateText = new();
-FormatOutput formatOutput = new();
-
-// Build a workflow: TranslateText -> FormatOutput
-Workflow translateWorkflow = new WorkflowBuilder(translateText)
-    .WithName("Translate")
-    .WithDescription("Translate text to uppercase and format the result")
-    .AddEdge(translateText, formatOutput)
-    .Build();
-
-// Use ConfigureDurableOptions to register both agents and workflows together
-using IHost app = FunctionsApplication
-    .CreateBuilder(args)
-    .ConfigureFunctionsWebApplication()
-    .ConfigureDurableOptions(options =>
-    {
-        // Register the standalone agent with HTTP and MCP tool triggers
-        options.Agents.AddAIAgent(assistant, enableHttpTrigger: true, enableMcpToolTrigger: true);
-
-        // Register the workflow with an HTTP endpoint and MCP tool trigger
-        options.Workflows.AddWorkflow(translateWorkflow, exposeStatusEndpoint: false, exposeMcpToolTrigger: true);
-    })
-    .Build();
-app.Run();
@@ -1,76 +0,0 @@
-# Workflow and Agents Sample
-
-This sample demonstrates how to use `ConfigureDurableOptions` to register **both** AI agents **and** workflows in a single Azure Functions app. This is the recommended approach when your application needs both standalone agents and orchestrated workflows.
-
-## Key Concepts Demonstrated
-
- **Unified Configuration**: Use `ConfigureDurableOptions` to register agents and workflows together
- **Standalone Agent**: An AI agent accessible via HTTP and MCP tool triggers
- **Workflow**: A simple text translation workflow also exposed as an MCP tool
- **Mixed Triggers**: Both agents and workflows coexist in the same Functions host
-
-## Sample Architecture
-
-### Standalone Agent
-
-| Agent | Description |
-|-------|-------------|
-| **Assistant** | A general-purpose AI assistant accessible via HTTP (`/agents/Assistant/run`) and as an MCP tool |
-
-### Translate Workflow
-
-| Executor | Input | Output | Description |
-|----------|-------|--------|-------------|
-| **TranslateText** | `string` | `TranslationResult` | Converts input text to uppercase |
-| **FormatOutput** | `TranslationResult` | `string` | Formats the result into a readable string |
-
-## Environment Setup
-
-See the [README.md](../../README.md) file in the parent directory for complete setup instructions, including:
-
- Prerequisites installation
- Durable Task Scheduler setup
- Storage emulator configuration
-
-This sample also requires Azure OpenAI credentials. Set the following in `local.settings.json`:
-
- `AZURE_OPENAI_ENDPOINT`: Your Azure OpenAI endpoint URL
- `AZURE_OPENAI_DEPLOYMENT_NAME`: Your chat model deployment name
- `AZURE_OPENAI_API_KEY` (optional): If not set, Azure CLI credential is used
-
-## Running the Sample
-
-1. **Start the Function App**:
-
-   ```bash
-   cd dotnet/samples/04-hosting/DurableWorkflows/AzureFunctions/05_WorkflowAndAgents
-   func start
-   ```
-
-2. **Expected Functions**: When the app starts, you should see functions for both the agent and the workflow:
-
-   - `dafx-Assistant` (entity trigger for the agent)
-   - `http-Assistant` (HTTP trigger for the agent)
-   - `mcptool-Assistant` (MCP tool trigger for the agent)
-   - `wf-Translate` (orchestration trigger for the workflow)
-   - `mcptool-wf-Translate` (MCP tool trigger for the workflow)
-
-## Invoking the Agent via HTTP
-
-```bash
-curl -X POST http://localhost:7071/agents/Assistant/run \
-  -H "Content-Type: application/json" \
-  -d '{"query": "What is the capital of France?"}'
-```
-
-## Invoking via MCP Inspector
-
-1. Install and run the [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector):
-
-   ```bash
-   npx @modelcontextprotocol/inspector
-   ```
-
-2. Connect to `http://localhost:7071/runtime/webhooks/mcp` using **Streamable HTTP** transport.
-
-3. Click **List Tools** to see both the `Assistant` agent tool and the `Translate` workflow tool.
@@ -1,20 +0,0 @@
-{
-  "version": "2.0",
-  "logging": {
-    "logLevel": {
-      "Microsoft.Agents.AI.DurableTask": "Information",
-      "Microsoft.Agents.AI.Hosting.AzureFunctions": "Information",
-      "DurableTask": "Information",
-      "Microsoft.DurableTask": "Information"
-    }
-  },
-  "extensions": {
-    "durableTask": {
-      "hubName": "default",
-      "storageProvider": {
-        "type": "AzureManaged",
-        "connectionStringName": "DURABLE_TASK_SCHEDULER_CONNECTION_STRING"
-      }
-    }
-  }
-}
@@ -1,10 +0,0 @@
-{
-  "IsEncrypted": false,
-  "Values": {
-    "FUNCTIONS_WORKER_RUNTIME": "dotnet-isolated",
-    "AzureWebJobsStorage": "UseDevelopmentStorage=true",
-    "DURABLE_TASK_SCHEDULER_CONNECTION_STRING": "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None",
-    "AZURE_OPENAI_ENDPOINT": "<AZURE_OPENAI_ENDPOINT>",
-    "AZURE_OPENAI_DEPLOYMENT_NAME": "<AZURE_OPENAI_DEPLOYMENT_NAME>"
-  }
-}
@@ -48,4 +48,3 @@ $env:DURABLE_TASK_SCHEDULER_CONNECTION_STRING = "AccountEndpoint=http://localhos
 | [01_SequentialWorkflow](AzureFunctions/01_SequentialWorkflow/) | Sequential workflow hosted in Azure Functions |
 | [02_ConcurrentWorkflow](AzureFunctions/02_ConcurrentWorkflow/) | Concurrent workflow hosted in Azure Functions |
 | [03_WorkflowHITL](AzureFunctions/03_WorkflowHITL/) | Human-in-the-loop workflow hosted in Azure Functions |
-| [04_WorkflowMcpTool](AzureFunctions/04_WorkflowMcpTool/) | Workflow exposed as an MCP tool |
@@ -167,20 +167,6 @@ internal sealed class BuiltInFunctionExecutor : IFunctionExecutor
            return;
        }

-        if (context.FunctionDefinition.EntryPoint == BuiltInFunctions.RunWorkflowMcpToolFunctionEntryPoint)
-        {
-            if (mcpToolInvocationContext is null)
-            {
-                throw new InvalidOperationException($"MCP tool invocation context binding is missing for the invocation {context.InvocationId}.");
-            }
-
-            context.GetInvocationResult().Value = await BuiltInFunctions.RunWorkflowMcpToolAsync(
-                mcpToolInvocationContext,
-                durableTaskClient,
-                context);
-            return;
-        }
-
        throw new InvalidOperationException($"Unsupported function entry point '{context.FunctionDefinition.EntryPoint}' for invocation {context.InvocationId}.");
    }

@@ -29,7 +29,6 @@ internal static class BuiltInFunctions
    internal static readonly string InvokeWorkflowActivityFunctionEntryPoint = $"{typeof(BuiltInFunctions).FullName!}.{nameof(InvokeWorkflowActivityAsync)}";
    internal static readonly string GetWorkflowStatusHttpFunctionEntryPoint = $"{typeof(BuiltInFunctions).FullName!}.{nameof(GetWorkflowStatusAsync)}";
    internal static readonly string RespondToWorkflowHttpFunctionEntryPoint = $"{typeof(BuiltInFunctions).FullName!}.{nameof(RespondToWorkflowAsync)}";
-    internal static readonly string RunWorkflowMcpToolFunctionEntryPoint = $"{typeof(BuiltInFunctions).FullName!}.{nameof(RunWorkflowMcpToolAsync)}";

 #pragma warning disable IL3000 // Avoid accessing Assembly file path when publishing as a single file - Azure Functions does not use single-file publishing
    internal static readonly string ScriptFile = Path.GetFileName(typeof(BuiltInFunctions).Assembly.Location);
@@ -379,55 +378,6 @@ internal static class BuiltInFunctions
        return agentResponse.Text;
    }

-    /// <summary>
-    /// Runs a workflow via MCP tool trigger.
-    /// Extracts the <c>input</c> argument, schedules a new orchestration, waits for completion, and returns the output.
-    /// </summary>
-    public static async Task<string?> RunWorkflowMcpToolAsync(
-        [McpToolTrigger("BuiltInWorkflowMcpTool")] ToolInvocationContext context,
-        [DurableClient] DurableTaskClient client,
-        FunctionContext functionContext)
-    {
-        if (context.Arguments is null)
-        {
-            throw new ArgumentException("MCP Tool invocation is missing required arguments.");
-        }
-
-        if (!context.Arguments.TryGetValue("input", out object? inputObj) || inputObj is not string input)
-        {
-            throw new ArgumentException("MCP Tool invocation is missing required 'input' argument of type string.");
-        }
-
-        string workflowName = context.Name;
-        string orchestrationFunctionName = WorkflowNamingHelper.ToOrchestrationFunctionName(workflowName);
-
-        DurableWorkflowInput<string> orchestrationInput = new() { Input = input };
-        string instanceId = await client.ScheduleNewOrchestrationInstanceAsync(orchestrationFunctionName, orchestrationInput);
-
-        OrchestrationMetadata? metadata = await client.WaitForInstanceCompletionAsync(
-            instanceId,
-            getInputsAndOutputs: true,
-            cancellation: functionContext.CancellationToken);
-
-        if (metadata is null)
-        {
-            throw new InvalidOperationException($"Workflow orchestration '{instanceId}' returned no metadata.");
-        }
-
-        if (metadata.RuntimeStatus is OrchestrationRuntimeStatus.Failed)
-        {
-            string errorMessage = metadata.FailureDetails?.ErrorMessage ?? "Unknown error";
-            throw new InvalidOperationException($"Workflow orchestration '{instanceId}' failed: {errorMessage}");
-        }
-
-        if (metadata.RuntimeStatus is not OrchestrationRuntimeStatus.Completed)
-        {
-            throw new InvalidOperationException($"Workflow orchestration '{instanceId}' ended with unexpected status '{metadata.RuntimeStatus}'.");
-        }
-
-        return metadata.ReadOutputAs<DurableWorkflowResult>()?.Result;
-    }
-
    /// <summary>
    /// Creates an error response with the specified status code and error message.
    /// </summary>
@@ -2,7 +2,6 @@

 ## [Unreleased]

- Added MCP tool trigger support for durable workflows ([#4768](https://github.com/microsoft/agent-framework/pull/4768))
 - Added Azure Functions hosting support for durable workflows ([#4436](https://github.com/microsoft/agent-framework/pull/4436))

 ## v1.0.0-preview.251219.1
@@ -6,8 +6,7 @@ namespace Microsoft.Agents.AI.Hosting.AzureFunctions;

 /// <summary>
 /// Provides access to agent-specific options for functions agents by name.
-/// Returns <see langword="false"/> when no explicit options have been configured for an agent,
-/// which distinguishes standalone agents from those auto-registered by workflows.
+/// Returns default options (HTTP trigger enabled, MCP tool disabled) when no explicit options were configured.
 /// </summary>
 internal sealed class DefaultFunctionsAgentOptionsProvider(IReadOnlyDictionary<string, FunctionsAgentOptions> functionsAgentOptions)
    : IFunctionsAgentOptionsProvider
@@ -15,19 +14,32 @@ internal sealed class DefaultFunctionsAgentOptionsProvider(IReadOnlyDictionary<s
    private readonly IReadOnlyDictionary<string, FunctionsAgentOptions> _functionsAgentOptions =
        functionsAgentOptions ?? throw new ArgumentNullException(nameof(functionsAgentOptions));

+    // Default options. HTTP trigger enabled, MCP tool disabled.
+    private static readonly FunctionsAgentOptions s_defaultOptions = new()
+    {
+        HttpTrigger = { IsEnabled = true },
+        McpToolTrigger = { IsEnabled = false }
+    };
+
    /// <summary>
    /// Attempts to retrieve the options associated with the specified agent name.
-    /// Returns <see langword="false"/> when no options have been explicitly configured for the agent.
+    /// If not found, a default options instance (with HTTP trigger enabled) is returned.
    /// </summary>
    /// <param name="agentName">The name of the agent whose options are to be retrieved. Cannot be null or empty.</param>
-    /// <param name="options">
-    /// When this method returns <see langword="true"/>, contains the options for the specified agent;
-    /// otherwise, <see langword="null"/>.
-    /// </param>
-    /// <returns><see langword="true"/> if options were found for the agent; otherwise, <see langword="false"/>.</returns>
+    /// <param name="options">The options for the specified agent. Will never be null.</param>
+    /// <returns>Always true. Returns configured options if present; otherwise default fallback options.</returns>
    public bool TryGet(string agentName, [NotNullWhen(true)] out FunctionsAgentOptions? options)
    {
        ArgumentException.ThrowIfNullOrEmpty(agentName);
-        return this._functionsAgentOptions.TryGetValue(agentName, out options);
+
+        if (this._functionsAgentOptions.TryGetValue(agentName, out FunctionsAgentOptions? existing))
+        {
+            options = existing;
+            return true;
+        }
+
+        // If not defined, return default options.
+        options = s_defaultOptions;
+        return true;
    }
 }
@@ -6,13 +6,9 @@ using Microsoft.Extensions.Logging;
 namespace Microsoft.Agents.AI.Hosting.AzureFunctions;

 /// <summary>
-/// Transforms function metadata by registering durable agent functions for each explicitly configured agent.
+/// Transforms function metadata by registering durable agent functions for each configured agent.
 /// </summary>
-/// <remarks>
-/// This transformer adds entity, HTTP, and MCP tool trigger functions for agents that have
-/// explicit <see cref="FunctionsAgentOptions"/>. Agents auto-registered by workflows
-/// (which lack explicit options) are handled by <see cref="DurableWorkflowsFunctionMetadataTransformer"/>.
-/// </remarks>
+/// <remarks>This transformer adds both entity trigger and HTTP trigger functions for every agent registered in the application.</remarks>
 internal sealed class DurableAgentFunctionMetadataTransformer : IFunctionMetadataTransformer
 {
    private readonly ILogger<DurableAgentFunctionMetadataTransformer> _logger;
@@ -42,27 +38,24 @@ internal sealed class DurableAgentFunctionMetadataTransformer : IFunctionMetadat
        {
            string agentName = kvp.Key;

-            // Only generate triggers for agents with explicit Functions agent options.
-            // Agents auto-registered by workflows are handled by DurableWorkflowsFunctionMetadataTransformer.
-            if (!this._functionsAgentOptionsProvider.TryGet(agentName, out FunctionsAgentOptions? agentTriggerOptions))
-            {
-                continue;
-            }
-
            this._logger.LogRegisteringTriggerForAgent(agentName, "entity");
+
            original.Add(FunctionMetadataFactory.CreateEntityTrigger(agentName));

-            if (agentTriggerOptions.HttpTrigger.IsEnabled)
+            if (this._functionsAgentOptionsProvider.TryGet(agentName, out FunctionsAgentOptions? agentTriggerOptions))
            {
-                this._logger.LogRegisteringTriggerForAgent(agentName, "http");
-                original.Add(FunctionMetadataFactory.CreateHttpTrigger(agentName, $"agents/{agentName}/run", BuiltInFunctions.RunAgentHttpFunctionEntryPoint));
-            }
+                if (agentTriggerOptions.HttpTrigger.IsEnabled)
+                {
+                    this._logger.LogRegisteringTriggerForAgent(agentName, "http");
+                    original.Add(FunctionMetadataFactory.CreateHttpTrigger(agentName, $"agents/{agentName}/run", BuiltInFunctions.RunAgentHttpFunctionEntryPoint));
+                }

-            if (agentTriggerOptions.McpToolTrigger.IsEnabled)
-            {
-                AIAgent agent = kvp.Value(this._serviceProvider);
-                this._logger.LogRegisteringTriggerForAgent(agentName, "mcpTool");
-                original.Add(CreateMcpToolTrigger(agentName, agent.Description));
+                if (agentTriggerOptions.McpToolTrigger.IsEnabled)
+                {
+                    AIAgent agent = kvp.Value(this._serviceProvider);
+                    this._logger.LogRegisteringTriggerForAgent(agentName, "mcpTool");
+                    original.Add(CreateMcpToolTrigger(agentName, agent.Description));
+                }
            }
        }
    }
@@ -134,17 +134,4 @@ public static class DurableAgentsOptionsExtensions
    {
        return new Dictionary<string, FunctionsAgentOptions>(s_agentOptions, StringComparer.OrdinalIgnoreCase);
    }
-
-    /// <summary>
-    /// Ensures every agent in <paramref name="agentNames"/> has an entry in the
-    /// options registry. Agents that already have explicit options are left untouched.
-    /// New entries receive the default configuration (HTTP trigger enabled, MCP tool disabled).
-    /// </summary>
-    internal static void EnsureDefaultOptionsForAll(IEnumerable<string> agentNames)
-    {
-        foreach (string name in agentNames)
-        {
-            s_agentOptions.TryAdd(name, new FunctionsAgentOptions { HttpTrigger = { IsEnabled = true } });
-        }
-    }
 }
@@ -1,6 +1,5 @@
 // Copyright (c) Microsoft. All rights reserved.

-using System.Text.Json.Nodes;
 using Microsoft.Agents.AI.DurableTask;
 using Microsoft.Azure.Functions.Worker.Core.FunctionMetadata;

@@ -99,65 +98,4 @@ internal static class FunctionMetadataFactory
            ScriptFile = BuiltInFunctions.ScriptFile,
        };
    }
-
-    /// <summary>
-    /// Creates function metadata for an MCP tool trigger function that starts a workflow.
-    /// </summary>
-    /// <param name="workflowName">The name of the workflow to expose as an MCP tool.</param>
-    /// <param name="description">An optional description for the MCP tool. If null, a default description is generated.</param>
-    /// <returns>A <see cref="DefaultFunctionMetadata"/> configured for an MCP tool trigger.</returns>
-    internal static DefaultFunctionMetadata CreateWorkflowMcpToolTrigger(
-        string workflowName,
-        string? description)
-    {
-        var functionName = $"{BuiltInFunctions.McpToolPrefix}{workflowName}";
-        var toolDescription = description ?? $"Run the {workflowName} workflow";
-
-        var toolProperties = new JsonArray(new JsonObject
-        {
-            ["propertyName"] = "input",
-            ["propertyType"] = "string",
-            ["description"] = "The input to the workflow.",
-            ["isRequired"] = true,
-            ["isArray"] = false,
-        });
-
-        var triggerBinding = new JsonObject
-        {
-            ["name"] = "context",
-            ["type"] = "mcpToolTrigger",
-            ["direction"] = "In",
-            ["toolName"] = workflowName,
-            ["description"] = toolDescription,
-            ["toolProperties"] = toolProperties.ToJsonString(),
-        };
-
-        var inputBinding = new JsonObject
-        {
-            ["name"] = "input",
-            ["type"] = "mcpToolProperty",
-            ["direction"] = "In",
-            ["propertyName"] = "input",
-            ["description"] = "The input to the workflow",
-            ["isRequired"] = true,
-            ["dataType"] = "String",
-            ["propertyType"] = "string",
-        };
-
-        var clientBinding = new JsonObject
-        {
-            ["name"] = "client",
-            ["type"] = "durableClient",
-            ["direction"] = "In",
-        };
-
-        return new DefaultFunctionMetadata
-        {
-            Name = functionName,
-            Language = "dotnet-isolated",
-            RawBindings = [triggerBinding.ToJsonString(), inputBinding.ToJsonString(), clientBinding.ToJsonString()],
-            EntryPoint = BuiltInFunctions.RunWorkflowMcpToolFunctionEntryPoint,
-            ScriptFile = BuiltInFunctions.ScriptFile,
-        };
-    }
 }
@@ -27,16 +27,9 @@ public static class FunctionsApplicationBuilderExtensions
    {
        ArgumentNullException.ThrowIfNull(configure);

-        // Create/get shared options BEFORE the DurableTask library call so it can find them.
-        FunctionsDurableOptions sharedOptions = GetOrCreateSharedOptions(builder.Services);
-
        // The main agent services registration is done in Microsoft.DurableTask.Agents.
        builder.Services.ConfigureDurableAgents(configure);

-        // Ensure all agents registered through this path have default FunctionsAgentOptions.
-        // This distinguishes them from agents auto-registered by workflows.
-        DurableAgentsOptionsExtensions.EnsureDefaultOptionsForAll(sharedOptions.Agents.GetAgentFactories().Keys);
-
        builder.Services.TryAddSingleton<IFunctionsAgentOptionsProvider>(_ =>
            new DefaultFunctionsAgentOptionsProvider(DurableAgentsOptionsExtensions.GetAgentOptionsSnapshot()));

@@ -74,13 +67,6 @@ public static class FunctionsApplicationBuilderExtensions

        builder.Services.ConfigureDurableOptions(configure);

-        if (DurableAgentsOptionsExtensions.GetAgentOptionsSnapshot().Count > 0)
-        {
-            builder.Services.TryAddSingleton<IFunctionsAgentOptionsProvider>(_ =>
-                new DefaultFunctionsAgentOptionsProvider(DurableAgentsOptionsExtensions.GetAgentOptionsSnapshot()));
-            builder.Services.TryAddEnumerable(ServiceDescriptor.Singleton<IFunctionMetadataTransformer, DurableAgentFunctionMetadataTransformer>());
-        }
-
        if (sharedOptions.Workflows.Workflows.Count > 0)
        {
            builder.Services.TryAddEnumerable(ServiceDescriptor.Singleton<IFunctionMetadataTransformer, DurableWorkflowsFunctionMetadataTransformer>());
@@ -116,14 +102,12 @@ public static class FunctionsApplicationBuilderExtensions

        builder.UseWhen<BuiltInFunctionExecutionMiddleware>(static context =>
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunAgentHttpFunctionEntryPoint, StringComparison.Ordinal) ||
-            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunAgentMcpToolFunctionEntryPoint, StringComparison.Ordinal) ||
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunAgentEntityFunctionEntryPoint, StringComparison.Ordinal) ||
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunWorkflowOrchestrationHttpFunctionEntryPoint, StringComparison.Ordinal) ||
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunWorkflowOrchestrationFunctionEntryPoint, StringComparison.Ordinal) ||
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.InvokeWorkflowActivityFunctionEntryPoint, StringComparison.Ordinal) ||
            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.GetWorkflowStatusHttpFunctionEntryPoint, StringComparison.Ordinal) ||
-            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RespondToWorkflowHttpFunctionEntryPoint, StringComparison.Ordinal) ||
-            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RunWorkflowMcpToolFunctionEntryPoint, StringComparison.Ordinal)
+            string.Equals(context.FunctionDefinition.EntryPoint, BuiltInFunctions.RespondToWorkflowHttpFunctionEntryPoint, StringComparison.Ordinal)
        );
        builder.Services.TryAddSingleton<BuiltInFunctionExecutor>();
    }
@@ -10,7 +10,6 @@ namespace Microsoft.Agents.AI.Hosting.AzureFunctions;
 internal sealed class FunctionsDurableOptions : DurableOptions
 {
    private readonly HashSet<string> _statusEndpointWorkflows = new(StringComparer.OrdinalIgnoreCase);
-    private readonly HashSet<string> _mcpToolTriggerWorkflows = new(StringComparer.OrdinalIgnoreCase);

    /// <summary>
    /// Enables the status HTTP endpoint for the specified workflow.
@@ -27,20 +26,4 @@ internal sealed class FunctionsDurableOptions : DurableOptions
    {
        return this._statusEndpointWorkflows.Contains(workflowName);
    }
-
-    /// <summary>
-    /// Enables the MCP tool trigger for the specified workflow.
-    /// </summary>
-    internal void EnableMcpToolTrigger(string workflowName)
-    {
-        this._mcpToolTriggerWorkflows.Add(workflowName);
-    }
-
-    /// <summary>
-    /// Returns whether the MCP tool trigger is enabled for the specified workflow.
-    /// </summary>
-    internal bool IsMcpToolTriggerEnabled(string workflowName)
-    {
-        return this._mcpToolTriggerWorkflows.Contains(workflowName);
-    }
 }
@@ -27,31 +27,4 @@ public static class DurableWorkflowOptionsExtensions
            functionsOptions.EnableStatusEndpoint(workflow.Name!);
        }
    }
-
-    /// <summary>
-    /// Adds a workflow and configures whether to expose a status HTTP endpoint and/or an MCP tool trigger.
-    /// </summary>
-    /// <param name="options">The workflow options to add the workflow to.</param>
-    /// <param name="workflow">The workflow instance to add.</param>
-    /// <param name="exposeStatusEndpoint">If <see langword="true"/>, a GET endpoint is generated at <c>workflows/{name}/status/{runId}</c>.</param>
-    /// <param name="exposeMcpToolTrigger">If <see langword="true"/>, an MCP tool trigger is generated for the workflow.</param>
-    public static void AddWorkflow(this DurableWorkflowOptions options, Workflow workflow, bool exposeStatusEndpoint, bool exposeMcpToolTrigger)
-    {
-        ArgumentNullException.ThrowIfNull(options);
-
-        options.AddWorkflow(workflow);
-
-        if (options.ParentOptions is FunctionsDurableOptions functionsOptions)
-        {
-            if (exposeStatusEndpoint)
-            {
-                functionsOptions.EnableStatusEndpoint(workflow.Name!);
-            }
-
-            if (exposeMcpToolTrigger)
-            {
-                functionsOptions.EnableMcpToolTrigger(workflow.Name!);
-            }
-        }
-    }
 }
@@ -50,11 +50,8 @@ internal sealed class DurableWorkflowsFunctionMetadataTransformer : IFunctionMet
        int initialCount = original.Count;
        this._logger.LogTransformingFunctionMetadata(initialCount);

-        // Seed with existing function names to avoid duplicates across transformers
-        // (e.g., when DurableAgentFunctionMetadataTransformer already registered entity triggers).
-        HashSet<string> registeredFunctions = new(
-            original.Select(f => f.Name!),
-            StringComparer.OrdinalIgnoreCase);
+        // Track registered function names to avoid duplicates when workflows share executors.
+        HashSet<string> registeredFunctions = [];

        DurableWorkflowOptions workflowOptions = this._options.Workflows;
        foreach (var workflow in workflowOptions.Workflows)
@@ -116,17 +113,6 @@ internal sealed class DurableWorkflowsFunctionMetadataTransformer : IFunctionMet
                }
            }

-            // Register an MCP tool trigger if opted in via AddWorkflow(exposeMcpToolTrigger: true).
-            if (this._options.IsMcpToolTriggerEnabled(workflow.Key))
-            {
-                string mcpToolFunctionName = $"{BuiltInFunctions.McpToolPrefix}{workflow.Key}";
-                if (registeredFunctions.Add(mcpToolFunctionName))
-                {
-                    this._logger.LogRegisteringWorkflowTrigger(workflow.Key, mcpToolFunctionName, "mcpTool");
-                    original.Add(FunctionMetadataFactory.CreateWorkflowMcpToolTrigger(workflow.Key, workflow.Value.Description));
-                }
-            }
-
            // Register activity or entity functions for each executor in the workflow.
            // ReflectExecutors() returns all executors across the graph; no need to manually traverse edges.
            foreach (KeyValuePair<string, ExecutorBinding> entry in workflow.Value.ReflectExecutors())
@@ -5,14 +5,11 @@ using System.Collections.Generic;
 using System.IO;
 using System.Text;
 using System.Text.Json;
-using System.Text.Json.Serialization.Metadata;
 using System.Threading;
 using System.Threading.Tasks;

 namespace Microsoft.Agents.AI.Workflows.Checkpointing;

-internal record CheckpointFileIndexEntry(CheckpointInfo CheckpointInfo, string FileName);
-
 /// <summary>
 /// Provides a file system-based implementation of a JSON checkpoint store that persists checkpoint data and index
 /// information to disk using JSON files.
@@ -31,8 +28,6 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
    internal DirectoryInfo Directory { get; }
    internal HashSet<CheckpointInfo> CheckpointIndex { get; }

-    private static JsonTypeInfo<CheckpointFileIndexEntry> EntryTypeInfo => WorkflowsJsonUtilities.JsonContext.Default.CheckpointFileIndexEntry;
-
    /// <summary>
    /// Initializes a new instance of the <see cref="FileSystemJsonCheckpointStore"/> class that uses the specified directory
    /// </summary>
@@ -69,11 +64,9 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
            using StreamReader reader = new(this._indexFile, encoding: Encoding.UTF8, detectEncodingFromByteOrderMarks: false, BufferSize, leaveOpen: true);
            while (reader.ReadLine() is string line)
            {
-                if (JsonSerializer.Deserialize(line, EntryTypeInfo) is { } entry)
+                if (JsonSerializer.Deserialize(line, KeyTypeInfo) is { } info)
                {
-                    // We never actually use the file names from the index entries since they can be derived from the CheckpointInfo, but it is useful to
-                    // have the UrlEncoded file names in the index file for human readability
-                    this.CheckpointIndex.Add(entry.CheckpointInfo);
+                    this.CheckpointIndex.Add(info);
                }
            }
        }
@@ -100,14 +93,8 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
        }
    }

-    internal string GetFileNameForCheckpoint(string sessionId, CheckpointInfo key)
-    {
-        string protoPath = $"{sessionId}_{key.CheckpointId}.json";
-
-        // Escape the protoPath to ensure it is a valid file name, especially if sessionId or CheckpointId contain path separators, etc.
-        return Uri.EscapeDataString(protoPath) // This takes care of most of the invalid path characters
-                  .Replace(".", "%2E");        // This takes care of escaping the root folder, since EscapeDataString does not escape dots
-    }
+    private string GetFileNameForCheckpoint(string sessionId, CheckpointInfo key)
+        => Path.Combine(this.Directory.FullName, $"{sessionId}_{key.CheckpointId}.json");

    private CheckpointInfo GetUnusedCheckpointInfo(string sessionId)
    {
@@ -129,16 +116,13 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos

        CheckpointInfo key = this.GetUnusedCheckpointInfo(sessionId);
        string fileName = this.GetFileNameForCheckpoint(sessionId, key);
-        string filePath = Path.Combine(this.Directory.FullName, fileName);
-
        try
        {
-            using Stream checkpointStream = File.Open(filePath, FileMode.Create, FileAccess.Write, FileShare.None);
+            using Stream checkpointStream = File.Open(fileName, FileMode.Create, FileAccess.Write, FileShare.None);
            using Utf8JsonWriter jsonWriter = new(checkpointStream, new JsonWriterOptions() { Indented = false });
            value.WriteTo(jsonWriter);

-            CheckpointFileIndexEntry entry = new(key, fileName);
-            JsonSerializer.Serialize(this._indexFile!, entry, EntryTypeInfo);
+            JsonSerializer.Serialize(this._indexFile!, key, KeyTypeInfo);
            byte[] bytes = Encoding.UTF8.GetBytes(Environment.NewLine);
            await this._indexFile!.WriteAsync(bytes, 0, bytes.Length, CancellationToken.None).ConfigureAwait(false);
            await this._indexFile!.FlushAsync(CancellationToken.None).ConfigureAwait(false);
@@ -152,7 +136,7 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
            try
            {
                // try to clean up after ourselves
-                File.Delete(filePath);
+                File.Delete(fileName);
            }
            catch { }

@@ -165,7 +149,6 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
    {
        this.CheckDisposed();
        string fileName = this.GetFileNameForCheckpoint(sessionId, key);
-        string filePath = Path.Combine(this.Directory.FullName, fileName);

        if (!this.CheckpointIndex.Contains(key) ||
            !File.Exists(fileName))
@@ -173,7 +156,7 @@ public sealed class FileSystemJsonCheckpointStore : JsonCheckpointStore, IDispos
            throw new KeyNotFoundException($"Checkpoint '{key.CheckpointId}' not found in store at '{this.Directory.FullName}'.");
        }

-        using FileStream checkpointFileStream = File.Open(filePath, FileMode.Open, FileAccess.Read, FileShare.Read);
+        using FileStream checkpointFileStream = File.Open(fileName, FileMode.Open, FileAccess.Read, FileShare.Read);
        using JsonDocument document = await JsonDocument.ParseAsync(checkpointFileStream).ConfigureAwait(false);

        return document.RootElement.Clone();
@@ -71,7 +71,6 @@ internal static partial class WorkflowsJsonUtilities
    [JsonSerializable(typeof(PortableValue))]
    [JsonSerializable(typeof(PortableMessageEnvelope))]
    [JsonSerializable(typeof(InMemoryCheckpointManager))]
-    [JsonSerializable(typeof(CheckpointFileIndexEntry))]

    // Runtime State Types
    [JsonSerializable(typeof(ScopeKey))]
@@ -138,9 +138,6 @@ public sealed partial class ChatClientAgent : AIAgent
        this._aiContextProviderStateKeys = ValidateAndCollectStateKeys(this._agentOptions?.AIContextProviders, this.ChatHistoryProvider);

        this._logger = (loggerFactory ?? chatClient.GetService<ILoggerFactory>() ?? NullLoggerFactory.Instance).CreateLogger<ChatClientAgent>();
-
-        // Warn if using a custom chat client stack with end-of-run persistence but no ChatHistoryPersistingChatClient.
-        this.WarnOnMissingPersistingClient();
    }

    /// <summary>
@@ -214,14 +211,12 @@ public sealed partial class ChatClientAgent : AIAgent
         ChatClientAgentContinuationToken? _) =
            await this.PrepareSessionAndMessagesAsync(session, inputMessages, options, cancellationToken).ConfigureAwait(false);

-        // Update the run context with the resolved session so any downstream classes
-        // always have a valid session, even when the caller passed null.
-        EnsureRunContextHasSession(safeSession);
-
        var chatClient = this.ChatClient;
+
        chatClient = ApplyRunOptionsTransformations(options, chatClient);

        var loggingAgentName = this.GetLoggingAgentName();
+
        this._logger.LogAgentChatClientInvokingAgent(nameof(RunAsync), this.Id, loggingAgentName, this._chatClientType);

        // Call the IChatClient and notify the AIContextProvider of any failures.
@@ -232,7 +227,8 @@ public sealed partial class ChatClientAgent : AIAgent
        }
        catch (Exception ex)
        {
-            await this.NotifyProvidersOfFailureAtEndOfRunAsync(safeSession, ex, inputMessagesForChatClient, chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyChatHistoryProviderOfFailureAsync(safeSession, ex, inputMessagesForChatClient, chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyAIContextProviderOfFailureAsync(safeSession, ex, inputMessagesForChatClient, cancellationToken).ConfigureAwait(false);
            throw;
        }

@@ -240,8 +236,7 @@ public sealed partial class ChatClientAgent : AIAgent

        // We can derive the type of supported session from whether we have a conversation id,
        // so let's update it and set the conversation id for the service session case.
-        var forceEndOfRunPersistence = chatOptions?.ContinuationToken is not null || chatOptions?.AllowBackgroundResponses is true;
-        this.UpdateSessionConversationIdAtEndOfRun(safeSession, chatResponse.ConversationId, cancellationToken, forceUpdate: forceEndOfRunPersistence);
+        this.UpdateSessionConversationId(safeSession, chatResponse.ConversationId, cancellationToken);

        // Ensure that the author name is set for each message in the response.
        foreach (ChatMessage chatResponseMessage in chatResponse.Messages)
@@ -249,10 +244,11 @@ public sealed partial class ChatClientAgent : AIAgent
            chatResponseMessage.AuthorName ??= this.Name;
        }

-        // Notify providers of all new messages unless persistence is handled per-service-call by the decorator.
-        // When background responses are allowed, force notification since per-service-call persistence
-        // is unreliable (the caller may stop consuming the stream before the decorator can persist).
-        await this.NotifyProvidersOfNewMessagesAtEndOfRunAsync(safeSession, inputMessagesForChatClient, chatResponse.Messages, chatOptions, cancellationToken, forceNotify: forceEndOfRunPersistence).ConfigureAwait(false);
+        // Only notify the session of new messages if the chatResponse was successful to avoid inconsistent message state in the session.
+        await this.NotifyChatHistoryProviderOfNewMessagesAsync(safeSession, inputMessagesForChatClient, chatResponse.Messages, chatOptions, cancellationToken).ConfigureAwait(false);
+
+        // Notify the AIContextProvider of all new messages.
+        await this.NotifyAIContextProviderOfSuccessAsync(safeSession, inputMessagesForChatClient, chatResponse.Messages, cancellationToken).ConfigureAwait(false);

        return new AgentResponse(chatResponse)
        {
@@ -300,10 +296,6 @@ public sealed partial class ChatClientAgent : AIAgent
         ChatClientAgentContinuationToken? continuationToken) =
            await this.PrepareSessionAndMessagesAsync(session, inputMessages, options, cancellationToken).ConfigureAwait(false);

-        // Update the run context with the resolved session so any downstream classes
-        // always have a valid session, even when the caller passed null.
-        EnsureRunContextHasSession(safeSession);
-
        var chatClient = this.ChatClient;

        chatClient = ApplyRunOptionsTransformations(options, chatClient);
@@ -323,7 +315,8 @@ public sealed partial class ChatClientAgent : AIAgent
        }
        catch (Exception ex)
        {
-            await this.NotifyProvidersOfFailureAtEndOfRunAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyChatHistoryProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyAIContextProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), cancellationToken).ConfigureAwait(false);
            throw;
        }

@@ -337,7 +330,8 @@ public sealed partial class ChatClientAgent : AIAgent
        }
        catch (Exception ex)
        {
-            await this.NotifyProvidersOfFailureAtEndOfRunAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyChatHistoryProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+            await this.NotifyAIContextProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), cancellationToken).ConfigureAwait(false);
            throw;
        }

@@ -359,31 +353,27 @@ public sealed partial class ChatClientAgent : AIAgent

            try
            {
-                // Re-ensure the run context has the resolved session before each MoveNextAsync.
-                // The base class RunStreamingAsync restores the original context (potentially with
-                // null session) after each yield, so we must re-establish it for the decorator.
-                EnsureRunContextHasSession(safeSession);
                hasUpdates = await responseUpdatesEnumerator.MoveNextAsync().ConfigureAwait(false);
            }
            catch (Exception ex)
            {
-                await this.NotifyProvidersOfFailureAtEndOfRunAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+                await this.NotifyChatHistoryProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), chatOptions, cancellationToken).ConfigureAwait(false);
+                await this.NotifyAIContextProviderOfFailureAsync(safeSession, ex, GetInputMessages(inputMessagesForChatClient, continuationToken), cancellationToken).ConfigureAwait(false);
                throw;
            }
        }

        var chatResponse = responseUpdates.ToChatResponse();

-        var forceEndOfRunPersistence = continuationToken is not null || chatOptions?.AllowBackgroundResponses is true;
-
        // We can derive the type of supported session from whether we have a conversation id,
        // so let's update it and set the conversation id for the service session case.
-        this.UpdateSessionConversationIdAtEndOfRun(safeSession, chatResponse.ConversationId, cancellationToken, forceUpdate: forceEndOfRunPersistence);
+        this.UpdateSessionConversationId(safeSession, chatResponse.ConversationId, cancellationToken);

-        // Notify providers of all new messages unless persistence is handled per-service-call by the decorator.
-        // When resuming from a continuation token or using background responses, force notification
-        // to send the combined data (per-service-call persistence is unreliable for these scenarios).
-        await this.NotifyProvidersOfNewMessagesAtEndOfRunAsync(safeSession, GetInputMessages(inputMessagesForChatClient, continuationToken), chatResponse.Messages, chatOptions, cancellationToken, forceNotify: forceEndOfRunPersistence).ConfigureAwait(false);
+        // To avoid inconsistent state we only notify the session of the input messages if no error occurs after the initial request.
+        await this.NotifyChatHistoryProviderOfNewMessagesAsync(safeSession, GetInputMessages(inputMessagesForChatClient, continuationToken), chatResponse.Messages, chatOptions, cancellationToken).ConfigureAwait(false);
+
+        // Notify the AIContextProvider of all new messages.
+        await this.NotifyAIContextProviderOfSuccessAsync(safeSession, GetInputMessages(inputMessagesForChatClient, continuationToken), chatResponse.Messages, cancellationToken).ConfigureAwait(false);
    }

    /// <inheritdoc/>
@@ -451,29 +441,17 @@ public sealed partial class ChatClientAgent : AIAgent
    #region Private

    /// <summary>
-    /// Notifies the <see cref="ChatHistoryProvider"/> and all <see cref="AIContextProviders"/> of successfully completed messages.
+    /// Notify the <see cref="AIContextProvider"/> when an agent run succeeded, if there is an <see cref="AIContextProvider"/>.
    /// </summary>
-    /// <remarks>
-    /// This method is also called by <see cref="ChatHistoryPersistingChatClient"/> to persist messages per-service-call.
-    /// </remarks>
-    internal async Task NotifyProvidersOfNewMessagesAsync(
+    private async Task NotifyAIContextProviderOfSuccessAsync(
        ChatClientAgentSession session,
-        IEnumerable<ChatMessage> requestMessages,
+        IEnumerable<ChatMessage> inputMessages,
        IEnumerable<ChatMessage> responseMessages,
-        ChatOptions? chatOptions,
        CancellationToken cancellationToken)
    {
-        ChatHistoryProvider? chatHistoryProvider = this.ResolveChatHistoryProvider(chatOptions, session);
-
-        if (chatHistoryProvider is not null)
-        {
-            var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, requestMessages, responseMessages);
-            await chatHistoryProvider.InvokedAsync(invokedContext, cancellationToken).ConfigureAwait(false);
-        }
-
        if (this.AIContextProviders is { Count: > 0 } contextProviders)
        {
-            AIContextProvider.InvokedContext invokedContext = new(this, session, requestMessages, responseMessages);
+            AIContextProvider.InvokedContext invokedContext = new(this, session, inputMessages, responseMessages);

            foreach (var contextProvider in contextProviders)
            {
@@ -483,29 +461,17 @@ public sealed partial class ChatClientAgent : AIAgent
    }

    /// <summary>
-    /// Notifies the <see cref="ChatHistoryProvider"/> and all <see cref="AIContextProviders"/> of a failure during a service call.
+    /// Notify the <see cref="AIContextProvider"/> of any failure during an agent run, if there is an <see cref="AIContextProvider"/>.
    /// </summary>
-    /// <remarks>
-    /// This method is also called by <see cref="ChatHistoryPersistingChatClient"/> to report failures per-service-call.
-    /// </remarks>
-    internal async Task NotifyProvidersOfFailureAsync(
+    private async Task NotifyAIContextProviderOfFailureAsync(
        ChatClientAgentSession session,
        Exception ex,
-        IEnumerable<ChatMessage> requestMessages,
-        ChatOptions? chatOptions,
+        IEnumerable<ChatMessage> inputMessages,
        CancellationToken cancellationToken)
    {
-        ChatHistoryProvider? chatHistoryProvider = this.ResolveChatHistoryProvider(chatOptions, session);
-
-        if (chatHistoryProvider is not null)
-        {
-            var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, requestMessages, ex);
-            await chatHistoryProvider.InvokedAsync(invokedContext, cancellationToken).ConfigureAwait(false);
-        }
-
        if (this.AIContextProviders is { Count: > 0 } contextProviders)
        {
-            AIContextProvider.InvokedContext invokedContext = new(this, session, requestMessages, ex);
+            AIContextProvider.InvokedContext invokedContext = new(this, session, inputMessages, ex);

            foreach (var contextProvider in contextProviders)
            {
@@ -701,12 +667,6 @@ public sealed partial class ChatClientAgent : AIAgent
            throw new InvalidOperationException("A session must be provided when continuing a background response with a continuation token.");
        }

-        if ((continuationToken is not null || chatOptions?.AllowBackgroundResponses is true) && this.PersistsChatHistoryPerServiceCall && this._logger.IsEnabled(LogLevel.Warning))
-        {
-            var warningAgentName = this.GetLoggingAgentName();
-            this._logger.LogAgentChatClientBackgroundResponseFallback(this.Id, warningAgentName);
-        }
-
        session ??= await this.CreateSessionAsync(cancellationToken).ConfigureAwait(false);
        if (session is not ChatClientAgentSession typedSession)
        {
@@ -794,7 +754,7 @@ public sealed partial class ChatClientAgent : AIAgent
        return (typedSession, chatOptions, messagesList, continuationToken);
    }

-    internal void UpdateSessionConversationId(ChatClientAgentSession session, string? responseConversationId, CancellationToken cancellationToken)
+    private void UpdateSessionConversationId(ChatClientAgentSession session, string? responseConversationId, CancellationToken cancellationToken)
    {
        if (string.IsNullOrWhiteSpace(responseConversationId) && !string.IsNullOrWhiteSpace(session.ConversationId))
        {
@@ -838,162 +798,45 @@ public sealed partial class ChatClientAgent : AIAgent
        }
    }

-    /// <summary>
-    /// Updates the session conversation ID at the end of an agent run.
-    /// </summary>
-    /// <remarks>
-    /// When a <see cref="ChatHistoryPersistingChatClient"/> in persist mode handles per-service-call
-    /// conversation ID updates, this end-of-run update is skipped. When the decorator is in mark-only
-    /// mode or absent, the update is performed here. When <paramref name="forceUpdate"/> is <see langword="true"/>
-    /// (continuation token scenarios), the update is always performed.
-    /// </remarks>
-    private void UpdateSessionConversationIdAtEndOfRun(ChatClientAgentSession session, string? responseConversationId, CancellationToken cancellationToken, bool forceUpdate = false)
-    {
-        if (!forceUpdate && this.PersistsChatHistoryPerServiceCall)
-        {
-            return;
-        }
-
-        this.UpdateSessionConversationId(session, responseConversationId, cancellationToken);
-    }
-
-    /// <summary>
-    /// Notifies providers of successfully completed messages at the end of an agent run.
-    /// </summary>
-    /// <remarks>
-    /// When a <see cref="ChatHistoryPersistingChatClient"/> in persist mode handles per-service-call
-    /// notification, this end-of-run notification is skipped. When the decorator is in mark-only mode,
-    /// only the marked messages are persisted. When no decorator is present (custom stack with
-    /// <see cref="ChatClientAgentOptions.PersistChatHistoryAtEndOfRun"/>), all messages are persisted.
-    /// When <paramref name="forceNotify"/> is <see langword="true"/> (continuation token or
-    /// background response scenarios), notification is always performed with all messages because
-    /// per-service-call persistence is unreliable in these scenarios.
-    /// </remarks>
-    private Task NotifyProvidersOfNewMessagesAtEndOfRunAsync(
-        ChatClientAgentSession session,
-        IEnumerable<ChatMessage> requestMessages,
-        IEnumerable<ChatMessage> responseMessages,
-        ChatOptions? chatOptions,
-        CancellationToken cancellationToken,
-        bool forceNotify = false)
-    {
-        if (!forceNotify && this.PersistsChatHistoryPerServiceCall)
-        {
-            return Task.CompletedTask;
-        }
-
-        if (!forceNotify && this.HasMarkOnlyChatHistoryPersistingClient)
-        {
-            // In mark-only mode, persist only messages that were marked by the decorator.
-            var markedRequestMessages = GetMarkedMessages(requestMessages);
-            var markedResponseMessages = GetMarkedMessages(responseMessages);
-            return this.NotifyProvidersOfNewMessagesAsync(session, markedRequestMessages, markedResponseMessages, chatOptions, cancellationToken);
-        }
-
-        return this.NotifyProvidersOfNewMessagesAsync(session, requestMessages, responseMessages, chatOptions, cancellationToken);
-    }
-
-    /// <summary>
-    /// Notifies providers of a failure at the end of an agent run.
-    /// </summary>
-    /// <remarks>
-    /// When a <see cref="ChatHistoryPersistingChatClient"/> in persist mode handles per-service-call
-    /// notification (including failure), this end-of-run notification is skipped to avoid
-    /// duplicate notification. In all other cases, failure is reported at the end of the run.
-    /// </remarks>
-    private Task NotifyProvidersOfFailureAtEndOfRunAsync(
+    private Task NotifyChatHistoryProviderOfFailureAsync(
        ChatClientAgentSession session,
        Exception ex,
        IEnumerable<ChatMessage> requestMessages,
        ChatOptions? chatOptions,
        CancellationToken cancellationToken)
    {
-        if (this.PersistsChatHistoryPerServiceCall)
+        ChatHistoryProvider? provider = this.ResolveChatHistoryProvider(chatOptions, session);
+
+        // Only notify the provider if we have one.
+        // If we don't have one, it means that the chat history is service managed and the underlying service is responsible for storing messages.
+        if (provider is not null)
        {
-            return Task.CompletedTask;
+            var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, requestMessages, ex);
+
+            return provider.InvokedAsync(invokedContext, cancellationToken).AsTask();
        }

-        return this.NotifyProvidersOfFailureAsync(session, ex, requestMessages, chatOptions, cancellationToken);
+        return Task.CompletedTask;
    }

-    /// <summary>
-    /// Gets a value indicating whether the agent has a <see cref="ChatHistoryPersistingChatClient"/>
-    /// decorator in persist mode (not mark-only), which handles per-service-call persistence.
-    /// </summary>
-    private bool PersistsChatHistoryPerServiceCall
+    private Task NotifyChatHistoryProviderOfNewMessagesAsync(
+        ChatClientAgentSession session,
+        IEnumerable<ChatMessage> requestMessages,
+        IEnumerable<ChatMessage> responseMessages,
+        ChatOptions? chatOptions,
+        CancellationToken cancellationToken)
    {
-        get
-        {
-            var persistingClient = this.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-            return persistingClient?.MarkOnly == false;
-        }
-    }
+        ChatHistoryProvider? provider = this.ResolveChatHistoryProvider(chatOptions, session);

-    /// <summary>
-    /// Gets a value indicating whether the agent has a <see cref="ChatHistoryPersistingChatClient"/>
-    /// decorator in mark-only mode, which marks messages for later persistence at the end of the run.
-    /// </summary>
-    private bool HasMarkOnlyChatHistoryPersistingClient
-    {
-        get
+        // Only notify the provider if we have one.
+        // If we don't have one, it means that the chat history is service managed and the underlying service is responsible for storing messages.
+        if (provider is not null)
        {
-            var persistingClient = this.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-            return persistingClient?.MarkOnly == true;
-        }
-    }
-
-    /// <summary>
-    /// Returns only the messages that have been marked as persisted by a <see cref="ChatHistoryPersistingChatClient"/> in mark-only mode.
-    /// </summary>
-    private static List<ChatMessage> GetMarkedMessages(IEnumerable<ChatMessage> messages)
-    {
-        return messages.Where(m =>
-            m.AdditionalProperties?.TryGetValue(ChatHistoryPersistingChatClient.PersistedMarkerKey, out var value) == true && value is true).ToList();
-    }
-
-    /// <summary>
-    /// Ensures that <see cref="AIAgent.CurrentRunContext"/> contains the resolved session.
-    /// </summary>
-    /// <remarks>
-    /// The base class sets <see cref="AIAgent.CurrentRunContext"/> with the raw session parameter
-    /// (which may be null) and restores it after each yield in streaming scenarios. After
-    /// <see cref="PrepareSessionAndMessagesAsync"/> resolves or creates a session, we update the
-    /// context so the <see cref="ChatHistoryPersistingChatClient"/> decorator always has a valid session.
-    /// The original agent from the context is preserved to maintain the top-of-stack agent in
-    /// decorated agent scenarios.
-    /// </remarks>
-    private static void EnsureRunContextHasSession(ChatClientAgentSession safeSession)
-    {
-        var context = CurrentRunContext;
-        if (context is not null && context.Session != safeSession)
-        {
-            CurrentRunContext = new(context.Agent, safeSession, context.RequestMessages, context.RunOptions);
-        }
-    }
-
-    /// <summary>
-    /// Checks for potential misconfiguration when using a custom chat client stack and logs warnings.
-    /// </summary>
-    private void WarnOnMissingPersistingClient()
-    {
-        if (this._agentOptions?.UseProvidedChatClientAsIs is not true)
-        {
-            return;
+            var invokedContext = new ChatHistoryProvider.InvokedContext(this, session, requestMessages, responseMessages);
+            return provider.InvokedAsync(invokedContext, cancellationToken).AsTask();
        }

-        if (this._agentOptions?.PersistChatHistoryAtEndOfRun is not true)
-        {
-            return;
-        }
-
-        var persistingClient = this.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-        if (persistingClient is null && this._logger.IsEnabled(LogLevel.Warning))
-        {
-            var loggingAgentName = this.GetLoggingAgentName();
-            this._logger.LogAgentChatClientMissingPersistingClient(
-                this.Id,
-                loggingAgentName);
-        }
+        return Task.CompletedTask;
    }

    private ChatHistoryProvider? ResolveChatHistoryProvider(ChatOptions? chatOptions, ChatClientAgentSession session)
@@ -69,32 +69,4 @@ internal static partial class ChatClientAgentLogMessages
        string chatHistoryProviderName,
        string agentId,
        string agentName);
-
-    /// <summary>
-    /// Logs a warning when <see cref="ChatClientAgentOptions.UseProvidedChatClientAsIs"/> is <see langword="true"/>
-    /// and <see cref="ChatClientAgentOptions.PersistChatHistoryAtEndOfRun"/> is <see langword="true"/>,
-    /// but no <see cref="ChatHistoryPersistingChatClient"/> is found in the custom chat client stack.
-    /// </summary>
-    [LoggerMessage(
-        Level = LogLevel.Warning,
-        Message = "Agent {AgentId}/{AgentName}: PersistChatHistoryAtEndOfRun is enabled with a custom chat client stack (UseProvidedChatClientAsIs), but no ChatHistoryPersistingChatClient was found in the pipeline. All messages will be persisted at the end of the run without marking. This setup is not supported with some other features, e.g. handoffs. Consider adding a ChatHistoryPersistingChatClient to the pipeline using the UseChatHistoryPersisting extension method.")]
-    public static partial void LogAgentChatClientMissingPersistingClient(
-        this ILogger logger,
-        string agentId,
-        string agentName);
-
-    /// <summary>
-    /// Logs a warning when per-service-call persistence falls back to end-of-run persistence
-    /// because the run involves background responses (continuation token resumption or
-    /// <c>AllowBackgroundResponses</c>). Per-service-call persistence is
-    /// unreliable in these scenarios because the caller may stop consuming the stream before
-    /// the decorator's post-stream persistence code can execute.
-    /// </summary>
-    [LoggerMessage(
-        Level = LogLevel.Warning,
-        Message = "Agent {AgentId}/{AgentName}: Per-service-call persistence is falling back to end-of-run persistence because the run involves background responses. Messages will be marked during the run and persisted at the end.")]
-    public static partial void LogAgentChatClientBackgroundResponseFallback(
-        this ILogger logger,
-        string agentId,
-        string agentName);
 }
@@ -1,9 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.

 using System.Collections.Generic;
-using System.Diagnostics.CodeAnalysis;
 using Microsoft.Extensions.AI;
-using Microsoft.Shared.DiagnosticIds;

 namespace Microsoft.Agents.AI;

@@ -91,56 +89,6 @@ public sealed class ChatClientAgentOptions
    /// </value>
    public bool ThrowOnChatHistoryProviderConflict { get; set; } = true;

-    /// <summary>
-    /// Gets or sets a value indicating whether to persist chat history only at the end of the full agent run
-    /// rather than after each individual service call.
-    /// </summary>
-    /// <remarks>
-    /// <para>
-    /// By default, <see cref="ChatClientAgent"/> persists request and response messages either via
-    /// a <see cref="ChatHistoryProvider"/>, or the underlying AI service's chat history storage.
-    /// Persistence is done immediately after each call to the AI service within the function invocation loop.
-    /// When storing in the underlying AI service, the session's <see cref="ChatClientAgentSession.ConversationId"/>
-    /// is also updated after each service call, keeping it in sync with the service-side conversation state.
-    /// </para>
-    /// <para>
-    /// Setting this property to <see langword="true"/> causes messages to be marked during the function
-    /// invocation loop but persisted only at the end of the full agent run, providing atomic run semantics.
-    /// Updating the <see cref="ChatClientAgentSession.ConversationId"/> is likewise deferred and
-    /// updated only at the end of the run, consistent with atomic run semantics.
-    /// A <see cref="ChatHistoryPersistingChatClient"/> decorator is inserted into the chat client pipeline
-    /// in mark-only mode, and the <see cref="ChatClientAgent"/> persists only the marked messages at the
-    /// end of the run.
-    /// </para>
-    /// <para>
-    /// When this option is <see langword="false"/> (the default), the <see cref="ChatHistoryPersistingChatClient"/>
-    /// decorator persists messages and updates the <see cref="ChatClientAgentSession.ConversationId"/>
-    /// immediately after each service call. This may leave chat history in a state where
-    /// <see cref="FunctionResultContent"/> is required to start a new run if the last successful service
-    /// call returned <see cref="FunctionCallContent"/>.
-    /// </para>
-    /// <para>
-    /// This option has no effect when <see cref="UseProvidedChatClientAsIs"/> is <see langword="true"/>.
-    /// When using a custom chat client stack, you can add a <see cref="ChatHistoryPersistingChatClient"/>
-    /// manually via the <see cref="ChatClientBuilderExtensions.UseChatHistoryPersisting"/>
-    /// extension method.
-    /// </para>
-    /// <para>
-    /// Note that when using single threaded service stored chat history, like OpenAI Conversations,
-    /// there is only one id, so even if the conversation id is not updated after each service call,
-    /// the chat history will still contain intermediate messages. Setting this property to <see langword="true"/>
-    /// in this case will therefore have no real effect. Setting this property to <see langword="true"/> when using
-    /// OpenAI Responses with response ids on the other hand, allows atomic run semantics, since
-    /// each service request produces a new response id, and if the run fails mid-loop, the session will
-    /// still contain the pre-run respnose id, allowing the next run to start with a clean slate.
-    /// </para>
-    /// </remarks>
-    /// <value>
-    /// Default is <see langword="false"/>.
-    /// </value>
-    [Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-    public bool PersistChatHistoryAtEndOfRun { get; set; }
-
    /// <summary>
    /// Creates a new instance of <see cref="ChatClientAgentOptions"/> with the same values as this instance.
    /// </summary>
@@ -157,6 +105,5 @@ public sealed class ChatClientAgentOptions
            ClearOnChatHistoryProviderConflict = this.ClearOnChatHistoryProviderConflict,
            WarnOnChatHistoryProviderConflict = this.WarnOnChatHistoryProviderConflict,
            ThrowOnChatHistoryProviderConflict = this.ThrowOnChatHistoryProviderConflict,
-            PersistChatHistoryAtEndOfRun = this.PersistChatHistoryAtEndOfRun,
        };
 }
@@ -2,10 +2,8 @@

 using System;
 using System.Collections.Generic;
-using System.Diagnostics.CodeAnalysis;
 using Microsoft.Agents.AI;
 using Microsoft.Extensions.Logging;
-using Microsoft.Shared.DiagnosticIds;
 using Microsoft.Shared.Diagnostics;

 namespace Microsoft.Extensions.AI;
@@ -84,46 +82,4 @@ public static class ChatClientBuilderExtensions
            options: options,
            loggerFactory: loggerFactory,
            services: services);
-
-    /// <summary>
-    /// Adds a <see cref="ChatHistoryPersistingChatClient"/> to the chat client pipeline.
-    /// </summary>
-    /// <remarks>
-    /// <para>
-    /// This decorator should be positioned between the <see cref="FunctionInvokingChatClient"/> and the leaf
-    /// <see cref="IChatClient"/> in the pipeline. It intercepts service calls to either persist messages
-    /// immediately or mark them for later persistence, depending on the <paramref name="markOnly"/> parameter.
-    /// </para>
-    /// <para>
-    /// If <paramref name="markOnly"/> is set to <see langword="true"/>, the <see cref="ChatClientAgent"/>
-    /// should be configured with <see cref="ChatClientAgentOptions.PersistChatHistoryAtEndOfRun"/> set to <see langword="true"/>
-    /// as without this combination, messages will never be persisted when using a <see cref="ChatHistoryProvider"/> for
-    /// chat history persistence.
-    /// </para>
-    /// <para>
-    /// This extension method is intended for use with custom chat client stacks when
-    /// <see cref="ChatClientAgentOptions.UseProvidedChatClientAsIs"/> is <see langword="true"/>.
-    /// When <see cref="ChatClientAgentOptions.UseProvidedChatClientAsIs"/> is <see langword="false"/> (the default),
-    /// the <see cref="ChatClientAgent"/> automatically injects this decorator.
-    /// </para>
-    /// <para>
-    /// This decorator only works within the context of a running <see cref="ChatClientAgent"/> and will throw an
-    /// exception if used in any other stack.
-    /// </para>
-    /// </remarks>
-    /// <param name="builder">The <see cref="ChatClientBuilder"/> to add the decorator to.</param>
-    /// <param name="markOnly">
-    /// When <see langword="true"/>, messages are marked with metadata but not persisted immediately,
-    /// and the session's <see cref="ChatClientAgentSession.ConversationId"/> is not updated.
-    /// The <see cref="ChatClientAgent"/> will persist only the marked messages and update the
-    /// conversation ID at the end of the run.
-    /// When <see langword="false"/> (the default), messages are persisted and the conversation ID
-    /// is updated immediately after each service call.
-    /// </param>
-    /// <returns>The <paramref name="builder"/> for chaining.</returns>
-    [Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-    public static ChatClientBuilder UseChatHistoryPersisting(this ChatClientBuilder builder, bool markOnly = false)
-    {
-        return builder.Use(innerClient => new ChatHistoryPersistingChatClient(innerClient, markOnly));
-    }
 }
@@ -63,15 +63,6 @@ public static class ChatClientExtensions
            });
        }

-        // ChatHistoryPersistingChatClient is registered after FunctionInvokingChatClient so that it sits
-        // between FIC and the leaf client. ChatClientBuilder.Build applies factories in reverse order,
-        // making the first Use() call outermost. By adding our decorator second, the resulting pipeline is:
-        //   FunctionInvokingChatClient → ChatHistoryPersistingChatClient → leaf IChatClient
-        // This allows the decorator to persist messages after each individual service call within
-        // FIC's function invocation loop, or to mark them for later persistence at the end of the run.
-        bool markOnly = options?.PersistChatHistoryAtEndOfRun is true;
-        chatBuilder.Use(innerClient => new ChatHistoryPersistingChatClient(innerClient, markOnly));
-
        var agentChatClient = chatBuilder.Build(services);

        if (options?.ChatOptions?.Tools is { Count: > 0 })
@@ -1,313 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Runtime.CompilerServices;
-using System.Threading;
-using System.Threading.Tasks;
-using Microsoft.Extensions.AI;
-
-namespace Microsoft.Agents.AI;
-
-/// <summary>
-/// A delegating chat client that notifies <see cref="ChatHistoryProvider"/> and <see cref="AIContextProvider"/>
-/// instances of request and response messages after each individual call to the inner chat client,
-/// or marks messages for later persistence depending on the configured mode.
-/// </summary>
-/// <remarks>
-/// <para>
-/// This decorator is intended to operate between the <see cref="FunctionInvokingChatClient"/> and the leaf
-/// <see cref="IChatClient"/> in a <see cref="ChatClientAgent"/> pipeline.
-/// </para>
-/// <para>
-/// In persist mode (the default), it ensures that providers are notified and the session's
-/// <see cref="ChatClientAgentSession.ConversationId"/> is updated after each service call, so that
-/// intermediate messages (e.g., tool calls and results) are saved even if the process is interrupted
-/// mid-loop.
-/// </para>
-/// <para>
-/// In mark-only mode (<see cref="MarkOnly"/> is <see langword="true"/>), it marks messages with metadata
-/// but does not notify providers or update the <see cref="ChatClientAgentSession.ConversationId"/>.
-/// Both are deferred to the <see cref="ChatClientAgent"/> at the end of the run, providing atomic
-/// run semantics.
-/// </para>
-/// <para>
-/// This chat client must be used within the context of a running <see cref="ChatClientAgent"/>. It retrieves the
-/// current agent and session from <see cref="AIAgent.CurrentRunContext"/>, which is set automatically when an agent's
-/// <see cref="AIAgent.RunAsync(IEnumerable{ChatMessage}, AgentSession?, AgentRunOptions?, CancellationToken)"/> or
-/// <see cref="AIAgent.RunStreamingAsync(IEnumerable{ChatMessage}, AgentSession?, AgentRunOptions?, CancellationToken)"/>
-/// method is called. The <see cref="ChatClientAgent"/> ensures the run context always contains a resolved session,
-/// even when the caller passes null. An <see cref="InvalidOperationException"/> is thrown if no run context is
-/// available or if the agent is not a <see cref="ChatClientAgent"/>.
-/// </para>
-/// </remarks>
-internal sealed class ChatHistoryPersistingChatClient : DelegatingChatClient
-{
-    /// <summary>
-    /// The key used in <see cref="ChatMessage.AdditionalProperties"/> and <see cref="AIContent.AdditionalProperties"/>
-    /// to mark messages and their content as already persisted to chat history.
-    /// </summary>
-    internal const string PersistedMarkerKey = "_chatHistoryPersisted";
-
-    /// <summary>
-    /// Initializes a new instance of the <see cref="ChatHistoryPersistingChatClient"/> class.
-    /// </summary>
-    /// <param name="innerClient">The underlying chat client that will handle the core operations.</param>
-    /// <param name="markOnly">
-    /// When <see langword="true"/>, messages are marked with metadata but not persisted immediately,
-    /// and the session's <see cref="ChatClientAgentSession.ConversationId"/> is not updated.
-    /// The <see cref="ChatClientAgent"/> will persist only the marked messages and update the
-    /// conversation ID at the end of the run.
-    /// When <see langword="false"/> (the default), messages are persisted and the conversation ID
-    /// is updated immediately after each service call.
-    /// </param>
-    public ChatHistoryPersistingChatClient(IChatClient innerClient, bool markOnly = false)
-        : base(innerClient)
-    {
-        this.MarkOnly = markOnly;
-    }
-
-    /// <summary>
-    /// Gets a value indicating whether this decorator is in mark-only mode.
-    /// </summary>
-    /// <remarks>
-    /// When <see langword="true"/>, messages are marked with metadata but not persisted immediately,
-    /// and the session's <see cref="ChatClientAgentSession.ConversationId"/> is not updated.
-    /// Both are deferred to the <see cref="ChatClientAgent"/> at the end of the run.
-    /// When <see langword="false"/>, messages are persisted and the conversation ID is updated
-    /// after each service call.
-    /// </remarks>
-    public bool MarkOnly { get; }
-
-    /// <inheritdoc/>
-    public override async Task<ChatResponse> GetResponseAsync(
-        IEnumerable<ChatMessage> messages,
-        ChatOptions? options = null,
-        CancellationToken cancellationToken = default)
-    {
-        var (agent, session) = GetRequiredAgentAndSession();
-
-        ChatResponse response;
-        try
-        {
-            response = await base.GetResponseAsync(messages, options, cancellationToken).ConfigureAwait(false);
-        }
-        catch (Exception ex)
-        {
-            var newRequestMessagesOnFailure = GetNewRequestMessages(messages);
-            await agent.NotifyProvidersOfFailureAsync(session, ex, newRequestMessagesOnFailure, options, cancellationToken).ConfigureAwait(false);
-            throw;
-        }
-
-        var newRequestMessages = GetNewRequestMessages(messages);
-
-        if (this.ShouldDeferPersistence(options))
-        {
-            // In mark-only mode or when resuming from a continuation token, just mark messages
-            // for later persistence by ChatClientAgent. Conversation ID and provider notification
-            // are deferred to end-of-run. For continuation tokens, the end-of-run handler needs
-            // to send the combined data from both the previous and current runs.
-            MarkAsPersisted(newRequestMessages);
-            MarkAsPersisted(response.Messages);
-        }
-        else
-        {
-            // In persist mode, persist immediately and update conversation ID.
-            agent.UpdateSessionConversationId(session, response.ConversationId, cancellationToken);
-            await agent.NotifyProvidersOfNewMessagesAsync(session, newRequestMessages, response.Messages, options, cancellationToken).ConfigureAwait(false);
-            MarkAsPersisted(newRequestMessages);
-            MarkAsPersisted(response.Messages);
-        }
-
-        return response;
-    }
-
-    /// <inheritdoc/>
-    public override async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
-        IEnumerable<ChatMessage> messages,
-        ChatOptions? options = null,
-        [EnumeratorCancellation] CancellationToken cancellationToken = default)
-    {
-        var (agent, session) = GetRequiredAgentAndSession();
-
-        List<ChatResponseUpdate> responseUpdates = [];
-
-        IAsyncEnumerator<ChatResponseUpdate> enumerator;
-        try
-        {
-            enumerator = base.GetStreamingResponseAsync(messages, options, cancellationToken).GetAsyncEnumerator(cancellationToken);
-        }
-        catch (Exception ex)
-        {
-            var newRequestMessagesOnFailure = GetNewRequestMessages(messages);
-            await agent.NotifyProvidersOfFailureAsync(session, ex, newRequestMessagesOnFailure, options, cancellationToken).ConfigureAwait(false);
-            throw;
-        }
-
-        bool hasUpdates;
-        try
-        {
-            hasUpdates = await enumerator.MoveNextAsync().ConfigureAwait(false);
-        }
-        catch (Exception ex)
-        {
-            var newRequestMessagesOnFailure = GetNewRequestMessages(messages);
-            await agent.NotifyProvidersOfFailureAsync(session, ex, newRequestMessagesOnFailure, options, cancellationToken).ConfigureAwait(false);
-            throw;
-        }
-
-        while (hasUpdates)
-        {
-            var update = enumerator.Current;
-            responseUpdates.Add(update);
-            yield return update;
-
-            try
-            {
-                hasUpdates = await enumerator.MoveNextAsync().ConfigureAwait(false);
-            }
-            catch (Exception ex)
-            {
-                var newRequestMessagesOnFailure = GetNewRequestMessages(messages);
-                await agent.NotifyProvidersOfFailureAsync(session, ex, newRequestMessagesOnFailure, options, cancellationToken).ConfigureAwait(false);
-                throw;
-            }
-        }
-
-        var chatResponse = responseUpdates.ToChatResponse();
-        var newRequestMessages = GetNewRequestMessages(messages);
-
-        if (this.ShouldDeferPersistence(options))
-        {
-            // In mark-only mode or when resuming from a continuation token, just mark messages
-            // for later persistence by ChatClientAgent. Conversation ID and provider notification
-            // are deferred to end-of-run. For continuation tokens, the end-of-run handler needs
-            // to send the combined data from both the previous and current runs.
-            MarkAsPersisted(newRequestMessages);
-            MarkAsPersisted(chatResponse.Messages);
-        }
-        else
-        {
-            // In persist mode, persist immediately and update conversation ID.
-            agent.UpdateSessionConversationId(session, chatResponse.ConversationId, cancellationToken);
-            await agent.NotifyProvidersOfNewMessagesAsync(session, newRequestMessages, chatResponse.Messages, options, cancellationToken).ConfigureAwait(false);
-            MarkAsPersisted(newRequestMessages);
-            MarkAsPersisted(chatResponse.Messages);
-        }
-    }
-
-    /// <summary>
-    /// Gets the current <see cref="ChatClientAgent"/> and <see cref="ChatClientAgentSession"/> from the run context.
-    /// </summary>
-    private static (ChatClientAgent Agent, ChatClientAgentSession Session) GetRequiredAgentAndSession()
-    {
-        var runContext = AIAgent.CurrentRunContext
-            ?? throw new InvalidOperationException(
-                $"{nameof(ChatHistoryPersistingChatClient)} can only be used within the context of a running AIAgent. " +
-                "Ensure that the chat client is being invoked as part of an AIAgent.RunAsync or AIAgent.RunStreamingAsync call.");
-
-        var chatClientAgent = runContext.Agent.GetService<ChatClientAgent>()
-            ?? throw new InvalidOperationException(
-                $"{nameof(ChatHistoryPersistingChatClient)} can only be used with a {nameof(ChatClientAgent)}. " +
-                $"The current agent is of type '{runContext.Agent.GetType().Name}'.");
-
-        if (runContext.Session is not ChatClientAgentSession chatClientAgentSession)
-        {
-            throw new InvalidOperationException(
-                $"{nameof(ChatHistoryPersistingChatClient)} requires a {nameof(ChatClientAgentSession)}. " +
-                $"The current session is of type '{runContext.Session?.GetType().Name ?? "null"}'.");
-        }
-
-        return (chatClientAgent, chatClientAgentSession);
-    }
-
-    /// <summary>
-    /// Determines whether persistence should be deferred to end-of-run instead of happening immediately.
-    /// </summary>
-    /// <returns>
-    /// <see langword="true"/> when in <see cref="MarkOnly"/> mode, when the call is resuming from
-    /// a continuation token (since the end-of-run handler needs to combine data from the previous
-    /// and current runs), or when background responses are allowed (since the caller may stop
-    /// consuming the stream mid-run, preventing the post-stream persistence code from executing).
-    /// </returns>
-    private bool ShouldDeferPersistence(ChatOptions? options)
-    {
-        return this.MarkOnly || options?.ContinuationToken is not null || options?.AllowBackgroundResponses is true;
-    }
-
-    /// <summary>
-    /// Returns only the request messages that have not yet been persisted to chat history.
-    /// </summary>
-    /// <remarks>
-    /// A message is considered already persisted if any of the following is true:
-    /// <list type="bullet">
-    /// <item>It has the <see cref="PersistedMarkerKey"/> in its <see cref="ChatMessage.AdditionalProperties"/>.</item>
-    /// <item>It has an <see cref="AgentRequestMessageSourceType"/> of <see cref="AgentRequestMessageSourceType.ChatHistory"/>
-    /// (indicating it was loaded from chat history and does not need to be re-persisted).</item>
-    /// <item>It has <see cref="ChatMessage.Contents"/> and all of its <see cref="AIContent"/> items have the
-    /// <see cref="PersistedMarkerKey"/> in their <see cref="AIContent.AdditionalProperties"/>. This handles the
-    /// streaming case where <see cref="FunctionInvokingChatClient"/> reconstructs <see cref="ChatMessage"/> objects
-    /// independently via <c>ToChatResponse()</c>, producing different object references that share the same
-    /// underlying <see cref="AIContent"/> instances.</item>
-    /// </list>
-    /// </remarks>
-    /// <returns>A list of request messages that have not yet been persisted.</returns>
-    /// <param name="messages">The full set of request messages to filter.</param>
-    private static List<ChatMessage> GetNewRequestMessages(IEnumerable<ChatMessage> messages)
-    {
-        return messages.Where(m => !IsAlreadyPersisted(m)).ToList();
-    }
-
-    /// <summary>
-    /// Determines whether a message has already been persisted to chat history by this decorator.
-    /// </summary>
-    private static bool IsAlreadyPersisted(ChatMessage message)
-    {
-        if (message.AdditionalProperties?.TryGetValue(PersistedMarkerKey, out var value) == true && value is true)
-        {
-            return true;
-        }
-
-        if (message.GetAgentRequestMessageSourceType() == AgentRequestMessageSourceType.ChatHistory)
-        {
-            return true;
-        }
-
-        // In streaming mode, FunctionInvokingChatClient reconstructs ChatMessage objects via ToChatResponse()
-        // independently, producing different ChatMessage instances. However, the underlying AIContent objects
-        // (e.g., FunctionCallContent, FunctionResultContent) are shared references. Checking for markers on
-        // AIContent handles dedup in this case.
-        if (message.Contents.Count > 0 && message.Contents.All(c => c.AdditionalProperties?.TryGetValue(PersistedMarkerKey, out var value) == true && value is true))
-        {
-            return true;
-        }
-
-        return false;
-    }
-
-    /// <summary>
-    /// Marks the given messages as persisted by setting a marker on both the <see cref="ChatMessage"/>
-    /// and each of its <see cref="AIContent"/> items.
-    /// </summary>
-    /// <remarks>
-    /// Both levels are marked because <see cref="FunctionInvokingChatClient"/> may reconstruct
-    /// <see cref="ChatMessage"/> objects in streaming mode (losing the message-level marker),
-    /// but the <see cref="AIContent"/> references are shared and retain their markers.
-    /// </remarks>
-    /// <param name="messages">The messages to mark as persisted.</param>
-    private static void MarkAsPersisted(IEnumerable<ChatMessage> messages)
-    {
-        foreach (var message in messages)
-        {
-            message.AdditionalProperties ??= new();
-            message.AdditionalProperties[PersistedMarkerKey] = true;
-
-            foreach (var content in message.Contents)
-            {
-                content.AdditionalProperties ??= new();
-                content.AdditionalProperties[PersistedMarkerKey] = true;
-            }
-        }
-    }
-}
@@ -5,8 +5,6 @@ using System.Reflection;
 using System.Text;
 using Microsoft.Extensions.Configuration;
 using Microsoft.Extensions.Logging;
-using ModelContextProtocol.Client;
-using ModelContextProtocol.Protocol;
 namespace Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests;

 /// <summary>
@@ -237,114 +235,6 @@ public sealed class WorkflowSamplesValidation(ITestOutputHelper outputHelper) :
        });
    }

-    [Fact]
-    public async Task WorkflowMcpToolSampleValidationAsync()
-    {
-        string samplePath = Path.Combine(s_samplesPath, "04_WorkflowMcpTool");
-        await this.RunSampleTestAsync(samplePath, requiresOpenAI: false, async (logs) =>
-        {
-            // Connect to the MCP endpoint exposed by the Azure Functions host
-            IClientTransport clientTransport = new HttpClientTransport(new()
-            {
-                Endpoint = new Uri($"http://localhost:{AzureFunctionsPort}/runtime/webhooks/mcp")
-            });
-
-            await using McpClient mcpClient = await McpClient.CreateAsync(clientTransport);
-
-            // Verify both workflow tools are listed
-            IList<McpClientTool> tools = await mcpClient.ListToolsAsync();
-            this._outputHelper.WriteLine($"MCP tools found: {string.Join(", ", tools.Select(t => t.Name))}");
-
-            Assert.Single(tools, t => t.Name == "Translate");
-            Assert.Single(tools, t => t.Name == "OrderLookup");
-
-            // Invoke the Translate workflow via MCP tool (returns a string result)
-            this._outputHelper.WriteLine("Invoking MCP tool 'Translate'...");
-            CallToolResult translateResult = await mcpClient.CallToolAsync(
-                "Translate",
-                arguments: new Dictionary<string, object?> { { "input", "hello world" } });
-
-            Assert.NotEmpty(translateResult.Content);
-            string translateResponse = Assert.IsType<TextContentBlock>(translateResult.Content[0]).Text;
-            this._outputHelper.WriteLine($"Translate MCP tool response: {translateResponse}");
-            Assert.NotEmpty(translateResponse);
-            Assert.Contains("HELLO WORLD", translateResponse);
-
-            // Invoke the OrderLookup workflow via MCP tool (returns a POCO serialized as JSON)
-            this._outputHelper.WriteLine("Invoking MCP tool 'OrderLookup'...");
-            CallToolResult orderResult = await mcpClient.CallToolAsync(
-                "OrderLookup",
-                arguments: new Dictionary<string, object?> { { "input", "ORD-2025-42" } });
-
-            Assert.NotEmpty(orderResult.Content);
-            string orderResponse = Assert.IsType<TextContentBlock>(orderResult.Content[0]).Text;
-            this._outputHelper.WriteLine($"OrderLookup MCP tool response: {orderResponse}");
-            Assert.NotEmpty(orderResponse);
-            Assert.Contains("ORD-2025-42", orderResponse);
-
-            // Verify executor activities ran in the logs
-            lock (logs)
-            {
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] TranslateText:")), "TranslateText activity not found in logs.");
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] FormatOutput:")), "FormatOutput activity not found in logs.");
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] LookupOrder:")), "LookupOrder activity not found in logs.");
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] EnrichOrder:")), "EnrichOrder activity not found in logs.");
-            }
-        });
-    }
-
-    [Fact]
-    public async Task WorkflowAndAgentsSampleValidationAsync()
-    {
-        string samplePath = Path.Combine(s_samplesPath, "05_WorkflowAndAgents");
-        await this.RunSampleTestAsync(samplePath, requiresOpenAI: true, async (logs) =>
-        {
-            // Connect to the MCP endpoint exposed by the Azure Functions host
-            IClientTransport clientTransport = new HttpClientTransport(new()
-            {
-                Endpoint = new Uri($"http://localhost:{AzureFunctionsPort}/runtime/webhooks/mcp")
-            });
-
-            await using McpClient mcpClient = await McpClient.CreateAsync(clientTransport);
-
-            // Verify both the agent and workflow tools are listed
-            IList<McpClientTool> tools = await mcpClient.ListToolsAsync();
-            this._outputHelper.WriteLine($"MCP tools found: {string.Join(", ", tools.Select(t => t.Name))}");
-
-            Assert.Single(tools, t => t.Name == "Assistant");
-            Assert.Single(tools, t => t.Name == "Translate");
-
-            // Invoke the Translate workflow via MCP tool
-            this._outputHelper.WriteLine("Invoking MCP tool 'Translate'...");
-            CallToolResult translateResult = await mcpClient.CallToolAsync(
-                "Translate",
-                arguments: new Dictionary<string, object?> { { "input", "hello world" } });
-
-            Assert.NotEmpty(translateResult.Content);
-            string translateResponse = Assert.IsType<TextContentBlock>(translateResult.Content[0]).Text;
-            this._outputHelper.WriteLine($"Translate MCP tool response: {translateResponse}");
-            Assert.Contains("HELLO WORLD", translateResponse);
-
-            // Invoke the Assistant agent via MCP tool
-            this._outputHelper.WriteLine("Invoking MCP tool 'Assistant'...");
-            CallToolResult assistantResult = await mcpClient.CallToolAsync(
-                "Assistant",
-                arguments: new Dictionary<string, object?> { { "query", "What is 2 + 2?" } });
-
-            Assert.NotEmpty(assistantResult.Content);
-            string assistantResponse = Assert.IsType<TextContentBlock>(assistantResult.Content[0]).Text;
-            this._outputHelper.WriteLine($"Assistant MCP tool response: {assistantResponse}");
-            Assert.NotEmpty(assistantResponse);
-
-            // Verify workflow executor activities ran in the logs
-            lock (logs)
-            {
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] TranslateText:")), "TranslateText activity not found in logs.");
-                Assert.True(logs.Any(log => log.Message.Contains("[Activity] FormatOutput:")), "FormatOutput activity not found in logs.");
-            }
-        });
-    }
-
    [Fact]
    public async Task ConcurrentWorkflowSampleValidationAsync()
    {
@@ -148,45 +148,6 @@ public sealed class DurableAgentFunctionMetadataTransformerTests
        }
    }

-    [Fact]
-    public void Transform_SkipsAgents_WithoutExplicitOptions()
-    {
-        // Arrange: two agents in the dictionary, but only one has explicit FunctionsAgentOptions.
-        // This simulates a workflow-auto-registered agent (workflowAgent) alongside a standalone agent.
-        Dictionary<string, Func<IServiceProvider, AIAgent>> agents = new()
-        {
-            { "standaloneAgent", _ => new TestAgent("standaloneAgent", "Standalone agent") },
-            { "workflowAgent", _ => new TestAgent("workflowAgent", "Auto-registered by workflow") }
-        };
-
-        FunctionsAgentOptions standaloneOptions = new();
-        standaloneOptions.HttpTrigger.IsEnabled = true;
-
-        // Only standaloneAgent has explicit options; workflowAgent does not.
-        IFunctionsAgentOptionsProvider agentOptionsProvider = new FakeOptionsProvider(new Dictionary<string, FunctionsAgentOptions>
-        {
-            { "standaloneAgent", standaloneOptions }
-        });
-
-        List<IFunctionMetadata> metadataList = [];
-
-        DurableAgentFunctionMetadataTransformer transformer = new(
-            agents,
-            NullLogger<DurableAgentFunctionMetadataTransformer>.Instance,
-            new FakeServiceProvider(),
-            agentOptionsProvider);
-
-        // Act
-        transformer.Transform(metadataList);
-
-        // Assert: only standaloneAgent should have triggers (entity + http = 2).
-        // workflowAgent should be skipped entirely.
-        Assert.Equal(2, metadataList.Count);
-        Assert.Contains(metadataList, m => m.Name == "dafx-standaloneAgent");
-        Assert.Contains(metadataList, m => m.Name == "http-standaloneAgent");
-        Assert.DoesNotContain(metadataList, m => m.Name!.Contains("workflowAgent"));
-    }
-
    private static List<IFunctionMetadata> BuildFunctionMetadataList(int numberOfFunctions)
    {
        List<IFunctionMetadata> list = [];
@@ -1,121 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Text.Json;
-using Microsoft.Azure.Functions.Worker.Core.FunctionMetadata;
-
-namespace Microsoft.Agents.AI.Hosting.AzureFunctions.UnitTests;
-
-public sealed class FunctionMetadataFactoryTests
-{
-    [Fact]
-    public void CreateEntityTrigger_SetsCorrectNameAndBindings()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateEntityTrigger("myAgent");
-
-        Assert.Equal("dafx-myAgent", metadata.Name);
-        Assert.Equal("dotnet-isolated", metadata.Language);
-        Assert.Equal(BuiltInFunctions.RunAgentEntityFunctionEntryPoint, metadata.EntryPoint);
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Equal(2, metadata.RawBindings.Count);
-        Assert.Contains("entityTrigger", metadata.RawBindings[0]);
-        Assert.Contains("durableClient", metadata.RawBindings[1]);
-    }
-
-    [Fact]
-    public void CreateHttpTrigger_SetsCorrectNameRouteAndDefaults()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateHttpTrigger(
-            "myWorkflow", "workflows/myWorkflow/run", BuiltInFunctions.RunWorkflowOrchestrationHttpFunctionEntryPoint);
-
-        Assert.Equal("http-myWorkflow", metadata.Name);
-        Assert.Equal("dotnet-isolated", metadata.Language);
-        Assert.Equal(BuiltInFunctions.RunWorkflowOrchestrationHttpFunctionEntryPoint, metadata.EntryPoint);
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Equal(3, metadata.RawBindings.Count);
-        Assert.Contains("httpTrigger", metadata.RawBindings[0]);
-        Assert.Contains("workflows/myWorkflow/run", metadata.RawBindings[0]);
-        Assert.Contains("\"post\"", metadata.RawBindings[0]);
-        Assert.Contains("http", metadata.RawBindings[1]);
-        Assert.Contains("durableClient", metadata.RawBindings[2]);
-    }
-
-    [Fact]
-    public void CreateHttpTrigger_RespectsCustomMethods()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateHttpTrigger(
-            "status", "workflows/status/{runId}", BuiltInFunctions.GetWorkflowStatusHttpFunctionEntryPoint, methods: "\"get\"");
-
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Contains("\"get\"", metadata.RawBindings[0]);
-        Assert.DoesNotContain("\"post\"", metadata.RawBindings[0]);
-    }
-
-    [Fact]
-    public void CreateActivityTrigger_SetsCorrectNameAndBindings()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateActivityTrigger("dafx-MyExecutor");
-
-        Assert.Equal("dafx-MyExecutor", metadata.Name);
-        Assert.Equal("dotnet-isolated", metadata.Language);
-        Assert.Equal(BuiltInFunctions.InvokeWorkflowActivityFunctionEntryPoint, metadata.EntryPoint);
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Equal(2, metadata.RawBindings.Count);
-        Assert.Contains("activityTrigger", metadata.RawBindings[0]);
-        Assert.Contains("durableClient", metadata.RawBindings[1]);
-    }
-
-    [Fact]
-    public void CreateOrchestrationTrigger_SetsCorrectNameAndBindings()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateOrchestrationTrigger(
-            "dafx-MyWorkflow", BuiltInFunctions.RunWorkflowOrchestrationFunctionEntryPoint);
-
-        Assert.Equal("dafx-MyWorkflow", metadata.Name);
-        Assert.Equal("dotnet-isolated", metadata.Language);
-        Assert.Equal(BuiltInFunctions.RunWorkflowOrchestrationFunctionEntryPoint, metadata.EntryPoint);
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Single(metadata.RawBindings);
-        Assert.Contains("orchestrationTrigger", metadata.RawBindings[0]);
-    }
-
-    [Fact]
-    public void CreateWorkflowMcpToolTrigger_SetsCorrectNameAndBindings()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateWorkflowMcpToolTrigger("Translate", "Translate text");
-
-        Assert.Equal("mcptool-Translate", metadata.Name);
-        Assert.Equal("dotnet-isolated", metadata.Language);
-        Assert.Equal(BuiltInFunctions.RunWorkflowMcpToolFunctionEntryPoint, metadata.EntryPoint);
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Equal(3, metadata.RawBindings.Count);
-
-        // Verify all bindings are valid JSON
-        foreach (string binding in metadata.RawBindings)
-        {
-            JsonDocument.Parse(binding);
-        }
-
-        // mcpToolTrigger binding
-        Assert.Contains("mcpToolTrigger", metadata.RawBindings[0]);
-        Assert.Contains("\"toolName\":\"Translate\"", metadata.RawBindings[0]);
-        Assert.Contains("\"description\":\"Translate text\"", metadata.RawBindings[0]);
-        Assert.Contains("toolProperties", metadata.RawBindings[0]);
-
-        // mcpToolProperty binding for input
-        Assert.Contains("mcpToolProperty", metadata.RawBindings[1]);
-        Assert.Contains("\"propertyName\":\"input\"", metadata.RawBindings[1]);
-        Assert.Contains("\"isRequired\":true", metadata.RawBindings[1]);
-
-        // durableClient binding
-        Assert.Contains("durableClient", metadata.RawBindings[2]);
-    }
-
-    [Fact]
-    public void CreateWorkflowMcpToolTrigger_UsesDefaultDescription_WhenNull()
-    {
-        DefaultFunctionMetadata metadata = FunctionMetadataFactory.CreateWorkflowMcpToolTrigger("MyWorkflow", description: null);
-
-        Assert.NotNull(metadata.RawBindings);
-        Assert.Contains("Run the MyWorkflow workflow", metadata.RawBindings[0]);
-    }
-}
@@ -1,766 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Threading;
-using System.Threading.Tasks;
-using Microsoft.Extensions.AI;
-using Microsoft.Extensions.DependencyInjection;
-using Moq;
-using Moq.Protected;
-
-namespace Microsoft.Agents.AI.UnitTests;
-
-/// <summary>
-/// Contains unit tests for the <see cref="ChatHistoryPersistingChatClient"/> decorator,
-/// verifying that it persists messages via the <see cref="ChatHistoryProvider"/> after each
-/// individual service call by default, or marks messages for end-of-run persistence when the
-/// <see cref="ChatClientAgentOptions.PersistChatHistoryAtEndOfRun"/> option is enabled.
-/// </summary>
-public class ChatHistoryPersistingChatClientTests
-{
-    /// <summary>
-    /// Verifies that by default (PersistChatHistoryAtEndOfRun is false),
-    /// the ChatHistoryProvider receives messages after a successful non-streaming call.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_PersistsMessagesPerServiceCall_ByDefaultAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")]));
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert — InvokedCoreAsync should be called by the decorator (per service call)
-        mockChatHistoryProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<ChatHistoryProvider.InvokedContext>(x =>
-                    x.RequestMessages.Any(m => m.Text == "test") &&
-                    x.ResponseMessages!.Any(m => m.Text == "response")),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default),
-    /// the ChatHistoryProvider receives messages at the end of the run.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_PersistsMessagesAtEndOfRun_WhenOptionEnabledAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")]));
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = true,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert — InvokedCoreAsync should be called once by the agent (end of run)
-        mockChatHistoryProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<ChatHistoryProvider.InvokedContext>(x =>
-                    x.RequestMessages.Any(m => m.Text == "test") &&
-                    x.ResponseMessages!.Any(m => m.Text == "response")),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default) and the service call fails,
-    /// the ChatHistoryProvider is notified with the exception.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_NotifiesProviderOfFailure_WhenPerServiceCallPersistenceActiveAsync()
-    {
-        // Arrange
-        var expectedException = new InvalidOperationException("Service failed");
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ThrowsAsync(expectedException);
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await Assert.ThrowsAsync<InvalidOperationException>(() => agent.RunAsync([new(ChatRole.User, "test")], session));
-
-        // Assert — the decorator should have notified the provider of the failure
-        mockChatHistoryProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<ChatHistoryProvider.InvokedContext>(x =>
-                    x.InvokeException != null &&
-                    x.InvokeException.Message == "Service failed"),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that the decorator is injected in persist mode by default
-    /// and can be discovered via GetService.
-    /// </summary>
-    [Fact]
-    public void ChatClient_ContainsDecorator_InPersistMode_ByDefault()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-
-        // Act
-        ChatClientAgent agent = new(mockService.Object, options: new());
-
-        // Assert
-        var decorator = agent.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-        Assert.NotNull(decorator);
-        Assert.False(decorator.MarkOnly);
-    }
-
-    /// <summary>
-    /// Verifies that the decorator is injected in mark-only mode when PersistChatHistoryAtEndOfRun is true.
-    /// </summary>
-    [Fact]
-    public void ChatClient_ContainsDecorator_InMarkOnlyMode_WhenPersistAtEndOfRun()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-
-        // Act
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            PersistChatHistoryAtEndOfRun = true,
-        });
-
-        // Assert
-        var decorator = agent.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-        Assert.NotNull(decorator);
-        Assert.True(decorator.MarkOnly);
-    }
-
-    /// <summary>
-    /// Verifies that the decorator is NOT injected when UseProvidedChatClientAsIs is true.
-    /// </summary>
-    [Fact]
-    public void ChatClient_DoesNotContainDecorator_WhenUseProvidedChatClientAsIs()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-
-        // Act
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            UseProvidedChatClientAsIs = true,
-        });
-
-        // Assert
-        var decorator = agent.ChatClient.GetService<ChatHistoryPersistingChatClient>();
-        Assert.Null(decorator);
-    }
-
-    /// <summary>
-    /// Verifies that the PersistChatHistoryAtEndOfRun option is included in Clone().
-    /// </summary>
-    [Fact]
-    public void ChatClientAgentOptions_Clone_IncludesPersistChatHistoryAtEndOfRun()
-    {
-        // Arrange
-        var options = new ChatClientAgentOptions
-        {
-            PersistChatHistoryAtEndOfRun = true,
-        };
-
-        // Act
-        var cloned = options.Clone();
-
-        // Assert
-        Assert.True(cloned.PersistChatHistoryAtEndOfRun);
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default) and the service call
-    /// involves a function invocation loop, the ChatHistoryProvider is called after each individual
-    /// service call (not just once at the end).
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_PersistsPerServiceCall_DuringFunctionInvocationLoopAsync()
-    {
-        // Arrange
-        int serviceCallCount = 0;
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .Returns(() =>
-            {
-                serviceCallCount++;
-                if (serviceCallCount == 1)
-                {
-                    // First call returns a tool call
-                    return Task.FromResult(new ChatResponse([new(ChatRole.Assistant, [new FunctionCallContent("call1", "myTool", new Dictionary<string, object?>())])]));
-                }
-
-                // Second call returns a final response
-                return Task.FromResult(new ChatResponse([new(ChatRole.Assistant, "final response")]));
-            });
-
-        var invokedContexts = new List<ChatHistoryProvider.InvokedContext>();
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Callback((ChatHistoryProvider.InvokedContext ctx, CancellationToken _) => invokedContexts.Add(ctx))
-            .Returns(() => new ValueTask());
-
-        // Define a simple tool
-        var tool = AIFunctionFactory.Create(() => "tool result", "myTool", "A test tool");
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatOptions = new() { Tools = [tool] },
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        }, services: new ServiceCollection().BuildServiceProvider());
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        Exception? caughtException = null;
-        try
-        {
-            await agent.RunAsync([new(ChatRole.User, "test")], session);
-        }
-        catch (Exception ex)
-        {
-            caughtException = ex;
-        }
-
-        // Diagnostic: check if there was an unexpected exception
-        Assert.Null(caughtException);
-
-        // Assert — the decorator should have been called twice (once per service call in the function invocation loop)
-        Assert.Equal(2, serviceCallCount);
-        Assert.Equal(2, invokedContexts.Count);
-
-        // First invocation should have the user message as request and tool call response
-        Assert.NotNull(invokedContexts[0].ResponseMessages);
-        var firstRequestMessages = invokedContexts[0].RequestMessages.ToList();
-        Assert.Contains(firstRequestMessages, m => m.Text == "test");
-        Assert.Contains(invokedContexts[0].ResponseMessages!, m => m.Contents.OfType<FunctionCallContent>().Any());
-
-        // Second invocation: request messages should NOT include the original user message (already notified).
-        // It should only include messages added since the first call (assistant tool call + tool result).
-        Assert.NotNull(invokedContexts[1].ResponseMessages);
-        var secondRequestMessages = invokedContexts[1].RequestMessages.ToList();
-        Assert.DoesNotContain(secondRequestMessages, m => m.Text == "test");
-        Assert.Contains(invokedContexts[1].ResponseMessages!, m => m.Text == "final response");
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default) with streaming,
-    /// the ChatHistoryProvider receives messages after the stream completes.
-    /// </summary>
-    [Fact]
-    public async Task RunStreamingAsync_PersistsMessagesPerServiceCall_ByDefaultAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetStreamingResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .Returns(CreateAsyncEnumerableAsync(
-                new ChatResponseUpdate(ChatRole.Assistant, "streaming "),
-                new ChatResponseUpdate(ChatRole.Assistant, "response")));
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await foreach (var _ in agent.RunStreamingAsync([new(ChatRole.User, "test")], session))
-        {
-            // Consume stream
-        }
-
-        // Assert — InvokedCoreAsync should be called by the decorator
-        mockChatHistoryProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<ChatHistoryProvider.InvokedContext>(x =>
-                    x.RequestMessages.Any(m => m.Text == "test") &&
-                    x.ResponseMessages != null),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default),
-    /// AIContextProviders are also notified of new messages after a successful call.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_NotifiesAIContextProviders_ByDefaultAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")]));
-
-        Mock<AIContextProvider> mockContextProvider = new(null, null, null);
-        mockContextProvider.SetupGet(p => p.StateKeys).Returns(["TestAIContextProvider"]);
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask<AIContext>>("InvokingCoreAsync", ItExpr.IsAny<AIContextProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask<AIContext>(new AIContext()));
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<AIContextProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            AIContextProviders = [mockContextProvider.Object],
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert — InvokedCoreAsync should be called by the decorator for the AIContextProvider
-        mockContextProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<AIContextProvider.InvokedContext>(x =>
-                    x.ResponseMessages != null &&
-                    x.ResponseMessages.Any(m => m.Text == "response")),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default) and the service fails,
-    /// AIContextProviders are notified of the failure.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_NotifiesAIContextProvidersOfFailure_ByDefaultAsync()
-    {
-        // Arrange
-        var expectedException = new InvalidOperationException("Service failed");
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ThrowsAsync(expectedException);
-
-        Mock<AIContextProvider> mockContextProvider = new(null, null, null);
-        mockContextProvider.SetupGet(p => p.StateKeys).Returns(["TestAIContextProvider"]);
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask<AIContext>>("InvokingCoreAsync", ItExpr.IsAny<AIContextProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask<AIContext>(new AIContext()));
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<AIContextProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            AIContextProviders = [mockContextProvider.Object],
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await Assert.ThrowsAsync<InvalidOperationException>(() => agent.RunAsync([new(ChatRole.User, "test")], session));
-
-        // Assert — the decorator should have notified the AIContextProvider of the failure
-        mockContextProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<AIContextProvider.InvokedContext>(x =>
-                    x.InvokeException != null &&
-                    x.InvokeException.Message == "Service failed"),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is active (default),
-    /// both ChatHistoryProvider and AIContextProviders are notified together.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_NotifiesBothProviders_ByDefaultAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")]));
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask());
-
-        Mock<AIContextProvider> mockContextProvider = new(null, null, null);
-        mockContextProvider.SetupGet(p => p.StateKeys).Returns(["TestAIContextProvider"]);
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask<AIContext>>("InvokingCoreAsync", ItExpr.IsAny<AIContextProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask<AIContext>(new AIContext()));
-        mockContextProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<AIContextProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            AIContextProviders = [mockContextProvider.Object],
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert — both providers should have been notified
-        mockChatHistoryProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<ChatHistoryProvider.InvokedContext>(x =>
-                    x.ResponseMessages != null &&
-                    x.ResponseMessages.Any(m => m.Text == "response")),
-                ItExpr.IsAny<CancellationToken>());
-
-        mockContextProvider
-            .Protected()
-            .Verify<ValueTask>("InvokedCoreAsync", Times.Once(),
-                ItExpr.Is<AIContextProvider.InvokedContext>(x =>
-                    x.ResponseMessages != null &&
-                    x.ResponseMessages.Any(m => m.Text == "response")),
-                ItExpr.IsAny<CancellationToken>());
-    }
-
-    /// <summary>
-    /// Verifies that during a FIC loop, response messages from the first call are not
-    /// re-notified as request messages on the second call.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_DoesNotReNotifyResponseMessagesAsRequestMessages_DuringFicLoopAsync()
-    {
-        // Arrange
-        int serviceCallCount = 0;
-        var assistantToolCallMessage = new ChatMessage(ChatRole.Assistant, [new FunctionCallContent("call1", "myTool", new Dictionary<string, object?>())]);
-
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .Returns(() =>
-            {
-                serviceCallCount++;
-                if (serviceCallCount == 1)
-                {
-                    return Task.FromResult(new ChatResponse([assistantToolCallMessage]));
-                }
-
-                return Task.FromResult(new ChatResponse([new(ChatRole.Assistant, "final response")]));
-            });
-
-        var invokedContexts = new List<ChatHistoryProvider.InvokedContext>();
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Callback((ChatHistoryProvider.InvokedContext ctx, CancellationToken _) => invokedContexts.Add(ctx))
-            .Returns(() => new ValueTask());
-
-        var tool = AIFunctionFactory.Create(() => "tool result", "myTool", "A test tool");
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatOptions = new() { Tools = [tool] },
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        }, services: new ServiceCollection().BuildServiceProvider());
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert
-        Assert.Equal(2, invokedContexts.Count);
-
-        // The assistant tool call message was a response in call 1
-        Assert.Contains(invokedContexts[0].ResponseMessages!, m => ReferenceEquals(m, assistantToolCallMessage));
-
-        // It should NOT appear as a request in call 2 (it was already notified as a response)
-        var secondRequestMessages = invokedContexts[1].RequestMessages.ToList();
-        Assert.DoesNotContain(secondRequestMessages, m => ReferenceEquals(m, assistantToolCallMessage));
-    }
-
-    /// <summary>
-    /// Verifies that when a failure occurs on the second call in a FIC loop,
-    /// only new request messages (not previously notified) are sent in the failure notification.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_DeduplicatesRequestMessages_OnFailureDuringFicLoopAsync()
-    {
-        // Arrange
-        int serviceCallCount = 0;
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .Returns(() =>
-            {
-                serviceCallCount++;
-                if (serviceCallCount == 1)
-                {
-                    return Task.FromResult(new ChatResponse([new(ChatRole.Assistant, [new FunctionCallContent("call1", "myTool", new Dictionary<string, object?>())])]));
-                }
-
-                throw new InvalidOperationException("Service failure on second call");
-            });
-
-        var invokedContexts = new List<ChatHistoryProvider.InvokedContext>();
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Callback((ChatHistoryProvider.InvokedContext ctx, CancellationToken _) => invokedContexts.Add(ctx))
-            .Returns(() => new ValueTask());
-
-        var tool = AIFunctionFactory.Create(() => "tool result", "myTool", "A test tool");
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatOptions = new() { Tools = [tool] },
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        }, services: new ServiceCollection().BuildServiceProvider());
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await Assert.ThrowsAsync<InvalidOperationException>(() =>
-            agent.RunAsync([new(ChatRole.User, "test")], session));
-
-        // Assert — should have 2 notifications: success on call 1, failure on call 2
-        Assert.Equal(2, invokedContexts.Count);
-
-        // First notification: success, has user message as request
-        Assert.Null(invokedContexts[0].InvokeException);
-        Assert.Contains(invokedContexts[0].RequestMessages, m => m.Text == "test");
-
-        // Second notification: failure, should NOT include the user message (already notified)
-        Assert.NotNull(invokedContexts[1].InvokeException);
-        var failureRequestMessages = invokedContexts[1].RequestMessages.ToList();
-        Assert.DoesNotContain(failureRequestMessages, m => m.Text == "test");
-    }
-
-    /// <summary>
-    /// Verifies that after a successful run with per-service-call persistence, the notified
-    /// messages are stamped with the persisted marker so they are not re-notified.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_MarksNotifiedMessages_WithPersistedMarkerAsync()
-    {
-        // Arrange
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>())).ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")]));
-
-        Mock<ChatHistoryProvider> mockChatHistoryProvider = new(null, null, null);
-        mockChatHistoryProvider.SetupGet(p => p.StateKeys).Returns(["TestChatHistoryProvider"]);
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask<IEnumerable<ChatMessage>>>("InvokingCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokingContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns((ChatHistoryProvider.InvokingContext ctx, CancellationToken _) =>
-                new ValueTask<IEnumerable<ChatMessage>>(ctx.RequestMessages.ToList()));
-        mockChatHistoryProvider
-            .Protected()
-            .Setup<ValueTask>("InvokedCoreAsync", ItExpr.IsAny<ChatHistoryProvider.InvokedContext>(), ItExpr.IsAny<CancellationToken>())
-            .Returns(() => new ValueTask());
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            ChatHistoryProvider = mockChatHistoryProvider.Object,
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var inputMessage = new ChatMessage(ChatRole.User, "test");
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([inputMessage], session);
-
-        // Assert — input message should be marked as persisted
-        Assert.True(
-            inputMessage.AdditionalProperties?.ContainsKey(ChatHistoryPersistingChatClient.PersistedMarkerKey) == true,
-            "Input message should be marked as persisted after a successful run.");
-    }
-
-    /// <summary>
-    /// Verifies that when per-service-call persistence is enabled and the inner client returns a
-    /// conversation ID, the session's ConversationId is updated after the service call.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_UpdatesSessionConversationId_WhenPerServiceCallPersistenceEnabledAsync()
-    {
-        // Arrange
-        const string ExpectedConversationId = "conv-123";
-
-        Mock<IChatClient> mockService = new();
-        mockService.Setup(
-            s => s.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .ReturnsAsync(new ChatResponse([new(ChatRole.Assistant, "response")])
-            {
-                ConversationId = ExpectedConversationId,
-            });
-
-        ChatClientAgent agent = new(mockService.Object, options: new()
-        {
-            PersistChatHistoryAtEndOfRun = false,
-        });
-
-        // Act
-        var session = await agent.CreateSessionAsync() as ChatClientAgentSession;
-        await agent.RunAsync([new(ChatRole.User, "test")], session);
-
-        // Assert — session should have the conversation ID returned by the inner client
-        Assert.Equal(ExpectedConversationId, session!.ConversationId);
-    }
-
-    private static async IAsyncEnumerable<ChatResponseUpdate> CreateAsyncEnumerableAsync(params ChatResponseUpdate[] updates)
-    {
-        foreach (var update in updates)
-        {
-            yield return update;
-        }
-
-        await Task.CompletedTask;
-    }
-}
@@ -9,173 +9,49 @@ using Microsoft.Agents.AI.Workflows.Checkpointing;

 namespace Microsoft.Agents.AI.Workflows.UnitTests;

-internal sealed class TempDirectory : IDisposable
-{
-    public DirectoryInfo DirectoryInfo { get; }
-
-    public TempDirectory()
-    {
-        string tempDirPath = Path.Combine(Path.GetTempPath(), Guid.NewGuid().ToString());
-        this.DirectoryInfo = Directory.CreateDirectory(tempDirPath);
-    }
-
-    public void Dispose()
-    {
-        this.DisposeInternal();
-        GC.SuppressFinalize(this);
-    }
-
-    private void DisposeInternal()
-    {
-        if (this.DirectoryInfo.Exists)
-        {
-            try
-            {
-                // Best efforts
-                this.DirectoryInfo.Delete(recursive: true);
-            }
-            catch { }
-        }
-    }
-
-    ~TempDirectory()
-    {
-        // Best efforts
-        this.DisposeInternal();
-    }
-
-    public static implicit operator DirectoryInfo(TempDirectory tempDirectory) => tempDirectory.DirectoryInfo;
-
-    public string FullName => this.DirectoryInfo.FullName;
-
-    public bool IsParentOf(FileInfo candidate)
-    {
-        if (candidate.Directory is null)
-        {
-            return false;
-        }
-
-        if (candidate.Directory.FullName == this.DirectoryInfo.FullName)
-        {
-            return true;
-        }
-
-        return this.IsParentOf(candidate.Directory);
-    }
-
-    public bool IsParentOf(DirectoryInfo candidate)
-    {
-        while (candidate.Parent is not null)
-        {
-            if (candidate.Parent.FullName == this.DirectoryInfo.FullName)
-            {
-                return true;
-            }
-
-            candidate = candidate.Parent;
-        }
-
-        return false;
-    }
-}
 public sealed class FileSystemJsonCheckpointStoreTests
 {
-    public static JsonElement TestData => JsonSerializer.SerializeToElement(new { test = "data" });
-
    [Fact]
    public async Task CreateCheckpointAsync_ShouldPersistIndexToDiskBeforeDisposeAsync()
    {
        // Arrange
-        using TempDirectory tempDirectory = new();
-        using FileSystemJsonCheckpointStore? store = new(tempDirectory);
+        DirectoryInfo tempDir = new(Path.Combine(Path.GetTempPath(), Guid.NewGuid().ToString()));
+        FileSystemJsonCheckpointStore? store = null;

-        string runId = Guid.NewGuid().ToString("N");
-
-        // Act
-        CheckpointInfo checkpoint = await store.CreateCheckpointAsync(runId, TestData);
-
-        // Assert - Check the file size before disposing to verify data was flushed to disk
-        // The index.jsonl file is held exclusively by the store, so we check via FileInfo
-        string indexPath = Path.Combine(tempDirectory.FullName, "index.jsonl");
-        FileInfo indexFile = new(indexPath);
-        indexFile.Refresh();
-        long fileSizeBeforeDispose = indexFile.Length;
-
-        // Data should already be on disk (file size > 0) before we dispose
-        fileSizeBeforeDispose.Should().BeGreaterThan(0, "index.jsonl should be flushed to disk after CreateCheckpointAsync");
-
-        // Dispose to release file lock before final verification
-        store.Dispose();
-
-        string[] lines = File.ReadAllLines(indexPath);
-        lines.Should().HaveCount(1);
-        lines[0].Should().Contain(checkpoint.CheckpointId);
-    }
-
-    private async ValueTask Run_EscapeRootFolderTestAsync(string escapingPath)
-    {
-        // Arrange
-        using TempDirectory tempDirectory = new();
-        using FileSystemJsonCheckpointStore store = new(tempDirectory);
-
-        string naivePath = Path.Combine(tempDirectory.DirectoryInfo.FullName, escapingPath);
-
-        // Check that the naive path is actually outside the temp directory to validate the test is meaningful
-        FileInfo naiveCheckpointFile = new(naivePath);
-        tempDirectory.IsParentOf(naiveCheckpointFile).Should().BeFalse("The naive path should be outside the root folder to validate that escaping is necessary.");
-
-        // Act
-        CheckpointInfo checkpointInfo = await store.CreateCheckpointAsync(escapingPath, TestData);
-
-        // Assert
-        string naivePathWithCheckpointId = Path.Combine(tempDirectory.DirectoryInfo.FullName, $"{escapingPath}_{checkpointInfo.CheckpointId}.json");
-        new FileInfo(naivePathWithCheckpointId).Exists.Should().BeFalse("The naive path should not be used to save a checkpoint file.");
-
-        string actualFileName = store.GetFileNameForCheckpoint(escapingPath, checkpointInfo);
-        string actualFilePath = Path.Combine(tempDirectory.DirectoryInfo.FullName, actualFileName);
-        FileInfo actualFile = new(actualFilePath);
-
-        tempDirectory.IsParentOf(actualFile).Should().BeTrue("The actual checkpoint should be saved inside the root folder.");
-        actualFile.Exists.Should().BeTrue("The actual path should be used to save a checkpoint file.");
-    }
-
-    [Fact]
-    public async Task CreateCheckpointAsync_ShouldNotEscapeRootFolderAsync()
-    {
-        // The SessionId is used as part of the file name, but if it contains path characters such as /.. it can escape the root folder.
-        // Testing that such characters are escaped properly to prevent directory traversal attacks, etc.
-
-        await this.Run_EscapeRootFolderTestAsync("../valid_suffix");
-
-#if !NETFRAMEWORK
-        if (OperatingSystem.IsWindows())
+        try
        {
-            // Windows allows both \ and / as path separators, so we test both
-            await this.Run_EscapeRootFolderTestAsync("..\\valid_suffix");
+            store = new(tempDir);
+            string runId = Guid.NewGuid().ToString("N");
+            JsonElement testData = JsonSerializer.SerializeToElement(new { test = "data" });
+
+            // Act
+            CheckpointInfo checkpoint = await store.CreateCheckpointAsync(runId, testData);
+
+            // Assert - Check the file size before disposing to verify data was flushed to disk
+            // The index.jsonl file is held exclusively by the store, so we check via FileInfo
+            string indexPath = Path.Combine(tempDir.FullName, "index.jsonl");
+            FileInfo indexFile = new(indexPath);
+            indexFile.Refresh();
+            long fileSizeBeforeDispose = indexFile.Length;
+
+            // Data should already be on disk (file size > 0) before we dispose
+            fileSizeBeforeDispose.Should().BeGreaterThan(0, "index.jsonl should be flushed to disk after CreateCheckpointAsync");
+
+            // Dispose to release file lock before final verification
+            store.Dispose();
+            store = null;
+
+            string[] lines = File.ReadAllLines(indexPath);
+            lines.Should().HaveCount(1);
+            lines[0].Should().Contain(checkpoint.CheckpointId);
+        }
+        finally
+        {
+            store?.Dispose();
+            if (tempDir.Exists)
+            {
+                tempDir.Delete(recursive: true);
+            }
        }
-#else
-        // .NET Framework is always on Windows
-        await this.Run_EscapeRootFolderTestAsync("..\\valid_suffix");
-#endif
-    }
-
-    private const string InvalidPathCharsWin32 = "\\/:*?\"<>|";
-    private const string InvalidPathCharsUnix = "/";
-    private const string InvalidPathCharsMacOS = "/:";
-
-    [Theory]
-    [InlineData(InvalidPathCharsWin32)]
-    [InlineData(InvalidPathCharsUnix)]
-    [InlineData(InvalidPathCharsMacOS)]
-    public async Task CreateCheckpointAsync_EscapesInvalidCharsAsync(string invalidChars)
-    {
-        // Arrange
-        using TempDirectory tempDirectory = new();
-        using FileSystemJsonCheckpointStore store = new(tempDirectory);
-
-        string runId = $"prefix_{invalidChars}_suffix";
-
-        Func<Task> createCheckpointAction = async () => await store.CreateCheckpointAsync(runId, TestData);
-        await createCheckpointAction.Should().NotThrowAsync();
    }
 }
@@ -24,14 +24,14 @@ If you only need specific integrations, you can install at a more granular level
 # also includes workflows and orchestrations
 pip install agent-framework-core --pre

-# Core + Azure AI Foundry integration
-pip install agent-framework-foundry --pre
+# Core + Azure AI integration
+pip install agent-framework-azure-ai --pre

 # Core + Microsoft Copilot Studio integration
 pip install agent-framework-copilotstudio --pre

-# Core + both Microsoft Copilot Studio and Azure AI Foundry integration
-pip install agent-framework-microsoft agent-framework-foundry --pre
+# Core + both Microsoft Copilot Studio and Azure AI integration
+pip install agent-framework-microsoft agent-framework-azure-ai --pre
 ```

 This selective approach is useful when you know which integrations you need, and it is the recommended way to set up lightweight environments.
@@ -53,8 +53,8 @@ AZURE_OPENAI_API_KEY=...
 AZURE_OPENAI_ENDPOINT=...
 AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=...
 ...
-FOUNDRY_PROJECT_ENDPOINT=...
-FOUNDRY_MODEL=...
+AZURE_AI_PROJECT_ENDPOINT=...
+AZURE_AI_MODEL_DEPLOYMENT_NAME=...
 ```

 You can also override environment variables by explicitly passing configuration parameters to the chat client constructor:
@@ -15,7 +15,7 @@ The Azure AI Search integration provides context providers for RAG (Retrieval Au

 ### Basic Usage Example

-See the [Azure AI Search context provider examples](../../samples/02-agents/context_providers/azure_ai_search/) which demonstrate:
+See the [Azure AI Search context provider examples](../../samples/02-agents/providers/azure_ai/) which demonstrate:

 - Semantic search with hybrid (vector + keyword) queries
 - Agentic mode with Knowledge Bases for complex multi-hop reasoning
@@ -16,7 +16,8 @@ from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypedDict
 from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Annotation, Content, Message, SupportsGetEmbeddings
 from agent_framework._sessions import AgentSession, BaseContextProvider, SessionContext
 from agent_framework._settings import SecretString, load_settings
-from azure.core.credentials import AzureKeyCredential, TokenCredential
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
+from azure.core.credentials import AzureKeyCredential
 from azure.core.credentials_async import AsyncTokenCredential
 from azure.core.exceptions import ResourceNotFoundError
 from azure.search.documents.aio import SearchClient
@@ -110,8 +111,6 @@ try:
 except ImportError:
    _agentic_retrieval_available = False

-AzureCredentialTypes = TokenCredential | AsyncTokenCredential
-
 logger = logging.getLogger("agent_framework.azure_ai_search")

 _DEFAULT_AGENTIC_MESSAGE_HISTORY_COUNT = 10
@@ -2,35 +2,23 @@

 import importlib.metadata

-from ._agent_provider import AzureAIAgentsProvider  # pyright: ignore[reportDeprecated]
-from ._chat_client import AzureAIAgentClient, AzureAIAgentOptions  # pyright: ignore[reportDeprecated]
-from ._client import AzureAIClient, AzureAIProjectAgentOptions, RawAzureAIClient  # pyright: ignore[reportDeprecated]
-from ._deprecated_azure_openai import (
-    AzureOpenAIAssistantsClient,  # pyright: ignore[reportDeprecated]
-    AzureOpenAIAssistantsOptions,
-    AzureOpenAIChatClient,  # pyright: ignore[reportDeprecated]
-    AzureOpenAIChatOptions,
-    AzureOpenAIConfigMixin,
-    AzureOpenAIEmbeddingClient,  # pyright: ignore[reportDeprecated]
-    AzureOpenAIResponsesClient,  # pyright: ignore[reportDeprecated]
-    AzureOpenAIResponsesOptions,
-    AzureOpenAISettings,
-    AzureUserSecurityContext,
-)
+from ._agent_provider import AzureAIAgentsProvider
+from ._chat_client import AzureAIAgentClient, AzureAIAgentOptions
+from ._client import AzureAIClient, AzureAIProjectAgentOptions, RawAzureAIClient
 from ._embedding_client import (
    AzureAIInferenceEmbeddingClient,
    AzureAIInferenceEmbeddingOptions,
    AzureAIInferenceEmbeddingSettings,
    RawAzureAIInferenceEmbeddingClient,
 )
-from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider
-from ._project_provider import AzureAIProjectAgentProvider  # pyright: ignore[reportDeprecated]
+from ._foundry_memory_provider import FoundryMemoryProvider
+from ._project_provider import AzureAIProjectAgentProvider
 from ._shared import AzureAISettings

 try:
    __version__ = importlib.metadata.version(__name__)
 except importlib.metadata.PackageNotFoundError:
-    __version__ = "0.0.0"
+    __version__ = "0.0.0"  # Fallback for development mode

 __all__ = [
    "AzureAIAgentClient",
@@ -43,18 +31,7 @@ __all__ = [
    "AzureAIProjectAgentOptions",
    "AzureAIProjectAgentProvider",
    "AzureAISettings",
-    "AzureCredentialTypes",
-    "AzureOpenAIAssistantsClient",
-    "AzureOpenAIAssistantsOptions",
-    "AzureOpenAIChatClient",
-    "AzureOpenAIChatOptions",
-    "AzureOpenAIConfigMixin",
-    "AzureOpenAIEmbeddingClient",
-    "AzureOpenAIResponsesClient",
-    "AzureOpenAIResponsesOptions",
-    "AzureOpenAISettings",
-    "AzureTokenProvider",
-    "AzureUserSecurityContext",
+    "FoundryMemoryProvider",
    "RawAzureAIClient",
    "RawAzureAIInferenceEmbeddingClient",
    "__version__",
@@ -18,23 +18,19 @@ from agent_framework import (
 from agent_framework._mcp import MCPTool
 from agent_framework._settings import load_settings
 from agent_framework._tools import ToolTypes
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from azure.ai.agents.aio import AgentsClient
 from azure.ai.agents.models import Agent as AzureAgent
 from azure.ai.agents.models import ResponseFormatJsonSchema, ResponseFormatJsonSchemaType
 from pydantic import BaseModel

-from ._chat_client import AzureAIAgentClient, AzureAIAgentOptions  # pyright: ignore[reportDeprecated]
-from ._entra_id_authentication import AzureCredentialTypes
+from ._chat_client import AzureAIAgentClient, AzureAIAgentOptions
 from ._shared import AzureAISettings, to_azure_ai_agent_tools

 if sys.version_info >= (3, 13):
    from typing import Self, TypeVar  # type: ignore # pragma: no cover
 else:
    from typing_extensions import Self, TypeVar  # type: ignore # pragma: no cover
-if sys.version_info >= (3, 13):
-    from warnings import deprecated  # type: ignore # pragma: no cover
-else:
-    from typing_extensions import deprecated  # type: ignore # pragma: no cover
 if sys.version_info >= (3, 11):
    from typing import TypedDict  # type: ignore # pragma: no cover
 else:
@@ -51,11 +47,6 @@ OptionsCoT = TypeVar(
 )


-@deprecated(
-    "AzureAIAgentClient and the AzureAIAgentsProvider are deprecated. "
-    "They target the V1 Agents Service API and have no direct replacement; "
-    "for new Foundry projects, use FoundryAgent."
-)
 class AzureAIAgentsProvider(Generic[OptionsCoT]):
    """Provider for Azure AI Agent Service V1 (Persistent Agents API).

@@ -435,7 +426,7 @@ class AzureAIAgentsProvider(Generic[OptionsCoT]):
            context_providers: Context providers to include during agent invocation.
        """
        # Create the underlying client
-        client = AzureAIAgentClient(  # pyright: ignore[reportDeprecated]
+        client = AzureAIAgentClient(
            agents_client=self._agents_client,
            agent_id=agent.id,
            agent_name=agent.name,
@@ -36,6 +36,7 @@ from agent_framework import (
 )
 from agent_framework._settings import load_settings
 from agent_framework._tools import ToolTypes
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from agent_framework.exceptions import (
    ChatClientException,
    ChatClientInvalidRequestException,
@@ -91,14 +92,12 @@ from azure.ai.agents.models import (
 )
 from pydantic import BaseModel

-from ._entra_id_authentication import AzureCredentialTypes
 from ._shared import AzureAISettings, resolve_file_ids, to_azure_ai_agent_tools

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
-    from warnings import deprecated  # type: ignore # pragma: no cover
 else:
-    from typing_extensions import TypeVar, deprecated  # type: ignore # pragma: no cover
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
 if sys.version_info >= (3, 12):
    from typing import override  # type: ignore # pragma: no cover
 else:
@@ -211,11 +210,6 @@ AzureAIAgentOptionsT = TypeVar(
 # endregion


-@deprecated(
-    "AzureAIAgentClient is deprecated. "
-    "It targets the V1 Agents Service API and has no direct replacement; "
-    "for new Foundry projects, use FoundryAgent."
-)
 class AzureAIAgentClient(
    FunctionInvocationLayer[AzureAIAgentOptionsT],
    ChatMiddlewareLayer[AzureAIAgentOptionsT],
@@ -227,8 +221,7 @@ class AzureAIAgentClient(

    .. deprecated::
        AzureAIAgentClient is deprecated and will be removed in a future release.
-        It targets the V1 Agents Service API and has no direct replacement.
-        For new Foundry projects, use :class:`FoundryAgent`.
+        Use :class:`AzureAIClient` instead for the V2 (Projects/Responses) API.
    """

    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai"  # type: ignore[reportIncompatibleVariableOverride, misc]
@@ -246,8 +239,7 @@ class AzureAIAgentClient(

        .. deprecated::
            This method is deprecated and will be removed in a future release.
-            For new Foundry projects, configure hosted tools on the Foundry agent definition
-            in the service instead.
+            Use :meth:`AzureAIClient.get_code_interpreter_tool` instead.

        Keyword Args:
            file_ids: List of uploaded file IDs or Content objects to make available to
@@ -280,7 +272,7 @@ class AzureAIAgentClient(
        """
        warnings.warn(
            "AzureAIAgentClient.get_code_interpreter_tool() is deprecated and will be removed in a future release; "
-            "for new Foundry projects, configure hosted tools on the Foundry agent definition in the service instead.",
+            "use AzureAIClient.get_code_interpreter_tool() instead.",
            DeprecationWarning,
            stacklevel=2,
        )
@@ -296,8 +288,7 @@ class AzureAIAgentClient(

        .. deprecated::
            This method is deprecated and will be removed in a future release.
-            For new Foundry projects, configure hosted tools on the Foundry agent definition
-            in the service instead.
+            Use :meth:`AzureAIClient.get_file_search_tool` instead.

        Keyword Args:
            vector_store_ids: List of vector store IDs to search within.
@@ -317,7 +308,7 @@ class AzureAIAgentClient(
        """
        warnings.warn(
            "AzureAIAgentClient.get_file_search_tool() is deprecated and will be removed in a future release; "
-            "for new Foundry projects, configure hosted tools on the Foundry agent definition in the service instead.",
+            "use AzureAIClient.get_file_search_tool() instead.",
            DeprecationWarning,
            stacklevel=2,
        )
@@ -334,8 +325,7 @@ class AzureAIAgentClient(

        .. deprecated::
            This method is deprecated and will be removed in a future release.
-            For new Foundry projects, configure hosted tools on the Foundry agent definition
-            in the service instead.
+            Use :meth:`AzureAIClient.get_web_search_tool` instead.

        For Azure AI Agents, web search uses Bing Grounding or Bing Custom Search.
        If no arguments are provided, attempts to read from environment variables.
@@ -379,7 +369,7 @@ class AzureAIAgentClient(
        """
        warnings.warn(
            "AzureAIAgentClient.get_web_search_tool() is deprecated and will be removed in a future release; "
-            "for new Foundry projects, configure hosted tools on the Foundry agent definition in the service instead.",
+            "use AzureAIClient.get_web_search_tool() instead.",
            DeprecationWarning,
            stacklevel=2,
        )
@@ -420,8 +410,7 @@ class AzureAIAgentClient(

        .. deprecated::
            This method is deprecated and will be removed in a future release.
-            For new Foundry projects, configure hosted tools on the Foundry agent definition
-            in the service instead.
+            Use :meth:`AzureAIClient.get_mcp_tool` instead.

        This configures an MCP (Model Context Protocol) server that will be called
        by Azure AI's service. The tools from this MCP server are executed remotely
@@ -457,7 +446,7 @@ class AzureAIAgentClient(
        """
        warnings.warn(
            "AzureAIAgentClient.get_mcp_tool() is deprecated and will be removed in a future release; "
-            "for new Foundry projects, configure hosted tools on the Foundry agent definition in the service instead.",
+            "use AzureAIClient.get_mcp_tool() instead.",
            DeprecationWarning,
            stacklevel=2,
        )
@@ -572,6 +561,12 @@ class AzureAIAgentClient(
                client: AzureAIAgentClient[MyOptions] = AzureAIAgentClient(credential=credential)
                response = await client.get_response("Hello", options={"my_custom_option": "value"})
        """
+        warnings.warn(
+            "AzureAIAgentClient is deprecated and will be removed in a future release; "
+            "use AzureAIClient instead for the V2 (Projects/Responses) API.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
        azure_ai_settings = load_settings(
            AzureAISettings,
            env_prefix="AZURE_AI_",
@@ -30,9 +30,10 @@ from agent_framework import (
 )
 from agent_framework._settings import load_settings
 from agent_framework._tools import ToolTypes
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from agent_framework.observability import ChatTelemetryLayer
 from agent_framework.openai import OpenAIResponsesOptions
-from agent_framework_openai._chat_client import RawOpenAIChatClient
+from agent_framework.openai._responses_client import RawOpenAIResponsesClient
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
    ApproximateLocation,
@@ -49,14 +50,12 @@ from azure.ai.projects.models import (
 from azure.ai.projects.models import FileSearchTool as ProjectsFileSearchTool
 from azure.core.exceptions import ResourceNotFoundError

-from ._entra_id_authentication import AzureCredentialTypes
 from ._shared import AzureAISettings, create_text_format_config, resolve_file_ids

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
-    from warnings import deprecated  # type: ignore # pragma: no cover
 else:
-    from typing_extensions import TypeVar, deprecated  # type: ignore # pragma: no cover
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
 if sys.version_info >= (3, 12):
    from typing import override  # type: ignore # pragma: no cover
 else:
@@ -69,7 +68,7 @@ else:
 logger = logging.getLogger("agent_framework.azure")


-class AzureAIProjectAgentOptions(OpenAIResponsesOptions, total=False):  # type: ignore[misc, call-arg]
+class AzureAIProjectAgentOptions(OpenAIResponsesOptions, total=False):
    """Azure AI Project Agent options."""

    rai_config: RaiConfig
@@ -89,13 +88,8 @@ AzureAIClientOptionsT = TypeVar(
 _DOC_INDEX_PATTERN = re.compile(r"doc_(\d+)")


-@deprecated(
-    "RawAzureAIClient is deprecated. "
-    "Use RawFoundryAgentChatClient for low-level Foundry agent client customization, "
-    "or FoundryAgent for the recommended production API."
-)
-class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[AzureAIClientOptionsT]):
-    """Deprecated raw Azure AI client without middleware, telemetry, or function invocation layers.
+class RawAzureAIClient(RawOpenAIResponsesClient[AzureAIClientOptionsT], Generic[AzureAIClientOptionsT]):
+    """Raw Azure AI client without middleware, telemetry, or function invocation layers.

    Warning:
        **This class should not normally be used directly.** It does not include middleware,
@@ -107,8 +101,7 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure
        2. **ChatMiddlewareLayer** - Applies chat middleware per model call and stays outside telemetry
        3. **ChatTelemetryLayer** - Must stay inside chat middleware for correct per-call telemetry

-        Use ``RawFoundryAgentChatClient`` for low-level Foundry agent customization, or
-        ``FoundryAgent`` for the recommended production API.
+        Use ``AzureAIClient`` instead for a fully-featured client with all layers applied.
    """

    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai"  # type: ignore[reportIncompatibleVariableOverride, misc]
@@ -222,10 +215,8 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure
            project_client = AIProjectClient(**project_client_kwargs)
            should_close_client = True

-        # Initialize parent with OpenAI client from project
-        super().__init__(  # type: ignore
-            async_client=project_client.get_openai_client(),
-            model=azure_ai_settings.get("model"),  # type: ignore[arg-type]
+        # Initialize parent
+        super().__init__(
            additional_properties=additional_properties,
        )

@@ -689,6 +680,10 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure

        return result, instructions

+    async def _initialize_client(self) -> None:
+        """Initialize OpenAI client."""
+        self.client = self.project_client.get_openai_client()  # type: ignore
+
    def _update_agent_name_and_description(self, agent_name: str | None, description: str | None = None) -> None:
        """Update the agent name in the chat client.

@@ -847,7 +842,7 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure
        if not stream:

            async def _enrich_response() -> ChatResponse:
-                response = await super(RawAzureAIClient, self)._inner_get_response(  # pyright: ignore[reportDeprecated]
+                response = await super(RawAzureAIClient, self)._inner_get_response(
                    messages=messages, options=options, stream=False, **kwargs
                )
                get_urls = self._extract_azure_search_urls(response.raw_representation.output)  # type: ignore[union-attr]
@@ -1187,8 +1182,8 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure
        It does NOT create an agent on the Azure AI service - the actual agent
        will be created on the server during the first invocation (run).

-        For working with pre-configured persistent agents on the server, use
-        :class:`~agent_framework_azure_ai.FoundryAgent` instead.
+        For creating and managing persistent agents on the server, use
+        :class:`~agent_framework_azure_ai.AzureAIProjectAgentProvider` instead.

        Keyword Args:
            id: The unique identifier for the agent. Will be created automatically if not provided.
@@ -1218,23 +1213,21 @@ class RawAzureAIClient(RawOpenAIChatClient[AzureAIClientOptionsT], Generic[Azure
        )


-@deprecated("AzureAIClient is deprecated. Use FoundryAgent instead.")
 class AzureAIClient(
    FunctionInvocationLayer[AzureAIClientOptionsT],
    ChatMiddlewareLayer[AzureAIClientOptionsT],
    ChatTelemetryLayer[AzureAIClientOptionsT],
-    RawAzureAIClient[AzureAIClientOptionsT],  # pyright: ignore[reportDeprecated]
+    RawAzureAIClient[AzureAIClientOptionsT],
    Generic[AzureAIClientOptionsT],
 ):
-    """Deprecated Azure AI client with middleware, telemetry, and function invocation support.
+    """Azure AI client with middleware, telemetry, and function invocation support.

-    This class is deprecated. Use ``FoundryAgent`` instead for connecting to
-    pre-configured agents in Foundry. It includes:
+    This is the recommended client for most use cases. It includes:
    - Chat middleware support for request/response interception
    - OpenTelemetry-based telemetry for observability
    - Automatic function/tool invocation handling

-    For a minimal implementation without these features, use :class:`RawFoundryAgentChatClient`.
+    For a minimal implementation without these features, use :class:`RawAzureAIClient`.
    """

    def __init__(
@@ -1,897 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Deprecated Azure OpenAI client classes.
-
-All classes in this module are deprecated and will be removed in a future release.
-Migrate to the ``agent_framework_openai`` package equivalents with an ``AsyncAzureOpenAI`` client,
-or use ``FoundryChatClient`` for Azure AI Foundry projects.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import sys
-from collections.abc import Mapping, Sequence
-from copy import copy
-from typing import TYPE_CHECKING, Any, ClassVar, Final, Generic, cast
-from urllib.parse import urljoin, urlparse
-
-from agent_framework._middleware import ChatMiddlewareLayer
-from agent_framework._settings import SecretString, load_settings
-from agent_framework._telemetry import AGENT_FRAMEWORK_USER_AGENT, APP_INFO, prepend_agent_framework_to_user_agent
-from agent_framework._tools import FunctionInvocationConfiguration, FunctionInvocationLayer
-from agent_framework._types import Annotation, Content
-from agent_framework.observability import ChatTelemetryLayer, EmbeddingTelemetryLayer
-from agent_framework_openai._assistants_client import OpenAIAssistantsClient, OpenAIAssistantsOptions
-from agent_framework_openai._chat_client import OpenAIChatOptions, RawOpenAIChatClient
-from agent_framework_openai._chat_completion_client import OpenAIChatCompletionOptions, RawOpenAIChatCompletionClient
-from agent_framework_openai._embedding_client import OpenAIEmbeddingOptions, RawOpenAIEmbeddingClient
-from agent_framework_openai._shared import OpenAIBase
-from azure.ai.projects.aio import AIProjectClient
-from openai import AsyncOpenAI
-from openai.lib.azure import AsyncAzureOpenAI
-from pydantic import BaseModel
-
-from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider, resolve_credential_to_token_provider
-
-if sys.version_info >= (3, 13):
-    from typing import TypeVar  # type: ignore # pragma: no cover
-    from warnings import deprecated  # type: ignore # pragma: no cover
-else:
-    from typing_extensions import TypeVar, deprecated  # type: ignore # pragma: no cover
-if sys.version_info >= (3, 12):
-    from typing import override  # type: ignore # pragma: no cover
-else:
-    from typing_extensions import override  # type: ignore # pragma: no cover
-if sys.version_info >= (3, 11):
-    from typing import TypedDict  # type: ignore # pragma: no cover
-else:
-    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
-
-if TYPE_CHECKING:
-    from agent_framework._middleware import MiddlewareTypes
-    from openai.types.chat.chat_completion import Choice
-    from openai.types.chat.chat_completion_chunk import Choice as ChunkChoice
-
-logger: logging.Logger = logging.getLogger(__name__)
-
-
-# region Constants and Settings
-
-DEFAULT_AZURE_API_VERSION: Final[str] = "2024-10-21"
-DEFAULT_AZURE_TOKEN_ENDPOINT: Final[str] = "https://cognitiveservices.azure.com/.default"  # noqa: S105
-
-
-class AzureOpenAISettings(TypedDict, total=False):
-    """AzureOpenAI model settings.
-
-    Settings are resolved in this order: explicit keyword arguments, values from an
-    explicitly provided .env file, then environment variables with the prefix
-    'AZURE_OPENAI_'. If settings are missing after resolution, validation will fail.
-
-    Keyword Args:
-        endpoint: The endpoint of the Azure deployment.
-        chat_deployment_name: The name of the Azure Chat deployment.
-        responses_deployment_name: The name of the Azure Responses deployment.
-        embedding_deployment_name: The name of the Azure Embedding deployment.
-        api_key: The API key for the Azure deployment.
-        api_version: The API version to use.
-        base_url: The url of the Azure deployment.
-        token_endpoint: The token endpoint to use to retrieve the authentication token.
-    """
-
-    chat_deployment_name: str | None
-    responses_deployment_name: str | None
-    embedding_deployment_name: str | None
-    endpoint: str | None
-    base_url: str | None
-    api_key: SecretString | None
-    api_version: str | None
-    token_endpoint: str | None
-
-
-def _apply_azure_defaults(
-    settings: AzureOpenAISettings,
-    default_api_version: str = DEFAULT_AZURE_API_VERSION,
-    default_token_endpoint: str = DEFAULT_AZURE_TOKEN_ENDPOINT,
-) -> None:
-    """Apply default values for api_version and token_endpoint after loading settings.
-
-    Args:
-        settings: The loaded Azure OpenAI settings dict.
-        default_api_version: The default API version to use if not set.
-        default_token_endpoint: The default token endpoint to use if not set.
-    """
-    if not settings.get("api_version"):
-        settings["api_version"] = default_api_version
-    if not settings.get("token_endpoint"):
-        settings["token_endpoint"] = default_token_endpoint
-
-
-# endregion
-
-
-# region AzureOpenAIConfigMixin
-
-
-class AzureOpenAIConfigMixin(OpenAIBase):
-    """Internal class for configuring a connection to an Azure OpenAI service."""
-
-    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai.openai"
-
-    def __init__(
-        self,
-        deployment_name: str,
-        endpoint: str | None = None,
-        base_url: str | None = None,
-        api_version: str = DEFAULT_AZURE_API_VERSION,
-        api_key: str | None = None,
-        token_endpoint: str | None = None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        **kwargs: Any,
-    ) -> None:
-        """Configure a connection to an Azure OpenAI service.
-
-        Args:
-            deployment_name: Name of the deployment.
-            endpoint: The specific endpoint URL for the deployment.
-            base_url: The base URL for Azure services.
-            api_version: Azure API version.
-            api_key: API key for Azure services.
-            token_endpoint: Azure AD token scope.
-            credential: Azure credential or token provider for authentication.
-            default_headers: Default headers for HTTP requests.
-            client: An existing client to use.
-            instruction_role: The role to use for 'instruction' messages.
-            kwargs: Additional keyword arguments.
-        """
-        merged_headers = dict(copy(default_headers)) if default_headers else {}
-        if APP_INFO:
-            merged_headers.update(APP_INFO)
-            merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-        if not client:
-            ad_token_provider = None
-            if not api_key and credential:
-                ad_token_provider = resolve_credential_to_token_provider(credential, token_endpoint)
-
-            if not api_key and not ad_token_provider:
-                raise ValueError("Please provide either api_key, credential, or a client.")
-
-            if not endpoint and not base_url:
-                raise ValueError("Please provide an endpoint or a base_url")
-
-            args: dict[str, Any] = {
-                "default_headers": merged_headers,
-            }
-            if api_version:
-                args["api_version"] = api_version
-            if ad_token_provider:
-                args["azure_ad_token_provider"] = ad_token_provider
-            if api_key:
-                args["api_key"] = api_key
-            if base_url:
-                args["base_url"] = str(base_url)
-            if endpoint and not base_url:
-                args["azure_endpoint"] = str(endpoint)
-            if deployment_name:
-                args["azure_deployment"] = deployment_name
-            if "websocket_base_url" in kwargs:
-                args["websocket_base_url"] = kwargs.pop("websocket_base_url")
-
-            client = AsyncAzureOpenAI(**args)
-
-        self.endpoint = str(endpoint)
-        self.base_url = str(base_url)
-        self.api_version = api_version
-        self.deployment_name = deployment_name
-        self.instruction_role = instruction_role
-        if default_headers:
-            from agent_framework._telemetry import USER_AGENT_KEY
-
-            def_headers = {k: v for k, v in default_headers.items() if k != USER_AGENT_KEY}
-        else:
-            def_headers = None
-        self.default_headers = def_headers
-
-        super().__init__(model_id=deployment_name, client=client, **kwargs)
-
-
-# endregion
-
-
-# region AzureOpenAIResponsesClient
-
-
-AzureOpenAIResponsesOptionsT = TypeVar(
-    "AzureOpenAIResponsesOptionsT",
-    bound=TypedDict,  # type: ignore[valid-type]
-    default="OpenAIChatOptions",
-    covariant=True,
-)
-
-AzureOpenAIResponsesOptions = OpenAIChatOptions
-
-
-@deprecated(
-    "AzureOpenAIResponsesClient is deprecated. "
-    "Use OpenAIChatClient with an AsyncAzureOpenAI client, or FoundryChatClient for Foundry projects."
-)
-class AzureOpenAIResponsesClient(  # type: ignore[misc]
-    FunctionInvocationLayer[AzureOpenAIResponsesOptionsT],
-    ChatMiddlewareLayer[AzureOpenAIResponsesOptionsT],
-    ChatTelemetryLayer[AzureOpenAIResponsesOptionsT],
-    RawOpenAIChatClient[AzureOpenAIResponsesOptionsT],
-    Generic[AzureOpenAIResponsesOptionsT],
-):
-    """Deprecated Azure Responses client. Use OpenAIChatClient with an AsyncAzureOpenAI client instead."""
-
-    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai.openai"
-
-    def __init__(
-        self,
-        *,
-        api_key: str | None = None,
-        deployment_name: str | None = None,
-        endpoint: str | None = None,
-        base_url: str | None = None,
-        api_version: str | None = None,
-        token_endpoint: str | None = None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        project_client: Any | None = None,
-        project_endpoint: str | None = None,
-        allow_preview: bool | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        instruction_role: str | None = None,
-        middleware: Sequence[MiddlewareTypes] | None = None,
-        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
-        **kwargs: Any,
-    ) -> None:
-        """Initialize an Azure OpenAI Responses client.
-
-        Keyword Args:
-            api_key: The API key.
-            deployment_name: The deployment name.
-            endpoint: The deployment endpoint.
-            base_url: The deployment base URL.
-            api_version: The deployment API version.
-            token_endpoint: The token endpoint to request an Azure token.
-            credential: Azure credential or token provider for authentication.
-            default_headers: Default headers for HTTP requests.
-            async_client: An existing client to use.
-            project_client: An existing AIProjectClient to use.
-            project_endpoint: The Azure AI Foundry project endpoint URL.
-            allow_preview: Enables preview opt-in on internally-created AIProjectClient.
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-            instruction_role: The role to use for 'instruction' messages.
-            middleware: Optional sequence of middleware.
-            function_invocation_configuration: Optional function invocation configuration.
-            kwargs: Additional keyword arguments.
-        """
-        if (model_id := kwargs.pop("model_id", None)) and not deployment_name:
-            deployment_name = str(model_id)
-
-        if async_client is None and (project_client is not None or project_endpoint is not None):
-            async_client = self._create_client_from_project(
-                project_client=project_client,
-                project_endpoint=project_endpoint,
-                credential=credential,
-                allow_preview=allow_preview,
-            )
-
-        azure_openai_settings = load_settings(
-            AzureOpenAISettings,
-            env_prefix="AZURE_OPENAI_",
-            api_key=api_key,
-            base_url=base_url,
-            endpoint=endpoint,
-            responses_deployment_name=deployment_name,
-            api_version=api_version,
-            env_file_path=env_file_path,
-            env_file_encoding=env_file_encoding,
-            token_endpoint=token_endpoint,
-        )
-        _apply_azure_defaults(azure_openai_settings, default_api_version="preview")
-        endpoint_value = azure_openai_settings.get("endpoint")
-        if (
-            not azure_openai_settings.get("base_url")
-            and endpoint_value
-            and (hostname := urlparse(str(endpoint_value)).hostname)
-            and hostname.endswith(".openai.azure.com")
-        ):
-            azure_openai_settings["base_url"] = urljoin(str(endpoint_value), "/openai/v1/")
-
-        responses_deployment_name = azure_openai_settings.get("responses_deployment_name")
-        if not responses_deployment_name:
-            raise ValueError(
-                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
-                "or 'AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME' environment variable."
-            )
-
-        if not async_client:
-            # Create the Azure OpenAI client directly
-            merged_headers = dict(copy(default_headers)) if default_headers else {}
-            if APP_INFO:
-                merged_headers.update(APP_INFO)
-                merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-            api_key_secret = azure_openai_settings.get("api_key")
-            ad_token_provider = None
-            if not api_key_secret and credential:
-                ad_token_provider = resolve_credential_to_token_provider(
-                    credential, azure_openai_settings.get("token_endpoint")
-                )
-
-            if not api_key_secret and not ad_token_provider:
-                raise ValueError("Please provide either api_key, credential, or a client.")
-
-            client_endpoint = azure_openai_settings.get("endpoint")
-            client_base_url = azure_openai_settings.get("base_url")
-            if not client_endpoint and not client_base_url:
-                raise ValueError("Please provide an endpoint or a base_url")
-
-            client_args: dict[str, Any] = {"default_headers": merged_headers}
-            if resolved_api_version := azure_openai_settings.get("api_version"):
-                client_args["api_version"] = resolved_api_version
-            if ad_token_provider:
-                client_args["azure_ad_token_provider"] = ad_token_provider
-            if api_key_secret:
-                client_args["api_key"] = api_key_secret.get_secret_value()
-            if client_base_url:
-                client_args["base_url"] = str(client_base_url)
-            if client_endpoint and not client_base_url:
-                client_args["azure_endpoint"] = str(client_endpoint)
-            if responses_deployment_name:
-                client_args["azure_deployment"] = responses_deployment_name
-            if "websocket_base_url" in kwargs:
-                client_args["websocket_base_url"] = kwargs.pop("websocket_base_url")
-
-            async_client = AsyncAzureOpenAI(**client_args)
-
-        # Store Azure-specific attributes for serialization
-        self.endpoint = str(endpoint_value) if endpoint_value else None
-        self.api_version = azure_openai_settings.get("api_version") or ""
-        self.deployment_name = responses_deployment_name
-
-        super().__init__(
-            async_client=async_client,
-            model=responses_deployment_name,
-            api_version=azure_openai_settings.get("api_version"),
-            instruction_role=instruction_role,
-            default_headers=default_headers,
-            middleware=middleware,  # type: ignore[arg-type]
-            function_invocation_configuration=function_invocation_configuration,
-            **kwargs,
-        )
-
-    @staticmethod
-    def _create_client_from_project(
-        *,
-        project_client: AIProjectClient | None,
-        project_endpoint: str | None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None,
-        allow_preview: bool | None = None,
-    ) -> AsyncOpenAI:
-        """Create an AsyncOpenAI client from an Azure AI Foundry project."""
-        if project_client is not None:
-            return project_client.get_openai_client()
-
-        if not project_endpoint:
-            raise ValueError("Azure AI project endpoint is required when project_client is not provided.")
-        if not credential:
-            raise ValueError("Azure credential is required when using project_endpoint without a project_client.")
-        project_client_kwargs: dict[str, Any] = {
-            "endpoint": project_endpoint,
-            "credential": credential,  # type: ignore[arg-type]
-            "user_agent": AGENT_FRAMEWORK_USER_AGENT,
-        }
-        if allow_preview is not None:
-            project_client_kwargs["allow_preview"] = allow_preview
-        project_client = AIProjectClient(**project_client_kwargs)
-        return project_client.get_openai_client()
-
-    @override
-    def _check_model_presence(self, options: dict[str, Any]) -> None:
-        if not options.get("model"):
-            if not self.model:
-                raise ValueError("deployment_name must be a non-empty string")
-            options["model"] = self.model
-
-
-# endregion
-
-
-# region AzureOpenAIChatClient
-
-
-ResponseModelT = TypeVar("ResponseModelT", bound=BaseModel | None, default=None)
-
-
-class AzureUserSecurityContext(TypedDict, total=False):
-    """User security context for Azure AI applications.
-
-    These fields help security operations teams investigate and mitigate security
-    incidents by providing context about the application and end user.
-    """
-
-    application_name: str
-    """Name of the application making the request."""
-
-    end_user_id: str
-    """Unique identifier for the end user (recommend hashing username/email)."""
-
-    end_user_tenant_id: str
-    """Microsoft 365 tenant ID the end user belongs to. Required for multi-tenant apps."""
-
-    source_ip: str
-    """The original client's IP address."""
-
-
-class AzureOpenAIChatOptions(OpenAIChatCompletionOptions[ResponseModelT], Generic[ResponseModelT], total=False):
-    """Azure OpenAI-specific chat options dict.
-
-    Extends OpenAIChatCompletionOptions with Azure-specific options including
-    the "On Your Data" feature and enhanced security context.
-    """
-
-    data_sources: list[dict[str, Any]]
-    """Azure "On Your Data" data sources for retrieval-augmented generation."""
-
-    user_security_context: AzureUserSecurityContext
-    """Enhanced security context for Azure Defender integration."""
-
-    n: int
-    """Number of chat completion choices to generate for each input message."""
-
-
-AzureOpenAIChatOptionsT = TypeVar(
-    "AzureOpenAIChatOptionsT",
-    bound=TypedDict,  # type: ignore[valid-type]
-    default="AzureOpenAIChatOptions",
-    covariant=True,
-)
-
-
-@deprecated("AzureOpenAIChatClient is deprecated. Use OpenAIChatCompletionClient with an AsyncAzureOpenAI client.")
-class AzureOpenAIChatClient(  # type: ignore[misc]
-    FunctionInvocationLayer[AzureOpenAIChatOptionsT],
-    ChatMiddlewareLayer[AzureOpenAIChatOptionsT],
-    ChatTelemetryLayer[AzureOpenAIChatOptionsT],
-    RawOpenAIChatCompletionClient[AzureOpenAIChatOptionsT],
-    Generic[AzureOpenAIChatOptionsT],
-):
-    """Deprecated Azure OpenAI Chat client. Use OpenAIChatCompletionClient with AsyncAzureOpenAI instead."""
-
-    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai.openai"
-
-    def __init__(
-        self,
-        *,
-        api_key: str | None = None,
-        deployment_name: str | None = None,
-        endpoint: str | None = None,
-        base_url: str | None = None,
-        api_version: str | None = None,
-        token_endpoint: str | None = None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | None = None,
-        additional_properties: dict[str, Any] | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        instruction_role: str | None = None,
-        middleware: Sequence[MiddlewareTypes] | None = None,
-        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
-    ) -> None:
-        """Initialize an Azure OpenAI Chat completion client.
-
-        Keyword Args:
-            api_key: The API key.
-            deployment_name: The deployment name.
-            endpoint: The deployment endpoint.
-            base_url: The deployment base URL.
-            api_version: The deployment API version.
-            token_endpoint: The token endpoint to request an Azure token.
-            credential: Azure credential or token provider for authentication.
-            default_headers: Default headers for HTTP requests.
-            async_client: An existing client to use.
-            additional_properties: Additional properties stored on the client instance.
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-            instruction_role: The role to use for 'instruction' messages.
-            middleware: Optional sequence of middleware.
-            function_invocation_configuration: Optional function invocation configuration.
-        """
-        azure_openai_settings = load_settings(
-            AzureOpenAISettings,
-            env_prefix="AZURE_OPENAI_",
-            api_key=api_key,
-            base_url=base_url,
-            endpoint=endpoint,
-            chat_deployment_name=deployment_name,
-            api_version=api_version,
-            env_file_path=env_file_path,
-            env_file_encoding=env_file_encoding,
-            token_endpoint=token_endpoint,
-        )
-        _apply_azure_defaults(azure_openai_settings)
-
-        chat_deployment_name = azure_openai_settings.get("chat_deployment_name")
-        if not chat_deployment_name:
-            raise ValueError(
-                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
-                "or 'AZURE_OPENAI_CHAT_DEPLOYMENT_NAME' environment variable."
-            )
-
-        if not async_client:
-            # Create the Azure OpenAI client directly
-            merged_headers = dict(copy(default_headers)) if default_headers else {}
-            if APP_INFO:
-                merged_headers.update(APP_INFO)
-                merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-            api_key_secret = azure_openai_settings.get("api_key")
-            ad_token_provider = None
-            if not api_key_secret and credential:
-                ad_token_provider = resolve_credential_to_token_provider(
-                    credential, azure_openai_settings.get("token_endpoint")
-                )
-
-            if not api_key_secret and not ad_token_provider:
-                raise ValueError("Please provide either api_key, credential, or a client.")
-
-            endpoint_value = azure_openai_settings.get("endpoint")
-            base_url_value = azure_openai_settings.get("base_url")
-            if not endpoint_value and not base_url_value:
-                raise ValueError("Please provide an endpoint or a base_url")
-
-            client_args: dict[str, Any] = {"default_headers": merged_headers}
-            if resolved_api_version := azure_openai_settings.get("api_version"):
-                client_args["api_version"] = resolved_api_version
-            if ad_token_provider:
-                client_args["azure_ad_token_provider"] = ad_token_provider
-            if api_key_secret:
-                client_args["api_key"] = api_key_secret.get_secret_value()
-            if base_url_value:
-                client_args["base_url"] = str(base_url_value)
-            if endpoint_value and not base_url_value:
-                client_args["azure_endpoint"] = str(endpoint_value)
-            if chat_deployment_name:
-                client_args["azure_deployment"] = chat_deployment_name
-
-            async_client = AsyncAzureOpenAI(**client_args)
-
-        # Store Azure-specific attributes for serialization
-        self.endpoint = str(azure_openai_settings.get("endpoint") or "")
-        self.api_version = azure_openai_settings.get("api_version") or ""
-        self.deployment_name = chat_deployment_name
-
-        super().__init__(
-            async_client=async_client,
-            model=chat_deployment_name,
-            api_version=azure_openai_settings.get("api_version"),
-            instruction_role=instruction_role,
-            default_headers=default_headers,
-            additional_properties=additional_properties,
-            middleware=middleware,  # type: ignore[arg-type]
-            function_invocation_configuration=function_invocation_configuration,
-        )
-
-    @override
-    def _parse_text_from_openai(self, choice: Choice | ChunkChoice) -> Content | None:
-        """Parse the choice into a Content object with type='text'.
-
-        Overwritten from RawOpenAIChatCompletionClient to deal with Azure On Your Data function.
-        """
-        message = getattr(choice, "message", None)
-        if message is None:
-            message = getattr(choice, "delta", None)
-        if message is None:  # type: ignore
-            return None
-        if hasattr(message, "refusal") and message.refusal:
-            return Content.from_text(text=message.refusal, raw_representation=choice)
-        if not message.content:
-            return None
-        text_content = Content.from_text(text=message.content, raw_representation=choice)
-        if not message.model_extra or "context" not in message.model_extra:
-            return text_content
-
-        context_raw: object = cast(object, message.context)  # type: ignore[union-attr]
-        if isinstance(context_raw, str):
-            try:
-                context_raw = json.loads(context_raw)
-            except json.JSONDecodeError:
-                logger.warning("Context is not a valid JSON string, ignoring context.")
-                return text_content
-        if not isinstance(context_raw, dict):
-            logger.warning("Context is not a valid dictionary, ignoring context.")
-            return text_content
-        context = cast(dict[str, Any], context_raw)
-        if intent := context.get("intent"):
-            text_content.additional_properties = {"intent": intent}
-        citations = context.get("citations")
-        if isinstance(citations, list) and citations:
-            annotations: list[Annotation] = []
-            for citation_raw in cast(list[object], citations):
-                if not isinstance(citation_raw, dict):
-                    continue
-                citation = cast(dict[str, Any], citation_raw)
-                annotations.append(
-                    Annotation(
-                        type="citation",
-                        title=citation.get("title", ""),
-                        url=citation.get("url", ""),
-                        snippet=citation.get("content", ""),
-                        file_id=citation.get("filepath", ""),
-                        tool_name="Azure-on-your-Data",
-                        additional_properties={"chunk_id": citation.get("chunk_id", "")},
-                        raw_representation=citation,
-                    )
-                )
-            text_content.annotations = annotations
-        return text_content
-
-
-# endregion
-
-
-# region AzureOpenAIAssistantsClient
-
-
-AzureOpenAIAssistantsOptionsT = TypeVar(
-    "AzureOpenAIAssistantsOptionsT",
-    bound=TypedDict,  # type: ignore[valid-type]
-    default="OpenAIAssistantsOptions",
-    covariant=True,
-)
-
-AzureOpenAIAssistantsOptions = OpenAIAssistantsOptions
-
-
-@deprecated(
-    "AzureOpenAIAssistantsClient is deprecated. "
-    "Use OpenAIAssistantsClient (also deprecated) or migrate to OpenAIChatClient."
-)
-class AzureOpenAIAssistantsClient(
-    OpenAIAssistantsClient[AzureOpenAIAssistantsOptionsT], Generic[AzureOpenAIAssistantsOptionsT]
-):
-    """Deprecated Azure OpenAI Assistants client. Use OpenAIAssistantsClient or migrate to OpenAIChatClient."""
-
-    DEFAULT_AZURE_API_VERSION: ClassVar[str] = "2024-05-01-preview"
-
-    def __init__(
-        self,
-        *,
-        deployment_name: str | None = None,
-        assistant_id: str | None = None,
-        assistant_name: str | None = None,
-        assistant_description: str | None = None,
-        thread_id: str | None = None,
-        api_key: str | None = None,
-        endpoint: str | None = None,
-        base_url: str | None = None,
-        api_version: str | None = None,
-        token_endpoint: str | None = None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize an Azure OpenAI Assistants client.
-
-        Keyword Args:
-            deployment_name: The Azure OpenAI deployment name.
-            assistant_id: The ID of an Azure OpenAI assistant to use.
-            assistant_name: The name to use when creating new assistants.
-            assistant_description: The description to use when creating new assistants.
-            thread_id: Default thread ID to use for conversations.
-            api_key: The API key to use.
-            endpoint: The deployment endpoint.
-            base_url: The deployment base URL.
-            api_version: The deployment API version.
-            token_endpoint: The token endpoint to request an Azure token.
-            credential: Azure credential or token provider for authentication.
-            default_headers: Default headers for HTTP requests.
-            async_client: An existing client to use.
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-        """
-        azure_openai_settings = load_settings(
-            AzureOpenAISettings,
-            env_prefix="AZURE_OPENAI_",
-            api_key=api_key,
-            base_url=base_url,
-            endpoint=endpoint,
-            chat_deployment_name=deployment_name,
-            api_version=api_version,
-            env_file_path=env_file_path,
-            env_file_encoding=env_file_encoding,
-            token_endpoint=token_endpoint,
-        )
-        _apply_azure_defaults(azure_openai_settings, default_api_version=self.DEFAULT_AZURE_API_VERSION)
-
-        chat_deployment_name = azure_openai_settings.get("chat_deployment_name")
-        if not chat_deployment_name:
-            raise ValueError(
-                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
-                "or 'AZURE_OPENAI_CHAT_DEPLOYMENT_NAME' environment variable."
-            )
-
-        api_key_secret = azure_openai_settings.get("api_key")
-        token_scope = azure_openai_settings.get("token_endpoint")
-
-        ad_token_provider = None
-        if not async_client and not api_key_secret and credential:
-            ad_token_provider = resolve_credential_to_token_provider(credential, token_scope)
-
-        if not async_client and not api_key_secret and not ad_token_provider:
-            raise ValueError("Please provide either api_key, credential, or a client.")
-
-        if not async_client:
-            client_params: dict[str, Any] = {
-                "default_headers": default_headers,
-            }
-            if resolved_api_version := azure_openai_settings.get("api_version"):
-                client_params["api_version"] = resolved_api_version
-
-            if api_key_secret:
-                client_params["api_key"] = api_key_secret.get_secret_value()
-            elif ad_token_provider:
-                client_params["azure_ad_token_provider"] = ad_token_provider
-
-            if resolved_base_url := azure_openai_settings.get("base_url"):
-                client_params["base_url"] = str(resolved_base_url)
-            elif resolved_endpoint := azure_openai_settings.get("endpoint"):
-                client_params["azure_endpoint"] = str(resolved_endpoint)
-
-            async_client = AsyncAzureOpenAI(**client_params)
-
-        super().__init__(
-            model_id=chat_deployment_name,
-            assistant_id=assistant_id,
-            assistant_name=assistant_name,
-            assistant_description=assistant_description,
-            thread_id=thread_id,
-            async_client=async_client,  # type: ignore[reportArgumentType]
-            default_headers=default_headers,
-        )
-
-
-# endregion
-
-
-# region AzureOpenAIEmbeddingClient
-
-
-AzureOpenAIEmbeddingOptionsT = TypeVar(
-    "AzureOpenAIEmbeddingOptionsT",
-    bound=TypedDict,  # type: ignore[valid-type]
-    default="OpenAIEmbeddingOptions",
-    covariant=True,
-)
-
-
-@deprecated("AzureOpenAIEmbeddingClient is deprecated. Use OpenAIEmbeddingClient with an AsyncAzureOpenAI client.")
-class AzureOpenAIEmbeddingClient(
-    EmbeddingTelemetryLayer[str, list[float], AzureOpenAIEmbeddingOptionsT],
-    RawOpenAIEmbeddingClient[AzureOpenAIEmbeddingOptionsT],
-    Generic[AzureOpenAIEmbeddingOptionsT],
-):
-    """Deprecated Azure OpenAI embedding client. Use OpenAIEmbeddingClient with AsyncAzureOpenAI instead."""
-
-    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai.openai"
-
-    def __init__(
-        self,
-        *,
-        api_key: str | None = None,
-        deployment_name: str | None = None,
-        endpoint: str | None = None,
-        base_url: str | None = None,
-        api_version: str | None = None,
-        token_endpoint: str | None = None,
-        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | None = None,
-        otel_provider_name: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None:
-        """Initialize an Azure OpenAI embedding client.
-
-        Keyword Args:
-            api_key: The API key.
-            deployment_name: The deployment name.
-            endpoint: The deployment endpoint.
-            base_url: The deployment base URL.
-            api_version: The deployment API version.
-            token_endpoint: The token endpoint to request an Azure token.
-            credential: Azure credential or token provider for authentication.
-            default_headers: Default headers for HTTP requests.
-            async_client: An existing client to use.
-            otel_provider_name: Override the OpenTelemetry provider name.
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-        """
-        azure_openai_settings = load_settings(
-            AzureOpenAISettings,
-            env_prefix="AZURE_OPENAI_",
-            api_key=api_key,
-            base_url=base_url,
-            endpoint=endpoint,
-            embedding_deployment_name=deployment_name,
-            api_version=api_version,
-            env_file_path=env_file_path,
-            env_file_encoding=env_file_encoding,
-            token_endpoint=token_endpoint,
-        )
-        _apply_azure_defaults(azure_openai_settings)
-
-        embedding_deployment_name = azure_openai_settings.get("embedding_deployment_name")
-        if not embedding_deployment_name:
-            raise ValueError(
-                "Azure OpenAI embedding deployment name is required. Set via 'deployment_name' parameter "
-                "or 'AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME' environment variable."
-            )
-
-        if not async_client:
-            # Create the Azure OpenAI client directly
-            merged_headers = dict(copy(default_headers)) if default_headers else {}
-            if APP_INFO:
-                merged_headers.update(APP_INFO)
-                merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-            api_key_secret = azure_openai_settings.get("api_key")
-            ad_token_provider = None
-            if not api_key_secret and credential:
-                ad_token_provider = resolve_credential_to_token_provider(
-                    credential, azure_openai_settings.get("token_endpoint")
-                )
-
-            if not api_key_secret and not ad_token_provider:
-                raise ValueError("Please provide either api_key, credential, or a client.")
-
-            endpoint_value = azure_openai_settings.get("endpoint")
-            base_url_value = azure_openai_settings.get("base_url")
-            if not endpoint_value and not base_url_value:
-                raise ValueError("Please provide an endpoint or a base_url")
-
-            client_args: dict[str, Any] = {"default_headers": merged_headers}
-            if resolved_api_version := azure_openai_settings.get("api_version"):
-                client_args["api_version"] = resolved_api_version
-            if ad_token_provider:
-                client_args["azure_ad_token_provider"] = ad_token_provider
-            if api_key_secret:
-                client_args["api_key"] = api_key_secret.get_secret_value()
-            if base_url_value:
-                client_args["base_url"] = str(base_url_value)
-            if endpoint_value and not base_url_value:
-                client_args["azure_endpoint"] = str(endpoint_value)
-            if embedding_deployment_name:
-                client_args["azure_deployment"] = embedding_deployment_name
-
-            async_client = AsyncAzureOpenAI(**client_args)
-
-        # Store Azure-specific attributes for serialization
-        self.endpoint = str(azure_openai_settings.get("endpoint") or "")
-        self.api_version = azure_openai_settings.get("api_version") or ""
-        self.deployment_name = embedding_deployment_name
-
-        super().__init__(
-            async_client=async_client,
-            model=embedding_deployment_name,
-            default_headers=default_headers,
-        )
-        if otel_provider_name is not None:
-            self.OTEL_PROVIDER_NAME = otel_provider_name  # type: ignore[misc]
-
-
-# endregion
@@ -1,67 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-from __future__ import annotations
-
-import logging
-from collections.abc import Awaitable, Callable
-from typing import Union
-
-from agent_framework.exceptions import ChatClientInvalidAuthException
-from azure.core.credentials import TokenCredential
-from azure.core.credentials_async import AsyncTokenCredential
-
-logger: logging.Logger = logging.getLogger(__name__)
-
-AzureTokenProvider = Callable[[], Union[str, Awaitable[str]]]
-"""A callable that returns a bearer token string, either synchronously or asynchronously."""
-
-AzureCredentialTypes = Union[TokenCredential, AsyncTokenCredential]
-"""Union of Azure credential types.
-
-Accepts:
- ``TokenCredential`` — synchronous Azure credential (e.g. ``DefaultAzureCredential()``)
- ``AsyncTokenCredential`` — asynchronous Azure credential (e.g. ``azure.identity.aio.DefaultAzureCredential()``)
-"""
-
-
-def resolve_credential_to_token_provider(
-    credential: AzureCredentialTypes | AzureTokenProvider,
-    token_endpoint: str | None,
-) -> AzureTokenProvider:
-    """Convert an Azure credential or token provider into an ``ad_token_provider`` callable.
-
-    If the credential is already a callable token provider, it is returned as-is
-    (``token_endpoint`` is not required in this case).
-    If it is a ``TokenCredential`` or ``AsyncTokenCredential``, it is wrapped using
-    ``azure.identity.get_bearer_token_provider`` (sync or async variant) which
-    handles token caching and automatic refresh.
-
-    Args:
-        credential: An Azure credential or token provider callable.
-        token_endpoint: The token scope/endpoint
-            (e.g. ``"https://cognitiveservices.azure.com/.default"``).
-            Required when ``credential`` is a ``TokenCredential`` or ``AsyncTokenCredential``.
-
-    Returns:
-        A callable that returns a bearer token string (sync or async).
-
-    Raises:
-        ServiceInvalidAuthError: If the token endpoint is empty when needed for credential wrapping.
-    """
-    # Already a token provider callable (not a credential object) — use directly
-    if callable(credential) and not isinstance(credential, (TokenCredential, AsyncTokenCredential)):
-        return credential
-
-    if not token_endpoint:
-        raise ChatClientInvalidAuthException(
-            "A token endpoint must be provided either in settings, as an environment variable, or as an argument."
-        )
-
-    if isinstance(credential, AsyncTokenCredential):
-        from azure.identity.aio import get_bearer_token_provider as get_async_bearer_token_provider
-
-        return get_async_bearer_token_provider(credential, token_endpoint)
-
-    from azure.identity import get_bearer_token_provider
-
-    return get_bearer_token_provider(credential, token_endpoint)  # type: ignore[arg-type]
@@ -16,11 +16,11 @@ from typing import TYPE_CHECKING, Any, ClassVar
 from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Message
 from agent_framework._sessions import AgentSession, BaseContextProvider, SessionContext
 from agent_framework._settings import load_settings
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from azure.ai.projects.aio import AIProjectClient
 from openai.types.responses import ResponseInputItemParam

-from ._entra_id_authentication import AzureCredentialTypes
-from ._shared import FoundryProjectSettings
+from ._shared import AzureAISettings

 if sys.version_info >= (3, 11):
    from typing import Self  # pragma: no cover
@@ -72,7 +72,7 @@ class FoundryMemoryProvider(BaseContextProvider):
        Args:
            source_id: Unique identifier for this provider instance.
            project_client: Azure AI Project client for memory operations.
-            project_endpoint: Foundry project endpoint URL. Used when project_client is not provided.
+            project_endpoint: Azure AI project endpoint URL. Used when project_client is not provided.
            credential: Azure credential for authentication. Accepts a TokenCredential,
                AsyncTokenCredential, or a callable token provider.
                Required when project_client is not provided.
@@ -86,20 +86,20 @@ class FoundryMemoryProvider(BaseContextProvider):
            env_file_encoding: Encoding of the environment file.
        """
        super().__init__(source_id)
-        foundry_settings = load_settings(
-            FoundryProjectSettings,
-            env_prefix="FOUNDRY_",
+        azure_ai_settings = load_settings(
+            AzureAISettings,
+            env_prefix="AZURE_AI_",
            project_endpoint=project_endpoint,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
        )

        if project_client is None:
-            resolved_endpoint = foundry_settings.get("project_endpoint")
+            resolved_endpoint = azure_ai_settings.get("project_endpoint")
            if not resolved_endpoint:
                raise ValueError(
-                    "Foundry project endpoint is required. Set via 'project_endpoint' parameter "
-                    "or 'FOUNDRY_PROJECT_ENDPOINT' environment variable."
+                    "Azure AI project endpoint is required. Set via 'project_endpoint' parameter "
+                    "or 'AZURE_AI_PROJECT_ENDPOINT' environment variable."
                )
            if not credential:
                raise ValueError("Azure credential is required when project_client is not provided.")
@@ -18,6 +18,7 @@ from agent_framework import (
 from agent_framework._mcp import MCPTool
 from agent_framework._settings import load_settings
 from agent_framework._tools import ToolTypes
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
    AgentVersionDetails,
@@ -28,15 +29,13 @@ from azure.ai.projects.models import (
    FunctionTool as AzureFunctionTool,
 )

-from ._client import AzureAIClient, AzureAIProjectAgentOptions  # pyright: ignore[reportDeprecated]
-from ._entra_id_authentication import AzureCredentialTypes
+from ._client import AzureAIClient, AzureAIProjectAgentOptions
 from ._shared import AzureAISettings, create_text_format_config, from_azure_ai_tools, to_azure_ai_tools

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
-    from warnings import deprecated  # type: ignore # pragma: no cover
 else:
-    from typing_extensions import TypeVar, deprecated  # type: ignore # pragma: no cover
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
 if sys.version_info >= (3, 11):
    from typing import Self, TypedDict  # type: ignore # pragma: no cover
 else:
@@ -56,12 +55,11 @@ OptionsCoT = TypeVar(
 )


-@deprecated("AzureAIProjectAgentProvider is deprecated. Use FoundryAgent instead.")
 class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
-    """Deprecated provider for Azure AI Agent Service (Responses API).
+    """Provider for Azure AI Agent Service (Responses API).

-    This provider is deprecated. Use ``FoundryAgent`` instead to connect to
-    pre-configured agents in Foundry.
+    This provider allows you to create, retrieve, and manage Azure AI agents
+    using the AIProjectClient from the Azure AI Projects SDK.

    Examples:
        Using with explicit AIProjectClient:
@@ -202,7 +200,7 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
            )

        # Extract options from default_options if present
-        opts: dict[str, Any] = dict(default_options) if default_options else {}
+        opts = dict(default_options) if default_options else {}
        response_format = opts.get("response_format")
        rai_config = opts.get("rai_config")
        reasoning = opts.get("reasoning")
@@ -386,7 +384,7 @@ class AzureAIProjectAgentProvider(Generic[OptionsCoT]):
        if not isinstance(details.definition, PromptAgentDefinition):
            raise ValueError("Agent definition must be PromptAgentDefinition to get a Agent.")

-        client = AzureAIClient(  # pyright: ignore[reportDeprecated]
+        client = AzureAIClient(
            project_client=self._project_client,
            agent_name=details.name,
            agent_version=details.version,
@@ -24,7 +24,6 @@ classifiers = [
 ]
 dependencies = [
    "agent-framework-core>=1.0.0rc5",
-    "agent-framework-openai>=1.0.0rc5",
    "azure-ai-agents>=1.2.0b5,<1.2.0b6",
    "azure-ai-inference>=1.0.0b9,<1.0.0b10",
    "aiohttp>=3.7.0,<4",
@@ -15,6 +15,7 @@ from azure.ai.agents.models import (
 from azure.ai.agents.models import (
    CodeInterpreterToolDefinition,
 )
+from azure.identity.aio import AzureCliCredential
 from pydantic import BaseModel

 from agent_framework_azure_ai import (
@@ -771,3 +772,82 @@ def test_from_azure_ai_agent_tools_unknown_dict() -> None:


 # endregion
+
+# region Integration Tests
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_create_agent() -> None:
+    """Integration test: Create an agent using the provider."""
+    async with (
+        AzureCliCredential() as credential,
+        AzureAIAgentsProvider(credential=credential) as provider,
+    ):
+        agent = await provider.create_agent(
+            name="IntegrationTestAgent",
+            instructions="You are a helpful assistant for testing.",
+        )
+
+        try:
+            assert isinstance(agent, Agent)
+            assert agent.name == "IntegrationTestAgent"
+            assert agent.id is not None
+        finally:
+            # Cleanup: delete the agent
+            if agent.id:
+                await provider._agents_client.delete_agent(agent.id)  # type: ignore
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_get_agent() -> None:
+    """Integration test: Get an existing agent using the provider."""
+    async with (
+        AzureCliCredential() as credential,
+        AzureAIAgentsProvider(credential=credential) as provider,
+    ):
+        # First create an agent
+        created = await provider._agents_client.create_agent(  # type: ignore
+            model=os.getenv("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
+            name="GetAgentTest",
+            instructions="Test agent",
+        )
+
+        try:
+            # Then get it using the provider
+            agent = await provider.get_agent(created.id)
+
+            assert isinstance(agent, Agent)
+            assert agent.id == created.id
+        finally:
+            await provider._agents_client.delete_agent(created.id)  # type: ignore
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_create_and_run() -> None:
+    """Integration test: Create an agent and run a conversation."""
+    async with (
+        AzureCliCredential() as credential,
+        AzureAIAgentsProvider(credential=credential) as provider,
+    ):
+        agent = await provider.create_agent(
+            name="RunTestAgent",
+            instructions="You are a helpful assistant. Always respond with 'Hello!' to any greeting.",
+        )
+
+        try:
+            result = await agent.run("Hi there!")
+
+            assert result is not None
+            assert len(result.messages) > 0
+        finally:
+            if agent.id:
+                await provider._agents_client.delete_agent(agent.id)  # type: ignore
+
+
+# endregion
@@ -1,11 +1,17 @@
 # Copyright (c) Microsoft. All rights reserved.

 import json
+import os
+from pathlib import Path
 from typing import Annotated, Any
 from unittest.mock import AsyncMock, MagicMock, patch

 import pytest
 from agent_framework import (
+    Agent,
+    AgentResponse,
+    AgentResponseUpdate,
+    AgentSession,
    ChatOptions,
    ChatResponse,
    ChatResponseUpdate,
@@ -22,6 +28,7 @@ from azure.ai.agents.models import (
    AgentsNamedToolChoiceType,
    AgentsToolChoiceOptionMode,
    CodeInterpreterToolDefinition,
+    FileInfo,
    MessageDeltaChunk,
    MessageDeltaTextContent,
    MessageDeltaTextFileCitationAnnotation,
@@ -34,12 +41,19 @@ from azure.ai.agents.models import (
    SubmitToolApprovalAction,
    SubmitToolOutputsAction,
    ThreadRun,
+    VectorStore,
 )
 from azure.core.credentials_async import AsyncTokenCredential
+from azure.identity.aio import AzureCliCredential
 from pydantic import BaseModel, Field

 from agent_framework_azure_ai import AzureAIAgentClient, AzureAISettings

+skip_if_azure_ai_integration_tests_disabled = pytest.mark.skipif(
+    os.getenv("AZURE_AI_PROJECT_ENDPOINT", "") in ("", "https://test-project.cognitiveservices.azure.com/"),
+    reason="No real AZURE_AI_PROJECT_ENDPOINT provided; skipping integration tests.",
+)
+

 def create_test_azure_ai_chat_client(
    mock_agents_client: MagicMock,
@@ -88,15 +102,6 @@ def create_test_azure_ai_chat_client(
    return client


-def test_init_emits_updated_deprecation_warning(mock_agents_client: MagicMock) -> None:
-    """Test that construction emits the updated class deprecation warning."""
-    with pytest.deprecated_call(match="V1 Agents Service API and has no direct replacement"):
-        AzureAIAgentClient(
-            agents_client=mock_agents_client,
-            agent_id="test-agent",
-        )
-
-
 def test_azure_ai_settings_init(azure_ai_unit_test_env: dict[str, str]) -> None:
    """Test AzureAISettings initialization."""
    settings = load_settings(AzureAISettings, env_prefix="AZURE_AI_")
@@ -1522,6 +1527,401 @@ def get_weather(
    return f"The weather in {location} is sunny with a high of 25°C."


+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_get_response() -> None:
+    """Test Azure AI Chat Client response."""
+    async with AzureAIAgentClient(credential=AzureCliCredential()) as azure_ai_chat_client:
+        assert isinstance(azure_ai_chat_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(
+            Message(
+                role="user",
+                text="The weather in Seattle is currently sunny with a high of 25°C. "
+                "It's a beautiful day for outdoor activities.",
+            )
+        )
+        messages.append(Message(role="user", text="What's the weather like today?"))
+
+        # Test that the agents_client can be used to get a response
+        response = await azure_ai_chat_client.get_response(messages=messages)
+
+        assert response is not None
+        assert isinstance(response, ChatResponse)
+        assert any(word in response.text.lower() for word in ["sunny", "25"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_get_response_tools() -> None:
+    """Test Azure AI Chat Client response with tools."""
+    async with AzureAIAgentClient(credential=AzureCliCredential()) as azure_ai_chat_client:
+        assert isinstance(azure_ai_chat_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(Message(role="user", text="What's the weather like in Seattle?"))
+
+        # Test that the agents_client can be used to get a response
+        response = await azure_ai_chat_client.get_response(
+            messages=messages,
+            options={"tools": [get_weather], "tool_choice": "auto"},
+        )
+
+        assert response is not None
+        assert isinstance(response, ChatResponse)
+        assert any(word in response.text.lower() for word in ["sunny", "25"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_streaming() -> None:
+    """Test Azure AI Chat Client streaming response."""
+    async with AzureAIAgentClient(credential=AzureCliCredential()) as azure_ai_chat_client:
+        assert isinstance(azure_ai_chat_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(
+            Message(
+                role="user",
+                text="The weather in Seattle is currently sunny with a high of 25°C. "
+                "It's a beautiful day for outdoor activities.",
+            )
+        )
+        messages.append(Message(role="user", text="What's the weather like today?"))
+
+        # Test that the agents_client can be used to get a response
+        response = azure_ai_chat_client.get_response(messages=messages, stream=True)
+
+        full_message: str = ""
+        async for chunk in response:
+            assert chunk is not None
+            assert isinstance(chunk, ChatResponseUpdate)
+            for content in chunk.contents:
+                if content.type == "text" and content.text:
+                    full_message += content.text
+
+        assert any(word in full_message.lower() for word in ["sunny", "25"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_streaming_tools() -> None:
+    """Test Azure AI Chat Client streaming response with tools."""
+    async with AzureAIAgentClient(credential=AzureCliCredential()) as azure_ai_chat_client:
+        assert isinstance(azure_ai_chat_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(Message(role="user", text="What's the weather like in Seattle?"))
+
+        # Test that the agents_client can be used to get a response
+        response = azure_ai_chat_client.get_response(
+            messages=messages,
+            stream=True,
+            options={"tools": [get_weather], "tool_choice": "auto"},
+        )
+        full_message: str = ""
+        async for chunk in response:
+            assert chunk is not None
+            assert isinstance(chunk, ChatResponseUpdate)
+            for content in chunk.contents:
+                if content.type == "text" and content.text:
+                    full_message += content.text
+
+        assert any(word in full_message.lower() for word in ["sunny", "25"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_basic_run() -> None:
+    """Test Agent basic run functionality with AzureAIAgentClient."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+    ) as agent:
+        # Run a simple query
+        response = await agent.run("Hello! Please respond with 'Hello World' exactly.")
+
+        # Validate response
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        assert len(response.text) > 0
+        assert "Hello World" in response.text
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_basic_run_streaming() -> None:
+    """Test Agent basic streaming functionality with AzureAIAgentClient."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+    ) as agent:
+        # Run streaming query
+        full_message: str = ""
+        async for chunk in agent.run("Please respond with exactly: 'This is a streaming response test.'", stream=True):
+            assert chunk is not None
+            assert isinstance(chunk, AgentResponseUpdate)
+            if chunk.text:
+                full_message += chunk.text
+
+        # Validate streaming response
+        assert len(full_message) > 0
+        assert "streaming response test" in full_message.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_thread_persistence() -> None:
+    """Test Agent session persistence across runs with AzureAIAgentClient."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant with good memory.",
+    ) as agent:
+        # Create a new session that will be reused
+        session = agent.create_session()
+
+        # First message - establish context
+        first_response = await agent.run(
+            "Remember this number: 42. What number did I just tell you to remember?", session=session
+        )
+        assert isinstance(first_response, AgentResponse)
+        assert "42" in first_response.text
+
+        # Second message - test conversation memory
+        second_response = await agent.run(
+            "What number did I tell you to remember in my previous message?", session=session
+        )
+        assert isinstance(second_response, AgentResponse)
+        assert "42" in second_response.text
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_existing_thread_id() -> None:
+    """Test Agent existing thread ID functionality with AzureAIAgentClient."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant with good memory.",
+    ) as first_agent:
+        # Start a conversation and get the session ID
+        session = first_agent.create_session()
+        first_response = await first_agent.run("My name is Alice. Remember this.", session=session)
+
+        # Validate first response
+        assert isinstance(first_response, AgentResponse)
+        assert first_response.text is not None
+
+        # The thread ID is set after the first response
+        existing_thread_id = session.service_session_id
+        assert existing_thread_id is not None
+
+    # Now continue with the same thread ID in a new agent instance
+    async with Agent(
+        client=AzureAIAgentClient(thread_id=existing_thread_id, credential=AzureCliCredential()),
+        instructions="You are a helpful assistant with good memory.",
+    ) as second_agent:
+        # Create a session with the existing ID
+        session = AgentSession(service_session_id=existing_thread_id)
+
+        # Ask about the previous conversation
+        response2 = await second_agent.run("What is my name?", session=session)
+
+        # Validate that the agent remembers the previous conversation
+        assert isinstance(response2, AgentResponse)
+        assert response2.text is not None
+        # Should reference Alice from the previous conversation
+        assert "alice" in response2.text.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_code_interpreter():
+    """Test Agent with code interpreter through AzureAIAgentClient."""
+
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant that can write and execute Python code.",
+        tools=[AzureAIAgentClient.get_code_interpreter_tool()],
+    ) as agent:
+        # Request code execution
+        response = await agent.run("Write Python code to calculate the factorial of 5 and show the result.")
+
+        # Validate response
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        # Factorial of 5 is 120
+        assert "120" in response.text or "factorial" in response.text.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_file_search():
+    """Test Agent with file search through AzureAIAgentClient."""
+
+    client = AzureAIAgentClient(credential=AzureCliCredential())
+    file: FileInfo | None = None
+    vector_store: VectorStore | None = None
+
+    try:
+        # 1. Read and upload the test file to the Azure AI agent service
+        test_file_path = Path(__file__).parent / "resources" / "employees.pdf"
+        file = await client.agents_client.files.upload_and_poll(file_path=str(test_file_path), purpose="assistants")
+        vector_store = await client.agents_client.vector_stores.create_and_poll(
+            file_ids=[file.id], name="test_employees_vectorstore"
+        )
+
+        # 2. Create file search tool with uploaded resources
+        file_search_tool = AzureAIAgentClient.get_file_search_tool(vector_store_ids=[vector_store.id])
+
+        async with Agent(
+            client=client,
+            instructions="You are a helpful assistant that can search through uploaded employee files.",
+            tools=[file_search_tool],
+        ) as agent:
+            # 3. Test file search functionality
+            response = await agent.run("Who is the youngest employee in the files?")
+
+            # Validate response
+            assert isinstance(response, AgentResponse)
+            assert response.text is not None
+            # Should find information about Alice Johnson (age 24) being the youngest
+            assert any(term in response.text.lower() for term in ["alice", "johnson", "24"])
+
+    finally:
+        # 4. Cleanup: Delete the vector store and file
+        try:
+            if vector_store:
+                await client.agents_client.vector_stores.delete(vector_store.id)
+            if file:
+                await client.agents_client.files.delete(file.id)
+        except Exception:
+            # Ignore cleanup errors to avoid masking the actual test failure
+            pass
+        finally:
+            await client.close()
+
+
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_hosted_mcp_tool() -> None:
+    """Integration test for MCP tool with Azure AI Agent using Microsoft Learn MCP."""
+
+    mcp_tool = AzureAIAgentClient.get_mcp_tool(
+        name="Microsoft Learn MCP",
+        url="https://learn.microsoft.com/api/mcp",
+        description="A Microsoft Learn MCP server for documentation questions",
+        approval_mode="never_require",
+    )
+
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant that can help with microsoft documentation questions.",
+        tools=[mcp_tool],
+    ) as agent:
+        response = await agent.run(
+            "How to create an Azure storage account using az cli?",
+            options={"max_tokens": 200},
+        )
+
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        assert len(response.text) > 0
+
+        # With never_require approval mode, there should be no approval requests
+        assert len(response.user_input_requests) == 0, (
+            f"Expected no approval requests with never_require mode, but got {len(response.user_input_requests)}"
+        )
+
+        # Should contain Azure-related content since it's asking about Azure CLI
+        assert any(term in response.text.lower() for term in ["azure", "storage", "account", "cli"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_level_tool_persistence():
+    """Test that agent-level tools persist across multiple runs with AzureAIAgentClient."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant that uses available tools.",
+        tools=[get_weather],
+    ) as agent:
+        # First run - agent-level tool should be available
+        first_response = await agent.run("What's the weather like in Chicago?")
+
+        assert isinstance(first_response, AgentResponse)
+        assert first_response.text is not None
+        # Should use the agent-level weather tool
+        assert any(term in first_response.text.lower() for term in ["chicago", "sunny", "25"])
+
+        # Second run - agent-level tool should still be available (persistence test)
+        second_response = await agent.run("What's the weather in Miami?")
+
+        assert isinstance(second_response, AgentResponse)
+        assert second_response.text is not None
+        # Should use the agent-level weather tool again
+        assert any(term in second_response.text.lower() for term in ["miami", "sunny", "25"])
+
+
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_chat_options_run_level() -> None:
+    """Test ChatOptions parameter coverage at run level."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant.",
+    ) as agent:
+        response = await agent.run(
+            "Provide a brief, helpful response.",
+            tools=[get_weather],
+            options={
+                "max_tokens": 100,
+                "temperature": 0.7,
+                "top_p": 0.9,
+                "tool_choice": "auto",
+                "metadata": {"test": "value"},
+            },
+        )
+
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        assert len(response.text) > 0
+
+
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_azure_ai_chat_client_agent_chat_options_agent_level() -> None:
+    """Test ChatOptions parameter coverage agent level."""
+    async with Agent(
+        client=AzureAIAgentClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant.",
+        tools=[get_weather],
+        default_options={
+            "max_tokens": 100,
+            "temperature": 0.7,
+            "top_p": 0.9,
+            "tool_choice": "auto",
+            "metadata": {"test": "value"},
+        },
+    ) as agent:
+        response = await agent.run(
+            "Provide a brief, helpful response.",
+        )
+
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        assert len(response.text) > 0
+
+
 async def test_azure_ai_chat_client_cleanup_agent_when_enabled_and_created(
    mock_agents_client: MagicMock,
 ) -> None:
@@ -11,6 +11,8 @@ from uuid import uuid4

 import pytest
 from agent_framework import (
+    Agent,
+    AgentResponse,
    Annotation,
    ChatOptions,
    ChatResponse,
@@ -22,7 +24,7 @@ from agent_framework import (
    tool,
 )
 from agent_framework._settings import load_settings
-from agent_framework_openai._chat_client import RawOpenAIChatClient
+from agent_framework.openai._responses_client import RawOpenAIResponsesClient
 from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
    ApproximateLocation,
@@ -39,11 +41,17 @@ from azure.identity.aio import AzureCliCredential
 from openai.types.responses.parsed_response import ParsedResponse
 from openai.types.responses.response import Response as OpenAIResponse
 from pydantic import BaseModel, ConfigDict, Field
-from pytest import fixture
+from pytest import fixture, param

 from agent_framework_azure_ai import AzureAIClient, AzureAISettings
 from agent_framework_azure_ai._shared import from_azure_ai_tools

+skip_if_azure_ai_integration_tests_disabled = pytest.mark.skipif(
+    os.getenv("AZURE_AI_PROJECT_ENDPOINT", "") in ("", "https://test-project.cognitiveservices.azure.com/")
+    or os.getenv("AZURE_AI_MODEL_DEPLOYMENT_NAME", "") == "",
+    reason="No real AZURE_AI_PROJECT_ENDPOINT or AZURE_AI_MODEL_DEPLOYMENT_NAME provided; skipping integration tests.",
+)
+

@pytest.fixture
 def mock_project_client() -> MagicMock:
@@ -407,7 +415,7 @@ async def test_prepare_options_basic(mock_project_client: MagicMock) -> None:

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model"},
        ),
        patch.object(
@@ -444,7 +452,7 @@ async def test_prepare_options_with_application_endpoint(

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model"},
        ),
        patch.object(
@@ -486,7 +494,7 @@ async def test_prepare_options_with_application_project_client(

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model"},
        ),
        patch.object(
@@ -504,6 +512,19 @@ async def test_prepare_options_with_application_project_client(
        assert "extra_body" not in run_options


+async def test_initialize_client(mock_project_client: MagicMock) -> None:
+    """Test _initialize_client method."""
+    client = create_test_azure_ai_client(mock_project_client)
+
+    mock_openai_client = MagicMock()
+    mock_project_client.get_openai_client = MagicMock(return_value=mock_openai_client)
+
+    await client._initialize_client()
+
+    assert client.client is mock_openai_client
+    mock_project_client.get_openai_client.assert_called_once()
+
+
 def test_update_agent_name_and_description(mock_project_client: MagicMock) -> None:
    """Test _update_agent_name_and_description method."""
    client = create_test_azure_ai_client(mock_project_client)
@@ -806,14 +827,14 @@ async def test_runtime_tools_override_logs_warning(
    messages = [Message(role="user", contents=[Content.from_text(text="Hello")])]

    with patch(
-        "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+        "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
        return_value={"model": "test-model", "tools": [{"type": "function", "name": "tool_one"}]},
    ):
        await client._prepare_options(messages, {})

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model", "tools": [{"type": "function", "name": "tool_two"}]},
        ),
        patch("agent_framework_azure_ai._client.logger.warning") as mock_warning,
@@ -832,7 +853,7 @@ async def test_prepare_options_logs_warning_for_tools_with_existing_agent_versio

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model", "tools": [{"type": "function", "name": "tool_one"}]},
        ),
        patch("agent_framework_azure_ai._client.logger.warning") as mock_warning,
@@ -854,7 +875,7 @@ async def test_prepare_options_logs_warning_for_tools_on_application_endpoint(

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model", "tools": [{"type": "function", "name": "tool_one"}]},
        ),
        patch.object(client, "_get_agent_reference_or_create", new_callable=AsyncMock) as mock_get_agent_reference,
@@ -1080,14 +1101,14 @@ async def test_runtime_structured_output_override_logs_warning(
    messages = [Message(role="user", contents=[Content.from_text(text="Hello")])]

    with patch(
-        "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+        "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
        return_value={"model": "test-model"},
    ):
        await client._prepare_options(messages, {"response_format": ResponseFormatModel})

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={"model": "test-model"},
        ),
        patch("agent_framework_azure_ai._client.logger.warning") as mock_warning,
@@ -1108,7 +1129,7 @@ async def test_prepare_options_excludes_response_format(

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={
                "model": "test-model",
                "response_format": ResponseFormatModel,
@@ -1143,7 +1164,7 @@ async def test_prepare_options_keeps_values_for_unsupported_option_keys(

    with (
        patch(
-            "agent_framework_openai._chat_client.RawOpenAIChatClient._prepare_options",
+            "agent_framework.openai._responses_client.RawOpenAIResponsesClient._prepare_options",
            return_value={
                "model": "test-model",
                "tools": [{"type": "function", "name": "weather"}],
@@ -1344,6 +1365,352 @@ async def client() -> AsyncGenerator[AzureAIClient, None]:
            await project_client.agents.delete(agent_name=agent_name)


+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+@pytest.mark.parametrize(
+    "option_name,option_value,needs_validation",
+    [
+        # Simple ChatOptions - just verify they don't fail
+        param("top_p", 0.9, False, id="top_p"),
+        param("max_tokens", 500, False, id="max_tokens"),
+        param("seed", 123, False, id="seed"),
+        param("user", "test-user-id", False, id="user"),
+        param("metadata", {"test_key": "test_value"}, False, id="metadata"),
+        param("frequency_penalty", 0.5, False, id="frequency_penalty"),
+        param("presence_penalty", 0.3, False, id="presence_penalty"),
+        param("stop", ["END"], False, id="stop"),
+        param("allow_multiple_tool_calls", True, False, id="allow_multiple_tool_calls"),
+        param("tool_choice", "none", True, id="tool_choice_none"),
+        param("tool_choice", "auto", True, id="tool_choice_auto"),
+        param("tool_choice", "required", True, id="tool_choice_required_any"),
+        param(
+            "tool_choice",
+            {"mode": "required", "required_function_name": "get_weather"},
+            True,
+            id="tool_choice_required",
+        ),
+        # OpenAIResponsesOptions - just verify they don't fail
+        param("safety_identifier", "user-hash-abc123", False, id="safety_identifier"),
+        param("truncation", "auto", False, id="truncation"),
+        param("top_logprobs", 5, False, id="top_logprobs"),
+        param("prompt_cache_key", "test-cache-key", False, id="prompt_cache_key"),
+        param("max_tool_calls", 3, False, id="max_tool_calls"),
+    ],
+)
+async def test_integration_options(
+    option_name: str,
+    option_value: Any,
+    needs_validation: bool,
+    client: AzureAIClient,
+) -> None:
+    """Parametrized test covering options that can be set at runtime for a Foundry Agent.
+
+    Tests both streaming and non-streaming modes for each option to ensure
+    they don't cause failures. Options marked with needs_validation also
+    check that the feature actually works correctly.
+
+    This test reuses a single agent.
+    """
+    # Prepare test message
+    if option_name.startswith("tool_choice"):
+        # Use weather-related prompt for tool tests
+        messages = [Message(role="user", text="What is the weather in Seattle?")]
+    else:
+        # Generic prompt for simple options
+        messages = [Message(role="user", text="Say 'Hello World' briefly.")]
+
+    # Build options dict
+    options: dict[str, Any] = {option_name: option_value, "tools": [get_weather]}
+
+    for streaming in [False, True]:
+        if streaming:
+            # Test streaming mode
+            response_stream = client.get_response(
+                messages=messages,
+                stream=True,
+                options=options,
+            )
+
+            response = await response_stream.get_final_response()
+        else:
+            # Test non-streaming mode
+            response = await client.get_response(
+                messages=messages,
+                options=options,
+            )
+
+        assert response is not None
+        assert isinstance(response, ChatResponse)
+
+        # For tool_choice="required", we return after tool execution without a model text response
+        is_required_tool_choice = option_name == "tool_choice" and (
+            option_value == "required" or (isinstance(option_value, dict) and option_value.get("mode") == "required")
+        )
+
+        if is_required_tool_choice:
+            # Response should have function call and function result, but no text from model
+            assert len(response.messages) >= 2, f"Expected function call + result for {option_name}"
+            has_function_call = any(c.type == "function_call" for msg in response.messages for c in msg.contents)
+            has_function_result = any(c.type == "function_result" for msg in response.messages for c in msg.contents)
+            assert has_function_call, f"No function call in response for {option_name}"
+            assert has_function_result, f"No function result in response for {option_name}"
+        else:
+            assert response.text is not None, f"No text in response for option '{option_name}'"
+            assert len(response.text) > 0, f"Empty response for option '{option_name}'"
+
+        # Validate based on option type
+        if needs_validation:
+            if option_name.startswith("tool_choice") and not is_required_tool_choice:
+                # Should have called the weather function
+                text = response.text.lower()
+                assert "sunny" in text or "seattle" in text, f"Tool not invoked for {option_name}"
+            elif option_name == "response_format":
+                if option_value == OutputStruct:
+                    # Should have structured output
+                    assert response.value is not None, "No structured output"
+                    assert isinstance(response.value, OutputStruct)
+                    assert "seattle" in response.value.location.lower()
+                else:
+                    # Runtime JSON schema
+                    assert response.value is None, "No structured output, can't parse any json."
+                    response_value = json.loads(response.text)
+                    assert isinstance(response_value, dict)
+                    assert "location" in response_value
+                    assert "seattle" in response_value["location"].lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+@pytest.mark.parametrize(
+    "option_name,option_value,needs_validation",
+    [
+        param("temperature", 0.7, False, id="temperature"),
+        # Complex options requiring output validation
+        param("response_format", OutputStruct, True, id="response_format_pydantic"),
+        param(
+            "response_format",
+            {
+                "type": "json_schema",
+                "json_schema": {
+                    "name": "WeatherDigest",
+                    "strict": True,
+                    "schema": {
+                        "title": "WeatherDigest",
+                        "type": "object",
+                        "properties": {
+                            "location": {"type": "string"},
+                            "conditions": {"type": "string"},
+                            "temperature_c": {"type": "number"},
+                            "advisory": {"type": "string"},
+                        },
+                        "required": ["location", "conditions", "temperature_c", "advisory"],
+                        "additionalProperties": False,
+                    },
+                },
+            },
+            True,
+            id="response_format_runtime_json_schema",
+        ),
+    ],
+)
+async def test_integration_agent_options(
+    option_name: str,
+    option_value: Any,
+    needs_validation: bool,
+) -> None:
+    """Test Foundry agent level options in both streaming and non-streaming modes.
+
+    Tests both streaming and non-streaming modes for each option to ensure
+    they don't cause failures. Options marked with needs_validation also
+    check that the feature actually works correctly.
+
+    This test create a new client and uses it for both streaming and non-streaming tests.
+    """
+    async with temporary_chat_client(agent_name=f"test-agent-{option_name.replace('_', '-')}-{uuid4()}") as client:
+        for streaming in [False, True]:
+            # Prepare test message
+            if option_name.startswith("response_format"):
+                # Use prompt that works well with structured output
+                messages = [Message(role="user", text="The weather in Seattle is sunny")]
+                messages.append(Message(role="user", text="What is the weather in Seattle?"))
+            else:
+                # Generic prompt for simple options
+                messages = [Message(role="user", text="Say 'Hello World' briefly.")]
+
+            # Build options dict
+            options = {option_name: option_value}
+
+            if streaming:
+                # Test streaming mode
+                response_stream = client.get_response(
+                    messages=messages,
+                    stream=True,
+                    options=options,
+                )
+
+                response = await response_stream.get_final_response()
+            else:
+                # Test non-streaming mode
+                response = await client.get_response(
+                    messages=messages,
+                    options=options,
+                )
+
+            assert response is not None
+            assert isinstance(response, ChatResponse)
+            assert response.text is not None, f"No text in response for option '{option_name}'"
+            assert len(response.text) > 0, f"Empty response for option '{option_name}'"
+
+            # Validate based on option type
+            if needs_validation and option_name.startswith("response_format"):
+                if option_value == OutputStruct:
+                    # Should have structured output
+                    assert response.value is not None, "No structured output"
+                    assert isinstance(response.value, OutputStruct)
+                    assert "seattle" in response.value.location.lower()
+                else:
+                    # Runtime JSON schema
+                    assert response.value is None, "No structured output, can't parse any json."
+                    response_value = json.loads(response.text)
+                    assert isinstance(response_value, dict)
+                    assert "location" in response_value
+                    assert "seattle" in response_value["location"].lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_web_search() -> None:
+    async with temporary_chat_client(agent_name="af-int-test-web-search") as client:
+        for streaming in [False, True]:
+            content = {
+                "messages": [
+                    Message(
+                        role="user",
+                        text="Who are the main characters of Kpop Demon Hunters? Do a web search to find the answer.",
+                    )
+                ],
+                "options": {
+                    "tool_choice": "auto",
+                    "tools": [client.get_web_search_tool()],
+                },
+            }
+            if streaming:
+                response = await client.get_response(stream=True, **content).get_final_response()
+            else:
+                response = await client.get_response(**content)
+
+            assert response is not None
+            assert isinstance(response, ChatResponse)
+            assert "Rumi" in response.text
+            assert "Mira" in response.text
+            assert "Zoey" in response.text
+
+            # Test that the client will use the web search tool with location
+            content = {
+                "messages": [
+                    Message(role="user", text="What is the current weather? Do not ask for my current location.")
+                ],
+                "options": {
+                    "tool_choice": "auto",
+                    "tools": [client.get_web_search_tool(user_location={"country": "US", "city": "Seattle"})],
+                },
+            }
+            if streaming:
+                response = await client.get_response(stream=True, **content).get_final_response()
+            else:
+                response = await client.get_response(**content)
+            assert response.text is not None
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_agent_hosted_mcp_tool() -> None:
+    """Integration test for MCP tool with Azure Response Agent using Microsoft Learn MCP."""
+    async with temporary_chat_client(agent_name="af-int-test-mcp") as client:
+        response = await client.get_response(
+            messages=[Message(role="user", text="How to create an Azure storage account using az cli?")],
+            options={
+                # this needs to be high enough to handle the full MCP tool response.
+                "max_tokens": 5000,
+                "tools": client.get_mcp_tool(
+                    name="Microsoft Learn MCP",
+                    url="https://learn.microsoft.com/api/mcp",
+                    description="A Microsoft Learn MCP server for documentation questions",
+                    approval_mode="never_require",
+                ),
+            },
+        )
+        assert isinstance(response, ChatResponse)
+        assert response.text
+        # Should contain Azure-related content since it's asking about Azure CLI
+        assert any(term in response.text.lower() for term in ["azure", "storage", "account", "cli"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_agent_hosted_code_interpreter_tool():
+    """Test Azure Responses Client agent with code interpreter tool through AzureAIClient."""
+    async with temporary_chat_client(agent_name="af-int-test-code-interpreter") as client:
+        response = await client.get_response(
+            messages=[Message(role="user", text="Calculate the sum of numbers from 1 to 10 using Python code.")],
+            options={
+                "tools": [client.get_code_interpreter_tool()],
+            },
+        )
+        # Should contain calculation result (sum of 1-10 = 55) or code execution content
+        contains_relevant_content = any(
+            term in response.text.lower() for term in ["55", "sum", "code", "python", "calculate", "10"]
+        )
+        assert contains_relevant_content or len(response.text.strip()) > 10
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_integration_agent_existing_session():
+    """Test Azure Responses Client agent with existing session to continue conversations across agent instances."""
+    # First conversation - capture the session
+    preserved_session = None
+
+    async with (
+        temporary_chat_client(agent_name="af-int-test-existing-session") as client,
+        Agent(
+            client=client,
+            instructions="You are a helpful assistant with good memory.",
+        ) as first_agent,
+    ):
+        # Start a conversation and capture the session
+        session = first_agent.create_session()
+        first_response = await first_agent.run("My hobby is photography. Remember this.", session=session, store=True)
+
+        assert isinstance(first_response, AgentResponse)
+        assert first_response.text is not None
+
+        # Preserve the session for reuse
+        preserved_session = session
+
+    # Second conversation - reuse the session in a new agent instance
+    if preserved_session:
+        async with (
+            temporary_chat_client(agent_name="af-int-test-existing-session-2") as client,
+            Agent(
+                client=client,
+                instructions="You are a helpful assistant with good memory.",
+            ) as second_agent,
+        ):
+            # Reuse the preserved session
+            second_response = await second_agent.run("What is my hobby?", session=preserved_session)
+
+            assert isinstance(second_response, AgentResponse)
+            assert second_response.text is not None
+            assert "photography" in second_response.text.lower()
+
+
 # region Factory Method Tests


@@ -1664,7 +2031,7 @@ async def test_inner_get_response_enriches_non_streaming(mock_project_client: Ma
    async def _fake_awaitable() -> ChatResponse:
        return base_response

-    with patch.object(RawOpenAIChatClient, "_inner_get_response", return_value=_fake_awaitable()):
+    with patch.object(RawOpenAIResponsesClient, "_inner_get_response", return_value=_fake_awaitable()):
        result_awaitable = client._inner_get_response(messages=[], options={}, stream=False)
        result = await result_awaitable  # type: ignore[misc]

@@ -1687,7 +2054,7 @@ async def test_inner_get_response_no_search_output_non_streaming(mock_project_cl
    async def _fake_awaitable() -> ChatResponse:
        return base_response

-    with patch.object(RawOpenAIChatClient, "_inner_get_response", return_value=_fake_awaitable()):
+    with patch.object(RawOpenAIResponsesClient, "_inner_get_response", return_value=_fake_awaitable()):
        result_awaitable = client._inner_get_response(messages=[], options={}, stream=False)
        result = await result_awaitable  # type: ignore[misc]

@@ -1708,7 +2075,7 @@ def test_inner_get_response_streaming_registers_hook(mock_project_client: MagicM

    mock_stream = _create_mock_stream()

-    with patch.object(RawOpenAIChatClient, "_inner_get_response", return_value=mock_stream):
+    with patch.object(RawOpenAIResponsesClient, "_inner_get_response", return_value=mock_stream):
        result = client._inner_get_response(messages=[], options={}, stream=True)

    assert result is mock_stream
@@ -1721,7 +2088,7 @@ def test_streaming_hook_captures_search_urls(mock_project_client: MagicMock) ->

    mock_stream = _create_mock_stream()

-    with patch.object(RawOpenAIChatClient, "_inner_get_response", return_value=mock_stream):
+    with patch.object(RawOpenAIResponsesClient, "_inner_get_response", return_value=mock_stream):
        client._inner_get_response(messages=[], options={}, stream=True)

    hook = mock_stream._transform_hooks[0]
@@ -1749,7 +2116,7 @@ def test_streaming_hook_enriches_url_citation(mock_project_client: MagicMock) ->

    mock_stream = _create_mock_stream()

-    with patch.object(RawOpenAIChatClient, "_inner_get_response", return_value=mock_stream):
+    with patch.object(RawOpenAIResponsesClient, "_inner_get_response", return_value=mock_stream):
        client._inner_get_response(messages=[], options={}, stream=True)

    hook = mock_stream._transform_hooks[0]
@@ -10,7 +10,7 @@ import pytest
 from agent_framework import AGENT_FRAMEWORK_USER_AGENT, AgentResponse, Message
 from agent_framework._sessions import AgentSession, SessionContext

-from agent_framework_foundry._foundry_memory_provider import FoundryMemoryProvider
+from agent_framework_azure_ai._foundry_memory_provider import FoundryMemoryProvider


@pytest.fixture
@@ -81,7 +81,7 @@ class TestInit:
    def test_init_with_project_endpoint_and_credential(
        self, mock_project_client: AsyncMock, mock_credential: Mock
    ) -> None:
-        with patch("agent_framework_foundry._foundry_memory_provider.AIProjectClient") as mock_ai_project_client:
+        with patch("agent_framework_azure_ai._foundry_memory_provider.AIProjectClient") as mock_ai_project_client:
            mock_ai_project_client.return_value = mock_project_client
            provider = FoundryMemoryProvider(
                project_endpoint="https://test.project.endpoint",
@@ -100,7 +100,7 @@ class TestInit:

    def test_init_requires_project_endpoint_without_project_client(self) -> None:
        with (
-            patch("agent_framework_foundry._foundry_memory_provider.load_settings") as mock_load_settings,
+            patch("agent_framework_azure_ai._foundry_memory_provider.load_settings") as mock_load_settings,
            patch.dict(os.environ, {}, clear=True),
            pytest.raises(ValueError, match="project endpoint is required"),
        ):
@@ -1,10 +1,12 @@
 # Copyright (c) Microsoft. All rights reserved.

+import os
 from unittest.mock import AsyncMock, MagicMock, patch

 import pytest
 from agent_framework import Agent, FunctionTool
 from agent_framework._mcp import MCPTool
+from azure.ai.projects.aio import AIProjectClient
 from azure.ai.projects.models import (
    AgentVersionDetails,
    PromptAgentDefinition,
@@ -12,9 +14,16 @@ from azure.ai.projects.models import (
 from azure.ai.projects.models import (
    FunctionTool as AzureFunctionTool,
 )
+from azure.identity.aio import AzureCliCredential

 from agent_framework_azure_ai import AzureAIProjectAgentProvider

+skip_if_azure_ai_integration_tests_disabled = pytest.mark.skipif(
+    os.getenv("AZURE_AI_PROJECT_ENDPOINT", "") in ("", "https://test-project.cognitiveservices.azure.com/")
+    or os.getenv("AZURE_AI_MODEL_DEPLOYMENT_NAME", "") == "",
+    reason="No real AZURE_AI_PROJECT_ENDPOINT or AZURE_AI_MODEL_DEPLOYMENT_NAME provided; skipping integration tests.",
+)
+

@pytest.fixture
 def mock_project_client() -> MagicMock:
@@ -680,3 +689,42 @@ async def test_provider_create_agent_with_mcp_and_regular_tools(
        assert "regular_function" in tool_names
        assert "mcp_function_1" in tool_names
        assert "mcp_function_2" in tool_names
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_ai_integration_tests_disabled
+async def test_provider_create_and_get_agent_integration() -> None:
+    """Integration test for provider create_agent and get_agent."""
+    endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
+    model = os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"]
+
+    async with (
+        AzureCliCredential() as credential,
+        AIProjectClient(endpoint=endpoint, credential=credential) as project_client,
+    ):
+        provider = AzureAIProjectAgentProvider(project_client=project_client)
+
+        try:
+            # Create agent
+            agent = await provider.create_agent(
+                name="ProviderTestAgent",
+                model=model,
+                instructions="You are a helpful assistant. Always respond with 'Hello from provider!'",
+            )
+
+            assert isinstance(agent, Agent)
+            assert agent.name == "ProviderTestAgent"
+
+            # Run the agent
+            response = await agent.run("Hi!")
+            assert response.text is not None
+            assert len(response.text) > 0
+
+            # Get the same agent
+            retrieved_agent = await provider.get_agent(name="ProviderTestAgent")
+            assert retrieved_agent.name == "ProviderTestAgent"
+
+        finally:
+            # Cleanup
+            await project_client.agents.delete(agent_name="ProviderTestAgent")
@@ -13,13 +13,10 @@ from typing import Any, ClassVar, TypedDict
 from agent_framework import AGENT_FRAMEWORK_USER_AGENT, Message
 from agent_framework._sessions import BaseHistoryProvider
 from agent_framework._settings import SecretString, load_settings
-from azure.core.credentials import TokenCredential
-from azure.core.credentials_async import AsyncTokenCredential
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes
 from azure.cosmos import PartitionKey
 from azure.cosmos.aio import ContainerProxy, CosmosClient, DatabaseProxy

-AzureCredentialTypes = TokenCredential | AsyncTokenCredential
-
 logger = logging.getLogger(__name__)


@@ -14,7 +14,7 @@ cp .env.example .env

 Required variables:
 - `AZURE_OPENAI_ENDPOINT`
- `AZURE_OPENAI_DEPLOYMENT_NAME`
+- `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`
 - `AZURE_OPENAI_API_KEY`
 - `AzureWebJobsStorage`
 - `DURABLE_TASK_SCHEDULER_CONNECTION_STRING`
@@ -111,17 +111,13 @@ def _should_skip_azure_functions_integration_tests() -> tuple[bool, str]:
            f"Durable Task Scheduler emulator not running on port {_DTS_EMULATOR_PORT}. Start with: docker run -d -p 8080:8080 -p 8082:8082 mcr.microsoft.com/dts/dts-emulator:latest",  # noqa: E501
        )

-    has_foundry_config = bool(os.getenv("FOUNDRY_PROJECT_ENDPOINT", "").strip()) and bool(
-        os.getenv("FOUNDRY_MODEL", "").strip()
-    )
-    has_azure_openai_config = bool(os.getenv("AZURE_OPENAI_ENDPOINT", "").strip()) and bool(
-        os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME", "").strip()
-    )
-    if not has_foundry_config and not has_azure_openai_config:
-        return (
-            True,
-            "No real FOUNDRY_* or AZURE_OPENAI_* configuration provided; skipping integration tests.",
-        )
+    endpoint = os.getenv("AZURE_OPENAI_ENDPOINT", "").strip()
+    if not endpoint or endpoint == "https://your-resource.openai.azure.com/":
+        return True, "No real AZURE_OPENAI_ENDPOINT provided; skipping integration tests."
+
+    deployment_name = os.getenv("AZURE_OPENAI_CHAT_DEPLOYMENT_NAME", "").strip()
+    if not deployment_name or deployment_name == "your-deployment-name":
+        return True, "No real AZURE_OPENAI_CHAT_DEPLOYMENT_NAME provided; skipping integration tests."

    return False, "Integration tests enabled."

@@ -326,22 +322,22 @@ def _is_port_in_use(port: int, host: str = _DEFAULT_HOST) -> bool:
        return sock.connect_ex((host, port)) == 0


-def _load_and_validate_env(sample_path: Path) -> None:
+def _load_and_validate_env() -> None:
    """Load .env file from current directory if it exists, then validate required environment variables.

    Raises pytest.fail if required environment variables are missing.
    """
    _load_env_file_if_present()
+
    # Required environment variables for Azure Functions samples
+    # These match the variables defined in .env.example
    required_env_vars = [
+        "AZURE_OPENAI_ENDPOINT",
+        "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME",
        "AzureWebJobsStorage",
        "DURABLE_TASK_SCHEDULER_CONNECTION_STRING",
        "FUNCTIONS_WORKER_RUNTIME",
    ]
-    if sample_path.name == "11_workflow_parallel":
-        required_env_vars.extend(["AZURE_OPENAI_ENDPOINT", "AZURE_OPENAI_DEPLOYMENT_NAME"])
-    else:
-        required_env_vars.extend(["FOUNDRY_PROJECT_ENDPOINT", "FOUNDRY_MODEL"])

    # Check if required env vars are set
    missing_vars = [var for var in required_env_vars if not os.environ.get(var)]
@@ -530,7 +526,7 @@ def function_app_for_test(request: pytest.FixtureRequest) -> Iterator[dict[str,
    assert sample_path is not None, "Sample path must be resolved before starting the function app"

    # Load .env file if it exists and validate required env vars
-    _load_and_validate_env(sample_path)
+    _load_and_validate_env()

    max_attempts = 3
    last_error: Exception | None = None
@@ -42,7 +42,6 @@ class TestWorkflowParallel:
        self.base_url = base_url
        self.helper = sample_helper

-    @pytest.mark.skip(reason="Causes timeouts.")
    def test_parallel_workflow_document_analysis(self) -> None:
        """Test parallel workflow with a standard document."""
        payload = {
@@ -71,7 +70,6 @@ class TestWorkflowParallel:
        assert status["runtimeStatus"] == "Completed"
        assert "output" in status

-    @pytest.mark.skip(reason="Causes timeouts.")
    def test_parallel_workflow_short_document(self) -> None:
        """Test parallel workflow with a short document."""
        payload = {
@@ -91,7 +89,6 @@ class TestWorkflowParallel:
        assert status["runtimeStatus"] == "Completed"
        assert "output" in status

-    @pytest.mark.skip(reason="Causes timeouts.")
    def test_parallel_workflow_technical_document(self) -> None:
        """Test parallel workflow with a technical document."""
        payload = {
@@ -115,7 +112,6 @@ class TestWorkflowParallel:
        status = self.helper.wait_for_orchestration_with_output(data["statusQueryGetUri"], max_wait=300)
        assert status["runtimeStatus"] == "Completed"

-    @pytest.mark.skip(reason="Causes timeouts.")
    def test_workflow_status_endpoint(self) -> None:
        """Test that the workflow status endpoint works correctly."""
        payload = {
@@ -14,8 +14,8 @@ Highlights

 ```bash
 pip install agent-framework-core --pre
-# Optional: Add Azure AI Foundry integration
-pip install agent-framework-foundry --pre
+# Optional: Add Azure AI integration
+pip install agent-framework-azure-ai --pre
 ```

 Supported Platforms:
@@ -36,8 +36,8 @@ AZURE_OPENAI_API_KEY=...
 AZURE_OPENAI_ENDPOINT=...
 AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=...
 ...
-FOUNDRY_PROJECT_ENDPOINT=...
-FOUNDRY_MODEL=...
+AZURE_AI_PROJECT_ENDPOINT=...
+AZURE_AI_MODEL_DEPLOYMENT_NAME=...
 ```

 You can also override environment variables by explicitly passing configuration parameters to the chat client constructor:
@@ -1995,7 +1995,6 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
        messages: Message | Sequence[Message] | None = None,
        response_id: str | None = None,
        conversation_id: str | None = None,
-        model: str | None = None,
        model_id: str | None = None,
        created_at: CreatedAtT | None = None,
        finish_reason: FinishReasonLiteral | FinishReason | None = None,
@@ -2012,9 +2011,8 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
            messages: A single Message or sequence of Message objects to include in the response.
            response_id: Optional ID of the chat response.
            conversation_id: Optional identifier for the state of the conversation.
-            model: Optional model used in the creation of the chat response.
-            model_id: Deprecated alias for ``model``.
-            created_at: Optional timestamp for when the response was created.
+            model_id: Optional model ID used in the creation of the chat response.
+            created_at: Optional timestamp for the chat response.
            finish_reason: Optional reason for the chat response (e.g., "stop", "length", "tool_calls").
            usage_details: Optional usage details for the chat response.
            value: Optional value of the structured output.
@@ -2024,8 +2022,6 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
            additional_properties: Optional additional properties associated with the chat response.
            raw_representation: Optional raw representation of the chat response from an underlying implementation.
        """
-        if model_id is not None and model is None:
-            model = model_id
        if messages is None:
            self.messages: list[Message] = []
        elif isinstance(messages, Message):
@@ -2043,7 +2039,7 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
            self.messages = processed_messages
        self.response_id = response_id
        self.conversation_id = conversation_id
-        self.model = model
+        self.model_id = model_id
        self.created_at = created_at
        self.finish_reason = finish_reason
        self.usage_details = usage_details
@@ -2056,15 +2052,6 @@ class ChatResponse(SerializationMixin, Generic[ResponseModelT]):
        self.continuation_token = continuation_token
        self.raw_representation: Any | list[Any] | None = raw_representation

-    @property
-    def model_id(self) -> str | None:
-        """Deprecated alias for :attr:`model`."""
-        return self.model
-
-    @model_id.setter
-    def model_id(self, value: str | None) -> None:
-        self.model = value
-
    @overload
    @classmethod
    def from_updates(
@@ -2262,7 +2249,6 @@ class ChatResponseUpdate(SerializationMixin):
        response_id: str | None = None,
        message_id: str | None = None,
        conversation_id: str | None = None,
-        model: str | None = None,
        model_id: str | None = None,
        created_at: CreatedAtT | None = None,
        finish_reason: FinishReasonLiteral | FinishReason | None = None,
@@ -2279,8 +2265,7 @@ class ChatResponseUpdate(SerializationMixin):
            response_id: Optional ID of the response of which this update is a part.
            message_id: Optional ID of the message of which this update is a part.
            conversation_id: Optional identifier for the state of the conversation of which this update is a part
-            model: Optional model associated with this response update.
-            model_id: Deprecated alias for ``model``.
+            model_id: Optional model ID associated with this response update.
            created_at: Optional timestamp for the chat response update.
            finish_reason: Optional finish reason for the operation.
            continuation_token: Optional token for resuming a long-running background operation.
@@ -2290,8 +2275,6 @@ class ChatResponseUpdate(SerializationMixin):
                from an underlying implementation.

        """
-        if model_id is not None and model is None:
-            model = model_id
        # Handle contents - support dict conversion for from_dict
        if contents is None:
            self.contents: list[Content] = []
@@ -2311,7 +2294,7 @@ class ChatResponseUpdate(SerializationMixin):
        self.response_id = response_id
        self.message_id = message_id
        self.conversation_id = conversation_id
-        self.model = model
+        self.model_id = model_id
        self.created_at = created_at
        self.finish_reason = finish_reason
        self.continuation_token = continuation_token
@@ -2321,15 +2304,6 @@ class ChatResponseUpdate(SerializationMixin):
        )
        self.raw_representation = raw_representation

-    @property
-    def model_id(self) -> str | None:
-        """Deprecated alias for :attr:`model`."""
-        return self.model
-
-    @model_id.setter
-    def model_id(self, value: str | None) -> None:
-        self.model = value
-
    @property
    def text(self) -> str:
        """Returns the concatenated text of all contents in the update."""
@@ -3444,7 +3418,7 @@ class Embedding(Generic[EmbeddingT]):

    Args:
        vector: The embedding vector data.
-        model: The model used to generate this embedding.
+        model_id: The model used to generate this embedding.
        dimensions: Explicit dimension count (computed from vector length if omitted).
        created_at: Timestamp of when the embedding was generated.
        additional_properties: Additional metadata.
@@ -3456,7 +3430,7 @@ class Embedding(Generic[EmbeddingT]):

            embedding = Embedding(
                vector=[0.1, 0.2, 0.3],
-                model="text-embedding-3-small",
+                model_id="text-embedding-3-small",
            )
            assert embedding.dimensions == 3
    """
@@ -3465,31 +3439,19 @@ class Embedding(Generic[EmbeddingT]):
        self,
        vector: EmbeddingT,
        *,
-        model: str | None = None,
        model_id: str | None = None,
        dimensions: int | None = None,
        created_at: datetime | None = None,
        additional_properties: dict[str, Any] | None = None,
    ) -> None:
-        if model_id is not None and model is None:
-            model = model_id
        self.vector = vector
        self._dimensions = dimensions
-        self.model = model
+        self.model_id = model_id
        self.created_at = created_at
        self.additional_properties = (
            _restore_compaction_annotation_in_additional_properties(additional_properties) or {}
        )

-    @property
-    def model_id(self) -> str | None:
-        """Deprecated alias for :attr:`model`."""
-        return self.model
-
-    @model_id.setter
-    def model_id(self, value: str | None) -> None:
-        self.model = value
-
    @property
    def dimensions(self) -> int | None:
        """Return the number of dimensions in the embedding vector.
@@ -121,7 +121,7 @@ WorkflowEventType = Literal[
    "executor_completed",  # Executor handler completed (use .executor_id, .data)
    "executor_failed",  # Executor handler raised error (use .executor_id, .details)
    # Orchestration event types (use .data for typed payload)
-    "group_chat",  # Group chat orchestrator events (use .data as GroupChatRequestSentEvent | GroupChatResponseReceivedEvent) # noqa: E501
+    "group_chat",  # Group chat orchestrator events (use .data as GroupChatRequestSentEvent | GroupChatResponseReceivedEvent)  # noqa: E501
    "handoff_sent",  # Handoff routing events (use .data as HandoffSentEvent)
    "magentic_orchestrator",  # Magentic orchestrator events (use .data as MagenticOrchestratorEvent)
 ]
@@ -2,7 +2,16 @@

 """Azure integration namespace for optional Agent Framework connectors.

-This module lazily re-exports objects from optional Azure connector packages.
+This module lazily re-exports objects from optional Azure connector packages and
+built-in core Azure OpenAI modules.
+
+Supported classes include:
+- AzureAIClient
+- AzureAIAgentClient
+- AzureOpenAIChatClient
+- AzureOpenAIResponsesClient
+- AzureAISearchContextProvider
+- DurableAIAgent
 """

 import importlib
@@ -21,17 +30,18 @@ _IMPORTS: dict[str, tuple[str, str]] = {
    "AzureAISearchSettings": ("agent_framework_azure_ai_search", "agent-framework-azure-ai-search"),
    "AzureAISettings": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
    "AzureAIAgentsProvider": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureCredentialTypes": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureTokenProvider": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIAssistantsClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIAssistantsOptions": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIChatClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIChatOptions": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIEmbeddingClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIResponsesClient": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAIResponsesOptions": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureOpenAISettings": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
-    "AzureUserSecurityContext": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
+    "AzureCredentialTypes": ("agent_framework.azure._entra_id_authentication", "agent-framework-core"),
+    "AzureTokenProvider": ("agent_framework.azure._entra_id_authentication", "agent-framework-core"),
+    "FoundryMemoryProvider": ("agent_framework_azure_ai", "agent-framework-azure-ai"),
+    "AzureOpenAIAssistantsClient": ("agent_framework.azure._assistants_client", "agent-framework-core"),
+    "AzureOpenAIAssistantsOptions": ("agent_framework.azure._assistants_client", "agent-framework-core"),
+    "AzureOpenAIChatClient": ("agent_framework.azure._chat_client", "agent-framework-core"),
+    "AzureOpenAIChatOptions": ("agent_framework.azure._chat_client", "agent-framework-core"),
+    "AzureOpenAIEmbeddingClient": ("agent_framework.azure._embedding_client", "agent-framework-core"),
+    "AzureOpenAIResponsesClient": ("agent_framework.azure._responses_client", "agent-framework-core"),
+    "AzureOpenAIResponsesOptions": ("agent_framework.azure._responses_client", "agent-framework-core"),
+    "AzureOpenAISettings": ("agent_framework.azure._shared", "agent-framework-core"),
+    "AzureUserSecurityContext": ("agent_framework.azure._chat_client", "agent-framework-core"),
    "DurableAIAgent": ("agent_framework_durabletask", "agent-framework-durabletask"),
    "DurableAIAgentClient": ("agent_framework_durabletask", "agent-framework-durabletask"),
    "DurableAIAgentOrchestrationContext": ("agent_framework_durabletask", "agent-framework-durabletask"),
@@ -1,8 +1,5 @@
 # Copyright (c) Microsoft. All rights reserved.

-# Type stubs for the agent_framework.azure lazy-loading namespace.
-# Install the relevant packages for full type support.
-
 from agent_framework_azure_ai import (
    AzureAIAgentClient,
    AzureAIAgentsProvider,
@@ -10,23 +7,9 @@ from agent_framework_azure_ai import (
    AzureAIProjectAgentOptions,
    AzureAIProjectAgentProvider,
    AzureAISettings,
-    AzureCredentialTypes,
-    AzureOpenAIAssistantsClient,
-    AzureOpenAIAssistantsOptions,
-    AzureOpenAIChatClient,
-    AzureOpenAIChatOptions,
-    AzureOpenAIEmbeddingClient,
-    AzureOpenAIResponsesClient,
-    AzureOpenAIResponsesOptions,
-    AzureOpenAISettings,
-    AzureTokenProvider,
-    AzureUserSecurityContext,
-    RawAzureAIClient,
-)
-from agent_framework_azure_ai_search import (
-    AzureAISearchContextProvider,
-    AzureAISearchSettings,
+    FoundryMemoryProvider,
 )
+from agent_framework_azure_ai_search import AzureAISearchContextProvider, AzureAISearchSettings
 from agent_framework_azurefunctions import AgentFunctionApp
 from agent_framework_durabletask import (
    AgentCallbackContext,
@@ -37,6 +20,13 @@ from agent_framework_durabletask import (
    DurableAIAgentWorker,
 )

+from agent_framework.azure._assistants_client import AzureOpenAIAssistantsClient
+from agent_framework.azure._chat_client import AzureOpenAIChatClient
+from agent_framework.azure._embedding_client import AzureOpenAIEmbeddingClient
+from agent_framework.azure._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider
+from agent_framework.azure._responses_client import AzureOpenAIResponsesClient
+from agent_framework.azure._shared import AzureOpenAISettings
+
 __all__ = [
    "AgentCallbackContext",
    "AgentFunctionApp",
@@ -51,18 +41,14 @@ __all__ = [
    "AzureAISettings",
    "AzureCredentialTypes",
    "AzureOpenAIAssistantsClient",
-    "AzureOpenAIAssistantsOptions",
    "AzureOpenAIChatClient",
-    "AzureOpenAIChatOptions",
    "AzureOpenAIEmbeddingClient",
    "AzureOpenAIResponsesClient",
-    "AzureOpenAIResponsesOptions",
    "AzureOpenAISettings",
    "AzureTokenProvider",
-    "AzureUserSecurityContext",
    "DurableAIAgent",
    "DurableAIAgentClient",
    "DurableAIAgentOrchestrationContext",
    "DurableAIAgentWorker",
-    "RawAzureAIClient",
+    "FoundryMemoryProvider",
 ]
@@ -0,0 +1,194 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from __future__ import annotations
+
+import sys
+from collections.abc import Mapping
+from typing import Any, ClassVar, Generic
+
+from openai.lib.azure import AsyncAzureOpenAI
+
+from .._settings import load_settings
+from ..openai import OpenAIAssistantsClient
+from ..openai._assistants_client import OpenAIAssistantsOptions
+from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider, resolve_credential_to_token_provider
+from ._shared import AzureOpenAISettings, _apply_azure_defaults  # pyright: ignore[reportPrivateUsage]
+
+if sys.version_info >= (3, 13):
+    from typing import TypeVar  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 11):
+    from typing import TypedDict  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
+
+
+# region Azure OpenAI Assistants Options TypedDict
+
+
+AzureOpenAIAssistantsOptionsT = TypeVar(
+    "AzureOpenAIAssistantsOptionsT",
+    bound=TypedDict,  # type: ignore[valid-type]
+    default="OpenAIAssistantsOptions",
+    covariant=True,
+)
+
+
+# endregion
+
+
+class AzureOpenAIAssistantsClient(
+    OpenAIAssistantsClient[AzureOpenAIAssistantsOptionsT], Generic[AzureOpenAIAssistantsOptionsT]
+):
+    """Azure OpenAI Assistants client."""
+
+    DEFAULT_AZURE_API_VERSION: ClassVar[str] = "2024-05-01-preview"
+
+    def __init__(
+        self,
+        *,
+        deployment_name: str | None = None,
+        assistant_id: str | None = None,
+        assistant_name: str | None = None,
+        assistant_description: str | None = None,
+        thread_id: str | None = None,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        api_version: str | None = None,
+        token_endpoint: str | None = None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
+        default_headers: Mapping[str, str] | None = None,
+        async_client: AsyncAzureOpenAI | None = None,
+        env_file_path: str | None = None,
+        env_file_encoding: str | None = None,
+    ) -> None:
+        """Initialize an Azure OpenAI Assistants client.
+
+        Keyword Args:
+            deployment_name: The Azure OpenAI deployment name for the model to use.
+                Can also be set via environment variable AZURE_OPENAI_CHAT_DEPLOYMENT_NAME.
+            assistant_id: The ID of an Azure OpenAI assistant to use.
+                If not provided, a new assistant will be created (and deleted after the request).
+            assistant_name: The name to use when creating new assistants.
+            assistant_description: The description to use when creating new assistants.
+            thread_id: Default thread ID to use for conversations. Can be overridden by
+                conversation_id property when making a request.
+                If not provided, a new thread will be created (and deleted after the request).
+            api_key: The API key to use. If provided will override the env vars or .env file value.
+                Can also be set via environment variable AZURE_OPENAI_API_KEY.
+            endpoint: The deployment endpoint. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_ENDPOINT.
+            base_url: The deployment base URL. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_BASE_URL.
+            api_version: The deployment API version. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_API_VERSION.
+            token_endpoint: The token endpoint to request an Azure token.
+                Can also be set via environment variable AZURE_OPENAI_TOKEN_ENDPOINT.
+            credential: Azure credential or token provider for authentication. Accepts a
+                ``TokenCredential``, ``AsyncTokenCredential``, or a callable that returns a
+                bearer token string (sync or async), for example from
+                ``azure.identity.get_bearer_token_provider()``.
+            default_headers: The default headers mapping of string keys to
+                string values for HTTP requests.
+            async_client: An existing client to use.
+            env_file_path: Use the environment settings file as a fallback
+                to environment variables.
+            env_file_encoding: The encoding of the environment settings file.
+
+        Examples:
+            .. code-block:: python
+
+                from agent_framework.azure import AzureOpenAIAssistantsClient
+
+                # Using environment variables
+                # Set AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com
+                # Set AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4
+                # Set AZURE_OPENAI_API_KEY=your-key
+                client = AzureOpenAIAssistantsClient()
+
+                # Or passing parameters directly
+                client = AzureOpenAIAssistantsClient(
+                    endpoint="https://your-endpoint.openai.azure.com", deployment_name="gpt-4", api_key="your-key"
+                )
+
+                # Or loading from a .env file
+                client = AzureOpenAIAssistantsClient(env_file_path="path/to/.env")
+
+                # Using custom ChatOptions with type safety:
+                from typing import TypedDict
+                from agent_framework.azure import AzureOpenAIAssistantsOptions
+
+
+                class MyOptions(AzureOpenAIAssistantsOptions, total=False):
+                    my_custom_option: str
+
+
+                client: AzureOpenAIAssistantsClient[MyOptions] = AzureOpenAIAssistantsClient()
+                response = await client.get_response("Hello", options={"my_custom_option": "value"})
+        """
+        azure_openai_settings = load_settings(
+            AzureOpenAISettings,
+            env_prefix="AZURE_OPENAI_",
+            api_key=api_key,
+            base_url=base_url,
+            endpoint=endpoint,
+            chat_deployment_name=deployment_name,
+            api_version=api_version,
+            env_file_path=env_file_path,
+            env_file_encoding=env_file_encoding,
+            token_endpoint=token_endpoint,
+        )
+        _apply_azure_defaults(azure_openai_settings, default_api_version=self.DEFAULT_AZURE_API_VERSION)
+
+        chat_deployment_name = azure_openai_settings.get("chat_deployment_name")
+        if not chat_deployment_name:
+            raise ValueError(
+                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
+                "or 'AZURE_OPENAI_CHAT_DEPLOYMENT_NAME' environment variable."
+            )
+
+        api_key_secret = azure_openai_settings.get("api_key")
+        token_scope = azure_openai_settings.get("token_endpoint")
+
+        # Resolve credential to token provider
+        ad_token_provider = None
+        if not async_client and not api_key_secret and credential:
+            ad_token_provider = resolve_credential_to_token_provider(credential, token_scope)
+
+        if not async_client and not api_key_secret and not ad_token_provider:
+            raise ValueError("Please provide either api_key, credential, or a client.")
+
+        # Create Azure client if not provided
+        if not async_client:
+            client_params: dict[str, Any] = {
+                "default_headers": default_headers,
+            }
+            if resolved_api_version := azure_openai_settings.get("api_version"):
+                client_params["api_version"] = resolved_api_version
+
+            if api_key_secret:
+                client_params["api_key"] = api_key_secret.get_secret_value()
+            elif ad_token_provider:
+                client_params["azure_ad_token_provider"] = ad_token_provider
+
+            if resolved_base_url := azure_openai_settings.get("base_url"):
+                client_params["base_url"] = str(resolved_base_url)
+            elif resolved_endpoint := azure_openai_settings.get("endpoint"):
+                client_params["azure_endpoint"] = str(resolved_endpoint)
+
+            async_client = AsyncAzureOpenAI(**client_params)
+
+        super().__init__(
+            model_id=chat_deployment_name,
+            assistant_id=assistant_id,
+            assistant_name=assistant_name,
+            assistant_description=assistant_description,
+            thread_id=thread_id,
+            async_client=async_client,  # type: ignore[reportArgumentType]
+            default_headers=default_headers,
+        )
@@ -0,0 +1,349 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from __future__ import annotations
+
+import json
+import logging
+import sys
+from collections.abc import Mapping, Sequence
+from typing import TYPE_CHECKING, Any, Generic, cast
+
+from pydantic import BaseModel
+
+from agent_framework import (
+    Annotation,
+    ChatMiddlewareLayer,
+    ChatResponse,
+    ChatResponseUpdate,
+    Content,
+    FunctionInvocationConfiguration,
+    FunctionInvocationLayer,
+)
+from agent_framework.observability import ChatTelemetryLayer
+from agent_framework.openai._chat_client import OpenAIChatOptions, RawOpenAIChatClient
+
+from .._settings import load_settings
+from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider
+from ._shared import (
+    AzureOpenAIConfigMixin,
+    AzureOpenAISettings,
+    _apply_azure_defaults,  # pyright: ignore[reportPrivateUsage]
+)
+
+if sys.version_info >= (3, 13):
+    from typing import TypeVar  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 12):
+    from typing import override  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import override  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 11):
+    from typing import TypedDict  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
+
+if TYPE_CHECKING:
+    from openai.lib.azure import AsyncAzureOpenAI
+    from openai.types.chat.chat_completion import Choice
+    from openai.types.chat.chat_completion_chunk import Choice as ChunkChoice
+
+    from agent_framework._middleware import MiddlewareTypes
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+ResponseModelT = TypeVar("ResponseModelT", bound=BaseModel | None, default=None)
+
+
+# region Azure OpenAI Chat Options TypedDict
+
+
+class AzureUserSecurityContext(TypedDict, total=False):
+    """User security context for Azure AI applications.
+
+    These fields help security operations teams investigate and mitigate security
+    incidents by providing context about the application and end user.
+
+    Learn more: https://learn.microsoft.com/azure/well-architected/service-guides/cosmos-db
+    """
+
+    application_name: str
+    """Name of the application making the request."""
+
+    end_user_id: str
+    """Unique identifier for the end user (recommend hashing username/email)."""
+
+    end_user_tenant_id: str
+    """Microsoft 365 tenant ID the end user belongs to. Required for multi-tenant apps."""
+
+    source_ip: str
+    """The original client's IP address."""
+
+
+class AzureOpenAIChatOptions(OpenAIChatOptions[ResponseModelT], Generic[ResponseModelT], total=False):
+    """Azure OpenAI-specific chat options dict.
+
+    Extends OpenAIChatOptions with Azure-specific options including
+    the "On Your Data" feature and enhanced security context.
+
+    See: https://learn.microsoft.com/azure/ai-foundry/openai/reference-preview-latest
+
+    Keys:
+        # Inherited from OpenAIChatOptions/ChatOptions:
+        model_id: The model to use for the request,
+            translates to ``model`` in Azure OpenAI API.
+        temperature: Sampling temperature between 0 and 2.
+        top_p: Nucleus sampling parameter.
+        max_tokens: Maximum number of tokens to generate,
+            translates to ``max_completion_tokens`` in Azure OpenAI API.
+        stop: Stop sequences.
+        seed: Random seed for reproducibility.
+        frequency_penalty: Frequency penalty between -2.0 and 2.0.
+        presence_penalty: Presence penalty between -2.0 and 2.0.
+        tools: List of tools (functions) available to the model.
+        tool_choice: How the model should use tools.
+        allow_multiple_tool_calls: Whether to allow parallel tool calls,
+            translates to ``parallel_tool_calls`` in Azure OpenAI API.
+        response_format: Structured output schema.
+        metadata: Request metadata for tracking.
+        user: End-user identifier for abuse monitoring.
+        store: Whether to store the conversation.
+        instructions: System instructions for the model.
+        logit_bias: Token bias values (-100 to 100).
+        logprobs: Whether to return log probabilities.
+        top_logprobs: Number of top log probabilities to return (0-20).
+
+        # Azure-specific options:
+        data_sources: Azure "On Your Data" data sources configuration.
+        user_security_context: Enhanced security context for Azure Defender.
+        n: Number of chat completions to generate (not recommended, incurs costs).
+    """
+
+    # Azure-specific options
+    data_sources: list[dict[str, Any]]
+    """Azure "On Your Data" data sources for retrieval-augmented generation.
+
+    Supported types: azure_search, azure_cosmos_db, elasticsearch, pinecone, mongo_db.
+    See: https://learn.microsoft.com/azure/ai-foundry/openai/references/on-your-data
+    """
+
+    user_security_context: AzureUserSecurityContext
+    """Enhanced security context for Azure Defender integration."""
+
+    n: int
+    """Number of chat completion choices to generate for each input message.
+    Note: You will be charged based on tokens across all choices. Keep n=1 to minimize costs."""
+
+
+AzureOpenAIChatOptionsT = TypeVar(
+    "AzureOpenAIChatOptionsT",
+    bound=TypedDict,  # type: ignore[valid-type]
+    default="AzureOpenAIChatOptions",
+    covariant=True,
+)
+
+
+# endregion
+
+ChatResponseT = TypeVar("ChatResponseT", ChatResponse, ChatResponseUpdate)
+AzureOpenAIChatClientT = TypeVar("AzureOpenAIChatClientT", bound="AzureOpenAIChatClient")
+
+
+class AzureOpenAIChatClient(  # type: ignore[misc]
+    AzureOpenAIConfigMixin,
+    FunctionInvocationLayer[AzureOpenAIChatOptionsT],
+    ChatMiddlewareLayer[AzureOpenAIChatOptionsT],
+    ChatTelemetryLayer[AzureOpenAIChatOptionsT],
+    RawOpenAIChatClient[AzureOpenAIChatOptionsT],
+    Generic[AzureOpenAIChatOptionsT],
+):
+    """Azure OpenAI Chat completion class with middleware, telemetry, and function invocation support."""
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        deployment_name: str | None = None,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        api_version: str | None = None,
+        token_endpoint: str | None = None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
+        default_headers: Mapping[str, str] | None = None,
+        async_client: AsyncAzureOpenAI | None = None,
+        additional_properties: dict[str, Any] | None = None,
+        env_file_path: str | None = None,
+        env_file_encoding: str | None = None,
+        instruction_role: str | None = None,
+        middleware: Sequence[MiddlewareTypes] | None = None,
+        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
+    ) -> None:
+        """Initialize an Azure OpenAI Chat completion client.
+
+        Keyword Args:
+            api_key: The API key. If provided, will override the value in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_API_KEY.
+            deployment_name: The deployment name. If provided, will override the value
+                (chat_deployment_name) in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_CHAT_DEPLOYMENT_NAME.
+            endpoint: The deployment endpoint. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_ENDPOINT.
+            base_url: The deployment base URL. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_BASE_URL.
+            api_version: The deployment API version. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_API_VERSION.
+            token_endpoint: The token endpoint to request an Azure token.
+                Can also be set via environment variable AZURE_OPENAI_TOKEN_ENDPOINT.
+            credential: Azure credential or token provider for authentication. Accepts a
+                ``TokenCredential``, ``AsyncTokenCredential``, or a callable that returns a
+                bearer token string (sync or async), for example from
+                ``azure.identity.get_bearer_token_provider()``.
+            default_headers: The default headers mapping of string keys to
+                string values for HTTP requests.
+            async_client: An existing client to use.
+            additional_properties: Additional properties stored on the client instance.
+            env_file_path: Use the environment settings file as a fallback to using env vars.
+            env_file_encoding: The encoding of the environment settings file, defaults to 'utf-8'.
+            instruction_role: The role to use for 'instruction' messages, for example, summarization
+                prompts could use `developer` or `system`.
+            middleware: Optional sequence of middleware to apply to requests.
+            function_invocation_configuration: Optional configuration for function invocation behavior.
+
+        Examples:
+            .. code-block:: python
+
+                from agent_framework.azure import AzureOpenAIChatClient
+
+                # Using environment variables
+                # Set AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com
+                # Set AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=<model name>
+                # Set AZURE_OPENAI_API_KEY=your-key
+                client = AzureOpenAIChatClient()
+
+                # Or passing parameters directly
+                client = AzureOpenAIChatClient(
+                    endpoint="https://your-endpoint.openai.azure.com",
+                    deployment_name="<model name>",
+                    api_key="your-key",
+                )
+
+                # Or loading from a .env file
+                client = AzureOpenAIChatClient(env_file_path="path/to/.env")
+
+                # Using custom ChatOptions with type safety:
+                from typing import TypedDict
+                from agent_framework.azure import AzureOpenAIChatOptions
+
+
+                class MyOptions(AzureOpenAIChatOptions, total=False):
+                    my_custom_option: str
+
+
+                client: AzureOpenAIChatClient[MyOptions] = AzureOpenAIChatClient()
+                response = await client.get_response("Hello", options={"my_custom_option": "value"})
+        """
+        azure_openai_settings = load_settings(
+            AzureOpenAISettings,
+            env_prefix="AZURE_OPENAI_",
+            api_key=api_key,
+            base_url=base_url,
+            endpoint=endpoint,
+            chat_deployment_name=deployment_name,
+            api_version=api_version,
+            env_file_path=env_file_path,
+            env_file_encoding=env_file_encoding,
+            token_endpoint=token_endpoint,
+        )
+        _apply_azure_defaults(azure_openai_settings)
+
+        chat_deployment_name = azure_openai_settings.get("chat_deployment_name")
+        if not chat_deployment_name:
+            raise ValueError(
+                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
+                "or 'AZURE_OPENAI_CHAT_DEPLOYMENT_NAME' environment variable."
+            )
+
+        endpoint_value = azure_openai_settings.get("endpoint")
+        base_url_value = azure_openai_settings.get("base_url")
+        api_version_value = cast(str, azure_openai_settings.get("api_version"))
+        api_key_value = azure_openai_settings.get("api_key")
+        token_endpoint_value = azure_openai_settings.get("token_endpoint")
+
+        super().__init__(
+            deployment_name=chat_deployment_name,
+            endpoint=endpoint_value,
+            base_url=base_url_value,
+            api_version=api_version_value,
+            api_key=api_key_value.get_secret_value() if api_key_value else None,
+            token_endpoint=token_endpoint_value,
+            credential=credential,
+            default_headers=default_headers,
+            client=async_client,
+            additional_properties=additional_properties,
+            instruction_role=instruction_role,
+            middleware=middleware,
+            function_invocation_configuration=function_invocation_configuration,
+        )
+
+    @override
+    def _parse_text_from_openai(self, choice: Choice | ChunkChoice) -> Content | None:
+        """Parse the choice into a Content object with type='text'.
+
+        Overwritten from RawOpenAIChatClient to deal with Azure On Your Data function.
+        For docs see:
+        https://learn.microsoft.com/en-us/azure/ai-foundry/openai/references/on-your-data?tabs=python#context
+        """
+        message = getattr(choice, "message", None)
+        if message is None:
+            message = getattr(choice, "delta", None)
+        # When you enable asynchronous content filtering in Azure OpenAI, you may receive empty deltas
+        if message is None:  # type: ignore
+            return None
+        if hasattr(message, "refusal") and message.refusal:
+            return Content.from_text(text=message.refusal, raw_representation=choice)
+        if not message.content:
+            return None
+        text_content = Content.from_text(text=message.content, raw_representation=choice)
+        if not message.model_extra or "context" not in message.model_extra:
+            return text_content
+
+        context_raw: object = cast(object, message.context)  # type: ignore[union-attr]
+        if isinstance(context_raw, str):
+            try:
+                context_raw = json.loads(context_raw)
+            except json.JSONDecodeError:
+                logger.warning("Context is not a valid JSON string, ignoring context.")
+                return text_content
+        if not isinstance(context_raw, dict):
+            logger.warning("Context is not a valid dictionary, ignoring context.")
+            return text_content
+        context = cast(dict[str, Any], context_raw)
+        # `all_retrieved_documents` is currently not used, but can be retrieved
+        # through the raw_representation in the text content.
+        if intent := context.get("intent"):
+            text_content.additional_properties = {"intent": intent}
+        citations = context.get("citations")
+        if isinstance(citations, list) and citations:
+            annotations: list[Annotation] = []
+            for citation_raw in cast(list[object], citations):
+                if not isinstance(citation_raw, dict):
+                    continue
+                citation = cast(dict[str, Any], citation_raw)
+                annotations.append(
+                    Annotation(
+                        type="citation",
+                        title=citation.get("title", ""),
+                        url=citation.get("url", ""),
+                        snippet=citation.get("content", ""),
+                        file_id=citation.get("filepath", ""),
+                        tool_name="Azure-on-your-Data",
+                        additional_properties={"chunk_id": citation.get("chunk_id", "")},
+                        raw_representation=citation,
+                    )
+                )
+            text_content.annotations = annotations
+        return text_content
@@ -0,0 +1,141 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from __future__ import annotations
+
+import sys
+from collections.abc import Mapping
+from typing import Generic
+
+from openai.lib.azure import AsyncAzureOpenAI
+
+from agent_framework.observability import EmbeddingTelemetryLayer
+from agent_framework.openai import OpenAIEmbeddingOptions
+from agent_framework.openai._embedding_client import RawOpenAIEmbeddingClient
+
+from .._settings import load_settings
+from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider
+from ._shared import (
+    AzureOpenAIConfigMixin,
+    AzureOpenAISettings,
+    _apply_azure_defaults,  # pyright: ignore[reportPrivateUsage]
+)
+
+if sys.version_info >= (3, 13):
+    from typing import TypeVar  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 11):
+    from typing import TypedDict  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
+
+
+AzureOpenAIEmbeddingOptionsT = TypeVar(
+    "AzureOpenAIEmbeddingOptionsT",
+    bound=TypedDict,  # type: ignore[valid-type]
+    default="OpenAIEmbeddingOptions",
+    covariant=True,
+)
+
+
+class AzureOpenAIEmbeddingClient(
+    AzureOpenAIConfigMixin,
+    EmbeddingTelemetryLayer[str, list[float], AzureOpenAIEmbeddingOptionsT],
+    RawOpenAIEmbeddingClient[AzureOpenAIEmbeddingOptionsT],
+    Generic[AzureOpenAIEmbeddingOptionsT],
+):
+    """Azure OpenAI embedding client with telemetry support.
+
+    Keyword Args:
+        api_key: The API key. If provided, will override the value in the env vars or .env file.
+            Can also be set via environment variable AZURE_OPENAI_API_KEY.
+        deployment_name: The deployment name. If provided, will override the value
+            (embedding_deployment_name) in the env vars or .env file.
+            Can also be set via environment variable AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME.
+        endpoint: The deployment endpoint.
+            Can also be set via environment variable AZURE_OPENAI_ENDPOINT.
+        base_url: The deployment base URL.
+            Can also be set via environment variable AZURE_OPENAI_BASE_URL.
+        api_version: The deployment API version.
+            Can also be set via environment variable AZURE_OPENAI_API_VERSION.
+        token_endpoint: The token endpoint to request an Azure token.
+            Can also be set via environment variable AZURE_OPENAI_TOKEN_ENDPOINT.
+        credential: Azure credential or token provider for authentication.
+        default_headers: Default headers for HTTP requests.
+        async_client: An existing client to use.
+        env_file_path: Path to .env file for settings.
+        env_file_encoding: Encoding for .env file.
+
+    Examples:
+        .. code-block:: python
+
+            from agent_framework.azure import AzureOpenAIEmbeddingClient
+
+            # Using environment variables
+            # Set AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com
+            # Set AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=text-embedding-3-small
+            # Set AZURE_OPENAI_API_KEY=your-key
+            client = AzureOpenAIEmbeddingClient()
+
+            # Or passing parameters directly
+            client = AzureOpenAIEmbeddingClient(
+                endpoint="https://your-endpoint.openai.azure.com",
+                deployment_name="text-embedding-3-small",
+                api_key="your-key",
+            )
+
+            result = await client.get_embeddings(["Hello, world!"])
+    """
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        deployment_name: str | None = None,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        api_version: str | None = None,
+        token_endpoint: str | None = None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
+        default_headers: Mapping[str, str] | None = None,
+        async_client: AsyncAzureOpenAI | None = None,
+        otel_provider_name: str | None = None,
+        env_file_path: str | None = None,
+        env_file_encoding: str | None = None,
+    ) -> None:
+        """Initialize an Azure OpenAI embedding client."""
+        azure_openai_settings = load_settings(
+            AzureOpenAISettings,
+            env_prefix="AZURE_OPENAI_",
+            api_key=api_key,
+            base_url=base_url,
+            endpoint=endpoint,
+            embedding_deployment_name=deployment_name,
+            api_version=api_version,
+            env_file_path=env_file_path,
+            env_file_encoding=env_file_encoding,
+            token_endpoint=token_endpoint,
+        )
+        _apply_azure_defaults(azure_openai_settings)
+
+        embedding_deployment_name = azure_openai_settings.get("embedding_deployment_name")
+        if not embedding_deployment_name:
+            raise ValueError(
+                "Azure OpenAI embedding deployment name is required. Set via 'deployment_name' parameter "
+                "or 'AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME' environment variable."
+            )
+
+        api_key_secret = azure_openai_settings.get("api_key")
+
+        super().__init__(
+            deployment_name=embedding_deployment_name,
+            endpoint=azure_openai_settings.get("endpoint"),
+            base_url=azure_openai_settings.get("base_url"),
+            api_version=azure_openai_settings.get("api_version") or "",
+            api_key=api_key_secret.get_secret_value() if api_key_secret else None,
+            token_endpoint=azure_openai_settings.get("token_endpoint"),
+            credential=credential,
+            default_headers=default_headers,
+            client=async_client,
+            otel_provider_name=otel_provider_name,
+        )
@@ -6,10 +6,11 @@ import logging
 from collections.abc import Awaitable, Callable
 from typing import Union

-from agent_framework.exceptions import ChatClientInvalidAuthException
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential

+from ..exceptions import ChatClientInvalidAuthException
+
 logger: logging.Logger = logging.getLogger(__name__)

 AzureTokenProvider = Callable[[], Union[str, Awaitable[str]]]
@@ -0,0 +1,277 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from __future__ import annotations
+
+import sys
+from collections.abc import Mapping, Sequence
+from typing import TYPE_CHECKING, Any, Generic
+from urllib.parse import urljoin, urlparse
+
+from azure.ai.projects.aio import AIProjectClient
+from openai import AsyncOpenAI
+
+from .._middleware import ChatMiddlewareLayer
+from .._settings import load_settings
+from .._telemetry import AGENT_FRAMEWORK_USER_AGENT
+from .._tools import FunctionInvocationConfiguration, FunctionInvocationLayer
+from ..observability import ChatTelemetryLayer
+from ..openai._responses_client import RawOpenAIResponsesClient
+from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider
+from ._shared import (
+    AzureOpenAIConfigMixin,
+    AzureOpenAISettings,
+    _apply_azure_defaults,  # pyright: ignore[reportPrivateUsage]
+)
+
+if sys.version_info >= (3, 13):
+    from typing import TypeVar  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypeVar  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 12):
+    from typing import override  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import override  # type: ignore # pragma: no cover
+if sys.version_info >= (3, 11):
+    from typing import TypedDict  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
+
+if TYPE_CHECKING:
+    from .._middleware import MiddlewareTypes
+    from ..openai._responses_client import OpenAIResponsesOptions
+
+
+AzureOpenAIResponsesOptionsT = TypeVar(
+    "AzureOpenAIResponsesOptionsT",
+    bound=TypedDict,  # type: ignore[valid-type]
+    default="OpenAIResponsesOptions",
+    covariant=True,
+)
+
+
+class AzureOpenAIResponsesClient(  # type: ignore[misc]
+    AzureOpenAIConfigMixin,
+    FunctionInvocationLayer[AzureOpenAIResponsesOptionsT],
+    ChatMiddlewareLayer[AzureOpenAIResponsesOptionsT],
+    ChatTelemetryLayer[AzureOpenAIResponsesOptionsT],
+    RawOpenAIResponsesClient[AzureOpenAIResponsesOptionsT],
+    Generic[AzureOpenAIResponsesOptionsT],
+):
+    """Azure Responses completion class with middleware, telemetry, and function invocation support."""
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        deployment_name: str | None = None,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        api_version: str | None = None,
+        token_endpoint: str | None = None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
+        default_headers: Mapping[str, str] | None = None,
+        async_client: AsyncOpenAI | None = None,
+        project_client: Any | None = None,
+        project_endpoint: str | None = None,
+        allow_preview: bool | None = None,
+        env_file_path: str | None = None,
+        env_file_encoding: str | None = None,
+        instruction_role: str | None = None,
+        middleware: Sequence[MiddlewareTypes] | None = None,
+        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
+        **kwargs: Any,
+    ) -> None:
+        """Initialize an Azure OpenAI Responses client.
+
+        The client can be created in two ways:
+
+        1. **Direct Azure OpenAI** (default): Provide endpoint, api_key, or credential
+           to connect directly to an Azure OpenAI deployment.
+        2. **Foundry project endpoint**: Provide a ``project_client`` or ``project_endpoint``
+           (with ``credential``) to create the client via an Azure AI Foundry project.
+           This requires the ``azure-ai-projects`` package to be installed.
+
+        Keyword Args:
+            api_key: The API key. If provided, will override the value in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_API_KEY.
+            deployment_name: The deployment name. If provided, will override the value
+                (responses_deployment_name) in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME.
+            endpoint: The deployment endpoint. If provided will override the value
+                in the env vars or .env file.
+                Can also be set via environment variable AZURE_OPENAI_ENDPOINT.
+            base_url: The deployment base URL. If provided will override the value
+                in the env vars or .env file. Currently, the base_url must end with "/openai/v1/".
+                Can also be set via environment variable AZURE_OPENAI_BASE_URL.
+            api_version: The deployment API version. If provided will override the value
+                in the env vars or .env file. Currently, the api_version must be "preview".
+                Can also be set via environment variable AZURE_OPENAI_API_VERSION.
+            token_endpoint: The token endpoint to request an Azure token.
+                Can also be set via environment variable AZURE_OPENAI_TOKEN_ENDPOINT.
+            credential: Azure credential or token provider for authentication. Accepts a
+                ``TokenCredential``, ``AsyncTokenCredential``, or a callable that returns a
+                bearer token string (sync or async), for example from
+                ``azure.identity.get_bearer_token_provider()``.
+            default_headers: The default headers mapping of string keys to
+                string values for HTTP requests.
+            async_client: An existing client to use.
+            project_client: An existing ``AIProjectClient`` (from ``azure.ai.projects.aio``) to use.
+                The OpenAI client will be obtained via ``project_client.get_openai_client()``.
+                Requires the ``azure-ai-projects`` package.
+            project_endpoint: The Azure AI Foundry project endpoint URL.
+                When provided with ``credential``, an ``AIProjectClient`` will be created
+                and used to obtain the OpenAI client. Requires the ``azure-ai-projects`` package.
+            allow_preview: Enables preview opt-in on internally-created ``AIProjectClient``.
+            env_file_path: Use the environment settings file as a fallback to using env vars.
+            env_file_encoding: The encoding of the environment settings file, defaults to 'utf-8'.
+            instruction_role: The role to use for 'instruction' messages, for example, summarization
+                prompts could use `developer` or `system`.
+            middleware: Optional sequence of middleware to apply to requests.
+            function_invocation_configuration: Optional configuration for function invocation behavior.
+            kwargs: Additional keyword arguments.
+
+        Examples:
+            .. code-block:: python
+
+                from agent_framework.azure import AzureOpenAIResponsesClient
+
+                # Using environment variables
+                # Set AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com
+                # Set AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4o
+                # Set AZURE_OPENAI_API_KEY=your-key
+                client = AzureOpenAIResponsesClient()
+
+                # Or passing parameters directly
+                client = AzureOpenAIResponsesClient(
+                    endpoint="https://your-endpoint.openai.azure.com", deployment_name="gpt-4o", api_key="your-key"
+                )
+
+                # Or loading from a .env file
+                client = AzureOpenAIResponsesClient(env_file_path="path/to/.env")
+
+                # Using a Foundry project endpoint
+                from azure.identity import DefaultAzureCredential
+
+                client = AzureOpenAIResponsesClient(
+                    project_endpoint="https://your-project.services.ai.azure.com",
+                    deployment_name="gpt-4o",
+                    credential=DefaultAzureCredential(),
+                )
+
+                # Or using an existing AIProjectClient
+                from azure.ai.projects.aio import AIProjectClient
+
+                project_client = AIProjectClient(
+                    endpoint="https://your-project.services.ai.azure.com",
+                    credential=DefaultAzureCredential(),
+                )
+                client = AzureOpenAIResponsesClient(
+                    project_client=project_client,
+                    deployment_name="gpt-4o",
+                )
+
+                # Using custom ChatOptions with type safety:
+                from typing import TypedDict
+                from agent_framework.azure import AzureOpenAIResponsesOptions
+
+
+                class MyOptions(AzureOpenAIResponsesOptions, total=False):
+                    my_custom_option: str
+
+
+                client: AzureOpenAIResponsesClient[MyOptions] = AzureOpenAIResponsesClient()
+                response = await client.get_response("Hello", options={"my_custom_option": "value"})
+        """
+        if (model_id := kwargs.pop("model_id", None)) and not deployment_name:
+            deployment_name = str(model_id)
+
+        # Project client path: create OpenAI client from an Azure AI Foundry project
+        if async_client is None and (project_client is not None or project_endpoint is not None):
+            async_client = self._create_client_from_project(
+                project_client=project_client,
+                project_endpoint=project_endpoint,
+                credential=credential,
+                allow_preview=allow_preview,
+            )
+
+        azure_openai_settings = load_settings(
+            AzureOpenAISettings,
+            env_prefix="AZURE_OPENAI_",
+            api_key=api_key,
+            base_url=base_url,
+            endpoint=endpoint,
+            responses_deployment_name=deployment_name,
+            api_version=api_version,
+            env_file_path=env_file_path,
+            env_file_encoding=env_file_encoding,
+            token_endpoint=token_endpoint,
+        )
+        _apply_azure_defaults(azure_openai_settings, default_api_version="preview")
+        # TODO(peterychang): This is a temporary hack to ensure that the base_url is set correctly
+        # while this feature is in preview.
+        # But we should only do this if we're on azure. Private deployments may not need this.
+        endpoint_value = azure_openai_settings.get("endpoint")
+        if (
+            not azure_openai_settings.get("base_url")
+            and endpoint_value
+            and (hostname := urlparse(str(endpoint_value)).hostname)
+            and hostname.endswith(".openai.azure.com")
+        ):
+            azure_openai_settings["base_url"] = urljoin(str(endpoint_value), "/openai/v1/")
+
+        responses_deployment_name = azure_openai_settings.get("responses_deployment_name")
+        if not responses_deployment_name:
+            raise ValueError(
+                "Azure OpenAI deployment name is required. Set via 'deployment_name' parameter "
+                "or 'AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME' environment variable."
+            )
+
+        api_key_secret = azure_openai_settings.get("api_key")
+
+        super().__init__(
+            deployment_name=responses_deployment_name,
+            endpoint=azure_openai_settings.get("endpoint"),
+            base_url=azure_openai_settings.get("base_url"),
+            api_version=azure_openai_settings.get("api_version") or "",
+            api_key=api_key_secret.get_secret_value() if api_key_secret else None,
+            token_endpoint=azure_openai_settings.get("token_endpoint"),
+            credential=credential,
+            default_headers=default_headers,
+            client=async_client,
+            instruction_role=instruction_role,
+            middleware=middleware,
+            function_invocation_configuration=function_invocation_configuration,
+        )
+
+    @staticmethod
+    def _create_client_from_project(
+        *,
+        project_client: AIProjectClient | None,
+        project_endpoint: str | None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None,
+        allow_preview: bool | None = None,
+    ) -> AsyncOpenAI:
+        """Create an AsyncOpenAI client from an Azure AI Foundry project."""
+        if project_client is not None:
+            return project_client.get_openai_client()
+
+        if not project_endpoint:
+            raise ValueError("Azure AI project endpoint is required when project_client is not provided.")
+        if not credential:
+            raise ValueError("Azure credential is required when using project_endpoint without a project_client.")
+        project_client_kwargs: dict[str, Any] = {
+            "endpoint": project_endpoint,
+            "credential": credential,  # type: ignore[arg-type]
+            "user_agent": AGENT_FRAMEWORK_USER_AGENT,
+        }
+        if allow_preview is not None:
+            project_client_kwargs["allow_preview"] = allow_preview
+        project_client = AIProjectClient(**project_client_kwargs)
+        return project_client.get_openai_client()
+
+    @override
+    def _check_model_presence(self, options: dict[str, Any]) -> None:
+        if not options.get("model"):
+            if not self.model_id:
+                raise ValueError("deployment_name must be a non-empty string")
+            options["model"] = self.model_id
@@ -0,0 +1,223 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from __future__ import annotations
+
+import logging
+import sys
+from collections.abc import Mapping
+from copy import copy
+from typing import Any, ClassVar, Final
+
+from openai import AsyncOpenAI
+from openai.lib.azure import AsyncAzureOpenAI
+
+from .._settings import SecretString
+from .._telemetry import APP_INFO, prepend_agent_framework_to_user_agent
+from ..openai._shared import OpenAIBase
+from ._entra_id_authentication import AzureCredentialTypes, AzureTokenProvider, resolve_credential_to_token_provider
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+if sys.version_info >= (3, 11):
+    from typing import TypedDict  # type: ignore # pragma: no cover
+else:
+    from typing_extensions import TypedDict  # type: ignore # pragma: no cover
+
+
+DEFAULT_AZURE_API_VERSION: Final[str] = "2024-10-21"
+DEFAULT_AZURE_TOKEN_ENDPOINT: Final[str] = "https://cognitiveservices.azure.com/.default"  # noqa: S105
+
+
+class AzureOpenAISettings(TypedDict, total=False):
+    """AzureOpenAI model settings.
+
+    Settings are resolved in this order: explicit keyword arguments, values from an
+    explicitly provided .env file, then environment variables with the prefix
+    'AZURE_OPENAI_'. If settings are missing after resolution, validation will fail.
+
+    Keyword Args:
+        endpoint: The endpoint of the Azure deployment. This value
+            can be found in the Keys & Endpoint section when examining
+            your resource from the Azure portal, the endpoint should end in openai.azure.com.
+            If both base_url and endpoint are supplied, base_url will be used.
+            Can be set via environment variable AZURE_OPENAI_ENDPOINT.
+        chat_deployment_name: The name of the Azure Chat deployment. This value
+            will correspond to the custom name you chose for your deployment
+            when you deployed a model. This value can be found under
+            Resource Management > Deployments in the Azure portal or, alternatively,
+            under Management > Deployments in Azure AI Foundry.
+            Can be set via environment variable AZURE_OPENAI_CHAT_DEPLOYMENT_NAME.
+        responses_deployment_name: The name of the Azure Responses deployment. This value
+            will correspond to the custom name you chose for your deployment
+            when you deployed a model. This value can be found under
+            Resource Management > Deployments in the Azure portal or, alternatively,
+            under Management > Deployments in Azure AI Foundry.
+            Can be set via environment variable AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME.
+        embedding_deployment_name: The name of the Azure Embedding deployment.
+            Can be set via environment variable AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME.
+        api_key: The API key for the Azure deployment. This value can be
+            found in the Keys & Endpoint section when examining your resource in
+            the Azure portal. You can use either KEY1 or KEY2.
+            Can be set via environment variable AZURE_OPENAI_API_KEY.
+        api_version: The API version to use. The default value is `DEFAULT_AZURE_API_VERSION`.
+            Can be set via environment variable AZURE_OPENAI_API_VERSION.
+        base_url: The url of the Azure deployment. This value
+            can be found in the Keys & Endpoint section when examining
+            your resource from the Azure portal, the base_url consists of the endpoint,
+            followed by /openai/deployments/{deployment_name}/,
+            use endpoint if you only want to supply the endpoint.
+            Can be set via environment variable AZURE_OPENAI_BASE_URL.
+        token_endpoint: The token endpoint to use to retrieve the authentication token.
+            The default value is `DEFAULT_AZURE_TOKEN_ENDPOINT`.
+            Can be set via environment variable AZURE_OPENAI_TOKEN_ENDPOINT.
+
+    Examples:
+        .. code-block:: python
+
+            from agent_framework.azure import AzureOpenAISettings
+
+            # Using environment variables
+            # Set AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com
+            # Set AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4
+            # Set AZURE_OPENAI_API_KEY=your-key
+            settings = load_settings(AzureOpenAISettings, env_prefix="AZURE_OPENAI_")
+
+            # Or passing parameters directly
+            settings = load_settings(
+                AzureOpenAISettings,
+                env_prefix="AZURE_OPENAI_",
+                endpoint="https://your-endpoint.openai.azure.com",
+                chat_deployment_name="gpt-4",
+                api_key="your-key",
+            )
+
+            # Or loading from a .env file
+            settings = load_settings(AzureOpenAISettings, env_prefix="AZURE_OPENAI_", env_file_path="path/to/.env")
+    """
+
+    chat_deployment_name: str | None
+    responses_deployment_name: str | None
+    embedding_deployment_name: str | None
+    endpoint: str | None
+    base_url: str | None
+    api_key: SecretString | None
+    api_version: str | None
+    token_endpoint: str | None
+
+
+def _apply_azure_defaults(
+    settings: AzureOpenAISettings,
+    default_api_version: str = DEFAULT_AZURE_API_VERSION,
+    default_token_endpoint: str = DEFAULT_AZURE_TOKEN_ENDPOINT,
+) -> None:
+    """Apply default values for api_version and token_endpoint after loading settings.
+
+    Args:
+        settings: The loaded Azure OpenAI settings dict.
+        default_api_version: The default API version to use if not set.
+        default_token_endpoint: The default token endpoint to use if not set.
+    """
+    if not settings.get("api_version"):
+        settings["api_version"] = default_api_version
+    if not settings.get("token_endpoint"):
+        settings["token_endpoint"] = default_token_endpoint
+
+
+_AZURE_DEFAULTS_APPLIER = _apply_azure_defaults
+
+
+class AzureOpenAIConfigMixin(OpenAIBase):
+    """Internal class for configuring a connection to an Azure OpenAI service."""
+
+    OTEL_PROVIDER_NAME: ClassVar[str] = "azure.ai.openai"
+    # Note: INJECTABLE = {"client"} is inherited from OpenAIBase
+
+    def __init__(
+        self,
+        deployment_name: str,
+        endpoint: str | None = None,
+        base_url: str | None = None,
+        api_version: str = DEFAULT_AZURE_API_VERSION,
+        api_key: str | None = None,
+        token_endpoint: str | None = None,
+        credential: AzureCredentialTypes | AzureTokenProvider | None = None,
+        default_headers: Mapping[str, str] | None = None,
+        client: AsyncOpenAI | None = None,
+        instruction_role: str | None = None,
+        **kwargs: Any,
+    ) -> None:
+        """Internal class for configuring a connection to an Azure OpenAI service.
+
+        The `validate_call` decorator is used with a configuration that allows arbitrary types.
+        This is necessary for types like `str` and `OpenAIModelTypes`.
+
+        Args:
+            deployment_name: Name of the deployment.
+            endpoint: The specific endpoint URL for the deployment.
+            base_url: The base URL for Azure services.
+            api_version: Azure API version. Defaults to the defined DEFAULT_AZURE_API_VERSION.
+            api_key: API key for Azure services.
+            token_endpoint: Azure AD token scope used to obtain a bearer token from a credential.
+            credential: Azure credential or token provider for authentication. Accepts a
+                ``TokenCredential``, ``AsyncTokenCredential``, or a callable that returns a
+                bearer token string (sync or async).
+            default_headers: Default headers for HTTP requests.
+            client: An existing client to use.
+            instruction_role: The role to use for 'instruction' messages, for example, summarization
+                prompts could use `developer` or `system`.
+            kwargs: Additional keyword arguments.
+
+        """
+        # Merge APP_INFO into the headers if it exists
+        merged_headers = dict(copy(default_headers)) if default_headers else {}
+        if APP_INFO:
+            merged_headers.update(APP_INFO)
+            merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
+        if not client:
+            # Resolve credential to a token provider if needed
+            ad_token_provider = None
+            if not api_key and credential:
+                ad_token_provider = resolve_credential_to_token_provider(credential, token_endpoint)
+
+            if not api_key and not ad_token_provider:
+                raise ValueError("Please provide either api_key, credential, or a client.")
+
+            if not endpoint and not base_url:
+                raise ValueError("Please provide an endpoint or a base_url")
+
+            args: dict[str, Any] = {
+                "default_headers": merged_headers,
+            }
+            if api_version:
+                args["api_version"] = api_version
+            if ad_token_provider:
+                args["azure_ad_token_provider"] = ad_token_provider
+            if api_key:
+                args["api_key"] = api_key
+            if base_url:
+                args["base_url"] = str(base_url)
+            if endpoint and not base_url:
+                args["azure_endpoint"] = str(endpoint)
+            if deployment_name:
+                args["azure_deployment"] = deployment_name
+            if "websocket_base_url" in kwargs:
+                args["websocket_base_url"] = kwargs.pop("websocket_base_url")
+
+            client = AsyncAzureOpenAI(**args)
+
+        # Store configuration as instance attributes for serialization
+        self.endpoint = str(endpoint)
+        self.base_url = str(base_url)
+        self.api_version = api_version
+        self.deployment_name = deployment_name
+        self.instruction_role = instruction_role
+        # Store default_headers but filter out USER_AGENT_KEY for serialization
+        if default_headers:
+            from .._telemetry import USER_AGENT_KEY
+
+            def_headers = {k: v for k, v in default_headers.items() if k != USER_AGENT_KEY}
+        else:
+            def_headers = None
+        self.default_headers = def_headers
+
+        super().__init__(model_id=deployment_name, client=client, **kwargs)
@@ -1,39 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-"""Foundry integration namespace for optional Agent Framework connectors.
-
-This module lazily re-exports objects from cloud Foundry and Foundry Local connector packages.
-"""
-
-import importlib
-from typing import Any
-
-_IMPORTS: dict[str, tuple[str, str]] = {
-    "FoundryAgent": ("agent_framework_foundry", "agent-framework-foundry"),
-    "FoundryChatClient": ("agent_framework_foundry", "agent-framework-foundry"),
-    "FoundryChatOptions": ("agent_framework_foundry", "agent-framework-foundry"),
-    "FoundryMemoryProvider": ("agent_framework_foundry", "agent-framework-foundry"),
-    "FoundryLocalChatOptions": ("agent_framework_foundry_local", "agent-framework-foundry-local"),
-    "FoundryLocalClient": ("agent_framework_foundry_local", "agent-framework-foundry-local"),
-    "FoundryLocalSettings": ("agent_framework_foundry_local", "agent-framework-foundry-local"),
-    "RawFoundryAgent": ("agent_framework_foundry", "agent-framework-foundry"),
-    "RawFoundryAgentChatClient": ("agent_framework_foundry", "agent-framework-foundry"),
-    "RawFoundryChatClient": ("agent_framework_foundry", "agent-framework-foundry"),
-}
-
-
-def __getattr__(name: str) -> Any:
-    if name in _IMPORTS:
-        import_path, package_name = _IMPORTS[name]
-        try:
-            return getattr(importlib.import_module(import_path), name)
-        except ModuleNotFoundError as exc:
-            raise ModuleNotFoundError(
-                f"The package {package_name} is required to use `{name}`. "
-                f"Please use `pip install {package_name}`, or update your requirements.txt or pyproject.toml file."
-            ) from exc
-    raise AttributeError(f"Module `foundry` has no attribute {name}.")
-
-
-def __dir__() -> list[str]:
-    return list(_IMPORTS.keys())
@@ -1,32 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-# Type stubs for the agent_framework.foundry lazy-loading namespace.
-# Install the relevant packages for full type support.
-
-from agent_framework_foundry import (
-    FoundryAgent,
-    FoundryChatClient,
-    FoundryChatOptions,
-    FoundryMemoryProvider,
-    RawFoundryAgent,
-    RawFoundryAgentChatClient,
-    RawFoundryChatClient,
-)
-from agent_framework_foundry_local import (
-    FoundryLocalChatOptions,
-    FoundryLocalClient,
-    FoundryLocalSettings,
-)
-
-__all__ = [
-    "FoundryAgent",
-    "FoundryChatClient",
-    "FoundryChatOptions",
-    "FoundryLocalChatOptions",
-    "FoundryLocalClient",
-    "FoundryLocalSettings",
-    "FoundryMemoryProvider",
-    "RawFoundryAgent",
-    "RawFoundryAgentChatClient",
-    "RawFoundryChatClient",
-]
@@ -1,55 +1,48 @@
 # Copyright (c) Microsoft. All rights reserved.

-"""OpenAI namespace for Agent Framework clients.
+"""OpenAI namespace for built-in Agent Framework clients.

-This module lazily re-exports objects from the ``agent-framework-openai`` package.
-Install it with: ``pip install agent-framework-openai``
+This module re-exports objects from the core OpenAI implementation modules in
+``agent_framework.openai``.

 Supported classes include:
- OpenAIChatClient (Responses API)
- OpenAIChatCompletionClient (Chat Completions API)
- OpenAIEmbeddingClient
- OpenAIAssistantsClient (deprecated)
+- OpenAIChatClient
+- OpenAIResponsesClient
+- OpenAIAssistantsClient
+- OpenAIAssistantProvider
 """

-import importlib
-from typing import Any
+from ._assistant_provider import OpenAIAssistantProvider
+from ._assistants_client import (
+    AssistantToolResources,
+    OpenAIAssistantsClient,
+    OpenAIAssistantsOptions,
+)
+from ._chat_client import OpenAIChatClient, OpenAIChatOptions
+from ._embedding_client import OpenAIEmbeddingClient, OpenAIEmbeddingOptions
+from ._exceptions import ContentFilterResultSeverity, OpenAIContentFilterException
+from ._responses_client import (
+    OpenAIContinuationToken,
+    OpenAIResponsesClient,
+    OpenAIResponsesOptions,
+    RawOpenAIResponsesClient,
+)
+from ._shared import OpenAISettings

-_IMPORTS: dict[str, tuple[str, str]] = {
-    "OpenAIChatClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIChatOptions": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIContinuationToken": ("agent_framework_openai", "agent-framework-openai"),
-    "RawOpenAIChatClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIChatCompletionClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIChatCompletionOptions": ("agent_framework_openai", "agent-framework-openai"),
-    "RawOpenAIChatCompletionClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIEmbeddingClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIEmbeddingOptions": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAISettings": ("agent_framework_openai", "agent-framework-openai"),
-    "ContentFilterResultSeverity": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIContentFilterException": ("agent_framework_openai", "agent-framework-openai"),
-    "AssistantToolResources": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIAssistantProvider": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIAssistantsClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIAssistantsOptions": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIResponsesClient": ("agent_framework_openai", "agent-framework-openai"),
-    "OpenAIResponsesOptions": ("agent_framework_openai", "agent-framework-openai"),
-    "RawOpenAIResponsesClient": ("agent_framework_openai", "agent-framework-openai"),
-}
-
-
-def __getattr__(name: str) -> Any:
-    if name in _IMPORTS:
-        import_path, package_name = _IMPORTS[name]
-        try:
-            return getattr(importlib.import_module(import_path), name)
-        except ModuleNotFoundError as exc:
-            raise ModuleNotFoundError(
-                f"The package {package_name} is required to use `{name}`. "
-                f"Please use `pip install {package_name}`, or update your requirements.txt or pyproject.toml file."
-            ) from exc
-    raise AttributeError(f"Module `openai` has no attribute {name}.")
-
-
-def __dir__() -> list[str]:
-    return list(_IMPORTS.keys())
+__all__ = [
+    "AssistantToolResources",
+    "ContentFilterResultSeverity",
+    "OpenAIAssistantProvider",
+    "OpenAIAssistantsClient",
+    "OpenAIAssistantsOptions",
+    "OpenAIChatClient",
+    "OpenAIChatOptions",
+    "OpenAIContentFilterException",
+    "OpenAIContinuationToken",
+    "OpenAIEmbeddingClient",
+    "OpenAIEmbeddingOptions",
+    "OpenAIResponsesClient",
+    "OpenAIResponsesOptions",
+    "OpenAISettings",
+    "RawOpenAIResponsesClient",
+]
@@ -1,48 +0,0 @@
-# Copyright (c) Microsoft. All rights reserved.
-
-# Type stubs for the agent_framework.openai lazy-loading namespace.
-# Install agent-framework-openai for full type support.
-
-from agent_framework_openai import (
-    AssistantToolResources,
-    ContentFilterResultSeverity,
-    OpenAIAssistantProvider,
-    OpenAIAssistantsClient,
-    OpenAIAssistantsOptions,
-    OpenAIChatClient,
-    OpenAIChatCompletionClient,
-    OpenAIChatCompletionOptions,
-    OpenAIChatOptions,
-    OpenAIContentFilterException,
-    OpenAIContinuationToken,
-    OpenAIEmbeddingClient,
-    OpenAIEmbeddingOptions,
-    OpenAIResponsesClient,
-    OpenAIResponsesOptions,
-    OpenAISettings,
-    RawOpenAIChatClient,
-    RawOpenAIChatCompletionClient,
-    RawOpenAIResponsesClient,
-)
-
-__all__ = [
-    "AssistantToolResources",
-    "ContentFilterResultSeverity",
-    "OpenAIAssistantProvider",
-    "OpenAIAssistantsClient",
-    "OpenAIAssistantsOptions",
-    "OpenAIChatClient",
-    "OpenAIChatCompletionClient",
-    "OpenAIChatCompletionOptions",
-    "OpenAIChatOptions",
-    "OpenAIContentFilterException",
-    "OpenAIContinuationToken",
-    "OpenAIEmbeddingClient",
-    "OpenAIEmbeddingOptions",
-    "OpenAIResponsesClient",
-    "OpenAIResponsesOptions",
-    "OpenAISettings",
-    "RawOpenAIChatClient",
-    "RawOpenAIChatCompletionClient",
-    "RawOpenAIResponsesClient",
-]
@@ -6,15 +6,16 @@ import sys
 from collections.abc import Awaitable, Callable, Mapping, MutableMapping, Sequence
 from typing import TYPE_CHECKING, Any, Generic, cast

-from agent_framework._agents import Agent
-from agent_framework._middleware import MiddlewareTypes
-from agent_framework._sessions import BaseContextProvider
-from agent_framework._settings import SecretString, load_settings
-from agent_framework._tools import FunctionTool, ToolTypes, normalize_tools
 from openai import AsyncOpenAI
 from openai.types.beta.assistant import Assistant
 from pydantic import BaseModel

+from agent_framework._settings import SecretString, load_settings
+
+from .._agents import Agent
+from .._middleware import MiddlewareTypes
+from .._sessions import BaseContextProvider
+from .._tools import FunctionTool, ToolTypes, normalize_tools
 from ._assistants_client import OpenAIAssistantsClient
 from ._shared import OpenAISettings, from_assistant_tools, to_assistant_tools

@@ -539,7 +540,7 @@ class OpenAIAssistantProvider(Generic[OptionsCoT]):
        """
        # Create the chat client with the assistant
        client = OpenAIAssistantsClient(
-            model=assistant.model,
+            model_id=assistant.model,
            assistant_id=assistant.id,
            assistant_name=assistant.name,
            assistant_description=assistant.description,
@@ -15,27 +15,6 @@ from collections.abc import (
 )
 from typing import TYPE_CHECKING, Any, Generic, Literal, TypedDict, cast

-from agent_framework._clients import BaseChatClient
-from agent_framework._middleware import ChatMiddlewareLayer
-from agent_framework._settings import load_settings
-from agent_framework._tools import (
-    FunctionInvocationConfiguration,
-    FunctionInvocationLayer,
-    FunctionTool,
-    normalize_tools,
-)
-from agent_framework._types import (
-    Annotation,
-    ChatOptions,
-    ChatResponse,
-    ChatResponseUpdate,
-    Content,
-    Message,
-    ResponseStream,
-    TextSpanRegion,
-    UsageDetails,
-)
-from agent_framework.observability import ChatTelemetryLayer
 from openai import AsyncOpenAI
 from openai.types.beta.threads import (
    FileCitationAnnotation,
@@ -58,6 +37,27 @@ from openai.types.beta.threads.run_submit_tool_outputs_params import ToolOutput
 from openai.types.beta.threads.runs import RunStep
 from pydantic import BaseModel

+from .._clients import BaseChatClient
+from .._middleware import ChatMiddlewareLayer
+from .._settings import load_settings
+from .._tools import (
+    FunctionInvocationConfiguration,
+    FunctionInvocationLayer,
+    FunctionTool,
+    normalize_tools,
+)
+from .._types import (
+    Annotation,
+    ChatOptions,
+    ChatResponse,
+    ChatResponseUpdate,
+    Content,
+    Message,
+    ResponseStream,
+    TextSpanRegion,
+    UsageDetails,
+)
+from ..observability import ChatTelemetryLayer
 from ._shared import OpenAIConfigMixin, OpenAISettings

 if sys.version_info >= (3, 13):
@@ -76,7 +76,7 @@ else:
    from typing_extensions import Self, TypedDict  # type: ignore # pragma: no cover

 if TYPE_CHECKING:
-    from agent_framework._middleware import MiddlewareTypes
+    from .._middleware import MiddlewareTypes

 logger = logging.getLogger("agent_framework.openai")

@@ -123,7 +123,7 @@ class OpenAIAssistantsOptions(ChatOptions[ResponseModelT], Generic[ResponseModel

    Keys:
        # Inherited from ChatOptions:
-        model_id: Deprecated. The model to use for the assistant,
+        model_id: The model to use for the assistant,
            translates to ``model`` in OpenAI API.
        temperature: Sampling temperature between 0 and 2.
        top_p: Nucleus sampling parameter.
@@ -191,7 +191,7 @@ class OpenAIAssistantsOptions(ChatOptions[ResponseModelT], Generic[ResponseModel


 ASSISTANTS_OPTION_TRANSLATIONS: dict[str, str] = {
-    "model_id": "model",  # backward compat: accept model_id in options
+    "model_id": "model",
    "max_tokens": "max_completion_tokens",
    "allow_multiple_tool_calls": "parallel_tool_calls",
 }
@@ -277,7 +277,6 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
    def __init__(
        self,
        *,
-        model: str | None = None,
        model_id: str | None = None,
        assistant_id: str | None = None,
        assistant_name: str | None = None,
@@ -297,9 +296,8 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
        """Initialize an OpenAI Assistants client.

        Keyword Args:
-            model: OpenAI model name, see https://platform.openai.com/docs/models.
-                Can also be set via environment variable OPENAI_MODEL.
-            model_id: Deprecated alias for ``model``.
+            model_id: OpenAI model name, see https://platform.openai.com/docs/models.
+                Can also be set via environment variable OPENAI_CHAT_MODEL_ID.
            assistant_id: The ID of an OpenAI assistant to use.
                If not provided, a new assistant will be created (and deleted after the request).
            assistant_name: The name to use when creating new assistants.
@@ -330,11 +328,11 @@ class OpenAIAssistantsClient(  # type: ignore[misc]

                # Using environment variables
                # Set OPENAI_API_KEY=sk-...
-                # Set OPENAI_MODEL=gpt-4
+                # Set OPENAI_CHAT_MODEL_ID=gpt-4
                client = OpenAIAssistantsClient()

                # Or passing parameters directly
-                client = OpenAIAssistantsClient(model="gpt-4", api_key="sk-...")
+                client = OpenAIAssistantsClient(model_id="gpt-4", api_key="sk-...")

                # Or loading from a .env file
                client = OpenAIAssistantsClient(env_file_path="path/to/.env")
@@ -348,21 +346,16 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
                    my_custom_option: str


-                client: OpenAIAssistantsClient[MyOptions] = OpenAIAssistantsClient(model="gpt-4")
+                client: OpenAIAssistantsClient[MyOptions] = OpenAIAssistantsClient(model_id="gpt-4")
                response = await client.get_response("Hello", options={"my_custom_option": "value"})
        """
-        if model_id is not None and model is None:
-            import warnings
-
-            warnings.warn("model_id is deprecated, use model instead", DeprecationWarning, stacklevel=2)
-            model = model_id
        openai_settings = load_settings(
            OpenAISettings,
            env_prefix="OPENAI_",
            api_key=api_key,
            base_url=base_url,
            org_id=org_id,
-            model=model,
+            chat_model_id=model_id,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
        )
@@ -373,14 +366,15 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
                "OpenAI API key is required. Set via 'api_key' parameter or 'OPENAI_API_KEY' environment variable."
            )

-        resolved_model = openai_settings.get("model")
-        if not resolved_model:
+        chat_model_id = openai_settings.get("chat_model_id")
+        if not chat_model_id:
            raise ValueError(
-                "OpenAI model is required. Set via 'model' parameter or 'OPENAI_MODEL' environment variable."
+                "OpenAI model ID is required. "
+                "Set via 'model_id' parameter or 'OPENAI_CHAT_MODEL_ID' environment variable."
            )

        super().__init__(
-            model=resolved_model,
+            model_id=chat_model_id,
            api_key=self._get_api_key(api_key_value),
            org_id=openai_settings.get("org_id"),
            default_headers=default_headers,
@@ -471,12 +465,12 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
        """
        # If no assistant is provided, create a temporary assistant
        if self.assistant_id is None:
-            if not self.model:
-                raise ValueError("Parameter 'model' is required for assistant creation.")
+            if not self.model_id:
+                raise ValueError("Parameter 'model_id' is required for assistant creation.")

            client = await self._ensure_client()
            created_assistant = await client.beta.assistants.create(  # type: ignore[reportDeprecated]
-                model=self.model,
+                model=self.model_id,
                description=self.assistant_description,
                name=self.assistant_name,
            )
@@ -787,13 +781,13 @@ class OpenAIAssistantsClient(  # type: ignore[misc]
        options: Mapping[str, Any],
        **kwargs: Any,
    ) -> tuple[dict[str, Any], list[Content] | None]:
-        from agent_framework._types import validate_tool_mode
+        from .._types import validate_tool_mode

        run_options: dict[str, Any] = {**kwargs}

        # Extract options from the dict
        max_tokens = options.get("max_tokens")
-        model = options.get("model") or options.get("model_id")  # backward compat
+        model_id = options.get("model_id")
        top_p = options.get("top_p")
        temperature = options.get("temperature")
        allow_multiple_tool_calls = options.get("allow_multiple_tool_calls")
@@ -804,8 +798,8 @@ class OpenAIAssistantsClient(  # type: ignore[misc]

        if max_tokens is not None:
            run_options["max_completion_tokens"] = max_tokens
-        if model is not None:
-            run_options["model"] = model
+        if model_id is not None:
+            run_options["model"] = model_id
        if top_p is not None:
            run_options["top_p"] = top_p
        if temperature is not None:
@@ -13,39 +13,11 @@ from collections.abc import (
    MutableMapping,
    Sequence,
 )
-from copy import copy
 from datetime import datetime, timezone
 from itertools import chain
-from typing import Any, ClassVar, Generic, Literal, cast, overload
+from typing import Any, Generic, Literal, cast, overload

-from agent_framework._clients import BaseChatClient
-from agent_framework._docstrings import apply_layered_docstring
-from agent_framework._middleware import ChatAndFunctionMiddlewareTypes, ChatMiddlewareLayer
-from agent_framework._settings import SecretString
-from agent_framework._telemetry import APP_INFO, USER_AGENT_KEY, prepend_agent_framework_to_user_agent
-from agent_framework._tools import (
-    FunctionInvocationConfiguration,
-    FunctionInvocationLayer,
-    FunctionTool,
-    ToolTypes,
-    normalize_tools,
-)
-from agent_framework._types import (
-    ChatOptions,
-    ChatResponse,
-    ChatResponseUpdate,
-    Content,
-    FinishReason,
-    Message,
-    ResponseStream,
-    UsageDetails,
-)
-from agent_framework.exceptions import (
-    ChatClientException,
-    ChatClientInvalidRequestException,
-)
-from agent_framework.observability import ChatTelemetryLayer
-from openai import AsyncAzureOpenAI, AsyncOpenAI, BadRequestError
+from openai import AsyncOpenAI, BadRequestError
 from openai.lib._parsing._completions import type_to_response_format_param
 from openai.types import CompletionUsage
 from openai.types.chat.chat_completion import ChatCompletion, Choice
@@ -57,13 +29,34 @@ from openai.types.chat.chat_completion_message_custom_tool_call import (
 from openai.types.chat.completion_create_params import WebSearchOptions
 from pydantic import BaseModel

-from ._exceptions import OpenAIContentFilterException
-from ._shared import (
-    DEFAULT_AZURE_OPENAI_CHAT_COMPLETION_API_VERSION,
-    get_api_key,
-    load_openai_service_settings,
-    maybe_append_azure_endpoint_guidance,
+from .._clients import BaseChatClient
+from .._docstrings import apply_layered_docstring
+from .._middleware import ChatAndFunctionMiddlewareTypes, ChatMiddlewareLayer
+from .._settings import load_settings
+from .._tools import (
+    FunctionInvocationConfiguration,
+    FunctionInvocationLayer,
+    FunctionTool,
+    ToolTypes,
+    normalize_tools,
 )
+from .._types import (
+    ChatOptions,
+    ChatResponse,
+    ChatResponseUpdate,
+    Content,
+    FinishReason,
+    Message,
+    ResponseStream,
+    UsageDetails,
+)
+from ..exceptions import (
+    ChatClientException,
+    ChatClientInvalidRequestException,
+)
+from ..observability import ChatTelemetryLayer
+from ._exceptions import OpenAIContentFilterException
+from ._shared import OpenAIBase, OpenAIConfigMixin, OpenAISettings

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
@@ -101,7 +94,7 @@ class Prediction(TypedDict, total=False):
    content: str | list[PredictionTextContent]


-class OpenAIChatCompletionOptions(ChatOptions[ResponseModelT], Generic[ResponseModelT], total=False):
+class OpenAIChatOptions(ChatOptions[ResponseModelT], Generic[ResponseModelT], total=False):
    """OpenAI-specific chat options dict.

    Extends ChatOptions with options specific to OpenAI's Chat Completions API.
@@ -140,24 +133,20 @@ class OpenAIChatCompletionOptions(ChatOptions[ResponseModelT], Generic[ResponseM
    prediction: Prediction


-OpenAIChatCompletionOptionsT = TypeVar(
-    "OpenAIChatCompletionOptionsT",
-    bound=TypedDict,  # type: ignore[valid-type]
-    default="OpenAIChatCompletionOptions",
-    covariant=True,
-)
+OpenAIChatOptionsT = TypeVar("OpenAIChatOptionsT", bound=TypedDict, default="OpenAIChatOptions", covariant=True)  # type: ignore[valid-type]

 OPTION_TRANSLATIONS: dict[str, str] = {
-    "model_id": "model",  # backward compat: accept model_id in options
+    "model_id": "model",
    "allow_multiple_tool_calls": "parallel_tool_calls",
    "max_tokens": "max_completion_tokens",
 }


 # region Base Client
-class RawOpenAIChatCompletionClient(  # type: ignore[misc]
-    BaseChatClient[OpenAIChatCompletionOptionsT],
-    Generic[OpenAIChatCompletionOptionsT],
+class RawOpenAIChatClient(  # type: ignore[misc]
+    OpenAIBase,
+    BaseChatClient[OpenAIChatOptionsT],
+    Generic[OpenAIChatOptionsT],
 ):
    """Raw OpenAI Chat completion class without middleware, telemetry, or function invocation.

@@ -171,178 +160,9 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
        2. **ChatMiddlewareLayer** - Applies chat middleware per model call and stays outside telemetry
        3. **ChatTelemetryLayer** - Must stay inside chat middleware for correct per-call telemetry

-        Use ``OpenAIChatCompletionClient`` instead for a fully-featured client with all layers applied.
+        Use ``OpenAIChatClient`` instead for a fully-featured client with all layers applied.
    """

-    INJECTABLE: ClassVar[set[str]] = {"client"}
-
-    @overload
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None: ...
-
-    @overload
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None: ...
-
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        model_id: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str | None = None,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        **kwargs: Any,
-    ) -> None:
-        """Initialize a raw OpenAI Chat completion client.
-
-        Keyword Args:
-            model: OpenAI model name.
-            model_id: Deprecated alias for ``model``.
-            api_key: OpenAI API key, SecretString, or callable returning a key.
-            org_id: OpenAI organization ID.
-            base_url: Custom API base URL.
-            azure_endpoint: Azure OpenAI endpoint. When provided, the client uses
-                ``AsyncAzureOpenAI`` instead of ``AsyncOpenAI``. The value should be the
-                resource endpoint and should not end with ``/openai/v1``. For Azure OpenAI
-                key auth, either pass the resource endpoint without that suffix to
-                ``azure_endpoint`` or pass the full ``.../openai/v1`` URL to ``base_url``.
-                Can also be set via ``AZURE_OPENAI_ENDPOINT`` when no ``OPENAI_BASE_URL``
-                is configured.
-            api_version: Azure OpenAI API version. Can also be set via
-                ``AZURE_OPENAI_API_VERSION``.
-            default_headers: Additional HTTP headers.
-            async_client: Pre-configured AsyncOpenAI client (skips client creation).
-            instruction_role: Role for instruction messages (e.g. ``"system"``).
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-            kwargs: Additional keyword arguments forwarded to ``BaseChatClient``.
-        """
-        if model_id is not None and model is None:
-            import warnings
-
-            warnings.warn("model_id is deprecated, use model instead", DeprecationWarning, stacklevel=2)
-            model = model_id
-
-        openai_settings: dict[str, Any] = {}
-        use_azure_client = isinstance(async_client, AsyncAzureOpenAI)
-        if not async_client:
-            resolved_settings, use_azure_client = load_openai_service_settings(
-                model=model,
-                api_key=api_key,
-                org_id=org_id,
-                base_url=base_url,
-                azure_endpoint=azure_endpoint,
-                api_version=api_version,
-                env_file_path=env_file_path,
-                env_file_encoding=env_file_encoding,
-                azure_model_env_vars=("AZURE_OPENAI_DEPLOYMENT_NAME",),
-                default_azure_api_version=DEFAULT_AZURE_OPENAI_CHAT_COMPLETION_API_VERSION,
-            )
-            openai_settings = dict(resolved_settings)
-
-            api_key_value = openai_settings.get("api_key")
-            if not api_key_value:
-                raise ValueError(
-                    "OpenAI API key is required. Set via the 'api_key' parameter or the "
-                    "'OPENAI_API_KEY' or 'AZURE_OPENAI_API_KEY' environment variables."
-                )
-            resolved_model = openai_settings.get("model") or model
-            if not resolved_model:
-                raise ValueError(
-                    "OpenAI model is required. Set via the 'model' parameter or the "
-                    "'OPENAI_MODEL' or 'AZURE_OPENAI_DEPLOYMENT_NAME' environment variables."
-                )
-            model = resolved_model
-
-            resolved_api_key = get_api_key(api_key_value)
-
-            # Merge APP_INFO into the headers
-            merged_headers = dict(copy(default_headers)) if default_headers else {}
-            if APP_INFO:
-                merged_headers.update(APP_INFO)
-                merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-            client_args: dict[str, Any] = {"api_key": resolved_api_key, "default_headers": merged_headers}
-            if use_azure_client:
-                client_args.pop("api_key")
-                if resolved_api_version := openai_settings.get("api_version"):
-                    client_args["api_version"] = resolved_api_version
-                if resolved_base_url := openai_settings.get("base_url"):
-                    client_args["base_url"] = resolved_base_url
-                elif resolved_azure_endpoint := openai_settings.get("azure_endpoint"):
-                    client_args["azure_endpoint"] = resolved_azure_endpoint
-                if callable(resolved_api_key):
-                    client_args["azure_ad_token_provider"] = resolved_api_key
-                else:
-                    client_args["api_key"] = resolved_api_key
-                client_args["azure_deployment"] = resolved_model
-                async_client = AsyncAzureOpenAI(**client_args)
-            else:
-                if resolved_org_id := openai_settings.get("org_id"):
-                    client_args["organization"] = resolved_org_id
-                if resolved_base_url := openai_settings.get("base_url"):
-                    client_args["base_url"] = resolved_base_url
-
-                async_client = AsyncOpenAI(**client_args)
-
-        self.client = async_client
-        self.model: str | None = model.strip() if model else None
-
-        # Store configuration for serialization
-        resolved_base_url = openai_settings.get("base_url") or base_url
-        resolved_azure_endpoint = openai_settings.get("azure_endpoint") or azure_endpoint
-        resolved_api_version = openai_settings.get("api_version") or api_version
-        self.org_id = openai_settings.get("org_id") or org_id
-        self.base_url = str(resolved_base_url) if resolved_base_url else None
-        self.azure_endpoint = str(resolved_azure_endpoint) if resolved_azure_endpoint else None
-        self.api_version = str(resolved_api_version) if use_azure_client and resolved_api_version else None
-        if default_headers:
-            self.default_headers: dict[str, Any] | None = {
-                k: v for k, v in default_headers.items() if k != USER_AGENT_KEY
-            }
-        else:
-            self.default_headers = None
-
-        if instruction_role is not None:
-            self.instruction_role = instruction_role
-
-        if use_azure_client:
-            self.OTEL_PROVIDER_NAME = "azure.ai.openai"  # type: ignore[misc]
-
-        super().__init__(**kwargs)
-
    # region Hosted Tool Factory Methods

    @staticmethod
@@ -368,13 +188,13 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatCompletionClient
+                from agent_framework.openai import OpenAIChatClient

                # Basic web search
-                tool = OpenAIChatCompletionClient.get_web_search_tool()
+                tool = OpenAIChatClient.get_web_search_tool()

                # With location context
-                tool = OpenAIChatCompletionClient.get_web_search_tool(
+                tool = OpenAIChatClient.get_web_search_tool(
                    web_search_options={
                        "user_location": {
                            "type": "approximate",
@@ -411,7 +231,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: Literal[False] = ...,
-        options: OpenAIChatCompletionOptionsT | ChatOptions[None] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[None] | None = None,
        **kwargs: Any,
    ) -> Awaitable[ChatResponse[Any]]: ...

@@ -421,7 +241,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: Literal[True],
-        options: OpenAIChatCompletionOptionsT | ChatOptions[Any] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[Any] | None = None,
        **kwargs: Any,
    ) -> ResponseStream[ChatResponseUpdate, ChatResponse[Any]]: ...

@@ -431,7 +251,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: bool = False,
-        options: OpenAIChatCompletionOptionsT | ChatOptions[Any] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[Any] | None = None,
        **kwargs: Any,
    ) -> Awaitable[ChatResponse[Any]] | ResponseStream[ChatResponseUpdate, ChatResponse[Any]]:
        """Get a response from the raw OpenAI chat client."""
@@ -463,7 +283,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
            options_dict["stream_options"] = {"include_usage": True}

            async def _stream() -> AsyncIterable[ChatResponseUpdate]:
-                client = self.client
+                client = await self._ensure_client()
                try:
                    async for chunk in await client.chat.completions.create(stream=True, **options_dict):
                        if len(chunk.choices) == 0 and chunk.usage is None:
@@ -476,18 +296,12 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
                            inner_exception=ex,
                        ) from ex
                    raise ChatClientException(
-                        maybe_append_azure_endpoint_guidance(
-                            f"{type(self)} service failed to complete the prompt: {ex}",
-                            azure_endpoint=self.azure_endpoint,
-                        ),
+                        f"{type(self)} service failed to complete the prompt: {ex}",
                        inner_exception=ex,
                    ) from ex
                except Exception as ex:
                    raise ChatClientException(
-                        maybe_append_azure_endpoint_guidance(
-                            f"{type(self)} service failed to complete the prompt: {ex}",
-                            azure_endpoint=self.azure_endpoint,
-                        ),
+                        f"{type(self)} service failed to complete the prompt: {ex}",
                        inner_exception=ex,
                    ) from ex

@@ -495,7 +309,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]

        # Non-streaming mode
        async def _get_response() -> ChatResponse:
-            client = self.client
+            client = await self._ensure_client()
            try:
                return self._parse_response_from_openai(
                    await client.chat.completions.create(stream=False, **options_dict), options
@@ -507,18 +321,12 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
                        inner_exception=ex,
                    ) from ex
                raise ChatClientException(
-                    maybe_append_azure_endpoint_guidance(
-                        f"{type(self)} service failed to complete the prompt: {ex}",
-                        azure_endpoint=self.azure_endpoint,
-                    ),
+                    f"{type(self)} service failed to complete the prompt: {ex}",
                    inner_exception=ex,
                ) from ex
            except Exception as ex:
                raise ChatClientException(
-                    maybe_append_azure_endpoint_guidance(
-                        f"{type(self)} service failed to complete the prompt: {ex}",
-                        azure_endpoint=self.azure_endpoint,
-                    ),
+                    f"{type(self)} service failed to complete the prompt: {ex}",
                    inner_exception=ex,
                ) from ex

@@ -566,7 +374,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]

    def _prepare_options(self, messages: Sequence[Message], options: Mapping[str, Any]) -> dict[str, Any]:
        # Prepend instructions from options if they exist
-        from agent_framework._types import prepend_instructions_to_messages, validate_tool_mode
+        from .._types import prepend_instructions_to_messages, validate_tool_mode

        if instructions := options.get("instructions"):
            messages = prepend_instructions_to_messages(list(messages), instructions, role="system")
@@ -589,9 +397,9 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]

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

        # tools
        tools = options.get("tools")
@@ -644,7 +452,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
            created_at=datetime.fromtimestamp(response.created, tz=timezone.utc).strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
            usage_details=self._parse_usage_from_openai(response.usage) if response.usage else None,
            messages=messages,
-            model=response.model,
+            model_id=response.model,
            additional_properties=response_metadata,
            finish_reason=finish_reason,
            response_format=options.get("response_format"),
@@ -680,7 +488,7 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
            created_at=datetime.fromtimestamp(chunk.created, tz=timezone.utc).strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
            contents=contents,
            role="assistant",
-            model=chunk.model,
+            model_id=chunk.model,
            additional_properties=chunk_metadata,
            finish_reason=finish_reason,
            raw_representation=chunk,
@@ -966,17 +774,16 @@ class RawOpenAIChatCompletionClient(  # type: ignore[misc]
 # region Public client


-class OpenAIChatCompletionClient(  # type: ignore[misc]
-    FunctionInvocationLayer[OpenAIChatCompletionOptionsT],
-    ChatMiddlewareLayer[OpenAIChatCompletionOptionsT],
-    ChatTelemetryLayer[OpenAIChatCompletionOptionsT],
-    RawOpenAIChatCompletionClient[OpenAIChatCompletionOptionsT],
-    Generic[OpenAIChatCompletionOptionsT],
+class OpenAIChatClient(  # type: ignore[misc]
+    OpenAIConfigMixin,
+    FunctionInvocationLayer[OpenAIChatOptionsT],
+    ChatMiddlewareLayer[OpenAIChatOptionsT],
+    ChatTelemetryLayer[OpenAIChatOptionsT],
+    RawOpenAIChatClient[OpenAIChatOptionsT],
+    Generic[OpenAIChatOptionsT],
 ):
    """OpenAI Chat completion class with middleware, telemetry, and function invocation support."""

-    OTEL_PROVIDER_NAME: ClassVar[str] = "openai"  # type: ignore[reportIncompatibleVariableOverride, misc]
-
    @overload
    def get_response(
        self,
@@ -996,7 +803,7 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: Literal[False] = ...,
-        options: OpenAIChatCompletionOptionsT | ChatOptions[None] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[None] | None = None,
        function_invocation_kwargs: Mapping[str, Any] | None = None,
        client_kwargs: Mapping[str, Any] | None = None,
        middleware: Sequence[ChatAndFunctionMiddlewareTypes] | None = None,
@@ -1009,7 +816,7 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: Literal[True],
-        options: OpenAIChatCompletionOptionsT | ChatOptions[Any] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[Any] | None = None,
        function_invocation_kwargs: Mapping[str, Any] | None = None,
        client_kwargs: Mapping[str, Any] | None = None,
        middleware: Sequence[ChatAndFunctionMiddlewareTypes] | None = None,
@@ -1022,7 +829,7 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
        messages: Sequence[Message],
        *,
        stream: bool = False,
-        options: OpenAIChatCompletionOptionsT | ChatOptions[Any] | None = None,
+        options: OpenAIChatOptionsT | ChatOptions[Any] | None = None,
        function_invocation_kwargs: Mapping[str, Any] | None = None,
        client_kwargs: Mapping[str, Any] | None = None,
        middleware: Sequence[ChatAndFunctionMiddlewareTypes] | None = None,
@@ -1048,15 +855,13 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
    def __init__(
        self,
        *,
-        model: str | None = None,
+        model_id: str | None = None,
        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
        org_id: str | None = None,
        default_headers: Mapping[str, str] | None = None,
        async_client: AsyncOpenAI | None = None,
        instruction_role: str | None = None,
        base_url: str | None = None,
-        azure_endpoint: str | None = None,
-        api_version: str | None = None,
        middleware: Sequence[ChatAndFunctionMiddlewareTypes] | None = None,
        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
        env_file_path: str | None = None,
@@ -1065,8 +870,8 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
        """Initialize an OpenAI Chat completion client.

        Keyword Args:
-            model: OpenAI model name, see https://platform.openai.com/docs/models.
-                Can also be set via environment variable OPENAI_MODEL.
+            model_id: OpenAI model name, see https://platform.openai.com/docs/models.
+                Can also be set via environment variable OPENAI_CHAT_MODEL_ID.
            api_key: The API key to use. If provided will override the env vars or .env file value.
                Can also be set via environment variable OPENAI_API_KEY.
            org_id: The org ID to use. If provided will override the env vars or .env file value.
@@ -1079,14 +884,6 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
            base_url: The base URL to use. If provided will override
                the standard value for an OpenAI connector, the env vars or .env file value.
                Can also be set via environment variable OPENAI_BASE_URL.
-            azure_endpoint: Azure OpenAI endpoint. When provided, the client uses
-                ``AsyncAzureOpenAI``. The value should be the Azure resource endpoint and
-                should not end with ``/openai/v1``. For Azure OpenAI key auth, either pass
-                the resource endpoint without that suffix to ``azure_endpoint`` or pass the
-                full ``.../openai/v1`` URL to ``base_url`` instead. Can also be discovered
-                from ``AZURE_OPENAI_ENDPOINT`` when no OpenAI base URL is configured.
-            api_version: Azure OpenAI API version. Can also be set via
-                ``AZURE_OPENAI_API_VERSION``.
            middleware: Optional sequence of ChatAndFunctionMiddlewareTypes to apply to requests.
            function_invocation_configuration: Optional configuration for function invocation support.
            env_file_path: Use the environment settings file as a fallback
@@ -1096,54 +893,76 @@ class OpenAIChatCompletionClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatCompletionClient
+                from agent_framework.openai import OpenAIChatClient

                # Using environment variables
                # Set OPENAI_API_KEY=sk-...
-                # Set OPENAI_MODEL=<model name>
-                client = OpenAIChatCompletionClient()
+                # Set OPENAI_CHAT_MODEL_ID=<model name>
+                client = OpenAIChatClient()

                # Or passing parameters directly
-                client = OpenAIChatCompletionClient(model="<model name>", api_key="sk-...")
+                client = OpenAIChatClient(model_id="<model name>", api_key="sk-...")

                # Or loading from a .env file
-                client = OpenAIChatCompletionClient(env_file_path="path/to/.env")
+                client = OpenAIChatClient(env_file_path="path/to/.env")

                # Using custom ChatOptions with type safety:
                from typing import TypedDict
-                from agent_framework.openai import OpenAIChatCompletionOptions
+                from agent_framework.openai import OpenAIChatOptions


-                class MyOptions(OpenAIChatCompletionOptions, total=False):
+                class MyOptions(OpenAIChatOptions, total=False):
                    my_custom_option: str


-                client: OpenAIChatCompletionClient[MyOptions] = OpenAIChatCompletionClient(model="<model name>")
+                client: OpenAIChatClient[MyOptions] = OpenAIChatClient(model_id="<model name>")
                response = await client.get_response("Hello", options={"my_custom_option": "value"})
        """
-        super().__init__(
-            model=model,
+        openai_settings = load_settings(
+            OpenAISettings,
+            env_prefix="OPENAI_",
            api_key=api_key,
-            org_id=org_id,
            base_url=base_url,
-            azure_endpoint=azure_endpoint,
-            api_version=api_version,
-            default_headers=default_headers,
-            async_client=async_client,
-            instruction_role=instruction_role,
+            org_id=org_id,
+            chat_model_id=model_id,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
+        )
+
+        api_key_value = openai_settings.get("api_key")
+        if not async_client and not api_key_value:
+            raise ValueError(
+                "OpenAI API key is required. Set via 'api_key' parameter or 'OPENAI_API_KEY' environment variable."
+            )
+
+        chat_model_id = openai_settings.get("chat_model_id")
+        if not chat_model_id:
+            raise ValueError(
+                "OpenAI model ID is required. "
+                "Set via 'model_id' parameter or 'OPENAI_CHAT_MODEL_ID' environment variable."
+            )
+
+        base_url_value = openai_settings.get("base_url")
+
+        super().__init__(
+            model_id=chat_model_id,
+            api_key=self._get_api_key(api_key_value),
+            base_url=base_url_value if base_url_value else None,
+            org_id=openai_settings.get("org_id"),
+            default_headers=default_headers,
+            client=async_client,
+            instruction_role=instruction_role,
            middleware=middleware,
            function_invocation_configuration=function_invocation_configuration,
        )


-def _apply_openai_chat_completion_client_docstrings() -> None:
-    """Align OpenAI chat completion client docstrings with the raw implementation."""
-    apply_layered_docstring(RawOpenAIChatCompletionClient.get_response, BaseChatClient.get_response)
+def _apply_openai_chat_client_docstrings() -> None:
+    """Align OpenAI chat-client docstrings with the raw implementation."""
+    apply_layered_docstring(RawOpenAIChatClient.get_response, BaseChatClient.get_response)
    apply_layered_docstring(
-        OpenAIChatCompletionClient.get_response,
-        RawOpenAIChatCompletionClient.get_response,
+        OpenAIChatClient.get_response,
+        RawOpenAIChatClient.get_response,
        extra_keyword_args={
            "middleware": """
                Optional per-call chat and function middleware.
@@ -1153,4 +972,4 @@ def _apply_openai_chat_completion_client_docstrings() -> None:
    )


-_apply_openai_chat_completion_client_docstrings()
+_apply_openai_chat_client_docstrings()
@@ -6,17 +6,15 @@ import base64
 import struct
 import sys
 from collections.abc import Awaitable, Callable, Mapping, Sequence
-from copy import copy
-from typing import Any, ClassVar, Generic, Literal, TypedDict
+from typing import Any, Generic, Literal, TypedDict

-from agent_framework._clients import BaseEmbeddingClient
-from agent_framework._settings import SecretString, load_settings
-from agent_framework._telemetry import APP_INFO, USER_AGENT_KEY, prepend_agent_framework_to_user_agent
-from agent_framework._types import Embedding, EmbeddingGenerationOptions, GeneratedEmbeddings, UsageDetails
-from agent_framework.observability import EmbeddingTelemetryLayer
 from openai import AsyncOpenAI

-from ._shared import OpenAISettings, get_api_key
+from .._clients import BaseEmbeddingClient
+from .._settings import load_settings
+from .._types import Embedding, EmbeddingGenerationOptions, GeneratedEmbeddings, UsageDetails
+from ..observability import EmbeddingTelemetryLayer
+from ._shared import OpenAIBase, OpenAIConfigMixin, OpenAISettings

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
@@ -35,7 +33,7 @@ class OpenAIEmbeddingOptions(EmbeddingGenerationOptions, total=False):
            from agent_framework.openai import OpenAIEmbeddingOptions

            options: OpenAIEmbeddingOptions = {
-                "model": "text-embedding-3-small",
+                "model_id": "text-embedding-3-small",
                "dimensions": 1536,
                "encoding_format": "float",
            }
@@ -54,103 +52,12 @@ OpenAIEmbeddingOptionsT = TypeVar(


 class RawOpenAIEmbeddingClient(
+    OpenAIBase,
    BaseEmbeddingClient[str, list[float], OpenAIEmbeddingOptionsT],
    Generic[OpenAIEmbeddingOptionsT],
 ):
    """Raw OpenAI embedding client without telemetry."""

-    INJECTABLE: ClassVar[set[str]] = {"client"}
-
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        model_id: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        **kwargs: Any,
-    ) -> None:
-        """Initialize a raw OpenAI embedding client.
-
-        Keyword Args:
-            model: OpenAI embedding model name.
-            model_id: Deprecated alias for ``model``.
-            api_key: OpenAI API key, SecretString, or callable returning a key.
-            org_id: OpenAI organization ID.
-            base_url: Custom API base URL.
-            default_headers: Additional HTTP headers.
-            async_client: Pre-configured AsyncOpenAI client (skips client creation).
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-            kwargs: Additional keyword arguments forwarded to ``BaseEmbeddingClient``.
-        """
-        if model_id is not None and model is None:
-            import warnings
-
-            warnings.warn("model_id is deprecated, use model instead", DeprecationWarning, stacklevel=2)
-            model = model_id
-
-        if not async_client:
-            openai_settings = load_settings(
-                OpenAISettings,
-                env_prefix="OPENAI_",
-                api_key=api_key,
-                org_id=org_id,
-                base_url=base_url,
-                embedding_model=model,
-                env_file_path=env_file_path,
-                env_file_encoding=env_file_encoding,
-            )
-
-            api_key_value = openai_settings.get("api_key")
-            resolved_model = openai_settings.get("embedding_model") or model
-
-            # Only create a client when we have enough configuration.
-            # Subclasses that manage their own client pass no args here
-            if api_key_value:
-                if not resolved_model:
-                    raise ValueError(
-                        "OpenAI embedding model is required. "
-                        "Set via 'model' parameter or 'OPENAI_EMBEDDING_MODEL' environment variable."
-                    )
-                model = resolved_model
-
-                resolved_api_key = get_api_key(api_key_value)
-
-                # Merge APP_INFO into the headers
-                merged_headers = dict(copy(default_headers)) if default_headers else {}
-                if APP_INFO:
-                    merged_headers.update(APP_INFO)
-                    merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-                client_args: dict[str, Any] = {"api_key": resolved_api_key, "default_headers": merged_headers}
-                if resolved_org_id := openai_settings.get("org_id"):
-                    client_args["organization"] = resolved_org_id
-                if resolved_base_url := openai_settings.get("base_url"):
-                    client_args["base_url"] = resolved_base_url
-
-                async_client = AsyncOpenAI(**client_args)
-
-        self.client = async_client
-        self.model: str | None = model.strip() if model else None
-
-        # Store configuration for serialization
-        self.org_id = org_id
-        self.base_url = str(base_url) if base_url else None
-        if default_headers:
-            self.default_headers: dict[str, Any] | None = {
-                k: v for k, v in default_headers.items() if k != USER_AGENT_KEY
-            }
-        else:
-            self.default_headers = None
-
-        super().__init__(**kwargs)
-
    def service_url(self) -> str:
        """Get the URL of the service."""
        return str(self.client.base_url) if self.client else "Unknown"
@@ -171,16 +78,15 @@ class RawOpenAIEmbeddingClient(
            Generated embeddings with usage metadata.

        Raises:
-            ValueError: If model is not provided or values is empty.
+            ValueError: If model_id is not provided or values is empty.
        """
        if not values:
            return GeneratedEmbeddings([], options=options)  # type: ignore

        opts: dict[str, Any] = options or {}  # type: ignore
-        # backward compat: accept model_id in options
-        model = opts.get("model") or opts.get("model_id") or self.model
+        model = opts.get("model_id") or self.model_id
        if not model:
-            raise ValueError("model is required")
+            raise ValueError("model_id is required")

        kwargs: dict[str, Any] = {"input": list(values), "model": model}
        if dimensions := opts.get("dimensions"):
@@ -190,7 +96,7 @@ class RawOpenAIEmbeddingClient(
        if user := opts.get("user"):
            kwargs["user"] = user

-        response = await self.client.embeddings.create(**kwargs)  # type: ignore[union-attr]
+        response = await (await self._ensure_client()).embeddings.create(**kwargs)

        encoding = kwargs.get("encoding_format", "float")
        embeddings: list[Embedding[list[float]]] = []
@@ -206,7 +112,7 @@ class RawOpenAIEmbeddingClient(
                Embedding(
                    vector=vector,
                    dimensions=len(vector),
-                    model=response.model,
+                    model_id=response.model,
                )
            )

@@ -221,6 +127,7 @@ class RawOpenAIEmbeddingClient(


 class OpenAIEmbeddingClient(
+    OpenAIConfigMixin,
    EmbeddingTelemetryLayer[str, list[float], OpenAIEmbeddingOptionsT],
    RawOpenAIEmbeddingClient[OpenAIEmbeddingOptionsT],
    Generic[OpenAIEmbeddingOptionsT],
@@ -228,9 +135,8 @@ class OpenAIEmbeddingClient(
    """OpenAI embedding client with telemetry support.

    Keyword Args:
-        model: The embedding model (e.g. "text-embedding-3-small").
-            Can also be set via environment variable OPENAI_EMBEDDING_MODEL.
-        model_id: Deprecated alias for ``model``.
+        model_id: The embedding model ID (e.g. "text-embedding-3-small").
+            Can also be set via environment variable OPENAI_EMBEDDING_MODEL_ID.
        api_key: OpenAI API key.
            Can also be set via environment variable OPENAI_API_KEY.
        org_id: OpenAI organization ID.
@@ -248,12 +154,12 @@ class OpenAIEmbeddingClient(

            # Using environment variables
            # Set OPENAI_API_KEY=sk-...
-            # Set OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+            # Set OPENAI_EMBEDDING_MODEL_ID=text-embedding-3-small
            client = OpenAIEmbeddingClient()

            # Or passing parameters directly
            client = OpenAIEmbeddingClient(
-                model="text-embedding-3-small",
+                model_id="text-embedding-3-small",
                api_key="sk-...",
            )

@@ -262,12 +168,10 @@ class OpenAIEmbeddingClient(
            print(result[0].vector)
    """

-    OTEL_PROVIDER_NAME: ClassVar[str] = "openai"  # type: ignore[reportIncompatibleVariableOverride, misc]
-
    def __init__(
        self,
        *,
-        model: str | None = None,
+        model_id: str | None = None,
        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
        org_id: str | None = None,
        default_headers: Mapping[str, str] | None = None,
@@ -278,26 +182,38 @@ class OpenAIEmbeddingClient(
        env_file_encoding: str | None = None,
    ) -> None:
        """Initialize an OpenAI embedding client."""
-        super().__init__(
-            model=model,
+        openai_settings = load_settings(
+            OpenAISettings,
+            env_prefix="OPENAI_",
            api_key=api_key,
-            org_id=org_id,
            base_url=base_url,
-            default_headers=default_headers,
-            async_client=async_client,
+            org_id=org_id,
+            embedding_model_id=model_id,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
        )
-        if otel_provider_name is not None:
-            self.OTEL_PROVIDER_NAME = otel_provider_name  # type: ignore[misc]

-        # Validate that the client was created successfully (from explicit args or env vars)
-        if self.client is None:
+        api_key_value = openai_settings.get("api_key")
+        if not async_client and not api_key_value:
            raise ValueError(
                "OpenAI API key is required. Set via 'api_key' parameter or 'OPENAI_API_KEY' environment variable."
            )
-        if not self.model:
+
+        embedding_model_id = openai_settings.get("embedding_model_id")
+        if not embedding_model_id:
            raise ValueError(
-                "OpenAI embedding model is required. "
-                "Set via 'model' parameter or 'OPENAI_EMBEDDING_MODEL' environment variable."
+                "OpenAI embedding model ID is required. "
+                "Set via 'model_id' parameter or 'OPENAI_EMBEDDING_MODEL_ID' environment variable."
            )
+
+        base_url_value = openai_settings.get("base_url")
+
+        super().__init__(
+            model_id=embedding_model_id,
+            api_key=self._get_api_key(api_key_value),
+            base_url=base_url_value if base_url_value else None,
+            org_id=openai_settings.get("org_id"),
+            default_headers=default_headers,
+            client=async_client,
+            otel_provider_name=otel_provider_name,
+        )
@@ -6,9 +6,10 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Any

-from agent_framework.exceptions import ChatClientContentFilterException
 from openai import BadRequestError

+from ..exceptions import ChatClientContentFilterException
+

 class ContentFilterResultSeverity(Enum):
    """The severity of the content filter result."""
@@ -14,7 +14,6 @@ from collections.abc import (
    MutableMapping,
    Sequence,
 )
-from copy import copy
 from datetime import datetime, timezone
 from itertools import chain
 from typing import (
@@ -26,45 +25,9 @@ from typing import (
    NoReturn,
    TypedDict,
    cast,
-    overload,
 )
-from urllib.parse import urljoin, urlparse

-from agent_framework._clients import BaseChatClient
-from agent_framework._middleware import ChatMiddlewareLayer
-from agent_framework._settings import SecretString
-from agent_framework._telemetry import APP_INFO, USER_AGENT_KEY, prepend_agent_framework_to_user_agent
-from agent_framework._tools import (
-    SHELL_TOOL_KIND_VALUE,
-    FunctionInvocationConfiguration,
-    FunctionInvocationLayer,
-    FunctionTool,
-    ToolTypes,
-    normalize_tools,
-    tool,
-)
-from agent_framework._types import (
-    Annotation,
-    ChatOptions,
-    ChatResponse,
-    ChatResponseUpdate,
-    Content,
-    ContinuationToken,
-    Message,
-    ResponseStream,
-    Role,
-    TextSpanRegion,
-    UsageDetails,
-    detect_media_type_from_base64,
-    prepend_instructions_to_messages,
-    validate_tool_mode,
-)
-from agent_framework.exceptions import (
-    ChatClientException,
-    ChatClientInvalidRequestException,
-)
-from agent_framework.observability import ChatTelemetryLayer
-from openai import AsyncAzureOpenAI, AsyncOpenAI, BadRequestError
+from openai import AsyncOpenAI, BadRequestError
 from openai.types.responses import FunctionShellTool
 from openai.types.responses.file_search_tool_param import FileSearchToolParam
 from openai.types.responses.function_tool_param import FunctionToolParam
@@ -85,13 +48,41 @@ from openai.types.responses.tool_param import (
 from openai.types.responses.web_search_tool_param import WebSearchToolParam
 from pydantic import BaseModel

-from ._exceptions import OpenAIContentFilterException
-from ._shared import (
-    DEFAULT_AZURE_OPENAI_RESPONSES_API_VERSION,
-    get_api_key,
-    load_openai_service_settings,
-    maybe_append_azure_endpoint_guidance,
+from .._clients import BaseChatClient
+from .._middleware import ChatMiddlewareLayer
+from .._settings import load_settings
+from .._tools import (
+    SHELL_TOOL_KIND_VALUE,
+    FunctionInvocationConfiguration,
+    FunctionInvocationLayer,
+    FunctionTool,
+    ToolTypes,
+    normalize_tools,
+    tool,
 )
+from .._types import (
+    Annotation,
+    ChatOptions,
+    ChatResponse,
+    ChatResponseUpdate,
+    Content,
+    ContinuationToken,
+    Message,
+    ResponseStream,
+    Role,
+    TextSpanRegion,
+    UsageDetails,
+    detect_media_type_from_base64,
+    prepend_instructions_to_messages,
+    validate_tool_mode,
+)
+from ..exceptions import (
+    ChatClientException,
+    ChatClientInvalidRequestException,
+)
+from ..observability import ChatTelemetryLayer
+from ._exceptions import OpenAIContentFilterException
+from ._shared import OpenAIBase, OpenAIConfigMixin, OpenAISettings

 if sys.version_info >= (3, 13):
    from typing import TypeVar  # type: ignore # pragma: no cover
@@ -107,7 +98,7 @@ else:
    from typing_extensions import TypedDict  # type: ignore # pragma: no cover

 if TYPE_CHECKING:
-    from agent_framework._middleware import (
+    from .._middleware import (
        ChatMiddleware,
        ChatMiddlewareCallable,
        FunctionMiddleware,
@@ -156,7 +147,7 @@ class StreamOptions(TypedDict, total=False):
 ResponseFormatT = TypeVar("ResponseFormatT", bound=BaseModel | None, default=None)


-class OpenAIChatOptions(ChatOptions[ResponseFormatT], Generic[ResponseFormatT], total=False):
+class OpenAIResponsesOptions(ChatOptions[ResponseFormatT], Generic[ResponseFormatT], total=False):
    """OpenAI Responses API-specific chat options.

    Extends ChatOptions with options specific to OpenAI's Responses API.
@@ -231,10 +222,10 @@ class OpenAIChatOptions(ChatOptions[ResponseFormatT], Generic[ResponseFormatT],
    completion or resume a streaming response."""


-OpenAIChatOptionsT = TypeVar(
-    "OpenAIChatOptionsT",
+OpenAIResponsesOptionsT = TypeVar(
+    "OpenAIResponsesOptionsT",
    bound=TypedDict,  # type: ignore[valid-type]
-    default="OpenAIChatOptions",
+    default="OpenAIResponsesOptions",
    covariant=True,
 )

@@ -245,9 +236,10 @@ OpenAIChatOptionsT = TypeVar(
 # region ResponsesClient


-class RawOpenAIChatClient(  # type: ignore[misc]
-    BaseChatClient[OpenAIChatOptionsT],
-    Generic[OpenAIChatOptionsT],
+class RawOpenAIResponsesClient(  # type: ignore[misc]
+    OpenAIBase,
+    BaseChatClient[OpenAIResponsesOptionsT],
+    Generic[OpenAIResponsesOptionsT],
 ):
    """Raw OpenAI Responses client without middleware, telemetry, or function invocation.

@@ -261,190 +253,13 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        2. **ChatMiddlewareLayer** - Applies chat middleware per model call and stays outside telemetry
        3. **ChatTelemetryLayer** - Must stay inside chat middleware for correct per-call telemetry

-        Use ``OpenAIChatClient`` instead for a fully-featured client with all layers applied.
+        Use ``OpenAIResponsesClient`` instead for a fully-featured client with all layers applied.
    """

-    INJECTABLE: ClassVar[set[str]] = {"client"}
    STORES_BY_DEFAULT: ClassVar[bool] = True  # type: ignore[reportIncompatibleVariableOverride, misc]

    FILE_SEARCH_MAX_RESULTS: int = 50

-    @overload
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None: ...
-
-    @overload
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-    ) -> None: ...
-
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        model_id: str | None = None,
-        api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str | None = None,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        **kwargs: Any,
-    ) -> None:
-        """Initialize a raw OpenAI Responses client.
-
-        Keyword Args:
-            model: OpenAI model name.
-            model_id: Deprecated alias for ``model``.
-            api_key: OpenAI API key, SecretString, or callable returning a key.
-            org_id: OpenAI organization ID.
-            base_url: Custom API base URL.
-            azure_endpoint: Azure OpenAI endpoint. When provided, the client uses
-                ``AsyncAzureOpenAI`` instead of ``AsyncOpenAI``. The value should be the
-                resource endpoint and should not end with ``/openai/v1``. For Azure OpenAI
-                key auth, either pass the resource endpoint without that suffix to
-                ``azure_endpoint`` or pass the full ``.../openai/v1`` URL to ``base_url``.
-                Can also be set via ``AZURE_OPENAI_ENDPOINT`` when no ``OPENAI_BASE_URL``
-                is configured.
-            api_version: Azure OpenAI API version. Can also be set via
-                ``AZURE_OPENAI_API_VERSION``.
-            default_headers: Additional HTTP headers.
-            async_client: Pre-configured AsyncOpenAI client (skips client creation).
-            instruction_role: Role for instruction messages (e.g. ``"system"``).
-            env_file_path: Path to .env file for settings.
-            env_file_encoding: Encoding for .env file.
-            kwargs: Additional keyword arguments forwarded to ``BaseChatClient``.
-        """
-        if model_id is not None and model is None:
-            import warnings
-
-            warnings.warn("model_id is deprecated, use model instead", DeprecationWarning, stacklevel=2)
-            model = model_id
-
-        openai_settings: dict[str, Any] = {}
-        use_azure_client = isinstance(async_client, AsyncAzureOpenAI)
-        if not async_client:
-            resolved_settings, use_azure_client = load_openai_service_settings(
-                model=model,
-                api_key=api_key,
-                org_id=org_id,
-                base_url=base_url,
-                azure_endpoint=azure_endpoint,
-                api_version=api_version,
-                env_file_path=env_file_path,
-                env_file_encoding=env_file_encoding,
-                azure_model_env_vars=("AZURE_OPENAI_DEPLOYMENT_NAME",),
-                default_azure_api_version=DEFAULT_AZURE_OPENAI_RESPONSES_API_VERSION,
-            )
-            openai_settings = dict(resolved_settings)
-
-            api_key_value = openai_settings.get("api_key")
-            if not api_key_value:
-                raise ValueError(
-                    "OpenAI API key is required. Set via the 'api_key' parameter or the "
-                    "'OPENAI_API_KEY' or 'AZURE_OPENAI_API_KEY' environment variables."
-                )
-            resolved_model = openai_settings.get("model") or model
-            if not resolved_model:
-                raise ValueError(
-                    "OpenAI model is required. Set via the 'model' parameter or the "
-                    "'OPENAI_MODEL' or 'AZURE_OPENAI_DEPLOYMENT_NAME' environment variables."
-                )
-            model = resolved_model
-
-            resolved_api_key = get_api_key(api_key_value)
-
-            # Merge APP_INFO into the headers
-            merged_headers = dict(copy(default_headers)) if default_headers else {}
-            if APP_INFO:
-                merged_headers.update(APP_INFO)
-                merged_headers = prepend_agent_framework_to_user_agent(merged_headers)
-
-            client_args: dict[str, Any] = {"api_key": resolved_api_key, "default_headers": merged_headers}
-            if use_azure_client:
-                endpoint_value = openai_settings.get("azure_endpoint")
-                if (
-                    not openai_settings.get("base_url")
-                    and endpoint_value
-                    and (hostname := urlparse(str(endpoint_value)).hostname)
-                    and hostname.endswith(".openai.azure.com")
-                ):
-                    openai_settings["base_url"] = urljoin(str(endpoint_value), "/openai/v1/")
-
-                client_args.pop("api_key")
-                if resolved_api_version := openai_settings.get("api_version"):
-                    client_args["api_version"] = resolved_api_version
-                if resolved_base_url := openai_settings.get("base_url"):
-                    client_args["base_url"] = resolved_base_url
-                elif resolved_azure_endpoint := openai_settings.get("azure_endpoint"):
-                    client_args["azure_endpoint"] = resolved_azure_endpoint
-                if callable(resolved_api_key):
-                    client_args["azure_ad_token_provider"] = resolved_api_key
-                else:
-                    client_args["api_key"] = resolved_api_key
-                client_args["azure_deployment"] = resolved_model
-                async_client = AsyncAzureOpenAI(**client_args)
-            else:
-                if resolved_org_id := openai_settings.get("org_id"):
-                    client_args["organization"] = resolved_org_id
-                if resolved_base_url := openai_settings.get("base_url"):
-                    client_args["base_url"] = resolved_base_url
-
-                async_client = AsyncOpenAI(**client_args)
-
-        self.client = async_client
-        self.model: str | None = model.strip() if model else None
-
-        # Store configuration for serialization
-        resolved_base_url = openai_settings.get("base_url") or base_url
-        resolved_azure_endpoint = openai_settings.get("azure_endpoint") or azure_endpoint
-        resolved_api_version = openai_settings.get("api_version") or api_version
-        self.org_id = openai_settings.get("org_id") or org_id
-        self.base_url = str(resolved_base_url) if resolved_base_url else None
-        self.azure_endpoint = str(resolved_azure_endpoint) if resolved_azure_endpoint else None
-        self.api_version = str(resolved_api_version) if use_azure_client and resolved_api_version else None
-        if default_headers:
-            self.default_headers: dict[str, Any] | None = {
-                k: v for k, v in default_headers.items() if k != USER_AGENT_KEY
-            }
-        else:
-            self.default_headers = None
-
-        if instruction_role is not None:
-            self.instruction_role = instruction_role
-
-        if use_azure_client:
-            self.OTEL_PROVIDER_NAME = "azure.ai.openai"  # type: ignore[misc]
-
-        super().__init__(**kwargs)
-
    # region Inner Methods

    async def _prepare_request(
@@ -458,7 +273,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Returns:
            Tuple of (client, run_options, validated_options).
        """
-        client = self.client
+        client = await self._ensure_client()
        validated_options = await self._validate_options(options)
        run_options = await self._prepare_options(messages, validated_options, **kwargs)
        return client, run_options, validated_options
@@ -471,10 +286,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
                inner_exception=ex,
            ) from ex
        raise ChatClientException(
-            maybe_append_azure_endpoint_guidance(
-                f"{type(self)} service failed to complete the prompt: {ex}",
-                azure_endpoint=self.azure_endpoint,
-            ),
+            f"{type(self)} service failed to complete the prompt: {ex}",
            inner_exception=ex,
        ) from ex

@@ -497,7 +309,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
                nonlocal validated_options
                if continuation_token is not None:
                    # Resume a background streaming response by retrieving with stream=True
-                    client = self.client
+                    client = await self._ensure_client()
                    validated_options = await self._validate_options(options)
                    try:
                        stream_response = await client.responses.retrieve(
@@ -544,7 +356,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        async def _get_response() -> ChatResponse:
            if continuation_token is not None:
                # Poll a background response by retrieving without stream
-                client = self.client
+                client = await self._ensure_client()
                validated_options = await self._validate_options(options)
                try:
                    response = await client.responses.retrieve(continuation_token["response_id"])
@@ -728,13 +540,13 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Basic code interpreter
-                tool = OpenAIChatClient.get_code_interpreter_tool()
+                tool = OpenAIResponsesClient.get_code_interpreter_tool()

                # With file access
-                tool = OpenAIChatClient.get_code_interpreter_tool(file_ids=["file-abc123"])
+                tool = OpenAIResponsesClient.get_code_interpreter_tool(file_ids=["file-abc123"])

                # Use with agent
                agent = ChatAgent(client, tools=[tool])
@@ -770,13 +582,13 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Basic web search
-                tool = OpenAIChatClient.get_web_search_tool()
+                tool = OpenAIResponsesClient.get_web_search_tool()

                # With location context
-                tool = OpenAIChatClient.get_web_search_tool(
+                tool = OpenAIResponsesClient.get_web_search_tool(
                    user_location={"city": "Seattle", "country": "US"},
                    search_context_size="medium",
                )
@@ -832,13 +644,13 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Basic image generation
-                tool = OpenAIChatClient.get_image_generation_tool()
+                tool = OpenAIResponsesClient.get_image_generation_tool()

                # High quality large image
-                tool = OpenAIChatClient.get_image_generation_tool(
+                tool = OpenAIResponsesClient.get_image_generation_tool(
                    size="1536x1024",
                    quality="high",
                    output_format="png",
@@ -900,16 +712,18 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Hosted shell (OpenAI container)
-                tool = OpenAIChatClient.get_shell_tool()
+                tool = OpenAIResponsesClient.get_shell_tool()

                # Hosted shell with custom environment
-                tool = OpenAIChatClient.get_shell_tool(environment={"type": "container_auto", "file_ids": ["file-abc"]})
+                tool = OpenAIResponsesClient.get_shell_tool(
+                    environment={"type": "container_auto", "file_ids": ["file-abc"]}
+                )

                # Local shell execution
-                tool = OpenAIChatClient.get_shell_tool(
+                tool = OpenAIResponsesClient.get_shell_tool(
                    func=my_shell_func,
                )
        """
@@ -987,16 +801,16 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Basic MCP tool
-                tool = OpenAIChatClient.get_mcp_tool(
+                tool = OpenAIResponsesClient.get_mcp_tool(
                    name="my_mcp",
                    url="https://mcp.example.com",
                )

                # With approval settings
-                tool = OpenAIChatClient.get_mcp_tool(
+                tool = OpenAIResponsesClient.get_mcp_tool(
                    name="github_mcp",
                    url="https://mcp.github.com",
                    description="GitHub MCP server",
@@ -1005,7 +819,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
                )

                # With specific tool approvals
-                tool = OpenAIChatClient.get_mcp_tool(
+                tool = OpenAIResponsesClient.get_mcp_tool(
                    name="tools_mcp",
                    url="https://tools.example.com",
                    approval_mode={
@@ -1060,15 +874,15 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Basic file search
-                tool = OpenAIChatClient.get_file_search_tool(
+                tool = OpenAIResponsesClient.get_file_search_tool(
                    vector_store_ids=["vs_abc123"],
                )

                # With result limit
-                tool = OpenAIChatClient.get_file_search_tool(
+                tool = OpenAIResponsesClient.get_file_search_tool(
                    vector_store_ids=["vs_abc123", "vs_def456"],
                    max_num_results=10,
                )
@@ -1129,7 +943,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]

        # translations between options and Responses API
        translations = {
-            "model_id": "model",  # backward compat: accept model_id in options
+            "model_id": "model",
            "allow_multiple_tool_calls": "parallel_tool_calls",
            "conversation_id": "previous_response_id",
            "max_tokens": "max_output_tokens",
@@ -1189,9 +1003,9 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        Since AzureAIClients use a different param for this, this method is overridden in those clients.
        """
        if not options.get("model"):
-            if not self.model:
-                raise ValueError("model must be a non-empty string")
-            options["model"] = self.model
+            if not self.model_id:
+                raise ValueError("model_id must be a non-empty string")
+            options["model"] = self.model_id

    def _get_current_conversation_id(self, options: Mapping[str, Any], **kwargs: Any) -> str | None:
        """Get the current conversation ID, preferring kwargs over options.
@@ -1870,7 +1684,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
                "%Y-%m-%dT%H:%M:%S.%fZ"
            ),
            "messages": response_message,
-            "model": response.model,
+            "model_id": response.model,
            "additional_properties": metadata,
            "raw_representation": response,
        }
@@ -1903,7 +1717,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        conversation_id: str | None = None
        response_id: str | None = None
        continuation_token: OpenAIContinuationToken | None = None
-        model = self.model
+        model = self.model_id
        match event.type:
            # types:
            # ResponseAudioDeltaEvent,
@@ -2416,7 +2230,7 @@ class RawOpenAIChatClient(  # type: ignore[misc]
            conversation_id=conversation_id,
            response_id=response_id,
            role="assistant",
-            model=model,
+            model_id=model,
            continuation_token=continuation_token,
            additional_properties=metadata,
            raw_representation=event,
@@ -2443,22 +2257,20 @@ class RawOpenAIChatClient(  # type: ignore[misc]
        return {}


-class OpenAIChatClient(  # type: ignore[misc]
-    FunctionInvocationLayer[OpenAIChatOptionsT],
-    ChatMiddlewareLayer[OpenAIChatOptionsT],
-    ChatTelemetryLayer[OpenAIChatOptionsT],
-    RawOpenAIChatClient[OpenAIChatOptionsT],
-    Generic[OpenAIChatOptionsT],
+class OpenAIResponsesClient(  # type: ignore[misc]
+    OpenAIConfigMixin,
+    FunctionInvocationLayer[OpenAIResponsesOptionsT],
+    ChatMiddlewareLayer[OpenAIResponsesOptionsT],
+    ChatTelemetryLayer[OpenAIResponsesOptionsT],
+    RawOpenAIResponsesClient[OpenAIResponsesOptionsT],
+    Generic[OpenAIResponsesOptionsT],
 ):
    """OpenAI Responses client class with middleware, telemetry, and function invocation support."""

-    OTEL_PROVIDER_NAME: ClassVar[str] = "openai"  # type: ignore[reportIncompatibleVariableOverride, misc]
-
-    @overload
    def __init__(
        self,
        *,
-        model: str | None = None,
+        model_id: str | None = None,
        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
        org_id: str | None = None,
        base_url: str | None = None,
@@ -2471,68 +2283,19 @@ class OpenAIChatClient(  # type: ignore[misc]
            Sequence[ChatMiddleware | ChatMiddlewareCallable | FunctionMiddleware | FunctionMiddlewareCallable] | None
        ) = None,
        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
-    ) -> None: ...
-
-    @overload
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncAzureOpenAI | AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        middleware: (
-            Sequence[ChatMiddleware | ChatMiddlewareCallable | FunctionMiddleware | FunctionMiddlewareCallable] | None
-        ) = None,
-        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
-    ) -> None: ...
-
-    def __init__(
-        self,
-        *,
-        model: str | None = None,
-        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
-        org_id: str | None = None,
-        base_url: str | None = None,
-        azure_endpoint: str | None = None,
-        api_version: str | None = None,
-        default_headers: Mapping[str, str] | None = None,
-        async_client: AsyncOpenAI | None = None,
-        instruction_role: str | None = None,
-        env_file_path: str | None = None,
-        env_file_encoding: str | None = None,
-        middleware: (
-            Sequence[ChatMiddleware | ChatMiddlewareCallable | FunctionMiddleware | FunctionMiddlewareCallable] | None
-        ) = None,
-        function_invocation_configuration: FunctionInvocationConfiguration | None = None,
        **kwargs: Any,
    ) -> None:
        """Initialize an OpenAI Responses client.

        Keyword Args:
-            model: OpenAI model name, see https://platform.openai.com/docs/models.
-                Can also be set via environment variable OPENAI_MODEL.
+            model_id: OpenAI model name, see https://platform.openai.com/docs/models.
+                Can also be set via environment variable OPENAI_RESPONSES_MODEL_ID.
            api_key: The API key to use. If provided will override the env vars or .env file value.
                Can also be set via environment variable OPENAI_API_KEY.
            org_id: The org ID to use. If provided will override the env vars or .env file value.
                Can also be set via environment variable OPENAI_ORG_ID.
            base_url: The base URL to use. If provided will override the standard value.
                Can also be set via environment variable OPENAI_BASE_URL.
-            azure_endpoint: Azure OpenAI endpoint. When provided, the client uses
-                ``AsyncAzureOpenAI``. The value should be the Azure resource endpoint and
-                should not end with ``/openai/v1``. For Azure OpenAI key auth, either pass
-                the resource endpoint without that suffix to ``azure_endpoint`` or pass the
-                full ``.../openai/v1`` URL to ``base_url`` instead. Can also be discovered
-                from ``AZURE_OPENAI_ENDPOINT`` when no OpenAI base URL is configured.
-            api_version: Azure OpenAI API version. Can also be set via
-                ``AZURE_OPENAI_API_VERSION``.
            default_headers: The default headers mapping of string keys to
                string values for HTTP requests.
            async_client: An existing client to use.
@@ -2548,65 +2311,63 @@ class OpenAIChatClient(  # type: ignore[misc]
        Examples:
            .. code-block:: python

-                from agent_framework.openai import OpenAIChatClient
+                from agent_framework.openai import OpenAIResponsesClient

                # Using environment variables
                # Set OPENAI_API_KEY=sk-...
-                # Set OPENAI_MODEL=gpt-4o
-                client = OpenAIChatClient()
+                # Set OPENAI_RESPONSES_MODEL_ID=gpt-4o
+                client = OpenAIResponsesClient()

                # Or passing parameters directly
-                client = OpenAIChatClient(model="gpt-4o", api_key="sk-...")
+                client = OpenAIResponsesClient(model_id="gpt-4o", api_key="sk-...")

                # Or loading from a .env file
-                client = OpenAIChatClient(env_file_path="path/to/.env")
+                client = OpenAIResponsesClient(env_file_path="path/to/.env")

                # Using custom ChatOptions with type safety:
                from typing import TypedDict
-                from agent_framework.openai import OpenAIChatOptions
+                from agent_framework.openai import OpenAIResponsesOptions


-                class MyOptions(OpenAIChatOptions, total=False):
+                class MyOptions(OpenAIResponsesOptions, total=False):
                    my_custom_option: str


-                client: OpenAIChatClient[MyOptions] = OpenAIChatClient(model="gpt-4o")
+                client: OpenAIResponsesClient[MyOptions] = OpenAIResponsesClient(model_id="gpt-4o")
                response = await client.get_response("Hello", options={"my_custom_option": "value"})
        """
-        super().__init__(
-            model=model,
+        openai_settings = load_settings(
+            OpenAISettings,
+            env_prefix="OPENAI_",
            api_key=api_key,
            org_id=org_id,
            base_url=base_url,
-            azure_endpoint=azure_endpoint,
-            api_version=api_version,
-            default_headers=default_headers,
-            async_client=async_client,
-            instruction_role=instruction_role,
+            responses_model_id=model_id,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
+        )
+
+        api_key_setting = openai_settings.get("api_key")
+        if not async_client and not api_key_setting:
+            raise ValueError(
+                "OpenAI API key is required. Set via 'api_key' parameter or 'OPENAI_API_KEY' environment variable."
+            )
+        responses_model_id = openai_settings.get("responses_model_id")
+        if not responses_model_id:
+            raise ValueError(
+                "OpenAI model ID is required. "
+                "Set via 'model_id' parameter or 'OPENAI_RESPONSES_MODEL_ID' environment variable."
+            )
+
+        super().__init__(
+            model_id=responses_model_id,
+            api_key=self._get_api_key(api_key_setting),
+            org_id=openai_settings.get("org_id"),
+            default_headers=default_headers,
+            client=async_client,
+            instruction_role=instruction_role,
+            base_url=openai_settings.get("base_url"),
            middleware=middleware,
            function_invocation_configuration=function_invocation_configuration,
            **kwargs,
        )
-
-
-def _apply_openai_chat_client_docstrings() -> None:
-    """Align OpenAI Responses client docstrings with the raw implementation."""
-    from agent_framework._clients import BaseChatClient
-    from agent_framework._docstrings import apply_layered_docstring
-
-    apply_layered_docstring(RawOpenAIChatClient.get_response, BaseChatClient.get_response)
-    apply_layered_docstring(
-        OpenAIChatClient.get_response,
-        RawOpenAIChatClient.get_response,
-        extra_keyword_args={
-            "middleware": """
-                Optional per-call chat and function middleware.
-                This is merged with any middleware configured on the client for the current request.
-            """,
-        },
-    )
-
-
-_apply_openai_chat_client_docstrings()
@@ -3,19 +3,17 @@
 from __future__ import annotations

 import logging
-import os
 import sys
 from collections.abc import Awaitable, Callable, Mapping, MutableMapping, Sequence
 from copy import copy
 from typing import Any, ClassVar, Union, cast

 import openai
-from agent_framework._serialization import SerializationMixin
-from agent_framework._settings import SecretString, load_settings
-from agent_framework._telemetry import APP_INFO, USER_AGENT_KEY, prepend_agent_framework_to_user_agent
-from agent_framework._tools import FunctionTool
-from dotenv import dotenv_values
-from openai import AsyncOpenAI, AsyncStream, _legacy_response  # type: ignore
+from openai import (
+    AsyncOpenAI,
+    AsyncStream,
+    _legacy_response,  # type: ignore
+)
 from openai.types import Completion
 from openai.types.audio import Transcription
 from openai.types.chat import ChatCompletion, ChatCompletionChunk
@@ -24,10 +22,12 @@ from openai.types.responses.response import Response
 from openai.types.responses.response_stream_event import ResponseStreamEvent
 from packaging.version import parse

-logger: logging.Logger = logging.getLogger("agent_framework.openai")
+from .._serialization import SerializationMixin
+from .._settings import SecretString
+from .._telemetry import APP_INFO, USER_AGENT_KEY, prepend_agent_framework_to_user_agent
+from .._tools import FunctionTool

-DEFAULT_AZURE_OPENAI_CHAT_COMPLETION_API_VERSION = "2024-10-21"
-DEFAULT_AZURE_OPENAI_RESPONSES_API_VERSION = "preview"
+logger: logging.Logger = logging.getLogger("agent_framework.openai")


 RESPONSE_TYPE = Union[
@@ -88,10 +88,12 @@ class OpenAISettings(TypedDict, total=False):
            Can be set via environment variable OPENAI_BASE_URL.
        org_id: This is usually optional unless your account belongs to multiple organizations.
            Can be set via environment variable OPENAI_ORG_ID.
-        model: The OpenAI model to use, for example, gpt-4o or o1.
-            Can be set via environment variable OPENAI_MODEL.
-        embedding_model: The OpenAI embedding model to use, for example, text-embedding-3-small.
-            Can be set via environment variable OPENAI_EMBEDDING_MODEL.
+        chat_model_id: The OpenAI chat model ID to use, for example, gpt-3.5-turbo or gpt-4.
+            Can be set via environment variable OPENAI_CHAT_MODEL_ID.
+        responses_model_id: The OpenAI responses model ID to use, for example, gpt-4o or o1.
+            Can be set via environment variable OPENAI_RESPONSES_MODEL_ID.
+        embedding_model_id: The OpenAI embedding model ID to use, for example, text-embedding-3-small.
+            Can be set via environment variable OPENAI_EMBEDDING_MODEL_ID.

    Examples:
        .. code-block:: python
@@ -100,11 +102,11 @@ class OpenAISettings(TypedDict, total=False):

            # Using environment variables
            # Set OPENAI_API_KEY=sk-...
-            # Set OPENAI_MODEL=gpt-4o
+            # Set OPENAI_CHAT_MODEL_ID=gpt-4
            settings = load_settings(OpenAISettings, env_prefix="OPENAI_")

            # Or passing parameters directly
-            settings = load_settings(OpenAISettings, env_prefix="OPENAI_", api_key="sk-...", model="gpt-4o")
+            settings = load_settings(OpenAISettings, env_prefix="OPENAI_", api_key="sk-...", chat_model_id="gpt-4")

            # Or loading from a .env file
            settings = load_settings(OpenAISettings, env_prefix="OPENAI_", env_file_path="path/to/.env")
@@ -113,184 +115,28 @@ class OpenAISettings(TypedDict, total=False):
    api_key: SecretString | Callable[[], str | Awaitable[str]] | None
    base_url: str | None
    org_id: str | None
-    model: str | None
-    embedding_model: str | None
-    azure_endpoint: str | None
-    api_version: str | None
-
-
-def _load_dotenv_values(*, env_file_path: str | None, env_file_encoding: str | None) -> dict[str, str]:
-    """Load dotenv values for non-standard environment variable aliases."""
-    if env_file_path is None or not os.path.exists(env_file_path):
-        return {}
-
-    raw_dotenv_values = dotenv_values(dotenv_path=env_file_path, encoding=env_file_encoding or "utf-8")
-    return {key: value for key, value in raw_dotenv_values.items() if value is not None}
-
-
-def _get_setting_from_alias(
-    name: str,
-    *,
-    dotenv_values_by_name: Mapping[str, str],
-) -> str | None:
-    """Resolve a setting from an explicit env-var alias."""
-    if dotenv_value := dotenv_values_by_name.get(name):
-        return dotenv_value
-    return os.getenv(name)
-
-
-def load_openai_service_settings(
-    *,
-    model: str | None,
-    api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None,
-    org_id: str | None,
-    base_url: str | None,
-    azure_endpoint: str | None,
-    api_version: str | None,
-    env_file_path: str | None,
-    env_file_encoding: str | None,
-    azure_model_env_vars: Sequence[str],
-    default_azure_api_version: str,
-) -> tuple[OpenAISettings, bool]:
-    """Load OpenAI settings, including Azure OpenAI aliases.
-
-    The generic OpenAI clients primarily read from ``OPENAI_*`` variables. When an
-    ``AZURE_OPENAI_ENDPOINT`` (or ``AZURE_OPENAI_BASE_URL``) is available and no
-    explicit OpenAI base URL is configured, this helper switches to Azure-specific
-    environment variables for endpoint, API key, model deployment, and API version.
-    """
-    openai_settings = load_settings(
-        OpenAISettings,
-        env_prefix="OPENAI_",
-        api_key=api_key,
-        org_id=org_id,
-        base_url=base_url,
-        model=model,
-        azure_endpoint=azure_endpoint,
-        api_version=api_version,
-        env_file_path=env_file_path,
-        env_file_encoding=env_file_encoding,
-    )
-
-    dotenv_values_by_name = _load_dotenv_values(
-        env_file_path=env_file_path,
-        env_file_encoding=env_file_encoding,
-    )
-
-    resolved_azure_endpoint = azure_endpoint
-    resolved_azure_base_url: str | None = None
-    if not openai_settings.get("base_url"):
-        if resolved_azure_endpoint is None:
-            resolved_azure_endpoint = _get_setting_from_alias(
-                "AZURE_OPENAI_ENDPOINT",
-                dotenv_values_by_name=dotenv_values_by_name,
-            )
-        if resolved_azure_endpoint is None:
-            resolved_azure_base_url = _get_setting_from_alias(
-                "AZURE_OPENAI_BASE_URL",
-                dotenv_values_by_name=dotenv_values_by_name,
-            )
-            if resolved_azure_base_url is not None:
-                openai_settings["base_url"] = resolved_azure_base_url
-
-    use_azure_client = resolved_azure_endpoint is not None or resolved_azure_base_url is not None
-    if resolved_azure_endpoint is not None:
-        openai_settings["azure_endpoint"] = resolved_azure_endpoint
-
-    if use_azure_client:
-        if api_key is None:
-            resolved_azure_api_key = _get_setting_from_alias(
-                "AZURE_OPENAI_API_KEY",
-                dotenv_values_by_name=dotenv_values_by_name,
-            )
-            if resolved_azure_api_key is not None:
-                openai_settings["api_key"] = SecretString(resolved_azure_api_key)
-
-        if model is None:
-            for env_var_name in azure_model_env_vars:
-                resolved_model = _get_setting_from_alias(
-                    env_var_name,
-                    dotenv_values_by_name=dotenv_values_by_name,
-                )
-                if resolved_model is not None:
-                    openai_settings["model"] = resolved_model
-                    break
-
-        if not openai_settings.get("api_version"):
-            resolved_api_version = _get_setting_from_alias(
-                "AZURE_OPENAI_API_VERSION",
-                dotenv_values_by_name=dotenv_values_by_name,
-            )
-            openai_settings["api_version"] = resolved_api_version or default_azure_api_version
-
-    return openai_settings, use_azure_client
-
-
-def maybe_append_azure_endpoint_guidance(message: str, *, azure_endpoint: str | None) -> str:
-    """Append Azure endpoint guidance only when the configured endpoint shape looks suspicious."""
-    if not azure_endpoint or not azure_endpoint.rstrip("/").endswith("/openai/v1"):
-        return message
-
-    return (
-        f"{message} If you are using Azure OpenAI key auth, pass the resource endpoint without "
-        "'/openai/v1' to 'azure_endpoint', or pass the full '/openai/v1' URL via 'base_url' instead."
-    )
-
-
-def get_api_key(
-    api_key: str | SecretString | Callable[[], str | Awaitable[str]] | None,
-) -> str | Callable[[], str | Awaitable[str]] | None:
-    """Get the appropriate API key value for client initialization.
-
-    Args:
-        api_key: The API key parameter which can be a string, SecretString, callable, or None.
-
-    Returns:
-        For callable API keys: returns the callable directly.
-        For SecretString: returns the unwrapped secret value.
-        For string/None API keys: returns as-is.
-    """
-    if isinstance(api_key, SecretString):
-        return api_key.get_secret_value()
-
-    # Check version compatibility for callable API keys
-    if callable(api_key):
-        _check_openai_version_for_callable_api_key()
-
-    return api_key  # Pass callable, string, or None directly to OpenAI SDK
+    chat_model_id: str | None
+    responses_model_id: str | None
+    embedding_model_id: str | None


 class OpenAIBase(SerializationMixin):
-    """Base class for OpenAI Clients.
-
-    .. deprecated::
-        ``OpenAIBase`` is deprecated and only used by ``OpenAIAssistantsClient``
-        and ``AzureOpenAIAssistantsClient``.  New clients should manage ``client``
-        and ``model`` directly in their own ``__init__``.
-    """
+    """Base class for OpenAI Clients."""

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

-    def __init__(
-        self, *, model: str | None = None, model_id: str | None = None, client: AsyncOpenAI | None = None, **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: The AI model to use.
-            model_id: Deprecated alias for ``model``.
+            model_id: The AI model ID to use.
            **kwargs: Additional keyword arguments.
        """
-        if model_id is not None and model is None:
-            import warnings
-
-            warnings.warn("model_id is deprecated, use model instead", DeprecationWarning, stacklevel=2)
-            model = model_id
        self.client = client
-        self.model: str | None = None
-        if model:
-            self.model = model.strip()
+        self.model_id = None
+        if model_id:
+            self.model_id = model_id.strip()

        # Call super().__init__() to continue MRO chain (e.g., RawChatClient)
        # Extract known kwargs that belong to other base classes
@@ -355,19 +201,13 @@ class OpenAIBase(SerializationMixin):


 class OpenAIConfigMixin(OpenAIBase):
-    """Internal class for configuring a connection to an OpenAI service.
-
-    .. deprecated::
-        ``OpenAIConfigMixin`` is deprecated and only used by ``OpenAIAssistantsClient``
-        and ``AzureOpenAIAssistantsClient``.  New clients handle configuration
-        directly in their own ``__init__``.
-    """
+    """Internal class for configuring a connection to an OpenAI service."""

    OTEL_PROVIDER_NAME: ClassVar[str] = "openai"  # type: ignore[reportIncompatibleVariableOverride, misc]

    def __init__(
        self,
-        model: str,
+        model_id: str,
        api_key: str | Callable[[], str | Awaitable[str]] | None = None,
        org_id: str | None = None,
        default_headers: Mapping[str, str] | None = None,
@@ -382,7 +222,7 @@ class OpenAIConfigMixin(OpenAIBase):
        different types of AI model interactions, like chat or text completion.

        Args:
-            model: OpenAI model identifier. Must be non-empty.
+            model_id: OpenAI model identifier. Must be non-empty.
                Default to a preset value.
            api_key: OpenAI API key for authentication, or a callable that returns an API key.
                Must be non-empty. (Optional)
@@ -429,7 +269,7 @@ class OpenAIConfigMixin(OpenAIBase):
            self.default_headers = None

        args = {
-            "model": model,
+            "model_id": model_id,
            "client": client,
        }
        if instruction_role:
@@ -54,7 +54,6 @@ all = [
    "agent-framework-declarative",
    "agent-framework-devui",
    "agent-framework-durabletask",
-    "agent-framework-foundry",
    "agent-framework-foundry-local",
    "agent-framework-github-copilot; python_version >= '3.11'",
    "agent-framework-lab",
@@ -1,9 +1,10 @@
 # Copyright (c) Microsoft. All rights reserved.
 from typing import Any

-from agent_framework import Message
 from pytest import fixture

+from agent_framework import Message
+

 # region: Connector Settings fixtures
@fixture
@@ -1,16 +1,31 @@
 # Copyright (c) Microsoft. All rights reserved.

+import os
 from typing import Annotated
 from unittest.mock import AsyncMock, MagicMock, patch

 import pytest
+from azure.identity import AzureCliCredential
+from pydantic import Field
+
 from agent_framework import (
+    Agent,
+    AgentResponse,
+    AgentResponseUpdate,
+    AgentSession,
+    ChatResponse,
+    ChatResponseUpdate,
+    Message,
    SupportsChatGetResponse,
    tool,
 )
 from agent_framework._settings import SecretString
 from agent_framework.azure import AzureOpenAIAssistantsClient
-from pydantic import Field
+
+skip_if_azure_integration_tests_disabled = pytest.mark.skipif(
+    os.getenv("AZURE_OPENAI_ENDPOINT", "") in ("", "https://test-endpoint.com"),
+    reason="No real AZURE_OPENAI_ENDPOINT provided; skipping integration tests.",
+)


 def create_test_azure_assistants_client(
@@ -72,7 +87,7 @@ def test_azure_assistants_client_init_with_client(mock_async_azure_openai: Magic
    )

    assert client.client is mock_async_azure_openai
-    assert client.model == "test_chat_deployment"
+    assert client.model_id == "test_chat_deployment"
    assert client.assistant_id == "existing-assistant-id"
    assert client.thread_id == "test-thread-id"
    assert not client._should_delete_assistant  # type: ignore
@@ -93,7 +108,7 @@ def test_azure_assistants_client_init_auto_create_client(
    )

    assert client.client is mock_async_azure_openai
-    assert client.model == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
+    assert client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
    assert client.assistant_id is None
    assert client.assistant_name == "TestAssistant"
    assert not client._should_delete_assistant  # type: ignore
@@ -124,7 +139,7 @@ def test_azure_assistants_client_init_with_default_headers(azure_openai_unit_tes
        default_headers=default_headers,
    )

-    assert client.model == "test_chat_deployment"
+    assert client.model_id == "test_chat_deployment"
    assert isinstance(client, SupportsChatGetResponse)

    # Assert that the default header we added is present in the client's default headers
@@ -220,7 +235,7 @@ def test_azure_assistants_client_serialize(azure_openai_unit_test_env: dict[str,

    dumped_settings = client.to_dict()

-    assert dumped_settings["model"] == "test_chat_deployment"
+    assert dumped_settings["model_id"] == "test_chat_deployment"
    assert dumped_settings["assistant_id"] == "test-assistant-id"
    assert dumped_settings["assistant_name"] == "TestAssistant"
    assert dumped_settings["thread_id"] == "test-thread-id"
@@ -241,18 +256,319 @@ def get_weather(
    return f"The weather in {location} is sunny with a high of 25°C."


+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_get_response() -> None:
+    """Test Azure Assistants Client response."""
+    async with AzureOpenAIAssistantsClient(credential=AzureCliCredential()) as azure_assistants_client:
+        assert isinstance(azure_assistants_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(
+            Message(
+                role="user",
+                text="The weather in Seattle is currently sunny with a high of 25°C. "
+                "It's a beautiful day for outdoor activities.",
+            )
+        )
+        messages.append(Message(role="user", text="What's the weather like today?"))
+
+        # Test that the client can be used to get a response
+        response = await azure_assistants_client.get_response(messages=messages)
+
+        assert response is not None
+        assert isinstance(response, ChatResponse)
+        assert any(word in response.text.lower() for word in ["sunny", "25", "weather", "seattle"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_get_response_tools() -> None:
+    """Test Azure Assistants Client response with tools."""
+    async with AzureOpenAIAssistantsClient(credential=AzureCliCredential()) as azure_assistants_client:
+        assert isinstance(azure_assistants_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(Message(role="user", text="What's the weather like in Seattle?"))
+
+        # Test that the client can be used to get a response
+        response = await azure_assistants_client.get_response(
+            messages=messages,
+            options={"tools": [get_weather], "tool_choice": "auto"},
+        )
+
+        assert response is not None
+        assert isinstance(response, ChatResponse)
+        assert any(word in response.text.lower() for word in ["sunny", "25", "weather"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_streaming() -> None:
+    """Test Azure Assistants Client streaming response."""
+    async with AzureOpenAIAssistantsClient(credential=AzureCliCredential()) as azure_assistants_client:
+        assert isinstance(azure_assistants_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(
+            Message(
+                role="user",
+                text="The weather in Seattle is currently sunny with a high of 25°C. "
+                "It's a beautiful day for outdoor activities.",
+            )
+        )
+        messages.append(Message(role="user", text="What's the weather like today?"))
+
+        # Test that the client can be used to get a response
+        response = azure_assistants_client.get_response(messages=messages, stream=True)
+
+        full_message: str = ""
+        async for chunk in response:
+            assert chunk is not None
+            assert isinstance(chunk, ChatResponseUpdate)
+            for content in chunk.contents:
+                if content.type == "text" and content.text:
+                    full_message += content.text
+
+        assert any(word in full_message.lower() for word in ["sunny", "25", "weather", "seattle"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_streaming_tools() -> None:
+    """Test Azure Assistants Client streaming response with tools."""
+    async with AzureOpenAIAssistantsClient(credential=AzureCliCredential()) as azure_assistants_client:
+        assert isinstance(azure_assistants_client, SupportsChatGetResponse)
+
+        messages: list[Message] = []
+        messages.append(Message(role="user", text="What's the weather like in Seattle?"))
+
+        # Test that the client can be used to get a response
+        response = azure_assistants_client.get_response(
+            messages=messages,
+            options={"tools": [get_weather], "tool_choice": "auto"},
+            stream=True,
+        )
+        full_message: str = ""
+        async for chunk in response:
+            assert chunk is not None
+            assert isinstance(chunk, ChatResponseUpdate)
+            for content in chunk.contents:
+                if content.type == "text" and content.text:
+                    full_message += content.text
+
+        assert any(word in full_message.lower() for word in ["sunny", "25", "weather"])
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_with_existing_assistant() -> None:
+    """Test Azure Assistants Client with existing assistant ID."""
+    # First create an assistant to use in the test
+    async with AzureOpenAIAssistantsClient(credential=AzureCliCredential()) as temp_client:
+        # Get the assistant ID by triggering assistant creation
+        messages = [Message(role="user", text="Hello")]
+        await temp_client.get_response(messages=messages)
+        assistant_id = temp_client.assistant_id
+
+        # Now test using the existing assistant
+        async with AzureOpenAIAssistantsClient(
+            assistant_id=assistant_id, credential=AzureCliCredential()
+        ) as azure_assistants_client:
+            assert isinstance(azure_assistants_client, SupportsChatGetResponse)
+            assert azure_assistants_client.assistant_id == assistant_id
+
+            messages = [Message(role="user", text="What can you do?")]
+
+            # Test that the client can be used to get a response
+            response = await azure_assistants_client.get_response(messages=messages)
+
+            assert response is not None
+            assert isinstance(response, ChatResponse)
+            assert len(response.text) > 0
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_agent_basic_run():
+    """Test Agent basic run functionality with AzureOpenAIAssistantsClient."""
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+    ) as agent:
+        # Run a simple query
+        response = await agent.run("Hello! Please respond with 'Hello World' exactly.")
+
+        # Validate response
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        assert len(response.text) > 0
+        assert "Hello World" in response.text
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_agent_basic_run_streaming():
+    """Test Agent basic streaming functionality with AzureOpenAIAssistantsClient."""
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+    ) as agent:
+        # Run streaming query
+        full_message: str = ""
+        async for chunk in agent.run("Please respond with exactly: 'This is a streaming response test.'", stream=True):
+            assert chunk is not None
+            assert isinstance(chunk, AgentResponseUpdate)
+            if chunk.text:
+                full_message += chunk.text
+
+        # Validate streaming response
+        assert len(full_message) > 0
+        assert "streaming response test" in full_message.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_agent_session_persistence():
+    """Test Agent session persistence across runs with AzureOpenAIAssistantsClient."""
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant with good memory.",
+    ) as agent:
+        # Create a new session that will be reused
+        session = agent.create_session()
+
+        # First message - establish context
+        first_response = await agent.run(
+            "Remember this number: 42. What number did I just tell you to remember?", session=session
+        )
+        assert isinstance(first_response, AgentResponse)
+        assert "42" in first_response.text
+
+        # Second message - test conversation memory
+        second_response = await agent.run(
+            "What number did I tell you to remember in my previous message?", session=session
+        )
+        assert isinstance(second_response, AgentResponse)
+        assert "42" in second_response.text
+
+        # Verify session has been populated with conversation ID
+        assert session.service_session_id is not None
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_agent_existing_session_id():
+    """Test Agent with existing session ID to continue conversations across agent instances."""
+    # First, create a conversation and capture the session ID
+    existing_session_id = None
+
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+        instructions="You are a helpful weather agent.",
+        tools=[get_weather],
+    ) as agent:
+        # Start a conversation and get the session ID
+        session = agent.create_session()
+        response1 = await agent.run("What's the weather in Paris?", session=session)
+
+        # Validate first response
+        assert isinstance(response1, AgentResponse)
+        assert response1.text is not None
+        assert any(word in response1.text.lower() for word in ["weather", "paris"])
+
+        # The session ID is set after the first response
+        existing_session_id = session.service_session_id
+        assert existing_session_id is not None
+
+    # Now continue with the same session ID in a new agent instance
+
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(thread_id=existing_session_id, credential=AzureCliCredential()),
+        instructions="You are a helpful weather agent.",
+        tools=[get_weather],
+    ) as agent:
+        # Create a session with the existing ID
+        session = AgentSession(service_session_id=existing_session_id)
+
+        # Ask about the previous conversation
+        response2 = await agent.run("What was the last city I asked about?", session=session)
+
+        # Validate that the agent remembers the previous conversation
+        assert isinstance(response2, AgentResponse)
+        assert response2.text is not None
+        # Should reference Paris from the previous conversation
+        assert "paris" in response2.text.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_agent_code_interpreter():
+    """Test Agent with code interpreter through AzureOpenAIAssistantsClient."""
+
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant that can write and execute Python code.",
+        tools=[AzureOpenAIAssistantsClient.get_code_interpreter_tool()],
+    ) as agent:
+        # Request code execution
+        response = await agent.run("Write Python code to calculate the factorial of 5 and show the result.")
+
+        # Validate response
+        assert isinstance(response, AgentResponse)
+        assert response.text is not None
+        # Factorial of 5 is 120
+        assert "120" in response.text or "factorial" in response.text.lower()
+
+
+@pytest.mark.flaky
+@pytest.mark.integration
+@skip_if_azure_integration_tests_disabled
+async def test_azure_assistants_client_agent_level_tool_persistence():
+    """Test that agent-level tools persist across multiple runs with Azure Assistants Client."""
+
+    async with Agent(
+        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+        instructions="You are a helpful assistant that uses available tools.",
+        tools=[get_weather],  # Agent-level tool
+    ) as agent:
+        # First run - agent-level tool should be available
+        first_response = await agent.run("What's the weather like in Chicago?")
+
+        assert isinstance(first_response, AgentResponse)
+        assert first_response.text is not None
+        # Should use the agent-level weather tool
+        assert any(term in first_response.text.lower() for term in ["chicago", "sunny", "72"])
+
+        # Second run - agent-level tool should still be available (persistence test)
+        second_response = await agent.run("What's the weather in Miami?")
+
+        assert isinstance(second_response, AgentResponse)
+        assert second_response.text is not None
+        # Should use the agent-level weather tool again
+        assert any(term in second_response.text.lower() for term in ["miami", "sunny", "72"])
+
+
 def test_azure_assistants_client_entra_id_authentication() -> None:
    """Test credential authentication path with sync credential."""
    mock_credential = MagicMock()
    mock_provider = MagicMock(return_value="token-string")

    with (
-        patch("agent_framework_azure_ai._deprecated_azure_openai.load_settings") as mock_load_settings,
+        patch("agent_framework.azure._assistants_client.load_settings") as mock_load_settings,
        patch(
-            "agent_framework_azure_ai._deprecated_azure_openai.resolve_credential_to_token_provider",
+            "agent_framework.azure._assistants_client.resolve_credential_to_token_provider",
            return_value=mock_provider,
        ) as mock_resolve,
-        patch("agent_framework_azure_ai._deprecated_azure_openai.AsyncAzureOpenAI") as mock_azure_client,
+        patch("agent_framework.azure._assistants_client.AsyncAzureOpenAI") as mock_azure_client,
        patch("agent_framework.openai.OpenAIAssistantsClient.__init__", return_value=None),
    ):
        mock_load_settings.return_value = {
@@ -286,7 +602,7 @@ def test_azure_assistants_client_entra_id_authentication() -> None:

 def test_azure_assistants_client_no_authentication_error() -> None:
    """Test authentication validation error when no auth provided."""
-    with patch("agent_framework_azure_ai._deprecated_azure_openai.load_settings") as mock_load_settings:
+    with patch("agent_framework.azure._assistants_client.load_settings") as mock_load_settings:
        mock_load_settings.return_value = {
            "chat_deployment_name": "test-deployment",
            "responses_deployment_name": None,
@@ -311,12 +627,12 @@ def test_azure_assistants_client_callable_credential() -> None:
    mock_provider = MagicMock(return_value="my-token")

    with (
-        patch("agent_framework_azure_ai._deprecated_azure_openai.load_settings") as mock_load_settings,
+        patch("agent_framework.azure._assistants_client.load_settings") as mock_load_settings,
        patch(
-            "agent_framework_azure_ai._deprecated_azure_openai.resolve_credential_to_token_provider",
+            "agent_framework.azure._assistants_client.resolve_credential_to_token_provider",
            return_value=mock_provider,
        ),
-        patch("agent_framework_azure_ai._deprecated_azure_openai.AsyncAzureOpenAI") as mock_azure_client,
+        patch("agent_framework.azure._assistants_client.AsyncAzureOpenAI") as mock_azure_client,
        patch("agent_framework.openai.OpenAIAssistantsClient.__init__", return_value=None),
    ):
        mock_load_settings.return_value = {
@@ -348,8 +664,8 @@ def test_azure_assistants_client_callable_credential() -> None:
 def test_azure_assistants_client_base_url_configuration() -> None:
    """Test base_url client parameter path."""
    with (
-        patch("agent_framework_azure_ai._deprecated_azure_openai.load_settings") as mock_load_settings,
-        patch("agent_framework_azure_ai._deprecated_azure_openai.AsyncAzureOpenAI") as mock_azure_client,
+        patch("agent_framework.azure._assistants_client.load_settings") as mock_load_settings,
+        patch("agent_framework.azure._assistants_client.AsyncAzureOpenAI") as mock_azure_client,
        patch("agent_framework.openai.OpenAIAssistantsClient.__init__", return_value=None),
    ):
        mock_load_settings.return_value = {
@@ -379,8 +695,8 @@ def test_azure_assistants_client_base_url_configuration() -> None:
 def test_azure_assistants_client_azure_endpoint_configuration() -> None:
    """Test azure_endpoint client parameter path."""
    with (
-        patch("agent_framework_azure_ai._deprecated_azure_openai.load_settings") as mock_load_settings,
-        patch("agent_framework_azure_ai._deprecated_azure_openai.AsyncAzureOpenAI") as mock_azure_client,
+        patch("agent_framework.azure._assistants_client.load_settings") as mock_load_settings,
+        patch("agent_framework.azure._assistants_client.AsyncAzureOpenAI") as mock_azure_client,
        patch("agent_framework.openai.OpenAIAssistantsClient.__init__", return_value=None),
    ):
        mock_load_settings.return_value = {
@@ -6,6 +6,16 @@ from unittest.mock import AsyncMock, MagicMock, patch

 import openai
 import pytest
+from azure.identity import AzureCliCredential
+from httpx import Request, Response
+from openai import AsyncAzureOpenAI, AsyncStream
+from openai.resources.chat.completions import AsyncCompletions as AsyncChatCompletions
+from openai.types.chat import ChatCompletion, ChatCompletionChunk
+from openai.types.chat.chat_completion import Choice
+from openai.types.chat.chat_completion_chunk import Choice as ChunkChoice
+from openai.types.chat.chat_completion_chunk import ChoiceDelta as ChunkChoiceDelta
+from openai.types.chat.chat_completion_message import ChatCompletionMessage
+
 from agent_framework import (
    Agent,
    AgentResponse,
@@ -19,19 +29,10 @@ from agent_framework import (
 from agent_framework._telemetry import USER_AGENT_KEY
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.exceptions import ChatClientException
-from agent_framework_openai import (
+from agent_framework.openai import (
    ContentFilterResultSeverity,
    OpenAIContentFilterException,
 )
-from azure.identity import AzureCliCredential
-from httpx import Request, Response
-from openai import AsyncAzureOpenAI, AsyncStream
-from openai.resources.chat.completions import AsyncCompletions as AsyncChatCompletions
-from openai.types.chat import ChatCompletion, ChatCompletionChunk
-from openai.types.chat.chat_completion import Choice
-from openai.types.chat.chat_completion_chunk import Choice as ChunkChoice
-from openai.types.chat.chat_completion_chunk import ChoiceDelta as ChunkChoiceDelta
-from openai.types.chat.chat_completion_message import ChatCompletionMessage

 # region Service Setup

@@ -47,7 +48,7 @@ def test_init(azure_openai_unit_test_env: dict[str, str]) -> None:

    assert azure_chat_client.client is not None
    assert isinstance(azure_chat_client.client, AsyncAzureOpenAI)
-    assert azure_chat_client.model == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
+    assert azure_chat_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
    assert isinstance(azure_chat_client, SupportsChatGetResponse)


@@ -70,7 +71,7 @@ def test_init_base_url(azure_openai_unit_test_env: dict[str, str]) -> None:

    assert azure_chat_client.client is not None
    assert isinstance(azure_chat_client.client, AsyncAzureOpenAI)
-    assert azure_chat_client.model == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
+    assert azure_chat_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
    assert isinstance(azure_chat_client, SupportsChatGetResponse)
    for key, value in default_headers.items():
        assert key in azure_chat_client.client.default_headers
@@ -83,7 +84,7 @@ def test_init_endpoint(azure_openai_unit_test_env: dict[str, str]) -> None:

    assert azure_chat_client.client is not None
    assert isinstance(azure_chat_client.client, AsyncAzureOpenAI)
-    assert azure_chat_client.model == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
+    assert azure_chat_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"]
    assert isinstance(azure_chat_client, SupportsChatGetResponse)


@@ -130,7 +131,7 @@ def test_serialize(azure_openai_unit_test_env: dict[str, str]) -> None:

    azure_chat_client = AzureOpenAIChatClient.from_dict(settings)
    dumped_settings = azure_chat_client.to_dict()
-    assert dumped_settings["model"] == settings["deployment_name"]
+    assert dumped_settings["model_id"] == settings["deployment_name"]
    assert str(settings["endpoint"]) in str(dumped_settings["endpoint"])
    assert str(settings["deployment_name"]) == str(dumped_settings["deployment_name"])
    assert settings["api_version"] == dumped_settings["api_version"]
@@ -6,12 +6,13 @@ import os
 from unittest.mock import AsyncMock, MagicMock

 import pytest
-from agent_framework.azure import AzureOpenAIEmbeddingClient
-from agent_framework_openai import OpenAIEmbeddingOptions
 from openai.types import CreateEmbeddingResponse
 from openai.types import Embedding as OpenAIEmbedding
 from openai.types.create_embedding_response import Usage

+from agent_framework.azure import AzureOpenAIEmbeddingClient
+from agent_framework.openai import OpenAIEmbeddingOptions
+

 def _make_openai_response(
    embeddings: list[list[float]],
@@ -48,7 +49,7 @@ def test_azure_construction_with_deployment_name(azure_embedding_unit_test_env:
        api_key="test-key",
        endpoint="https://test.openai.azure.com/",
    )
-    assert client.model == "text-embedding-3-small"
+    assert client.model_id == "text-embedding-3-small"


 def test_azure_construction_with_existing_client(azure_embedding_unit_test_env: None) -> None:
@@ -57,7 +58,7 @@ def test_azure_construction_with_existing_client(azure_embedding_unit_test_env:
        deployment_name="my-deployment",
        async_client=mock_client,
    )
-    assert client.model == "my-deployment"
+    assert client.model_id == "my-deployment"
    assert client.client is mock_client


@@ -8,6 +8,10 @@ from typing import Annotated, Any
 from unittest.mock import MagicMock

 import pytest
+from azure.identity import AzureCliCredential
+from pydantic import BaseModel
+from pytest import param
+
 from agent_framework import (
    Agent,
    AgentResponse,
@@ -18,9 +22,6 @@ from agent_framework import (
    tool,
 )
 from agent_framework.azure import AzureOpenAIResponsesClient
-from azure.identity import AzureCliCredential
-from pydantic import BaseModel
-from pytest import param

 skip_if_azure_integration_tests_disabled = pytest.mark.skipif(
    os.getenv("AZURE_OPENAI_ENDPOINT", "") in ("", "https://test-endpoint.com"),
@@ -74,7 +75,7 @@ def test_init(azure_openai_unit_test_env: dict[str, str]) -> None:
    # Test successful initialization
    azure_responses_client = AzureOpenAIResponsesClient(credential=AzureCliCredential())

-    assert azure_responses_client.model == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]
+    assert azure_responses_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]
    assert isinstance(azure_responses_client, SupportsChatGetResponse)


@@ -89,7 +90,7 @@ def test_init_model_id_constructor(azure_openai_unit_test_env: dict[str, str]) -
    model_id = "test_model_id"
    azure_responses_client = AzureOpenAIResponsesClient(deployment_name=model_id)

-    assert azure_responses_client.model == model_id
+    assert azure_responses_client.model_id == model_id
    assert isinstance(azure_responses_client, SupportsChatGetResponse)


@@ -97,7 +98,7 @@ def test_init_model_id_kwarg(azure_openai_unit_test_env: dict[str, str]) -> None
    """Test that model_id kwarg correctly sets the deployment name (issue #4299)."""
    azure_responses_client = AzureOpenAIResponsesClient(model_id="gpt-4o")

-    assert azure_responses_client.model == "gpt-4o"
+    assert azure_responses_client.model_id == "gpt-4o"
    assert isinstance(azure_responses_client, SupportsChatGetResponse)


@@ -107,7 +108,7 @@ def test_init_model_id_kwarg_does_not_override_deployment_name(
    """Test that deployment_name takes precedence over model_id kwarg (issue #4299)."""
    azure_responses_client = AzureOpenAIResponsesClient(deployment_name="my-deployment", model_id="gpt-4o")

-    assert azure_responses_client.model == "my-deployment"
+    assert azure_responses_client.model_id == "my-deployment"
    assert isinstance(azure_responses_client, SupportsChatGetResponse)


@@ -115,7 +116,7 @@ def test_init_model_id_kwarg_none(azure_openai_unit_test_env: dict[str, str]) ->
    """Test that model_id=None does not override the env-var deployment name."""
    azure_responses_client = AzureOpenAIResponsesClient(model_id=None)

-    assert azure_responses_client.model == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]
+    assert azure_responses_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]


 def test_init_with_default_header(azure_openai_unit_test_env: dict[str, str]) -> None:
@@ -126,7 +127,7 @@ def test_init_with_default_header(azure_openai_unit_test_env: dict[str, str]) ->
        default_headers=default_headers,
    )

-    assert azure_responses_client.model == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]
+    assert azure_responses_client.model_id == azure_openai_unit_test_env["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"]
    assert isinstance(azure_responses_client, SupportsChatGetResponse)

    # Assert that the default header we added is present in the client's default headers
@@ -155,7 +156,7 @@ def test_init_with_project_client(azure_openai_unit_test_env: dict[str, str]) ->
    mock_project_client.get_openai_client.return_value = mock_openai_client

    with patch(
-        "agent_framework_azure_ai._deprecated_azure_openai.AzureOpenAIResponsesClient._create_client_from_project",
+        "agent_framework.azure._responses_client.AzureOpenAIResponsesClient._create_client_from_project",
        return_value=mock_openai_client,
    ):
        azure_responses_client = AzureOpenAIResponsesClient(
@@ -163,7 +164,7 @@ def test_init_with_project_client(azure_openai_unit_test_env: dict[str, str]) ->
            deployment_name="gpt-4o",
        )

-    assert azure_responses_client.model == "gpt-4o"
+    assert azure_responses_client.model_id == "gpt-4o"
    assert azure_responses_client.client is mock_openai_client
    assert isinstance(azure_responses_client, SupportsChatGetResponse)

@@ -178,7 +179,7 @@ def test_init_with_project_endpoint(azure_openai_unit_test_env: dict[str, str])
    mock_openai_client.default_headers = {}

    with patch(
-        "agent_framework_azure_ai._deprecated_azure_openai.AzureOpenAIResponsesClient._create_client_from_project",
+        "agent_framework.azure._responses_client.AzureOpenAIResponsesClient._create_client_from_project",
        return_value=mock_openai_client,
    ):
        azure_responses_client = AzureOpenAIResponsesClient(
@@ -187,7 +188,7 @@ def test_init_with_project_endpoint(azure_openai_unit_test_env: dict[str, str])
            credential=AzureCliCredential(),
        )

-    assert azure_responses_client.model == "gpt-4o"
+    assert azure_responses_client.model_id == "gpt-4o"
    assert azure_responses_client.client is mock_openai_client
    assert isinstance(azure_responses_client, SupportsChatGetResponse)

@@ -219,7 +220,7 @@ def test_create_client_from_project_with_endpoint() -> None:
    mock_openai_client = MagicMock(spec=AsyncOpenAI)
    mock_credential = MagicMock()

-    with patch("agent_framework_azure_ai._deprecated_azure_openai.AIProjectClient") as MockAIProjectClient:
+    with patch("agent_framework.azure._responses_client.AIProjectClient") as MockAIProjectClient:
        mock_instance = MockAIProjectClient.return_value
        mock_instance.get_openai_client.return_value = mock_openai_client

@@ -667,8 +668,8 @@ async def test_azure_openai_responses_client_tool_rich_content_image() -> None:

 skip_if_azure_ai_integration_tests_disabled = pytest.mark.skipif(
    os.getenv("AZURE_AI_PROJECT_ENDPOINT", "") in ("", "https://test-project.cognitiveservices.azure.com/")
-    or os.getenv("AZURE_AI_MODEL", "") == "",
-    reason="No real AZURE_AI_PROJECT_ENDPOINT or AZURE_AI_MODEL provided; skipping integration tests.",
+    or os.getenv("AZURE_AI_MODEL_DEPLOYMENT_NAME", "") == "",
+    reason="No real AZURE_AI_PROJECT_ENDPOINT or AZURE_AI_MODEL_DEPLOYMENT_NAME provided; skipping integration tests.",
 )


@@ -694,7 +695,7 @@ async def test_integration_function_call_roundtrip_preserves_fidelity():

    client = AzureOpenAIResponsesClient(
        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-        deployment_name=os.environ["AZURE_AI_MODEL"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
        credential=AzureCliCredential(),
    )

@@ -3,13 +3,13 @@
 from unittest.mock import MagicMock, patch

 import pytest
-from agent_framework.exceptions import ChatClientInvalidAuthException
 from azure.core.credentials import TokenCredential
 from azure.core.credentials_async import AsyncTokenCredential

-from agent_framework_azure_ai._entra_id_authentication import (
+from agent_framework.azure._entra_id_authentication import (
    resolve_credential_to_token_provider,
 )
+from agent_framework.exceptions import ChatClientInvalidAuthException

 TOKEN_ENDPOINT = "https://cognitiveservices.azure.com/.default"

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Tao ChenandGitHub	4c0f0ec99a	Merge branch 'main' into taochen/python-update-sample-validation-scripts	2026-03-24 18:16:22 -07:00
Tao Chen	6185ba2125	force node22	2026-03-24 17:10:25 -07:00
Tao Chen	dcc1eeac36	force node24	2026-03-24 17:06:41 -07:00
Tao Chen	3f2096595f	force node24	2026-03-24 16:58:18 -07:00
Tao Chen	45a9da5523	Comments	2026-03-24 16:51:44 -07:00
Tao Chen	6364c05efc	Add more env vars	2026-03-24 16:19:36 -07:00
Tao Chen	bbb871e4cd	Add timestamp	2026-03-24 12:47:55 -07:00
Tao Chen	7d7b8dd1a4	Create trend report	2026-03-24 11:33:20 -07:00
Tao Chen	2f51a5ca78	Add .env	2026-03-24 08:58:33 -07:00
Tao Chen	ad5749c92a	Split jobs	2026-03-23 17:16:19 -07:00
Tao Chen	ed6b290457	Add fix suggestion	2026-03-23 16:15:47 -07:00
Tao Chen	63039cb748	Update autogen-migration samples	2026-03-23 15:51:17 -07:00
Tao Chen	3e7c94699f	Adjust prompt	2026-03-23 15:17:45 -07:00
Tao Chen	6320443969	Update sample validation scripts	2026-03-23 14:40:37 -07:00